Merge drm/drm-next into drm-misc-next

Paul Cercueil needs some patches in -rc5 to apply new patches for ingenic
properly.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

2720 files changed, 34425 insertions, 15119 deletions

diff --git a/.clang-format b/.clang-format
index a0a96088c74f..badfc1ba440a 100644
--- a/.clang-format
+++ b/.clang-format
@@ -111,6 +111,7 @@ ForEachMacros:
   - 'css_for_each_descendant_pre'
   - 'device_for_each_child_node'
   - 'dma_fence_chain_for_each'
+  - 'do_for_each_ftrace_op'
   - 'drm_atomic_crtc_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane_state'
@@ -136,6 +137,7 @@ ForEachMacros:
   - 'for_each_active_dev_scope'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
+  - 'for_each_aggr_pgid'
   - 'for_each_available_child_of_node'
   - 'for_each_bio'
   - 'for_each_board_func_rsrc'
@@ -234,6 +236,7 @@ ForEachMacros:
   - 'for_each_node_state'
   - 'for_each_node_with_cpus'
   - 'for_each_node_with_property'
+  - 'for_each_nonreserved_multicast_dest_pgid'
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
   - 'for_each_of_cpu_node'
@@ -256,6 +259,7 @@ ForEachMacros:
   - 'for_each_pci_dev'
   - 'for_each_pci_msi_entry'
   - 'for_each_pcm_streams'
+  - 'for_each_physmem_range'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
   - 'for_each_present_cpu'
@@ -265,6 +269,8 @@ ForEachMacros:
   - 'for_each_process_thread'
   - 'for_each_property_of_node'
   - 'for_each_registered_fb'
+  - 'for_each_requested_gpio'
+  - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
@@ -278,12 +284,17 @@ ForEachMacros:
   - 'for_each_sg'
   - 'for_each_sg_dma_page'
   - 'for_each_sg_page'
+  - 'for_each_sgtable_dma_page'
+  - 'for_each_sgtable_dma_sg'
+  - 'for_each_sgtable_page'
+  - 'for_each_sgtable_sg'
   - 'for_each_sibling_event'
   - 'for_each_subelement'
   - 'for_each_subelement_extid'
   - 'for_each_subelement_id'
   - '__for_each_thread'
   - 'for_each_thread'
+  - 'for_each_unicast_dest_pgid'
   - 'for_each_wakeup_source'
   - 'for_each_zone'
   - 'for_each_zone_zonelist'
@@ -464,6 +475,7 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_src_buf'
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
+  - 'while_for_each_ftrace_op'
   - 'xa_for_each'
   - 'xa_for_each_marked'
   - 'xa_for_each_range'
diff --git a/.mailmap b/.mailmap
index 57fe0085b465..50096b96c85d 100644
--- a/.mailmap
+++ b/.mailmap
@@ -15,30 +15,31 @@
 Aaron Durbin <adurbin@google.com>
 Adam Oldham <oldhamca@gmail.com>
 Adam Radford <aradford@gmail.com>
-Adrian Bunk <bunk@stusta.de>
 Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com>
+Adrian Bunk <bunk@stusta.de>
 Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
-Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
-Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
-Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
+Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru>
 Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com>
 Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru>
 Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
-Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
+Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
+Andi Kleen <ak@linux.intel.com> <ak@suse.de>
 Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
 Andreas Herrmann <aherrman@de.ibm.com>
-Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
-Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
+Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
+Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andy Adamson <andros@citi.umich.edu>
 Antoine Tenart <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
@@ -48,40 +49,42 @@ Arnaud Patard <arnaud.patard@rtp-net.org>
 Arnd Bergmann <arnd@arndb.de>
 Axel Dyks <xl@xlsigned.net>
 Axel Lin <axel.lin@gmail.com>
-Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
 Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>
+Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
 Ben Gardner <bgardner@wabtec.com>
 Ben M Cahill <ben.m.cahill@intel.com>
 Björn Steinbrink <B.Steinbrink@gmx.de>
-Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
-Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
 Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com>
 Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com>
+Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
+Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
 Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
-Christoph Hellwig <hch@lst.de>
 Christophe Ricard <christophe.ricard@gmail.com>
+Christoph Hellwig <hch@lst.de>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
-Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
-Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
 Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
-Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
-Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
-Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com>
+Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
+Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
 <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
 Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
-Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
-Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>
@@ -92,20 +95,22 @@ Felix Kuhling <fxkuehl@gmx.de>
 Felix Moeller <felix@derklecks.de>
 Filipe Lautert <filipe@icewall.org>
 Franck Bui-Huu <vagabon.xyz@gmail.com>
-Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com>
+Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
 Frank Zago <fzago@systemfabricworks.com>
 Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
-Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
+Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Gustavo Padovan <gustavo@las.ic.unicamp.br>
+Gustavo Padovan <padovan@profusion.mobi>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
 Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com>
 Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com>
@@ -115,32 +120,33 @@ Henrik Rydberg <rydberg@bitmath.org>
 Herbert Xu <herbert@gondor.apana.org.au>
 Jacob Shin <Jacob.Shin@amd.com>
 Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com>
-Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com>
 Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com>
+Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com>
 Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
 James Bottomley <jejb@mulgrave.(none)>
 James Bottomley <jejb@titanic.il.steeleye.com>
 James E Wilson <wilson@specifix.com>
-James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 James Hogan <jhogan@kernel.org> <james@albanarts.com>
+James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 James Ketrenos <jketreno@io.(none)>
 Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
+Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
-Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
+Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
 Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
 Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
 Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
-Jean Tourrilhes <jt@hpl.hp.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
+Jean Tourrilhes <jt@hpl.hp.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
-Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
 Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
 Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
+Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com>
@@ -164,30 +170,31 @@ Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
 Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com>
 Kay Sievers <kay.sievers@vrfy.org>
 Kenneth W Chen <kenneth.w.chen@intel.com>
-Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
+Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
-Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
 Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
+Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
-Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
-Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
+Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
+Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
+Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
 Linas Vepstas <linas@austin.ibm.com>
-Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
-Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
+Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
+Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
-Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
+Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
 Mark Brown <broonie@sirena.org.uk>
 Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com>
-Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Mathieu Othacehe <m.othacehe@gmail.com>
 Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com>
 Matthew Wilcox <willy@infradead.org> <matthew@wil.cx>
@@ -197,17 +204,17 @@ Matthew Wilcox <willy@infradead.org> <willy@debian.org>
 Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com>
 Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org>
 Matthieu CASTET <castet.matthieu@free.fr>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
+Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
+Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
+Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
+Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
 Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
 Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@infradead.org>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com>
 Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com>
 Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com>
 Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com>
-Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
-Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
-Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
-Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
 Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com>
 Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com>
 Mayuresh Janorkar <mayur@ti.com>
@@ -239,13 +246,13 @@ Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
 Patrick Mochel <mochel@digitalimplant.org>
 Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com>
 Paul Burton <paulburton@kernel.org> <paul.burton@mips.com>
+Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.ibm.com>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.vnet.ibm.com>
-Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@us.ibm.com>
 Peter A Jonsson <pj@ludd.ltu.se>
-Peter Oruba <peter@oruba.de>
 Peter Oruba <peter.oruba@amd.com>
+Peter Oruba <peter@oruba.de>
 Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
 Praveen BP <praveenbp@ti.com>
 Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
@@ -258,23 +265,23 @@ Ralf Baechle <ralf@linux-mips.org>
 Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
 Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net>
 Rémi Denis-Courmont <rdenis@simphalempin.com>
-Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
 Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
+Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
 Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
 Sachin P Sant <ssant@in.ibm.com>
-Sarangdhar Joshi <spjoshi@codeaurora.org>
+Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
 Sam Ravnborg <sam@mars.ravnborg.org>
-Santosh Shilimkar <ssantosh@kernel.org>
 Santosh Shilimkar <santosh.shilimkar@oracle.org>
+Santosh Shilimkar <ssantosh@kernel.org>
+Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sascha Hauer <s.hauer@pengutronix.de>
 S.Çağlar Onur <caglar@pardus.org.tr>
-Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
 Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
-Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
+Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
 Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
 Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
@@ -285,19 +292,23 @@ Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com>
+Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com>
 Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
 Subhash Jadavani <subhashj@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
+Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
 Thomas Pedersen <twp@codeaurora.org>
 Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
 Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org>
 Tony Luck <tony.luck@intel.com>
-TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
+TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
@@ -305,22 +316,16 @@ Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com>
 Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
-Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
-Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
-Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com>
 Will Deacon <will@kernel.org> <will.deacon@arm.com>
-Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de>
+Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
-Gustavo Padovan <gustavo@las.ic.unicamp.br>
-Gustavo Padovan <padovan@profusion.mobi>
-Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
-Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
-Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com>
-Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com>
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index f7e32f218f73..e82fc37be802 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -43,7 +43,7 @@ Description:	read only
 		This sysfs interface exposes the number of cores per chip
 		present in the system.
 
-What:		/sys/devices/hv_24x7/interface/cpumask
+What:		/sys/devices/hv_24x7/cpumask
 Date:		July 2020
 Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:	read only
diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst
index f1fc8ae3846a..cc860a0c296b 100644
--- a/Documentation/RCU/lockdep.rst
+++ b/Documentation/RCU/lockdep.rst
@@ -49,7 +49,7 @@ checking of rcu_dereference() primitives:
 		is invoked by both RCU-sched readers and updaters.
 	srcu_dereference_check(p, c):
 		Use explicit check expression "c" along with
-		srcu_read_lock_held()().  This is useful in code that
+		srcu_read_lock_held().  This is useful in code that
 		is invoked by both SRCU readers and updaters.
 	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt
index d336f3f73a4c..63fd4e6a014b 100644
--- a/Documentation/admin-guide/devices.txt
+++ b/Documentation/admin-guide/devices.txt
@@ -1662,7 +1662,7 @@
 
   98 block	User-mode virtual block device
 		  0 = /dev/ubda		First user-mode block device
-		 16 = /dev/udbb		Second user-mode block device
+		 16 = /dev/ubdb		Second user-mode block device
 		    ...
 
 		Partitions are handled in the same way as for IDE
diff --git a/Documentation/admin-guide/dynamic-debug-howto.rst b/Documentation/admin-guide/dynamic-debug-howto.rst
index e5a8def45f3f..6c04aea8f4cd 100644
--- a/Documentation/admin-guide/dynamic-debug-howto.rst
+++ b/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -156,7 +156,6 @@ against.  Possible keywords are:::
   ``line-range`` cannot contain space, e.g.
   "1-30" is valid range but "1 - 30" is not.
 
-  ``module=foo`` combined keyword=value form is interchangably accepted
 
 The meanings of each keyword are:
 
diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst
index a683976fad6d..d2795ca6821e 100644
--- a/Documentation/admin-guide/ext4.rst
+++ b/Documentation/admin-guide/ext4.rst
@@ -489,6 +489,9 @@ Files in /sys/fs/ext4/<devname>:
         multiple of this tuning parameter if the stripe size is not set in the
         ext4 superblock
 
+  mb_max_inode_prealloc
+        The maximum length of per-inode ext4_prealloc_space list.
+
   mb_max_to_scan
         The maximum number of extents the multiblock allocator will search to
         find the best extent.
@@ -529,21 +532,21 @@ Files in /sys/fs/ext4/<devname>:
 Ioctls
 ======
 
-There is some Ext4 specific functionality which can be accessed by applications
-through the system call interfaces. The list of all Ext4 specific ioctls are
-shown in the table below.
+Ext4 implements various ioctls which can be used by applications to access
+ext4-specific functionality. An incomplete list of these ioctls is shown in the
+table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as
+well as ioctls that may have been ext4-specific originally but are now supported
+by some other filesystem(s) too (``FS_IOC_*``).
 
-Table of Ext4 specific ioctls
+Table of Ext4 ioctls
 
-  EXT4_IOC_GETFLAGS
+  FS_IOC_GETFLAGS
         Get additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_GETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
-  EXT4_IOC_SETFLAGS
+  FS_IOC_SETFLAGS
         Set additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_SETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
   EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD
         Get the inode i_generation number stored for each inode. The
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bdc1f33fd3d1..a1068742a6df 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1233,8 +1233,7 @@
 	efi=		[EFI]
 			Format: { "debug", "disable_early_pci_dma",
 				  "nochunk", "noruntime", "nosoftreserve",
-				  "novamap", "no_disable_early_pci_dma",
-				  "old_map" }
+				  "novamap", "no_disable_early_pci_dma" }
 			debug: enable misc debug output.
 			disable_early_pci_dma: disable the busmaster bit on all
 			PCI bridges while in the EFI boot stub.
@@ -1251,8 +1250,6 @@
 			novamap: do not call SetVirtualAddressMap().
 			no_disable_early_pci_dma: Leave the busmaster bit set
 			on all PCI bridges while in the EFI boot stub
-			old_map [X86-64]: switch to the old ioremap-based EFI
-			runtime services mapping. [Needs CONFIG_X86_UV=y]
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
index 5e477869df18..5fe1ade88c17 100644
--- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst
+++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
@@ -1434,7 +1434,7 @@ on the feature, restricting the viewing angles.
 
 
 DYTC Lapmode sensor
-------------------
+-------------------
 
 sysfs: dytc_lapmode
 
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index 7adef969ffee..5072e7064d13 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -123,7 +123,9 @@ Energy-Performance Bias (EPB) knob (otherwise), which means that the processor's
 internal P-state selection logic is expected to focus entirely on performance.
 
 This will override the EPP/EPB setting coming from the ``sysfs`` interface
-(see `Energy vs Performance Hints`_ below).
+(see `Energy vs Performance Hints`_ below).  Moreover, any attempts to change
+the EPP/EPB to a value different from 0 ("performance") via ``sysfs`` in this
+configuration will be rejected.
 
 Also, in this configuration the range of P-states available to the processor's
 internal P-state selection logic is always restricted to the upper boundary
@@ -564,8 +566,8 @@ Energy-Performance Preference (EPP) knob (if supported) or its
 Energy-Performance Bias (EPB) knob. It is also possible to write a positive
 integer value between 0 to 255, if the EPP feature is present. If the EPP
 feature is not present, writing integer value to this attribute is not
-supported. In this case, user can use
- "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
+supported. In this case, user can use the
+"/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
 
 [Note that tasks may by migrated from one CPU to another by the scheduler's
 load-balancing algorithm and if different energy vs performance hints are
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index d46429be334e..7df2465fd108 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -36,6 +36,12 @@ Two sets of Questions and Answers (Q&A) are maintained.
    bpf_devel_QA
 
 
+Helper functions
+================
+
+* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs.
+
+
 Program types
 =============
 
@@ -79,4 +85,5 @@ Other
 .. _networking-filter: ../networking/filter.rst
 .. _man-pages: https://www.kernel.org/doc/man-pages/
 .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html
+.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html
 .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/
diff --git a/Documentation/devicetree/bindings/clock/imx23-clock.yaml b/Documentation/devicetree/bindings/clock/imx23-clock.yaml
index 66cb238a1040..ad21899981af 100644
--- a/Documentation/devicetree/bindings/clock/imx23-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx23-clock.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Clock bindings for Freescale i.MX23
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/clock/imx28-clock.yaml b/Documentation/devicetree/bindings/clock/imx28-clock.yaml
index 72328d5ca09a..f1af1108129e 100644
--- a/Documentation/devicetree/bindings/clock/imx28-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx28-clock.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Clock bindings for Freescale i.MX28
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
index ccf5b50e798b..dfa1133f8c5e 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
+++ b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale MXS GPIO controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <Anson.Huang@nxp.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
index d3134ed775fa..21ae7bce038e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale MXS Inter IC (I2C) Controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
deleted file mode 100644
index 7841cb099e13..000000000000
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Texas Instruments K3 Interrupt Aggregator
-=========================================
-
-The Interrupt Aggregator (INTA) provides a centralized machine
-which handles the termination of system events to that they can
-be coherently processed by the host(s) in the system. A maximum
-of 64 events can be mapped to a single interrupt.
-
-
-                              Interrupt Aggregator
-                     +-----------------------------------------+
-                     |      Intmap            VINT             |
-                     | +--------------+  +------------+        |
-            m ------>| | vint  | bit  |  | 0 |.....|63| vint0  |
-               .     | +--------------+  +------------+        |       +------+
-               .     |         .               .               |       | HOST |
-Globalevents  ------>|         .               .               |------>| IRQ  |
-               .     |         .               .               |       | CTRL |
-               .     |         .               .               |       +------+
-            n ------>| +--------------+  +------------+        |
-                     | | vint  | bit  |  | 0 |.....|63| vintx  |
-                     | +--------------+  +------------+        |
-                     |                                         |
-                     +-----------------------------------------+
-
-Configuration of these Intmap registers that maps global events to vint is done
-by a system controller (like the Device Memory and Security Controller on K3
-AM654 SoC). Driver should request the system controller to get the range
-of global events and vints assigned to the requesting host. Management
-of these requested resources should be handled by driver and requests
-system controller to map specific global event to vint, bit pair.
-
-Communication between the host processor running an OS and the system
-controller happens through a protocol called TI System Control Interface
-(TISCI protocol). For more details refer:
-Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
-
-TISCI Interrupt Aggregator Node:
--------------------------------
-- compatible:		Must be "ti,sci-inta".
-- reg:			Should contain registers location and length.
-- interrupt-controller:	Identifies the node as an interrupt controller
-- msi-controller:	Identifies the node as an MSI controller.
-- interrupt-parent:	phandle of irq parent.
-- ti,sci:		Phandle to TI-SCI compatible System controller node.
-- ti,sci-dev-id:	TISCI device ID of the Interrupt Aggregator.
-- ti,sci-rm-range-vint:	Array of TISCI subtype ids representing vints(inta
-			outputs) range within this INTA, assigned to the
-			requesting host context.
-- ti,sci-rm-range-global-event:	Array of TISCI subtype ids representing the
-			global events range reaching this IA and are assigned
-			to the requesting host context.
-
-Example:
---------
-main_udmass_inta: interrupt-controller@33d00000 {
-	compatible = "ti,sci-inta";
-	reg = <0x0 0x33d00000 0x0 0x100000>;
-	interrupt-controller;
-	msi-controller;
-	interrupt-parent = <&main_navss_intr>;
-	ti,sci = <&dmsc>;
-	ti,sci-dev-id = <179>;
-	ti,sci-rm-range-vint = <0x0>;
-	ti,sci-rm-range-global-event = <0x1>;
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
new file mode 100644
index 000000000000..c7cd05656a3e
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
@@ -0,0 +1,98 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-inta.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments K3 Interrupt Aggregator
+
+maintainers:
+  - Lokesh Vutla <lokeshvutla@ti.com>
+
+allOf:
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
+
+description: |
+  The Interrupt Aggregator (INTA) provides a centralized machine
+  which handles the termination of system events to that they can
+  be coherently processed by the host(s) in the system. A maximum
+  of 64 events can be mapped to a single interrupt.
+
+                                Interrupt Aggregator
+                       +-----------------------------------------+
+                       |      Intmap            VINT             |
+                       | +--------------+  +------------+        |
+              m ------>| | vint  | bit  |  | 0 |.....|63| vint0  |
+                 .     | +--------------+  +------------+        |      +------+
+                 .     |         .               .               |      | HOST |
+  Globalevents  ------>|         .               .               |----->| IRQ  |
+                 .     |         .               .               |      | CTRL |
+                 .     |         .               .               |      +------+
+              n ------>| +--------------+  +------------+        |
+                       | | vint  | bit  |  | 0 |.....|63| vintx  |
+                       | +--------------+  +------------+        |
+                       |                                         |
+                       +-----------------------------------------+
+
+  Configuration of these Intmap registers that maps global events to vint is
+  done by a system controller (like the Device Memory and Security Controller
+  on AM654 SoC). Driver should request the system controller to get the range
+  of global events and vints assigned to the requesting host. Management
+  of these requested resources should be handled by driver and requests
+  system controller to map specific global event to vint, bit pair.
+
+  Communication between the host processor running an OS and the system
+  controller happens through a protocol called TI System Control Interface
+  (TISCI protocol).
+
+properties:
+  compatible:
+    const: ti,sci-inta
+
+  reg:
+    maxItems: 1
+
+  interrupt-controller: true
+
+  msi-controller: true
+
+  ti,interrupt-ranges:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    description: |
+      Interrupt ranges that converts the INTA output hw irq numbers
+      to parents's input interrupt numbers.
+    items:
+      items:
+        - description: |
+            "output_irq" specifies the base for inta output irq
+        - description: |
+            "parent's input irq" specifies the base for parent irq
+        - description: |
+            "limit" specifies the limit for translation
+
+required:
+  - compatible
+  - reg
+  - interrupt-controller
+  - msi-controller
+  - ti,sci
+  - ti,sci-dev-id
+  - ti,interrupt-ranges
+
+examples:
+  - |
+    bus {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        main_udmass_inta: msi-controller@33d00000 {
+            compatible = "ti,sci-inta";
+            reg = <0x0 0x33d00000 0x0 0x100000>;
+            interrupt-controller;
+            msi-controller;
+            interrupt-parent = <&main_navss_intr>;
+            ti,sci = <&dmsc>;
+            ti,sci-dev-id = <179>;
+            ti,interrupt-ranges = <0 0 256>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
deleted file mode 100644
index 178fca08278f..000000000000
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
+++ /dev/null
@@ -1,82 +0,0 @@
-Texas Instruments K3 Interrupt Router
-=====================================
-
-The Interrupt Router (INTR) module provides a mechanism to mux M
-interrupt inputs to N interrupt outputs, where all M inputs are selectable
-to be driven per N output. An Interrupt Router can either handle edge triggered
-or level triggered interrupts and that is fixed in hardware.
-
-                                 Interrupt Router
-                             +----------------------+
-                             |  Inputs     Outputs  |
-        +-------+            | +------+    +-----+  |
-        | GPIO  |----------->| | irq0 |    |  0  |  |       Host IRQ
-        +-------+            | +------+    +-----+  |      controller
-                             |    .           .     |      +-------+
-        +-------+            |    .           .     |----->|  IRQ  |
-        | INTA  |----------->|    .           .     |      +-------+
-        +-------+            |    .        +-----+  |
-                             | +------+    |  N  |  |
-                             | | irqM |    +-----+  |
-                             | +------+             |
-                             |                      |
-                             +----------------------+
-
-There is one register per output (MUXCNTL_N) that controls the selection.
-Configuration of these MUXCNTL_N registers is done by a system controller
-(like the Device Memory and Security Controller on K3 AM654 SoC). System
-controller will keep track of the used and unused registers within the Router.
-Driver should request the system controller to get the range of GIC IRQs
-assigned to the requesting hosts. It is the drivers responsibility to keep
-track of Host IRQs.
-
-Communication between the host processor running an OS and the system
-controller happens through a protocol called TI System Control Interface
-(TISCI protocol). For more details refer:
-Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
-
-TISCI Interrupt Router Node:
-----------------------------
-Required Properties:
-- compatible:		Must be "ti,sci-intr".
-- ti,intr-trigger-type:	Should be one of the following:
-			1: If intr supports edge triggered interrupts.
-			4: If intr supports level triggered interrupts.
-- interrupt-controller:	Identifies the node as an interrupt controller
-- #interrupt-cells:	Specifies the number of cells needed to encode an
-			interrupt source. The value should be 2.
-			First cell should contain the TISCI device ID of source
-			Second cell should contain the interrupt source offset
-			within the device.
-- ti,sci:		Phandle to TI-SCI compatible System controller node.
-- ti,sci-dst-id:	TISCI device ID of the destination IRQ controller.
-- ti,sci-rm-range-girq:	Array of TISCI subtype ids representing the host irqs
-			assigned to this interrupt router. Each subtype id
-			corresponds to a range of host irqs.
-
-For more details on TISCI IRQ resource management refer:
-https://downloads.ti.com/tisci/esd/latest/2_tisci_msgs/rm/rm_irq.html
-
-Example:
---------
-The following example demonstrates both interrupt router node and the consumer
-node(main gpio) on the AM654 SoC:
-
-main_intr: interrupt-controller0 {
-	compatible = "ti,sci-intr";
-	ti,intr-trigger-type = <1>;
-	interrupt-controller;
-	interrupt-parent = <&gic500>;
-	#interrupt-cells = <2>;
-	ti,sci = <&dmsc>;
-	ti,sci-dst-id = <56>;
-	ti,sci-rm-range-girq = <0x1>;
-};
-
-main_gpio0: gpio@600000 {
-	...
-	interrupt-parent = <&main_intr>;
-	interrupts = <57 256>, <57 257>, <57 258>,
-		     <57 259>, <57 260>, <57 261>;
-	...
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
new file mode 100644
index 000000000000..cff6a956afb4
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-intr.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments K3 Interrupt Router
+
+maintainers:
+  - Lokesh Vutla <lokeshvutla@ti.com>
+
+allOf:
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
+
+description: |
+  The Interrupt Router (INTR) module provides a mechanism to mux M
+  interrupt inputs to N interrupt outputs, where all M inputs are selectable
+  to be driven per N output. An Interrupt Router can either handle edge
+  triggered or level triggered interrupts and that is fixed in hardware.
+
+                                   Interrupt Router
+                               +----------------------+
+                               |  Inputs     Outputs  |
+          +-------+            | +------+    +-----+  |
+          | GPIO  |----------->| | irq0 |    |  0  |  |       Host IRQ
+          +-------+            | +------+    +-----+  |      controller
+                               |    .           .     |      +-------+
+          +-------+            |    .           .     |----->|  IRQ  |
+          | INTA  |----------->|    .           .     |      +-------+
+          +-------+            |    .        +-----+  |
+                               | +------+    |  N  |  |
+                               | | irqM |    +-----+  |
+                               | +------+             |
+                               |                      |
+                               +----------------------+
+
+  There is one register per output (MUXCNTL_N) that controls the selection.
+  Configuration of these MUXCNTL_N registers is done by a system controller
+  (like the Device Memory and Security Controller on K3 AM654 SoC). System
+  controller will keep track of the used and unused registers within the Router.
+  Driver should request the system controller to get the range of GIC IRQs
+  assigned to the requesting hosts. It is the drivers responsibility to keep
+  track of Host IRQs.
+
+  Communication between the host processor running an OS and the system
+  controller happens through a protocol called TI System Control Interface
+  (TISCI protocol).
+
+properties:
+  compatible:
+    const: ti,sci-intr
+
+  ti,intr-trigger-type:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [1, 4]
+    description: |
+      Should be one of the following.
+        1 = If intr supports edge triggered interrupts.
+        4 = If intr supports level triggered interrupts.
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 1
+    description: |
+      The 1st cell should contain interrupt router input hw number.
+
+  ti,interrupt-ranges:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    description: |
+      Interrupt ranges that converts the INTR output hw irq numbers
+      to parents's input interrupt numbers.
+    items:
+      items:
+        - description: |
+            "output_irq" specifies the base for intr output irq
+        - description: |
+            "parent's input irq" specifies the base for parent irq
+        - description: |
+            "limit" specifies the limit for translation
+
+required:
+  - compatible
+  - ti,intr-trigger-type
+  - interrupt-controller
+  - '#interrupt-cells'
+  - ti,sci
+  - ti,sci-dev-id
+  - ti,interrupt-ranges
+
+examples:
+  - |
+    main_gpio_intr: interrupt-controller0 {
+        compatible = "ti,sci-intr";
+        ti,intr-trigger-type = <1>;
+        interrupt-controller;
+        interrupt-parent = <&gic500>;
+        #interrupt-cells = <1>;
+        ti,sci = <&dmsc>;
+        ti,sci-dev-id = <131>;
+        ti,interrupt-ranges = <0 360 32>;
+    };
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
index 5887c917d480..58fe9d02a781 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
@@ -30,9 +30,13 @@ allOf:
     then:
       properties:
         clock-output-names:
-          items:
-            - const: clk_out_sd0
-            - const: clk_in_sd0
+          oneOf:
+            - items:
+              - const: clk_out_sd0
+              - const: clk_in_sd0
+            - items:
+              - const: clk_out_sd1
+              - const: clk_in_sd1
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
index 75dc1168d717..10b45966f1b8 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale Enhanced Secure Digital Host Controller (eSDHC) for i.MX
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 allOf:
   - $ref: "mmc-controller.yaml"
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index 0c9cf6a8808c..26a8f320a156 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -50,6 +50,8 @@ Optional properties:
 		     error caused by stop clock(fifo full)
 		     Valid range = [0:0x7]. if not present, default value is 0.
 		     applied to compatible "mediatek,mt2701-mmc".
+- resets: Phandle and reset specifier pair to softreset line of MSDC IP.
+- reset-names: Should be "hrst".
 
 Examples:
 mmc0: mmc@11230000 {
diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
index 1cccc0478d49..bec8f8c71ff2 100644
--- a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
+++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale MXS MMC controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller
diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
index 2cf3affa1be7..96c0b1440c9c 100644
--- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
@@ -15,8 +15,15 @@ Required properties:
   - "nvidia,tegra210-sdhci": for Tegra210
   - "nvidia,tegra186-sdhci": for Tegra186
   - "nvidia,tegra194-sdhci": for Tegra194
-- clocks : Must contain one entry, for the module clock.
-  See ../clocks/clock-bindings.txt for details.
+- clocks: For Tegra210, Tegra186 and Tegra194 must contain two entries.
+	  One for the module clock and one for the timeout clock.
+	  For all other Tegra devices, must contain a single entry for
+	  the module clock. See ../clocks/clock-bindings.txt for details.
+- clock-names: For Tegra210, Tegra186 and Tegra194 must contain the
+	       strings 'sdhci' and 'tmclk' to represent the module and
+	       the timeout clocks, respectively.
+	       For all other Tegra devices must contain the string 'sdhci'
+	       to represent the module clock.
 - resets : Must contain an entry for each entry in reset-names.
   See ../reset/reset.txt for details.
 - reset-names : Must include the following entries:
@@ -99,7 +106,7 @@ Optional properties for Tegra210, Tegra186 and Tegra194:
 
 Example:
 sdhci@700b0000 {
-	compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci";
+	compatible = "nvidia,tegra124-sdhci";
 	reg = <0x0 0x700b0000 0x0 0x200>;
 	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>;
@@ -115,3 +122,22 @@ sdhci@700b0000 {
 	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
 	status = "disabled";
 };
+
+sdhci@700b0000 {
+	compatible = "nvidia,tegra210-sdhci";
+	reg = <0x0 0x700b0000 0x0 0x200>;
+	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>,
+		 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+	clock-names = "sdhci", "tmclk";
+	resets = <&tegra_car 14>;
+	reset-names = "sdhci";
+	pinctrl-names = "sdmmc-3v3", "sdmmc-1v8";
+	pinctrl-0 = <&sdmmc1_3v3>;
+	pinctrl-1 = <&sdmmc1_1v8>;
+	nvidia,pad-autocal-pull-up-offset-3v3 = <0x00>;
+	nvidia,pad-autocal-pull-down-offset-3v3 = <0x7d>;
+	nvidia,pad-autocal-pull-up-offset-1v8 = <0x7b>;
+	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index bf7328aba330..dab208b5c7c7 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -1,4 +1,4 @@
 Distributed Switch Architecture Device Tree Bindings
 ----------------------------------------------------
 
-See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documenation.
+See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documentation.
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 1c4474036d46..fa2baca8c726 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -54,7 +54,8 @@ properties:
 
   phy-connection-type:
     description:
-      Operation mode of the PHY interface
+      Specifies interface type between the Ethernet device and a physical
+      layer (PHY) device.
     enum:
       # There is not a standard bus between the MAC and the PHY,
       # something proprietary is being used to embed the PHY in the
diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml
index 08678af5ed93..8ce5ed8a58dd 100644
--- a/Documentation/devicetree/bindings/net/renesas,ether.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml
@@ -59,9 +59,15 @@ properties:
   clocks:
     maxItems: 1
 
-  pinctrl-0: true
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
 
-  pinctrl-names: true
+  phy-mode: true
+
+  phy-handle: true
 
   renesas,no-ether-link:
     type: boolean
@@ -74,6 +80,11 @@ properties:
       specify when the Ether LINK signal is active-low instead of normal
       active-high
 
+patternProperties:
+  "^ethernet-phy@[0-9a-f]$":
+    type: object
+    $ref: ethernet-phy.yaml#
+
 required:
   - compatible
   - reg
@@ -83,7 +94,8 @@ required:
   - '#address-cells'
   - '#size-cells'
   - clocks
-  - pinctrl-0
+
+additionalProperties: false
 
 examples:
   # Lager board
@@ -99,8 +111,6 @@ examples:
         clocks = <&mstp8_clks R8A7790_CLK_ETHER>;
         phy-mode = "rmii";
         phy-handle = <&phy1>;
-        pinctrl-0 = <&ether_pins>;
-        pinctrl-names = "default";
         renesas,ether-link-active-low;
         #address-cells = <1>;
         #size-cells = <0>;
@@ -109,7 +119,5 @@ examples:
             reg = <1>;
             interrupt-parent = <&irqc0>;
             interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-            pinctrl-0 = <&phy1_pins>;
-            pinctrl-names = "default";
         };
     };
diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
index 64b2c64ca806..a1e2be737eec 100644
--- a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
@@ -9,6 +9,14 @@ title: PCIe RC controller on Intel Gateway SoCs
 maintainers:
   - Dilip Kota <eswara.kota@linux.intel.com>
 
+select:
+  properties:
+    compatible:
+      contains:
+        const: intel,lgm-pcie
+  required:
+    - compatible
+
 properties:
   compatible:
     items:
diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
index da68f4a25dd9..8740e076061e 100644
--- a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale MXS PWM controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <anson.huang@nxp.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
index f5e518d099f2..62d4ed2d7fd7 100644
--- a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
@@ -23,8 +23,8 @@ Required properties:
 
 - compatible:
     Must be one of :
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-qspi" : MSPI+BSPI on BRCMSTB SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi" : MSPI+BSPI on BRCMSTB SoCs
+    "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi" : Second Instance of MSPI
 						   BRCMSTB  SoCs
     "brcm,spi-bcm7425-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
@@ -36,8 +36,8 @@ Required properties:
     			     			  			    BRCMSTB  SoCs
     "brcm,spi-bcm7278-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"     : MSPI+BSPI on Cygnus, NSP
-    "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"     : NS2 SoCs
+    "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"     : MSPI+BSPI on Cygnus, NSP
+    "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"     : NS2 SoCs
 
 - reg:
     Define the bases and ranges of the associated I/O address spaces.
@@ -86,7 +86,7 @@ BRCMSTB SoC Example:
     spi@f03e3400 {
 		#address-cells = <0x1>;
 		#size-cells = <0x0>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-qspi";
+		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi";
 		reg = <0xf03e0920 0x4 0xf03e3400 0x188 0xf03e3200 0x50>;
 		reg-names = "cs_reg", "mspi", "bspi";
 		interrupts = <0x6 0x5 0x4 0x3 0x2 0x1 0x0>;
@@ -149,7 +149,7 @@ BRCMSTB SoC Example:
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&upg_fixed>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-mspi";
+		compatible = "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi";
 		reg = <0xf0416000 0x180>;
 		reg-names = "mspi";
 		interrupts = <0x14>;
@@ -160,7 +160,7 @@ BRCMSTB SoC Example:
 iProc SoC Example:
 
     qspi: spi@18027200 {
-	compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+	compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 	reg = <0x18027200 0x184>,
 	      <0x18027000 0x124>,
 	      <0x1811c408 0x004>,
@@ -191,7 +191,7 @@ iProc SoC Example:
  NS2 SoC Example:
 
 	       qspi: spi@66470200 {
-		       compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+		       compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 		       reg = <0x66470200 0x184>,
 			     <0x66470000 0x124>,
 			     <0x67017408 0x004>,
diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
index 1b50cedbfb3e..50df1a40bbe3 100644
--- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
+++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale (Enhanced) Configurable Serial Peripheral Interface (CSPI/eCSPI) for i.MX
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 allOf:
   - $ref: "/schemas/spi/spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
index 22882e769e26..312d8fee9dbb 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
@@ -39,6 +39,7 @@ properties:
       spi common code does not support use of CS signals discontinuously.
       i.MX8DXL-EVK board only uses CS1 without using CS0. Therefore, add
       this property to re-config the chipselect value in the LPSPI driver.
+    type: boolean
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
index aedac1669998..16b57f57d103 100644
--- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: NXP i.MX Thermal Binding
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <Anson.Huang@nxp.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
new file mode 100644
index 000000000000..2a0e9cd9fbcf
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/timer/sifive,clint.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SiFive Core Local Interruptor
+
+maintainers:
+  - Palmer Dabbelt <palmer@dabbelt.com>
+  - Anup Patel <anup.patel@wdc.com>
+
+description:
+  SiFive (and other RISC-V) SOCs include an implementation of the SiFive
+  Core Local Interruptor (CLINT) for M-mode timer and M-mode inter-processor
+  interrupts. It directly connects to the timer and inter-processor interrupt
+  lines of various HARTs (or CPUs) so RISC-V per-HART (or per-CPU) local
+  interrupt controller is the parent interrupt controller for CLINT device.
+  The clock frequency of CLINT is specified via "timebase-frequency" DT
+  property of "/cpus" DT node. The "timebase-frequency" DT property is
+  described in Documentation/devicetree/bindings/riscv/cpus.yaml
+
+properties:
+  compatible:
+    items:
+      - const: sifive,fu540-c000-clint
+      - const: sifive,clint0
+
+    description:
+      Should be "sifive,<chip>-clint" and "sifive,clint<version>".
+      Supported compatible strings are -
+      "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated
+      onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive
+      CLINT v0 IP block with no chip integration tweaks.
+      Please refer to sifive-blocks-ip-versioning.txt for details
+
+  reg:
+    maxItems: 1
+
+  interrupts-extended:
+    minItems: 1
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts-extended
+
+examples:
+  - |
+    timer@2000000 {
+      compatible = "sifive,fu540-c000-clint", "sifive,clint0";
+      interrupts-extended = <&cpu1intc 3 &cpu1intc 7
+                             &cpu2intc 3 &cpu2intc 7
+                             &cpu3intc 3 &cpu3intc 7
+                             &cpu4intc 3 &cpu4intc 7>;
+       reg = <0x2000000 0x10000>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index a1e4356cf522..8f27994d4497 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -1001,7 +1001,7 @@ patternProperties:
   "^sst,.*":
     description: Silicon Storage Technology, Inc.
   "^sstar,.*":
-    description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. 
+    description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd.
       (formerly part of MStar Semiconductor, Inc.)
   "^st,.*":
     description: STMicroelectronics
diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst
index 8c74a99f95e2..16f21e182ff6 100644
--- a/Documentation/devicetree/writing-schema.rst
+++ b/Documentation/devicetree/writing-schema.rst
@@ -5,7 +5,7 @@ Writing DeviceTree Bindings in json-schema
 
 Devicetree bindings are written using json-schema vocabulary. Schema files are
 written in a JSON compatible subset of YAML. YAML is used instead of JSON as it
-considered more human readable and has some advantages such as allowing
+is considered more human readable and has some advantages such as allowing
 comments (Prefixed with '#').
 
 Schema Contents
@@ -19,7 +19,7 @@ $id
   A json-schema unique identifier string. The string must be a valid
   URI typically containing the binding's filename and path. For DT schema, it must
   begin with "http://devicetree.org/schemas/". The URL is used in constructing
-  references to other files specified in schema "$ref" properties. A $ref values
+  references to other files specified in schema "$ref" properties. A $ref value
   with a leading '/' will have the hostname prepended. A $ref value a relative
   path or filename only will be prepended with the hostname and path components
   of the current schema file's '$id' value. A URL is used even for local files,
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 100bfd227265..13ea0cc0a3fa 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -179,7 +179,7 @@ DMA Fence uABI/Sync File
    :internal:
 
 Indefinite DMA Fences
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~
 
 At various times &dma_fence with an indefinite time until dma_fence_wait()
 finishes have been proposed. Examples include:
diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst
index 71c5a40da320..ccd677ba7d76 100644
--- a/Documentation/driver-api/fpga/fpga-bridge.rst
+++ b/Documentation/driver-api/fpga/fpga-bridge.rst
@@ -6,9 +6,9 @@ API to implement a new FPGA bridge
 
 * struct :c:type:`fpga_bridge` — The FPGA Bridge structure
 * struct :c:type:`fpga_bridge_ops` — Low level Bridge driver ops
-* :c:func:`devm_fpga_bridge_create()` — Allocate and init a bridge struct
-* :c:func:`fpga_bridge_register()` — Register a bridge
-* :c:func:`fpga_bridge_unregister()` — Unregister a bridge
+* devm_fpga_bridge_create() — Allocate and init a bridge struct
+* fpga_bridge_register() — Register a bridge
+* fpga_bridge_unregister() — Unregister a bridge
 
 .. kernel-doc:: include/linux/fpga/fpga-bridge.h
    :functions: fpga_bridge
diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst
index 576f1945eacd..af5382af1379 100644
--- a/Documentation/driver-api/fpga/fpga-mgr.rst
+++ b/Documentation/driver-api/fpga/fpga-mgr.rst
@@ -104,9 +104,9 @@ API for implementing a new FPGA Manager driver
 * ``fpga_mgr_states`` —  Values for :c:member:`fpga_manager->state`.
 * struct :c:type:`fpga_manager` —  the FPGA manager struct
 * struct :c:type:`fpga_manager_ops` —  Low level FPGA manager driver ops
-* :c:func:`devm_fpga_mgr_create` —  Allocate and init a manager struct
-* :c:func:`fpga_mgr_register` —  Register an FPGA manager
-* :c:func:`fpga_mgr_unregister` —  Unregister an FPGA manager
+* devm_fpga_mgr_create() —  Allocate and init a manager struct
+* fpga_mgr_register() —  Register an FPGA manager
+* fpga_mgr_unregister() —  Unregister an FPGA manager
 
 .. kernel-doc:: include/linux/fpga/fpga-mgr.h
    :functions: fpga_mgr_states
diff --git a/Documentation/driver-api/fpga/fpga-programming.rst b/Documentation/driver-api/fpga/fpga-programming.rst
index b5484df6ff0f..f487ad64dfb9 100644
--- a/Documentation/driver-api/fpga/fpga-programming.rst
+++ b/Documentation/driver-api/fpga/fpga-programming.rst
@@ -6,9 +6,9 @@ Overview
 
 The in-kernel API for FPGA programming is a combination of APIs from
 FPGA manager, bridge, and regions.  The actual function used to
-trigger FPGA programming is :c:func:`fpga_region_program_fpga()`.
+trigger FPGA programming is fpga_region_program_fpga().
 
-:c:func:`fpga_region_program_fpga()` uses functionality supplied by
+fpga_region_program_fpga() uses functionality supplied by
 the FPGA manager and bridges.  It will:
 
  * lock the region's mutex
@@ -20,8 +20,8 @@ the FPGA manager and bridges.  It will:
  * release the locks
 
 The struct fpga_image_info specifies what FPGA image to program.  It is
-allocated/freed by :c:func:`fpga_image_info_alloc()` and freed with
-:c:func:`fpga_image_info_free()`
+allocated/freed by fpga_image_info_alloc() and freed with
+fpga_image_info_free()
 
 How to program an FPGA using a region
 -------------------------------------
@@ -84,10 +84,10 @@ will generate that list.  Here's some sample code of what to do next::
 API for programming an FPGA
 ---------------------------
 
-* :c:func:`fpga_region_program_fpga` —  Program an FPGA
-* :c:type:`fpga_image_info` —  Specifies what FPGA image to program
-* :c:func:`fpga_image_info_alloc()` —  Allocate an FPGA image info struct
-* :c:func:`fpga_image_info_free()` —  Free an FPGA image info struct
+* fpga_region_program_fpga() —  Program an FPGA
+* fpga_image_info() —  Specifies what FPGA image to program
+* fpga_image_info_alloc() —  Allocate an FPGA image info struct
+* fpga_image_info_free() —  Free an FPGA image info struct
 
 .. kernel-doc:: drivers/fpga/fpga-region.c
    :functions: fpga_region_program_fpga
diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst
index 0529b2d2231a..31118a8ba218 100644
--- a/Documentation/driver-api/fpga/fpga-region.rst
+++ b/Documentation/driver-api/fpga/fpga-region.rst
@@ -46,18 +46,18 @@ API to add a new FPGA region
 ----------------------------
 
 * struct :c:type:`fpga_region` — The FPGA region struct
-* :c:func:`devm_fpga_region_create` — Allocate and init a region struct
-* :c:func:`fpga_region_register` —  Register an FPGA region
-* :c:func:`fpga_region_unregister` —  Unregister an FPGA region
+* devm_fpga_region_create() — Allocate and init a region struct
+* fpga_region_register() —  Register an FPGA region
+* fpga_region_unregister() —  Unregister an FPGA region
 
 The FPGA region's probe function will need to get a reference to the FPGA
 Manager it will be using to do the programming.  This usually would happen
 during the region's probe function.
 
-* :c:func:`fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count
-* :c:func:`of_fpga_mgr_get` —  Get a reference to an FPGA manager, raise ref count,
+* fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count
+* of_fpga_mgr_get() —  Get a reference to an FPGA manager, raise ref count,
   given a device node.
-* :c:func:`fpga_mgr_put` — Put an FPGA manager
+* fpga_mgr_put() — Put an FPGA manager
 
 The FPGA region will need to specify which bridges to control while programming
 the FPGA.  The region driver can build a list of bridges during probe time
@@ -66,11 +66,11 @@ the list of bridges to program just before programming
 (:c:member:`fpga_region->get_bridges`).  The FPGA bridge framework supplies the
 following APIs to handle building or tearing down that list.
 
-* :c:func:`fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a
+* fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a
   list
-* :c:func:`of_fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a
+* of_fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a
   list, given a device node
-* :c:func:`fpga_bridges_put` — Given a list of bridges, put them
+* fpga_bridges_put() — Given a list of bridges, put them
 
 .. kernel-doc:: include/linux/fpga/fpga-region.h
    :functions: fpga_region
diff --git a/Documentation/driver-api/iio/core.rst b/Documentation/driver-api/iio/core.rst
index b0bc0c028cc5..51b21e002396 100644
--- a/Documentation/driver-api/iio/core.rst
+++ b/Documentation/driver-api/iio/core.rst
@@ -11,10 +11,10 @@ Industrial I/O Devices
 ----------------------
 
 * struct :c:type:`iio_dev` - industrial I/O device
-* :c:func:`iio_device_alloc()` - allocate an :c:type:`iio_dev` from a driver
-* :c:func:`iio_device_free()` - free an :c:type:`iio_dev` from a driver
-* :c:func:`iio_device_register()` - register a device with the IIO subsystem
-* :c:func:`iio_device_unregister()` - unregister a device from the IIO
+* iio_device_alloc() - allocate an :c:type:`iio_dev` from a driver
+* iio_device_free() - free an :c:type:`iio_dev` from a driver
+* iio_device_register() - register a device with the IIO subsystem
+* iio_device_unregister() - unregister a device from the IIO
   subsystem
 
 An IIO device usually corresponds to a single hardware sensor and it
@@ -34,17 +34,17 @@ A typical IIO driver will register itself as an :doc:`I2C <../i2c>` or
 
 At probe:
 
-1. Call :c:func:`iio_device_alloc()`, which allocates memory for an IIO device.
+1. Call iio_device_alloc(), which allocates memory for an IIO device.
 2. Initialize IIO device fields with driver specific information (e.g.
    device name, device channels).
-3. Call :c:func:`iio_device_register()`, this registers the device with the
+3. Call iio_device_register(), this registers the device with the
    IIO core. After this call the device is ready to accept requests from user
    space applications.
 
 At remove, we free the resources allocated in probe in reverse order:
 
-1. :c:func:`iio_device_unregister()`, unregister the device from the IIO core.
-2. :c:func:`iio_device_free()`, free the memory allocated for the IIO device.
+1. iio_device_unregister(), unregister the device from the IIO core.
+2. iio_device_free(), free the memory allocated for the IIO device.
 
 IIO device sysfs interface
 ==========================
diff --git a/Documentation/fault-injection/nvme-fault-injection.rst b/Documentation/fault-injection/nvme-fault-injection.rst
index cdb2e829228e..1d4427890d75 100644
--- a/Documentation/fault-injection/nvme-fault-injection.rst
+++ b/Documentation/fault-injection/nvme-fault-injection.rst
@@ -3,7 +3,7 @@ NVMe Fault Injection
 Linux's fault injection framework provides a systematic way to support
 error injection via debugfs in the /sys/kernel/debug directory. When
 enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
-injected into the nvme_end_request. Users can change the default status
+injected into the nvme_try_complete_req. Users can change the default status
 code and no retry flag via the debugfs. The list of Generic Command
 Status can be found in include/linux/nvme.h
 
diff --git a/Documentation/filesystems/affs.rst b/Documentation/filesystems/affs.rst
index 7f1a40dce6d3..5776cbd5fa53 100644
--- a/Documentation/filesystems/affs.rst
+++ b/Documentation/filesystems/affs.rst
@@ -110,13 +110,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows:
 
   - R maps to r for user, group and others. On directories, R implies x.
 
-  - If both W and D are allowed, w will be set.
+  - W maps to w.
 
   - E maps to x.
 
-  - H and P are always retained and ignored under Linux.
+  - D is ignored.
 
-  - A is always reset when a file is written to.
+  - H, S and P are always retained and ignored under Linux.
+
+  - A is cleared when a file is written to.
 
 User id and group id will be used unless set[gu]id are given as mount
 options. Since most of the Amiga file systems are single user systems
@@ -128,11 +130,13 @@ Linux -> Amiga:
 
 The Linux rwxrwxrwx file mode is handled as follows:
 
-  - r permission will set R for user, group and others.
+  - r permission will allow R for user, group and others.
+
+  - w permission will allow W for user, group and others.
 
-  - w permission will set W and D for user, group and others.
+  - x permission of the user will allow E for plain files.
 
-  - x permission of the user will set E for plain files.
+  - D will be allowed for user, group and others.
 
   - All other flags (suid, sgid, ...) are ignored and will
     not be retained.
diff --git a/Documentation/filesystems/ext4/about.rst b/Documentation/filesystems/ext4/about.rst
index 0aadba052264..cc76b577d2f4 100644
--- a/Documentation/filesystems/ext4/about.rst
+++ b/Documentation/filesystems/ext4/about.rst
@@ -39,6 +39,6 @@ entry.
 Other References
 ----------------
 
-Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+Also see https://www.nongnu.org/ext2-doc/ for quite a collection of
 information about ext2/3. Here's another old reference:
 http://wiki.osdev.org/Ext2
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 17112352f605..29ca5f5feb35 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -153,7 +153,7 @@ This section covers hwmon and power/thermal controls.
 HWMON Interfaces
 ----------------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: hwmon
 
 GPU sysfs Power State Interfaces
@@ -164,48 +164,54 @@ GPU power controls are exposed via sysfs files.
 power_dpm_state
 ~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: power_dpm_state
 
 power_dpm_force_performance_level
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: power_dpm_force_performance_level
 
 pp_table
 ~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pp_table
 
 pp_od_clk_voltage
 ~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pp_od_clk_voltage
 
 pp_dpm_*
 ~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pp_dpm_sclk pp_dpm_mclk pp_dpm_socclk pp_dpm_fclk pp_dpm_dcefclk pp_dpm_pcie
 
 pp_power_profile_mode
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pp_power_profile_mode
 
 *_busy_percent
 ~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: gpu_busy_percent
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: mem_busy_percent
 
+gpu_metrics
+~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
+   :doc: gpu_metrics
+
 GPU Product Information
 =======================
 
@@ -233,7 +239,7 @@ serial_number
 unique_id
 ---------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: unique_id
 
 GPU Memory Usage Information
@@ -283,7 +289,7 @@ PCIe Accounting Information
 pcie_bw
 -------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+.. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pcie_bw
 
 pcie_replay_count
diff --git a/Documentation/hwmon/abituguru-datasheet.rst b/Documentation/hwmon/abituguru-datasheet.rst
index 6d5253e2223b..0cd61471d2a2 100644
--- a/Documentation/hwmon/abituguru-datasheet.rst
+++ b/Documentation/hwmon/abituguru-datasheet.rst
@@ -68,7 +68,7 @@ See below for all known bank addresses, numbers of sensors in that bank,
 number of bytes data per sensor and contents/meaning of those bytes.
 
 Although both this document and the kernel driver have kept the sensor
-terminoligy for the addressing within a bank this is not 100% correct, in
+terminology for the addressing within a bank this is not 100% correct, in
 bank 0x24 for example the addressing within the bank selects a PWM output not
 a sensor.
 
@@ -155,7 +155,7 @@ After wider testing of the Linux kernel driver some variants of the uGuru have
 turned up which do not hold 0x08 at DATA within 250 reads after writing the
 bank address. With these versions this happens quite frequent, using larger
 timeouts doesn't help, they just go offline for a second or 2, doing some
-internal callibration or whatever. Your code should be prepared to handle
+internal calibration or whatever. Your code should be prepared to handle
 this and in case of no response in this specific case just goto sleep for a
 while and then retry.
 
@@ -331,6 +331,6 @@ the voltage / clock programming out, I tried reading and only reading banks
 0-0x30 with the reading code used for the sensor banks (0x20-0x28) and this
 resulted in a _permanent_ reprogramming of the voltages, luckily I had the
 sensors part configured so that it would shutdown my system on any out of spec
-voltages which proprably safed my computer (after a reboot I managed to
+voltages which probably safed my computer (after a reboot I managed to
 immediately enter the bios and reload the defaults). This probably means that
 the read/write cycle for the non sensor part is different from the sensor part.
diff --git a/Documentation/hwmon/abituguru.rst b/Documentation/hwmon/abituguru.rst
index d8243c827de9..cfda60b757ce 100644
--- a/Documentation/hwmon/abituguru.rst
+++ b/Documentation/hwmon/abituguru.rst
@@ -17,7 +17,7 @@ Supported chips:
     Note:
 	The uGuru is a microcontroller with onboard firmware which programs
 	it to behave as a hwmon IC. There are many different revisions of the
-	firmware and thus effectivly many different revisions of the uGuru.
+	firmware and thus effectively many different revisions of the uGuru.
 	Below is an incomplete list with which revisions are used for which
 	Motherboards:
 
@@ -33,7 +33,7 @@ Supported chips:
 	sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's
 	this does not always work. For these uGuru's the autodetection can
 	be overridden with the bank1_types module param. For all 3 known
-	revison 1 motherboards the correct use of this param is:
+	revision 1 motherboards the correct use of this param is:
 	bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
 	You may also need to specify the fan_sensors option for these boards
 	fan_sensors=5
diff --git a/Documentation/hwmon/abituguru3.rst b/Documentation/hwmon/abituguru3.rst
index 514f11f41e8b..88046d866385 100644
--- a/Documentation/hwmon/abituguru3.rst
+++ b/Documentation/hwmon/abituguru3.rst
@@ -13,7 +13,7 @@ Supported chips:
     Note:
 	The uGuru is a microcontroller with onboard firmware which programs
 	it to behave as a hwmon IC. There are many different revisions of the
-	firmware and thus effectivly many different revisions of the uGuru.
+	firmware and thus effectively many different revisions of the uGuru.
 	Below is an incomplete list with which revisions are used for which
 	Motherboards:
 
@@ -24,7 +24,7 @@ Supported chips:
 	- uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
 	  AW9D-MAX)
 
-	The abituguru3 driver is only for revison 3.0.x.x motherboards,
+	The abituguru3 driver is only for revision 3.0.x.x motherboards,
 	this driver will not work on older motherboards. For older
 	motherboards use the abituguru (without the 3 !) driver.
 
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index 2aac50b97921..334df758dce3 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -23,8 +23,8 @@ supports C and the GNU C extensions required by the kernel, and is pronounced
 Clang
 -----
 
-The compiler used can be swapped out via `CC=` command line argument to `make`.
-`CC=` should be set when selecting a config and during a build.
+The compiler used can be swapped out via ``CC=`` command line argument to ``make``.
+``CC=`` should be set when selecting a config and during a build. ::
 
 	make CC=clang defconfig
 
@@ -34,33 +34,33 @@ Cross Compiling
 ---------------
 
 A single Clang compiler binary will typically contain all supported backends,
-which can help simplify cross compiling.
+which can help simplify cross compiling. ::
 
 	ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang
 
-`CROSS_COMPILE` is not used to prefix the Clang compiler binary, instead
-`CROSS_COMPILE` is used to set a command line flag: `--target <triple>`. For
-example:
+``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead
+``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For
+example: ::
 
 	clang --target aarch64-linux-gnu foo.c
 
 LLVM Utilities
 --------------
 
-LLVM has substitutes for GNU binutils utilities. Kbuild supports `LLVM=1`
-to enable them.
+LLVM has substitutes for GNU binutils utilities. Kbuild supports ``LLVM=1``
+to enable them. ::
 
 	make LLVM=1
 
-They can be enabled individually. The full list of the parameters:
+They can be enabled individually. The full list of the parameters: ::
 
-	make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\
-	  OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \\
-	  READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \\
+	make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \
+	  OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \
+	  READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \
 	  HOSTLD=ld.lld
 
 Currently, the integrated assembler is disabled by default. You can pass
-`LLVM_IAS=1` to enable it.
+``LLVM_IAS=1`` to enable it.
 
 Getting Help
 ------------
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index b81b8913a5a3..58d513a0fa95 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -16,7 +16,7 @@ This document describes the Linux kernel Makefiles.
 	   --- 3.5 Library file goals - lib-y
 	   --- 3.6 Descending down in directories
 	   --- 3.7 Compilation flags
-	   --- 3.8 Command line dependency
+	   --- 3.8 <deleted>
 	   --- 3.9 Dependency tracking
 	   --- 3.10 Special Rules
 	   --- 3.11 $(CC) support functions
@@ -39,8 +39,8 @@ This document describes the Linux kernel Makefiles.
 
 	=== 7 Architecture Makefiles
 	   --- 7.1 Set variables to tweak the build to the architecture
-	   --- 7.2 Add prerequisites to archheaders:
-	   --- 7.3 Add prerequisites to archprepare:
+	   --- 7.2 Add prerequisites to archheaders
+	   --- 7.3 Add prerequisites to archprepare
 	   --- 7.4 List directories to visit when descending
 	   --- 7.5 Architecture-specific boot images
 	   --- 7.6 Building non-kbuild targets
@@ -129,7 +129,7 @@ The preferred name for the kbuild files are 'Makefile' but 'Kbuild' can
 be used and if both a 'Makefile' and a 'Kbuild' file exists, then the 'Kbuild'
 file will be used.
 
-Section 3.1 "Goal definitions" is a quick intro, further chapters provide
+Section 3.1 "Goal definitions" is a quick intro; further chapters provide
 more details, with real examples.
 
 3.1 Goal definitions
@@ -965,7 +965,7 @@ When kbuild executes, the following steps are followed (roughly):
 		KBUILD_LDFLAGS         := -m elf_s390
 
 	Note: ldflags-y can be used to further customise
-	the flags used. See chapter 3.7.
+	the flags used. See section 3.7.
 
     LDFLAGS_vmlinux
 	Options for $(LD) when linking vmlinux
@@ -1121,7 +1121,7 @@ When kbuild executes, the following steps are followed (roughly):
 
 	In this example, the file target maketools will be processed
 	before descending down in the subdirectories.
-	See also chapter XXX-TODO that describe how kbuild supports
+	See also chapter XXX-TODO that describes how kbuild supports
 	generating offset header files.
 
 
@@ -1261,7 +1261,7 @@ When kbuild executes, the following steps are followed (roughly):
 	always be built.
 	Assignments to $(targets) are without $(obj)/ prefix.
 	if_changed may be used in conjunction with custom commands as
-	defined in 6.8 "Custom kbuild commands".
+	defined in 7.8 "Custom kbuild commands".
 
 	Note: It is a typical mistake to forget the FORCE prerequisite.
 	Another common pitfall is that whitespace is sometimes
@@ -1411,7 +1411,7 @@ When kbuild executes, the following steps are followed (roughly):
 	that may be shared between individual architectures.
 	The recommended approach how to use a generic header file is
 	to list the file in the Kbuild file.
-	See "7.2 generic-y" for further info on syntax etc.
+	See "8.2 generic-y" for further info on syntax etc.
 
 7.11 Post-link pass
 -------------------
@@ -1601,4 +1601,4 @@ is the right choice.
 
 - Describe how kbuild supports shipped files with _shipped.
 - Generating offset header files.
-- Add more variables to section 7?
+- Add more variables to chapters 7 or 9?
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
index 4cefed8048ca..ddada4a53749 100644
--- a/Documentation/locking/locktypes.rst
+++ b/Documentation/locking/locktypes.rst
@@ -164,14 +164,14 @@ by disabling preemption or interrupts.
 On non-PREEMPT_RT kernels local_lock operations map to the preemption and
 interrupt disabling and enabling primitives:
 
- =========================== ======================
- local_lock(&llock)          preempt_disable()
- local_unlock(&llock)        preempt_enable()
- local_lock_irq(&llock)      local_irq_disable()
- local_unlock_irq(&llock)    local_irq_enable()
- local_lock_save(&llock)     local_irq_save()
- local_lock_restore(&llock)  local_irq_save()
- =========================== ======================
+ ===============================  ======================
+ local_lock(&llock)               preempt_disable()
+ local_unlock(&llock)             preempt_enable()
+ local_lock_irq(&llock)           local_irq_disable()
+ local_unlock_irq(&llock)         local_irq_enable()
+ local_lock_irqsave(&llock)       local_irq_save()
+ local_unlock_irqrestore(&llock)  local_irq_restore()
+ ===============================  ======================
 
 The named scope of local_lock has two advantages over the regular
 primitives:
@@ -353,14 +353,14 @@ protection scope. So the following substitution is wrong::
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock_1, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_1, flags);
   }
 
   func2()
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock_2, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_2, flags);
   }
 
   func3()
@@ -379,14 +379,14 @@ PREEMPT_RT-specific semantics of spinlock_t. The correct substitution is::
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags);
   }
 
   func2()
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags);
   }
 
   func3()
diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst
index 227f427118e8..b7a627d6c97d 100644
--- a/Documentation/maintainer/maintainer-entry-profile.rst
+++ b/Documentation/maintainer/maintainer-entry-profile.rst
@@ -101,3 +101,4 @@ to do something different in the near future.
 
    ../doc-guide/maintainer-profile
    ../nvdimm/maintainer-entry-profile
+   ../riscv/patch-acceptance
diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index 24168b0d16bd..adc314639085 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -2860,17 +2860,6 @@ version of the linux kernel, found on http://kernel.org
 The latest version of this document can be found in the latest kernel
 source (named Documentation/networking/bonding.rst).
 
-Discussions regarding the usage of the bonding driver take place on the
-bonding-devel mailing list, hosted at sourceforge.net. If you have questions or
-problems, post them to the list.  The list address is:
-
-bonding-devel@lists.sourceforge.net
-
-The administrative interface (to subscribe or unsubscribe) can
-be found at:
-
-https://lists.sourceforge.net/lists/listinfo/bonding-devel
-
 Discussions regarding the development of the bonding driver take place
 on the main Linux network mailing list, hosted at vger.kernel.org. The list
 address is:
@@ -2881,10 +2870,3 @@ The administrative interface (to subscribe or unsubscribe) can
 be found at:
 
 http://vger.kernel.org/vger-lists.html#netdev
-
-Donald Becker's Ethernet Drivers and diag programs may be found at :
-
- - http://web.archive.org/web/%2E/http://www.scyld.com/network/
-
-You will also find a lot of information regarding Ethernet, NWay, MII,
-etc. at www.scyld.com.
diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst
index af029b3ca2ab..11bd5e6108c0 100644
--- a/Documentation/networking/dsa/configuration.rst
+++ b/Documentation/networking/dsa/configuration.rst
@@ -180,7 +180,7 @@ The configuration can only be set up via VLAN tagging and bridge setup.
 
   # bring up the slave interfaces
   ip link set lan1 up
-  ip link set lan1 up
+  ip link set lan2 up
   ip link set lan3 up
 
   # create bridge
diff --git a/Documentation/powerpc/syscall64-abi.rst b/Documentation/powerpc/syscall64-abi.rst
index 46caaadbb029..379817ca64d2 100644
--- a/Documentation/powerpc/syscall64-abi.rst
+++ b/Documentation/powerpc/syscall64-abi.rst
@@ -49,16 +49,18 @@ Register preservation rules
 Register preservation rules match the ELF ABI calling sequence with the
 following differences:
 
-=========== ============= ========================================
 --- For the sc instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)
 cr0         Volatile      (cr0.SO is the return error condition.)
 cr1, cr5-7  Nonvolatile
 lr          Nonvolatile
+=========== ============= ========================================
 
 --- For the scv 0 instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)
diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst
index 4a9aa4f0681e..918e32d76fc4 100644
--- a/Documentation/process/deprecated.rst
+++ b/Documentation/process/deprecated.rst
@@ -142,7 +142,7 @@ only NUL-terminated strings. The safe replacement is strscpy().
 (Users of strscpy() still needing NUL-padding should instead
 use strscpy_pad().)
 
-If a caller is using non-NUL-terminated strings, strncpy()() can
+If a caller is using non-NUL-terminated strings, strncpy() can
 still be used, but destinations should be marked with the `__nonstring
 <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
 attribute to avoid future compiler warnings.
diff --git a/Documentation/sound/cards/audigy-mixer.rst b/Documentation/sound/cards/audigy-mixer.rst
index 998f76e19cdd..f3f4640ee2af 100644
--- a/Documentation/sound/cards/audigy-mixer.rst
+++ b/Documentation/sound/cards/audigy-mixer.rst
@@ -332,7 +332,7 @@ WO 9901953 (A1)
 
 
 US Patents (https://www.uspto.gov/)
-----------------------------------
+-----------------------------------
 
 US 5925841
 	Digital Sampling Instrument employing cache memory (Jul. 20, 1999)
diff --git a/Documentation/sound/cards/sb-live-mixer.rst b/Documentation/sound/cards/sb-live-mixer.rst
index eccb0f0ffd0f..2ce41d3822d8 100644
--- a/Documentation/sound/cards/sb-live-mixer.rst
+++ b/Documentation/sound/cards/sb-live-mixer.rst
@@ -337,7 +337,7 @@ WO 9901953 (A1)
 
 
 US Patents (https://www.uspto.gov/)
-----------------------------------
+-----------------------------------
 
 US 5925841
 	Digital Sampling Instrument employing cache memory (Jul. 20, 1999)
diff --git a/Documentation/sound/designs/timestamping.rst b/Documentation/sound/designs/timestamping.rst
index 2b0fff503415..7c7ecf5dbc4b 100644
--- a/Documentation/sound/designs/timestamping.rst
+++ b/Documentation/sound/designs/timestamping.rst
@@ -143,7 +143,7 @@ timestamp shows when the information is put together by the driver
 before returning from the ``STATUS`` and ``STATUS_EXT`` ioctl. in most cases
 this driver_timestamp will be identical to the regular system tstamp.
 
-Examples of typestamping with HDaudio:
+Examples of timestamping with HDAudio:
 
 1. DMA timestamp, no compensation for DMA+analog delay
 ::
diff --git a/Documentation/translations/it_IT/process/deprecated.rst b/Documentation/translations/it_IT/process/deprecated.rst
index e108eaf82cf6..a642ff3fdc8b 100644
--- a/Documentation/translations/it_IT/process/deprecated.rst
+++ b/Documentation/translations/it_IT/process/deprecated.rst
@@ -130,7 +130,7 @@ chi usa solo stringe terminate. La versione sicura da usare è
 strscpy(). (chi usa strscpy() e necessita di estendere la
 terminazione con NUL deve aggiungere una chiamata a memset())
 
-Se il chiamate no usa stringhe terminate con NUL, allore strncpy()()
+Se il chiamate no usa stringhe terminate con NUL, allore strncpy()
 può continuare ad essere usata, ma i buffer di destinazione devono essere
 marchiati con l'attributo `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
 per evitare avvisi durante la compilazione.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index eb3a1316f03e..d2b733dc7892 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6130,7 +6130,7 @@ HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
 -----------------------------------
 
-:Architecture: x86
+:Architectures: x86
 
 This capability indicates that KVM running on top of Hyper-V hypervisor
 enables Direct TLB flush for its guests meaning that TLB flush
@@ -6143,19 +6143,33 @@ in CPUID and only exposes Hyper-V identification. In this case, guest
 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
 
 8.22 KVM_CAP_S390_VCPU_RESETS
+-----------------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the KVM_S390_NORMAL_RESET and
 KVM_S390_CLEAR_RESET ioctls are available.
 
 8.23 KVM_CAP_S390_PROTECTED
+---------------------------
 
-Architecture: s390
-
+:Architectures: s390
 
 This capability indicates that the Ultravisor has been initialized and
 KVM can therefore start protected VMs.
 This capability governs the KVM_S390_PV_COMMAND ioctl and the
 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
 guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces.  This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa.  For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
diff --git a/MAINTAINERS b/MAINTAINERS
index 557d79a5b9f1..c4e8bd1ab761 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1694,7 +1694,6 @@ F:	arch/arm/mach-cns3xxx/
 
 ARM/CAVIUM THUNDER NETWORK DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/net/ethernet/cavium/thunder/
@@ -3205,6 +3204,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 
@@ -3388,6 +3388,7 @@ M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Supported
+F:	Documentation/devicetree/bindings/net/dsa/b53.txt
 F:	drivers/net/dsa/b53/*
 F:	include/linux/platform_data/b53.h
 
@@ -3573,13 +3574,28 @@ L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	drivers/phy/broadcom/phy-brcm-usb*
 
+BROADCOM ETHERNET PHY DRIVERS
+M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	bcm-kernel-feedback-list@broadcom.com
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt
+F:	drivers/net/phy/bcm*.[ch]
+F:	drivers/net/phy/broadcom.c
+F:	include/linux/brcmphy.h
+
 BROADCOM GENET ETHERNET DRIVER
 M:	Doug Berger <opendmb@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 L:	netdev@vger.kernel.org
 S:	Supported
+F:	Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+F:	Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
 F:	drivers/net/ethernet/broadcom/genet/
+F:	drivers/net/mdio/mdio-bcm-unimac.c
+F:	include/linux/platform_data/bcmgenet.h
+F:	include/linux/platform_data/mdio-bcm-unimac.h
 
 BROADCOM IPROC ARM ARCHITECTURE
 M:	Ray Jui <rjui@broadcom.com>
@@ -3931,8 +3947,8 @@ W:	https://wireless.wiki.kernel.org/en/users/Drivers/carl9170
 F:	drivers/net/wireless/ath/carl9170/
 
 CAVIUM I2C DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
@@ -3947,8 +3963,8 @@ W:	http://www.marvell.com
 F:	drivers/net/ethernet/cavium/liquidio/
 
 CAVIUM MMC DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/mmc/host/cavium*
 
@@ -3960,9 +3976,9 @@ W:	http://www.marvell.com
 F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
+S:	Odd Fixes
 F:	Documentation/devicetree/bindings/arm/cavium-thunder2.txt
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*
 
@@ -4241,6 +4257,8 @@ S:	Maintained
 F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
+M:	Nathan Chancellor <natechancellor@gmail.com>
+M:	Nick Desaulniers <ndesaulniers@google.com>
 L:	clang-built-linux@googlegroups.com
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
@@ -5050,7 +5068,7 @@ F:	include/linux/dm-*.h
 F:	include/uapi/linux/dm-*.h
 
 DEVLINK
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/devlink
@@ -5239,6 +5257,7 @@ DOCUMENTATION
 M:	Jonathan Corbet <corbet@lwn.net>
 L:	linux-doc@vger.kernel.org
 S:	Maintained
+P:	Documentation/doc-guide/maintainer-profile.rst
 T:	git git://git.lwn.net/linux.git docs-next
 F:	Documentation/
 F:	scripts/documentation-file-ref-check
@@ -6089,7 +6108,7 @@ F:	include/linux/dynamic_debug.h
 F:	lib/dynamic_debug.c
 
 DYNAMIC INTERRUPT MODERATION
-M:	Tal Gilboa <talgi@mellanox.com>
+M:	Tal Gilboa <talgi@nvidia.com>
 S:	Maintained
 F:	Documentation/networking/net_dim.rst
 F:	include/linux/dim.h
@@ -6169,7 +6188,7 @@ F:	Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt
 F:	drivers/edac/aspeed_edac.c
 
 EDAC-BLUEFIELD
-M:	Shravan Kumar Ramani <sramani@mellanox.com>
+M:	Shravan Kumar Ramani <sramani@nvidia.com>
 S:	Supported
 F:	drivers/edac/bluefield_edac.c
 
@@ -6181,16 +6200,15 @@ F:	drivers/edac/highbank*
 
 EDAC-CAVIUM OCTEON
 M:	Ralf Baechle <ralf@linux-mips.org>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-edac@vger.kernel.org
 L:	linux-mips@vger.kernel.org
 S:	Supported
 F:	drivers/edac/octeon_edac*
 
 EDAC-CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
-S:	Supported
+S:	Odd Fixes
 F:	drivers/edac/thunderx_edac*
 
 EDAC-CORE
@@ -6198,7 +6216,7 @@ M:	Borislav Petkov <bp@alien8.de>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 M:	Tony Luck <tony.luck@intel.com>
 R:	James Morse <james.morse@arm.com>
-R:	Robert Richter <rrichter@marvell.com>
+R:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next
@@ -6491,8 +6509,8 @@ S:	Odd Fixes
 F:	drivers/net/ethernet/agere/
 
 ETHERNET BRIDGE
-M:	Roopa Prabhu <roopa@cumulusnetworks.com>
-M:	Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+M:	Roopa Prabhu <roopa@nvidia.com>
+M:	Nikolay Aleksandrov <nikolay@nvidia.com>
 L:	bridge@lists.linux-foundation.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -6502,7 +6520,6 @@ F:	net/bridge/
 
 ETHERNET PHY LIBRARY
 M:	Andrew Lunn <andrew@lunn.ch>
-M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Heiner Kallweit <hkallweit1@gmail.com>
 R:	Russell King <linux@armlinux.org.uk>
 L:	netdev@vger.kernel.org
@@ -6607,7 +6624,7 @@ F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
 M:	Vineet Gupta <vgupta@synopsys.com>
-M:	Ofer Levi <oferle@mellanox.com>
+M:	Ofer Levi <oferle@nvidia.com>
 S:	Supported
 F:	arch/arc/boot/dts/eznps.dts
 F:	arch/arc/plat-eznps
@@ -6892,6 +6909,14 @@ L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/dma/fsldma.*
 
+FREESCALE DSPI DRIVER
+M:	Vladimir Oltean <olteanv@gmail.com>
+L:	linux-spi@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
+F:	drivers/spi/spi-fsl-dspi.c
+F:	include/linux/spi/spi-fsl-dspi.h
+
 FREESCALE ENETC ETHERNET DRIVERS
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
 L:	netdev@vger.kernel.org
@@ -8263,7 +8288,7 @@ IA64 (Itanium) PLATFORM
 M:	Tony Luck <tony.luck@intel.com>
 M:	Fenghua Yu <fenghua.yu@intel.com>
 L:	linux-ia64@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git
 F:	Documentation/ia64/
 F:	arch/ia64/
@@ -8571,7 +8596,7 @@ F:	drivers/iio/pressure/dps310.c
 
 INFINIBAND SUBSYSTEM
 M:	Doug Ledford <dledford@redhat.com>
-M:	Jason Gunthorpe <jgg@mellanox.com>
+M:	Jason Gunthorpe <jgg@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	https://github.com/linux-rdma/rdma-core
@@ -9234,7 +9259,7 @@ F:	drivers/firmware/iscsi_ibft*
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Sagi Grimberg <sagi@grimberg.me>
-M:	Max Gurtovoy <maxg@mellanox.com>
+M:	Max Gurtovoy <maxg@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org
@@ -9783,7 +9808,7 @@ F:	drivers/scsi/53c700*
 
 LEAKING_ADDRESSES
 M:	Tobin C. Harding <me@tobin.cc>
-M:	Tycho Andersen <tycho@tycho.ws>
+M:	Tycho Andersen <tycho@tycho.pizza>
 L:	kernel-hardening@lists.openwall.com
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tobin/leaks.git
@@ -11080,7 +11105,7 @@ F:	Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
 F:	drivers/input/touchscreen/melfas_mip4.c
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
-M:	Tariq Toukan <tariqt@mellanox.com>
+M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11088,7 +11113,7 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
 MELLANOX ETHERNET DRIVER (mlx5e)
-M:	Saeed Mahameed <saeedm@mellanox.com>
+M:	Saeed Mahameed <saeedm@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11096,7 +11121,7 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
 
 MELLANOX ETHERNET INNOVA DRIVERS
-R:	Boris Pismenny <borisp@mellanox.com>
+R:	Boris Pismenny <borisp@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11107,8 +11132,8 @@ F:	drivers/net/ethernet/mellanox/mlx5/core/fpga/*
 F:	include/linux/mlx5/mlx5_ifc_fpga.h
 
 MELLANOX ETHERNET SWITCH DRIVERS
-M:	Jiri Pirko <jiri@mellanox.com>
-M:	Ido Schimmel <idosch@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
+M:	Ido Schimmel <idosch@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11117,7 +11142,7 @@ F:	drivers/net/ethernet/mellanox/mlxsw/
 F:	tools/testing/selftests/drivers/net/mlxsw/
 
 MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
-M:	mlxsw@mellanox.com
+M:	mlxsw@nvidia.com
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11127,7 +11152,7 @@ F:	drivers/net/ethernet/mellanox/mlxfw/
 MELLANOX HARDWARE PLATFORM SUPPORT
 M:	Andy Shevchenko <andy@infradead.org>
 M:	Darren Hart <dvhart@infradead.org>
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
 F:	Documentation/ABI/testing/sysfs-platform-mellanox-bootctl
@@ -11135,7 +11160,7 @@ F:	drivers/platform/mellanox/
 F:	include/linux/platform_data/mlxreg.h
 
 MELLANOX MLX4 core VPI driver
-M:	Tariq Toukan <tariqt@mellanox.com>
+M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -11145,7 +11170,7 @@ F:	drivers/net/ethernet/mellanox/mlx4/
 F:	include/linux/mlx4/
 
 MELLANOX MLX4 IB driver
-M:	Yishai Hadas <yishaih@mellanox.com>
+M:	Yishai Hadas <yishaih@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11155,8 +11180,8 @@ F:	include/linux/mlx4/
 F:	include/uapi/rdma/mlx4-abi.h
 
 MELLANOX MLX5 core VPI driver
-M:	Saeed Mahameed <saeedm@mellanox.com>
-M:	Leon Romanovsky <leonro@mellanox.com>
+M:	Saeed Mahameed <saeedm@nvidia.com>
+M:	Leon Romanovsky <leonro@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -11167,7 +11192,7 @@ F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
 
 MELLANOX MLX5 IB driver
-M:	Leon Romanovsky <leonro@mellanox.com>
+M:	Leon Romanovsky <leonro@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11177,8 +11202,8 @@ F:	include/linux/mlx5/
 F:	include/uapi/rdma/mlx5-abi.h
 
 MELLANOX MLXCPLD I2C AND MUX DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
-M:	Michael Shych <michaelsh@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
+M:	Michael Shych <michaelsh@nvidia.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	Documentation/i2c/busses/i2c-mlxcpld.rst
@@ -11186,7 +11211,7 @@ F:	drivers/i2c/busses/i2c-mlxcpld.c
 F:	drivers/i2c/muxes/i2c-mux-mlxcpld.c
 
 MELLANOX MLXCPLD LED DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	linux-leds@vger.kernel.org
 S:	Supported
 F:	Documentation/leds/leds-mlxcpld.rst
@@ -11194,7 +11219,7 @@ F:	drivers/leds/leds-mlxcpld.c
 F:	drivers/leds/leds-mlxreg.c
 
 MELLANOX PLATFORM DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
 F:	drivers/platform/x86/mlx-platform.c
@@ -12175,8 +12200,8 @@ F:	net/ipv6/syncookies.c
 F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
-M:	Boris Pismenny <borisp@mellanox.com>
-M:	Aviad Yehezkel <aviadye@mellanox.com>
+M:	Boris Pismenny <borisp@nvidia.com>
+M:	Aviad Yehezkel <aviadye@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <kuba@kernel.org>
@@ -12484,7 +12509,7 @@ S:	Supported
 F:	drivers/nfc/nxp-nci
 
 OBJAGG
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	include/linux/objagg.h
@@ -13126,7 +13151,7 @@ F:	drivers/video/logo/logo_parisc*
 F:	include/linux/hp_sdc.h
 
 PARMAN
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	include/linux/parman.h
@@ -13445,10 +13470,10 @@ F:	Documentation/devicetree/bindings/pci/axis,artpec*
 F:	drivers/pci/controller/dwc/*artpec*
 
 PCIE DRIVER FOR CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Odd Fixes
 F:	drivers/pci/controller/pci-thunder-*
 
 PCIE DRIVER FOR HISILICON
@@ -13585,12 +13610,18 @@ F:	kernel/events/*
 F:	tools/lib/perf/
 F:	tools/perf/
 
-PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS
+PERFORMANCE EVENTS TOOLING ARM64
 R:	John Garry <john.garry@huawei.com>
 R:	Will Deacon <will@kernel.org>
+R:	Mathieu Poirier <mathieu.poirier@linaro.org>
+R:	Leo Yan <leo.yan@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
+F:	tools/build/feature/test-libopencsd.c
+F:	tools/perf/arch/arm*/
 F:	tools/perf/pmu-events/arch/arm64/
+F:	tools/perf/util/arm-spe*
+F:	tools/perf/util/cs-etm*
 
 PERSONALITY HANDLING
 M:	Christoph Hellwig <hch@infradead.org>
@@ -14381,7 +14412,7 @@ M:	Rob Clark <robdclark@gmail.com>
 L:	iommu@lists.linux-foundation.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
-F:	drivers/iommu/qcom_iommu.c
+F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
 
 QUALCOMM IPCC MAILBOX DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -15562,6 +15593,7 @@ F:	include/uapi/linux/sed*
 SECURITY CONTACT
 M:	Security Officers <security@kernel.org>
 S:	Supported
+F:	Documentation/admin-guide/security-bugs.rst
 
 SECURITY SUBSYSTEM
 M:	James Morris <jmorris@namei.org>
@@ -16050,7 +16082,7 @@ F:	drivers/infiniband/sw/siw/
 F:	include/uapi/rdma/siw-abi.h
 
 SOFT-ROCE DRIVER (rxe)
-M:	Zhu Yanjun <yanjunz@mellanox.com>
+M:	Zhu Yanjun <yanjunz@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/sw/rxe/
@@ -17132,8 +17164,8 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml
 F:	Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
 F:	Documentation/devicetree/bindings/clock/ti,sci-clk.txt
-F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
-F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
+F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
 F:	Documentation/devicetree/bindings/reset/ti,sci-reset.txt
 F:	Documentation/devicetree/bindings/soc/ti/sci-pm-domain.txt
 F:	drivers/clk/keystone/sci-clk.c
@@ -17230,8 +17262,8 @@ S:	Maintained
 F:	drivers/net/thunderbolt.c
 
 THUNDERX GPIO DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Maintained
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 F:	drivers/gpio/gpio-thunderx.c
 
 TI AM437X VPFE DRIVER
@@ -18890,6 +18922,15 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 F:	arch/x86/platform
 
+X86 PLATFORM UV HPE SUPERDOME FLEX
+M:	Steve Wahl <steve.wahl@hpe.com>
+R:	Dimitri Sivanich <dimitri.sivanich@hpe.com>
+R:	Russ Anderson <russ.anderson@hpe.com>
+S:	Supported
+F:	arch/x86/include/asm/uv/
+F:	arch/x86/kernel/apic/x2apic_uv_x.c
+F:	arch/x86/platform/uv/
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org
diff --git a/Makefile b/Makefile
index 9cac6fde3479..19d012810fbb 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc5
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -265,8 +265,7 @@ no-dot-config-targets := $(clean-targets) \
 			 $(version_h) headers headers_% archheaders archscripts \
 			 %asm-generic kernelversion %src-pkg dt_binding_check \
 			 outputmakefile
-no-sync-config-targets := $(no-dot-config-targets) install %install \
-			   kernelrelease
+no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease
 single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
 
 config-build	:=
@@ -292,7 +291,7 @@ ifneq ($(KBUILD_EXTMOD),)
 endif
 
 ifeq ($(KBUILD_EXTMOD),)
-        ifneq ($(filter config %config,$(MAKECMDGOALS)),)
+        ifneq ($(filter %config,$(MAKECMDGOALS)),)
 		config-build := 1
                 ifneq ($(words $(MAKECMDGOALS)),1)
 			mixed-build := 1
@@ -883,10 +882,6 @@ KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections
 LDFLAGS_vmlinux += --gc-sections
 endif
 
-ifdef CONFIG_LIVEPATCH
-KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone)
-endif
-
 ifdef CONFIG_SHADOW_CALL_STACK
 CC_FLAGS_SCS	:= -fsanitize=shadow-call-stack
 KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c
index ac110ae8f978..5b60c248de9e 100644
--- a/arch/alpha/kernel/module.c
+++ b/arch/alpha/kernel/module.c
@@ -212,7 +212,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab,
 			    STO_ALPHA_STD_GPLOAD)
 				/* Omit the prologue. */
 				value += 8;
-			/* FALLTHRU */
+			fallthrough;
 		case R_ALPHA_BRADDR:
 			value -= (u64)location + 4;
 			if (value & 3)
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index a813020d2f11..15bc9d1e79f4 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -453,7 +453,7 @@ syscall_restart(unsigned long r0, unsigned long r19,
 			regs->r0 = EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case ERESTARTNOINTR:
 		regs->r0 = r0;	/* reset v0 and a3 and replay syscall */
 		regs->r19 = r19;
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 49754e07e04f..921d4b6e4d95 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -883,7 +883,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 
 	case 0x26: /* sts */
 		fake_reg = s_reg_to_mem(alpha_read_fp_reg(reg));
-		/* FALLTHRU */
+		fallthrough;
 
 	case 0x2c: /* stl */
 		__asm__ __volatile__(
@@ -911,7 +911,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 
 	case 0x27: /* stt */
 		fake_reg = alpha_read_fp_reg(reg);
-		/* FALLTHRU */
+		fallthrough;
 
 	case 0x2d: /* stq */
 		__asm__ __volatile__(
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 9acbeba832c0..dcaa44e408ac 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -88,6 +88,8 @@
 
 	arcpct: pct {
 		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
 	};
 
 	/* TIMER0 with interrupt for clockevent */
@@ -208,7 +210,7 @@
 			reg = <0x8000 0x2000>;
 			interrupts = <10>;
 			interrupt-names = "macirq";
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 			snps,pbl = <32>;
 			snps,multicast-filter-bins = <256>;
 			clocks = <&gmacclk>;
@@ -226,7 +228,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "snps,dwmac-mdio";
-				phy0: ethernet-phy@0 {
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
 					reg = <0>;
 				};
 			};
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index b747f2ec2928..6147db925248 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -18,10 +18,10 @@
  * vineetg: April 2010
  *  -Switched pgtable_t from being struct page * to unsigned long
  *      =Needed so that Page Table allocator (pte_alloc_one) is not forced to
- *       to deal with struct page. Thay way in future we can make it allocate
+ *       deal with struct page. That way in future we can make it allocate
  *       multiple PG Tbls in one Page Frame
  *      =sweet side effect is avoiding calls to ugly page_address( ) from the
- *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate
+ *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate)
  *
  *  Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
index d04837d91b40..03f8b1be0c3a 100644
--- a/arch/arc/kernel/disasm.c
+++ b/arch/arc/kernel/disasm.c
@@ -339,7 +339,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state,
 
 	case op_LDWX_S:	/* LDWX_S c, [b, u6] */
 		state->x = 1;
-		/* intentional fall-through */
+		fallthrough;
 
 	case op_LDW_S:	/* LDW_S c, [b, u6] */
 		state->zz = 2;
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 661fd842ea97..79849f37e782 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, has_interrupts;
+	int i, has_interrupts, irq;
 	int counter_size;	/* in bits */
 
 	union cc_name {
@@ -637,13 +637,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.attr_groups	= arc_pmu->attr_groups,
 	};
 
-	if (has_interrupts) {
-		int irq = platform_get_irq(pdev, 0);
-
-		if (irq < 0) {
-			pr_err("Cannot get IRQ number for the platform\n");
-			return -ENODEV;
-		}
+	if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) {
 
 		arc_pmu->irq = irq;
 
@@ -652,9 +646,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 				   this_cpu_ptr(&arc_pmu_cpu));
 
 		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
-
-	} else
+	} else {
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	}
 
 	/*
 	 * perf parser doesn't really like '-' symbol in events name, so let's
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 3d57ed0d8535..8222f8c54690 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -321,7 +321,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs)
 			regs->r0 = -EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 
 	case -ERESTARTNOINTR:
 		/*
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 28e8bf04b253..a331bb5d8319 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,44 +18,37 @@
 
 #define ARC_PATH_MAX	256
 
-/*
- * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
- *   -Prints 3 regs per line and a CR.
- *   -To continue, callee regs right after scratch, special handling of CR
- */
-static noinline void print_reg_file(long *reg_rev, int start_num)
+static noinline void print_regs_scratch(struct pt_regs *regs)
 {
-	unsigned int i;
-	char buf[512];
-	int n = 0, len = sizeof(buf);
-
-	for (i = start_num; i < start_num + 13; i++) {
-		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
-			       i, (unsigned long)*reg_rev);
-
-		if (((i + 1) % 3) == 0)
-			n += scnprintf(buf + n, len - n, "\n");
-
-		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
-		if (is_isa_arcv2() && start_num == 0)
-			reg_rev++;
-		else
-			reg_rev--;
-	}
-
-	if (start_num != 0)
-		n += scnprintf(buf + n, len - n, "\n\n");
+	pr_cont("BTA: 0x%08lx\n SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
+	pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+		regs->lp_start, regs->lp_end, regs->lp_count);
 
-	/* To continue printing callee regs on same line as scratch regs */
-	if (start_num == 0)
-		pr_info("%s", buf);
-	else
-		pr_cont("%s\n", buf);
+	pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n"	\
+		"r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n"	\
+		"r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n"	\
+		"r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n"	\
+		"r12: 0x%08lx\t",
+		regs->r0, regs->r1, regs->r2,
+		regs->r3, regs->r4, regs->r5,
+		regs->r6, regs->r7, regs->r8,
+		regs->r9, regs->r10, regs->r11,
+		regs->r12);
 }
 
-static void show_callee_regs(struct callee_regs *cregs)
+static void print_regs_callee(struct callee_regs *regs)
 {
-	print_reg_file(&(cregs->r13), 13);
+	pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n"			\
+		"r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n"	\
+		"r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n"	\
+		"r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n"	\
+		"r24: 0x%08lx\tr25: 0x%08lx\n",
+		regs->r13, regs->r14,
+		regs->r15, regs->r16, regs->r17,
+		regs->r18, regs->r19, regs->r20,
+		regs->r21, regs->r22, regs->r23,
+		regs->r24, regs->r25);
 }
 
 static void print_task_path_n_nm(struct task_struct *tsk)
@@ -175,7 +168,7 @@ static void show_ecr_verbose(struct pt_regs *regs)
 void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct callee_regs *cregs;
+	struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg;
 
 	/*
 	 * generic code calls us with preemption disabled, but some calls
@@ -204,25 +197,15 @@ void show_regs(struct pt_regs *regs)
 			STS_BIT(regs, A2), STS_BIT(regs, A1),
 			STS_BIT(regs, E2), STS_BIT(regs, E1));
 #else
-	pr_cont(" [%2s%2s%2s%2s]",
+	pr_cont(" [%2s%2s%2s%2s]   ",
 			STS_BIT(regs, IE),
 			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
 			STS_BIT(regs, DE), STS_BIT(regs, AE));
 #endif
-	pr_cont("  BTA: 0x%08lx\n  SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
-		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
-	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
-		regs->lp_start, regs->lp_end, regs->lp_count);
-
-	/* print regs->r0 thru regs->r12
-	 * Sequential printing was generating horrible code
-	 */
-	print_reg_file(&(regs->r0), 0);
 
-	/* If Callee regs were saved, display them too */
-	cregs = (struct callee_regs *)current->thread.callee_reg;
+	print_regs_scratch(regs);
 	if (cregs)
-		show_callee_regs(cregs);
+		print_regs_callee(cregs);
 
 	preempt_disable();
 }
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index f87758a6851b..74ad4256022e 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -572,7 +572,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end,
 #else
 		BUILD_BUG_ON(sizeof(u32) != sizeof(value));
 #endif
-		/* Fall through */
+		fallthrough;
 	case DW_EH_PE_native:
 		if (end < (const void *)(ptr.pul + 1))
 			return 0;
@@ -827,7 +827,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc,
 			case DW_CFA_def_cfa:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset:
 				state->cfa.offs = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa_offset: 0x%lx ",
@@ -835,7 +835,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc,
 				break;
 			case DW_CFA_def_cfa_sf:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset_sf:
 				state->cfa.offs = get_sleb128(&ptr.p8, end)
 				    * state->dataAlign;
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index f886ac69d8ad..3a35b82a718e 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -26,8 +26,8 @@ static unsigned long low_mem_sz;
 
 #ifdef CONFIG_HIGHMEM
 static unsigned long min_high_pfn, max_high_pfn;
-static u64 high_mem_start;
-static u64 high_mem_sz;
+static phys_addr_t high_mem_start;
+static phys_addr_t high_mem_sz;
 #endif
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -69,6 +69,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 		high_mem_sz = size;
 		in_use = 1;
 		memblock_add_node(base, size, 1);
+		memblock_reserve(base, size);
 #endif
 	}
 
@@ -157,7 +158,7 @@ void __init setup_arch_memory(void)
 	min_high_pfn = PFN_DOWN(high_mem_start);
 	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
 
-	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
+	max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn;
 
 	high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
 	kmap_init();
@@ -166,22 +167,26 @@ void __init setup_arch_memory(void)
 	free_area_init(max_zone_pfn);
 }
 
-/*
- * mem_init - initializes memory
- *
- * Frees up bootmem
- * Calculates and displays memory available/used
- */
-void __init mem_init(void)
+static void __init highmem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
 	unsigned long tmp;
 
-	reset_all_zones_managed_pages();
+	memblock_free(high_mem_start, high_mem_sz);
 	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
 		free_highmem_page(pfn_to_page(tmp));
 #endif
+}
 
+/*
+ * mem_init - initializes memory
+ *
+ * Frees up bootmem
+ * Calculates and displays memory available/used
+ */
+void __init mem_init(void)
+{
 	memblock_free_all();
+	highmem_init();
 	mem_init_print_info(NULL);
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index a4a61531c7fb..77712c5ffe84 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -33,7 +33,6 @@
 #define CTOP_AUX_DPC				(CTOP_AUX_BASE + 0x02C)
 #define CTOP_AUX_LPC				(CTOP_AUX_BASE + 0x030)
 #define CTOP_AUX_EFLAGS				(CTOP_AUX_BASE + 0x080)
-#define CTOP_AUX_IACK				(CTOP_AUX_BASE + 0x088)
 #define CTOP_AUX_GPA1				(CTOP_AUX_BASE + 0x08C)
 #define CTOP_AUX_UDMC				(CTOP_AUX_BASE + 0x300)
 
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index cbebed5f050e..e8df458aad39 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -217,7 +217,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 0346ea621f0f..c846fa3c244d 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -284,7 +284,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 2d9b4dd05830..0016720ce530 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -488,7 +488,7 @@
 	};
 
 	spi@18029200 {
-		compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+		compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 		reg = <0x18029200 0x184>,
 		      <0x18029000 0x124>,
 		      <0x1811b408 0x004>,
diff --git a/arch/arm/boot/dts/imx6q-logicpd.dts b/arch/arm/boot/dts/imx6q-logicpd.dts
index 7a3d1d3e54a9..8f94364ba484 100644
--- a/arch/arm/boot/dts/imx6q-logicpd.dts
+++ b/arch/arm/boot/dts/imx6q-logicpd.dts
@@ -13,7 +13,7 @@
 
 	backlight: backlight-lvds {
 		compatible = "pwm-backlight";
-		pwms = <&pwm3 0 20000>;
+		pwms = <&pwm3 0 20000 0>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
 		default-brightness-level = <6>;
 		power-supply = <&reg_lcd>;
diff --git a/arch/arm/boot/dts/imx6q-prtwd2.dts b/arch/arm/boot/dts/imx6q-prtwd2.dts
index dffafbcaa7af..349959d38020 100644
--- a/arch/arm/boot/dts/imx6q-prtwd2.dts
+++ b/arch/arm/boot/dts/imx6q-prtwd2.dts
@@ -30,7 +30,7 @@
 	};
 
 	/* PRTWD2 rev 1 bitbang I2C for Ethernet Switch */
-	i2c@4 {
+	i2c {
 		compatible = "i2c-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c4>;
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index 7705285d9e3c..4d01c3300b97 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -22,8 +22,6 @@
 
 	gpio-keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		user-pb {
 			label = "user_pb";
diff --git a/arch/arm/boot/dts/imx6sx-pinfunc.h b/arch/arm/boot/dts/imx6sx-pinfunc.h
index 0b02c7e60c17..f4dc46207954 100644
--- a/arch/arm/boot/dts/imx6sx-pinfunc.h
+++ b/arch/arm/boot/dts/imx6sx-pinfunc.h
@@ -1026,7 +1026,7 @@
 #define MX6SX_PAD_QSPI1B_DQS__SIM_M_HADDR_15                      0x01B0 0x04F8 0x0000 0x7 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__QSPI1_B_SCLK                       0x01B4 0x04FC 0x0000 0x0 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__UART3_DCE_RX                       0x01B4 0x04FC 0x0840 0x1 0x4
-#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x0 0x0
+#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x1 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__ECSPI3_SCLK                        0x01B4 0x04FC 0x0730 0x2 0x1
 #define MX6SX_PAD_QSPI1B_SCLK__ESAI_RX_HF_CLK                     0x01B4 0x04FC 0x0780 0x3 0x2
 #define MX6SX_PAD_QSPI1B_SCLK__CSI1_DATA_16                       0x01B4 0x04FC 0x06DC 0x4 0x1
diff --git a/arch/arm/boot/dts/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
index e5e20b07f184..7cb6153fc650 100644
--- a/arch/arm/boot/dts/imx7d-zii-rmu2.dts
+++ b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
@@ -58,7 +58,7 @@
 			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
 	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
 	assigned-clock-rates = <0>, <100000000>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&fec1_phy>;
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi
index 367439639da9..b7ea37ad4e55 100644
--- a/arch/arm/boot/dts/imx7ulp.dtsi
+++ b/arch/arm/boot/dts/imx7ulp.dtsi
@@ -394,7 +394,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLC>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 0 32>;
+			gpio-ranges = <&iomuxc1 0 0 20>;
 		};
 
 		gpio_ptd: gpio@40af0000 {
@@ -408,7 +408,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLD>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 32 32>;
+			gpio-ranges = <&iomuxc1 0 32 12>;
 		};
 
 		gpio_pte: gpio@40b00000 {
@@ -422,7 +422,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLE>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 64 32>;
+			gpio-ranges = <&iomuxc1 0 64 16>;
 		};
 
 		gpio_ptf: gpio@40b10000 {
@@ -436,7 +436,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLF>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 96 32>;
+			gpio-ranges = <&iomuxc1 0 96 20>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
index 100396f6c2fe..395e05f10d36 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
@@ -51,6 +51,8 @@
 
 &mcbsp2 {
 	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 };
 
 &charger {
@@ -102,35 +104,18 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
-	lcd0: display@0 {
-		compatible = "panel-dpi";
-		label = "28";
-		status = "okay";
-		/* default-on; */
+	lcd0: display {
+		/* This isn't the exact LCD, but the timings meet spec */
+		compatible = "logicpd,type28";
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcd_enable_pin>;
-		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
+		backlight = <&bl>;
+		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
 			};
 		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <2>;
-			vsync-len = <11>;
-			hsync-active = <1>;
-			vsync-active = <1>;
-			de-active = <1>;
-			pixelclk-active = <0>;
-		};
 	};
 
 	bl: backlight {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
index 381f0e82bb70..b0f6613e6d54 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
@@ -81,6 +81,8 @@
 };
 
 &mcbsp2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 069af9a19bb6..827373ef1a54 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -182,7 +182,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x1550000 0x0 0x10000>,
-			      <0x0 0x40000000 0x0 0x40000000>;
+			      <0x0 0x40000000 0x0 0x20000000>;
 			reg-names = "QuadSPI", "QuadSPI-memory";
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 			clock-names = "qspi_en", "qspi";
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 5da9cff7a53c..a82c96258a93 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -488,11 +488,11 @@
 					};
 				};
 
-				target-module@5000 {
+				target-module@4000 {
 					compatible = "ti,sysc-omap2", "ti,sysc";
-					reg = <0x5000 0x4>,
-					      <0x5010 0x4>,
-					      <0x5014 0x4>;
+					reg = <0x4000 0x4>,
+					      <0x4010 0x4>,
+					      <0x4014 0x4>;
 					reg-names = "rev", "sysc", "syss";
 					ti,sysc-sidle = <SYSC_IDLE_FORCE>,
 							<SYSC_IDLE_NO>,
@@ -504,7 +504,7 @@
 					ti,syss-mask = <1>;
 					#address-cells = <1>;
 					#size-cells = <1>;
-					ranges = <0 0x5000 0x1000>;
+					ranges = <0 0x4000 0x1000>;
 
 					dsi1: encoder@0 {
 						compatible = "ti,omap5-dsi";
@@ -514,8 +514,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
@@ -545,8 +546,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index fc4abef143a0..0013ec3463c4 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -821,7 +821,7 @@
 		timer3: timer3@ffd00100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>;
-			reg = <0xffd01000 0x100>;
+			reg = <0xffd00100 0x100>;
 			clocks = <&l4_sys_free_clk>;
 			clock-names = "timer";
 			resets = <&rst L4SYSTIMER1_RESET>;
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 0fe03aa0367f..2259d11af721 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -495,7 +495,7 @@
 			};
 
 			ocotp: ocotp@400a5000 {
-				compatible = "fsl,vf610-ocotp";
+				compatible = "fsl,vf610-ocotp", "syscon";
 				reg = <0x400a5000 0x1000>;
 				clocks = <&clks VF610_CLK_OCOTP>;
 			};
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index a9755c501bec..b06e537d5149 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -1,13 +1,11 @@
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
@@ -15,19 +13,17 @@ CONFIG_ARCH_INTEGRATOR=y
 CONFIG_ARCH_INTEGRATOR_AP=y
 CONFIG_INTEGRATOR_IMPD1=y
 CONFIG_ARCH_INTEGRATOR_CP=y
-CONFIG_PCI=y
-CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 # CONFIG_ATAGS is not set
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPUFREQ_DT=y
-CONFIG_CMA=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -37,6 +33,7 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
+CONFIG_PCI=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_AFS_PARTS=y
@@ -52,9 +49,12 @@ CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_NETDEVICES=y
 CONFIG_E100=y
 CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
+CONFIG_KEYBOARD_GPIO=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_DRM=y
+CONFIG_DRM_DISPLAY_CONNECTOR=y
 CONFIG_DRM_SIMPLE_BRIDGE=y
 CONFIG_DRM_PL111=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 7fff88e61252..7a4853b1213a 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -547,7 +547,7 @@ static int arch_build_bp_info(struct perf_event *bp,
 		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
@@ -612,12 +612,12 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 		/* Allow halfword watchpoints and breakpoints. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	case 3:
 		/* Allow single byte watchpoint. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -884,7 +884,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		break;
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
-		/* Fall through */
+		fallthrough;
 	case ARM_ENTRY_SYNC_WATCHPOINT:
 		watchpoint_handler(addr, fsr, regs);
 		break;
@@ -933,7 +933,7 @@ static bool core_has_os_save_restore(void)
 		ARM_DBG_READ(c1, c1, 4, oslsr);
 		if (oslsr & ARM_OSLSR_OSLM0)
 			return true;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index c9dc912b83f0..c1892f733f20 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -596,7 +596,7 @@ static int do_signal(struct pt_regs *regs, int syscall)
 		switch (retval) {
 		case -ERESTART_RESTARTBLOCK:
 			restart -= 2;
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
diff --git a/arch/arm/mach-ep93xx/crunch.c b/arch/arm/mach-ep93xx/crunch.c
index 1c05c5bf7e5c..757032d82f63 100644
--- a/arch/arm/mach-ep93xx/crunch.c
+++ b/arch/arm/mach-ep93xx/crunch.c
@@ -49,7 +49,7 @@ static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t)
 		 * FALLTHROUGH: Ensure we don't try to overwrite our newly
 		 * initialised state information on the first fault.
 		 */
-		/* Fall through */
+		fallthrough;
 
 	case THREAD_NOTIFY_EXIT:
 		crunch_task_release(thread);
diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c
index 2d86381e152d..7a6f74c32d42 100644
--- a/arch/arm/mach-mmp/pm-mmp2.c
+++ b/arch/arm/mach-mmp/pm-mmp2.c
@@ -123,19 +123,19 @@ void mmp2_pm_enter_lowpower_mode(int state)
 	case POWER_MODE_SYS_SLEEP:
 		apcr |= MPMU_PCR_PJ_SLPEN;		/* set the SLPEN bit */
 		apcr |= MPMU_PCR_PJ_VCTCXOSD;		/* set VCTCXOSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CHIP_SLEEP:
 		apcr |= MPMU_PCR_PJ_SLPEN;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_SLEEP:
 		apcr |= MPMU_PCR_PJ_APBSD;		/* set APBSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_IDLE:
 		apcr |= MPMU_PCR_PJ_AXISD;		/* set AXISDD bit */
 		apcr |= MPMU_PCR_PJ_DDRCORSD;		/* set DDRCORSD bit */
 		idle_cfg |= APMU_PJ_IDLE_CFG_PJ_PWRDWN;	/* PJ power down */
 		apcr |= MPMU_PCR_PJ_SPSD;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_EXTIDLE:
 		idle_cfg |= APMU_PJ_IDLE_CFG_PJ_IDLE;	/* set the IDLE bit */
 		idle_cfg &= ~APMU_PJ_IDLE_CFG_ISO_MODE_CNTRL_MASK;
diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c
index 69ebe18ff209..1d71d73c1862 100644
--- a/arch/arm/mach-mmp/pm-pxa910.c
+++ b/arch/arm/mach-mmp/pm-pxa910.c
@@ -145,23 +145,23 @@ void pxa910_pm_enter_lowpower_mode(int state)
 	case POWER_MODE_UDR:
 		/* only shutdown APB in UDR */
 		apcr |= MPMU_APCR_STBYEN | MPMU_APCR_APBSD;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_SYS_SLEEP:
 		apcr |= MPMU_APCR_SLPEN;		/* set the SLPEN bit */
 		apcr |= MPMU_APCR_VCTCXOSD;		/* set VCTCXOSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_SLEEP:
 		apcr |= MPMU_APCR_DDRCORSD;		/* set DDRCORSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_IDLE:
 		apcr |= MPMU_APCR_AXISD;		/* set AXISDD bit */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_EXTIDLE:
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_IDLE;
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWRDWN;
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWR_SW(3)
 			| APMU_MOH_IDLE_CFG_MOH_L2_PWR_SW(3);
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_INTIDLE:
 		break;
 	}
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 1d119b974f5f..59755b5a1ad7 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -396,7 +396,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "3.1";
 			break;
 		case 7:
-		/* FALLTHROUGH */
 		default:
 			/* Use the latest known revision as default */
 			omap_revision = OMAP3430_REV_ES3_1_2;
@@ -416,7 +415,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "1.0";
 			break;
 		case 1:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM35XX_REV_ES1_1;
 			cpu_rev = "1.1";
@@ -435,7 +433,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "1.1";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = OMAP3630_REV_ES1_2;
 			cpu_rev = "1.2";
@@ -456,7 +453,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "2.0";
 			break;
 		case 3:
-			/* FALLTHROUGH */
 		default:
 			omap_revision = TI8168_REV_ES2_1;
 			cpu_rev = "2.1";
@@ -473,7 +469,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "2.0";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM335X_REV_ES2_1;
 			cpu_rev = "2.1";
@@ -491,7 +486,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "1.1";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM437X_REV_ES1_2;
 			cpu_rev = "1.2";
@@ -502,7 +496,6 @@ void __init omap3xxx_check_revision(void)
 	case 0xb968:
 		switch (rev) {
 		case 0:
-		/* FALLTHROUGH */
 		case 1:
 			omap_revision = TI8148_REV_ES1_0;
 			cpu_rev = "1.0";
@@ -512,7 +505,6 @@ void __init omap3xxx_check_revision(void)
 			cpu_rev = "2.0";
 			break;
 		case 3:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = TI8148_REV_ES2_1;
 			cpu_rev = "2.1";
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index 54aff33e55e6..bfa5e1b8dba7 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -74,7 +74,7 @@ static struct powerdomain *_get_pwrdm(struct device *dev)
 		return pwrdm;
 
 	clk = of_clk_get(dev->of_node->parent, 0);
-	if (!clk) {
+	if (IS_ERR(clk)) {
 		dev_err(dev, "no fck found\n");
 		return NULL;
 	}
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 6b4548f3b57f..fc7bb2ca1672 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -240,7 +240,7 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
 		omap_auxdata_legacy_init(dev);
-		/* fall through */
+		fallthrough;
 	default:
 		od = to_omap_device(pdev);
 		if (od)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 6df395fff971..f5dfddf492e2 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -298,11 +298,7 @@ static void omap3_pm_idle(void)
 	if (omap_irq_pending())
 		return;
 
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
-
 	omap_sram_idle();
-
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index d13344b2ddcd..87cb47220e82 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -624,7 +624,7 @@ static void __init dns323_init(void)
 		 dns323ab_leds[0].active_low = 1;
 		 gpio_request(DNS323_GPIO_LED_POWER1, "Power Led Enable");
 		 gpio_direction_output(DNS323_GPIO_LED_POWER1, 0);
-		/* Fall through */
+		fallthrough;
 	case DNS323_REV_B1:
 		i2c_register_board_info(0, dns323ab_i2c_devices,
 				ARRAY_SIZE(dns323ab_i2c_devices));
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index ea2c84214bac..d23970bd638d 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -46,7 +46,7 @@ static int __init parse_tag_acorn(const struct tag *tag)
 	switch (tag->u.acorn.vram_pages) {
 	case 512:
 		vram_size += PAGE_SIZE * 256;
-		/* Fall through - ??? */
+		fallthrough;	/* ??? */
 	case 256:
 		vram_size += PAGE_SIZE * 256;
 	default:
diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c
index 76a65df42d10..d5c805adf7a8 100644
--- a/arch/arm/mach-tegra/reset.c
+++ b/arch/arm/mach-tegra/reset.c
@@ -70,7 +70,7 @@ static void __init tegra_cpu_reset_handler_enable(void)
 	switch (err) {
 	case -ENOSYS:
 		tegra_cpu_reset_handler_set(reset_address);
-		/* fall through */
+		fallthrough;
 	case 0:
 		is_enabled = true;
 		break;
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index f4bfc1cac91a..ea81e89e7740 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -694,7 +694,7 @@ thumb2arm(u16 tinstr)
 			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
 			    (tinstr & 255);		/* register_list */
 		}
-		/* Else, fall through - for illegal instruction case */
+		fallthrough;	/* for illegal instruction case */
 
 	default:
 		return BAD_INSTR;
@@ -750,7 +750,7 @@ do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
 	case 0xe8e0:
 	case 0xe9e0:
 		poffset->un = (tinst2 & 0xff) << 2;
-		/* Fall through */
+		fallthrough;
 
 	case 0xe940:
 	case 0xe9c0:
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index c0fbfca5da8b..114c05ab4dd9 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -71,7 +71,7 @@ static void cpu_v7_spectre_init(void)
 		/* Other ARM CPUs require no workaround */
 		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)
 			break;
-		/* fallthrough */
+		fallthrough;
 		/* Cortex A57/A72 require firmware workaround */
 	case ARM_CPU_PART_CORTEX_A57:
 	case ARM_CPU_PART_CORTEX_A72: {
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index b2e9e822426f..1eb59003bdec 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -309,14 +309,14 @@ void omap_set_dma_src_burst_mode(int lch, enum omap_dma_burst_mode burst_mode)
 		 * not supported by current hardware on OMAP1
 		 * w |= (0x03 << 7);
 		 */
-		/* fall through */
+		fallthrough;
 	case OMAP_DMA_DATA_BURST_16:
 		if (dma_omap2plus()) {
 			burst = 0x3;
 			break;
 		}
 		/* OMAP1 don't support burst 16 */
-		/* fall through */
+		fallthrough;
 	default:
 		BUG();
 	}
@@ -393,7 +393,7 @@ void omap_set_dma_dest_burst_mode(int lch, enum omap_dma_burst_mode burst_mode)
 			break;
 		}
 		/* OMAP1 don't support burst 16 */
-		/* fall through */
+		fallthrough;
 	default:
 		printk(KERN_ERR "Invalid DMA burst mode\n");
 		BUG();
diff --git a/arch/arm/probes/decode.c b/arch/arm/probes/decode.c
index fe81a9c21f2d..c84053a81358 100644
--- a/arch/arm/probes/decode.c
+++ b/arch/arm/probes/decode.c
@@ -307,7 +307,7 @@ static bool __kprobes decode_regs(probes_opcode_t *pinsn, u32 regs, bool modify)
 		case REG_TYPE_NOPCWB:
 			if (!is_writeback(insn))
 				break; /* No writeback, so any register is OK */
-			/* fall through... */
+			fallthrough;
 		case REG_TYPE_NOPC:
 		case REG_TYPE_NOPCX:
 			/* Reject PC (R15) */
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 90b5bc723c83..feefa2055eba 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -280,7 +280,7 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				/* A nested probe was hit in FIQ, it is a BUG */
 				pr_warn("Unrecoverable kprobe detected.\n");
 				dump_kprobe(p);
-				/* fall through */
+				fallthrough;
 			default:
 				/* impossible cases */
 				BUG();
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 55bc8546d9c7..130569f90c54 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -82,8 +82,8 @@ endif
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
-ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
-branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
+ifeq ($(CONFIG_AS_HAS_PAC), y)
+asm-arch := armv8.3-a
 endif
 endif
 
@@ -91,7 +91,12 @@ KBUILD_CFLAGS += $(branch-prot-flags-y)
 
 ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
 # make sure to pass the newest target architecture to -march.
-KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+asm-arch := armv8.4-a
+endif
+
+ifdef asm-arch
+KBUILD_CFLAGS	+= -Wa,-march=$(asm-arch) \
+		   -DARM64_ASM_ARCH='"$(asm-arch)"'
 endif
 
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
@@ -165,6 +170,8 @@ zinstall install:
 PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
+	$(if $(CONFIG_COMPAT_VDSO), \
+		$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@)
 
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 15f7b0ed3836..39802066232e 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -745,7 +745,7 @@
 		};
 
 		qspi: spi@66470200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+			compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x66470200 0x184>,
 				<0x66470000 0x124>,
 				<0x67017408 0x004>,
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index a39f0a1723e0..903c0eb61290 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -28,6 +28,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb
 
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr4-evk.dtb
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 9de2aa1c573c..a5154f13a18e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -702,7 +702,7 @@
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_SDMA1_ROOT>,
-					 <&clk IMX8MP_CLK_SDMA1_ROOT>;
+					 <&clk IMX8MP_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index f70435cf9ad5..561fa792fe5a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -423,7 +423,7 @@
 			tmu: tmu@30260000 {
 				compatible = "fsl,imx8mq-tmu";
 				reg = <0x30260000 0x10000>;
-				interrupt = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MQ_CLK_TMU_ROOT>;
 				little-endian;
 				fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
index 1a39e0ef776b..5b9ec032ce8d 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
@@ -686,6 +686,8 @@
 		clocks = <&pericfg CLK_PERI_MSDC30_0_PD>,
 			 <&topckgen CLK_TOP_MSDC50_0_SEL>;
 		clock-names = "source", "hclk";
+		resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>;
+		reset-names = "hrst";
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 34d249d85da7..8eb61dd9921e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -337,8 +337,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03400000 0x0 0x10000>;
 		interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC1>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC1>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC1>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>,
@@ -366,8 +367,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03420000 0x0 0x10000>;
 		interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC2>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC2>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC2>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>,
@@ -390,8 +392,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03440000 0x0 0x10000>;
 		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC3>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC3>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC3>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>,
@@ -416,8 +419,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03460000 0x0 0x10000>;
 		interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC4>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC4>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>,
 				  <&bpmp TEGRA186_CLK_PLLC4_VCO>;
 		assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 48160f48003a..ca5cb6aef5ee 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -460,8 +460,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03400000 0x10000>;
 			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC1>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC1>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			resets = <&bpmp TEGRA194_RESET_SDMMC1>;
 			reset-names = "sdhci";
 			interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>,
@@ -485,8 +486,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03440000 0x10000>;
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC3>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC3>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			resets = <&bpmp TEGRA194_RESET_SDMMC3>;
 			reset-names = "sdhci";
 			interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>,
@@ -511,8 +513,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03460000 0x10000>;
 			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC4>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC4>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>,
 					  <&bpmp TEGRA194_CLK_PLLC4>;
 			assigned-clock-parents =
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 829f786af133..8cca2166a446 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -1194,8 +1194,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0000 0x0 0x200>;
 		interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC1>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC1>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 14>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3", "sdmmc-1v8",
@@ -1222,8 +1223,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0200 0x0 0x200>;
 		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC2>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC2>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 9>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-1v8-drv";
@@ -1239,8 +1241,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0400 0x0 0x200>;
 		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC3>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC3>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 69>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3", "sdmmc-1v8",
@@ -1262,8 +1265,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0600 0x0 0x200>;
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC4>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC4>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 15>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv";
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index 9edfae5944f7..24ef18fe77df 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -417,10 +417,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <56>;
-		ti,sci-rm-range-girq = <0x1>;
+		ti,sci-dev-id = <100>;
+		ti,interrupt-ranges = <0 392 32>;
 	};
 
 	main_navss {
@@ -438,10 +438,11 @@
 			ti,intr-trigger-type = <4>;
 			interrupt-controller;
 			interrupt-parent = <&gic500>;
-			#interrupt-cells = <2>;
+			#interrupt-cells = <1>;
 			ti,sci = <&dmsc>;
-			ti,sci-dst-id = <56>;
-			ti,sci-rm-range-girq = <0x0>, <0x2>;
+			ti,sci-dev-id = <182>;
+			ti,interrupt-ranges = <0 64 64>,
+					      <64 448 64>;
 		};
 
 		inta_main_udmass: interrupt-controller@33d00000 {
@@ -452,8 +453,7 @@
 			msi-controller;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <179>;
-			ti,sci-rm-range-vint = <0x0>;
-			ti,sci-rm-range-global-event = <0x1>;
+			ti,interrupt-ranges = <0 0 256>;
 		};
 
 		secure_proxy_main: mailbox@32c00000 {
@@ -589,7 +589,7 @@
 				<0x0 0x33000000 0x0 0x40000>;
 			reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target";
 			ti,num-rings = <818>;
-			ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */
+			ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */
 			ti,dma-ring-reset-quirk;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <187>;
@@ -609,11 +609,11 @@
 			ti,sci-dev-id = <188>;
 			ti,ringacc = <&ringacc>;
 
-			ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */
-						<0x2>; /* TX_CHAN */
-			ti,sci-rm-range-rchan = <0x4>, /* RX_HCHAN */
-						<0x5>; /* RX_CHAN */
-			ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */
+			ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */
+						<0xd>; /* TX_CHAN */
+			ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */
+						<0xa>; /* RX_CHAN */
+			ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */
 		};
 
 		cpts@310d0000 {
@@ -622,7 +622,7 @@
 			reg-names = "cpts";
 			clocks = <&main_cpts_mux>;
 			clock-names = "cpts";
-			interrupts-extended = <&intr_main_navss 163 0>;
+			interrupts-extended = <&intr_main_navss 391>;
 			interrupt-names = "cpts";
 			ti,cpts-periodic-outputs = <6>;
 			ti,cpts-ext-ts-inputs = <8>;
@@ -645,8 +645,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_main_gpio>;
-		interrupts = <57 256>, <57 257>, <57 258>, <57 259>, <57 260>,
-				<57 261>;
+		interrupts = <192>, <193>, <194>, <195>, <196>, <197>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <96>;
@@ -661,8 +660,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_main_gpio>;
-		interrupts = <58 256>, <58 257>, <58 258>, <58 259>, <58 260>,
-				<58 261>;
+		interrupts = <200>, <201>, <202>, <203>, <204>, <205>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <90>;
diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
index 8c1abcfe0860..51ca4b4d4c21 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
@@ -134,7 +134,7 @@
 				<0x0 0x2a500000 0x0 0x40000>;
 			reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target";
 			ti,num-rings = <286>;
-			ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */
+			ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */
 			ti,dma-ring-reset-quirk;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <195>;
@@ -154,11 +154,11 @@
 			ti,sci-dev-id = <194>;
 			ti,ringacc = <&mcu_ringacc>;
 
-			ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */
-						<0x2>; /* TX_CHAN */
-			ti,sci-rm-range-rchan = <0x3>, /* RX_HCHAN */
-						<0x4>; /* RX_CHAN */
-			ti,sci-rm-range-rflow = <0x5>; /* GP RFLOW */
+			ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */
+						<0xd>; /* TX_CHAN */
+			ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */
+						<0xa>; /* RX_CHAN */
+			ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
index 5f55b9e82cf1..a1ffe88d9664 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
@@ -74,10 +74,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <56>;
-		ti,sci-rm-range-girq = <0x4>;
+		ti,sci-dev-id = <156>;
+		ti,interrupt-ranges = <0 712 16>;
 	};
 
 	wkup_gpio0: wkup_gpio0@42110000 {
@@ -86,7 +86,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_wkup_gpio>;
-		interrupts = <59 128>, <59 129>, <59 130>, <59 131>;
+		interrupts = <60>, <61>, <62>, <63>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <56>;
diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
index 611e66207010..b8a8a0fcb8af 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
@@ -384,7 +384,7 @@
 };
 
 &mailbox0_cluster0 {
-	interrupts = <164 0>;
+	interrupts = <436>;
 
 	mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 {
 		ti,mbox-tx = <1 0 0>;
@@ -393,7 +393,7 @@
 };
 
 &mailbox0_cluster1 {
-	interrupts = <165 0>;
+	interrupts = <432>;
 
 	mbox_mcu_r5fss0_core1: mbox-mcu-r5fss0-core1 {
 		ti,mbox-tx = <1 0 0>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
index 8bc1e6ecc50e..e8fc01d97ada 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
@@ -287,7 +287,7 @@
 };
 
 &mailbox0_cluster0 {
-	interrupts = <214 0>;
+	interrupts = <436>;
 
 	mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -301,7 +301,7 @@
 };
 
 &mailbox0_cluster1 {
-	interrupts = <215 0>;
+	interrupts = <432>;
 
 	mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -315,7 +315,7 @@
 };
 
 &mailbox0_cluster2 {
-	interrupts = <216 0>;
+	interrupts = <428>;
 
 	mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -329,7 +329,7 @@
 };
 
 &mailbox0_cluster3 {
-	interrupts = <217 0>;
+	interrupts = <424>;
 
 	mbox_c66_0: mbox-c66-0 {
 		ti,mbox-rx = <0 0 0>;
@@ -343,7 +343,7 @@
 };
 
 &mailbox0_cluster4 {
-	interrupts = <218 0>;
+	interrupts = <420>;
 
 	mbox_c71_0: mbox-c71-0 {
 		ti,mbox-rx = <0 0 0>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index d14060207f00..12ceea9b3c9a 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -80,10 +80,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <14>;
-		ti,sci-rm-range-girq = <0x1>;
+		ti,sci-dev-id = <131>;
+		ti,interrupt-ranges = <8 392 56>;
 	};
 
 	main_navss {
@@ -101,10 +101,12 @@
 			ti,intr-trigger-type = <4>;
 			interrupt-controller;
 			interrupt-parent = <&gic500>;
-			#interrupt-cells = <2>;
+			#interrupt-cells = <1>;
 			ti,sci = <&dmsc>;
-			ti,sci-dst-id = <14>;
-			ti,sci-rm-range-girq = <0>, <2>;
+			ti,sci-dev-id = <213>;
+			ti,interrupt-ranges = <0 64 64>,
+					      <64 448 64>,
+					      <128 672 64>;
 		};
 
 		main_udmass_inta: interrupt-controller@33d00000 {
@@ -115,8 +117,7 @@
 			msi-controller;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <209>;
-			ti,sci-rm-range-vint = <0xa>;
-			ti,sci-rm-range-global-event = <0xd>;
+			ti,interrupt-ranges = <0 0 256>;
 		};
 
 		secure_proxy_main: mailbox@32c00000 {
@@ -296,7 +297,7 @@
 			reg-names = "cpts";
 			clocks = <&k3_clks 201 1>;
 			clock-names = "cpts";
-			interrupts-extended = <&main_navss_intr 201 0>;
+			interrupts-extended = <&main_navss_intr 391>;
 			interrupt-names = "cpts";
 			ti,cpts-periodic-outputs = <6>;
 			ti,cpts-ext-ts-inputs = <8>;
@@ -688,8 +689,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <105 0>, <105 1>, <105 2>, <105 3>,
-			     <105 4>, <105 5>, <105 6>, <105 7>;
+		interrupts = <256>, <257>, <258>, <259>,
+			     <260>, <261>, <262>, <263>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -705,7 +706,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <106 0>, <106 1>, <106 2>;
+		interrupts = <288>, <289>, <290>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -721,8 +722,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <107 0>, <107 1>, <107 2>, <107 3>,
-			     <107 4>, <107 5>, <107 6>, <107 7>;
+		interrupts = <264>, <265>, <266>, <267>,
+			     <268>, <269>, <270>, <271>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -738,7 +739,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <108 0>, <108 1>, <108 2>;
+		interrupts = <292>, <293>, <294>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -754,8 +755,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <109 0>, <109 1>, <109 2>, <109 3>,
-			     <109 4>, <109 5>, <109 6>, <109 7>;
+		interrupts = <272>, <273>, <274>, <275>,
+			     <276>, <277>, <278>, <279>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -771,7 +772,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <110 0>, <110 1>, <110 2>;
+		interrupts = <296>, <297>, <298>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -787,8 +788,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <111 0>, <111 1>, <111 2>, <111 3>,
-			     <111 4>, <111 5>, <111 6>, <111 7>;
+		interrupts = <280>, <281>, <282>, <283>,
+			     <284>, <285>, <286>, <287>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -804,7 +805,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <112 0>, <112 1>, <112 2>;
+		interrupts = <300>, <301>, <302>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
index 30a735bcd0c8..c4a48e8d420a 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
@@ -101,10 +101,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <14>;
-		ti,sci-rm-range-girq = <0x5>;
+		ti,sci-dev-id = <137>;
+		ti,interrupt-ranges = <16 960 16>;
 	};
 
 	wkup_gpio0: gpio@42110000 {
@@ -113,8 +113,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&wkup_gpio_intr>;
-		interrupts = <113 0>, <113 1>, <113 2>,
-			     <113 3>, <113 4>, <113 5>;
+		interrupts = <103>, <104>, <105>, <106>, <107>, <108>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <84>;
@@ -130,8 +129,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&wkup_gpio_intr>;
-		interrupts = <114 0>, <114 1>, <114 2>,
-			     <114 3>, <114 4>, <114 5>;
+		interrupts = <112>, <113>, <114>, <115>, <116>, <117>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <84>;
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 9174ddc76bdc..3ec99f13c259 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -13,6 +13,7 @@
  */
 
 #include <dt-bindings/power/xlnx-zynqmp-power.h>
+#include <dt-bindings/reset/xlnx-zynqmp-resets.h>
 
 / {
 	compatible = "xlnx,zynqmp";
@@ -558,6 +559,15 @@
 			};
 		};
 
+		psgtr: phy@fd400000 {
+			compatible = "xlnx,zynqmp-psgtr-v1.1";
+			status = "disabled";
+			reg = <0x0 0xfd400000 0x0 0x40000>,
+			      <0x0 0xfd3d0000 0x0 0x1000>;
+			reg-names = "serdes", "siou";
+			#phy-cells = <4>;
+		};
+
 		rtc: rtc@ffa60000 {
 			compatible = "xlnx,zynqmp-rtc";
 			status = "disabled";
@@ -601,7 +611,7 @@
 			power-domains = <&zynqmp_firmware PD_SD_1>;
 		};
 
-		smmu: smmu@fd800000 {
+		smmu: iommu@fd800000 {
 			compatible = "arm,mmu-500";
 			reg = <0x0 0xfd800000 0x0 0x20000>;
 			status = "disabled";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index e0f33826819f..6d04b9577b0b 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -724,6 +724,17 @@ CONFIG_USB_GADGET=y
 CONFIG_USB_RENESAS_USBHS_UDC=m
 CONFIG_USB_RENESAS_USB3=m
 CONFIG_USB_TEGRA_XUDC=m
+CONFIG_USB_CONFIGFS=m
+CONFIG_USB_CONFIGFS_SERIAL=y
+CONFIG_USB_CONFIGFS_ACM=y
+CONFIG_USB_CONFIGFS_OBEX=y
+CONFIG_USB_CONFIGFS_NCM=y
+CONFIG_USB_CONFIGFS_ECM=y
+CONFIG_USB_CONFIGFS_ECM_SUBSET=y
+CONFIG_USB_CONFIGFS_RNDIS=y
+CONFIG_USB_CONFIGFS_EEM=y
+CONFIG_USB_CONFIGFS_MASS_STORAGE=y
+CONFIG_USB_CONFIGFS_F_FS=y
 CONFIG_TYPEC=m
 CONFIG_TYPEC_TCPM=m
 CONFIG_TYPEC_FUSB302=m
@@ -914,6 +925,7 @@ CONFIG_ARCH_TEGRA_194_SOC=y
 CONFIG_ARCH_K3_AM6_SOC=y
 CONFIG_ARCH_K3_J721E_SOC=y
 CONFIG_TI_SCI_PM_DOMAINS=y
+CONFIG_EXTCON_PTN5150=m
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_EXTCON_USBC_CROS_EC=y
 CONFIG_IIO=y
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
index 51a7ce87cdfe..6fb2e6bcc392 100644
--- a/arch/arm64/include/asm/compiler.h
+++ b/arch/arm64/include/asm/compiler.h
@@ -2,6 +2,12 @@
 #ifndef __ASM_COMPILER_H
 #define __ASM_COMPILER_H
 
+#ifdef ARM64_ASM_ARCH
+#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n"
+#else
+#define ARM64_ASM_PREAMBLE
+#endif
+
 /*
  * The EL0/EL1 pointer bits used by a pointer authentication code.
  * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index aa4b6521ef14..ff328e5bbb75 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -95,6 +95,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return res;
 }
 
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 51c1d9918999..1da8e3dc4455 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -71,11 +71,12 @@
  * IMO:		Override CPSR.I and enable signaling with VI
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
-			 HCR_FMO | HCR_IMO)
+			 HCR_FMO | HCR_IMO | HCR_PTW )
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index fb1a922b31ba..6f98fbd0ac81 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -169,6 +169,34 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 		*__hyp_this_cpu_ptr(sym);				\
 	 })
 
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
 #else /* __ASSEMBLY__ */
 
 .macro hyp_adr_this_cpu reg, sym, tmp
@@ -193,6 +221,21 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
 .endm
 
+/*
+ * KVM extable for unexpected exceptions.
+ * In the same format _asm_extable, but output to a different section so that
+ * it can be mapped to EL2. The KVM version is not sorted. The caller must
+ * ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 65568b23868a..905c2b87e05a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -368,7 +368,6 @@ struct kvm_vcpu_arch {
 
 	/* Guest PV state */
 	struct {
-		u64 steal;
 		u64 last_steal;
 		gpa_t base;
 	} steal;
@@ -473,7 +472,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end);
+			unsigned long start, unsigned long end, unsigned flags);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
@@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index d493174415db..cc3f5a33ff9c 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -28,14 +28,16 @@
  * not. The macros handles invoking the asm with or without the
  * register argument as appropriate.
  */
-#define __TLBI_0(op, arg) asm ("tlbi " #op "\n"				       \
+#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op "\n"				       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op,	       \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
-#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n"			       \
+#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op ", %0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op ", %0",     \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 455966401102..a85174d05473 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -322,7 +322,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 			 */
 			if (memblock_is_map_memory(phys))
 				return (void __iomem *)__phys_to_virt(phys);
-			/* fall through */
+			fallthrough;
 
 		default:
 			if (region->attribute & EFI_MEMORY_WB)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6bd1d3ad037a..c332d49780dc 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
+		.type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU |
+			 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU),
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a389b999482e..6424584be01e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -686,7 +686,7 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
 	case FTR_HIGHER_OR_ZERO_SAFE:
 		if (!cur || !new)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	case FTR_HIGHER_SAFE:
 		ret = new > cur ? new : cur;
 		break;
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 393c6fb1f1cb..d0076c2159e6 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -327,7 +327,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
 		set_bit(ICACHEF_VPIPT, &__icache_flags);
 		break;
 	default:
-		/* Fallthrough */
 	case ICACHE_POLICY_VIPT:
 		/* Assume aliasing */
 		set_bit(ICACHEF_ALIASING, &__icache_flags);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2646178c8329..55af8b504b65 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -170,19 +170,6 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-	.if	\regsize == 32
-	/*
-	 * If we're returning from a 32-bit task on a system affected by
-	 * 1418040 then re-enable userspace access to the virtual counter.
-	 */
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if ARM64_WORKAROUND_1418040
-	mrs	x0, cntkctl_el1
-	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x0
-alternative_else_nop_endif
-#endif
-	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
@@ -294,14 +281,6 @@ alternative_else_nop_endif
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if ARM64_WORKAROUND_1418040
-	mrs	x0, cntkctl_el1
-	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x0
-alternative_else_nop_endif
-#endif
-
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index af234a1e08b7..712e97c03e54 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -257,7 +257,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
 		 * level.
 		 */
 		enable_debug_monitors(dbg_el);
-		/* Fall through */
+		fallthrough;
 	case HW_BREAKPOINT_RESTORE:
 		/* Setup the address register. */
 		write_wb_reg(val_reg, i, info->address);
@@ -541,13 +541,13 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 
-			/* Fallthrough */
+			fallthrough;
 		case 3:
 			/* Allow single byte watchpoint. */
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return -EINVAL;
 		}
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 9e897c500237..8982b68289b7 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -103,6 +103,10 @@ KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
 KVM_NVHE_ALIAS(gic_pmr_sync);
 #endif
 
+/* EL2 exception handling */
+KVM_NVHE_ALIAS(__start___kvm_ex_table);
+KVM_NVHE_ALIAS(__stop___kvm_ex_table);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 0ce3a28e3347..2e224435c024 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -305,8 +305,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			mod->arch.core.plt_shndx = i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt_shndx = i;
-		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-			 !strcmp(secstrings + sechdrs[i].sh_name,
+		else if (!strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
 			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 1cd1a4d0ed30..2a1ad95d9b2c 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -315,21 +315,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		/* MOVW instruction relocations. */
 		case R_AARCH64_MOVW_UABS_G0_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
 					      AARCH64_INSN_IMM_MOVKZ);
@@ -397,7 +397,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_adrp(me, sechdrs, loc, val);
 			if (ovf && ovf != -ERANGE)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 84ec630b8ab5..f1804496b935 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -123,10 +123,8 @@ void arch_cpu_idle(void)
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	cpu_do_idle();
 	local_irq_enable();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -516,6 +514,39 @@ static void entry_task_switch(struct task_struct *next)
 }
 
 /*
+ * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
+ * Assuming the virtual counter is enabled at the beginning of times:
+ *
+ * - disable access when switching from a 64bit task to a 32bit task
+ * - enable access when switching from a 32bit task to a 64bit task
+ */
+static void erratum_1418040_thread_switch(struct task_struct *prev,
+					  struct task_struct *next)
+{
+	bool prev32, next32;
+	u64 val;
+
+	if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
+	      cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+		return;
+
+	prev32 = is_compat_thread(task_thread_info(prev));
+	next32 = is_compat_thread(task_thread_info(next));
+
+	if (prev32 == next32)
+		return;
+
+	val = read_sysreg(cntkctl_el1);
+
+	if (!next32)
+		val |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+	else
+		val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+	write_sysreg(val, cntkctl_el1);
+}
+
+/*
  * Thread switching.
  */
 __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
@@ -530,6 +561,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	entry_task_switch(next);
 	uao_thread_switch(next);
 	ssbs_thread_switch(next);
+	erratum_1418040_thread_switch(prev, next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 77c4c9bad1b8..53acbeca4f57 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -280,7 +280,6 @@ u64 cpu_logical_map(int cpu)
 {
 	return __cpu_logical_map[cpu];
 }
-EXPORT_SYMBOL_GPL(cpu_logical_map);
 
 void __init __no_sanitize_address setup_arch(char **cmdline_p)
 {
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 03957a1ae6c0..355ee9eed4dd 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -151,7 +151,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 			break;
 		}
 		pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
-		/* Fall through */
+		fallthrough;
 	case CPU_STUCK_IN_KERNEL:
 		pr_crit("CPU%u: is stuck in kernel\n", cpu);
 		if (status & CPU_STUCK_REASON_52_BIT_VA)
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 5139a5f19256..d6adb4677c25 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@
       cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 # Install commands for the unstripped file
-quiet_cmd_vdso_install = INSTALL $@
+quiet_cmd_vdso_install = INSTALL32 $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
 
 vdso.so: $(obj)/vdso.so.dbg
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ec8e894684a7..7cba7623fcec 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -20,6 +20,13 @@ ENTRY(_text)
 
 jiffies = jiffies_64;
 
+
+#define HYPERVISOR_EXTABLE					\
+	. = ALIGN(SZ_8);					\
+	__start___kvm_ex_table = .;				\
+	*(__kvm_ex_table)					\
+	__stop___kvm_ex_table = .;
+
 #define HYPERVISOR_TEXT					\
 	/*						\
 	 * Align to 4 KB so that			\
@@ -35,6 +42,7 @@ jiffies = jiffies_64;
 	__hyp_idmap_text_end = .;			\
 	__hyp_text_start = .;				\
 	*(.hyp.text)					\
+	HYPERVISOR_EXTABLE				\
 	__hyp_text_end = .;
 
 #define IDMAP_TEXT					\
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 691d21e4c717..b588c3b5c2f0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
@@ -1640,6 +1643,10 @@ int kvm_arch_init(void *opaque)
 		return -ENODEV;
 	}
 
+	if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE))
+		kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
+			 "Only trusted guests should be used on this system.\n");
+
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
 		if (ret < 0) {
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index fe6c7d79309d..5d690d60ccad 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -128,7 +128,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
-		/* fall through */
+		fallthrough;
 	case ESR_ELx_EC_SOFTSTP_LOW:
 	case ESR_ELx_EC_BREAKPT_LOW:
 	case ESR_ELx_EC_BKPT32:
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index ee32a7743389..76e7eaf4675e 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -196,20 +196,23 @@ alternative_endif
 	// This is our single instruction exception window. A pending
 	// SError is guaranteed to occur at the earliest when we unmask
 	// it, and at the latest just after the ISB.
-	.global	abort_guest_exit_start
 abort_guest_exit_start:
 
 	isb
 
-	.global	abort_guest_exit_end
 abort_guest_exit_end:
 
 	msr	daifset, #4	// Mask aborts
+	ret
+
+	_kvm_extable	abort_guest_exit_start, 9997f
+	_kvm_extable	abort_guest_exit_end, 9997f
+9997:
+	msr	daifset, #4	// Mask aborts
+	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
 
-	// If the exception took place, restore the EL1 exception
-	// context so that we can report some information.
-	// Merge the exception code with the SError pending bit.
-	tbz	x0, #ARM_EXIT_WITH_SERROR_BIT, 1f
+	// restore the EL1 exception context so that we can report some
+	// information. Merge the exception code with the SError pending bit.
 	msr	elr_el2, x2
 	msr	esr_el2, x3
 	msr	spsr_el2, x4
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 689fccbc9de7..46b4dab933d0 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -15,6 +15,30 @@
 #include <asm/kvm_mmu.h>
 #include <asm/mmu.h>
 
+.macro save_caller_saved_regs_vect
+	/* x0 and x1 were saved in the vector entry */
+	stp	x2, x3,   [sp, #-16]!
+	stp	x4, x5,   [sp, #-16]!
+	stp	x6, x7,   [sp, #-16]!
+	stp	x8, x9,   [sp, #-16]!
+	stp	x10, x11, [sp, #-16]!
+	stp	x12, x13, [sp, #-16]!
+	stp	x14, x15, [sp, #-16]!
+	stp	x16, x17, [sp, #-16]!
+.endm
+
+.macro restore_caller_saved_regs_vect
+	ldp	x16, x17, [sp], #16
+	ldp	x14, x15, [sp], #16
+	ldp	x12, x13, [sp], #16
+	ldp	x10, x11, [sp], #16
+	ldp	x8, x9,   [sp], #16
+	ldp	x6, x7,   [sp], #16
+	ldp	x4, x5,   [sp], #16
+	ldp	x2, x3,   [sp], #16
+	ldp	x0, x1,   [sp], #16
+.endm
+
 	.text
 
 .macro do_el2_call
@@ -143,13 +167,19 @@ el1_error:
 	b	__guest_exit
 
 el2_sync:
-	/* Check for illegal exception return, otherwise panic */
+	/* Check for illegal exception return */
 	mrs	x0, spsr_el2
+	tbnz	x0, #20, 1f
 
-	/* if this was something else, then panic! */
-	tst	x0, #PSR_IL_BIT
-	b.eq	__hyp_panic
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
+	bl	kvm_unexpected_el2_exception
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
 
+	eret
+
+1:
 	/* Let's attempt a recovery from the illegal exception return */
 	get_vcpu_ptr	x1, x0
 	mov	x0, #ARM_EXCEPTION_IL
@@ -157,27 +187,14 @@ el2_sync:
 
 
 el2_error:
-	ldp	x0, x1, [sp], #16
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
+
+	bl	kvm_unexpected_el2_exception
+
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
 
-	/*
-	 * Only two possibilities:
-	 * 1) Either we come from the exit path, having just unmasked
-	 *    PSTATE.A: change the return code to an EL2 fault, and
-	 *    carry on, as we're already in a sane state to handle it.
-	 * 2) Or we come from anywhere else, and that's a bug: we panic.
-	 *
-	 * For (1), x0 contains the original return code and x1 doesn't
-	 * contain anything meaningful at that stage. We can reuse them
-	 * as temp registers.
-	 * For (2), who cares?
-	 */
-	mrs	x0, elr_el2
-	adr	x1, abort_guest_exit_start
-	cmp	x0, x1
-	adr	x1, abort_guest_exit_end
-	ccmp	x0, x1, #4, ne
-	b.ne	__hyp_panic
-	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
 	eret
 	sb
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 0297dc63988c..5e28ea6aa097 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -21,70 +21,70 @@
 #define save_debug(ptr,reg,nr)						\
 	switch (nr) {							\
 	case 15:	ptr[15] = read_debug(reg, 15);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 14:	ptr[14] = read_debug(reg, 14);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 13:	ptr[13] = read_debug(reg, 13);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 12:	ptr[12] = read_debug(reg, 12);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 11:	ptr[11] = read_debug(reg, 11);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 10:	ptr[10] = read_debug(reg, 10);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 9:		ptr[9] = read_debug(reg, 9);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 8:		ptr[8] = read_debug(reg, 8);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 7:		ptr[7] = read_debug(reg, 7);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 6:		ptr[6] = read_debug(reg, 6);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 5:		ptr[5] = read_debug(reg, 5);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 4:		ptr[4] = read_debug(reg, 4);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 3:		ptr[3] = read_debug(reg, 3);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 2:		ptr[2] = read_debug(reg, 2);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 1:		ptr[1] = read_debug(reg, 1);			\
-			/* Fall through */				\
+			fallthrough;					\
 	default:	ptr[0] = read_debug(reg, 0);			\
 	}
 
 #define restore_debug(ptr,reg,nr)					\
 	switch (nr) {							\
 	case 15:	write_debug(ptr[15], reg, 15);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 14:	write_debug(ptr[14], reg, 14);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 13:	write_debug(ptr[13], reg, 13);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 12:	write_debug(ptr[12], reg, 12);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 11:	write_debug(ptr[11], reg, 11);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 10:	write_debug(ptr[10], reg, 10);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 9:		write_debug(ptr[9], reg, 9);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 8:		write_debug(ptr[8], reg, 8);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 7:		write_debug(ptr[7], reg, 7);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 6:		write_debug(ptr[6], reg, 6);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 5:		write_debug(ptr[5], reg, 5);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 4:		write_debug(ptr[4], reg, 4);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 3:		write_debug(ptr[3], reg, 3);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 2:		write_debug(ptr[2], reg, 2);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 1:		write_debug(ptr[1], reg, 1);			\
-			/* Fall through */				\
+			fallthrough;					\
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 426ef65601dd..5b6b8fa00f0a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -17,6 +17,7 @@
 
 #include <asm/barrier.h>
 #include <asm/cpufeature.h>
+#include <asm/extable.h>
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -29,6 +30,9 @@
 
 extern const char __hyp_panic_string[];
 
+extern struct exception_table_entry __start___kvm_ex_table;
+extern struct exception_table_entry __stop___kvm_ex_table;
+
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
 static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
 {
@@ -142,10 +146,10 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	 * saved the guest context yet, and we may return early...
 	 */
 	par = read_sysreg(par_el1);
-	asm volatile("at s1e1r, %0" : : "r" (far));
-	isb();
-
-	tmp = read_sysreg(par_el1);
+	if (!__kvm_at("s1e1r", far))
+		tmp = read_sysreg(par_el1);
+	else
+		tmp = SYS_PAR_EL1_F; /* back to the guest */
 	write_sysreg(par, par_el1);
 
 	if (unlikely(tmp & SYS_PAR_EL1_F))
@@ -508,4 +512,31 @@ static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static inline void __kvm_unexpected_el2_exception(void)
+{
+	unsigned long addr, fixup;
+	struct kvm_cpu_context *host_ctxt;
+	struct exception_table_entry *entry, *end;
+	unsigned long elr_el2 = read_sysreg(elr_el2);
+
+	entry = hyp_symbol_addr(__start___kvm_ex_table);
+	end = hyp_symbol_addr(__stop___kvm_ex_table);
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+
+	while (entry < end) {
+		addr = (unsigned long)&entry->insn + entry->insn;
+		fixup = (unsigned long)&entry->fixup + entry->fixup;
+
+		if (addr != elr_el2) {
+			entry++;
+			continue;
+		}
+
+		write_sysreg(fixup, elr_el2);
+		return;
+	}
+
+	hyp_panic(host_ctxt);
+}
+
 #endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 341be2f2f312..0970442d2dbc 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -270,3 +270,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 		       read_sysreg(hpfar_el2), par, vcpu);
 	unreachable();
 }
+
+asmlinkage void kvm_unexpected_el2_exception(void)
+{
+	return __kvm_unexpected_el2_exception();
+}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 5a0073511efb..452f4cacd674 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -340,10 +340,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	case 7:
 		cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
 		cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
-		/* Fall through */
+		fallthrough;
 	default:
 		cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
 	}
@@ -352,10 +352,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	case 7:
 		cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
 		cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
-		/* Fall through */
+		fallthrough;
 	default:
 		cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
 	}
@@ -373,10 +373,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 	case 7:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
-		/* Fall through */
+		fallthrough;
 	default:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
 	}
@@ -385,10 +385,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 	case 7:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
-		/* Fall through */
+		fallthrough;
 	default:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
 	}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c52d714e0d75..c1da4f86ccac 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -217,3 +217,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 	__hyp_call_panic(spsr, elr, par, host_ctxt);
 	unreachable();
 }
+
+asmlinkage void kvm_unexpected_el2_exception(void)
+{
+	return __kvm_unexpected_el2_exception();
+}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0121ef2c7c8d..9a636b8064f1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -343,7 +343,8 @@ static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size,
+				 bool may_block)
 {
 	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
@@ -369,11 +370,16 @@ static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
 		 */
-		if (next != end)
+		if (may_block && next != end)
 			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+{
+	__unmap_stage2_range(mmu, start, size, true);
+}
+
 static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
@@ -1871,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1964,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
@@ -2208,18 +2220,21 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	unsigned flags = *(unsigned *)data;
+	bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE;
+
+	__unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block);
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end)
+			unsigned long start, unsigned long end, unsigned flags)
 {
 	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
-	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags);
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce1557e..920ac43077ad 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053c5ee4..ff0444352bba 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate,
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e0f5bd..8d78acc4fba7 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64,
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64,
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg,
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index a206655a39a5..9b11c096a042 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -45,7 +45,7 @@ static u32 get_cpu_asid_bits(void)
 	default:
 		pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
 					smp_processor_id(),  fld);
-		/* Fallthrough */
+		fallthrough;
 	case 0:
 		asid = 8;
 		break;
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index e456652facce..d05c78eace1b 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -220,7 +220,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler)
 			regs->a4 = -EINTR;
 			break;
 		}
-	/* fallthrough */
+		fallthrough;
 	case -ERESTARTNOINTR:
 do_restart:
 		regs->a4 = regs->orig_a4;
@@ -252,7 +252,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs,
 				break;
 			}
 
-			/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->a4 = regs->orig_a4;
 			regs->pc -= 4;
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index 9452d6570b7e..970895df75ec 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -194,7 +194,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				regs->a0 = -EINTR;
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->a0 = regs->orig_a0;
 			regs->pc -= TRAP0_SIZE;
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index 38d335488a54..69e68949787f 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -227,7 +227,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka)
 			regs->er0 = -EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case -ERESTARTNOINTR:
 do_restart:
 		regs->er0 = regs->orig_er0;
diff --git a/arch/hexagon/kernel/module.c b/arch/hexagon/kernel/module.c
index cf99fb79a124..cb3bf19b0640 100644
--- a/arch/hexagon/kernel/module.c
+++ b/arch/hexagon/kernel/module.c
@@ -120,7 +120,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		}
 		case R_HEXAGON_HI16:
 			value = (value>>16) & 0xffff;
-			/* fallthrough */
+			fallthrough;
 		case R_HEXAGON_LO16:
 			*location &= ~0x00c03fff;
 			*location |= value & 0x3fff;
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index d48864c48e5a..94cc7ff52dce 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -155,7 +155,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				regs->r00 = -EINTR;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->r06 = regs->syscall_nr;
 			pt_set_elr(regs, pt_elr(regs) - 4);
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 10850897a91c..779b6972aa84 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -366,6 +366,15 @@ pgd_index (unsigned long address)
 }
 #define pgd_index pgd_index
 
+/*
+ * In the kernel's mapped region we know everything is in region number 5, so
+ * as an optimisation its PGD already points to the area for that region.
+ * However, this also means that we cannot use pgd_index() and we must
+ * never add the region here.
+ */
+#define pgd_offset_k(addr) \
+	(init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)))
+
 /* Look up a pgd entry in the gate area.  On IA-64, the gate-area
    resides in the kernel-mapped segment, hence we use pgd_offset_k()
    here.  */
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index bec762a9b418..fec70d662d0c 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -163,7 +163,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 		case DIE_INIT_MONARCH_LEAVE:
 			if (!kdump_freeze_monarch)
 				break;
-			/* fall through */
+			fallthrough;
 		case DIE_INIT_SLAVE_LEAVE:
 		case DIE_INIT_MONARCH_ENTER:
 		case DIE_MCA_RENDZVOUS_LEAVE:
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index b49fe6f618ed..f8150ee74f29 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -3,7 +3,7 @@
  * Architecture-specific kernel symbols
  */
 
-#ifdef CONFIG_VIRTUAL_MEM_MAP
+#if defined(CONFIG_VIRTUAL_MEM_MAP) || defined(CONFIG_DISCONTIGMEM)
 #include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 1a42ba885188..00a496cb346f 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -654,7 +654,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend,
 				}
 			} else if (!is_internal(mod, val))
 				val = get_plt(mod, location, val, &ok);
-			/* FALL THROUGH */
+			fallthrough;
 		      default:
 			val -= bundle(location);
 			break;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 971f166873aa..0dc3611e7971 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -3472,7 +3472,7 @@ pfm_restart(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs)
 			break;
 		case PFM_CTX_LOADED: 
 			if (CTX_HAS_SMPL(ctx) && fmt->fmt_restart_active) break;
-			/* fall through */
+			fallthrough;
 		case PFM_CTX_UNLOADED:
 		case PFM_CTX_ZOMBIE:
 			DPRINT(("invalid state=%d\n", state));
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index d07ed65c9c6e..e67b22fc3c60 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -374,7 +374,7 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall)
 					/* note: scr->pt.r10 is already -1 */
 					break;
 				}
-				/*FALLTHRU*/
+				fallthrough;
 			case ERESTARTNOINTR:
 				ia64_decrement_ip(&scr->pt);
 				restart = 0; /* don't restart twice if handle_signal() fails... */
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 2d4e65ba5c3e..6c1a8951dfbb 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -1431,7 +1431,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 		if (u.insn.x)
 			/* oops, really a semaphore op (cmpxchg, etc) */
 			goto failure;
-		/*FALLTHRU*/
+		fallthrough;
 	      case LDS_IMM_OP:
 	      case LDSA_IMM_OP:
 	      case LDFS_OP:
@@ -1459,7 +1459,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 		if (u.insn.x)
 			/* oops, really a semaphore op (cmpxchg, etc) */
 			goto failure;
-		/*FALLTHRU*/
+		fallthrough;
 	      case LD_IMM_OP:
 	      case LDA_IMM_OP:
 	      case LDBIAS_IMM_OP:
@@ -1475,7 +1475,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 		if (u.insn.x)
 			/* oops, really a semaphore op (cmpxchg, etc) */
 			goto failure;
-		/*FALLTHRU*/
+		fallthrough;
 	      case ST_IMM_OP:
 	      case STREL_IMM_OP:
 		ret = emulate_store_int(ifa, u.insn, regs);
diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c
index 7601fe0622d2..6bd64c35e691 100644
--- a/arch/ia64/kernel/unwind.c
+++ b/arch/ia64/kernel/unwind.c
@@ -324,7 +324,7 @@ unw_access_gr (struct unw_frame_info *info, int regnum, unsigned long *val, char
 							return 0;
 						}
 					}
-					/* fall through */
+					fallthrough;
 				      case UNW_NAT_NONE:
 					dummy_nat = 0;
 					nat_addr = &dummy_nat;
diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c
index 37091898adb3..5e0e682f9c61 100644
--- a/arch/m68k/atari/atakeyb.c
+++ b/arch/m68k/atari/atakeyb.c
@@ -207,7 +207,7 @@ repeat:
 					self_test_last_rcv = jiffies;
 					break;
 				}
-				/* FALL THROUGH */
+				fallthrough;
 
 			default:
 				break_flag = scancode & BREAK_MASK;
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index fc034fd19798..a98fca977073 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -1067,7 +1067,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler)
 			regs->d0 = -EINTR;
 			break;
 		}
-	/* fallthrough */
+		fallthrough;
 	case -ERESTARTNOINTR:
 	do_restart:
 		regs->d0 = regs->orig_d0;
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 5c9f3a2d6538..a621fcc1a576 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -1018,7 +1018,7 @@ int __init mac_platform_init(void)
 		 */
 		platform_device_register_simple("mac_scsi", 1,
 			mac_scsi_duo_rsrc, ARRAY_SIZE(mac_scsi_duo_rsrc));
-		/* fall through */
+		fallthrough;
 	case MAC_SCSI_OLD:
 		/* Addresses from Developer Notes for Duo System,
 		 * PowerBook 180 & 160, 140 & 170, Macintosh IIsi
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 1f0fad2a98a0..ac77d73af19a 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -370,7 +370,7 @@ void via_nubus_irq_startup(int irq)
 			/* Allow NuBus slots 9 through F. */
 			via2[vDirA] &= 0x80 | ~(1 << irq_idx);
 		}
-		/* fall through */
+		fallthrough;
 	case MAC_VIA_IICI:
 		via_irq_enable(irq);
 		break;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 795f483b1050..ef46e77e97a5 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -118,7 +118,7 @@ good_area:
 	pr_debug("do_page_fault: good_area\n");
 	switch (error_code & 3) {
 		default:	/* 3: write, present */
-			/* fall through */
+			fallthrough;
 		case 2:		/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto acc_err;
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 65bf5fd8d473..4a96b59f0bee 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -249,7 +249,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler)
 			regs->r3 = -EINTR;
 			break;
 	}
-	/* fallthrough */
+		fallthrough;
 	case -ERESTARTNOINTR:
 do_restart:
 		/* offset of 4 bytes to re-execute trap (brki) instruction */
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 0880a003573d..3344d4a1fe89 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -46,6 +46,9 @@ unsigned long memory_size;
 EXPORT_SYMBOL(memory_size);
 unsigned long lowmem_size;
 
+EXPORT_SYMBOL(min_low_pfn);
+EXPORT_SYMBOL(max_low_pfn);
+
 #ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 EXPORT_SYMBOL(kmap_pte);
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 47a8ffc0b413..f5b8300f4573 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -137,6 +137,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return !(flags & 1);
 }
 
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
 #endif /* #ifndef __ASSEMBLY__ */
 
 /*
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index d35eaed1668f..825d337a505a 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -969,7 +969,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu,
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end);
+			unsigned long start, unsigned long end, unsigned flags);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
index b6e9c99b85a5..eb181224eb4c 100644
--- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
@@ -26,7 +26,6 @@
 #define cpu_has_counter		1
 #define cpu_has_dc_aliases	(PAGE_SIZE < 0x4000)
 #define cpu_has_divec		0
-#define cpu_has_ejtag		0
 #define cpu_has_inclusive_pcaches	1
 #define cpu_has_llsc		1
 #define cpu_has_mcheck		0
@@ -42,7 +41,6 @@
 #define cpu_has_veic		0
 #define cpu_has_vint		0
 #define cpu_has_vtag_icache	0
-#define cpu_has_watch		1
 #define cpu_has_wsbh		1
 #define cpu_has_ic_fills_f_dc	1
 #define cpu_hwrena_impl_bits	0xc0000000
diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h
index f5e362f79701..bf2480923154 100644
--- a/arch/mips/include/asm/mach-loongson64/irq.h
+++ b/arch/mips/include/asm/mach-loongson64/irq.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_MACH_LOONGSON64_IRQ_H_
 #define __ASM_MACH_LOONGSON64_IRQ_H_
 
-#include <boot_param.h>
-
 /* cpu core interrupt numbers */
 #define NR_IRQS_LEGACY		16
 #define NR_MIPS_CPU_IRQS	8
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index 3a25dbd3b3e9..5eaca4fe3f92 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -9,7 +9,6 @@
 #ifndef _ASM_MACH_LOONGSON64_MMZONE_H
 #define _ASM_MACH_LOONGSON64_MMZONE_H
 
-#include <boot_param.h>
 #define NODE_ADDRSPACE_SHIFT 44
 #define NODE0_ADDRSPACE_OFFSET 0x000000000000UL
 #define NODE1_ADDRSPACE_OFFSET 0x100000000000UL
diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h
index 7dd4a80e05d6..6f4ac854b12d 100644
--- a/arch/mips/include/asm/unroll.h
+++ b/arch/mips/include/asm/unroll.h
@@ -28,38 +28,38 @@
 	BUILD_BUG_ON(!__builtin_constant_p(times));		\
 								\
 	switch (times) {					\
-	case 32: fn(__VA_ARGS__); /* fall through */		\
-	case 31: fn(__VA_ARGS__); /* fall through */		\
-	case 30: fn(__VA_ARGS__); /* fall through */		\
-	case 29: fn(__VA_ARGS__); /* fall through */		\
-	case 28: fn(__VA_ARGS__); /* fall through */		\
-	case 27: fn(__VA_ARGS__); /* fall through */		\
-	case 26: fn(__VA_ARGS__); /* fall through */		\
-	case 25: fn(__VA_ARGS__); /* fall through */		\
-	case 24: fn(__VA_ARGS__); /* fall through */		\
-	case 23: fn(__VA_ARGS__); /* fall through */		\
-	case 22: fn(__VA_ARGS__); /* fall through */		\
-	case 21: fn(__VA_ARGS__); /* fall through */		\
-	case 20: fn(__VA_ARGS__); /* fall through */		\
-	case 19: fn(__VA_ARGS__); /* fall through */		\
-	case 18: fn(__VA_ARGS__); /* fall through */		\
-	case 17: fn(__VA_ARGS__); /* fall through */		\
-	case 16: fn(__VA_ARGS__); /* fall through */		\
-	case 15: fn(__VA_ARGS__); /* fall through */		\
-	case 14: fn(__VA_ARGS__); /* fall through */		\
-	case 13: fn(__VA_ARGS__); /* fall through */		\
-	case 12: fn(__VA_ARGS__); /* fall through */		\
-	case 11: fn(__VA_ARGS__); /* fall through */		\
-	case 10: fn(__VA_ARGS__); /* fall through */		\
-	case 9: fn(__VA_ARGS__); /* fall through */		\
-	case 8: fn(__VA_ARGS__); /* fall through */		\
-	case 7: fn(__VA_ARGS__); /* fall through */		\
-	case 6: fn(__VA_ARGS__); /* fall through */		\
-	case 5: fn(__VA_ARGS__); /* fall through */		\
-	case 4: fn(__VA_ARGS__); /* fall through */		\
-	case 3: fn(__VA_ARGS__); /* fall through */		\
-	case 2: fn(__VA_ARGS__); /* fall through */		\
-	case 1: fn(__VA_ARGS__); /* fall through */		\
+	case 32: fn(__VA_ARGS__); fallthrough;			\
+	case 31: fn(__VA_ARGS__); fallthrough;			\
+	case 30: fn(__VA_ARGS__); fallthrough;			\
+	case 29: fn(__VA_ARGS__); fallthrough;			\
+	case 28: fn(__VA_ARGS__); fallthrough;			\
+	case 27: fn(__VA_ARGS__); fallthrough;			\
+	case 26: fn(__VA_ARGS__); fallthrough;			\
+	case 25: fn(__VA_ARGS__); fallthrough;			\
+	case 24: fn(__VA_ARGS__); fallthrough;			\
+	case 23: fn(__VA_ARGS__); fallthrough;			\
+	case 22: fn(__VA_ARGS__); fallthrough;			\
+	case 21: fn(__VA_ARGS__); fallthrough;			\
+	case 20: fn(__VA_ARGS__); fallthrough;			\
+	case 19: fn(__VA_ARGS__); fallthrough;			\
+	case 18: fn(__VA_ARGS__); fallthrough;			\
+	case 17: fn(__VA_ARGS__); fallthrough;			\
+	case 16: fn(__VA_ARGS__); fallthrough;			\
+	case 15: fn(__VA_ARGS__); fallthrough;			\
+	case 14: fn(__VA_ARGS__); fallthrough;			\
+	case 13: fn(__VA_ARGS__); fallthrough;			\
+	case 12: fn(__VA_ARGS__); fallthrough;			\
+	case 11: fn(__VA_ARGS__); fallthrough;			\
+	case 10: fn(__VA_ARGS__); fallthrough;			\
+	case 9: fn(__VA_ARGS__); fallthrough;			\
+	case 8: fn(__VA_ARGS__); fallthrough;			\
+	case 7: fn(__VA_ARGS__); fallthrough;			\
+	case 6: fn(__VA_ARGS__); fallthrough;			\
+	case 5: fn(__VA_ARGS__); fallthrough;			\
+	case 4: fn(__VA_ARGS__); fallthrough;			\
+	case 3: fn(__VA_ARGS__); fallthrough;			\
+	case 2: fn(__VA_ARGS__); fallthrough;			\
+	case 1: fn(__VA_ARGS__); fallthrough;			\
 	case 0: break;						\
 								\
 	default:						\
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index efce5defcc5c..011eb6bbf81a 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1898,8 +1898,8 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 				(base_id >= 64 && base_id < 90) ||
 				(base_id >= 128 && base_id < 164) ||
 				(base_id >= 192 && base_id < 200) ||
-				(base_id >= 256 && base_id < 274) ||
-				(base_id >= 320 && base_id < 358) ||
+				(base_id >= 256 && base_id < 275) ||
+				(base_id >= 320 && base_id < 361) ||
 				(base_id >= 384 && base_id < 574))
 				break;
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 2f513506a3d5..1dbfb5aadffd 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -239,6 +239,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle)
  */
 static void bmips_init_secondary(void)
 {
+	bmips_cpu_setup();
+
 	switch (current_cpu_type()) {
 	case CPU_BMIPS4350:
 	case CPU_BMIPS4380:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 38aa07ccdbcc..cf788591f091 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1287,6 +1287,18 @@ static int enable_restore_fp_context(int msa)
 		err = own_fpu_inatomic(1);
 		if (msa && !err) {
 			enable_msa();
+			/*
+			 * with MSA enabled, userspace can see MSACSR
+			 * and MSA regs, but the values in them are from
+			 * other task before current task, restore them
+			 * from saved fp/msa context
+			 */
+			write_msa_csr(current->thread.fpu.msacsr);
+			/*
+			 * own_fpu_inatomic(1) just restore low 64bit,
+			 * fix the high 64bit
+			 */
+			init_msa_upper();
 			set_thread_flag(TIF_USEDMSA);
 			set_thread_flag(TIF_MSA_CTX_LIVE);
 		}
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7de85d2253ff..0c50ac444222 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm);
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 87fa8d8a1031..28c366d307e7 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -486,7 +486,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end,
 	return 1;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index fc5a6d25f74f..0ef717093262 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1712,7 +1712,11 @@ static void setup_scache(void)
 				printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n",
 				       scache_size >> 10,
 				       way_string[c->scache.ways], c->scache.linesz);
+
+				if (current_cpu_type() == CPU_BMIPS5000)
+					c->options |= MIPS_CPU_INCLUSIVE_CACHES;
 			}
+
 #else
 			if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT))
 				panic("Dunno how to handle MIPS32 / MIPS64 second level cache");
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index 1493c49ca47a..55d7b7fd18b6 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -245,7 +245,6 @@ static int mipsxx_perfcount_handler(void)
 
 	switch (counters) {
 #define HANDLE_COUNTER(n)						\
-	fallthrough;							\
 	case n + 1:							\
 		control = r_c0_perfctrl ## n();				\
 		counter = r_c0_perfcntr ## n();				\
@@ -256,8 +255,11 @@ static int mipsxx_perfcount_handler(void)
 			handled = IRQ_HANDLED;				\
 		}
 	HANDLE_COUNTER(3)
+	fallthrough;
 	HANDLE_COUNTER(2)
+	fallthrough;
 	HANDLE_COUNTER(1)
+	fallthrough;
 	HANDLE_COUNTER(0)
 	}
 
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index 0ecffb65fd6d..b09dc844985a 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -222,8 +222,8 @@ void __init sni_a20r_irq_init(void)
 		irq_set_chip_and_handler(i, &a20r_irq_type, handle_level_irq);
 	sni_hwint = a20r_hwint;
 	change_c0_status(ST0_IM, IE_IRQ0);
-	if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA",
-			NULL))
+	if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler,
+			IRQF_SHARED, "ISA", sni_isa_irq_handler))
 		pr_err("Failed to register ISA interrupt\n");
 }
 
diff --git a/arch/nds32/include/asm/irqflags.h b/arch/nds32/include/asm/irqflags.h
index fb45ec46bb1b..51ef800bb301 100644
--- a/arch/nds32/include/asm/irqflags.h
+++ b/arch/nds32/include/asm/irqflags.h
@@ -34,3 +34,8 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !flags;
 }
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c
index 62bdafbc53f4..9edd7ed7d7bf 100644
--- a/arch/nds32/kernel/fpu.c
+++ b/arch/nds32/kernel/fpu.c
@@ -45,7 +45,7 @@ void save_fpu(struct task_struct *tsk)
 			      :	/* no output */
 			      : "r" (&tsk->thread.fpu)
 			      : "memory");
-		/* fall through */
+		fallthrough;
 	case SP32_DP16_reg:
 		asm volatile ("fsdi $fd15, [%0+0x78]\n\t"
 			      "fsdi $fd14, [%0+0x70]\n\t"
@@ -58,7 +58,7 @@ void save_fpu(struct task_struct *tsk)
 			      :	/* no output */
 			      : "r" (&tsk->thread.fpu)
 			      : "memory");
-		/* fall through */
+		fallthrough;
 	case SP16_DP8_reg:
 		asm volatile ("fsdi $fd7,  [%0+0x38]\n\t"
 			      "fsdi $fd6,  [%0+0x30]\n\t"
@@ -67,7 +67,7 @@ void save_fpu(struct task_struct *tsk)
 			      :	/* no output */
 			      : "r" (&tsk->thread.fpu)
 			      : "memory");
-		/* fall through */
+		fallthrough;
 	case SP8_DP4_reg:
 		asm volatile ("fsdi $fd3,  [%1+0x18]\n\t"
 			      "fsdi $fd2,  [%1+0x10]\n\t"
@@ -108,7 +108,7 @@ void load_fpu(const struct fpu_struct *fpregs)
 			      "fldi $fd16, [%0+0x80]\n\t"
 			      :	/* no output */
 			      : "r" (fpregs));
-		/* fall through */
+		fallthrough;
 	case SP32_DP16_reg:
 		asm volatile ("fldi $fd15, [%0+0x78]\n\t"
 			      "fldi $fd14, [%0+0x70]\n\t"
@@ -120,7 +120,7 @@ void load_fpu(const struct fpu_struct *fpregs)
 			      "fldi $fd8,  [%0+0x40]\n\t"
 			      :	/* no output */
 			      : "r" (fpregs));
-		/* fall through */
+		fallthrough;
 	case SP16_DP8_reg:
 		asm volatile ("fldi $fd7,  [%0+0x38]\n\t"
 			      "fldi $fd6,  [%0+0x30]\n\t"
@@ -128,7 +128,7 @@ void load_fpu(const struct fpu_struct *fpregs)
 			      "fldi $fd4,  [%0+0x20]\n\t"
 			      :	/* no output */
 			      : "r" (fpregs));
-		/* fall through */
+		fallthrough;
 	case SP8_DP4_reg:
 		asm volatile ("fldi $fd3,  [%1+0x18]\n\t"
 			      "fldi $fd2,  [%1+0x10]\n\t"
diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c
index 330b19fcd990..36e25a410bb0 100644
--- a/arch/nds32/kernel/signal.c
+++ b/arch/nds32/kernel/signal.c
@@ -316,7 +316,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				regs->uregs[0] = -EINTR;
 				break;
 			}
-			/* Else, fall through */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->uregs[0] = regs->orig_r0;
 			regs->ipc -= 4;
@@ -361,7 +361,7 @@ static void do_signal(struct pt_regs *regs)
 		switch (regs->uregs[0]) {
 		case -ERESTART_RESTARTBLOCK:
 			regs->uregs[15] = __NR_restart_syscall;
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index f0390211236b..120f5005461b 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -165,19 +165,19 @@ struct __large_struct {
 
 #define __get_user_nocheck(x, ptr, size)			\
 ({								\
-	long __gu_err, __gu_val;				\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;		\
+	long __gu_err;						\
+	__get_user_size((x), (ptr), (size), __gu_err);		\
 	__gu_err;						\
 })
 
 #define __get_user_check(x, ptr, size)					\
 ({									\
-	long __gu_err = -EFAULT, __gu_val = 0;				\
+	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
-	if (access_ok(__gu_addr, size))			\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	if (access_ok(__gu_addr, size))					\
+		__get_user_size((x), __gu_addr, (size), __gu_err);	\
+	else								\
+		(x) = (__typeof__(*(ptr))) 0;				\
 	__gu_err;							\
 })
 
@@ -191,11 +191,13 @@ do {									\
 	case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break;		\
 	case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break;		\
 	case 8: __get_user_asm2(x, ptr, retval); break;			\
-	default: (x) = __get_user_bad();				\
+	default: (x) = (__typeof__(*(ptr)))__get_user_bad();		\
 	}								\
 } while (0)
 
 #define __get_user_asm(x, addr, err, op)		\
+{							\
+	unsigned long __gu_tmp;				\
 	__asm__ __volatile__(				\
 		"1:	"op" %1,0(%2)\n"		\
 		"2:\n"					\
@@ -209,10 +211,14 @@ do {									\
 		"	.align 2\n"			\
 		"	.long 1b,3b\n"			\
 		".previous"				\
-		: "=r"(err), "=r"(x)			\
-		: "r"(addr), "i"(-EFAULT), "0"(err))
+		: "=r"(err), "=r"(__gu_tmp)		\
+		: "r"(addr), "i"(-EFAULT), "0"(err));	\
+	(x) = (__typeof__(*(addr)))__gu_tmp;		\
+}
 
 #define __get_user_asm2(x, addr, err)			\
+{							\
+	unsigned long long __gu_tmp;			\
 	__asm__ __volatile__(				\
 		"1:	l.lwz %1,0(%2)\n"		\
 		"2:	l.lwz %H1,4(%2)\n"		\
@@ -229,8 +235,11 @@ do {									\
 		"	.long 1b,4b\n"			\
 		"	.long 2b,4b\n"			\
 		".previous"				\
-		: "=r"(err), "=&r"(x)			\
-		: "r"(addr), "i"(-EFAULT), "0"(err))
+		: "=r"(err), "=&r"(__gu_tmp)		\
+		: "r"(addr), "i"(-EFAULT), "0"(err));	\
+	(x) = (__typeof__(*(addr)))(			\
+		(__typeof__((x)-(x)))__gu_tmp);		\
+}
 
 /* more complex routines */
 
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index b18e775f8be3..13c87f1f872b 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -80,6 +80,16 @@ static void __init setup_memory(void)
 	 */
 	memblock_reserve(__pa(_stext), _end - _stext);
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	/* Then reserve the initrd, if any */
+	if (initrd_start && (initrd_end > initrd_start)) {
+		unsigned long aligned_start = ALIGN_DOWN(initrd_start, PAGE_SIZE);
+		unsigned long aligned_end = ALIGN(initrd_end, PAGE_SIZE);
+
+		memblock_reserve(__pa(aligned_start), aligned_end - aligned_start);
+	}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
 	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 97804f21a40c..c779364f0cd0 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -244,7 +244,7 @@ int do_signal(struct pt_regs *regs, int syscall)
 		switch (retval) {
 		case -ERESTART_RESTARTBLOCK:
 			restart = -2;
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index 08f56af387ac..534a52ec5e66 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -16,7 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-static void cache_loop(struct page *page, const unsigned int reg)
+static __always_inline void cache_loop(struct page *page, const unsigned int reg)
 {
 	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
 	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 5df5d4cd5d4c..3c037fc96038 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -502,7 +502,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 			regs->gr[28] = -EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case -ERESTARTNOINTR:
 		check_syscallno_in_delay_branch(regs);
 		break;
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 43875c289723..a52c7abf2ca4 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -437,7 +437,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o
 		break;
 
 	default:
-		/* Fall through */
 		break;
 
 	}
@@ -644,12 +643,12 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	case 15:
 		/* Data TLB miss fault/Data page fault */
-		/* Fall through */
+		fallthrough;
 	case 16:
 		/* Non-access instruction TLB miss fault */
 		/* The instruction TLB entry needed for the target address of the FIC
 		   is absent, and hardware can't find it, so we get to cleanup */
-		/* Fall through */
+		fallthrough;
 	case 17:
 		/* Non-access data TLB miss fault/Non-access data page fault */
 		/* FIXME: 
@@ -673,7 +672,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			handle_unaligned(regs);
 			return;
 		}
-		/* Fall Through */
+		fallthrough;
 	case 26: 
 		/* PCXL: Data memory access rights trap */
 		fault_address = regs->ior;
@@ -683,7 +682,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	case 19:
 		/* Data memory break trap */
 		regs->gr[0] |= PSW_X; /* So we can single-step over the trap */
-		/* fall thru */
+		fallthrough;
 	case 21:
 		/* Page reference trap */
 		handle_gdb_break(regs, TRAP_HWBKPT);
@@ -730,7 +729,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			}
 			mmap_read_unlock(current->mm);
 		}
-		/* Fall Through */
+		fallthrough;
 	case 27: 
 		/* Data memory protection ID trap */
 		if (code == 27 && !user_mode(regs) &&
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 4bfe2da9fbe3..716960f5d92e 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -67,7 +67,7 @@ parisc_acctyp(unsigned long code, unsigned int inst)
 	case 0x30000000: /* coproc2 */
 		if (bit22set(inst))
 			return VM_WRITE;
-		/* fall through */
+		fallthrough;
 
 	case 0x0: /* indexed/memory management */
 		if (bit22set(inst)) {
@@ -370,7 +370,7 @@ bad_area:
 			}
 
 			/* probably address is outside of mapped file */
-			/* fall through */
+			fallthrough;
 		case 17:	/* NA data TLB miss / page fault */
 		case 18:	/* Unaligned access - PCXS only */
 			signo = SIGBUS;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..65bed1fdeaad 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT
 
 	  If unsure, say N here.
 
+config PPC_PROT_SAO_LPAR
+	bool "Support PROT_SAO mappings in LPARs"
+	depends on PPC_BOOK3S_64
+	help
+	  This option adds support for PROT_SAO mappings from userspace
+	  inside LPARs on supported CPUs.
+
+	  This may cause issues when performing guest migration from
+	  a CPU that supports SAO to one that does not.
+
+	  If unsure, say N here.
+
 config PPC_COPRO_BASE
 	bool
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 6de56c3b33c4..495fc0ccb453 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -20,13 +20,9 @@
 #define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
 #define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
-
-#define _PAGE_CACHE_CTL		0x00030 /* Bits for the folowing cache modes */
-			/*	No bits set is normal cacheable memory */
-			/*	0x00010 unused, is SAO bit on radix POWER9 */
+#define _PAGE_SAO		0x00010 /* Strong access order */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
 #define _PAGE_TOLERANT		0x00030 /* tolerant memory, cache inhibited */
-
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
 /*
@@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	return hash__set_pte_at(mm, addr, ptep, pte, percpu);
 }
 
+#define _PAGE_CACHE_CTL	(_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
+
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
 {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index fdddb822d564..32a15dc49e8c 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -9,6 +9,11 @@
 
 #ifndef __ASSEMBLY__
 
+/*
+ * Added to include __machine_check_early_realmode_* functions
+ */
+#include <asm/mce.h>
+
 /* This structure can grow, it's real size is used by head.S code
  * via the mkdefs mechanism.
  */
@@ -191,7 +196,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
 #define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
-// Free					LONG_ASM_CONST(0x0000000008000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
@@ -436,7 +441,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
 	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
@@ -445,7 +450,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
@@ -456,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
@@ -474,7 +479,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 925cf89cbf4b..6bfc87915d5d 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -52,7 +52,7 @@ enum fixed_addresses {
 	FIX_HOLE,
 	/* reserve the top 128K for early debugging purposes */
 	FIX_EARLY_DEBUG_TOP = FIX_HOLE,
-	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1,
+	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 3a0db7b0b46e..35060be09073 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -200,17 +200,14 @@ static inline bool arch_irqs_disabled(void)
 #define powerpc_local_irq_pmu_save(flags)			\
 	 do {							\
 		raw_local_irq_pmu_save(flags);			\
-		trace_hardirqs_off();				\
+		if (!raw_irqs_disabled_flags(flags))		\
+			trace_hardirqs_off();			\
 	} while(0)
 #define powerpc_local_irq_pmu_restore(flags)			\
 	do {							\
-		if (raw_irqs_disabled_flags(flags)) {		\
-			raw_local_irq_pmu_restore(flags);	\
-			trace_hardirqs_off();			\
-		} else {					\
+		if (!raw_irqs_disabled_flags(flags))		\
 			trace_hardirqs_on();			\
-			raw_local_irq_pmu_restore(flags);	\
-		}						\
+		raw_local_irq_pmu_restore(flags);		\
 	} while(0)
 #else
 #define powerpc_local_irq_pmu_save(flags)			\
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index d635b96c7ea6..7355ed05e65e 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -15,11 +15,18 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/page.h>
+#include <linux/sizes.h>
 
 #define KASAN_SHADOW_SCALE_SHIFT	3
 
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX)
+#define KASAN_KERN_START	ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M)
+#else
+#define KASAN_KERN_START	PAGE_OFFSET
+#endif
+
 #define KASAN_SHADOW_START	(KASAN_SHADOW_OFFSET + \
-				 (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT))
+				 (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT))
 
 #define KASAN_SHADOW_OFFSET	ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e020d269416d..10ded83414de 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -58,7 +58,8 @@
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
 extern int kvm_unmap_hva_range(struct kvm *kvm,
-			       unsigned long start, unsigned long end);
+			       unsigned long start, unsigned long end,
+			       unsigned flags);
 extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index adf2cda67f9a..89aa8248a57d 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -210,6 +210,9 @@ struct mce_error_info {
 #define MCE_EVENT_RELEASE	true
 #define MCE_EVENT_DONTRELEASE	false
 
+struct pt_regs;
+struct notifier_block;
+
 extern void save_mce_event(struct pt_regs *regs, long handled,
 			   struct mce_error_info *mce_err, uint64_t nip,
 			   uint64_t addr, uint64_t phys_addr);
@@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb);
 int mce_unregister_notifier(struct notifier_block *nb);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
+long __machine_check_early_realmode_p7(struct pt_regs *regs);
+long __machine_check_early_realmode_p8(struct pt_regs *regs);
+long __machine_check_early_realmode_p9(struct pt_regs *regs);
+long __machine_check_early_realmode_p10(struct pt_regs *regs);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 7c07728af300..7cb6d18f5cd6 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -13,20 +13,43 @@
 #include <linux/pkeys.h>
 #include <asm/cpu_has_feature.h>
 
-#ifdef CONFIG_PPC_MEM_KEYS
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
-	return pkey_to_vmflag_bits(pkey);
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
+#else
+	return ((prot & PROT_SAO) ? VM_SAO : 0);
+#endif
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return __pgprot(vmflag_to_pte_pkey_bits(vm_flags));
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (vm_flags & VM_SAO) ?
+		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
+		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
+#else
+	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
+#endif
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-#endif
+
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
+		return false;
+	if (prot & PROT_SAO) {
+		if (!cpu_has_feature(CPU_FTR_SAO))
+			return false;
+		if (firmware_has_feature(FW_FEATURE_LPAR) &&
+		    !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR))
+			return false;
+	}
+	return true;
+}
+#define arch_validate_prot arch_validate_prot
 
 #endif /* CONFIG_PPC64 */
 #endif	/* _ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 59ee9fa4ae09..6cb8aa357191 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -82,6 +82,8 @@
  */
 #include <asm/nohash/pte-book3e.h>
 
+#define _PAGE_SAO	0
+
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
 
 /*
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 1e8b2e1ec1db..daec64d41b44 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; }
 
 /* To support perf_regs sier update */
 extern bool is_sier_available(void);
+/* To define perf extended regs mask value */
+extern u64 PERF_REG_EXTENDED_MASK;
+#define PERF_REG_EXTENDED_MASK	PERF_REG_EXTENDED_MASK
 #endif
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 86c9eb064b22..f6acabb6c9be 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -62,6 +62,11 @@ struct power_pmu {
 	int 		*blacklist_ev;
 	/* BHRB entries in the PMU */
 	int		bhrb_nr;
+	/*
+	 * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if
+	 * the pmu supports extended perf regs capability
+	 */
+	int		capabilities;
 };
 
 /*
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 3a700351feca..c0c737215b00 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -11,7 +11,7 @@
 #include <asm-generic/mman-common.h>
 
 
-#define PROT_SAO	0x10		/* Unsupported since v5.9 */
+#define PROT_SAO	0x10		/* Strong Access Ordering */
 
 #define MAP_RENAME      MAP_ANONYMOUS   /* In SunOS terminology */
 #define MAP_NORESERVE   0x40            /* don't reserve swap pages */
diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h
index f599064dd8dc..bdf5f10f8b9f 100644
--- a/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -48,6 +48,24 @@ enum perf_event_powerpc_regs {
 	PERF_REG_POWERPC_DSISR,
 	PERF_REG_POWERPC_SIER,
 	PERF_REG_POWERPC_MMCRA,
-	PERF_REG_POWERPC_MAX,
+	/* Extended registers */
+	PERF_REG_POWERPC_MMCR0,
+	PERF_REG_POWERPC_MMCR1,
+	PERF_REG_POWERPC_MMCR2,
+	PERF_REG_POWERPC_MMCR3,
+	PERF_REG_POWERPC_SIER2,
+	PERF_REG_POWERPC_SIER3,
+	/* Max regs without the extended regs */
+	PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
 };
+
+#define PERF_REG_PMU_MASK	((1ULL << PERF_REG_POWERPC_MAX) - 1)
+
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */
+#define PERF_REG_PMU_MASK_300   (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK)
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */
+#define PERF_REG_PMU_MASK_31   (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK)
+
+#define PERF_REG_MAX_ISA_300   (PERF_REG_POWERPC_MMCR2 + 1)
+#define PERF_REG_MAX_ISA_31    (PERF_REG_POWERPC_SIER3 + 1)
 #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3d406a9626e8..2aa89c6b2896 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power9(void);
 extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power10(void);
-extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
+	{	/* Power10 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00800000,
+		.cpu_name		= "POWER10 (raw)",
+		.cpu_features		= CPU_FTRS_POWER10,
+		.cpu_user_features	= COMMON_USER_POWER10,
+		.cpu_user_features2	= COMMON_USER2_POWER10,
+		.mmu_features		= MMU_FTRS_POWER10,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power10",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power10,
+		.cpu_restore		= __restore_cpu_power10,
+		.machine_check_early	= __machine_check_early_realmode_p10,
+		.platform		= "power10",
+	},
 	{	/* Cell Broadband Engine */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00700000,
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 6f8c0c6b937a..f204ad79b6b5 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -64,10 +64,6 @@ struct dt_cpu_feature {
  * Set up the base CPU
  */
 
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p10(struct pt_regs *regs);
-
 static int hv_mode;
 
 static struct {
@@ -657,7 +653,7 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
 	{"no-execute", feat_enable, 0},
-	/* strong-access-ordering is unused */
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
 	{"coprocessor-icswx", feat_enable, 0},
 	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 33a42e42c56f..733e40eba4eb 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -113,6 +113,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r10)		/* "regshere" marker */
 
+BEGIN_FTR_SECTION
+	HMT_MEDIUM
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	/*
 	 * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
 	 * would clobber syscall parameters. Also we always enter with IRQs
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 016bd831908e..73a57043ee66 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -548,7 +548,7 @@ void notrace restore_math(struct pt_regs *regs)
 	 * are live for the user thread).
 	 */
 	if ((!(msr & MSR_FP)) && should_restore_fp())
-		new_msr |= MSR_FP | current->thread.fpexc_mode;
+		new_msr |= MSR_FP;
 
 	if ((!(msr & MSR_VEC)) && should_restore_altivec())
 		new_msr |= MSR_VEC;
@@ -559,11 +559,17 @@ void notrace restore_math(struct pt_regs *regs)
 	}
 
 	if (new_msr) {
+		unsigned long fpexc_mode = 0;
+
 		msr_check_and_set(new_msr);
 
-		if (new_msr & MSR_FP)
+		if (new_msr & MSR_FP) {
 			do_restore_fp();
 
+			// This also covers VSX, because VSX implies FP
+			fpexc_mode = current->thread.fpexc_mode;
+		}
+
 		if (new_msr & MSR_VEC)
 			do_restore_altivec();
 
@@ -572,7 +578,7 @@ void notrace restore_math(struct pt_regs *regs)
 
 		msr_check_and_clear(new_msr);
 
-		regs->msr |= new_msr;
+		regs->msr |= new_msr | fpexc_mode;
 	}
 }
 #endif
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index b198b0ff25bc..808ec9fab605 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 				min = pvr & 0xFF;
 				break;
 			case 0x004e: /* POWER9 bits 12-15 give chip type */
+			case 0x0080: /* POWER10 bit 12 gives SMT8/4 */
 				maj = (pvr >> 8) & 0x0F;
 				min = pvr & 0xFF;
 				break;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 41fedec69ac3..49db50d1db04 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change);
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
 }
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index d6c1069e9954..ed0c9c43d0cf 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 	return 0;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	/* kvm_unmap_hva flushes everything anyways */
 	kvm_unmap_hva(kvm, start);
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index c0162911f6cb..d426eaf76bb0 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr)
 {
 	if (!IS_ENABLED(CONFIG_MODULES))
 		return false;
+#ifdef MODULES_VADDR
+	if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
+		return false;
+	if (addr > ALIGN(MODULES_END, SZ_256M) - 1)
+		return false;
+#else
 	if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
 		return false;
-	if (addr >= ALIGN(VMALLOC_END, SZ_256M))
+	if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1)
 		return false;
+#endif
 	return true;
 }
 
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 1da9dbba9217..c663e7ba801f 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		rflags |= HPTE_R_I;
 	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
 	else
 		/*
 		 * Add memory coherence if cache inhibited is not set
@@ -1115,8 +1117,10 @@ void hash__early_init_mmu_secondary(void)
 			&& cpu_has_feature(CPU_FTR_HVMODE))
 		tlbiel_all();
 
-	if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY))
+#ifdef CONFIG_PPC_MEM_KEYS
+	if (mmu_has_feature(MMU_FTR_PKEY))
 		mtspr(SPRN_UAMOR, default_uamor);
+#endif
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 16d09b36fe06..78d61f97371e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -475,7 +475,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
-			/* Fall through */
+			fallthrough;
 		cond_branch:
 			/* same targets, can avoid doing the test :) */
 			if (filter[i].jt == filter[i].jf) {
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 78fe34986594..08643cba1494 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1557,9 +1557,16 @@ nocheck:
 	ret = 0;
  out:
 	if (has_branch_stack(event)) {
-		power_pmu_bhrb_enable(event);
-		cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
-					event->attr.branch_sample_type);
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
+				event->attr.branch_sample_type);
+
+		if (bhrb_filter != -1) {
+			cpuhw->bhrb_filter = bhrb_filter;
+			power_pmu_bhrb_enable(event);
+		}
 	}
 
 	perf_pmu_enable(event->pmu);
@@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event)
 	int n;
 	int err;
 	struct cpu_hw_events *cpuhw;
-	u64 bhrb_filter;
 
 	if (!ppmu)
 		return -ENOENT;
@@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 
 	if (has_branch_stack(event)) {
-		bhrb_filter = ppmu->bhrb_filter_map(
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
 					event->attr.branch_sample_type);
 
 		if (bhrb_filter == -1) {
@@ -2141,6 +2150,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
+	} else if (period) {
+		/* Account for interrupt in case of invalid SIAR */
+		if (perf_event_account_interrupt(event))
+			power_pmu_stop(event, 0);
 	}
 }
 
@@ -2323,6 +2336,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		pmu->name);
 
 	power_pmu.attr_groups = ppmu->attr_groups;
+	power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS);
 
 #ifdef MSR_HV
 	/*
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index cdb7bfbd157e..6e7e820508df 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = {
 	NULL,
 };
 
+static struct attribute *cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group cpumask_attr_group = {
+	.attrs = cpumask_attrs,
+};
+
 static struct attribute *if_attrs[] = {
 	&dev_attr_catalog_len.attr,
 	&dev_attr_catalog_version.attr,
@@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = {
 	&dev_attr_sockets.attr,
 	&dev_attr_chipspersocket.attr,
 	&dev_attr_coresperchip.attr,
-	&dev_attr_cpumask.attr,
 	NULL,
 };
 
@@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = {
 	&event_desc_group,
 	&event_long_desc_group,
 	&if_group,
+	&cpumask_attr_group,
 	NULL,
 };
 
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index a45d694a5d5d..62d0b54086f8 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 	header->misc = 0;
 
 	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
-		switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) {
+		switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) {
 		case 0:/* when MSR HV and PR not set in the trace-record */
 			header->misc |= PERF_RECORD_MISC_GUEST_KERNEL;
 			break;
@@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 			header->misc |= PERF_RECORD_MISC_GUEST_USER;
 			break;
 		case 2: /* MSR HV is 1 and PR is 0 */
-			header->misc |= PERF_RECORD_MISC_HYPERVISOR;
+			header->misc |= PERF_RECORD_MISC_KERNEL;
 			break;
 		case 3: /* MSR HV is 1 and PR is 1 */
 			header->misc |= PERF_RECORD_MISC_USER;
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index a213a0aa5d25..8e53f2fc3fe0 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -13,9 +13,11 @@
 #include <asm/ptrace.h>
 #include <asm/perf_regs.h>
 
+u64 PERF_REG_EXTENDED_MASK;
+
 #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
 
-#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1))
+#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK))
 
 static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_R0,  gpr[0]),
@@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
 };
 
+/* Function to return the extended register values */
+static u64 get_ext_regs_value(int idx)
+{
+	switch (idx) {
+	case PERF_REG_POWERPC_MMCR0:
+		return mfspr(SPRN_MMCR0);
+	case PERF_REG_POWERPC_MMCR1:
+		return mfspr(SPRN_MMCR1);
+	case PERF_REG_POWERPC_MMCR2:
+		return mfspr(SPRN_MMCR2);
+#ifdef CONFIG_PPC64
+	case PERF_REG_POWERPC_MMCR3:
+		return mfspr(SPRN_MMCR3);
+	case PERF_REG_POWERPC_SIER2:
+		return mfspr(SPRN_SIER2);
+	case PERF_REG_POWERPC_SIER3:
+		return mfspr(SPRN_SIER3);
+#endif
+	default: return 0;
+	}
+}
+
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
-	if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX))
-		return 0;
+	u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		perf_reg_extended_max = PERF_REG_MAX_ISA_31;
+	else if (cpu_has_feature(CPU_FTR_ARCH_300))
+		perf_reg_extended_max = PERF_REG_MAX_ISA_300;
 
 	if (idx == PERF_REG_POWERPC_SIER &&
 	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
@@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	    IS_ENABLED(CONFIG_PPC32)))
 		return 0;
 
+	if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max)
+		return get_ext_regs_value(idx);
+
+	/*
+	 * If the idx is referring to value beyond the
+	 * supported registers, return 0 with a warning
+	 */
+	if (WARN_ON_ONCE(idx >= perf_reg_extended_max))
+		return 0;
+
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index f7cff7f36a1c..83148656b524 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -87,6 +87,8 @@
 #define POWER10_MMCRA_IFM3		0x00000000C0000000UL
 #define POWER10_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
+extern u64 PERF_REG_EXTENDED_MASK;
+
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int power10_event_alternatives[][MAX_ALT] = {
 	{ PM_RUN_CYC_ALT,		PM_RUN_CYC },
@@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = {
 	.cache_events		= &power10_cache_events,
 	.attr_groups		= power10_pmu_attr_groups,
 	.bhrb_nr		= 32,
+	.capabilities           = PERF_PMU_CAP_EXTENDED_REGS,
 };
 
 int init_power10_pmu(void)
@@ -408,6 +411,9 @@ int init_power10_pmu(void)
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
 		return -ENODEV;
 
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+
 	rc = register_power_pmu(&power10_pmu);
 	if (rc)
 		return rc;
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 05dae38b969a..2a57e93a79dc 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -90,6 +90,8 @@ enum {
 #define POWER9_MMCRA_IFM3		0x00000000C0000000UL
 #define POWER9_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
+extern u64 PERF_REG_EXTENDED_MASK;
+
 /* Nasty Power9 specific hack */
 #define PVR_POWER9_CUMULUS		0x00002000
 
@@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = {
 	.cache_events		= &power9_cache_events,
 	.attr_groups		= power9_pmu_attr_groups,
 	.bhrb_nr		= 32,
+	.capabilities           = PERF_PMU_CAP_EXTENDED_REGS,
 };
 
 int init_power9_pmu(void)
@@ -457,6 +460,9 @@ int init_power9_pmu(void)
 		}
 	}
 
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300;
+
 	rc = register_power_pmu(&power9_pmu);
 	if (rc)
 		return rc;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 87737ec86d39..1dc9d3c81872 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -36,7 +36,7 @@ config PPC_BOOK3S_6xx
 	select PPC_HAVE_PMU_SUPPORT
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
-	select HAVE_ARCH_VMAP_STACK
+	select HAVE_ARCH_VMAP_STACK if !ADB_PMU
 
 config PPC_BOOK3S_601
 	bool "PowerPC 601"
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 77513a80cef9..345ab062b21a 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -1223,7 +1223,7 @@ static void __init pnv_probe_idle_states(void)
 		return;
 	}
 
-	if (pvr_version_is(PVR_POWER9))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		pnv_power9_idle_init();
 
 	for (i = 0; i < nr_pnv_idle_states; i++)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index c9c25fb0783c..023a4f987bb2 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 	struct iommu_table *tbl = pe->table_group.tables[0];
 	int64_t rc;
 
-	if (pe->dma_setup_done)
+	if (!pe->dma_setup_done)
 		return;
 
 	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index c6e0d8abf75e..7a974ed6b240 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -107,22 +107,28 @@ static int pseries_cpu_disable(void)
  */
 static void pseries_cpu_die(unsigned int cpu)
 {
-	int tries;
 	int cpu_status = 1;
 	unsigned int pcpu = get_hard_smp_processor_id(cpu);
+	unsigned long timeout = jiffies + msecs_to_jiffies(120000);
 
-	for (tries = 0; tries < 25; tries++) {
+	while (true) {
 		cpu_status = smp_query_cpu_stopped(pcpu);
 		if (cpu_status == QCSS_STOPPED ||
 		    cpu_status == QCSS_HARDWARE_ERROR)
 			break;
-		cpu_relax();
 
+		if (time_after(jiffies, timeout)) {
+			pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n",
+				cpu, pcpu);
+			timeout = jiffies + msecs_to_jiffies(120000);
+		}
+
+		cond_resched();
 	}
 
-	if (cpu_status != 0) {
-		printk("Querying DEAD? cpu %i (%i) shows %i\n",
-		       cpu, pcpu, cpu_status);
+	if (cpu_status == QCSS_HARDWARE_ERROR) {
+		pr_warn("CPU %i (hwid %i) reported error while dying\n",
+			cpu, pcpu);
 	}
 
 	/* Isolation and deallocation are definitely done by
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f3736fcd98fc..13c86a292c6d 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier)
 	case EPOW_SHUTDOWN_ON_UPS:
 		pr_emerg("Loss of system power detected. System is running on"
 			 " UPS/battery. Check RTAS error log for details\n");
-		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS:
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7b5905529146..df18372861d8 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -81,7 +81,7 @@ config RISCV
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_MSI if PCI
 	select RISCV_INTC
-	select RISCV_TIMER
+	select RISCV_TIMER if RISCV_SBI
 	select SPARSEMEM_STATIC if 32BIT
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 6c88148f1b9b..8a55f6156661 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -12,6 +12,7 @@ config SOC_SIFIVE
 
 config SOC_VIRT
 	bool "QEMU Virt Machine"
+	select CLINT_TIMER if RISCV_M_MODE
 	select POWER_RESET
 	select POWER_RESET_SYSCON
 	select POWER_RESET_SYSCON_POWEROFF
@@ -24,6 +25,7 @@ config SOC_VIRT
 config SOC_KENDRYTE
 	bool "Kendryte K210 SoC"
 	depends on !MMU
+	select CLINT_TIMER if RISCV_M_MODE
 	select SERIAL_SIFIVE if TTY
 	select SERIAL_SIFIVE_CONSOLE if TTY
 	select SIFIVE_PLIC
diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig
index f27596e9663e..e046a0babde4 100644
--- a/arch/riscv/configs/nommu_virt_defconfig
+++ b/arch/riscv/configs/nommu_virt_defconfig
@@ -26,6 +26,7 @@ CONFIG_EXPERT=y
 CONFIG_SLOB=y
 # CONFIG_SLAB_MERGE_DEFAULT is not set
 # CONFIG_MMU is not set
+CONFIG_SOC_VIRT=y
 CONFIG_MAXPHYSMEM_2GB=y
 CONFIG_SMP=y
 CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0"
@@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_LDISC_AUTOLOAD is not set
-# CONFIG_DEVMEM is not set
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
+# CONFIG_DEVMEM is not set
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_VIRTIO_MMIO=y
 CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
-CONFIG_SIFIVE_PLIC=y
-# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT2_FS=y
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index 3a55f0e00d6c..2c2cda6cc1c5 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_SOC_SIFIVE=y
 CONFIG_SOC_VIRT=y
 CONFIG_ARCH_RV32I=y
 CONFIG_SMP=y
@@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_SPI=y
+CONFIG_SPI_SIFIVE=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_POWER_RESET=y
 CONFIG_DRM=y
@@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_UAS=y
+CONFIG_MMC=y
+CONFIG_MMC_SPI=y
 CONFIG_RTC_CLASS=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BALLOON=y
diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h
deleted file mode 100644
index a279b17a6aad..000000000000
--- a/arch/riscv/include/asm/clint.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_RISCV_CLINT_H
-#define _ASM_RISCV_CLINT_H 1
-
-#include <linux/io.h>
-#include <linux/smp.h>
-
-#ifdef CONFIG_RISCV_M_MODE
-extern u32 __iomem *clint_ipi_base;
-
-void clint_init_boot_cpu(void);
-
-static inline void clint_send_ipi_single(unsigned long hartid)
-{
-	writel(1, clint_ipi_base + hartid);
-}
-
-static inline void clint_send_ipi_mask(const struct cpumask *mask)
-{
-	int cpu;
-
-	for_each_cpu(cpu, mask)
-		clint_send_ipi_single(cpuid_to_hartid_map(cpu));
-}
-
-static inline void clint_clear_ipi(unsigned long hartid)
-{
-	writel(0, clint_ipi_base + hartid);
-}
-#else /* CONFIG_RISCV_M_MODE */
-#define clint_init_boot_cpu()	do { } while (0)
-
-/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */
-void clint_send_ipi_single(unsigned long hartid);
-void clint_send_ipi_mask(const struct cpumask *hartid_mask);
-void clint_clear_ipi(unsigned long hartid);
-#endif /* CONFIG_RISCV_M_MODE */
-
-#endif /* _ASM_RISCV_CLINT_H */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 6dfd2a1446d5..df1f7c4cd433 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -15,6 +15,11 @@
 struct seq_file;
 extern unsigned long boot_cpu_hartid;
 
+struct riscv_ipi_ops {
+	void (*ipi_inject)(const struct cpumask *target);
+	void (*ipi_clear)(void);
+};
+
 #ifdef CONFIG_SMP
 /*
  * Mapping between linux logical cpu index and hartid.
@@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu);
 int riscv_hartid_to_cpuid(int hartid);
 void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
 
+/* Set custom IPI operations */
+void riscv_set_ipi_ops(struct riscv_ipi_ops *ops);
+
+/* Clear IPI for current CPU */
+void riscv_clear_ipi(void);
+
 /* Secondary hart entry */
 asmlinkage void smp_callin(void);
 
@@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
 	cpumask_set_cpu(boot_cpu_hartid, out);
 }
 
+static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops)
+{
+}
+
+static inline void riscv_clear_ipi(void)
+{
+}
+
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index bad2a7c2cda5..a3fb85d505d4 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -7,41 +7,27 @@
 #define _ASM_RISCV_TIMEX_H
 
 #include <asm/csr.h>
-#include <asm/mmio.h>
 
 typedef unsigned long cycles_t;
 
-extern u64 __iomem *riscv_time_val;
-extern u64 __iomem *riscv_time_cmp;
-
-#ifdef CONFIG_64BIT
-#define mmio_get_cycles()	readq_relaxed(riscv_time_val)
-#else
-#define mmio_get_cycles()	readl_relaxed(riscv_time_val)
-#define mmio_get_cycles_hi()	readl_relaxed(((u32 *)riscv_time_val) + 1)
-#endif
-
 static inline cycles_t get_cycles(void)
 {
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		return csr_read(CSR_TIME);
-	return mmio_get_cycles();
+	return csr_read(CSR_TIME);
 }
 #define get_cycles get_cycles
 
+static inline u32 get_cycles_hi(void)
+{
+	return csr_read(CSR_TIMEH);
+}
+#define get_cycles_hi get_cycles_hi
+
 #ifdef CONFIG_64BIT
 static inline u64 get_cycles64(void)
 {
 	return get_cycles();
 }
 #else /* CONFIG_64BIT */
-static inline u32 get_cycles_hi(void)
-{
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		return csr_read(CSR_TIMEH);
-	return mmio_get_cycles_hi();
-}
-
 static inline u64 get_cycles64(void)
 {
 	u32 hi, lo;
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index a5287ab9f7f2..dc93710f0b2f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -31,7 +31,7 @@ obj-y	+= cacheinfo.o
 obj-y	+= patch.o
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_M_MODE)	+= clint.o traps_misaligned.o
+obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c
deleted file mode 100644
index 3647980d14c3..000000000000
--- a/arch/riscv/kernel/clint.c
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2019 Christoph Hellwig.
- */
-
-#include <linux/io.h>
-#include <linux/of_address.h>
-#include <linux/types.h>
-#include <asm/clint.h>
-#include <asm/csr.h>
-#include <asm/timex.h>
-#include <asm/smp.h>
-
-/*
- * This is the layout used by the SiFive clint, which is also shared by the qemu
- * virt platform, and the Kendryte KD210 at least.
- */
-#define CLINT_IPI_OFF		0
-#define CLINT_TIME_CMP_OFF	0x4000
-#define CLINT_TIME_VAL_OFF	0xbff8
-
-u32 __iomem *clint_ipi_base;
-
-void clint_init_boot_cpu(void)
-{
-	struct device_node *np;
-	void __iomem *base;
-
-	np = of_find_compatible_node(NULL, NULL, "riscv,clint0");
-	if (!np) {
-		panic("clint not found");
-		return;
-	}
-
-	base = of_iomap(np, 0);
-	if (!base)
-		panic("could not map CLINT");
-
-	clint_ipi_base = base + CLINT_IPI_OFF;
-	riscv_time_cmp = base + CLINT_TIME_CMP_OFF;
-	riscv_time_val = base + CLINT_TIME_VAL_OFF;
-
-	clint_clear_ipi(boot_cpu_hartid);
-}
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index f383ef5672b2..226ccce0f9e0 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void)
 	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION);
 }
 
+static void sbi_send_cpumask_ipi(const struct cpumask *target)
+{
+	struct cpumask hartid_mask;
+
+	riscv_cpuid_to_hartid_mask(target, &hartid_mask);
+
+	sbi_send_ipi(cpumask_bits(&hartid_mask));
+}
+
+static struct riscv_ipi_ops sbi_ipi_ops = {
+	.ipi_inject = sbi_send_cpumask_ipi
+};
 
 int __init sbi_init(void)
 {
@@ -587,5 +599,7 @@ int __init sbi_init(void)
 		__sbi_rfence	= __sbi_rfence_v01;
 	}
 
+	riscv_set_ipi_ops(&sbi_ipi_ops);
+
 	return 0;
 }
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f04373be54a6..2c6dd329312b 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -18,7 +18,6 @@
 #include <linux/swiotlb.h>
 #include <linux/smp.h>
 
-#include <asm/clint.h>
 #include <asm/cpu_ops.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p)
 #else
 	unflatten_device_tree();
 #endif
-	clint_init_boot_cpu();
 
 #ifdef CONFIG_SWIOTLB
 	swiotlb_init(1);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 17ba190e84a5..e996e08f1061 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -250,7 +250,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				regs->a0 = -EINTR;
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
                         regs->a0 = regs->orig_a0;
 			regs->epc -= 0x4;
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 554b0fb47060..ea028d9e0d24 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -18,7 +18,6 @@
 #include <linux/delay.h>
 #include <linux/irq_work.h>
 
-#include <asm/clint.h>
 #include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
@@ -86,9 +85,25 @@ static void ipi_stop(void)
 		wait_for_interrupt();
 }
 
+static struct riscv_ipi_ops *ipi_ops;
+
+void riscv_set_ipi_ops(struct riscv_ipi_ops *ops)
+{
+	ipi_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
+
+void riscv_clear_ipi(void)
+{
+	if (ipi_ops && ipi_ops->ipi_clear)
+		ipi_ops->ipi_clear();
+
+	csr_clear(CSR_IP, IE_SIE);
+}
+EXPORT_SYMBOL_GPL(riscv_clear_ipi);
+
 static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
 {
-	struct cpumask hartid_mask;
 	int cpu;
 
 	smp_mb__before_atomic();
@@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
 		set_bit(op, &ipi_data[cpu].bits);
 	smp_mb__after_atomic();
 
-	riscv_cpuid_to_hartid_mask(mask, &hartid_mask);
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		sbi_send_ipi(cpumask_bits(&hartid_mask));
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(mask);
 	else
-		clint_send_ipi_mask(mask);
+		pr_warn("SMP: IPI inject method not available\n");
 }
 
 static void send_ipi_single(int cpu, enum ipi_message_type op)
 {
-	int hartid = cpuid_to_hartid_map(cpu);
-
 	smp_mb__before_atomic();
 	set_bit(op, &ipi_data[cpu].bits);
 	smp_mb__after_atomic();
 
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		sbi_send_ipi(cpumask_bits(cpumask_of(hartid)));
-	else
-		clint_send_ipi_single(hartid);
-}
-
-static inline void clear_ipi(void)
-{
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		csr_clear(CSR_IP, IE_SIE);
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(cpumask_of(cpu));
 	else
-		clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id()));
+		pr_warn("SMP: IPI inject method not available\n");
 }
 
 #ifdef CONFIG_IRQ_WORK
@@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs)
 
 	irq_enter();
 
-	clear_ipi();
+	riscv_clear_ipi();
 
 	while (true) {
 		unsigned long ops;
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 356825a57551..96167d55ed98 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
-#include <asm/clint.h>
 #include <asm/cpu_ops.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
@@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int curr_cpuid = smp_processor_id();
 
-	if (!IS_ENABLED(CONFIG_RISCV_SBI))
-		clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id()));
+	riscv_clear_ipi();
 
 	/* All kernel threads share the same mm context.  */
 	mmgrab(mm);
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index bc5f2204693f..579575f9cdae 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -1020,7 +1020,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_zext64(dst, ctx);
 			break;
 		}
-		/* Fallthrough. */
+		fallthrough;
 
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU | BPF_SUB | BPF_X:
@@ -1079,7 +1079,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		case 16:
 			emit(rv_slli(lo(rd), lo(rd), 16), ctx);
 			emit(rv_srli(lo(rd), lo(rd), 16), ctx);
-			/* Fallthrough. */
+			fallthrough;
 		case 32:
 			if (!ctx->prog->aux->verifier_zext)
 				emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3d86e12e8e3c..b29fcc66ec39 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
 config GENERIC_LOCKBREAK
-	def_bool y if PREEMPTTION
+	def_bool y if PREEMPTION
 
 config PGSTE
 	def_bool y if KVM
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 0cf9a82326a8..7228aabe9da6 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -626,6 +626,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -807,6 +808,7 @@ CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_REF_SCALE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
 # CONFIG_RCU_TRACE is not set
 CONFIG_LATENCYTOP=y
@@ -818,6 +820,7 @@ CONFIG_PREEMPT_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_S390_PTDUMP=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
@@ -829,6 +832,7 @@ CONFIG_FAIL_MAKE_REQUEST=y
 CONFIG_FAIL_IO_TIMEOUT=y
 CONFIG_FAIL_FUTEX=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
+CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_LIST_SORT=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 5df9759e8ff6..fab03b7a6932 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -617,6 +617,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -763,6 +764,7 @@ CONFIG_PANIC_ON_OOPS=y
 CONFIG_TEST_LOCKUP=m
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_REF_SCALE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
@@ -771,6 +773,7 @@ CONFIG_STACK_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_S390_PTDUMP=y
 CONFIG_LKDTM=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 4091c50449cd..8f67c55625f9 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -74,5 +74,6 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_PANIC_ON_OOPS=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
+# CONFIG_RCU_TRACE is not set
 # CONFIG_FTRACE is not set
 # CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 50b4ce8cddfd..918f0ba4f4d2 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -29,7 +29,7 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
@@ -37,7 +37,7 @@
 		new__ = old__ op (val);					\
 		prev__ = cmpxchg(ptr__, old__, new__);			\
 	} while (prev__ != old__);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	new__;								\
 })
 
@@ -68,7 +68,7 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
@@ -84,7 +84,7 @@
 			: [val__] "d" (val__)				\
 			: "cc");					\
 	}								\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
@@ -95,14 +95,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 
@@ -114,14 +114,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_and_4(pcp, val)	arch_this_cpu_to_op(pcp, val, "lan")
@@ -136,10 +136,10 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -152,10 +152,10 @@
 ({									\
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -171,11 +171,11 @@
 	typeof(pcp1) *p1__;						\
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	p1__ = raw_cpu_ptr(&(pcp1));					\
 	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 88bb42ca5008..c73f50649e7e 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -33,14 +33,13 @@ void enabled_wait(void)
 		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	clear_cpu_flag(CIF_NOHZ_DELAY);
 
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	local_irq_save(flags);
 	/* Call the assembler magic in entry.S */
 	psw_idle(idle, psw_mask);
 	local_irq_restore(flags);
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
+	/* XXX seqcount has tracepoints that require RCU */
 	write_seqcount_begin(&idle->seqcount);
 	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 11d2f7d05f91..a76dd27fb2e8 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb)
 		cb->pc == 1 &&
 		cb->qc == 0 &&
 		cb->reserved2 == 0 &&
-		cb->key == PAGE_DEFAULT_KEY &&
 		cb->reserved3 == 0 &&
 		cb->reserved4 == 0 &&
 		cb->reserved5 == 0 &&
@@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target,
 		kfree(data);
 		return -EINVAL;
 	}
-
+	/*
+	 * Override access key in any case, since user space should
+	 * not be able to set it, nor should it care about it.
+	 */
+	ri_cb.key = PAGE_DEFAULT_KEY >> 4;
 	preempt_disable();
 	if (!target->thread.ri_cb)
 		target->thread.ri_cb = data;
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 125c7f6e8715..1788a5454b6f 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb)
 	cb->k = 1;
 	cb->ps = 1;
 	cb->pc = 1;
-	cb->key = PAGE_DEFAULT_KEY;
+	cb->key = PAGE_DEFAULT_KEY >> 4;
 	cb->v = 1;
 }
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 1aed1a4dfc2d..eddf71c22875 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -402,6 +402,7 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end,
 			pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
 			if (!pud)
 				goto out;
+			p4d_populate(&init_mm, p4d, pud);
 		}
 		ret = modify_pud_table(p4d, addr, next, add, direct);
 		if (ret)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 3902c9f6f2d6..4b62d6b55024 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev)
 }
 EXPORT_SYMBOL_GPL(zpci_disable_device);
 
+void zpci_remove_device(struct zpci_dev *zdev)
+{
+	struct zpci_bus *zbus = zdev->zbus;
+	struct pci_dev *pdev;
+
+	pdev = pci_get_slot(zbus->bus, zdev->devfn);
+	if (pdev) {
+		if (pdev->is_virtfn)
+			return zpci_remove_virtfn(pdev, zdev->vfn);
+		pci_stop_and_remove_bus_device_locked(pdev);
+	}
+}
+
 int zpci_create_device(struct zpci_dev *zdev)
 {
 	int rc;
@@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref)
 {
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
 
-	if (zdev->zbus->bus) {
-		struct pci_dev *pdev;
-
-		pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
-		if (pdev)
-			pci_stop_and_remove_bus_device_locked(pdev);
-	}
+	if (zdev->zbus->bus)
+		zpci_remove_device(zdev);
 
 	switch (zdev->state) {
 	case ZPCI_FN_STATE_ONLINE:
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 642a99384688..5967f3014156 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev,
 {
 	int rc;
 
-	virtfn->physfn = pci_dev_get(pdev);
 	rc = pci_iov_sysfs_link(pdev, virtfn, vfid);
-	if (rc) {
-		pci_dev_put(pdev);
-		virtfn->physfn = NULL;
+	if (rc)
 		return rc;
-	}
+
+	virtfn->is_virtfn = 1;
+	virtfn->multifunction = 0;
+	virtfn->physfn = pci_dev_get(pdev);
+
 	return 0;
 }
 
@@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
 	int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
 	int rc = 0;
 
-	virtfn->is_virtfn = 1;
-	virtfn->multifunction = 0;
-	WARN_ON(vfid < 0);
+	if (!zbus->multifunction)
+		return 0;
+
 	/* If the parent PF for the given VF is also configured in the
 	 * instance, it must be on the same zbus.
 	 * We can then identify the parent PF by checking what
@@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
 		zdev = zbus->function[i];
 		if (zdev && zdev->is_physfn) {
 			pdev = pci_get_slot(zbus->bus, zdev->devfn);
+			if (!pdev)
+				continue;
 			cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
 			if (cand_devfn == virtfn->devfn) {
 				rc = zpci_bus_link_virtfn(pdev, virtfn, vfid);
+				/* balance pci_get_slot() */
+				pci_dev_put(pdev);
 				break;
 			}
+			/* balance pci_get_slot() */
+			pci_dev_put(pdev);
 		}
 	}
 	return rc;
@@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
 static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
 		struct pci_dev *virtfn, int vfn)
 {
-	virtfn->is_virtfn = 1;
-	virtfn->multifunction = 0;
 	return 0;
 }
 #endif
 
+void pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+
+	/*
+	 * With pdev->no_vf_scan the common PCI probing code does not
+	 * perform PF/VF linking.
+	 */
+	if (zdev->vfn)
+		zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn);
+
+}
+
 static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)
 {
 	struct pci_bus *bus;
@@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)
 	}
 
 	pdev = pci_scan_single_device(bus, zdev->devfn);
-	if (pdev) {
-		if (!zdev->is_physfn) {
-			rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn);
-			if (rc)
-				goto failed_with_pdev;
-		}
+	if (pdev)
 		pci_bus_add_device(pdev);
-	}
-	return 0;
 
-failed_with_pdev:
-	pci_stop_and_remove_bus_device(pdev);
-	pci_dev_put(pdev);
-	return rc;
+	return 0;
 }
 
 static void zpci_bus_add_devices(struct zpci_bus *zbus)
diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h
index 89be3c354b7b..4972433df458 100644
--- a/arch/s390/pci/pci_bus.h
+++ b/arch/s390/pci/pci_bus.h
@@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus,
 
 	return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn];
 }
+
+#ifdef CONFIG_PCI_IOV
+static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn)
+{
+
+	pci_lock_rescan_remove();
+	/* Linux' vfid's start at 0 vfn at 1 */
+	pci_iov_remove_virtfn(pdev->physfn, vfn - 1);
+	pci_unlock_rescan_remove();
+}
+#else /* CONFIG_PCI_IOV */
+static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {}
+#endif /* CONFIG_PCI_IOV */
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index fdebd286f402..9a3a291cad43 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1);
 			break;
 		}
+		/* the configuration request may be stale */
+		if (zdev->state != ZPCI_FN_STATE_STANDBY)
+			break;
 		zdev->fh = ccdf->fh;
 		zdev->state = ZPCI_FN_STATE_CONFIGURED;
 		ret = zpci_enable_device(zdev);
@@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		if (!zdev)
 			break;
 		if (pdev)
-			pci_stop_and_remove_bus_device_locked(pdev);
+			zpci_remove_device(zdev);
 
 		ret = zpci_disable_device(zdev);
 		if (ret)
@@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			/* Give the driver a hint that the function is
 			 * already unusable. */
 			pdev->error_state = pci_channel_io_perm_failure;
-			pci_stop_and_remove_bus_device_locked(pdev);
+			zpci_remove_device(zdev);
 		}
 
 		zdev->state = ZPCI_FN_STATE_STANDBY;
diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c
index f3dc3f25b3ff..143747c45206 100644
--- a/arch/sh/drivers/platform_early.c
+++ b/arch/sh/drivers/platform_early.c
@@ -246,7 +246,7 @@ static int __init sh_early_platform_driver_probe_id(char *class_str,
 		case EARLY_PLATFORM_ID_ERROR:
 			pr_warn("%s: unable to parse %s parameter\n",
 				class_str, epdrv->pdrv->driver.name);
-			/* fall-through */
+			fallthrough;
 		case EARLY_PLATFORM_ID_UNSET:
 			match = NULL;
 			break;
diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c
index 08e1af63edd9..34e25a439c81 100644
--- a/arch/sh/kernel/disassemble.c
+++ b/arch/sh/kernel/disassemble.c
@@ -486,7 +486,7 @@ static void print_sh_insn(u32 memaddr, u16 insn)
 					pr_cont("xd%d", rn & ~1);
 					break;
 				}
-				/* else, fall through */
+				fallthrough;
 			case D_REG_N:
 				pr_cont("dr%d", rn);
 				break;
@@ -495,7 +495,7 @@ static void print_sh_insn(u32 memaddr, u16 insn)
 					pr_cont("xd%d", rm & ~1);
 					break;
 				}
-				/* else, fall through */
+				fallthrough;
 			case D_REG_M:
 				pr_cont("dr%d", rm);
 				break;
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 0d5f3c9d52f3..e4147efa9ec6 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -266,7 +266,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 		ptr = &remcomInBuffer[1];
 		if (kgdb_hex2long(&ptr, &addr))
 			linux_regs->pc = addr;
-		/* fallthrough */
+		fallthrough;
 	case 'D':
 	case 'k':
 		atomic_set(&kgdb_cpu_doing_single_step, -1);
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index a0fbb8427b39..4fe3f00137bc 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -418,7 +418,7 @@ handle_syscall_restart(unsigned long save_r0, struct pt_regs *regs,
 		case -ERESTARTSYS:
 			if (!(sa->sa_flags & SA_RESTART))
 				goto no_system_call_restart;
-		/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->regs[0] = save_r0;
 			regs->pc -= instruction_size(__raw_readw(regs->pc - 4));
diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c
index 4843f48bfe85..774a82b0c649 100644
--- a/arch/sparc/kernel/auxio_64.c
+++ b/arch/sparc/kernel/auxio_64.c
@@ -87,7 +87,6 @@ void auxio_set_lte(int on)
 		__auxio_sbus_set_lte(on);
 		break;
 	case AUXIO_TYPE_EBUS:
-		/* FALL-THROUGH */
 	default:
 		break;
 	}
diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c
index bfae98ab8638..23f8838dd96e 100644
--- a/arch/sparc/kernel/central.c
+++ b/arch/sparc/kernel/central.c
@@ -55,7 +55,7 @@ static int clock_board_calc_nslots(struct clock_board *p)
 			else
 				return 5;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		return 4;
 	}
diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c
index 7580775a14b9..58ad3f7de1fb 100644
--- a/arch/sparc/kernel/kgdb_32.c
+++ b/arch/sparc/kernel/kgdb_32.c
@@ -122,7 +122,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			linux_regs->pc = addr;
 			linux_regs->npc = addr + 4;
 		}
-		/* fall through */
+		fallthrough;
 
 	case 'D':
 	case 'k':
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index 5d6c2d287e85..177746ae2c81 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -148,7 +148,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			linux_regs->tpc = addr;
 			linux_regs->tnpc = addr + 4;
 		}
-		/* fall through */
+		fallthrough;
 
 	case 'D':
 	case 'k':
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index c0886b400dad..2a12c86af956 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -359,7 +359,7 @@ int __init pcr_arch_init(void)
 		 * counter overflow interrupt so we can't make use of
 		 * their hardware currently.
 		 */
-		/* fallthrough */
+		fallthrough;
 	default:
 		err = -ENODEV;
 		goto out_unregister;
diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c
index da8902295c8c..3df960c137f7 100644
--- a/arch/sparc/kernel/prom_32.c
+++ b/arch/sparc/kernel/prom_32.c
@@ -224,7 +224,7 @@ void __init of_console_init(void)
 
 		case PROMDEV_TTYB:
 			skip = 1;
-			/* FALLTHRU */
+			fallthrough;
 
 		case PROMDEV_TTYA:
 			type = "serial";
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index e2c6f0abda00..e9695a06492f 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -646,7 +646,7 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs
 	case ERESTARTSYS:
 		if (!(sa->sa_flags & SA_RESTART))
 			goto no_system_call_restart;
-		/* fallthrough */
+		fallthrough;
 	case ERESTARTNOINTR:
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->tpc -= 4;
@@ -686,7 +686,7 @@ void do_signal32(struct pt_regs * regs)
 				regs->tpc -= 4;
 				regs->tnpc -= 4;
 				pt_regs_clear_syscall(regs);
-				/* fall through */
+				fallthrough;
 			case ERESTART_RESTARTBLOCK:
 				regs->u_regs[UREG_G1] = __NR_restart_syscall;
 				regs->tpc -= 4;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index f1f8c8ebe641..d0e0025ee3ba 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -440,7 +440,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs,
 	case ERESTARTSYS:
 		if (!(sa->sa_flags & SA_RESTART))
 			goto no_system_call_restart;
-		/* fallthrough */
+		fallthrough;
 	case ERESTARTNOINTR:
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->pc -= 4;
@@ -506,7 +506,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 				regs->pc -= 4;
 				regs->npc -= 4;
 				pt_regs_clear_syscall(regs);
-				/* fall through */
+				fallthrough;
 			case ERESTART_RESTARTBLOCK:
 				regs->u_regs[UREG_G1] = __NR_restart_syscall;
 				regs->pc -= 4;
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 6937339a272c..255264bcb46a 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -461,7 +461,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs,
 	case ERESTARTSYS:
 		if (!(sa->sa_flags & SA_RESTART))
 			goto no_system_call_restart;
-		/* fallthrough */
+		fallthrough;
 	case ERESTARTNOINTR:
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->tpc -= 4;
@@ -532,7 +532,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 				regs->tpc -= 4;
 				regs->tnpc -= 4;
 				pt_regs_clear_syscall(regs);
-				/* fall through */
+				fallthrough;
 			case ERESTART_RESTARTBLOCK:
 				regs->u_regs[UREG_G1] = __NR_restart_syscall;
 				regs->tpc -= 4;
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index 72e560ef4a09..d5beec856146 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -359,7 +359,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 			*pfsr |= (6 << 14);
 			return 0;			/* simulate invalid_fp_register exception */
 		}
-	/* fall through */
+		fallthrough;
 	case 2:
 		if (freg & 1) {				/* doublewords must have bit 5 zeroed */
 			*pfsr |= (6 << 14);
@@ -380,7 +380,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 			*pfsr |= (6 << 14);
 			return 0;			/* simulate invalid_fp_register exception */
 		}
-	/* fall through */
+		fallthrough;
 	case 2:
 		if (freg & 1) {				/* doublewords must have bit 5 zeroed */
 			*pfsr |= (6 << 14);
@@ -408,13 +408,13 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 			*pfsr |= (6 << 14);
 			return 0;			/* simulate invalid_fp_register exception */
 		}
-	/* fall through */
+		fallthrough;
 	case 2:
 		if (freg & 1) {				/* doublewords must have bit 5 zeroed */
 			*pfsr |= (6 << 14);
 			return 0;
 		}
-	/* fall through */
+		fallthrough;
 	case 1:
 		rd = (void *)&fregs[freg];
 		break;
diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c
index c8eabb973b86..b1dbf2fa8c0a 100644
--- a/arch/sparc/net/bpf_jit_comp_32.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -491,7 +491,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				} else {
 					emit_loadimm(K, r_A);
 				}
-				/* Fallthrough */
+				fallthrough;
 			case BPF_RET | BPF_A:
 				if (seen_or_pass0) {
 					if (i != flen - 1) {
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 3d57c71c532e..88cd9b5c1b74 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -70,7 +70,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				PT_REGS_SYSCALL_RET(regs) = -EINTR;
 				break;
 			}
-		/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			PT_REGS_RESTART_SYSCALL(regs);
 			PT_REGS_ORIG_SYSCALL(regs) = PT_REGS_SYSCALL_NR(regs);
diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c
index 4ff01176c1cc..21d56ae83cdf 100644
--- a/arch/x86/boot/cmdline.c
+++ b/arch/x86/boot/cmdline.c
@@ -54,7 +54,7 @@ int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *b
 			/* else */
 			state = st_wordcmp;
 			opptr = option;
-			/* fall through */
+			fallthrough;
 
 		case st_wordcmp:
 			if (c == '=' && !*opptr) {
@@ -129,7 +129,7 @@ int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option)
 			state = st_wordcmp;
 			opptr = option;
 			wstart = pos;
-			/* fall through */
+			fallthrough;
 
 		case st_wordcmp:
 			if (!*opptr)
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 0048269180d5..dde7cb3724df 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -178,7 +178,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
 			}
 			*size = 0;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		/*
 		 * If w/o offset, only size specified, memmap=nn[KMG] has the
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 39e592d0e0b4..e478e40fbe5a 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -30,12 +30,9 @@
 #define STATIC		static
 
 /*
- * Use normal definitions of mem*() from string.c. There are already
- * included header files which expect a definition of memset() and by
- * the time we define memset macro, it is too late.
+ * Provide definitions of memzero and memmove as some of the decompressors will
+ * try to define their own functions if these are not defined as macros.
  */
-#undef memcpy
-#undef memset
 #define memzero(s, n)	memset((s), 0, (n))
 #define memmove		memmove
 
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 995f7b7ad512..a232da487cd2 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len);
 void *memset(void *dst, int c, size_t len);
 int memcmp(const void *s1, const void *s2, size_t len);
 
-/*
- * Access builtin version by default. If one needs to use optimized version,
- * do "undef memcpy" in .c file and link against right string.c
- */
+/* Access builtin version by default. */
 #define memcpy(d,s,l) __builtin_memcpy(d,s,l)
 #define memset(d,c,l) __builtin_memset(d,c,l)
 #define memcmp	__builtin_memcmp
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 98e4d8886f11..ae9b0d4615b3 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with
  * Fetch the per-CPU GSBASE value for this processor and put it in @reg.
  * We normally use %gs for accessing per-CPU data, but we are setting up
  * %gs here and obviously can not use %gs itself to access per-CPU data.
+ *
+ * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and
+ * may not restore the host's value until the CPU returns to userspace.
+ * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives
+ * while running KVM's run loop.
  */
 .macro GET_PERCPU_BASE reg:req
-	ALTERNATIVE \
-		"LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \
-		"RDPID	\reg", \
-		X86_FEATURE_RDPID
+	LOAD_CPU_AND_NODE_SEG_LIMIT \reg
 	andq	$VDSO_CPUNODE_MASK, \reg
 	movq	__per_cpu_offset(, \reg, 8), \reg
 .endm
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 48512c7944e7..2f84c7ca74ea 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -60,16 +60,10 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
 {
-	unsigned int nr = (unsigned int)regs->orig_ax;
-
 	if (IS_ENABLED(CONFIG_IA32_EMULATION))
 		current_thread_info()->status |= TS_COMPAT;
-	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
-	 * orig_ax, the unsigned int return value truncates it.  This may
-	 * or may not be necessary, but it matches the old asm behavior.
-	 */
-	return (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
+	return (unsigned int)regs->orig_ax;
 }
 
 /*
@@ -91,15 +85,29 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	unsigned int nr = syscall_32_enter(regs);
 
+	/*
+	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
+	 * orig_ax, the unsigned int return value truncates it.  This may
+	 * or may not be necessary, but it matches the old asm behavior.
+	 */
+	nr = (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
 	do_syscall_32_irqs_on(regs, nr);
 	syscall_exit_to_user_mode(regs);
 }
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
-	unsigned int nr	= syscall_32_enter(regs);
+	unsigned int nr = syscall_32_enter(regs);
 	int res;
 
+	/*
+	 * This cannot use syscall_enter_from_user_mode() as it has to
+	 * fetch EBP before invoking any of the syscall entry work
+	 * functions.
+	 */
+	syscall_enter_from_user_mode_prepare(regs);
+
 	instrumentation_begin();
 	/* Fetch EBP from where the vDSO stashed it. */
 	if (IS_ENABLED(CONFIG_X86_64)) {
@@ -122,6 +130,9 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		return false;
 	}
 
+	/* The case truncates any ptrace induced syscall nr > 2^32 -1 */
+	nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr);
+
 	/* Now this is just like a normal syscall. */
 	do_syscall_32_irqs_on(regs, nr);
 	syscall_exit_to_user_mode(regs);
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 3a07ce3ec70b..f1f96d4d8cd6 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -29,11 +29,6 @@ SYM_CODE_START_NOALIGN(\name)
 SYM_CODE_END(\name)
 	.endm
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
-	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
 #ifdef CONFIG_PREEMPTION
 	THUNK preempt_schedule_thunk, preempt_schedule
 	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 50963472ee85..31e6887d24f1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4682,7 +4682,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
-		/* fall through */
+		fallthrough;
 
 	case INTEL_FAM6_CORE2_MEROM_L:
 	case INTEL_FAM6_CORE2_PENRYN:
@@ -5062,7 +5062,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_SKYLAKE_X:
 		pmem = true;
-		/* fall through */
+		fallthrough;
 	case INTEL_FAM6_SKYLAKE_L:
 	case INTEL_FAM6_SKYLAKE:
 	case INTEL_FAM6_KABYLAKE_L:
@@ -5114,7 +5114,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_ICELAKE_D:
 		pmem = true;
-		/* fall through */
+		fallthrough;
 	case INTEL_FAM6_ICELAKE_L:
 	case INTEL_FAM6_ICELAKE:
 	case INTEL_FAM6_TIGERLAKE_L:
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 63f58bdf556c..8961653c5dd2 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1268,7 +1268,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			ret = X86_BR_ZERO_CALL;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case 0x9a: /* call far absolute */
 		ret = X86_BR_CALL;
 		break;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index cb94ba86efd2..6a4ca27b2c9e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = {
 	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
 	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
 
+	INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"),
+	INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"),
+	INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"),
+	INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"),
+
 	{ /* end: all zeroes */ },
 };
 
@@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = {
 #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
 #define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
 
+/* BW break down- legacy counters */
+#define SNB_UNCORE_PCI_IMC_GT_REQUESTS		0x3
+#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE	0x5040
+#define SNB_UNCORE_PCI_IMC_IA_REQUESTS		0x4
+#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE	0x5044
+#define SNB_UNCORE_PCI_IMC_IO_REQUESTS		0x5
+#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE	0x5048
+
 enum perf_snb_uncore_imc_freerunning_types {
-	SNB_PCI_UNCORE_IMC_DATA		= 0,
+	SNB_PCI_UNCORE_IMC_DATA_READS		= 0,
+	SNB_PCI_UNCORE_IMC_DATA_WRITES,
+	SNB_PCI_UNCORE_IMC_GT_REQUESTS,
+	SNB_PCI_UNCORE_IMC_IA_REQUESTS,
+	SNB_PCI_UNCORE_IMC_IO_REQUESTS,
+
 	SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
 };
 
 static struct freerunning_counters snb_uncore_imc_freerunning[] = {
-	[SNB_PCI_UNCORE_IMC_DATA]     = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 },
+	[SNB_PCI_UNCORE_IMC_DATA_READS]		= { SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+							0x0, 0x0, 1, 32 },
+	[SNB_PCI_UNCORE_IMC_DATA_READS]		= { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
+							0x0, 0x0, 1, 32 },
+	[SNB_PCI_UNCORE_IMC_GT_REQUESTS]	= { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE,
+							0x0, 0x0, 1, 32 },
+	[SNB_PCI_UNCORE_IMC_IA_REQUESTS]	= { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE,
+							0x0, 0x0, 1, 32 },
+	[SNB_PCI_UNCORE_IMC_IO_REQUESTS]	= { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE,
+							0x0, 0x0, 1, 32 },
 };
 
 static struct attribute *snb_uncore_imc_formats_attr[] = {
@@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
 		idx = UNCORE_PMC_IDX_FREERUNNING;
 		break;
+	case SNB_UNCORE_PCI_IMC_GT_REQUESTS:
+		base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
+		break;
+	case SNB_UNCORE_PCI_IMC_IA_REQUESTS:
+		base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
+		break;
+	case SNB_UNCORE_PCI_IMC_IO_REQUESTS:
+		base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 
 static struct intel_uncore_type snb_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 2,
+	.num_counters   = 5,
 	.num_boxes	= 1,
 	.num_freerunning_types	= SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
 	.mmio_map_size	= SNB_UNCORE_PCI_IMC_MAP_SIZE,
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b9c2667ac46c..bc9758ef292e 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table;
 	kernel_fpu_end();						\
 })
 
-
 #define arch_efi_call_virt(p, f, args...)	p->f(args)
 
-#define efi_ioremap(addr, size, type, attr)	ioremap_cache(addr, size)
-
 #else /* !CONFIG_X86_32 */
 
 #define EFI_LOADER_SIGNATURE	"EL64"
@@ -125,9 +122,6 @@ struct efi_scratch {
 	kernel_fpu_end();						\
 })
 
-extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
-					u32 type, u64 attribute);
-
 #ifdef CONFIG_KASAN
 /*
  * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
@@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern struct efi_scratch efi_scratch;
-extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int __init efi_memblock_x86_reserve_range(void);
 extern void __init efi_print_memmap(void);
-extern void __init efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
 extern int __init efi_alloc_page_tables(void);
 extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
-extern void __init old_map_region(efi_memory_desc_t *md);
-extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_update_mappings(void);
 extern void __init efi_dump_pagetable(void);
 extern void __init efi_apply_memmap_quirks(void);
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index a8f9315b9eae..6fe54b2813c1 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -18,8 +18,16 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		 * state, not the interrupt state as imagined by Xen.
 		 */
 		unsigned long flags = native_save_fl();
-		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
-				      X86_EFLAGS_NT));
+		unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT;
+
+		/*
+		 * For !SMAP hardware we patch out CLAC on entry.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMAP) ||
+		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+			mask |= X86_EFLAGS_AC;
+
+		WARN_ON_ONCE(flags & mask);
 
 		/* We think we came from user mode. Make sure pt_regs agrees. */
 		WARN_ON_ONCE(!user_mode(regs));
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5ab3af7275d8..5303dbc5c9bc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void);
 	_ASM_EXTABLE(666b, 667b)
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 0a301ad0b02f..9257667d13c5 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -59,5 +59,6 @@ typedef struct {
 	}
 
 void leave_mm(int cpu);
+#define leave_mm leave_mm
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 40aa69d04862..d8324a236696 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -327,8 +327,8 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
 	static const unsigned int argument_offs[] = {
 #ifdef __i386__
 		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
 		offsetof(struct pt_regs, dx),
+		offsetof(struct pt_regs, cx),
 #define NR_REG_ARGUMENTS 3
 #else
 		offsetof(struct pt_regs, di),
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c3daf0aaa0ee..cdaab30880b9 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -239,7 +239,7 @@ void __init arch_init_ideal_nops(void)
 			return;
 		}
 
-		/* fall through */
+		fallthrough;
 
 	default:
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 21325a4a78b9..779a89e31c4c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -800,7 +800,7 @@ static int irq_polarity(int idx)
 		return IOAPIC_POL_HIGH;
 	case MP_IRQPOL_RESERVED:
 		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
-		/* fall through */
+		fallthrough;
 	case MP_IRQPOL_ACTIVE_LOW:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_POL_LOW;
@@ -848,7 +848,7 @@ static int irq_trigger(int idx)
 		return IOAPIC_EDGE;
 	case MP_IRQTRIG_RESERVED:
 		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
-		/* fall through */
+		fallthrough;
 	case MP_IRQTRIG_LEVEL:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_LEVEL;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 7bda71def557..99ee61c9ba54 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -149,7 +149,7 @@ void __init default_setup_apic_routing(void)
 				break;
 			}
 			/* P4 and above */
-			/* fall through */
+			fallthrough;
 		case X86_VENDOR_HYGON:
 		case X86_VENDOR_AMD:
 			def_to_bigsmp = 1;
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index dae32d948bf2..f8a56b5dc29f 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec,
 		apicd->move_in_progress = true;
 		apicd->prev_vector = apicd->vector;
 		apicd->prev_cpu = apicd->cpu;
+		WARN_ON_ONCE(apicd->cpu == newcpu);
 	} else {
 		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
 				managed);
@@ -910,7 +911,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 		__send_cleanup_vector(apicd);
 }
 
-static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
+void irq_complete_move(struct irq_cfg *cfg)
 {
 	struct apic_chip_data *apicd;
 
@@ -918,15 +919,16 @@ static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 	if (likely(!apicd->move_in_progress))
 		return;
 
-	if (vector == apicd->vector && apicd->cpu == smp_processor_id())
+	/*
+	 * If the interrupt arrived on the new target CPU, cleanup the
+	 * vector on the old target CPU. A vector check is not required
+	 * because an interrupt can never move from one vector to another
+	 * on the same CPU.
+	 */
+	if (apicd->cpu == smp_processor_id())
 		__send_cleanup_vector(apicd);
 }
 
-void irq_complete_move(struct irq_cfg *cfg)
-{
-	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
-}
-
 /*
  * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
  */
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index c7503be92f35..57074cf3ad7c 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -248,7 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	switch (leaf) {
 	case 1:
 		l1 = &l1i;
-		/* fall through */
+		fallthrough;
 	case 0:
 		if (!l1->val)
 			return;
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 7843ab3fde09..3a44346f2276 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -199,7 +199,7 @@ static int raise_local(void)
 			 * calling irq_enter, but the necessary
 			 * machinery isn't exported currently.
 			 */
-			/*FALL THROUGH*/
+			fallthrough;
 		case MCJ_CTX_PROCESS:
 			raise_exception(m, NULL);
 			break;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index d8f9230d2034..abe9fe0fb851 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -193,7 +193,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 		if (!atomic_sub_return(1, &cmci_storm_on_cpus))
 			pr_notice("CMCI storm subsided: switching to interrupt mode\n");
 
-		/* FALLTHROUGH */
+		fallthrough;
 
 	case CMCI_STORM_SUBSIDED:
 		/*
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 72182809b333..ca670919b561 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -98,7 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 	case 7:
 		if (size < 0x40)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	case 6:
 	case 5:
 	case 4:
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 8cdf29ffd95f..b98ff620ba77 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -349,7 +349,7 @@ static int arch_build_bp_info(struct perf_event *bp,
 			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 68acd30c6b87..c2f02f308ecf 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -450,7 +450,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 		ptr = &remcomInBuffer[1];
 		if (kgdb_hex2long(&ptr, &addr))
 			linux_regs->ip = addr;
-		/* fall through */
+		fallthrough;
 	case 'D':
 	case 'k':
 		/* clear the trace bit */
@@ -539,7 +539,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 			 * a system call which should be ignored
 			 */
 			return NOTIFY_DONE;
-		/* fall through */
+		fallthrough;
 	default:
 		if (user_mode(regs))
 			return NOTIFY_DONE;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 08320b0b2b27..1b51b727b140 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	u32 token;
-	irqentry_state_t state;
 
-	state = irqentry_enter(regs);
+	ack_APIC_irq();
 
 	inc_irq_stat(irq_hv_callback_count);
 
@@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
 	}
 
-	irqentry_exit(regs, state);
 	set_irq_regs(old_regs);
 }
 
@@ -654,7 +652,6 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (pv_tlb_flush_supported()) {
-		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
@@ -767,6 +764,14 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
+static void kvm_free_pv_cpu_mask(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		free_cpumask_var(per_cpu(__pv_cpu_mask, cpu));
+}
+
 static __init int kvm_alloc_cpumask(void)
 {
 	int cpu;
@@ -785,11 +790,20 @@ static __init int kvm_alloc_cpumask(void)
 
 	if (alloc)
 		for_each_possible_cpu(cpu) {
-			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
-				GFP_KERNEL, cpu_to_node(cpu));
+			if (!zalloc_cpumask_var_node(
+				per_cpu_ptr(&__pv_cpu_mask, cpu),
+				GFP_KERNEL, cpu_to_node(cpu))) {
+				goto zalloc_cpumask_fail;
+			}
 		}
 
+	apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
+	pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 	return 0;
+
+zalloc_cpumask_fail:
+	kvm_free_pv_cpu_mask();
+	return -ENOMEM;
 }
 arch_initcall(kvm_alloc_cpumask);
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 411af4aa7b51..baa21090c9be 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -312,7 +312,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 		case 2:
 			if (i == 0 || i == 13)
 				continue;	/* IRQ0 & IRQ13 not connected */
-			/* fall through */
+			fallthrough;
 		default:
 			if (i == 2)
 				continue;	/* IRQ2 is never connected */
@@ -356,7 +356,7 @@ static void __init construct_ioapic_table(int mpc_default_type)
 	default:
 		pr_err("???\nUnknown standard configuration %d\n",
 		       mpc_default_type);
-		/* fall through */
+		fallthrough;
 	case 1:
 	case 5:
 		memcpy(bus.bustype, "ISA   ", 6);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 994d8393f2f7..13ce616cc7af 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -684,9 +684,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	safe_halt();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -792,7 +790,6 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 static __cpuidle void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
-		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
 			mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
@@ -804,7 +801,6 @@ static __cpuidle void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
-		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 	}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 5679aa3fdcb8..e7537c5440bb 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -204,7 +204,7 @@ static int set_segment_reg(struct task_struct *task,
 	case offsetof(struct user_regs_struct, ss):
 		if (unlikely(value == 0))
 			return -EIO;
-		/* Else, fall through */
+		fallthrough;
 
 	default:
 		*pt_regs_access(task_pt_regs(task), offset) = value;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0ec7ced727fe..a515e2d230b7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -654,7 +654,7 @@ static void native_machine_emergency_restart(void)
 
 		case BOOT_CF9_FORCE:
 			port_cf9_safe = true;
-			/* Fall through */
+			fallthrough;
 
 		case BOOT_CF9_SAFE:
 			if (port_cf9_safe) {
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index d5fa494c2304..be0d7d4152ec 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -726,7 +726,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 				regs->ax = -EINTR;
 				break;
 			}
-		/* fallthrough */
+			fallthrough;
 		case -ERESTARTNOINTR:
 			regs->ax = regs->orig_ax;
 			regs->ip -= 2;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 27aa04a95702..f5ef689dd62a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1594,14 +1594,28 @@ int native_cpu_disable(void)
 	if (ret)
 		return ret;
 
-	/*
-	 * Disable the local APIC. Otherwise IPI broadcasts will reach
-	 * it. It still responds normally to INIT, NMI, SMI, and SIPI
-	 * messages.
-	 */
-	apic_soft_disable();
 	cpu_disable_common();
 
+        /*
+         * Disable the local APIC. Otherwise IPI broadcasts will reach
+         * it. It still responds normally to INIT, NMI, SMI, and SIPI
+         * messages.
+         *
+         * Disabling the APIC must happen after cpu_disable_common()
+         * which invokes fixup_irqs().
+         *
+         * Disabling the APIC preserves already set bits in IRR, but
+         * an interrupt arriving after disabling the local APIC does not
+         * set the corresponding IRR bit.
+         *
+         * fixup_irqs() scans IRR for set bits so it can raise a not
+         * yet handled interrupt on the new destination CPU via an IPI
+         * but obviously it can't do so for IRR bits which are not set.
+         * IOW, interrupts arriving after disabling the local APIC will
+         * be lost.
+         */
+	apic_soft_disable();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1f66d2d1e998..81a2fb711091 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -729,20 +729,9 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
 #endif
 }
 
-static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7)
+static __always_inline unsigned long debug_read_clear_dr6(void)
 {
-	/*
-	 * Disable breakpoints during exception handling; recursive exceptions
-	 * are exceedingly 'fun'.
-	 *
-	 * Since this function is NOKPROBE, and that also applies to
-	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
-	 * HW_BREAKPOINT_W on our stack)
-	 *
-	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
-	 * includes the entry stack is excluded for everything.
-	 */
-	*dr7 = local_db_save();
+	unsigned long dr6;
 
 	/*
 	 * The Intel SDM says:
@@ -755,15 +744,12 @@ static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7)
 	 *
 	 * Keep it simple: clear DR6 immediately.
 	 */
-	get_debugreg(*dr6, 6);
+	get_debugreg(dr6, 6);
 	set_debugreg(0, 6);
 	/* Filter out all the reserved bits which are preset to 1 */
-	*dr6 &= ~DR6_RESERVED;
-}
+	dr6 &= ~DR6_RESERVED;
 
-static __always_inline void debug_exit(unsigned long dr7)
-{
-	local_db_restore(dr7);
+	return dr6;
 }
 
 /*
@@ -863,6 +849,18 @@ out:
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
+	/*
+	 * Disable breakpoints during exception handling; recursive exceptions
+	 * are exceedingly 'fun'.
+	 *
+	 * Since this function is NOKPROBE, and that also applies to
+	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
+	 * HW_BREAKPOINT_W on our stack)
+	 *
+	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
+	 * includes the entry stack is excluded for everything.
+	 */
+	unsigned long dr7 = local_db_save();
 	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
 
@@ -883,6 +881,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 
 	instrumentation_end();
 	idtentry_exit_nmi(regs, irq_state);
+
+	local_db_restore(dr7);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
@@ -894,6 +894,15 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	 */
 	WARN_ON_ONCE(!user_mode(regs));
 
+	/*
+	 * NB: We can't easily clear DR7 here because
+	 * idtentry_exit_to_usermode() can invoke ptrace, schedule, access
+	 * user memory, etc.  This means that a recursive #DB is possible.  If
+	 * this happens, that #DB will hit exc_debug_kernel() and clear DR7.
+	 * Since we're not on the IST stack right now, everything will be
+	 * fine.
+	 */
+
 	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
 
@@ -907,36 +916,24 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_kernel(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_kernel(regs, debug_read_clear_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_user(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_user(regs, debug_read_clear_dr6());
 }
 #else
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
+	unsigned long dr6 = debug_read_clear_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);
 	else
 		exc_debug_kernel(regs, dr6);
-
-	debug_exit(dr7);
 }
 #endif
 
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 15e5aad8ac2c..3fdaa042823d 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -735,7 +735,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 		 * OPCODE1() of the "short" jmp which checks the same condition.
 		 */
 		opc1 = OPCODE2(insn) - 0x10;
-		/* fall through */
+		fallthrough;
 	default:
 		if (!is_cond_jmp_opcode(opc1))
 			return -ENOSYS;
@@ -892,7 +892,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			fix_ip_or_call = 0;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		riprel_analyze(auprobe, &insn);
 	}
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d0e2825ae617..2f6510de6b0c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7fc8);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
 	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
@@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
 	val = GET_SMSTATE(u32, smstate, 0x7f68);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7f60);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
 	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
 	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
-	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
 	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
@@ -3016,7 +3028,7 @@ static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
 	case 0xa4:	/* movsb */
 	case 0xa5:	/* movsd/w */
 		*reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1;
-		/* fall through */
+		fallthrough;
 	case 0xaa:	/* stosb */
 	case 0xab:	/* stosd/w */
 		*reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 814d3aee5cef..1d330564eed8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1779,7 +1779,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
 		if (ret != HV_STATUS_INVALID_PORT_ID)
 			break;
-		/* fall through - maybe userspace knows this conn_id. */
+		fallthrough;	/* maybe userspace knows this conn_id */
 	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
 		if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index c47d2acec529..4aa1c2e00e2a 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -285,7 +285,7 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		switch (ue->u.irqchip.irqchip) {
 		case KVM_IRQCHIP_PIC_SLAVE:
 			e->irqchip.pin += PIC_NUM_PINS / 2;
-			/* fall through */
+			fallthrough;
 		case KVM_IRQCHIP_PIC_MASTER:
 			if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2)
 				return -EINVAL;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5ccbee7165a2..35cca2e0c802 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1053,7 +1053,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	switch (delivery_mode) {
 	case APIC_DM_LOWEST:
 		vcpu->arch.apic_arb_prio++;
-		/* fall through */
+		fallthrough;
 	case APIC_DM_FIXED:
 		if (unlikely(trig_mode && !level))
 			break;
@@ -1341,7 +1341,7 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 		break;
 	case APIC_TASKPRI:
 		report_tpr_access(apic, false);
-		/* fall thru */
+		fallthrough;
 	default:
 		val = kvm_lapic_get_reg(apic, offset);
 		break;
@@ -2027,7 +2027,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_LVT0:
 		apic_manage_nmi_watchdog(apic, val);
-		/* fall through */
+		fallthrough;
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 4e03841f053d..71aa3da2a0b7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
 }
@@ -2468,7 +2469,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		}
 
 		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
 
 		__clear_sp_write_flooding_count(sp);
 
@@ -4421,7 +4422,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[1][4] =
 			rsvd_check->rsvd_bits_mask[0][4];
-		/* fall through */
+		fallthrough;
 	case PT64_ROOT_4LEVEL:
 		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index fb68467e6049..e90bc436f584 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -586,7 +586,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	/* Give the current vmcb to the guest */
-	svm_set_gif(svm, false);
 
 	nested_vmcb->save.es     = vmcb->save.es;
 	nested_vmcb->save.cs     = vmcb->save.cs;
@@ -632,6 +631,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(&vmcb->control, &hsave->control);
 
+	/* On vmexit the  GIF is set to false */
+	svm_set_gif(svm, false);
+
 	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
 		svm->vcpu.arch.l1_tsc_offset;
 
@@ -1132,6 +1134,9 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	load_nested_vmcb_control(svm, &ctl);
 	nested_prepare_vmcb_control(svm);
 
+	if (!nested_svm_vmrun_msrpm(svm))
+		return -EINVAL;
+
 out_set_gif:
 	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 	return 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 402dc4234e39..7bf7bf734979 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1106,6 +1106,7 @@ void sev_vm_destroy(struct kvm *kvm)
 		list_for_each_safe(pos, q, head) {
 			__unregister_enc_region_locked(kvm,
 				list_entry(pos, struct enc_region, list));
+			cond_resched();
 		}
 	}
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 03dd7bac8034..c44f3e9140d5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2668,7 +2668,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);
-		/* Fall through */
+		fallthrough;
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -2938,8 +2938,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (npt_enabled)
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
 
-	svm_complete_interrupts(svm);
-
 	if (is_guest_mode(vcpu)) {
 		int vmexit;
 
@@ -3504,7 +3502,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	stgi();
 
 	/* Any pending NMI will happen here */
-	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_after_interrupt(&svm->vcpu);
@@ -3518,6 +3515,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
+	vmcb_mark_all_clean(svm->vmcb);
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
@@ -3537,7 +3535,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
 		svm_handle_mce(svm);
 
-	vmcb_mark_all_clean(svm->vmcb);
+	svm_complete_interrupts(svm);
+	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 	return exit_fastpath;
 }
 
@@ -3900,21 +3899,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *nested_vmcb;
 	struct kvm_host_map map;
-	u64 guest;
-	u64 vmcb;
 	int ret = 0;
 
-	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+		u64 vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (guest) {
-		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
-			return 1;
-		nested_vmcb = map.hva;
-		ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb);
-		kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		if (guest) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+				return 1;
+
+			if (!(saved_efer & EFER_SVME))
+				return 1;
+
+			if (kvm_vcpu_map(&svm->vcpu,
+					 gpa_to_gfn(vmcb), &map) == -EINVAL)
+				return 1;
+
+			ret = enter_svm_guest_mode(svm, vmcb, map.hva);
+			kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		}
 	}
 
 	return ret;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c28a1c9..1bb6b31eb646 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4404,6 +4404,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);
 
+	/*
+	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
+	 * now and the new vmentry.  Ensure that the VMCS02 PDPTR fields are
+	 * up-to-date before switching to L1.
+	 */
+	if (enable_ept && is_pae_paging(vcpu))
+		vmx_ept_load_pdptrs(vcpu);
+
 	leave_guest_mode(vcpu);
 
 	if (nested_cpu_has_preemption_timer(vmcs12))
@@ -4668,7 +4676,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 		vmx->nested.msrs.entry_ctls_high &=
 				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 		vmx->nested.msrs.exit_ctls_high &=
-				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+				~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 46ba2e03a892..8646a797b7a8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2971,7 +2971,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	vpid_sync_context(to_vmx(vcpu)->vpid);
 }
 
-static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
@@ -3114,7 +3114,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
 			guest_cr3 = vcpu->arch.cr3;
 		else /* vmcs01.GUEST_CR3 is already up-to-date. */
 			update_guest_cr3 = false;
-		ept_load_pdptrs(vcpu);
+		vmx_ept_load_pdptrs(vcpu);
 	} else {
 		guest_cr3 = pgd;
 	}
@@ -4654,7 +4654,7 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
 			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
 			return false;
-		/* fall through */
+		fallthrough;
 	case DB_VECTOR:
 		return !(vcpu->guest_debug &
 			(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP));
@@ -4827,7 +4827,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 		}
 		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
 		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
-		/* fall through */
+		fallthrough;
 	case BP_VECTOR:
 		/*
 		 * Update instruction length as we may reinject #BP from
@@ -5257,7 +5257,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 				error_code =
 					vmcs_read32(IDT_VECTORING_ERROR_CODE);
 			}
-			/* fall through */
+			fallthrough;
 		case INTR_TYPE_SOFT_EXCEPTION:
 			kvm_clear_exception_queue(vcpu);
 			break;
@@ -5610,7 +5610,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 		 * keeping track of global entries in shadow page tables.
 		 */
 
-		/* fall-through */
+		fallthrough;
 	case INVPCID_TYPE_ALL_INCL_GLOBAL:
 		kvm_mmu_unload(vcpu);
 		return kvm_skip_emulated_instruction(vcpu);
@@ -6054,6 +6054,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -6578,7 +6579,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
 		break;
 	case INTR_TYPE_SOFT_EXCEPTION:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
-		/* fall through */
+		fallthrough;
 	case INTR_TYPE_HARD_EXCEPTION:
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
 			u32 err = vmcs_read32(error_code_field);
@@ -6588,7 +6589,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
 		break;
 	case INTR_TYPE_SOFT_INTR:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
-		/* fall through */
+		fallthrough;
 	case INTR_TYPE_EXT_INTR:
 		kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR);
 		break;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 26175a4759fa..a2f82127c170 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -356,6 +356,7 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
 int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 			      struct x86_exception *e);
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 599d73206299..1994602a0851 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -975,7 +975,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+				   X86_CR4_SMEP;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -1116,14 +1116,12 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 			vcpu->arch.eff_db[dr] = val;
 		break;
 	case 4:
-		/* fall through */
 	case 6:
 		if (!kvm_dr6_valid(val))
 			return -1; /* #GP */
 		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
 		break;
 	case 5:
-		/* fall through */
 	default: /* 7 */
 		if (!kvm_dr7_valid(val))
 			return -1; /* #GP */
@@ -1154,12 +1152,10 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 		*val = vcpu->arch.db[array_index_nospec(dr, size)];
 		break;
 	case 4:
-		/* fall through */
 	case 6:
 		*val = vcpu->arch.dr6;
 		break;
 	case 5:
-		/* fall through */
 	default: /* 7 */
 		*val = vcpu->arch.dr7;
 		break;
@@ -2735,7 +2731,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 1;
 
 	if (!lapic_in_kernel(vcpu))
-		return 1;
+		return data ? 1 : 0;
 
 	vcpu->arch.apf.msr_en_val = data;
 
@@ -3051,7 +3047,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 	case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
-		pr = true; /* fall through */
+		pr = true;
+		fallthrough;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 	case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
 		if (kvm_pmu_is_valid_msr(vcpu, msr))
@@ -3581,6 +3578,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = sched_info_on();
+		break;
 	default:
 		break;
 	}
@@ -4359,7 +4359,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	case KVM_CAP_HYPERV_SYNIC2:
 		if (cap->args[0])
 			return -EINVAL;
-		/* fall through */
+		fallthrough;
 
 	case KVM_CAP_HYPERV_SYNIC:
 		if (!irqchip_in_kernel(vcpu->kvm))
@@ -8672,7 +8672,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 		vcpu->arch.pv.pv_unhalted = false;
 		vcpu->arch.mp_state =
 			KVM_MP_STATE_RUNNABLE;
-		/* fall through */
+		fallthrough;
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.apf.halted = false;
 		break;
@@ -10751,9 +10751,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value);
 void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code)
 {
 	struct x86_exception fault;
+	u32 access = error_code &
+		(PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK);
 
 	if (!(error_code & PFERR_PRESENT_MASK) ||
-	    vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) {
+	    vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) {
 		/*
 		 * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page
 		 * tables probably do not match the TLB.  Just proceed
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index d46fff11f06f..aa067859a70b 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_cmdline.o = -pg
 endif
 
-CFLAGS_cmdline.o := -fno-stack-protector
+CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
 endif
 
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
index 4f1719e22d3c..b6da09339308 100644
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -58,7 +58,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size,
 			state = st_wordcmp;
 			opptr = option;
 			wstart = pos;
-			/* fall through */
+			fallthrough;
 
 		case st_wordcmp:
 			if (!*opptr) {
@@ -89,7 +89,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size,
 				break;
 			}
 			state = st_wordskip;
-			/* fall through */
+			fallthrough;
 
 		case st_wordskip:
 			if (!c)
@@ -151,7 +151,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size,
 
 			state = st_wordcmp;
 			opptr = option;
-			/* fall through */
+			fallthrough;
 
 		case st_wordcmp:
 			if ((c == '=') && !*opptr) {
@@ -172,7 +172,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size,
 				break;
 			}
 			state = st_wordskip;
-			/* fall through */
+			fallthrough;
 
 		case st_wordskip:
 			if (myisspace(c))
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 31600d851fd8..5e69603ff63f 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -179,7 +179,7 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off)
 		if (insn->addr_bytes == 2)
 			return -EINVAL;
 
-		/* fall through */
+		fallthrough;
 
 	case -EDOM:
 	case offsetof(struct pt_regs, bx):
@@ -362,7 +362,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 		case INAT_SEG_REG_GS:
 			return vm86regs->gs;
 		case INAT_SEG_REG_IGNORE:
-			/* fall through */
 		default:
 			return -EINVAL;
 		}
@@ -386,7 +385,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 		 */
 		return get_user_gs(regs);
 	case INAT_SEG_REG_IGNORE:
-		/* fall through */
 	default:
 		return -EINVAL;
 	}
@@ -786,7 +784,7 @@ int insn_get_code_seg_params(struct pt_regs *regs)
 		 */
 		return INSN_CODE_SEG_PARAMS(4, 8);
 	case 3: /* Invalid setting. CS.L=1, CS.D=1 */
-		/* fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c
index 73dc66d887f3..ec071cbb0804 100644
--- a/arch/x86/math-emu/errors.c
+++ b/arch/x86/math-emu/errors.c
@@ -186,7 +186,7 @@ void FPU_printall(void)
 		case TAG_Special:
 			/* Update tagi for the printk below */
 			tagi = FPU_Special(r);
-			/* fall through */
+			fallthrough;
 		case TAG_Valid:
 			printk("st(%d)  %c .%04lx %04lx %04lx %04lx e%+-6d ", i,
 			       getsign(r) ? '-' : '+',
diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c
index 127ea54122d7..4a9887851ad8 100644
--- a/arch/x86/math-emu/fpu_trig.c
+++ b/arch/x86/math-emu/fpu_trig.c
@@ -1352,7 +1352,7 @@ static void fyl2xp1(FPU_REG *st0_ptr, u_char st0_tag)
 		case TW_Denormal:
 			if (denormal_operand() < 0)
 				return;
-			/* fall through */
+			fallthrough;
 		case TAG_Zero:
 		case TAG_Valid:
 			setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr));
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 35f1498e9832..6e3e8a124903 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -190,6 +190,53 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	return pmd_k;
 }
 
+/*
+ *   Handle a fault on the vmalloc or module mapping area
+ *
+ *   This is needed because there is a race condition between the time
+ *   when the vmalloc mapping code updates the PMD to the point in time
+ *   where it synchronizes this update with the other page-tables in the
+ *   system.
+ *
+ *   In this race window another thread/CPU can map an area on the same
+ *   PMD, finds it already present and does not synchronize it with the
+ *   rest of the system yet. As a result v[mz]alloc might return areas
+ *   which are not mapped in every page-table in the system, causing an
+ *   unhandled page-fault when they are accessed.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+	unsigned long pgd_paddr;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "current" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	pgd_paddr = read_cr3_pa();
+	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+	if (!pmd_k)
+		return -1;
+
+	if (pmd_large(*pmd_k))
+		return 0;
+
+	pte_k = pte_offset_kernel(pmd_k, address);
+	if (!pte_present(*pte_k))
+		return -1;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(vmalloc_fault);
+
 void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
@@ -1110,6 +1157,37 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 	 */
 	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
 
+#ifdef CONFIG_X86_32
+	/*
+	 * We can fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * Before doing this on-demand faulting, ensure that the
+	 * fault is not any of the following:
+	 * 1. A fault on a PTE with a reserved bit set.
+	 * 2. A fault caused by a user-mode access.  (Do not demand-
+	 *    fault kernel memory due to user-mode accesses).
+	 * 3. A fault caused by a page-level protection violation.
+	 *    (A demand fault would be on a non-present page which
+	 *     would have X86_PF_PROT==0).
+	 *
+	 * This is only needed to close a race condition on x86-32 in
+	 * the vmalloc mapping/unmapping code. See the comment above
+	 * vmalloc_fault() for details. On x86-64 the race does not
+	 * exist as the vmalloc mappings don't need to be synchronized
+	 * there.
+	 */
+	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+		if (vmalloc_fault(address) >= 0)
+			return;
+	}
+#endif
+
 	/* Was the fault spurious, caused by lazy TLB invalidation? */
 	if (spurious_kernel_fault(hw_error_code, address))
 		return;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 84d85dbd1dad..9e5ccc56f8e0 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -574,7 +574,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr,
 		/* For SEV, these areas are encrypted */
 		if (sev_active())
 			break;
-		/* Fallthrough */
+		fallthrough;
 
 	case E820_TYPE_PRAM:
 		return true;
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index c5174b4e318b..683cd12f4793 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -321,7 +321,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 					      u64 addr, u64 max_addr, u64 size)
 {
 	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
-			0, NULL, NUMA_NO_NODE);
+			0, NULL, 0);
 }
 
 static int __init setup_emu2phys_nid(int *dfl_phys_nid)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1a3569b43aa5..0951b47e64c1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, true);
 
-		/*
-		 * NB: This gets called via leave_mm() in the idle path
-		 * where RCU functions differently.  Tracing normally
-		 * uses RCU, so we need to use the _rcuidle variant.
-		 *
-		 * (There is no good reason for this.  The idle code should
-		 *  be rearranged to call this before rcu_idle_enter().)
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
 		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		/* See above wrt _rcuidle. */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
 	/* Make sure we write CR3 before loaded_mm. */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 9f9aad42ccff..89395a5049bb 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -26,6 +26,7 @@
 #include <asm/xen/pci.h>
 #include <asm/xen/cpuid.h>
 #include <asm/apic.h>
+#include <asm/acpi.h>
 #include <asm/i8259.h>
 
 static int xen_pcifront_enable_irq(struct pci_dev *dev)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f6ea8f1a9d57..d37ebe6e70d7 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -49,7 +49,6 @@
 #include <asm/efi.h>
 #include <asm/e820/api.h>
 #include <asm/time.h>
-#include <asm/set_memory.h>
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/uv/uv.h>
@@ -496,74 +495,6 @@ void __init efi_init(void)
 		efi_print_memmap();
 }
 
-#if defined(CONFIG_X86_32)
-
-void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
-{
-	u64 addr, npages;
-
-	addr = md->virt_addr;
-	npages = md->num_pages;
-
-	memrange_efi_to_native(&addr, &npages);
-
-	if (executable)
-		set_memory_x(addr, npages);
-	else
-		set_memory_nx(addr, npages);
-}
-
-void __init runtime_code_page_mkexec(void)
-{
-	efi_memory_desc_t *md;
-
-	/* Make EFI runtime service code area executable */
-	for_each_efi_memory_desc(md) {
-		if (md->type != EFI_RUNTIME_SERVICES_CODE)
-			continue;
-
-		efi_set_executable(md, true);
-	}
-}
-
-void __init efi_memory_uc(u64 addr, unsigned long size)
-{
-	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
-	u64 npages;
-
-	npages = round_up(size, page_shift) / page_shift;
-	memrange_efi_to_native(&addr, &npages);
-	set_memory_uc(addr, npages);
-}
-
-void __init old_map_region(efi_memory_desc_t *md)
-{
-	u64 start_pfn, end_pfn, end;
-	unsigned long size;
-	void *va;
-
-	start_pfn = PFN_DOWN(md->phys_addr);
-	size	  = md->num_pages << PAGE_SHIFT;
-	end	  = md->phys_addr + size;
-	end_pfn   = PFN_UP(end);
-
-	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
-		va = __va(md->phys_addr);
-
-		if (!(md->attribute & EFI_MEMORY_WB))
-			efi_memory_uc((u64)(unsigned long)va, size);
-	} else
-		va = efi_ioremap(md->phys_addr, size,
-				 md->type, md->attribute);
-
-	md->virt_addr = (u64) (unsigned long) va;
-	if (!va)
-		pr_err("ioremap of 0x%llX failed!\n",
-		       (unsigned long long)md->phys_addr);
-}
-
-#endif
-
 /* Merge contiguous regions of the same type and attribute */
 static void __init efi_merge_regions(void)
 {
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 826ead67753d..e06a199423c0 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -29,9 +29,35 @@
 #include <asm/io.h>
 #include <asm/desc.h>
 #include <asm/page.h>
+#include <asm/set_memory.h>
 #include <asm/tlbflush.h>
 #include <asm/efi.h>
 
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	u64 start_pfn, end_pfn, end;
+	unsigned long size;
+	void *va;
+
+	start_pfn	= PFN_DOWN(md->phys_addr);
+	size		= md->num_pages << PAGE_SHIFT;
+	end		= md->phys_addr + size;
+	end_pfn 	= PFN_UP(end);
+
+	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
+		va = __va(md->phys_addr);
+
+		if (!(md->attribute & EFI_MEMORY_WB))
+			set_memory_uc((unsigned long)va, md->num_pages);
+	} else {
+		va = ioremap_cache(md->phys_addr, size);
+	}
+
+	md->virt_addr = (unsigned long)va;
+	if (!va)
+		pr_err("ioremap of 0x%llX failed!\n", md->phys_addr);
+}
+
 /*
  * To make EFI call EFI runtime service in physical addressing mode we need
  * prolog/epilog before/after the invocation to claim the EFI runtime service
@@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	return 0;
 }
 
-void __init efi_map_region(efi_memory_desc_t *md)
-{
-	old_map_region(md);
-}
-
 void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
 void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
 
@@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size,
 
 void __init efi_runtime_update_mappings(void)
 {
-	if (__supported_pte_mask & _PAGE_NX)
-		runtime_code_page_mkexec();
+	if (__supported_pte_mask & _PAGE_NX) {
+		efi_memory_desc_t *md;
+
+		/* Make EFI runtime service code area executable */
+		for_each_efi_memory_desc(md) {
+			if (md->type != EFI_RUNTIME_SERVICES_CODE)
+				continue;
+
+			set_memory_x(md->virt_addr, md->num_pages);
+		}
+	}
 }
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 413583f904a6..6af4da1149ba 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT;
 	rodata = __pa(__start_rodata);
 	pfn = rodata >> PAGE_SHIFT;
+
+	pf = _PAGE_NX | _PAGE_ENC;
 	if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) {
 		pr_err("Failed to map kernel rodata 1:1\n");
 		return 1;
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 76cee341507b..b3b17d6c50f0 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -448,7 +448,7 @@ static void do_signal(struct pt_regs *regs)
 						regs->areg[2] = -EINTR;
 						break;
 					}
-					/* fallthrough */
+					fallthrough;
 				case -ERESTARTNOINTR:
 					regs->areg[2] = regs->syscall;
 					regs->pc -= 3;
diff --git a/block/badblocks.c b/block/badblocks.c
index 2e5f5697db35..d39056630d9c 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -525,7 +525,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
 	case 3:
 		if (newline != '\n')
 			return -EINVAL;
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (length <= 0)
 			return -EINVAL;
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 68882b9b8f11..b791e2041e49 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg)
 		kfree(bfqg);
 }
 
-void bfqg_and_blkg_get(struct bfq_group *bfqg)
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
 {
 	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
 	bfqg_get(bfqg);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a4c0bec920cb..fa98470df3f0 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4980,7 +4980,7 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 		pr_err("bdi %s: bfq: bad prio class %d\n",
 				bdi_dev_name(bfqq->bfqd->queue->backing_dev_info),
 				ioprio_class);
-		/* fall through */
+		fallthrough;
 	case IOPRIO_CLASS_NONE:
 		/*
 		 * No prio set, inherit CPU scheduling settings.
@@ -5112,7 +5112,7 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
 		return &bfqg->async_bfqq[0][ioprio];
 	case IOPRIO_CLASS_NONE:
 		ioprio = IOPRIO_NORM;
-		/* fall through */
+		fallthrough;
 	case IOPRIO_CLASS_BE:
 		return &bfqg->async_bfqq[1][ioprio];
 	case IOPRIO_CLASS_IDLE:
@@ -5896,18 +5896,6 @@ static void bfq_finish_requeue_request(struct request *rq)
 	struct bfq_data *bfqd;
 
 	/*
-	 * Requeue and finish hooks are invoked in blk-mq without
-	 * checking whether the involved request is actually still
-	 * referenced in the scheduler. To handle this fact, the
-	 * following two checks make this function exit in case of
-	 * spurious invocations, for which there is nothing to do.
-	 *
-	 * First, check whether rq has nothing to do with an elevator.
-	 */
-	if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
-		return;
-
-	/*
 	 * rq either is not associated with any icq, or is an already
 	 * requeued request that has not (yet) been re-inserted into
 	 * a bfq_queue.
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index cd224aaf9f52..703895224562 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -986,7 +986,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_and_blkg_get(struct bfq_group *bfqg);
 void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index eb0e2a6daabe..26776bdbdf36 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -533,9 +533,7 @@ static void bfq_get_entity(struct bfq_entity *entity)
 		bfqq->ref++;
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
 			     bfqq, bfqq->ref);
-	} else
-		bfqg_and_blkg_get(container_of(entity, struct bfq_group,
-					       entity));
+	}
 }
 
 /**
@@ -649,14 +647,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
 
 	entity->on_st_or_in_serv = false;
 	st->wsum -= entity->weight;
-	if (is_in_service)
-		return;
-
-	if (bfqq)
+	if (bfqq && !is_in_service)
 		bfq_put_queue(bfqq);
-	else
-		bfqg_and_blkg_put(container_of(entity, struct bfq_group,
-					       entity));
 }
 
 /**
diff --git a/block/bio.c b/block/bio.c
index c63ba04bd629..e865ea55b9f9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -740,8 +740,8 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		struct page *page, unsigned int len, unsigned int off,
 		bool *same_page)
 {
-	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
-		bv->bv_offset + bv->bv_len - 1;
+	size_t bv_end = bv->bv_offset + bv->bv_len;
+	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
 	phys_addr_t page_addr = page_to_phys(page);
 
 	if (vec_end_addr + 1 != page_addr + off)
@@ -750,9 +750,9 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		return false;
 
 	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
-	if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page)
-		return false;
-	return true;
+	if (*same_page)
+		return true;
+	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
 }
 
 /*
@@ -879,8 +879,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len)
+			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+				*same_page = false;
 				return false;
+			}
 			bv->bv_len += len;
 			bio->bi_iter.bi_size += len;
 			return true;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 619a79b51068..c195365c9817 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1152,13 +1152,15 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
+	ret = blk_throtl_init(q);
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(q);
-	if (ret)
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
 		goto err_destroy_all;
+	}
 	return 0;
 
 err_destroy_all:
diff --git a/block/blk-core.c b/block/blk-core.c
index d9d632639bd1..10c08ac50697 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -539,6 +539,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 		goto fail_stats;
 
 	q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
+	q->backing_dev_info->io_pages = VM_READAHEAD_PAGES;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 413e0b5c8e6b..d37b55db2409 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2092,14 +2092,15 @@ static void ioc_pd_free(struct blkg_policy_data *pd)
 {
 	struct ioc_gq *iocg = pd_to_iocg(pd);
 	struct ioc *ioc = iocg->ioc;
+	unsigned long flags;
 
 	if (ioc) {
-		spin_lock(&ioc->lock);
+		spin_lock_irqsave(&ioc->lock, flags);
 		if (!list_empty(&iocg->active_list)) {
 			propagate_active_weight(iocg, 0, 0);
 			list_del_init(&iocg->active_list);
 		}
-		spin_unlock(&ioc->lock);
+		spin_unlock_irqrestore(&ioc->lock, flags);
 
 		hrtimer_cancel(&iocg->waitq_timer);
 		hrtimer_cancel(&iocg->delay_timer);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 6529e3aab001..f685d633bcc9 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -154,7 +154,7 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	if (max_sectors > start_offset)
 		return max_sectors - start_offset;
 
-	return sectors & (lbs - 1);
+	return sectors & ~(lbs - 1);
 }
 
 static inline unsigned get_max_segment_size(const struct request_queue *q,
@@ -533,10 +533,17 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(__blk_rq_map_sg);
 
+static inline unsigned int blk_rq_get_max_segments(struct request *rq)
+{
+	if (req_op(rq) == REQ_OP_DISCARD)
+		return queue_max_discard_segments(rq->q);
+	return queue_max_segments(rq->q);
+}
+
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
 		unsigned int nr_phys_segs)
 {
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q))
+	if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
 		goto no_merge;
 
 	if (blk_integrity_merge_bio(req->q, req, bio) == false)
@@ -624,7 +631,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (total_phys_segments > queue_max_segments(q))
+	if (total_phys_segments > blk_rq_get_max_segments(req))
 		return 0;
 
 	if (blk_integrity_merge_rq(q, req, next) == false)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index a19cdf159b75..d2790e5b06d1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -78,6 +78,15 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 		return;
 	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
+	/*
+	 * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch)
+	 * in blk_mq_run_hw_queue(). Its pair is the barrier in
+	 * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART,
+	 * meantime new request added to hctx->dispatch is missed to check in
+	 * blk_mq_run_hw_queue().
+	 */
+	smp_mb();
+
 	blk_mq_run_hw_queue(hctx, true);
 }
 
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 126021fc3a11..e81ca1bf6e10 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -66,7 +66,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e && e->type->ops.requeue_request)
+	if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
 		e->type->ops.requeue_request(rq);
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0015a1892153..b3d2785eefe9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1438,6 +1438,15 @@ out:
 		spin_unlock(&hctx->lock);
 
 		/*
+		 * Order adding requests to hctx->dispatch and checking
+		 * SCHED_RESTART flag. The pair of this smp_mb() is the one
+		 * in blk_mq_sched_restart(). Avoid restart code path to
+		 * miss the new added requests to hctx->dispatch, meantime
+		 * SCHED_RESTART is observed here.
+		 */
+		smp_mb();
+
+		/*
 		 * If SCHED_RESTART was set by the caller of this function and
 		 * it is no longer set that means that it was cleared by another
 		 * thread and hence that a queue rerun is needed.
@@ -1834,6 +1843,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
+ * @at_head: true if the request should be inserted at the head of the list.
  * @run_queue: If we should run the hardware queue after inserting the request.
  *
  * Should only be used carefully, when the caller knows we want to
@@ -2016,7 +2026,8 @@ insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, false, run_queue);
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+
 	return BLK_STS_OK;
 }
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 7da302ff88d0..ae3dd1fb8e61 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -137,6 +137,7 @@ void blk_stat_add_callback(struct request_queue *q,
 			   struct blk_stat_callback *cb)
 {
 	unsigned int bucket;
+	unsigned long flags;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -147,20 +148,22 @@ void blk_stat_add_callback(struct request_queue *q,
 			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
-	spin_lock(&q->stats->lock);
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 
 void blk_stat_remove_callback(struct request_queue *q,
 			      struct blk_stat_callback *cb)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_del_rcu(&cb->list);
 	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
 		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 
 	del_timer_sync(&cb->timer);
 }
@@ -183,10 +186,12 @@ void blk_stat_free_callback(struct blk_stat_callback *cb)
 
 void blk_stat_enable_accounting(struct request_queue *q)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	q->stats->enable_accounting = true;
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 0fa615eefd52..fd410086fe1d 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -528,7 +528,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 		if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) ==
 		    (REQ_SYNC | REQ_IDLE))
 			return false;
-		/* fallthrough */
+		fallthrough;
 	case REQ_OP_DISCARD:
 		return true;
 	default:
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index fb7b347f8010..d185396d88bb 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -378,7 +378,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	bset->timeout_fn = timeout;
 
 	set = &bset->tag_set;
-	set->ops = &bsg_mq_ops,
+	set->ops = &bsg_mq_ops;
 	set->nr_hw_queues = 1;
 	set->queue_depth = 128;
 	set->numa_node = NUMA_NO_NODE;
diff --git a/block/ioprio.c b/block/ioprio.c
index 77bcab11dce5..04ebd37966f1 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -71,7 +71,7 @@ int ioprio_check_cap(int ioprio)
 		case IOPRIO_CLASS_RT:
 			if (!capable(CAP_SYS_ADMIN))
 				return -EPERM;
-			/* fall through */
+			fallthrough;
 			/* rt has prio field too */
 		case IOPRIO_CLASS_BE:
 			if (data >= IOPRIO_BE_NR || data < 0)
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e62a98a8eeb7..722406b841df 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -278,6 +278,15 @@ static void hd_struct_free_work(struct work_struct *work)
 {
 	struct hd_struct *part =
 		container_of(to_rcu_work(work), struct hd_struct, rcu_work);
+	struct gendisk *disk = part_to_disk(part);
+
+	/*
+	 * Release the disk reference acquired in delete_partition here.
+	 * We can't release it in hd_struct_free because the final put_device
+	 * needs process context and thus can't be run directly from a
+	 * percpu_ref ->release handler.
+	 */
+	put_device(disk_to_dev(disk));
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
@@ -293,7 +302,6 @@ static void hd_struct_free(struct percpu_ref *ref)
 		rcu_dereference_protected(disk->part_tbl, 1);
 
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
-	put_device(disk_to_dev(disk));
 
 	INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
 	queue_rcu_work(system_wq, &part->rcu_work);
@@ -524,19 +532,20 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 int bdev_del_partition(struct block_device *bdev, int partno)
 {
 	struct block_device *bdevp;
-	struct hd_struct *part;
-	int ret = 0;
+	struct hd_struct *part = NULL;
+	int ret;
 
-	part = disk_get_part(bdev->bd_disk, partno);
-	if (!part)
-		return -ENXIO;
-
-	ret = -ENOMEM;
-	bdevp = bdget(part_devt(part));
+	bdevp = bdget_disk(bdev->bd_disk, partno);
 	if (!bdevp)
-		goto out_put_part;
+		return -ENXIO;
 
 	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, 1);
+
+	ret = -ENXIO;
+	part = disk_get_part(bdev->bd_disk, partno);
+	if (!part)
+		goto out_unlock;
 
 	ret = -EBUSY;
 	if (bdevp->bd_openers)
@@ -545,16 +554,14 @@ int bdev_del_partition(struct block_device *bdev, int partno)
 	sync_blockdev(bdevp);
 	invalidate_bdev(bdevp);
 
-	mutex_lock_nested(&bdev->bd_mutex, 1);
 	delete_partition(bdev->bd_disk, part);
-	mutex_unlock(&bdev->bd_mutex);
-
 	ret = 0;
 out_unlock:
+	mutex_unlock(&bdev->bd_mutex);
 	mutex_unlock(&bdevp->bd_mutex);
 	bdput(bdevp);
-out_put_part:
-	disk_put_part(part);
+	if (part)
+		disk_put_part(part);
 	return ret;
 }
 
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index a6f581ab200c..8be8bec07cdd 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/sched.h>
 #include <linux/sched/signal.h>
 #include <linux/security.h>
 
@@ -845,9 +846,15 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	}
 
 	lock_sock(sk);
-	if (ctx->init && (init || !ctx->more)) {
-		err = -EINVAL;
-		goto unlock;
+	if (ctx->init && !ctx->more) {
+		if (ctx->used) {
+			err = -EINVAL;
+			goto unlock;
+		}
+
+		pr_info_once(
+			"%s sent an empty control message without MSG_MORE.\n",
+			current->comm);
 	}
 	ctx->init = true;
 
diff --git a/crypto/drbg.c b/crypto/drbg.c
index e99fe34cfa00..3132967a1749 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1521,7 +1521,7 @@ static int drbg_prepare_hrng(struct drbg_state *drbg)
 
 	case -EALREADY:
 		err = 0;
-		/* fall through */
+		fallthrough;
 
 	default:
 		drbg->random_ready.func = NULL;
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index ba0b7702f2e9..12e82a61b896 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -2348,121 +2348,121 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 			test_hash_speed(alg, sec, generic_hash_speed_template);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case 301:
 		test_hash_speed("md4", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 302:
 		test_hash_speed("md5", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 303:
 		test_hash_speed("sha1", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 304:
 		test_hash_speed("sha256", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 305:
 		test_hash_speed("sha384", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 306:
 		test_hash_speed("sha512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 307:
 		test_hash_speed("wp256", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 308:
 		test_hash_speed("wp384", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 309:
 		test_hash_speed("wp512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 310:
 		test_hash_speed("tgr128", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 311:
 		test_hash_speed("tgr160", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 312:
 		test_hash_speed("tgr192", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 313:
 		test_hash_speed("sha224", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 314:
 		test_hash_speed("rmd128", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 315:
 		test_hash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 316:
 		test_hash_speed("rmd256", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 317:
 		test_hash_speed("rmd320", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 318:
 		test_hash_speed("ghash-generic", sec, hash_speed_template_16);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 319:
 		test_hash_speed("crc32c", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 320:
 		test_hash_speed("crct10dif", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 321:
 		test_hash_speed("poly1305", sec, poly1305_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 322:
 		test_hash_speed("sha3-224", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 323:
 		test_hash_speed("sha3-256", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 324:
 		test_hash_speed("sha3-384", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 325:
 		test_hash_speed("sha3-512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 326:
 		test_hash_speed("sm3", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 327:
 		test_hash_speed("streebog256", sec,
 				generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 328:
 		test_hash_speed("streebog512", sec,
 				generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
-		/* fall through */
+		fallthrough;
 	case 399:
 		break;
 
@@ -2471,121 +2471,121 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 			test_ahash_speed(alg, sec, generic_hash_speed_template);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case 401:
 		test_ahash_speed("md4", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 402:
 		test_ahash_speed("md5", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 403:
 		test_ahash_speed("sha1", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 404:
 		test_ahash_speed("sha256", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 405:
 		test_ahash_speed("sha384", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 406:
 		test_ahash_speed("sha512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 407:
 		test_ahash_speed("wp256", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 408:
 		test_ahash_speed("wp384", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 409:
 		test_ahash_speed("wp512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 410:
 		test_ahash_speed("tgr128", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 411:
 		test_ahash_speed("tgr160", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 412:
 		test_ahash_speed("tgr192", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 413:
 		test_ahash_speed("sha224", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 414:
 		test_ahash_speed("rmd128", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 415:
 		test_ahash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 416:
 		test_ahash_speed("rmd256", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 417:
 		test_ahash_speed("rmd320", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 418:
 		test_ahash_speed("sha3-224", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 419:
 		test_ahash_speed("sha3-256", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 420:
 		test_ahash_speed("sha3-384", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 421:
 		test_ahash_speed("sha3-512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 422:
 		test_mb_ahash_speed("sha1", sec, generic_hash_speed_template,
 				    num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 423:
 		test_mb_ahash_speed("sha256", sec, generic_hash_speed_template,
 				    num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 424:
 		test_mb_ahash_speed("sha512", sec, generic_hash_speed_template,
 				    num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 425:
 		test_mb_ahash_speed("sm3", sec, generic_hash_speed_template,
 				    num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 426:
 		test_mb_ahash_speed("streebog256", sec,
 				    generic_hash_speed_template, num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 427:
 		test_mb_ahash_speed("streebog512", sec,
 				    generic_hash_speed_template, num_mb);
 		if (mode > 400 && mode < 500) break;
-		/* fall through */
+		fallthrough;
 	case 499:
 		break;
 
diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c
index c2b452af6806..9861302cc7db 100644
--- a/drivers/accessibility/braille/braille_console.c
+++ b/drivers/accessibility/braille/braille_console.c
@@ -290,7 +290,7 @@ static int vt_notifier_call(struct notifier_block *blk,
 			break;
 		case '\t':
 			c = ' ';
-			/* Fallthrough */
+			fallthrough;
 		default:
 			if (c < 32)
 				/* Ignore other control sequences */
diff --git a/drivers/accessibility/speakup/Kconfig b/drivers/accessibility/speakup/Kconfig
index 0803c2013cf4..07ecbbde0384 100644
--- a/drivers/accessibility/speakup/Kconfig
+++ b/drivers/accessibility/speakup/Kconfig
@@ -42,6 +42,11 @@ config SPEAKUP
 		one of the listed synthesizers, you should say n.
 
 if SPEAKUP
+
+config SPEAKUP_SERIALIO
+	def_bool y
+	depends on ISA || COMPILE_TEST
+
 config SPEAKUP_SYNTH_ACNTSA
 	tristate "Accent SA synthesizer support"
 	help
@@ -52,7 +57,7 @@ config SPEAKUP_SYNTH_ACNTSA
 
 config SPEAKUP_SYNTH_ACNTPC
 	tristate "Accent PC synthesizer support"
-	depends on ISA || COMPILE_TEST
+	depends on SPEAKUP_SERIALIO
 	help
 		This is the Speakup driver for the accent pc
 		synthesizer.  You can say y to build it into the kernel,
@@ -104,7 +109,7 @@ config SPEAKUP_SYNTH_DECEXT
 
 config SPEAKUP_SYNTH_DECPC
 	depends on m
-	depends on ISA || COMPILE_TEST
+	depends on SPEAKUP_SERIALIO
 	tristate "DECtalk PC (big ISA card) synthesizer support"
 	help
 
@@ -127,7 +132,7 @@ config SPEAKUP_SYNTH_DECPC
 
 config SPEAKUP_SYNTH_DTLK
 	tristate "DoubleTalk PC synthesizer support"
-	depends on ISA || COMPILE_TEST
+	depends on SPEAKUP_SERIALIO
 	help
 
 		This is the Speakup driver for the internal DoubleTalk
@@ -138,7 +143,7 @@ config SPEAKUP_SYNTH_DTLK
 
 config SPEAKUP_SYNTH_KEYPC
 	tristate "Keynote Gold PC synthesizer support"
-	depends on ISA || COMPILE_TEST
+	depends on SPEAKUP_SERIALIO
 	help
 
 		This is the Speakup driver for the Keynote Gold
diff --git a/drivers/accessibility/speakup/Makefile b/drivers/accessibility/speakup/Makefile
index 5befb4933b85..6e4bfac8af65 100644
--- a/drivers/accessibility/speakup/Makefile
+++ b/drivers/accessibility/speakup/Makefile
@@ -25,8 +25,8 @@ speakup-y := \
 	keyhelp.o \
 	kobjects.o \
 	selection.o \
-	serialio.o \
 	spk_ttyio.o \
 	synth.o \
 	thread.o \
 	varhandlers.o
+speakup-$(CONFIG_SPEAKUP_SERIALIO) += serialio.o
diff --git a/drivers/accessibility/speakup/serialio.c b/drivers/accessibility/speakup/serialio.c
index 177a2988641c..403b01d66367 100644
--- a/drivers/accessibility/speakup/serialio.c
+++ b/drivers/accessibility/speakup/serialio.c
@@ -32,6 +32,7 @@ static void spk_serial_tiocmset(unsigned int set, unsigned int clear);
 static unsigned char spk_serial_in(void);
 static unsigned char spk_serial_in_nowait(void);
 static void spk_serial_flush_buffer(void);
+static int spk_serial_wait_for_xmitr(struct spk_synth *in_synth);
 
 struct spk_io_ops spk_serial_io_ops = {
 	.synth_out = spk_serial_out,
@@ -40,6 +41,7 @@ struct spk_io_ops spk_serial_io_ops = {
 	.synth_in = spk_serial_in,
 	.synth_in_nowait = spk_serial_in_nowait,
 	.flush_buffer = spk_serial_flush_buffer,
+	.wait_for_xmitr = spk_serial_wait_for_xmitr,
 };
 EXPORT_SYMBOL_GPL(spk_serial_io_ops);
 
@@ -211,7 +213,7 @@ void spk_stop_serial_interrupt(void)
 }
 EXPORT_SYMBOL_GPL(spk_stop_serial_interrupt);
 
-int spk_wait_for_xmitr(struct spk_synth *in_synth)
+static int spk_serial_wait_for_xmitr(struct spk_synth *in_synth)
 {
 	int tmout = SPK_XMITR_TIMEOUT;
 
@@ -280,7 +282,7 @@ static void spk_serial_flush_buffer(void)
 
 static int spk_serial_out(struct spk_synth *in_synth, const char ch)
 {
-	if (in_synth->alive && spk_wait_for_xmitr(in_synth)) {
+	if (in_synth->alive && spk_serial_wait_for_xmitr(in_synth)) {
 		outb_p(ch, speakup_info.port_tts);
 		return 1;
 	}
@@ -295,7 +297,7 @@ const char *spk_serial_synth_immediate(struct spk_synth *synth,
 	while ((ch = *buff)) {
 		if (ch == '\n')
 			ch = synth->procspeech;
-		if (spk_wait_for_xmitr(synth))
+		if (spk_serial_wait_for_xmitr(synth))
 			outb(ch, speakup_info.port_tts);
 		else
 			return buff;
diff --git a/drivers/accessibility/speakup/spk_priv.h b/drivers/accessibility/speakup/spk_priv.h
index c75b40838794..0f4bcbe5ddb9 100644
--- a/drivers/accessibility/speakup/spk_priv.h
+++ b/drivers/accessibility/speakup/spk_priv.h
@@ -34,7 +34,6 @@
 
 const struct old_serial_port *spk_serial_init(int index);
 void spk_stop_serial_interrupt(void);
-int spk_wait_for_xmitr(struct spk_synth *in_synth);
 void spk_serial_release(void);
 void spk_ttyio_release(void);
 void spk_ttyio_register_ldisc(void);
diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c
index 9b95f77f9265..a831ff64f8ba 100644
--- a/drivers/accessibility/speakup/spk_ttyio.c
+++ b/drivers/accessibility/speakup/spk_ttyio.c
@@ -116,6 +116,7 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear);
 static unsigned char spk_ttyio_in(void);
 static unsigned char spk_ttyio_in_nowait(void);
 static void spk_ttyio_flush_buffer(void);
+static int spk_ttyio_wait_for_xmitr(struct spk_synth *in_synth);
 
 struct spk_io_ops spk_ttyio_ops = {
 	.synth_out = spk_ttyio_out,
@@ -125,6 +126,7 @@ struct spk_io_ops spk_ttyio_ops = {
 	.synth_in = spk_ttyio_in,
 	.synth_in_nowait = spk_ttyio_in_nowait,
 	.flush_buffer = spk_ttyio_flush_buffer,
+	.wait_for_xmitr = spk_ttyio_wait_for_xmitr,
 };
 EXPORT_SYMBOL_GPL(spk_ttyio_ops);
 
@@ -286,6 +288,11 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear)
 	mutex_unlock(&speakup_tty_mutex);
 }
 
+static int spk_ttyio_wait_for_xmitr(struct spk_synth *in_synth)
+{
+	return 1;
+}
+
 static unsigned char ttyio_in(int timeout)
 {
 	struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data;
diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h
index d3272c6d199a..7398f1196e10 100644
--- a/drivers/accessibility/speakup/spk_types.h
+++ b/drivers/accessibility/speakup/spk_types.h
@@ -158,6 +158,7 @@ struct spk_io_ops {
 	unsigned char (*synth_in)(void);
 	unsigned char (*synth_in_nowait)(void);
 	void (*flush_buffer)(void);
+	int (*wait_for_xmitr)(struct spk_synth *synth);
 };
 
 struct spk_synth {
diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c
index 3568bfb89912..ac47dbac7207 100644
--- a/drivers/accessibility/speakup/synth.c
+++ b/drivers/accessibility/speakup/synth.c
@@ -159,7 +159,7 @@ int spk_synth_is_alive_restart(struct spk_synth *synth)
 {
 	if (synth->alive)
 		return 1;
-	if (spk_wait_for_xmitr(synth) > 0) {
+	if (synth->io_ops->wait_for_xmitr(synth) > 0) {
 		/* restart */
 		synth->alive = 1;
 		synth_printf("%s", synth->init);
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index 4c348377a39d..806b8ce05624 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -99,8 +99,8 @@ static int fch_misc_setup(struct apd_private_data *pdata)
 	if (ret < 0)
 		return -ENOENT;
 
-	acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj);
-	clk_data->is_rv = obj->integer.value;
+	if (!acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj))
+		clk_data->is_rv = obj->integer.value;
 
 	list_for_each_entry(rentry, &resource_list, node) {
 		clk_data->base = devm_ioremap(&adev->dev, rentry->res->start,
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 6ad8cb05f672..4a0b07792233 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -350,7 +350,7 @@ void __iomem __ref
 
 	pg_off = round_down(phys, PAGE_SIZE);
 	pg_sz = round_up(phys + size, PAGE_SIZE) - pg_off;
-	virt = acpi_map(pg_off, pg_sz);
+	virt = acpi_map(phys, size);
 	if (!virt) {
 		mutex_unlock(&acpi_ioremap_lock);
 		kfree(map);
@@ -358,7 +358,7 @@ void __iomem __ref
 	}
 
 	INIT_LIST_HEAD(&map->list);
-	map->virt = virt;
+	map->virt = (void __iomem __force *)((unsigned long)virt & PAGE_MASK);
 	map->phys = pg_off;
 	map->size = pg_sz;
 	map->track.refcount = 1;
@@ -1575,11 +1575,26 @@ static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level,
 acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
 				u32 level)
 {
+	acpi_status status;
+
 	if (!(res->flags & IORESOURCE_MEM))
 		return AE_TYPE;
 
-	return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
-				   acpi_deactivate_mem_region, NULL, res, NULL);
+	status = acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
+				     acpi_deactivate_mem_region, NULL,
+				     res, NULL);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	/*
+	 * Wait for all of the mappings queued up for removal by
+	 * acpi_deactivate_mem_region() to actually go away.
+	 */
+	synchronize_rcu();
+	rcu_barrier();
+	flush_scheduled_work();
+
+	return AE_OK;
 }
 EXPORT_SYMBOL_GPL(acpi_release_memory);
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 0c0a736eb861..fbd8eaa32d32 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -807,8 +807,7 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
 				(sstatus & 0xf) != 1)
 			break;
 
-		ata_link_printk(link, KERN_INFO, "avn bounce port%d\n",
-				port);
+		ata_link_info(link,  "avn bounce port%d\n", port);
 
 		pci_read_config_word(pdev, 0x92, &val);
 		val &= ~(1 << port);
diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c
index 6853dbb4131d..49f7acbfcf01 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -470,7 +470,7 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	switch (priv->version) {
 	case BRCM_SATA_BCM7425:
 		hpriv->flags |= AHCI_HFLAG_DELAY_ENGINE;
-		/* fall through */
+		fallthrough;
 	case BRCM_SATA_NSP:
 		hpriv->flags |= AHCI_HFLAG_NO_NCQ;
 		priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE;
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 129556fcf6be..86261deeb4c5 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -326,7 +326,7 @@ static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port,
 				node);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case -ENODEV:
 		/* continue normally */
 		hpriv->phys[port] = NULL;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b1cd4d97bc2a..f546a5761c4f 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -190,7 +190,7 @@ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap,
 		case ATA_LITER_PMP_FIRST:
 			if (sata_pmp_attached(ap))
 				return ap->pmp_link;
-			/* fall through */
+			fallthrough;
 		case ATA_LITER_HOST_FIRST:
 			return &ap->link;
 		}
@@ -201,11 +201,11 @@ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap,
 		case ATA_LITER_HOST_FIRST:
 			if (sata_pmp_attached(ap))
 				return ap->pmp_link;
-			/* fall through */
+			fallthrough;
 		case ATA_LITER_PMP_FIRST:
 			if (unlikely(ap->slave_link))
 				return ap->slave_link;
-			/* fall through */
+			fallthrough;
 		case ATA_LITER_EDGE:
 			return NULL;
 		}
@@ -523,7 +523,7 @@ int atapi_cmd_type(u8 opcode)
 	case ATA_12:
 		if (atapi_passthru16)
 			return ATAPI_PASS_THRU;
-		/* fall thru */
+		fallthrough;
 	default:
 		return ATAPI_MISC;
 	}
@@ -1800,7 +1800,7 @@ retry:
 	switch (class) {
 	case ATA_DEV_SEMB:
 		class = ATA_DEV_ATA;	/* some hard drives report SEMB sig */
-		/* fall through */
+		fallthrough;
 	case ATA_DEV_ATA:
 	case ATA_DEV_ZAC:
 		tf.command = ATA_CMD_ID_ATA;
@@ -2907,7 +2907,7 @@ int ata_bus_probe(struct ata_port *ap)
 	case -ENODEV:
 		/* give it just one more chance */
 		tries[dev->devno] = min(tries[dev->devno], 1);
-		/* fall through */
+		fallthrough;
 	case -EIO:
 		if (tries[dev->devno] == 1) {
 			/* This is the last chance, better to slow
@@ -3158,7 +3158,7 @@ int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel)
 
 	case ATA_DNXFER_FORCE_PIO0:
 		pio_mask &= 1;
-		/* fall through */
+		fallthrough;
 	case ATA_DNXFER_FORCE_PIO:
 		mwdma_mask = 0;
 		udma_mask = 0;
@@ -3868,9 +3868,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */
 	{ "C300-CTFDDAC128MAG",	"0001",		ATA_HORKAGE_NONCQ, },
 
-	/* Some Sandisk SSDs lock up hard with NCQ enabled.  Reported on
-	   SD7SN6S256G and SD8SN8U256G */
-	{ "SanDisk SD[78]SN*G",	NULL,		ATA_HORKAGE_NONCQ, },
+	/* Sandisk SD7/8/9s lock up hard on large trims */
+	{ "SanDisk SD[789]*",	NULL,		ATA_HORKAGE_MAX_TRIM_128M, },
 
 	/* devices which puke on READ_NATIVE_MAX */
 	{ "HDS724040KLSA80",	"KFAOA20N",	ATA_HORKAGE_BROKEN_HPA, },
@@ -4694,7 +4693,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 			    qc->tf.feature != SETFEATURES_RA_ON &&
 			    qc->tf.feature != SETFEATURES_RA_OFF)
 				break;
-			/* fall through */
+			fallthrough;
 		case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */
 		case ATA_CMD_SET_MULTI: /* multi_count changed */
 			/* revalidate device */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 474c6c34fe02..d912eaa65c94 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1576,7 +1576,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 	case ATA_DEV_ZAC:
 		if (stat & ATA_SENSE)
 			ata_eh_request_sense(qc, qc->scsicmd);
-		/* fall through */
+		fallthrough;
 	case ATA_DEV_ATA:
 		if (err & ATA_ICRC)
 			qc->err_mask |= AC_ERR_ATA_BUS;
@@ -3473,11 +3473,11 @@ static int ata_eh_handle_dev_fail(struct ata_device *dev, int err)
 	case -ENODEV:
 		/* device missing or wrong IDENTIFY data, schedule probing */
 		ehc->i.probe_mask |= (1 << dev->devno);
-		/* fall through */
+		fallthrough;
 	case -EINVAL:
 		/* give it just one more chance */
 		ehc->tries[dev->devno] = min(ehc->tries[dev->devno], 1);
-		/* fall through */
+		fallthrough;
 	case -EIO:
 		if (ehc->tries[dev->devno] == 1) {
 			/* This is the last chance, better to slow
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index ec233208585b..70431912dc63 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2080,6 +2080,7 @@ static unsigned int ata_scsiop_inq_89(struct ata_scsi_args *args, u8 *rbuf)
 
 static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 {
+	struct ata_device *dev = args->dev;
 	u16 min_io_sectors;
 
 	rbuf[1] = 0xb0;
@@ -2105,7 +2106,12 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 	 * with the unmap bit set.
 	 */
 	if (ata_id_has_trim(args->id)) {
-		put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]);
+		u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM;
+
+		if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M)
+			max_blocks = 128 << (20 - SECTOR_SHIFT);
+
+		put_unaligned_be64(max_blocks, &rbuf[36]);
 		put_unaligned_be32(1, &rbuf[28]);
 	}
 
@@ -4162,7 +4168,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 				ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6);
 				break;
 			}
-			/* Fallthrough */
+			fallthrough;
 		default:
 			ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
 			break;
@@ -4198,7 +4204,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 	 * turning this into a no-op.
 	 */
 	case SYNCHRONIZE_CACHE:
-		/* fall through */
+		fallthrough;
 
 	/* no-op's, complete with success */
 	case REZERO_UNIT:
diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c
index e01a3a6e4d46..2bc5fc81efe3 100644
--- a/drivers/ata/pata_atp867x.c
+++ b/drivers/ata/pata_atp867x.c
@@ -157,7 +157,7 @@ static int atp867x_get_active_clocks_shifted(struct ata_port *ap,
 	default:
 		printk(KERN_WARNING "ATP867X: active %dclk is invalid. "
 			"Using 12clk.\n", clk);
-		/* fall through */
+		fallthrough;
 	case 9 ... 12:
 		clocks = 7;	/* 12 clk */
 		break;
@@ -190,7 +190,7 @@ static int atp867x_get_recover_clocks_shifted(unsigned int clk)
 	default:
 		printk(KERN_WARNING "ATP867X: recover %dclk is invalid. "
 			"Using default 12clk.\n", clk);
-		/* fall through */
+		fallthrough;
 	case 12:	/* default 12 clk */
 		clocks = 0;
 		break;
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index 916bf024d737..7511e11eef4d 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -369,7 +369,7 @@ static int serverworks_fixup(struct pci_dev *pdev)
 		break;
 	case PCI_DEVICE_ID_SERVERWORKS_CSB5IDE:
 		ata_pci_bmdma_clear_simplex(pdev);
-		/* fall through */
+		fallthrough;
 	case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE:
 	case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE2:
 		rc = serverworks_fixup_csb(pdev);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index d7228f8e9297..664ef658a955 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -2010,7 +2010,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc)
 				break;
 			case ATA_CMD_WRITE_MULTI_FUA_EXT:
 				tf->flags &= ~ATA_TFLAG_FUA; /* ugh */
-				/* fall through */
+				fallthrough;
 			case ATA_CMD_WRITE_MULTI_EXT:
 				tf->command = ATA_CMD_PIO_WRITE_EXT;
 				break;
@@ -2044,7 +2044,7 @@ static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc)
 	case ATA_PROT_DMA:
 		if (tf->command == ATA_CMD_DSM)
 			return AC_ERR_OK;
-		/* fall-thru */
+		fallthrough;
 	case ATA_PROT_NCQ:
 		break;	/* continue below */
 	case ATA_PROT_PIO:
@@ -2296,7 +2296,7 @@ static unsigned int mv_qc_issue_fis(struct ata_queued_cmd *qc)
 	switch (qc->tf.protocol) {
 	case ATAPI_PROT_PIO:
 		pp->pp_flags |= MV_PP_FLAG_FAKE_ATA_BUSY;
-		/* fall through */
+		fallthrough;
 	case ATAPI_PROT_NODATA:
 		ap->hsm_task_state = HSM_ST_FIRST;
 		break;
@@ -2347,7 +2347,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc)
 				return AC_ERR_OTHER;
 			break;  /* use bmdma for this */
 		}
-		/* fall thru */
+		fallthrough;
 	case ATA_PROT_NCQ:
 		mv_start_edma(ap, port_mmio, pp, qc->tf.protocol);
 		pp->req_idx = (pp->req_idx + 1) & MV_MAX_Q_DEPTH_MASK;
@@ -2376,7 +2376,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc)
 				      ": attempting PIO w/multiple DRQ: "
 				      "this may fail due to h/w errata\n");
 		}
-		/* fall through */
+		fallthrough;
 	case ATA_PROT_NODATA:
 	case ATAPI_PROT_PIO:
 	case ATAPI_PROT_NODATA:
@@ -3864,7 +3864,7 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx)
 				" and avoid the final two gigabytes on"
 				" all RocketRAID BIOS initialized drives.\n");
 		}
-		/* fall through */
+		fallthrough;
 	case chip_6042:
 		hpriv->ops = &mv6xxx_ops;
 		hp_flags |= MV_HP_GEN_IIE;
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 8729f78cef5f..7815da8ef9e5 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -637,7 +637,7 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 	switch (qc->tf.protocol) {
 	case ATA_PROT_DMA:
 		pdc_fill_sg(qc);
-		/*FALLTHROUGH*/
+		fallthrough;
 	case ATA_PROT_NODATA:
 		i = pdc_pkt_header(&qc->tf, qc->ap->bmdma_prd_dma,
 				   qc->dev->devno, pp->pkt);
@@ -652,7 +652,7 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 		break;
 	case ATAPI_PROT_DMA:
 		pdc_fill_sg(qc);
-		/*FALLTHROUGH*/
+		fallthrough;
 	case ATAPI_PROT_NODATA:
 		pdc_atapi_pkt(qc);
 		break;
@@ -1022,11 +1022,11 @@ static unsigned int pdc_qc_issue(struct ata_queued_cmd *qc)
 	case ATAPI_PROT_NODATA:
 		if (qc->dev->flags & ATA_DFLAG_CDB_INTR)
 			break;
-		/*FALLTHROUGH*/
+		fallthrough;
 	case ATA_PROT_NODATA:
 		if (qc->tf.flags & ATA_TFLAG_POLLING)
 			break;
-		/*FALLTHROUGH*/
+		fallthrough;
 	case ATAPI_PROT_DMA:
 	case ATA_PROT_DMA:
 		pdc_packet_start(qc);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 2c7b30c5ea3d..4c01190a5e37 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -669,7 +669,7 @@ static unsigned int pdc20621_qc_issue(struct ata_queued_cmd *qc)
 	case ATA_PROT_NODATA:
 		if (qc->tf.flags & ATA_TFLAG_POLLING)
 			break;
-		/*FALLTHROUGH*/
+		fallthrough;
 	case ATA_PROT_DMA:
 		pdc20621_packet_start(qc);
 		return 0;
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 2ca9ec802734..0ddd611b4277 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -711,7 +711,7 @@ static void process_txdone_queue (struct fs_dev *dev, struct queue *q)
 
 		switch (STATUS_CODE (qe)) {
 		case 0x01: /* This is for AAL0 where we put the chip in streaming mode */
-			/* Fall through */
+			fallthrough;
 		case 0x02:
 			/* Process a real txdone entry. */
 			tmp = qe->p0;
@@ -998,6 +998,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 				error = make_rate (pcr, r, &tmc0, NULL);
 				if (error) {
 					kfree(tc);
+					kfree(vcc);
 					return error;
 				}
 			}
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index a81bc49c14ac..9a70bee84125 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -376,33 +376,33 @@ fore200e_shutdown(struct fore200e* fore200e)
     case FORE200E_STATE_COMPLETE:
 	kfree(fore200e->stats);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_IRQ:
 	free_irq(fore200e->irq, fore200e->atm_dev);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_ALLOC_BUF:
 	fore200e_free_rx_buf(fore200e);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_INIT_BSQ:
 	fore200e_uninit_bs_queue(fore200e);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_INIT_RXQ:
 	fore200e_dma_chunk_free(fore200e, &fore200e->host_rxq.status);
 	fore200e_dma_chunk_free(fore200e, &fore200e->host_rxq.rpd);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_INIT_TXQ:
 	fore200e_dma_chunk_free(fore200e, &fore200e->host_txq.status);
 	fore200e_dma_chunk_free(fore200e, &fore200e->host_txq.tpd);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_INIT_CMDQ:
 	fore200e_dma_chunk_free(fore200e, &fore200e->host_cmdq.status);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_INITIALIZE:
 	/* nothing to do for that state */
 
@@ -415,7 +415,7 @@ fore200e_shutdown(struct fore200e* fore200e)
     case FORE200E_STATE_MAP:
 	fore200e->bus->unmap(fore200e);
 
-	/* fall through */
+	fallthrough;
     case FORE200E_STATE_CONFIGURE:
 	/* nothing to do for that state */
 
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 8af793f5e811..17f44abc9418 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1944,14 +1944,14 @@ he_tasklet(unsigned long data)
 		switch (type) {
 			case ITYPE_RBRQ_THRESH:
 				HPRINTK("rbrq%d threshold\n", group);
-				/* fall through */
+				fallthrough;
 			case ITYPE_RBRQ_TIMER:
 				if (he_service_rbrq(he_dev, group))
 					he_service_rbpl(he_dev, group);
 				break;
 			case ITYPE_TBRQ_THRESH:
 				HPRINTK("tbrq%d threshold\n", group);
-				/* fall through */
+				fallthrough;
 			case ITYPE_TPD_COMPLETE:
 				he_service_tbrq(he_dev, group);
 				break;
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 63871859e6e8..3c081b6171a8 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -192,7 +192,7 @@ static int idt77105_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 	switch (cmd) {
 		case IDT77105_GETSTATZ:
 			if (!capable(CAP_NET_ADMIN)) return -EPERM;
-			/* fall through */
+			fallthrough;
 		case IDT77105_GETSTAT:
 			return fetch_stats(dev, arg, cmd == IDT77105_GETSTATZ);
 		case ATM_SETLOOP:
diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c
index 986c1313694c..ac811cfa6843 100644
--- a/drivers/atm/lanai.c
+++ b/drivers/atm/lanai.c
@@ -2019,7 +2019,7 @@ static int lanai_normalize_ci(struct lanai_dev *lanai,
 	switch (*vpip) {
 		case ATM_VPI_ANY:
 			*vpip = 0;
-			/* FALLTHROUGH */
+			fallthrough;
 		case 0:
 			break;
 		default:
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index ee059c77e3bb..cf5fffcf98a1 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1447,7 +1447,7 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 	switch (cmd) {
 		case ZATM_GETPOOLZ:
 			if (!capable(CAP_NET_ADMIN)) return -EPERM;
-			/* fall through */
+			fallthrough;
 		case ZATM_GETPOOL:
 			{
 				struct zatm_pool_info info;
diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c
index dea031484cc4..0b1c99cca733 100644
--- a/drivers/auxdisplay/arm-charlcd.c
+++ b/drivers/auxdisplay/arm-charlcd.c
@@ -2,7 +2,7 @@
 /*
  * Driver for the on-board character LCD found on some ARM reference boards
  * This is basically an Hitachi HD44780 LCD with a custom IP block to drive it
- * http://en.wikipedia.org/wiki/HD44780_Character_LCD
+ * https://en.wikipedia.org/wiki/HD44780_Character_LCD
  * Currently it will just display the text "ARM Linux" and the linux version
  *
  * Author: Linus Walleij <triad@df.lth.se>
diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c
index 99980aa3644b..1c82d824ae00 100644
--- a/drivers/auxdisplay/panel.c
+++ b/drivers/auxdisplay/panel.c
@@ -1365,7 +1365,7 @@ static void panel_process_inputs(void)
 				break;
 			input->rise_timer = 0;
 			input->state = INPUT_ST_RISING;
-			/* fall through */
+			fallthrough;
 		case INPUT_ST_RISING:
 			if ((phys_curr & input->mask) != input->value) {
 				input->state = INPUT_ST_LOW;
@@ -1378,11 +1378,11 @@ static void panel_process_inputs(void)
 			}
 			input->high_timer = 0;
 			input->state = INPUT_ST_HIGH;
-			/* fall through */
+			fallthrough;
 		case INPUT_ST_HIGH:
 			if (input_state_high(input))
 				break;
-			/* fall through */
+			fallthrough;
 		case INPUT_ST_FALLING:
 			input_state_falling(input);
 		}
diff --git a/drivers/base/core.c b/drivers/base/core.c
index ac1046a382bc..bb5806a2bd4c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -807,9 +807,7 @@ static void device_link_put_kref(struct device_link *link)
 void device_link_del(struct device_link *link)
 {
 	device_links_write_lock();
-	device_pm_lock();
 	device_link_put_kref(link);
-	device_pm_unlock();
 	device_links_write_unlock();
 }
 EXPORT_SYMBOL_GPL(device_link_del);
@@ -830,7 +828,6 @@ void device_link_remove(void *consumer, struct device *supplier)
 		return;
 
 	device_links_write_lock();
-	device_pm_lock();
 
 	list_for_each_entry(link, &supplier->links.consumers, s_node) {
 		if (link->consumer == consumer) {
@@ -839,7 +836,6 @@ void device_link_remove(void *consumer, struct device *supplier)
 		}
 	}
 
-	device_pm_unlock();
 	device_links_write_unlock();
 }
 EXPORT_SYMBOL_GPL(device_link_remove);
@@ -4237,10 +4233,10 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
 	vaf.va = &args;
 
 	if (err != -EPROBE_DEFER) {
-		dev_err(dev, "error %d: %pV", err, &vaf);
+		dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
 	} else {
 		device_set_deferred_probe_reason(dev, &vaf);
-		dev_dbg(dev, "error %d: %pV", err, &vaf);
+		dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
 	}
 
 	va_end(args);
@@ -4264,9 +4260,9 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
  */
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 {
-	if (fwnode) {
-		struct fwnode_handle *fn = dev->fwnode;
+	struct fwnode_handle *fn = dev->fwnode;
 
+	if (fwnode) {
 		if (fwnode_is_primary(fn))
 			fn = fn->secondary;
 
@@ -4276,8 +4272,12 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 		}
 		dev->fwnode = fwnode;
 	} else {
-		dev->fwnode = fwnode_is_primary(dev->fwnode) ?
-			dev->fwnode->secondary : NULL;
+		if (fwnode_is_primary(fn)) {
+			dev->fwnode = fn->secondary;
+			fn->secondary = NULL;
+		} else {
+			dev->fwnode = NULL;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(set_primary_fwnode);
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 5327bfc6ba71..283ca2de76d4 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -289,10 +289,10 @@ static ssize_t firmware_loading_store(struct device *dev,
 			}
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	default:
 		dev_err(dev, "%s: unexpected value (%d)\n", __func__, loading);
-		/* fallthrough */
+		fallthrough;
 	case -1:
 		fw_load_abort(fw_sysfs);
 		break;
diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index 933e2192fbe8..d08efc77cf16 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -142,10 +142,12 @@ int assign_fw(struct firmware *fw, struct device *device, u32 opt_flags);
 void fw_free_paged_buf(struct fw_priv *fw_priv);
 int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed);
 int fw_map_paged_buf(struct fw_priv *fw_priv);
+bool fw_is_paged_buf(struct fw_priv *fw_priv);
 #else
 static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {}
 static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; }
 static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; }
+static inline bool fw_is_paged_buf(struct fw_priv *fw_priv) { return false; }
 #endif
 
 #endif /* __FIRMWARE_LOADER_H */
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 9da0c9d5f538..63b9714a0154 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -252,9 +252,11 @@ static void __free_fw_priv(struct kref *ref)
 	list_del(&fw_priv->list);
 	spin_unlock(&fwc->lock);
 
-	fw_free_paged_buf(fw_priv); /* free leftover pages */
-	if (!fw_priv->allocated_size)
+	if (fw_is_paged_buf(fw_priv))
+		fw_free_paged_buf(fw_priv);
+	else if (!fw_priv->allocated_size)
 		vfree(fw_priv->data);
+
 	kfree_const(fw_priv->fw_name);
 	kfree(fw_priv);
 }
@@ -268,6 +270,11 @@ static void free_fw_priv(struct fw_priv *fw_priv)
 }
 
 #ifdef CONFIG_FW_LOADER_PAGED_BUF
+bool fw_is_paged_buf(struct fw_priv *fw_priv)
+{
+	return fw_priv->is_paged_buf;
+}
+
 void fw_free_paged_buf(struct fw_priv *fw_priv)
 {
 	int i;
@@ -275,6 +282,8 @@ void fw_free_paged_buf(struct fw_priv *fw_priv)
 	if (!fw_priv->pages)
 		return;
 
+	vunmap(fw_priv->data);
+
 	for (i = 0; i < fw_priv->nr_pages; i++)
 		__free_page(fw_priv->pages[i]);
 	kvfree(fw_priv->pages);
@@ -328,10 +337,6 @@ int fw_map_paged_buf(struct fw_priv *fw_priv)
 	if (!fw_priv->data)
 		return -ENOMEM;
 
-	/* page table is no longer needed after mapping, let's free */
-	kvfree(fw_priv->pages);
-	fw_priv->pages = NULL;
-
 	return 0;
 }
 #endif
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9dd85bea4026..205a06752ca9 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1606,13 +1606,17 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	}
 
 	/*
-	 * If a device configured to wake up the system from sleep states
-	 * has been suspended at run time and there's a resume request pending
-	 * for it, this is equivalent to the device signaling wakeup, so the
-	 * system suspend operation should be aborted.
+	 * Wait for possible runtime PM transitions of the device in progress
+	 * to complete and if there's a runtime resume request pending for it,
+	 * resume it before proceeding with invoking the system-wide suspend
+	 * callbacks for it.
+	 *
+	 * If the system-wide suspend callbacks below change the configuration
+	 * of the device, they must disable runtime PM for it or otherwise
+	 * ensure that its runtime-resume callbacks will not be confused by that
+	 * change in case they are invoked going forward.
 	 */
-	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
-		pm_wakeup_event(dev, 0);
+	pm_runtime_barrier(dev);
 
 	if (pm_wakeup_pending()) {
 		dev->power.direct_complete = false;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 3cf9bc5d8d95..6dba41395155 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1135,7 +1135,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
-		/* fall through */
+		fallthrough;
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 1553d41f0b91..a50e13af0305 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1726,7 +1726,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
 		/* MSch: invalidate default_params */
 		default_params[drive].blocks  = 0;
 		set_capacity(floppy->disk, MAX_DISK_SIZE * 2);
-		/* Fall through */
+		fallthrough;
 	case FDFMTEND:
 	case FDFLUSH:
 		/* invalidate the buffer track to force a reread */
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index fe6cb99eb917..740e93bad21f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1733,7 +1733,7 @@ static inline void __drbd_chk_io_error_(struct drbd_device *device,
 				_drbd_set_state(_NS(device, disk, D_INCONSISTENT), CS_HARD, NULL);
 			break;
 		}
-		/* fall through - for DRBD_META_IO_ERROR or DRBD_FORCE_DETACH */
+		fallthrough;	/* for DRBD_META_IO_ERROR or DRBD_FORCE_DETACH */
 	case EP_DETACH:
 	case EP_CALL_HELPER:
 		/* Remember whether we saw a READ or WRITE error.
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index cb687ccdbd96..04b6bde9419d 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -430,7 +430,7 @@ int drbd_thread_start(struct drbd_thread *thi)
 		thi->t_state = RESTARTING;
 		drbd_info(resource, "Restarting %s thread (from %s [%d])\n",
 				thi->name, current->comm, current->pid);
-		/* fall through */
+		fallthrough;
 	case RUNNING:
 	case RESTARTING:
 	default:
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 28eb078f8b75..43c8ae4d9fca 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -3883,7 +3883,7 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device,
 			if (nla_put_u32(skb, T_helper_exit_code,
 					sib->helper_exit_code))
 				goto nla_put_failure;
-			/* fall through */
+			fallthrough;
 		case SIB_HELPER_PRE:
 			if (nla_put_string(skb, T_helper, sib->helper_name))
 				goto nla_put_failure;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 1d17593f5d2b..422363daa618 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1797,7 +1797,7 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf
 			break;
 		else
 			drbd_warn(connection, "Allocation of an epoch failed, slowing down\n");
-			/* Fall through */
+		fallthrough;
 
 	case WO_BDEV_FLUSH:
 	case WO_DRAIN_IO:
@@ -2917,7 +2917,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
-		/* fall through */
+		fallthrough;
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -3083,7 +3083,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 			rv =  1;
 			break;
 		}
-		/* Else fall through - to one of the other strategies... */
+		fallthrough;	/* to one of the other strategies */
 	case ASB_DISCARD_OLDER_PRI:
 		if (self == 0 && peer == 1) {
 			rv = 1;
@@ -3096,7 +3096,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
-		/* fall through */
+		fallthrough;
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -3108,7 +3108,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
-		/* else, fall through */
+		fallthrough;
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
@@ -3608,7 +3608,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 		switch (rr_conflict) {
 		case ASB_CALL_HELPER:
 			drbd_khelper(device, "pri-lost");
-			/* fall through */
+			fallthrough;
 		case ASB_DISCONNECT:
 			drbd_err(device, "I shall become SyncTarget, but I am primary!\n");
 			return C_MASK;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 674be09b2da9..5c975af9c15f 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -611,7 +611,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		drbd_set_out_of_sync(device, req->i.sector, req->i.size);
 		drbd_report_io_error(device, req);
 		__drbd_chk_io_error(device, DRBD_READ_ERROR);
-		/* fall through. */
+		fallthrough;
 	case READ_AHEAD_COMPLETED_WITH_ERROR:
 		/* it is legal to fail read-ahead, no __drbd_chk_io_error in that case. */
 		mod_rq_state(req, m, RQ_LOCAL_PENDING, RQ_LOCAL_COMPLETED);
@@ -836,7 +836,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 			} /* else: FIXME can this happen? */
 			break;
 		}
-		/* else, fall through - to BARRIER_ACKED */
+		fallthrough;	/* to BARRIER_ACKED */
 
 	case BARRIER_ACKED:
 		/* barrier ack for READ requests does not make sense */
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 09079aee8dc4..a563b023458a 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1680,7 +1680,7 @@ static void recal_interrupt(void)
 			clear_bit(FD_DISK_NEWCHANGE_BIT,
 				  &drive_state[current_drive].flags);
 			drive_state[current_drive].select_date = jiffies;
-			/* fall through */
+			fallthrough;
 		default:
 			debugt(__func__, "default");
 			/* Recalibrate moves the head by at
@@ -3592,7 +3592,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
 		process_fd_request();
-		/* fall through */
+		fallthrough;
 	case FDGETDRVSTAT:
 		outparam = &drive_state[drive];
 		break;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 2f137d6ce169..d3394191e168 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -878,6 +878,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	u32 granularity, max_discard_sectors;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -890,11 +891,10 @@ static void loop_config_discard(struct loop_device *lo)
 		struct request_queue *backingq;
 
 		backingq = bdev_get_queue(inode->i_bdev);
-		blk_queue_max_discard_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
 
-		blk_queue_max_write_zeroes_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
+		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
+		granularity = backingq->limits.discard_granularity ?:
+			queue_physical_block_size(backingq);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -903,23 +903,26 @@ static void loop_config_discard(struct loop_device *lo)
 	 * useful information.
 	 */
 	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
+		max_discard_sectors = 0;
+		granularity = 0;
 
 	} else {
-		q->limits.discard_granularity = inode->i_sb->s_blocksize;
-		q->limits.discard_alignment = 0;
-
-		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
 	}
 
-	if (q->limits.max_write_zeroes_sectors)
+	if (max_discard_sectors) {
+		q->limits.discard_granularity = granularity;
+		blk_queue_max_discard_sectors(q, max_discard_sectors);
+		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
 		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-	else
+	} else {
+		q->limits.discard_granularity = 0;
+		blk_queue_max_discard_sectors(q, 0);
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
+	}
+	q->limits.discard_alignment = 0;
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)
@@ -1111,8 +1114,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
-	size = get_loop_size(lo, file);
-
 	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
 		error = -EINVAL;
 		goto out_unlock;
@@ -1162,6 +1163,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
+
+	size = get_loop_size(lo, file);
 	loop_set_size(lo, size);
 
 	set_blocksize(bdev, S_ISBLK(inode->i_mode) ?
@@ -1719,7 +1722,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_BLOCK_SIZE:
 		if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		/* Fall through */
+		fallthrough;
 	default:
 		err = lo_simple_ioctl(lo, cmd, arg);
 		break;
@@ -1867,7 +1870,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_STATUS64:
 	case LOOP_CONFIGURE:
 		arg = (unsigned long) compat_ptr(arg);
-		/* fall through */
+		fallthrough;
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3ff4054d6834..edf8b632e3d2 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1363,6 +1363,8 @@ static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout)
 	nbd->tag_set.timeout = timeout * HZ;
 	if (timeout)
 		blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+	else
+		blk_queue_rq_timeout(nbd->disk->queue, 30 * HZ);
 }
 
 /* Must be called with config_lock held */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 47a9dad880af..d74443a9c8fa 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -1147,7 +1147,7 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
-				     req_op(rq) & REQ_FUA);
+				     rq->cmd_flags & REQ_FUA);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index c0967507d085..a7af4f27b7c3 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -440,7 +440,7 @@ static void run_fsm(void)
 				pd_claimed = 1;
 				if (!pi_schedule_claimed(pi_current, run_fsm))
 					return;
-				/* fall through */
+				fallthrough;
 			case 1:
 				pd_claimed = 2;
 				pi_current->proto->connect(pi_current);
@@ -465,7 +465,7 @@ static void run_fsm(void)
 				if (stop)
 					return;
 				}
-				/* fall through */
+				fallthrough;
 			case Hold:
 				schedule_fsm();
 				return;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4becc1efe775..1034e445680c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2641,7 +2641,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 		 */
 		if (pd->refcnt == 1)
 			pkt_lock_door(pd, 0);
-		/* fall through */
+		fallthrough;
 	/*
 	 * forward selected CDROM ioctls to CD-ROM, for UDF
 	 */
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d9c0e7d154f9..e77eaab5cf23 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3293,7 +3293,7 @@ again:
 	case __RBD_OBJ_COPYUP_OBJECT_MAPS:
 		if (!pending_result_dec(&obj_req->pending, result))
 			return false;
-		/* fall through */
+		fallthrough;
 	case RBD_OBJ_COPYUP_OBJECT_MAPS:
 		if (*result) {
 			rbd_warn(rbd_dev, "snap object map update failed: %d",
@@ -3312,7 +3312,7 @@ again:
 	case __RBD_OBJ_COPYUP_WRITE_OBJECT:
 		if (!pending_result_dec(&obj_req->pending, result))
 			return false;
-		/* fall through */
+		fallthrough;
 	case RBD_OBJ_COPYUP_WRITE_OBJECT:
 		return true;
 	default:
@@ -3399,7 +3399,7 @@ again:
 	case __RBD_OBJ_WRITE_COPYUP:
 		if (!rbd_obj_advance_copyup(obj_req, result))
 			return false;
-		/* fall through */
+		fallthrough;
 	case RBD_OBJ_WRITE_COPYUP:
 		if (*result) {
 			rbd_warn(rbd_dev, "copyup failed: %d", *result);
@@ -3592,7 +3592,7 @@ again:
 	case __RBD_IMG_OBJECT_REQUESTS:
 		if (!pending_result_dec(&img_req->pending, result))
 			return false;
-		/* fall through */
+		fallthrough;
 	case RBD_IMG_OBJECT_REQUESTS:
 		return true;
 	default:
@@ -5120,6 +5120,9 @@ static ssize_t rbd_config_info_show(struct device *dev,
 {
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	return sprintf(buf, "%s\n", rbd_dev->config_info);
 }
 
@@ -5231,6 +5234,9 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	ret = rbd_dev_refresh(rbd_dev);
 	if (ret)
 		return ret;
@@ -7059,6 +7065,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_client *rbdc;
 	int rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
@@ -7209,6 +7218,9 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 	bool force = false;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	dev_id = -1;
 	opt_buf[0] = '\0';
 	sscanf(buf, "%d %5s", &dev_id, opt_buf);
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index 0fb94843a495..e1bc8b4cd592 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -148,7 +148,8 @@ static int process_rdma(struct rtrs_srv *sess,
 	/* Generate bio with pages pointing to the rdma buffer */
 	bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %ld\n", PTR_ERR(bio));
+		err = PTR_ERR(bio);
+		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err);
 		goto sess_dev_put;
 	}
 
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 7e261224ff10..8799e3bab067 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -425,7 +425,7 @@ static void card_state_change(struct rsxx_cardinfo *card,
 		 * Fall through so the DMA devices can be attached and
 		 * the user can attempt to pull off their data.
 		 */
-		/* fall through */
+		fallthrough;
 	case CARD_STATE_GOOD:
 		st = rsxx_get_card_size8(card, &card->size8);
 		if (st)
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 3a476dc1d14f..ae6454c24594 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -1436,7 +1436,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 			blk_mq_requeue_request(req, true);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case SKD_CHECK_STATUS_REPORT_ERROR:
 	default:
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 63b213e00b37..b2e48dac1ebd 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -126,16 +126,31 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	if (!range)
 		return -ENOMEM;
 
-	__rq_for_each_bio(bio, req) {
-		u64 sector = bio->bi_iter.bi_sector;
-		u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
-
-		range[n].flags = cpu_to_le32(flags);
-		range[n].num_sectors = cpu_to_le32(num_sectors);
-		range[n].sector = cpu_to_le64(sector);
-		n++;
+	/*
+	 * Single max discard segment means multi-range discard isn't
+	 * supported, and block layer only runs contiguity merge like
+	 * normal RW request. So we can't reply on bio for retrieving
+	 * each range info.
+	 */
+	if (queue_max_discard_segments(req->q) == 1) {
+		range[0].flags = cpu_to_le32(flags);
+		range[0].num_sectors = cpu_to_le32(blk_rq_sectors(req));
+		range[0].sector = cpu_to_le64(blk_rq_pos(req));
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 sector = bio->bi_iter.bi_sector;
+			u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+
+			range[n].flags = cpu_to_le32(flags);
+			range[n].num_sectors = cpu_to_le32(num_sectors);
+			range[n].sector = cpu_to_le64(sector);
+			n++;
+		}
 	}
 
+	WARN_ON_ONCE(n != segments);
+
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
 	req->special_vec.bv_len = sizeof(*range) * segments;
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index c2f71265af4b..adfc9352351d 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -1260,7 +1260,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 		break;
 	case BLKIF_OP_WRITE_BARRIER:
 		drain = true;
-		/* fall through */
+		fallthrough;
 	case BLKIF_OP_FLUSH_DISKCACHE:
 		ring->st_f_req++;
 		operation = REQ_OP_WRITE;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 42944d41aea0..b9aa5d1ac10b 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -843,7 +843,7 @@ static void frontend_changed(struct xenbus_device *dev,
 		xenbus_switch_state(dev, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
-		/* fall through */
+		fallthrough;
 		/* if not online */
 	case XenbusStateUnknown:
 		/* implies xen_blkif_disconnect() via xen_blkbk_remove() */
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3bb3dd8da9b0..91de2e0755ae 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1403,7 +1403,6 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp)
 	case BLKIF_RSP_EOPNOTSUPP:
 		return REQ_EOPNOTSUPP;
 	case BLKIF_RSP_ERROR:
-		/* Fallthrough. */
 	default:
 		return REQ_ERROR;
 	}
@@ -1643,7 +1642,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				info->feature_flush = 0;
 				xlvbd_flush(info);
 			}
-			/* fall through */
+			fallthrough;
 		case BLKIF_OP_READ:
 		case BLKIF_OP_WRITE:
 			if (unlikely(bret->status != BLKIF_RSP_OKAY))
@@ -2484,7 +2483,7 @@ static void blkback_changed(struct xenbus_device *dev,
 	case XenbusStateClosed:
 		if (dev->state == XenbusStateClosed)
 			break;
-		/* fall through */
+		fallthrough;
 	case XenbusStateClosing:
 		if (info)
 			blkfront_closing(info);
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index fb5a901fd89e..efb088df1276 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -1849,7 +1849,7 @@ static int sysc_clockdomain_init(struct sysc *ddata)
 	switch (ddata->nr_clocks) {
 	case 2:
 		ick = ddata->clocks[SYSC_ICK];
-		/* fallthrough */
+		fallthrough;
 	case 1:
 		fck = ddata->clocks[SYSC_FCK];
 		break;
diff --git a/drivers/char/agp/ali-agp.c b/drivers/char/agp/ali-agp.c
index 89527bae4602..760d9a931289 100644
--- a/drivers/char/agp/ali-agp.c
+++ b/drivers/char/agp/ali-agp.c
@@ -357,7 +357,7 @@ found:
 		default:
 			break;
 		}
-		/*FALLTHROUGH*/
+		fallthrough;
 	default:
 		bridge->driver = &ali_generic_bridge;
 	}
diff --git a/drivers/char/hw_random/ingenic-rng.c b/drivers/char/hw_random/ingenic-rng.c
index d704cef64b64..055cfe59f519 100644
--- a/drivers/char/hw_random/ingenic-rng.c
+++ b/drivers/char/hw_random/ingenic-rng.c
@@ -92,8 +92,7 @@ static int ingenic_rng_probe(struct platform_device *pdev)
 	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base)) {
 		pr_err("%s: Failed to map RNG registers\n", __func__);
-		ret = PTR_ERR(priv->base);
-		goto err_free_rng;
+		return PTR_ERR(priv->base);
 	}
 
 	priv->version = (enum ingenic_rng_version)of_device_get_match_data(&pdev->dev);
@@ -106,17 +105,13 @@ static int ingenic_rng_probe(struct platform_device *pdev)
 	ret = hwrng_register(&priv->rng);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register hwrng\n");
-		goto err_free_rng;
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, priv);
 
 	dev_info(&pdev->dev, "Ingenic RNG driver registered\n");
 	return 0;
-
-err_free_rng:
-	kfree(priv);
-	return ret;
 }
 
 static int ingenic_rng_remove(struct platform_device *pdev)
diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c
index ed4dc3b1843e..f292e74bd4a5 100644
--- a/drivers/char/ipmi/kcs_bmc.c
+++ b/drivers/char/ipmi/kcs_bmc.c
@@ -99,7 +99,7 @@ static void kcs_bmc_handle_data(struct kcs_bmc *kcs_bmc)
 	switch (kcs_bmc->phase) {
 	case KCS_PHASE_WRITE_START:
 		kcs_bmc->phase = KCS_PHASE_WRITE_DATA;
-		/* fall through */
+		fallthrough;
 
 	case KCS_PHASE_WRITE_DATA:
 		if (kcs_bmc->data_in_idx < KCS_MSG_BUFSIZ) {
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index bd95aba1f9fe..45932f05fd67 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -734,7 +734,7 @@ static long lp_ioctl(struct file *file, unsigned int cmd,
 			ret = lp_set_timeout32(minor, (void __user *)arg);
 			break;
 		}
-		/* fall through - for 64-bit */
+		fallthrough;	/* for 64-bit */
 	case LPSETTIMEOUT_NEW:
 		ret = lp_set_timeout64(minor, (void __user *)arg);
 		break;
@@ -762,7 +762,7 @@ static long lp_compat_ioctl(struct file *file, unsigned int cmd,
 			ret = lp_set_timeout32(minor, (void __user *)arg);
 			break;
 		}
-		/* fall through - for x32 mode */
+		fallthrough;	/* for x32 mode */
 	case LPSETTIMEOUT_NEW:
 		ret = lp_set_timeout64(minor, (void __user *)arg);
 		break;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 687d4af6945d..abd4ffdc8cde 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -791,7 +791,7 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
 	switch (orig) {
 	case SEEK_CUR:
 		offset += file->f_pos;
-		/* fall through */
+		fallthrough;
 	case SEEK_SET:
 		/* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
 		if ((unsigned long long)offset >= -MAX_ERRNO) {
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 8206412d25ba..e9f694b36871 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -286,7 +286,7 @@ static long nvram_misc_ioctl(struct file *file, unsigned int cmd,
 #ifdef CONFIG_PPC
 	case OBSOLETE_PMAC_NVRAM_GET_OFFSET:
 		pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n");
-		/* fall through */
+		fallthrough;
 	case IOC_NVRAM_GET_OFFSET:
 		ret = -EINVAL;
 #ifdef CONFIG_PPC_PMAC
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 3576ad7bd380..68b087bff59c 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -653,9 +653,8 @@ config ATCPIT100_TIMER
 	  This option enables support for the Andestech ATCPIT100 timers.
 
 config RISCV_TIMER
-	bool "Timer for the RISC-V platform"
+	bool "Timer for the RISC-V platform" if COMPILE_TEST
 	depends on GENERIC_SCHED_CLOCK && RISCV
-	default y
 	select TIMER_PROBE
 	select TIMER_OF
 	help
@@ -663,6 +662,15 @@ config RISCV_TIMER
 	  is accessed via both the SBI and the rdcycle instruction.  This is
 	  required for all RISC-V systems.
 
+config CLINT_TIMER
+	bool "CLINT Timer for the RISC-V platform" if COMPILE_TEST
+	depends on GENERIC_SCHED_CLOCK && RISCV
+	select TIMER_PROBE
+	select TIMER_OF
+	help
+	  This option enables the CLINT timer for RISC-V systems.  The CLINT
+	  driver is usually used for NoMMU RISC-V systems.
+
 config CSKY_MP_TIMER
 	bool "SMP Timer for the C-SKY platform" if COMPILE_TEST
 	depends on CSKY
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index eaedb7240ae7..1c444cc3bb44 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -89,6 +89,7 @@ obj-$(CONFIG_CLKSRC_ST_LPC)		+= clksrc_st_lpc.o
 obj-$(CONFIG_X86_NUMACHIP)		+= numachip.o
 obj-$(CONFIG_ATCPIT100_TIMER)		+= timer-atcpit100.o
 obj-$(CONFIG_RISCV_TIMER)		+= timer-riscv.o
+obj-$(CONFIG_CLINT_TIMER)		+= timer-clint.o
 obj-$(CONFIG_CSKY_MP_TIMER)		+= timer-mp-csky.o
 obj-$(CONFIG_GX6605S_TIMER)		+= timer-gx6605s.o
 obj-$(CONFIG_HYPERV_TIMER)		+= hyperv_timer.o
diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c
index 38858e141731..80e960602030 100644
--- a/drivers/clocksource/timer-cadence-ttc.c
+++ b/drivers/clocksource/timer-cadence-ttc.c
@@ -309,7 +309,7 @@ static int ttc_rate_change_clocksource_cb(struct notifier_block *nb,
 		/* restore original register value */
 		writel_relaxed(ttccs->scale_clk_ctrl_reg_old,
 			       ttccs->ttc.base_addr + TTC_CLK_CNTRL_OFFSET);
-		/* fall through */
+		fallthrough;
 	default:
 		return NOTIFY_DONE;
 	}
@@ -392,7 +392,7 @@ static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
 
 		clockevents_update_freq(&ttcce->ce, ndata->new_rate / PRESCALE);
 
-		/* fall through */
+		fallthrough;
 	case PRE_RATE_CHANGE:
 	case ABORT_RATE_CHANGE:
 	default:
diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c
new file mode 100644
index 000000000000..8eeafa82c03d
--- /dev/null
+++ b/drivers/clocksource/timer-clint.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ *
+ * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a
+ * CLINT MMIO timer device.
+ */
+
+#define pr_fmt(fmt) "clint: " fmt
+#include <linux/bitops.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/sched_clock.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include <linux/smp.h>
+
+#define CLINT_IPI_OFF		0
+#define CLINT_TIMER_CMP_OFF	0x4000
+#define CLINT_TIMER_VAL_OFF	0xbff8
+
+/* CLINT manages IPI and Timer for RISC-V M-mode  */
+static u32 __iomem *clint_ipi_base;
+static u64 __iomem *clint_timer_cmp;
+static u64 __iomem *clint_timer_val;
+static unsigned long clint_timer_freq;
+static unsigned int clint_timer_irq;
+
+static void clint_send_ipi(const struct cpumask *target)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, target)
+		writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu));
+}
+
+static void clint_clear_ipi(void)
+{
+	writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id()));
+}
+
+static struct riscv_ipi_ops clint_ipi_ops = {
+	.ipi_inject = clint_send_ipi,
+	.ipi_clear = clint_clear_ipi,
+};
+
+#ifdef CONFIG_64BIT
+#define clint_get_cycles()	readq_relaxed(clint_timer_val)
+#else
+#define clint_get_cycles()	readl_relaxed(clint_timer_val)
+#define clint_get_cycles_hi()	readl_relaxed(((u32 *)clint_timer_val) + 1)
+#endif
+
+#ifdef CONFIG_64BIT
+static u64 notrace clint_get_cycles64(void)
+{
+	return clint_get_cycles();
+}
+#else /* CONFIG_64BIT */
+static u64 notrace clint_get_cycles64(void)
+{
+	u32 hi, lo;
+
+	do {
+		hi = clint_get_cycles_hi();
+		lo = clint_get_cycles();
+	} while (hi != clint_get_cycles_hi());
+
+	return ((u64)hi << 32) | lo;
+}
+#endif /* CONFIG_64BIT */
+
+static u64 clint_rdtime(struct clocksource *cs)
+{
+	return clint_get_cycles64();
+}
+
+static struct clocksource clint_clocksource = {
+	.name		= "clint_clocksource",
+	.rating		= 300,
+	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+	.read		= clint_rdtime,
+};
+
+static int clint_clock_next_event(unsigned long delta,
+				   struct clock_event_device *ce)
+{
+	void __iomem *r = clint_timer_cmp +
+			  cpuid_to_hartid_map(smp_processor_id());
+
+	csr_set(CSR_IE, IE_TIE);
+	writeq_relaxed(clint_get_cycles64() + delta, r);
+	return 0;
+}
+
+static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = {
+	.name		= "clint_clockevent",
+	.features	= CLOCK_EVT_FEAT_ONESHOT,
+	.rating		= 100,
+	.set_next_event	= clint_clock_next_event,
+};
+
+static int clint_timer_starting_cpu(unsigned int cpu)
+{
+	struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu);
+
+	ce->cpumask = cpumask_of(cpu);
+	clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff);
+
+	enable_percpu_irq(clint_timer_irq,
+			  irq_get_trigger_type(clint_timer_irq));
+	return 0;
+}
+
+static int clint_timer_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(clint_timer_irq);
+	return 0;
+}
+
+static irqreturn_t clint_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event);
+
+	csr_clear(CSR_IE, IE_TIE);
+	evdev->event_handler(evdev);
+
+	return IRQ_HANDLED;
+}
+
+static int __init clint_timer_init_dt(struct device_node *np)
+{
+	int rc;
+	u32 i, nr_irqs;
+	void __iomem *base;
+	struct of_phandle_args oirq;
+
+	/*
+	 * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or
+	 * RV_IRQ_SOFT. If it's anything else then we ignore the device.
+	 */
+	nr_irqs = of_irq_count(np);
+	for (i = 0; i < nr_irqs; i++) {
+		if (of_irq_parse_one(np, i, &oirq)) {
+			pr_err("%pOFP: failed to parse irq %d.\n", np, i);
+			continue;
+		}
+
+		if ((oirq.args_count != 1) ||
+		    (oirq.args[0] != RV_IRQ_TIMER &&
+		     oirq.args[0] != RV_IRQ_SOFT)) {
+			pr_err("%pOFP: invalid irq %d (hwirq %d)\n",
+			       np, i, oirq.args[0]);
+			return -ENODEV;
+		}
+
+		/* Find parent irq domain and map timer irq */
+		if (!clint_timer_irq &&
+		    oirq.args[0] == RV_IRQ_TIMER &&
+		    irq_find_host(oirq.np))
+			clint_timer_irq = irq_of_parse_and_map(np, i);
+	}
+
+	/* If CLINT timer irq not found then fail */
+	if (!clint_timer_irq) {
+		pr_err("%pOFP: timer irq not found\n", np);
+		return -ENODEV;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("%pOFP: could not map registers\n", np);
+		return -ENODEV;
+	}
+
+	clint_ipi_base = base + CLINT_IPI_OFF;
+	clint_timer_cmp = base + CLINT_TIMER_CMP_OFF;
+	clint_timer_val = base + CLINT_TIMER_VAL_OFF;
+	clint_timer_freq = riscv_timebase;
+
+	pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq);
+
+	rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq);
+	if (rc) {
+		pr_err("%pOFP: clocksource register failed [%d]\n", np, rc);
+		goto fail_iounmap;
+	}
+
+	sched_clock_register(clint_get_cycles64, 64, clint_timer_freq);
+
+	rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt,
+				 "clint-timer", &clint_clock_event);
+	if (rc) {
+		pr_err("registering percpu irq failed [%d]\n", rc);
+		goto fail_iounmap;
+	}
+
+	rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING,
+				"clockevents/clint/timer:starting",
+				clint_timer_starting_cpu,
+				clint_timer_dying_cpu);
+	if (rc) {
+		pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc);
+		goto fail_free_irq;
+	}
+
+	riscv_set_ipi_ops(&clint_ipi_ops);
+	clint_clear_ipi();
+
+	return 0;
+
+fail_free_irq:
+	free_irq(clint_timer_irq, &clint_clock_event);
+fail_iounmap:
+	iounmap(base);
+	return rc;
+}
+
+TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt);
+TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt);
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 9de1dabfb126..c51c5ed15aa7 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -19,26 +19,13 @@
 #include <linux/of_irq.h>
 #include <asm/smp.h>
 #include <asm/sbi.h>
-
-u64 __iomem *riscv_time_cmp;
-u64 __iomem *riscv_time_val;
-
-static inline void mmio_set_timer(u64 val)
-{
-	void __iomem *r;
-
-	r = riscv_time_cmp + cpuid_to_hartid_map(smp_processor_id());
-	writeq_relaxed(val, r);
-}
+#include <asm/timex.h>
 
 static int riscv_clock_next_event(unsigned long delta,
 		struct clock_event_device *ce)
 {
 	csr_set(CSR_IE, IE_TIE);
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
-		sbi_set_timer(get_cycles64() + delta);
-	else
-		mmio_set_timer(get_cycles64() + delta);
+	sbi_set_timer(get_cycles64() + delta);
 	return 0;
 }
 
diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c
index f7b7743ddb94..b7b252c5addf 100644
--- a/drivers/counter/microchip-tcb-capture.c
+++ b/drivers/counter/microchip-tcb-capture.c
@@ -320,8 +320,8 @@ static int mchp_tc_probe(struct platform_device *pdev)
 	}
 
 	regmap = syscon_node_to_regmap(np->parent);
-	if (IS_ERR(priv->regmap))
-		return PTR_ERR(priv->regmap);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
 	/* max. channels number is 2 when in QDEC mode */
 	priv->num_channels = of_property_count_u32_elems(np, "reg");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02ab56b2a0d8..47aa90f9a7c2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -703,8 +703,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	freq = arch_freq_get_on_cpu(policy->cpu);
 	if (freq)
 		ret = sprintf(buf, "%u\n", freq);
-	else if (cpufreq_driver && cpufreq_driver->setpolicy &&
-			cpufreq_driver->get)
+	else if (cpufreq_driver->setpolicy && cpufreq_driver->get)
 		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
 	else
 		ret = sprintf(buf, "%u\n", policy->cur);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e0220a6fbc69..a827b000ef51 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -219,14 +219,13 @@ struct global_params {
  * @epp_policy:		Last saved policy used to set EPP/EPB
  * @epp_default:	Power on default HWP energy performance
  *			preference/bias
- * @epp_saved:		Saved EPP/EPB during system suspend or CPU offline
- *			operation
  * @epp_cached		Cached HWP energy-performance preference value
  * @hwp_req_cached:	Cached value of the last HWP Request MSR
  * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
  * @last_io_update:	Last time when IO wake flag was set
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
+ * @suspended:		Whether or not the driver has been suspended.
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -258,13 +257,13 @@ struct cpudata {
 	s16 epp_powersave;
 	s16 epp_policy;
 	s16 epp_default;
-	s16 epp_saved;
 	s16 epp_cached;
 	u64 hwp_req_cached;
 	u64 hwp_cap_cached;
 	u64 last_io_update;
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
+	bool suspended;
 };
 
 static struct cpudata **all_cpu_data;
@@ -644,6 +643,8 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw
 
 static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
 {
+	int ret;
+
 	/*
 	 * Use the cached HWP Request MSR value, because in the active mode the
 	 * register itself may be updated by intel_pstate_hwp_boost_up() or
@@ -659,7 +660,11 @@ static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
 	 * function, so it cannot run in parallel with the update below.
 	 */
 	WRITE_ONCE(cpu->hwp_req_cached, value);
-	return wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+	ret = wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+	if (!ret)
+		cpu->epp_cached = epp;
+
+	return ret;
 }
 
 static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
@@ -678,6 +683,14 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 		else if (epp == -EINVAL)
 			epp = epp_values[pref_index - 1];
 
+		/*
+		 * To avoid confusion, refuse to set EPP to any values different
+		 * from 0 (performance) if the current policy is "performance",
+		 * because those values would be overridden.
+		 */
+		if (epp > 0 && cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
+			return -EBUSY;
+
 		ret = intel_pstate_set_epp(cpu_data, epp);
 	} else {
 		if (epp == -EINVAL)
@@ -762,10 +775,8 @@ static ssize_t store_energy_performance_preference(
 			cpufreq_stop_governor(policy);
 			ret = intel_pstate_set_epp(cpu, epp);
 			err = cpufreq_start_governor(policy);
-			if (!ret) {
-				cpu->epp_cached = epp;
+			if (!ret)
 				ret = err;
-			}
 		}
 	}
 
@@ -825,7 +836,7 @@ static void intel_pstate_get_hwp_max(unsigned int cpu, int *phy_max,
 
 	rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
 	WRITE_ONCE(all_cpu_data[cpu]->hwp_cap_cached, cap);
-	if (global.no_turbo)
+	if (global.no_turbo || global.turbo_disabled)
 		*current_max = HWP_GUARANTEED_PERF(cap);
 	else
 		*current_max = HWP_HIGHEST_PERF(cap);
@@ -859,12 +870,6 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 
 	cpu_data->epp_policy = cpu_data->policy;
 
-	if (cpu_data->epp_saved >= 0) {
-		epp = cpu_data->epp_saved;
-		cpu_data->epp_saved = -EINVAL;
-		goto update_epp;
-	}
-
 	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		epp = intel_pstate_get_epp(cpu_data, value);
 		cpu_data->epp_powersave = epp;
@@ -891,7 +896,6 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 
 		epp = cpu_data->epp_powersave;
 	}
-update_epp:
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		value &= ~GENMASK_ULL(31, 24);
 		value |= (u64)epp << 24;
@@ -903,14 +907,24 @@ skip_epp:
 	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
 
-static void intel_pstate_hwp_force_min_perf(int cpu)
+static void intel_pstate_hwp_offline(struct cpudata *cpu)
 {
-	u64 value;
+	u64 value = READ_ONCE(cpu->hwp_req_cached);
 	int min_perf;
 
-	value = all_cpu_data[cpu]->hwp_req_cached;
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
+		/*
+		 * In case the EPP has been set to "performance" by the
+		 * active mode "performance" scaling algorithm, replace that
+		 * temporary value with the cached EPP one.
+		 */
+		value &= ~GENMASK_ULL(31, 24);
+		value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached);
+		WRITE_ONCE(cpu->hwp_req_cached, value);
+	}
+
 	value &= ~GENMASK_ULL(31, 0);
-	min_perf = HWP_LOWEST_PERF(all_cpu_data[cpu]->hwp_cap_cached);
+	min_perf = HWP_LOWEST_PERF(cpu->hwp_cap_cached);
 
 	/* Set hwp_max = hwp_min */
 	value |= HWP_MAX_PERF(min_perf);
@@ -920,19 +934,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 
-	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
-}
-
-static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
-
-	if (!hwp_active)
-		return 0;
-
-	cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0);
-
-	return 0;
+	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
 }
 
 #define POWER_CTL_EE_ENABLE	1
@@ -959,8 +961,28 @@ static void set_power_ctl_ee_state(bool input)
 
 static void intel_pstate_hwp_enable(struct cpudata *cpudata);
 
+static void intel_pstate_hwp_reenable(struct cpudata *cpu)
+{
+	intel_pstate_hwp_enable(cpu);
+	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, READ_ONCE(cpu->hwp_req_cached));
+}
+
+static int intel_pstate_suspend(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d suspending\n", cpu->cpu);
+
+	cpu->suspended = true;
+
+	return 0;
+}
+
 static int intel_pstate_resume(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d resuming\n", cpu->cpu);
 
 	/* Only restore if the system default is changed */
 	if (power_ctl_ee_state == POWER_CTL_EE_ENABLE)
@@ -968,18 +990,16 @@ static int intel_pstate_resume(struct cpufreq_policy *policy)
 	else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE)
 		set_power_ctl_ee_state(false);
 
-	if (!hwp_active)
-		return 0;
+	if (cpu->suspended && hwp_active) {
+		mutex_lock(&intel_pstate_limits_lock);
 
-	mutex_lock(&intel_pstate_limits_lock);
+		/* Re-enable HWP, because "online" has not done that. */
+		intel_pstate_hwp_reenable(cpu);
 
-	if (policy->cpu == 0)
-		intel_pstate_hwp_enable(all_cpu_data[policy->cpu]);
+		mutex_unlock(&intel_pstate_limits_lock);
+	}
 
-	all_cpu_data[policy->cpu]->epp_policy = 0;
-	intel_pstate_hwp_set(policy->cpu);
-
-	mutex_unlock(&intel_pstate_limits_lock);
+	cpu->suspended = false;
 
 	return 0;
 }
@@ -1428,7 +1448,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
-	cpudata->epp_policy = 0;
 	if (cpudata->epp_default == -EINVAL)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 }
@@ -2097,25 +2116,31 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 		all_cpu_data[cpunum] = cpu;
 
-		cpu->epp_default = -EINVAL;
-		cpu->epp_powersave = -EINVAL;
-		cpu->epp_saved = -EINVAL;
-	}
-
-	cpu = all_cpu_data[cpunum];
+		cpu->cpu = cpunum;
 
-	cpu->cpu = cpunum;
+		cpu->epp_default = -EINVAL;
 
-	if (hwp_active) {
-		const struct x86_cpu_id *id;
+		if (hwp_active) {
+			const struct x86_cpu_id *id;
 
-		intel_pstate_hwp_enable(cpu);
+			intel_pstate_hwp_enable(cpu);
 
-		id = x86_match_cpu(intel_pstate_hwp_boost_ids);
-		if (id && intel_pstate_acpi_pm_profile_server())
-			hwp_boost = true;
+			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
+			if (id && intel_pstate_acpi_pm_profile_server())
+				hwp_boost = true;
+		}
+	} else if (hwp_active) {
+		/*
+		 * Re-enable HWP in case this happens after a resume from ACPI
+		 * S3 if the CPU was offline during the whole system/resume
+		 * cycle.
+		 */
+		intel_pstate_hwp_reenable(cpu);
 	}
 
+	cpu->epp_powersave = -EINVAL;
+	cpu->epp_policy = 0;
+
 	intel_pstate_get_cpu_pstates(cpu);
 
 	pr_debug("controlling: cpu %d\n", cpunum);
@@ -2296,28 +2321,61 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
-static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy)
+static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d going offline\n", cpu->cpu);
+
+	if (cpu->suspended)
+		return 0;
+
+	/*
+	 * If the CPU is an SMT thread and it goes offline with the performance
+	 * settings different from the minimum, it will prevent its sibling
+	 * from getting to lower performance levels, so force the minimum
+	 * performance on CPU offline to prevent that from happening.
+	 */
 	if (hwp_active)
-		intel_pstate_hwp_force_min_perf(policy->cpu);
+		intel_pstate_hwp_offline(cpu);
 	else
-		intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]);
+		intel_pstate_set_min_pstate(cpu);
+
+	intel_pstate_exit_perf_limits(policy);
+
+	return 0;
+}
+
+static int intel_pstate_cpu_online(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d going online\n", cpu->cpu);
+
+	intel_pstate_init_acpi_perf_limits(policy);
+
+	if (hwp_active) {
+		/*
+		 * Re-enable HWP and clear the "suspended" flag to let "resume"
+		 * know that it need not do that.
+		 */
+		intel_pstate_hwp_reenable(cpu);
+		cpu->suspended = false;
+	}
+
+	return 0;
 }
 
 static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 {
-	pr_debug("CPU %d exiting\n", policy->cpu);
+	pr_debug("CPU %d stopping\n", policy->cpu);
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
-	if (hwp_active)
-		intel_pstate_hwp_save_state(policy);
-
-	intel_cpufreq_stop_cpu(policy);
 }
 
 static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
-	intel_pstate_exit_perf_limits(policy);
+	pr_debug("CPU %d exiting\n", policy->cpu);
 
 	policy->fast_switch_possible = false;
 
@@ -2378,6 +2436,12 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	 */
 	policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
+	if (hwp_active) {
+		struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+		cpu->epp_cached = intel_pstate_get_epp(cpu, 0);
+	}
+
 	return 0;
 }
 
@@ -2385,11 +2449,13 @@ static struct cpufreq_driver intel_pstate = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
-	.suspend	= intel_pstate_hwp_save_state,
+	.suspend	= intel_pstate_suspend,
 	.resume		= intel_pstate_resume,
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
+	.offline	= intel_pstate_cpu_offline,
+	.online		= intel_pstate_cpu_online,
 	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_pstate",
 };
@@ -2585,7 +2651,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;
 		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
 		WRITE_ONCE(cpu->hwp_req_cached, value);
-		cpu->epp_cached = (value & GENMASK_ULL(31, 24)) >> 24;
+		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
 	} else {
 		turbo_max = cpu->pstate.turbo_pstate;
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
@@ -2644,7 +2710,10 @@ static struct cpufreq_driver intel_cpufreq = {
 	.fast_switch	= intel_cpufreq_fast_switch,
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_cpufreq_cpu_exit,
-	.stop_cpu	= intel_cpufreq_stop_cpu,
+	.offline	= intel_pstate_cpu_offline,
+	.online		= intel_pstate_cpu_online,
+	.suspend	= intel_pstate_suspend,
+	.resume		= intel_pstate_resume,
 	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
 };
@@ -2667,9 +2736,6 @@ static void intel_pstate_driver_cleanup(void)
 	}
 	put_online_cpus();
 
-	if (intel_pstate_driver == &intel_pstate)
-		intel_pstate_sysfs_hide_hwp_dynamic_boost();
-
 	intel_pstate_driver = NULL;
 }
 
@@ -2695,14 +2761,6 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver)
 	return 0;
 }
 
-static int intel_pstate_unregister_driver(void)
-{
-	cpufreq_unregister_driver(intel_pstate_driver);
-	intel_pstate_driver_cleanup();
-
-	return 0;
-}
-
 static ssize_t intel_pstate_show_status(char *buf)
 {
 	if (!intel_pstate_driver)
@@ -2714,20 +2772,23 @@ static ssize_t intel_pstate_show_status(char *buf)
 
 static int intel_pstate_update_status(const char *buf, size_t size)
 {
-	int ret;
+	if (size == 3 && !strncmp(buf, "off", size)) {
+		if (!intel_pstate_driver)
+			return -EINVAL;
+
+		if (hwp_active)
+			return -EBUSY;
 
-	if (size == 3 && !strncmp(buf, "off", size))
-		return intel_pstate_driver ?
-			intel_pstate_unregister_driver() : -EINVAL;
+		cpufreq_unregister_driver(intel_pstate_driver);
+		intel_pstate_driver_cleanup();
+	}
 
 	if (size == 6 && !strncmp(buf, "active", size)) {
 		if (intel_pstate_driver) {
 			if (intel_pstate_driver == &intel_pstate)
 				return 0;
 
-			ret = intel_pstate_unregister_driver();
-			if (ret)
-				return ret;
+			cpufreq_unregister_driver(intel_pstate_driver);
 		}
 
 		return intel_pstate_register_driver(&intel_pstate);
@@ -2738,9 +2799,8 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 			if (intel_pstate_driver == &intel_cpufreq)
 				return 0;
 
-			ret = intel_pstate_unregister_driver();
-			if (ret)
-				return ret;
+			cpufreq_unregister_driver(intel_pstate_driver);
+			intel_pstate_sysfs_hide_hwp_dynamic_boost();
 		}
 
 		return intel_pstate_register_driver(&intel_cpufreq);
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index bb61677c11c7..ef0a3216a386 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -129,7 +129,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 			return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
 		case 0x0D: /* Pentium M (Dothan) */
 			p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
-			/* fall through */
+			fallthrough;
 		case 0x09: /* Pentium M (Banias) */
 			return speedstep_get_frequency(SPEEDSTEP_CPU_PM);
 		}
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 5c4f8f07c5a6..a13a2d1e444e 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -366,7 +366,7 @@ enum speedstep_processor speedstep_detect_processor(void)
 			} else
 				return SPEEDSTEP_CPU_PIII_C;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index bae527e507e0..e1d931c457a7 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -56,9 +56,11 @@ struct read_counters_work {
 
 static struct workqueue_struct *read_counters_wq;
 
-static enum cluster get_cpu_cluster(u8 cpu)
+static void get_cpu_cluster(void *cluster)
 {
-	return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+
+	*((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 }
 
 /*
@@ -186,8 +188,10 @@ static unsigned int tegra194_get_speed(u32 cpu)
 static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	int cl = get_cpu_cluster(policy->cpu);
 	u32 cpu;
+	u32 cl;
+
+	smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true);
 
 	if (cl >= data->num_clusters)
 		return -EINVAL;
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index ab0de27539ad..8f9fdd864391 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -86,11 +86,11 @@ static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
 	case DRA76_EFUSE_HAS_PLUS_MPU_OPP:
 	case DRA76_EFUSE_HAS_ALL_MPU_OPP:
 		calculated_efuse |= DRA76_EFUSE_PLUS_MPU_OPP;
-		/* Fall through */
+		fallthrough;
 	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
 	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;
-		/* Fall through */
+		fallthrough;
 	case DRA7_EFUSE_HAS_OD_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP;
 	}
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 87197319ab06..04becd70cc41 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <linux/tick.h>
+#include <linux/mmu_context.h>
 #include <trace/events/power.h>
 
 #include "cpuidle.h"
@@ -145,21 +146,24 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 	 * executing it contains RCU usage regarded as invalid in the idle
 	 * context, so tell RCU about that.
 	 */
-	RCU_NONIDLE(tick_freeze());
+	tick_freeze();
 	/*
 	 * The state used here cannot be a "coupled" one, because the "coupled"
 	 * cpuidle mechanism enables interrupts and doing that with timekeeping
 	 * suspended is generally unsafe.
 	 */
 	stop_critical_timings();
+	rcu_idle_enter();
 	drv->states[index].enter_s2idle(dev, drv, index);
-	WARN_ON(!irqs_disabled());
+	if (WARN_ON_ONCE(!irqs_disabled()))
+		local_irq_disable();
 	/*
 	 * timekeeping_resume() that will be called by tick_unfreeze() for the
 	 * first CPU executing it calls functions containing RCU read-side
 	 * critical sections, so tell RCU about that.
 	 */
-	RCU_NONIDLE(tick_unfreeze());
+	rcu_idle_exit();
+	tick_unfreeze();
 	start_critical_timings();
 
 	time_end = ns_to_ktime(local_clock());
@@ -225,19 +229,24 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		broadcast = false;
 	}
 
+	if (target_state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
+		leave_mm(dev->cpu);
+
 	/* Take note of the planned idle state. */
 	sched_idle_set_state(target_state);
 
-	trace_cpu_idle_rcuidle(index, dev->cpu);
+	trace_cpu_idle(index, dev->cpu);
 	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
+	rcu_idle_enter();
 	entered_state = target_state->enter(dev, drv, index);
+	rcu_idle_exit();
 	start_critical_timings();
 
 	sched_clock_idle_wakeup_event();
 	time_end = ns_to_ktime(local_clock());
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+	trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
 	sched_idle_set_state(NULL);
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index aa3a4ed07a66..52a9b7cf6576 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -873,6 +873,9 @@ config CRYPTO_DEV_SA2UL
 	select CRYPTO_AES
 	select CRYPTO_AES_ARM64
 	select CRYPTO_ALGAPI
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
 	select HW_RANDOM
 	select SG_SPLIT
 	help
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 1a46eeddf082..809c3033ca74 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2310,7 +2310,7 @@ static int artpec6_crypto_prepare_submit_hash(struct ahash_request *req)
 
 	case ARTPEC6_CRYPTO_PREPARE_HASH_NO_START:
 		ret = 0;
-		/* Fallthrough */
+		fallthrough;
 
 	default:
 		artpec6_crypto_common_destroy(&req_ctx->common);
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index dc5fda522719..4fe7898c8561 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -90,11 +90,11 @@ static int setup_sgio_components(struct cpt_vf *cptvf, struct buf_ptr *list,
 	case 3:
 		sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size);
 		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
-		/* Fall through */
+		fallthrough;
 	case 2:
 		sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size);
 		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
-		/* Fall through */
+		fallthrough;
 	case 1:
 		sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size);
 		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c
index 91dee616d15e..c5cce024886a 100644
--- a/drivers/crypto/chelsio/chcr_ktls.c
+++ b/drivers/crypto/chelsio/chcr_ktls.c
@@ -135,7 +135,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info,
 			break;
 		/* update to the next state and also initialize TCB */
 		tx_info->connection_state = new_state;
-		/* FALLTHRU */
+		fallthrough;
 	case KTLS_CONN_ACT_OPEN_RPL:
 		/* if we are stuck in this state, means tcb init might not
 		 * received by HW, try sending it again.
@@ -150,7 +150,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info,
 			break;
 		/* update to the next state and check if l2t_state is valid  */
 		tx_info->connection_state = new_state;
-		/* FALLTHRU */
+		fallthrough;
 	case KTLS_CONN_SET_TCB_RPL:
 		/* Check if l2t state is valid, then move to ready state. */
 		if (cxgb4_check_l2t_valid(tx_info->l2te)) {
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
index cbc3d7869ebe..c80baf1ad90b 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
@@ -140,11 +140,11 @@ static inline int setup_sgio_components(struct pci_dev *pdev,
 	case 3:
 		sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size);
 		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
-		/* Fall through */
+		fallthrough;
 	case 2:
 		sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size);
 		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
-		/* Fall through */
+		fallthrough;
 	case 1:
 		sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size);
 		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/qat/qat_common/adf_admin.c
index 1c8ca151a963..ec9b390276d6 100644
--- a/drivers/crypto/qat/qat_common/adf_admin.c
+++ b/drivers/crypto/qat/qat_common/adf_admin.c
@@ -131,9 +131,10 @@ static int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev, u32 ae,
 	memcpy(admin->virt_addr + offset, in, ADF_ADMINMSG_LEN);
 	ADF_CSR_WR(mailbox, mb_offset, 1);
 
-	ret = readl_poll_timeout(mailbox + mb_offset, status,
-				 status == 0, ADF_ADMIN_POLL_DELAY_US,
-				 ADF_ADMIN_POLL_TIMEOUT_US);
+	ret = read_poll_timeout(ADF_CSR_RD, status, status == 0,
+				ADF_ADMIN_POLL_DELAY_US,
+				ADF_ADMIN_POLL_TIMEOUT_US, true,
+				mailbox, mb_offset);
 	if (ret < 0) {
 		/* Response timeout */
 		dev_err(&GET_DEV(accel_dev),
diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
index 519fd5acf713..8b090b7ae8c6 100644
--- a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
+++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
@@ -340,7 +340,7 @@ static int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev)
 		/* VF is newer than PF and decides whether it is compatible */
 		if (accel_dev->vf.pf_version >= hw_data->min_iov_compat_ver)
 			break;
-		/* fall through */
+		fallthrough;
 	case ADF_PF2VF_VF_INCOMPATIBLE:
 		dev_err(&GET_DEV(accel_dev),
 			"PF (vers %d) and VF (vers %d) are not compatible\n",
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index bff759e2f811..00c615f9f9a8 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -752,7 +752,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle,
 	case ICP_GPA_ABS:
 	case ICP_GPB_ABS:
 		ctx_mask = 0;
-		/* fall through */
+		fallthrough;
 	case ICP_GPA_REL:
 	case ICP_GPB_REL:
 		return qat_hal_init_gpr(handle, ae, ctx_mask, reg_type,
@@ -762,7 +762,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle,
 	case ICP_SR_RD_ABS:
 	case ICP_DR_RD_ABS:
 		ctx_mask = 0;
-		/* fall through */
+		fallthrough;
 	case ICP_SR_REL:
 	case ICP_DR_REL:
 	case ICP_SR_RD_REL:
@@ -772,7 +772,7 @@ static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle,
 	case ICP_SR_WR_ABS:
 	case ICP_DR_WR_ABS:
 		ctx_mask = 0;
-		/* fall through */
+		fallthrough;
 	case ICP_SR_WR_REL:
 	case ICP_DR_WR_REL:
 		return qat_hal_init_wr_xfer(handle, ae, ctx_mask, reg_type,
diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c
index f22f6fa612b3..9866c2a5e9a7 100644
--- a/drivers/crypto/ux500/cryp/cryp.c
+++ b/drivers/crypto/ux500/cryp/cryp.c
@@ -314,17 +314,17 @@ void cryp_save_device_context(struct cryp_device_data *device_data,
 	case CRYP_KEY_SIZE_256:
 		ctx->key_4_l = readl_relaxed(&src_reg->key_4_l);
 		ctx->key_4_r = readl_relaxed(&src_reg->key_4_r);
-		/* Fall through */
+		fallthrough;
 
 	case CRYP_KEY_SIZE_192:
 		ctx->key_3_l = readl_relaxed(&src_reg->key_3_l);
 		ctx->key_3_r = readl_relaxed(&src_reg->key_3_r);
-		/* Fall through */
+		fallthrough;
 
 	case CRYP_KEY_SIZE_128:
 		ctx->key_2_l = readl_relaxed(&src_reg->key_2_l);
 		ctx->key_2_r = readl_relaxed(&src_reg->key_2_r);
-		/* Fall through */
+		fallthrough;
 
 	default:
 		ctx->key_1_l = readl_relaxed(&src_reg->key_1_l);
@@ -364,17 +364,17 @@ void cryp_restore_device_context(struct cryp_device_data *device_data,
 	case CRYP_KEY_SIZE_256:
 		writel_relaxed(ctx->key_4_l, &reg->key_4_l);
 		writel_relaxed(ctx->key_4_r, &reg->key_4_r);
-		/* Fall through */
+		fallthrough;
 
 	case CRYP_KEY_SIZE_192:
 		writel_relaxed(ctx->key_3_l, &reg->key_3_l);
 		writel_relaxed(ctx->key_3_r, &reg->key_3_r);
-		/* Fall through */
+		fallthrough;
 
 	case CRYP_KEY_SIZE_128:
 		writel_relaxed(ctx->key_2_l, &reg->key_2_l);
 		writel_relaxed(ctx->key_2_r, &reg->key_2_r);
-		/* Fall through */
+		fallthrough;
 
 	default:
 		writel_relaxed(ctx->key_1_l, &reg->key_1_l);
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 4c0af2eb7e19..1e89513f3c59 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -429,7 +429,7 @@ int dev_dax_probe(struct device *dev)
 		return -EBUSY;
 	}
 
-	dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
+	dev_dax->pgmap.type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index c82cbcb64202..e5767c83ea23 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -100,6 +100,12 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 		return false;
 	}
 
+	if (!dax_dev || !bdev_dax_supported(bdev, blocksize)) {
+		pr_debug("%s: error: dax unsupported by block device\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
 	id = dax_read_lock();
 	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
 	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 1699a8e309ef..58564d82a3a2 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -316,9 +316,9 @@ out:
  * name of the dma-buf if the same piece of memory is used for multiple
  * purpose between different devices.
  *
- * @dmabuf [in]     dmabuf buffer that will be renamed.
- * @buf:   [in]     A piece of userspace memory that contains the name of
- *                  the dma-buf.
+ * @dmabuf: [in]     dmabuf buffer that will be renamed.
+ * @buf:    [in]     A piece of userspace memory that contains the name of
+ *                   the dma-buf.
  *
  * Returns 0 on success. If the dma-buf buffer is already attached to
  * devices, return -EBUSY.
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
index 3d123502ff12..7d129e68ac70 100644
--- a/drivers/dma-buf/dma-fence-chain.c
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -222,6 +222,7 @@ EXPORT_SYMBOL(dma_fence_chain_ops);
  * @chain: the chain node to initialize
  * @prev: the previous fence
  * @fence: the current fence
+ * @seqno: the sequence number to use for the fence chain
  *
  * Initialize a new chain node and either start a new chain or add the node to
  * the existing chain of the previous fence.
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 35f4804ea4af..235f1396f968 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -135,11 +135,13 @@ static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
 		if (ret < 0) {
 			dev_warn(&adev->dev,
 				 "error in parsing resource group\n");
-			return;
+			break;
 		}
 
 		grp = (struct acpi_csrt_group *)((void *)grp + grp->length);
 	}
+
+	acpi_put_table((struct acpi_table_header *)csrt);
 }
 
 /**
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 9adc7a2fa3d3..a24882ba3764 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1767,7 +1767,7 @@ static u32 pl08x_memcpy_cctl(struct pl08x_driver_data *pl08x)
 	default:
 		dev_err(&pl08x->adev->dev,
 			"illegal burst size for memcpy, set to 1\n");
-		/* Fall through */
+		fallthrough;
 	case PL08X_BURST_SZ_1:
 		cctl |= PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT |
 			PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT;
@@ -1806,7 +1806,7 @@ static u32 pl08x_memcpy_cctl(struct pl08x_driver_data *pl08x)
 	default:
 		dev_err(&pl08x->adev->dev,
 			"illegal bus width for memcpy, set to 8 bits\n");
-		/* Fall through */
+		fallthrough;
 	case PL08X_BUS_WIDTH_8_BITS:
 		cctl |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT |
 			PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT;
@@ -1850,7 +1850,7 @@ static u32 pl08x_ftdmac020_memcpy_cctl(struct pl08x_driver_data *pl08x)
 	default:
 		dev_err(&pl08x->adev->dev,
 			"illegal bus width for memcpy, set to 8 bits\n");
-		/* Fall through */
+		fallthrough;
 	case PL08X_BUS_WIDTH_8_BITS:
 		cctl |= PL080_WIDTH_8BIT << FTDMAC020_LLI_SRC_WIDTH_SHIFT |
 			PL080_WIDTH_8BIT << FTDMAC020_LLI_DST_WIDTH_SHIFT;
@@ -2612,7 +2612,7 @@ static int pl08x_of_probe(struct amba_device *adev,
 	switch (val) {
 	default:
 		dev_err(&adev->dev, "illegal burst size for memcpy, set to 1\n");
-		/* Fall through */
+		fallthrough;
 	case 1:
 		pd->memcpy_burst_size = PL08X_BURST_SZ_1;
 		break;
@@ -2647,7 +2647,7 @@ static int pl08x_of_probe(struct amba_device *adev,
 	switch (val) {
 	default:
 		dev_err(&adev->dev, "illegal bus width for memcpy, set to 8 bits\n");
-		/* Fall through */
+		fallthrough;
 	case 8:
 		pd->memcpy_bus_width = PL08X_BUS_WIDTH_8_BITS;
 		break;
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 45bbcd6146fd..a2cf25c6e3b3 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1650,13 +1650,17 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	dmac_pdev = of_find_device_by_node(dma_spec->np);
+	if (!dmac_pdev)
+		return NULL;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
 	atslave = kmalloc(sizeof(*atslave), GFP_KERNEL);
-	if (!atslave)
+	if (!atslave) {
+		put_device(&dmac_pdev->dev);
 		return NULL;
+	}
 
 	atslave->cfg = ATC_DST_H2SEL_HW | ATC_SRC_H2SEL_HW;
 	/*
@@ -1685,8 +1689,11 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec,
 	atslave->dma_dev = &dmac_pdev->dev;
 
 	chan = dma_request_channel(mask, at_dma_filter, atslave);
-	if (!chan)
+	if (!chan) {
+		put_device(&dmac_pdev->dev);
+		kfree(atslave);
 		return NULL;
+	}
 
 	atchan = to_at_dma_chan(chan);
 	atchan->per_if = dma_spec->args[0] & 0xff;
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 448f663da89c..8beed91428bd 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -879,24 +879,11 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	ret = platform_get_irq(pdev, 0);
-	if (ret < 0)
-		return ret;
-
-	jzdma->irq = ret;
-
-	ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev),
-			  jzdma);
-	if (ret) {
-		dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq);
-		return ret;
-	}
-
 	jzdma->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(jzdma->clk)) {
 		dev_err(dev, "failed to get clock\n");
 		ret = PTR_ERR(jzdma->clk);
-		goto err_free_irq;
+		return ret;
 	}
 
 	clk_prepare_enable(jzdma->clk);
@@ -949,10 +936,23 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 		jzchan->vchan.desc_free = jz4780_dma_desc_free;
 	}
 
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto err_disable_clk;
+
+	jzdma->irq = ret;
+
+	ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev),
+			  jzdma);
+	if (ret) {
+		dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq);
+		goto err_disable_clk;
+	}
+
 	ret = dmaenginem_async_device_register(dd);
 	if (ret) {
 		dev_err(dev, "failed to register device\n");
-		goto err_disable_clk;
+		goto err_free_irq;
 	}
 
 	/* Register with OF DMA helpers. */
@@ -960,17 +960,17 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 					 jzdma);
 	if (ret) {
 		dev_err(dev, "failed to register OF DMA controller\n");
-		goto err_disable_clk;
+		goto err_free_irq;
 	}
 
 	dev_info(dev, "JZ4780 DMA controller initialised\n");
 	return 0;
 
-err_disable_clk:
-	clk_disable_unprepare(jzdma->clk);
-
 err_free_irq:
 	free_irq(jzdma->irq, jzdma);
+
+err_disable_clk:
+	clk_disable_unprepare(jzdma->clk);
 	return ret;
 }
 
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index ed430ad9b3dd..b971505b8715 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -405,7 +405,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 			if (xfer->cyclic) {
 				burst->dar = xfer->xfer.cyclic.paddr;
 			} else {
-				burst->dar = sg_dma_address(sg);
+				burst->dar = dst_addr;
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -413,14 +413,13 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
-				src_addr += sg_dma_len(sg);
 			}
 		} else {
 			burst->dar = dst_addr;
 			if (xfer->cyclic) {
 				burst->sar = xfer->xfer.cyclic.paddr;
 			} else {
-				burst->sar = sg_dma_address(sg);
+				burst->sar = src_addr;
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -428,12 +427,14 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
-				dst_addr += sg_dma_len(sg);
 			}
 		}
 
-		if (!xfer->cyclic)
+		if (!xfer->cyclic) {
+			src_addr += sg_dma_len(sg);
+			dst_addr += sg_dma_len(sg);
 			sg = sg_next(sg);
+		}
 	}
 
 	return vchan_tx_prep(&chan->vc, &desc->vd, xfer->flags);
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index ad72b3f42ffa..e342cf52d296 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -1163,7 +1163,7 @@ static int fsl_dma_chan_probe(struct fsldma_device *fdev,
 	switch (chan->feature & FSL_DMA_IP_MASK) {
 	case FSL_DMA_IP_85XX:
 		chan->toggle_ext_pause = fsl_chan_toggle_ext_pause;
-		/* Fall through */
+		fallthrough;
 	case FSL_DMA_IP_83XX:
 		chan->toggle_ext_start = fsl_chan_toggle_ext_start;
 		chan->set_src_loop_size = fsl_chan_set_src_loop_size;
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 56f18ae99233..308bed0a560a 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -205,10 +205,10 @@ struct fsldma_chan {
 #else
 static u64 fsl_ioread64(const u64 __iomem *addr)
 {
-	u32 fsl_addr = lower_32_bits(addr);
-	u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32;
+	u32 val_lo = in_le32((u32 __iomem *)addr);
+	u32 val_hi = in_le32((u32 __iomem *)addr + 1);
 
-	return fsl_addr_hi | in_le32((u32 *)fsl_addr);
+	return ((u64)val_hi << 32) + val_lo;
 }
 
 static void fsl_iowrite64(u64 val, u64 __iomem *addr)
@@ -219,10 +219,10 @@ static void fsl_iowrite64(u64 val, u64 __iomem *addr)
 
 static u64 fsl_ioread64be(const u64 __iomem *addr)
 {
-	u32 fsl_addr = lower_32_bits(addr);
-	u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32;
+	u32 val_hi = in_be32((u32 __iomem *)addr);
+	u32 val_lo = in_be32((u32 __iomem *)addr + 1);
 
-	return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1));
+	return ((u64)val_hi << 32) + val_lo;
 }
 
 static void fsl_iowrite64be(u64 val, u64 __iomem *addr)
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 14b45853aa5f..b75d699160bf 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -410,10 +410,27 @@ int idxd_device_enable(struct idxd_device *idxd)
 	return 0;
 }
 
+void idxd_device_wqs_clear_state(struct idxd_device *idxd)
+{
+	int i;
+
+	lockdep_assert_held(&idxd->dev_lock);
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		if (wq->state == IDXD_WQ_ENABLED) {
+			idxd_wq_disable_cleanup(wq);
+			wq->state = IDXD_WQ_DISABLED;
+		}
+	}
+}
+
 int idxd_device_disable(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
 	u32 status;
+	unsigned long flags;
 
 	if (!idxd_is_enabled(idxd)) {
 		dev_dbg(dev, "Device is not enabled\n");
@@ -429,13 +446,22 @@ int idxd_device_disable(struct idxd_device *idxd)
 		return -ENXIO;
 	}
 
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	idxd_device_wqs_clear_state(idxd);
 	idxd->state = IDXD_DEV_CONF_READY;
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
 	return 0;
 }
 
 void idxd_device_reset(struct idxd_device *idxd)
 {
+	unsigned long flags;
+
 	idxd_cmd_exec(idxd, IDXD_CMD_RESET_DEVICE, 0, NULL);
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	idxd_device_wqs_clear_state(idxd);
+	idxd->state = IDXD_DEV_CONF_READY;
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
 }
 
 /* Device configuration bits */
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index b5142556cc4e..1e9e6991f543 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -11,18 +11,6 @@
 #include "idxd.h"
 #include "registers.h"
 
-void idxd_device_wqs_clear_state(struct idxd_device *idxd)
-{
-	int i;
-
-	lockdep_assert_held(&idxd->dev_lock);
-	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
-
-		wq->state = IDXD_WQ_DISABLED;
-	}
-}
-
 static void idxd_device_reinit(struct work_struct *work)
 {
 	struct idxd_device *idxd = container_of(work, struct idxd_device, work);
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 5c0fb3134825..88717506c1f6 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -556,7 +556,7 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 		 * We fall-through here intentionally, since a 2D transfer is
 		 * similar to MEMCPY just adding the 2D slot configuration.
 		 */
-		/* Fall through */
+		fallthrough;
 	case IMXDMA_DESC_MEMCPY:
 		imx_dmav1_writel(imxdma, d->src, DMA_SAR(imxdmac->channel));
 		imx_dmav1_writel(imxdma, d->dest, DMA_DAR(imxdmac->channel));
diff --git a/drivers/dma/iop-adma.h b/drivers/dma/iop-adma.h
index c499c9578f00..d44eabb6f5eb 100644
--- a/drivers/dma/iop-adma.h
+++ b/drivers/dma/iop-adma.h
@@ -496,7 +496,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt,
 		}
 		hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = edcr;
 		src_cnt = 24;
-		/* fall through */
+		fallthrough;
 	case 17 ... 24:
 		if (!u_desc_ctrl.field.blk_ctrl) {
 			hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
@@ -510,7 +510,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt,
 		}
 		hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = edcr;
 		src_cnt = 16;
-		/* fall through */
+		fallthrough;
 	case 9 ... 16:
 		if (!u_desc_ctrl.field.blk_ctrl)
 			u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */
@@ -522,7 +522,7 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt,
 		}
 		hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = edcr;
 		src_cnt = 8;
-		/* fall through */
+		fallthrough;
 	case 2 ... 8:
 		shift = 1;
 		for (i = 0; i < src_cnt; i++) {
@@ -602,19 +602,19 @@ iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt,
 	case 25 ... 32:
 		u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
 		hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
-		/* fall through */
+		fallthrough;
 	case 17 ... 24:
 		if (!u_desc_ctrl.field.blk_ctrl) {
 			hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
 			u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
 		}
 		hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = 0;
-		/* fall through */
+		fallthrough;
 	case 9 ... 16:
 		if (!u_desc_ctrl.field.blk_ctrl)
 			u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */
 		hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = 0;
-		/* fall through */
+		fallthrough;
 	case 1 ... 8:
 		if (!u_desc_ctrl.field.blk_ctrl && src_cnt > 4)
 			u_desc_ctrl.field.blk_ctrl = 0x1; /* use mini-desc */
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 74df621402e1..ca4e0930207a 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -483,7 +483,7 @@ static size_t nbpf_xfer_size(struct nbpf_device *nbpf,
 
 	default:
 		pr_warn("%s(): invalid bus width %u\n", __func__, width);
-		/* fall through */
+		fallthrough;
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
 		size = burst;
 	}
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 863f2aaf5c8f..8a4f608904b9 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -71,12 +71,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
-	if (chan) {
-		chan->router = ofdma->dma_router;
-		chan->route_data = route_data;
-	} else {
+	if (IS_ERR_OR_NULL(chan)) {
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
+	} else {
+		chan->router = ofdma->dma_router;
+		chan->route_data = route_data;
 	}
 
 	/*
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 2c508ee672b9..5274a0704d96 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1061,16 +1061,16 @@ static bool _start(struct pl330_thread *thrd)
 
 		if (_state(thrd) == PL330_STATE_KILLING)
 			UNTIL(thrd, PL330_STATE_STOPPED)
-		/* fall through */
+		fallthrough;
 
 	case PL330_STATE_FAULTING:
 		_stop(thrd);
-		/* fall through */
+		fallthrough;
 
 	case PL330_STATE_KILLING:
 	case PL330_STATE_COMPLETING:
 		UNTIL(thrd, PL330_STATE_STOPPED)
-		/* fall through */
+		fallthrough;
 
 	case PL330_STATE_STOPPED:
 		return _trigger(thrd);
@@ -1121,7 +1121,6 @@ static u32 _emit_load(unsigned int dry_run, u8 buf[],
 
 	switch (direction) {
 	case DMA_MEM_TO_MEM:
-		/* fall through */
 	case DMA_MEM_TO_DEV:
 		off += _emit_LD(dry_run, &buf[off], cond);
 		break;
@@ -1155,7 +1154,6 @@ static inline u32 _emit_store(unsigned int dry_run, u8 buf[],
 
 	switch (direction) {
 	case DMA_MEM_TO_MEM:
-		/* fall through */
 	case DMA_DEV_TO_MEM:
 		off += _emit_ST(dry_run, &buf[off], cond);
 		break;
@@ -1216,7 +1214,6 @@ static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
-		/* fall through */
 	case DMA_DEV_TO_MEM:
 		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, cyc,
 			cond);
@@ -1266,7 +1263,6 @@ static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[],
 
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
-		/* fall through */
 	case DMA_DEV_TO_MEM:
 		off += _emit_MOV(dry_run, &buf[off], CCR, dregs_ccr);
 		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, 1,
@@ -2801,6 +2797,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	while (burst != (1 << desc->rqcfg.brst_size))
 		desc->rqcfg.brst_size++;
 
+	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	/*
 	 * If burst size is smaller than bus width then make sure we only
 	 * transfer one at a time to avoid a burst stradling an MFIFO entry.
@@ -2808,7 +2805,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width)
 		desc->rqcfg.brst_len = 1;
 
-	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 2deeaab078a4..788d696323bb 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -383,7 +383,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 			switch (desc->mark) {
 			case DESC_COMPLETED:
 				desc->mark = DESC_WAITING;
-				/* Fall through */
+				fallthrough;
 			case DESC_WAITING:
 				if (head_acked)
 					async_tx_ack(&desc->async_tx);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index c14e6cb105cd..d86dba0fd8e6 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -2059,9 +2059,9 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 			return NULL;
 		}
 
-		cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false,
-			      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
-		cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT);
+		cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false,
+			      false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+		cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT);
 
 		tr_req[tr_idx].addr = sg_addr;
 		tr_req[tr_idx].icnt0 = tr0_cnt0;
@@ -3101,14 +3101,14 @@ static struct udma_match_data am654_main_data = {
 	.psil_base = 0x1000,
 	.enable_memcpy_support = true,
 	.statictr_z_mask = GENMASK(11, 0),
-	.rchan_oes_offset = 0x2000,
+	.rchan_oes_offset = 0x200,
 };
 
 static struct udma_match_data am654_mcu_data = {
 	.psil_base = 0x6000,
 	.enable_memcpy_support = false,
 	.statictr_z_mask = GENMASK(11, 0),
-	.rchan_oes_offset = 0x2000,
+	.rchan_oes_offset = 0x200,
 };
 
 static struct udma_match_data j721e_main_data = {
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 6262f6370c5d..fcc08bbf6945 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3375,7 +3375,7 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			pvt->ops = &family_types[F17_M70H_CPUS].ops;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case 0x18:
 		fam_type	= &family_types[F17_CPUS];
 		pvt->ops	= &family_types[F17_CPUS].ops;
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index da60c29468a7..54ebc8afc6b1 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -55,6 +55,8 @@ static DEFINE_SPINLOCK(ghes_lock);
 static bool __read_mostly force_load;
 module_param(force_load, bool, 0);
 
+static bool system_scanned;
+
 /* Memory Device - Type 17 of SMBIOS spec */
 struct memdev_dmi_entry {
 	u8 type;
@@ -225,14 +227,12 @@ static void enumerate_dimms(const struct dmi_header *dh, void *arg)
 
 static void ghes_scan_system(void)
 {
-	static bool scanned;
-
-	if (scanned)
+	if (system_scanned)
 		return;
 
 	dmi_walk(enumerate_dimms, &ghes_hw);
 
-	scanned = true;
+	system_scanned = true;
 }
 
 void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
@@ -631,6 +631,8 @@ void ghes_edac_unregister(struct ghes *ghes)
 
 	mutex_lock(&ghes_reg_mutex);
 
+	system_scanned = false;
+
 	if (!refcount_dec_and_test(&ghes_refcount))
 		goto unlock;
 
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 5860ca41185c..2acd9f9284a2 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1710,9 +1710,9 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci,
 	if (uncorrected_error) {
 		core_err_cnt = 1;
 		if (ripv)
-			tp_event = HW_EVENT_ERR_FATAL;
-		else
 			tp_event = HW_EVENT_ERR_UNCORRECTED;
+		else
+			tp_event = HW_EVENT_ERR_FATAL;
 	} else {
 		tp_event = HW_EVENT_ERR_CORRECTED;
 	}
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index fd363746f5b0..928f63a374c7 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -198,7 +198,7 @@ static int apl_rd_reg(int port, int off, int op, void *data, size_t sz, char *na
 	switch (sz) {
 	case 8:
 		ret = _apl_rd_reg(port, off + 4, op, (u32 *)(data + 4));
-		/* fall through */
+		fallthrough;
 	case 4:
 		ret |= _apl_rd_reg(port, off, op, (u32 *)data);
 		pnd2_printk(KERN_DEBUG, "%s=%x%08x ret=%d\n", name,
@@ -1155,7 +1155,7 @@ static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m,
 	u32 optypenum = GET_BITFIELD(m->status, 4, 6);
 	int rc;
 
-	tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) :
+	tp_event = uc_err ? (ripv ? HW_EVENT_ERR_UNCORRECTED : HW_EVENT_ERR_FATAL) :
 						 HW_EVENT_ERR_CORRECTED;
 
 	/*
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index d414698ca324..c5ab634cb6a4 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -2982,9 +2982,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	if (uncorrected_error) {
 		core_err_cnt = 1;
 		if (ripv) {
-			tp_event = HW_EVENT_ERR_FATAL;
-		} else {
 			tp_event = HW_EVENT_ERR_UNCORRECTED;
+		} else {
+			tp_event = HW_EVENT_ERR_FATAL;
 		}
 	} else {
 		tp_event = HW_EVENT_ERR_CORRECTED;
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 6d8d6dc626bf..2b4ce8e5ac2f 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -493,9 +493,9 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
 	if (uncorrected_error) {
 		core_err_cnt = 1;
 		if (ripv) {
-			tp_event = HW_EVENT_ERR_FATAL;
-		} else {
 			tp_event = HW_EVENT_ERR_UNCORRECTED;
+		} else {
+			tp_event = HW_EVENT_ERR_FATAL;
 		}
 	} else {
 		tp_event = HW_EVENT_ERR_CORRECTED;
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index b785e936244f..80db43a22069 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -957,7 +957,7 @@ static void set_broadcast_channel(struct fw_device *device, int generation)
 				device->bc_implemented = BC_IMPLEMENTED;
 				break;
 			}
-			/* else, fall through - to case address error */
+			fallthrough;	/* to case address error */
 		case RCODE_ADDRESS_ERROR:
 			device->bc_implemented = BC_UNIMPLEMENTED;
 		}
diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c
index 185b0b78b3d6..af70e74f9a7e 100644
--- a/drivers/firewire/core-iso.c
+++ b/drivers/firewire/core-iso.c
@@ -277,7 +277,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation,
 			if ((data[0] & bit) == (data[1] & bit))
 				continue;
 
-			/* fall through - It's a 1394-1995 IRM, retry. */
+			fallthrough;	/* It's a 1394-1995 IRM, retry */
 		default:
 			if (retry) {
 				retry--;
diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c
index 94a13fca8267..ec68ed27b0a5 100644
--- a/drivers/firewire/core-topology.c
+++ b/drivers/firewire/core-topology.c
@@ -54,7 +54,7 @@ static u32 *count_ports(u32 *sid, int *total_port_count, int *child_port_count)
 		switch (port_type) {
 		case SELFID_PORT_CHILD:
 			(*child_port_count)++;
-			/* fall through */
+			fallthrough;
 		case SELFID_PORT_PARENT:
 		case SELFID_PORT_NCONN:
 			(*total_port_count)++;
diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c
index 439d918bbaaf..ac487c96bb71 100644
--- a/drivers/firewire/core-transaction.c
+++ b/drivers/firewire/core-transaction.c
@@ -1097,14 +1097,14 @@ static void handle_registers(struct fw_card *card, struct fw_request *request,
 			rcode = RCODE_ADDRESS_ERROR;
 			break;
 		}
-		/* else fall through */
+		fallthrough;
 
 	case CSR_NODE_IDS:
 		/*
 		 * per IEEE 1394-2008 8.3.22.3, not IEEE 1394.1-2004 3.2.8
 		 * and 9.6, but interoperable with IEEE 1394.1-2004 bridges
 		 */
-		/* fall through */
+		fallthrough;
 
 	case CSR_STATE_CLEAR:
 	case CSR_STATE_SET:
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 7dde21b18b04..020cb15a4d8f 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -1495,7 +1495,7 @@ static int handle_at_packet(struct context *context,
 			packet->ack = RCODE_GENERATION;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	default:
 		packet->ack = RCODE_SEND_ERROR;
@@ -3054,7 +3054,7 @@ static int ohci_start_iso(struct fw_iso_context *base,
 
 	case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL:
 		control |= IR_CONTEXT_BUFFER_FILL|IR_CONTEXT_MULTI_CHANNEL_MODE;
-		/* fall through */
+		fallthrough;
 	case FW_ISO_CONTEXT_RECEIVE:
 		index = ctx - ohci->ir_context_list;
 		match = (tags << 28) | (sync << 8) | ctx->base.channel;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index fdd1db025dbf..3aa07c3b5136 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -381,6 +381,7 @@ static int __init efisubsys_init(void)
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
 	if (!efi_kobj) {
 		pr_err("efi: Firmware registration failed.\n");
+		destroy_workqueue(efi_rts_wq);
 		return -ENOMEM;
 	}
 
@@ -424,6 +425,7 @@ err_unregister:
 		generic_ops_unregister();
 err_put:
 	kobject_put(efi_kobj);
+	destroy_workqueue(efi_rts_wq);
 	return error;
 }
 
diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index e97a9c9d010c..21ae0c48232a 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -16,9 +16,9 @@
 
 /* Exported for use by lib/test_firmware.c only */
 LIST_HEAD(efi_embedded_fw_list);
-EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-
-static bool checked_for_fw;
+EXPORT_SYMBOL_NS_GPL(efi_embedded_fw_list, TEST_FIRMWARE);
+bool efi_embedded_fw_checked;
+EXPORT_SYMBOL_NS_GPL(efi_embedded_fw_checked, TEST_FIRMWARE);
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -116,14 +116,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	checked_for_fw = true;
+	efi_embedded_fw_checked = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!checked_for_fw) {
+	if (!efi_embedded_fw_checked) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 6bca70bbb43d..f735db55adc0 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -187,20 +187,28 @@ int efi_printk(const char *fmt, ...)
  */
 efi_status_t efi_parse_options(char const *cmdline)
 {
-	size_t len = strlen(cmdline) + 1;
+	size_t len;
 	efi_status_t status;
 	char *str, *buf;
 
+	if (!cmdline)
+		return EFI_SUCCESS;
+
+	len = strnlen(cmdline, COMMAND_LINE_SIZE - 1) + 1;
 	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, len, (void **)&buf);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	str = skip_spaces(memcpy(buf, cmdline, len));
+	memcpy(buf, cmdline, len - 1);
+	buf[len - 1] = '\0';
+	str = skip_spaces(buf);
 
 	while (*str) {
 		char *param, *val;
 
 		str = next_arg(str, &param, &val);
+		if (!val && !strcmp(param, "--"))
+			break;
 
 		if (!strcmp(param, "nokaslr")) {
 			efi_nokaslr = true;
diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 53cee17d0115..722af9ee53d6 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -65,36 +65,18 @@ struct ti_sci_xfers_info {
 };
 
 /**
- * struct ti_sci_rm_type_map - Structure representing TISCI Resource
- *				management representation of dev_ids.
- * @dev_id:	TISCI device ID
- * @type:	Corresponding id as identified by TISCI RM.
- *
- * Note: This is used only as a work around for using RM range apis
- *	for AM654 SoC. For future SoCs dev_id will be used as type
- *	for RM range APIs. In order to maintain ABI backward compatibility
- *	type is not being changed for AM654 SoC.
- */
-struct ti_sci_rm_type_map {
-	u32 dev_id;
-	u16 type;
-};
-
-/**
  * struct ti_sci_desc - Description of SoC integration
  * @default_host_id:	Host identifier representing the compute entity
  * @max_rx_timeout_ms:	Timeout for communication with SoC (in Milliseconds)
  * @max_msgs: Maximum number of messages that can be pending
  *		  simultaneously in the system
  * @max_msg_size: Maximum size of data per message that can be handled.
- * @rm_type_map: RM resource type mapping structure.
  */
 struct ti_sci_desc {
 	u8 default_host_id;
 	int max_rx_timeout_ms;
 	int max_msgs;
 	int max_msg_size;
-	struct ti_sci_rm_type_map *rm_type_map;
 };
 
 /**
@@ -1710,33 +1692,6 @@ fail:
 	return ret;
 }
 
-static int ti_sci_get_resource_type(struct ti_sci_info *info, u16 dev_id,
-				    u16 *type)
-{
-	struct ti_sci_rm_type_map *rm_type_map = info->desc->rm_type_map;
-	bool found = false;
-	int i;
-
-	/* If map is not provided then assume dev_id is used as type */
-	if (!rm_type_map) {
-		*type = dev_id;
-		return 0;
-	}
-
-	for (i = 0; rm_type_map[i].dev_id; i++) {
-		if (rm_type_map[i].dev_id == dev_id) {
-			*type = rm_type_map[i].type;
-			found = true;
-			break;
-		}
-	}
-
-	if (!found)
-		return -EINVAL;
-
-	return 0;
-}
-
 /**
  * ti_sci_get_resource_range - Helper to get a range of resources assigned
  *			       to a host. Resource is uniquely identified by
@@ -1760,7 +1715,6 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 	struct ti_sci_xfer *xfer;
 	struct ti_sci_info *info;
 	struct device *dev;
-	u16 type;
 	int ret = 0;
 
 	if (IS_ERR(handle))
@@ -1780,15 +1734,9 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 		return ret;
 	}
 
-	ret = ti_sci_get_resource_type(info, dev_id, &type);
-	if (ret) {
-		dev_err(dev, "rm type lookup failed for %u\n", dev_id);
-		goto fail;
-	}
-
 	req = (struct ti_sci_msg_req_get_resource_range *)xfer->xfer_buf;
 	req->secondary_host = s_host;
-	req->type = type & MSG_RM_RESOURCE_TYPE_MASK;
+	req->type = dev_id & MSG_RM_RESOURCE_TYPE_MASK;
 	req->subtype = subtype & MSG_RM_RESOURCE_SUBTYPE_MASK;
 
 	ret = ti_sci_do_xfer(info, xfer);
@@ -3260,61 +3208,50 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res)
 EXPORT_SYMBOL_GPL(ti_sci_get_num_resources);
 
 /**
- * devm_ti_sci_get_of_resource() - Get a TISCI resource assigned to a device
+ * devm_ti_sci_get_resource_sets() - Get a TISCI resources assigned to a device
  * @handle:	TISCI handle
  * @dev:	Device pointer to which the resource is assigned
  * @dev_id:	TISCI device id to which the resource is assigned
- * @of_prop:	property name by which the resource are represented
+ * @sub_types:	Array of sub_types assigned corresponding to device
+ * @sets:	Number of sub_types
  *
  * Return: Pointer to ti_sci_resource if all went well else appropriate
  *	   error pointer.
  */
-struct ti_sci_resource *
-devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle,
-			    struct device *dev, u32 dev_id, char *of_prop)
+static struct ti_sci_resource *
+devm_ti_sci_get_resource_sets(const struct ti_sci_handle *handle,
+			      struct device *dev, u32 dev_id, u32 *sub_types,
+			      u32 sets)
 {
 	struct ti_sci_resource *res;
 	bool valid_set = false;
-	u32 resource_subtype;
 	int i, ret;
 
 	res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL);
 	if (!res)
 		return ERR_PTR(-ENOMEM);
 
-	ret = of_property_count_elems_of_size(dev_of_node(dev), of_prop,
-					      sizeof(u32));
-	if (ret < 0) {
-		dev_err(dev, "%s resource type ids not available\n", of_prop);
-		return ERR_PTR(ret);
-	}
-	res->sets = ret;
-
+	res->sets = sets;
 	res->desc = devm_kcalloc(dev, res->sets, sizeof(*res->desc),
 				 GFP_KERNEL);
 	if (!res->desc)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < res->sets; i++) {
-		ret = of_property_read_u32_index(dev_of_node(dev), of_prop, i,
-						 &resource_subtype);
-		if (ret)
-			return ERR_PTR(-EINVAL);
-
 		ret = handle->ops.rm_core_ops.get_range(handle, dev_id,
-							resource_subtype,
+							sub_types[i],
 							&res->desc[i].start,
 							&res->desc[i].num);
 		if (ret) {
 			dev_dbg(dev, "dev = %d subtype %d not allocated for this host\n",
-				dev_id, resource_subtype);
+				dev_id, sub_types[i]);
 			res->desc[i].start = 0;
 			res->desc[i].num = 0;
 			continue;
 		}
 
 		dev_dbg(dev, "dev = %d, subtype = %d, start = %d, num = %d\n",
-			dev_id, resource_subtype, res->desc[i].start,
+			dev_id, sub_types[i], res->desc[i].start,
 			res->desc[i].num);
 
 		valid_set = true;
@@ -3332,6 +3269,62 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle,
 	return ERR_PTR(-EINVAL);
 }
 
+/**
+ * devm_ti_sci_get_of_resource() - Get a TISCI resource assigned to a device
+ * @handle:	TISCI handle
+ * @dev:	Device pointer to which the resource is assigned
+ * @dev_id:	TISCI device id to which the resource is assigned
+ * @of_prop:	property name by which the resource are represented
+ *
+ * Return: Pointer to ti_sci_resource if all went well else appropriate
+ *	   error pointer.
+ */
+struct ti_sci_resource *
+devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle,
+			    struct device *dev, u32 dev_id, char *of_prop)
+{
+	struct ti_sci_resource *res;
+	u32 *sub_types;
+	int sets;
+
+	sets = of_property_count_elems_of_size(dev_of_node(dev), of_prop,
+					       sizeof(u32));
+	if (sets < 0) {
+		dev_err(dev, "%s resource type ids not available\n", of_prop);
+		return ERR_PTR(sets);
+	}
+
+	sub_types = kcalloc(sets, sizeof(*sub_types), GFP_KERNEL);
+	if (!sub_types)
+		return ERR_PTR(-ENOMEM);
+
+	of_property_read_u32_array(dev_of_node(dev), of_prop, sub_types, sets);
+	res = devm_ti_sci_get_resource_sets(handle, dev, dev_id, sub_types,
+					    sets);
+
+	kfree(sub_types);
+	return res;
+}
+EXPORT_SYMBOL_GPL(devm_ti_sci_get_of_resource);
+
+/**
+ * devm_ti_sci_get_resource() - Get a resource range assigned to the device
+ * @handle:	TISCI handle
+ * @dev:	Device pointer to which the resource is assigned
+ * @dev_id:	TISCI device id to which the resource is assigned
+ * @suub_type:	TISCI resource subytpe representing the resource.
+ *
+ * Return: Pointer to ti_sci_resource if all went well else appropriate
+ *	   error pointer.
+ */
+struct ti_sci_resource *
+devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev,
+			 u32 dev_id, u32 sub_type)
+{
+	return devm_ti_sci_get_resource_sets(handle, dev, dev_id, &sub_type, 1);
+}
+EXPORT_SYMBOL_GPL(devm_ti_sci_get_resource);
+
 static int tisci_reboot_handler(struct notifier_block *nb, unsigned long mode,
 				void *cmd)
 {
@@ -3352,17 +3345,6 @@ static const struct ti_sci_desc ti_sci_pmmc_k2g_desc = {
 	/* Limited by MBOX_TX_QUEUE_LEN. K2G can handle upto 128 messages! */
 	.max_msgs = 20,
 	.max_msg_size = 64,
-	.rm_type_map = NULL,
-};
-
-static struct ti_sci_rm_type_map ti_sci_am654_rm_type_map[] = {
-	{.dev_id = 56, .type = 0x00b}, /* GIC_IRQ */
-	{.dev_id = 179, .type = 0x000}, /* MAIN_NAV_UDMASS_IA0 */
-	{.dev_id = 187, .type = 0x009}, /* MAIN_NAV_RA */
-	{.dev_id = 188, .type = 0x006}, /* MAIN_NAV_UDMAP */
-	{.dev_id = 194, .type = 0x007}, /* MCU_NAV_UDMAP */
-	{.dev_id = 195, .type = 0x00a}, /* MCU_NAV_RA */
-	{.dev_id = 0, .type = 0x000}, /* end of table */
 };
 
 /* Description for AM654 */
@@ -3373,7 +3355,6 @@ static const struct ti_sci_desc ti_sci_pmmc_am654_desc = {
 	/* Limited by MBOX_TX_QUEUE_LEN. K2G can handle upto 128 messages! */
 	.max_msgs = 20,
 	.max_msg_size = 60,
-	.rm_type_map = ti_sci_am654_rm_type_map,
 };
 
 static const struct of_device_id ti_sci_of_match[] = {
diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c
index d16645c1d8d9..3aa45934d60c 100644
--- a/drivers/gpio/gpio-aspeed-sgpio.c
+++ b/drivers/gpio/gpio-aspeed-sgpio.c
@@ -303,16 +303,16 @@ static int aspeed_sgpio_set_type(struct irq_data *d, unsigned int type)
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_BOTH:
 		type2 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_EDGE_RISING:
 		type0 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_EDGE_FALLING:
 		handler = handle_edge_irq;
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
 		type0 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_LEVEL_LOW:
 		type1 |= bit;
 		handler = handle_level_irq;
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 879db23d8454..bf08b4561f36 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -611,16 +611,16 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_BOTH:
 		type2 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_EDGE_RISING:
 		type0 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_EDGE_FALLING:
 		handler = handle_edge_irq;
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
 		type0 |= bit;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_LEVEL_LOW:
 		type1 |= bit;
 		handler = handle_level_irq;
diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 53fae02c40ad..d5359341cc6b 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -129,7 +129,7 @@ static int ath79_gpio_irq_set_type(struct irq_data *data,
 
 	case IRQ_TYPE_LEVEL_HIGH:
 		polarity |= mask;
-		/* fall through */
+		fallthrough;
 	case IRQ_TYPE_LEVEL_LOW:
 		type |= mask;
 		break;
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index 8c9757774010..ad61daf6c212 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -617,14 +617,12 @@ static int sprd_eic_probe(struct platform_device *pdev)
 		sprd_eic->chip.free = sprd_eic_free;
 		sprd_eic->chip.set_config = sprd_eic_set_config;
 		sprd_eic->chip.set = sprd_eic_set;
-		/* fall-through */
+		fallthrough;
 	case SPRD_EIC_ASYNC:
-		/* fall-through */
 	case SPRD_EIC_SYNC:
 		sprd_eic->chip.get = sprd_eic_get;
 		break;
 	case SPRD_EIC_LATCH:
-		/* fall-through */
 	default:
 		break;
 	}
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 6c48809d0505..b0155d6007c8 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -308,7 +308,7 @@ static void stmpe_dbg_show_one(struct seq_file *s,
 			if (ret < 0)
 				return;
 			edge_det = !!(ret & mask);
-			/* fall through */
+			fallthrough;
 		case STMPE1801:
 			rise_reg = stmpe->regs[STMPE_IDX_GPRER_LSB + bank];
 			fall_reg = stmpe->regs[STMPE_IDX_GPFER_LSB + bank];
@@ -321,7 +321,7 @@ static void stmpe_dbg_show_one(struct seq_file *s,
 			if (ret < 0)
 				return;
 			fall = !!(ret & mask);
-			/* fall through */
+			fallthrough;
 		case STMPE801:
 		case STMPE1600:
 			irqen_reg = stmpe->regs[STMPE_IDX_IEGPIOR_LSB + bank];
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9276051663da..54ca3c18b291 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1264,7 +1264,7 @@ static int acpi_gpio_package_count(const union acpi_object *obj)
 		switch (element->type) {
 		case ACPI_TYPE_LOCAL_REFERENCE:
 			element += 3;
-			/* Fallthrough */
+			fallthrough;
 		case ACPI_TYPE_INTEGER:
 			element++;
 			count++;
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 403ec3db29df..39976c7b100c 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -30,7 +30,7 @@ FULL_AMD_DISPLAY_PATH = $(FULL_AMD_PATH)/$(DISPLAY_FOLDER_NAME)
 ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \
 	-I$(FULL_AMD_PATH)/include \
 	-I$(FULL_AMD_PATH)/amdgpu \
-	-I$(FULL_AMD_PATH)/powerplay/inc \
+	-I$(FULL_AMD_PATH)/pm/inc \
 	-I$(FULL_AMD_PATH)/acp/include \
 	-I$(FULL_AMD_DISPLAY_PATH) \
 	-I$(FULL_AMD_DISPLAY_PATH)/include \
@@ -47,7 +47,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_encoders.o amdgpu_display.o amdgpu_i2c.o \
 	amdgpu_fb.o amdgpu_gem.o amdgpu_ring.o \
 	amdgpu_cs.o amdgpu_bios.o amdgpu_benchmark.o amdgpu_test.o \
-	amdgpu_pm.o atombios_dp.o amdgpu_afmt.o amdgpu_trace_points.o \
+	atombios_dp.o amdgpu_afmt.o amdgpu_trace_points.o \
 	atombios_encoders.o amdgpu_sa.o atombios_i2c.o \
 	amdgpu_dma_buf.o amdgpu_vm.o amdgpu_ib.o amdgpu_pll.o \
 	amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
@@ -55,15 +55,15 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
 	amdgpu_gmc.o amdgpu_mmhub.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
 	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \
-	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o
+	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o
 
 amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
 
 # add asic specific block
-amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
+amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o \
 	dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o
 
-amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o si_dpm.o si_smc.o \
+amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o \
 	uvd_v3_1.o
 
 amdgpu-y += \
@@ -85,7 +85,7 @@ amdgpu-y += \
 
 # add UMC block
 amdgpu-y += \
-	umc_v6_1.o umc_v6_0.o
+	umc_v6_1.o umc_v6_0.o umc_v8_7.o
 
 # add IH block
 amdgpu-y += \
@@ -105,10 +105,6 @@ amdgpu-y += \
 	psp_v11_0.o \
 	psp_v12_0.o
 
-# add SMC block
-amdgpu-y += \
-	amdgpu_dpm.o
-
 # add DCE block
 amdgpu-y += \
 	dce_v10_0.o \
@@ -212,7 +208,7 @@ amdgpu-$(CONFIG_VGA_SWITCHEROO) += amdgpu_atpx_handler.o
 amdgpu-$(CONFIG_ACPI) += amdgpu_acpi.o
 amdgpu-$(CONFIG_HMM_MIRROR) += amdgpu_mn.o
 
-include $(FULL_AMD_PATH)/powerplay/Makefile
+include $(FULL_AMD_PATH)/pm/Makefile
 
 amdgpu-y += $(AMD_POWERPLAY_FILES)
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 327a0daf4a1d..4009d2e30727 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -178,6 +178,7 @@ extern uint amdgpu_dm_abm_level;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
+extern int amdgpu_bad_page_threshold;
 extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
@@ -187,9 +188,11 @@ extern int amdgpu_force_asic_type;
 #ifdef CONFIG_HSA_AMD
 extern int sched_policy;
 extern bool debug_evictions;
+extern bool no_system_mem_limit;
 #else
 static const int sched_policy = KFD_SCHED_POLICY_HWS;
 static const bool debug_evictions; /* = false */
+static const bool no_system_mem_limit;
 #endif
 
 extern int amdgpu_tmz;
@@ -201,6 +204,7 @@ extern int amdgpu_si_support;
 #ifdef CONFIG_DRM_AMDGPU_CIK
 extern int amdgpu_cik_support;
 #endif
+extern int amdgpu_num_kcq;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
@@ -212,6 +216,8 @@ extern int amdgpu_cik_support;
 #define AMDGPUFB_CONN_LIMIT			4
 #define AMDGPU_BIOS_NUM_SCRATCH			16
 
+#define AMDGPU_VBIOS_VGA_ALLOCATION		(9 * 1024 * 1024) /* reserve 8MB for vga emulator and 1 MB for FB */
+
 /* hard reset data */
 #define AMDGPU_ASIC_RESET_DATA                  0x39d5e86b
 
@@ -245,6 +251,7 @@ struct amdgpu_fpriv;
 struct amdgpu_bo_va_mapping;
 struct amdgpu_atif;
 struct kfd_vm_fault_info;
+struct amdgpu_hive_info;
 
 enum amdgpu_cp_irq {
 	AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP = 0,
@@ -611,6 +618,8 @@ struct amdgpu_asic_funcs {
 	uint64_t (*get_pcie_replay_count)(struct amdgpu_device *adev);
 	/* device supports BACO */
 	bool (*supports_baco)(struct amdgpu_device *adev);
+	/* pre asic_init quirks */
+	void (*pre_asic_init)(struct amdgpu_device *adev);
 };
 
 /*
@@ -648,16 +657,6 @@ struct amdgpu_atcs {
 };
 
 /*
- * Firmware VRAM reservation
- */
-struct amdgpu_fw_vram_usage {
-	u64 start_offset;
-	u64 size;
-	struct amdgpu_bo *reserved_bo;
-	void *va;
-};
-
-/*
  * CGS
  */
 struct cgs_device *amdgpu_cgs_create_device(struct amdgpu_device *adev);
@@ -725,13 +724,13 @@ struct amd_powerplay {
 #define AMDGPU_MAX_DF_PERFMONS 4
 struct amdgpu_device {
 	struct device			*dev;
-	struct drm_device		*ddev;
 	struct pci_dev			*pdev;
+	struct drm_device		ddev;
 
 #ifdef CONFIG_DRM_AMD_ACP
 	struct amdgpu_acp		acp;
 #endif
-
+	struct amdgpu_hive_info *hive;
 	/* ASIC */
 	enum amd_asic_type		asic_type;
 	uint32_t			family;
@@ -765,7 +764,6 @@ struct amdgpu_device {
 	bool				is_atom_fw;
 	uint8_t				*bios;
 	uint32_t			bios_size;
-	struct amdgpu_bo		*stolen_vga_memory;
 	uint32_t			bios_scratch_reg_offset;
 	uint32_t			bios_scratch[AMDGPU_BIOS_NUM_SCRATCH];
 
@@ -917,11 +915,6 @@ struct amdgpu_device {
 	/* display related functionality */
 	struct amdgpu_display_manager dm;
 
-	/* discovery */
-	uint8_t				*discovery_bin;
-	uint32_t			discovery_tmr_size;
-	struct amdgpu_bo		*discovery_memory;
-
 	/* mes */
 	bool                            enable_mes;
 	struct amdgpu_mes               mes;
@@ -946,8 +939,6 @@ struct amdgpu_device {
 	struct delayed_work     delayed_init_work;
 
 	struct amdgpu_virt	virt;
-	/* firmware VRAM reservation */
-	struct amdgpu_fw_vram_usage fw_vram_usage;
 
 	/* link all shadow bo */
 	struct list_head                shadow_list;
@@ -961,9 +952,9 @@ struct amdgpu_device {
 	bool                            in_suspend;
 	bool				in_hibernate;
 
-	bool                            in_gpu_reset;
+	atomic_t 			in_gpu_reset;
 	enum pp_mp1_state               mp1_state;
-	struct mutex  lock_reset;
+	struct rw_semaphore reset_sem;
 	struct amdgpu_doorbell_index doorbell_index;
 
 	struct mutex			notifier_lock;
@@ -995,16 +986,25 @@ struct amdgpu_device {
 
 	atomic_t			throttling_logging_enabled;
 	struct ratelimit_state		throttling_logging_rs;
+	uint32_t			ras_features;
 };
 
+static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
+{
+	return container_of(ddev, struct amdgpu_device, ddev);
+}
+
+static inline struct drm_device *adev_to_drm(struct amdgpu_device *adev)
+{
+	return &adev->ddev;
+}
+
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
 {
 	return container_of(bdev, struct amdgpu_device, mman.bdev);
 }
 
 int amdgpu_device_init(struct amdgpu_device *adev,
-		       struct drm_device *ddev,
-		       struct pci_dev *pdev,
 		       uint32_t flags);
 void amdgpu_device_fini(struct amdgpu_device *adev);
 int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
@@ -1141,10 +1141,12 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_need_reset_on_init(adev) (adev)->asic_funcs->need_reset_on_init((adev))
 #define amdgpu_asic_get_pcie_replay_count(adev) ((adev)->asic_funcs->get_pcie_replay_count((adev)))
 #define amdgpu_asic_supports_baco(adev) (adev)->asic_funcs->supports_baco((adev))
+#define amdgpu_asic_pre_asic_init(adev) (adev)->asic_funcs->pre_asic_init((adev))
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
 /* Common functions */
+bool amdgpu_device_has_job_running(struct amdgpu_device *adev);
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			      struct amdgpu_job* job);
@@ -1194,7 +1196,7 @@ static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
 extern const struct drm_ioctl_desc amdgpu_ioctls_kms[];
 extern const int amdgpu_max_kms_ioctl;
 
-int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags);
+int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags);
 void amdgpu_driver_unload_kms(struct drm_device *dev);
 void amdgpu_driver_lastclose_kms(struct drm_device *dev);
 int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
@@ -1278,4 +1280,8 @@ static inline bool amdgpu_is_tmz(struct amdgpu_device *adev)
        return adev->gmc.tmz_enabled;
 }
 
+static inline int amdgpu_in_reset(struct amdgpu_device *adev)
+{
+	return atomic_read(&adev->in_gpu_reset);
+}
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 12247a32f9ef..d3e51d361179 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -136,9 +136,7 @@ static int acp_poweroff(struct generic_pm_domain *genpd)
 	 * 2. power off the acp tiles
 	 * 3. check and enter ulv state
 	 */
-		if (adev->powerplay.pp_funcs &&
-			adev->powerplay.pp_funcs->set_powergating_by_smu)
-			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, true);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, true);
 	}
 	return 0;
 }
@@ -157,8 +155,7 @@ static int acp_poweron(struct generic_pm_domain *genpd)
 	 * 2. turn on acp clock
 	 * 3. power on acp tiles
 	 */
-		if (adev->powerplay.pp_funcs->set_powergating_by_smu)
-			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, false);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, false);
 	}
 	return 0;
 }
@@ -529,9 +526,7 @@ static int acp_set_powergating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_PG_STATE_GATE);
 
-	if (adev->powerplay.pp_funcs &&
-		adev->powerplay.pp_funcs->set_powergating_by_smu)
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, enable);
+	amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, enable);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 913c8f0513bd..4a93b880c6bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -463,11 +463,11 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 
 		if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
 			if (adev->flags & AMD_IS_PX) {
-				pm_runtime_get_sync(adev->ddev->dev);
+				pm_runtime_get_sync(adev_to_drm(adev)->dev);
 				/* Just fire off a uevent and let userspace tell us what to do */
-				drm_helper_hpd_irq_event(adev->ddev);
-				pm_runtime_mark_last_busy(adev->ddev->dev);
-				pm_runtime_put_autosuspend(adev->ddev->dev);
+				drm_helper_hpd_irq_event(adev_to_drm(adev));
+				pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+				pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			}
 		}
 		/* TODO: check other events */
@@ -817,7 +817,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 			struct drm_encoder *tmp;
 
 			/* Find the encoder controlling the brightness */
-			list_for_each_entry(tmp, &adev->ddev->mode_config.encoder_list,
+			list_for_each_entry(tmp, &adev_to_drm(adev)->mode_config.encoder_list,
 					    head) {
 				struct amdgpu_encoder *enc = to_amdgpu_encoder(tmp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 478f67498a17..edff1b7f282a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -119,7 +119,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.gpuvm_size = min(adev->vm_manager.max_pfn
 					  << AMDGPU_GPU_PAGE_SHIFT,
 					  AMDGPU_GMC_HOLE_START),
-			.drm_render_minor = adev->ddev->render->index,
+			.drm_render_minor = adev_to_drm(adev)->render->index,
 			.sdma_doorbell_idx = adev->doorbell_index.sdma_engine,
 
 		};
@@ -160,7 +160,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 					adev->doorbell_index.last_non_cp;
 		}
 
-		kgd2kfd_device_init(adev->kfd.dev, adev->ddev, &gpu_resources);
+		kgd2kfd_device_init(adev->kfd.dev, adev_to_drm(adev), &gpu_resources);
 	}
 }
 
@@ -479,11 +479,11 @@ int amdgpu_amdkfd_get_dmabuf_info(struct kgd_dev *kgd, int dma_buf_fd,
 		goto out_put;
 
 	obj = dma_buf->priv;
-	if (obj->dev->driver != adev->ddev->driver)
+	if (obj->dev->driver != adev_to_drm(adev)->driver)
 		/* Can't handle buffers from different drivers */
 		goto out_put;
 
-	adev = obj->dev->dev_private;
+	adev = drm_to_adev(obj->dev);
 	bo = gem_to_amdgpu_bo(obj);
 	if (!(bo->preferred_domains & (AMDGPU_GEM_DOMAIN_VRAM |
 				    AMDGPU_GEM_DOMAIN_GTT)))
@@ -613,6 +613,7 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 	job->vmid = vmid;
 
 	ret = amdgpu_ib_schedule(ring, 1, ib, job, &f);
+
 	if (ret) {
 		DRM_ERROR("amdgpu: failed to schedule IB.\n");
 		goto err_ib_sched;
@@ -756,4 +757,8 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 {
 }
+
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+{
+}
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ffe149aafc39..a10507ecb750 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -270,5 +270,6 @@ int kgd2kfd_resume_mm(struct mm_struct *mm);
 int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 					       struct dma_fence *fence);
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask);
 
 #endif /* AMDGPU_AMDKFD_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 35d4a5ab0228..1afa8f122e7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -283,22 +283,6 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	return 0;
 }
 
-static void kgd_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_t page_table_base)
-{
-	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("trying to set page table base for wrong VMID %u\n",
-		       vmid);
-		return;
-	}
-
-	mmhub_v9_4_setup_vm_pt_regs(adev, vmid, page_table_base);
-
-	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
-}
-
 const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
@@ -317,7 +301,7 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.wave_control_execute = kgd_gfx_v9_wave_control_execute,
 	.address_watch_get_offset = kgd_gfx_v9_address_watch_get_offset,
 	.get_atc_vmid_pasid_mapping_info =
-			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
-	.set_vm_context_page_table_base = kgd_set_vm_context_page_table_base,
-	.get_hive_id = amdgpu_amdkfd_get_hive_id,
+				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
+	.set_vm_context_page_table_base =
+				kgd_gfx_v9_set_vm_context_page_table_base,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index bf927f432506..df0aab0fc67e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -542,7 +542,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v10_compute_mqd *m = get_mqd(mqd);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 #if 0
@@ -776,6 +776,4 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.get_hive_id = amdgpu_amdkfd_get_hive_id,
-	.get_unique_id = amdgpu_amdkfd_get_unique_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
index 7e59e473a190..5b38f848b772 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
@@ -152,7 +152,7 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 		dev_warn(adev->dev,
 			 "Invalid sdma engine id (%d), using engine id 0\n",
 			 engine_id);
-		/* fall through */
+		fallthrough;
 	case 0:
 		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0,
 				mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
@@ -822,7 +822,6 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = {
 	.address_watch_get_offset = address_watch_get_offset_v10_3,
 	.get_atc_vmid_pasid_mapping_info = NULL,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base_v10_3,
-	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 #if 0
 	.enable_debug_trap = enable_debug_trap_v10_3,
 	.disable_debug_trap = disable_debug_trap_v10_3,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 744366c7ee85..275f20399373 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -423,7 +423,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	unsigned long flags, end_jiffies;
 	int retry;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	acquire_queue(kgd, pipe_id, queue_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index feab4cc6e836..4997189d8b36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -419,7 +419,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	int retry;
 	struct vi_mqd *m = get_mqd(mqd);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	acquire_queue(kgd, pipe_id, queue_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index c7fd0c47b254..e6aede725197 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -195,19 +195,32 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t sdma_engine_reg_base[2] = {
-		SOC15_REG_OFFSET(SDMA0, 0,
-				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA1, 0,
-				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL
-	};
-	uint32_t retval = sdma_engine_reg_base[engine_id]
+	uint32_t sdma_engine_reg_base = 0;
+	uint32_t sdma_rlc_reg_offset;
+
+	switch (engine_id) {
+	default:
+		dev_warn(adev->dev,
+			 "Invalid sdma engine id (%d), using engine id 0\n",
+			 engine_id);
+		fallthrough;
+	case 0:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0,
+				mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	case 1:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0,
+				mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	}
+
+	sdma_rlc_reg_offset = sdma_engine_reg_base
 		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
 	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
-			queue_id, retval);
+		 queue_id, sdma_rlc_reg_offset);
 
-	return retval;
+	return sdma_rlc_reg_offset;
 }
 
 static inline struct v9_mqd *get_mqd(void *mqd)
@@ -539,7 +552,7 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	acquire_queue(kgd, pipe_id, queue_id);
@@ -677,7 +690,7 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 	return 0;
 }
 
-static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
+void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
@@ -688,7 +701,7 @@ static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 		return;
 	}
 
-	mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	adev->mmhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 
 	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 }
@@ -713,6 +726,4 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.get_hive_id = amdgpu_amdkfd_get_hive_id,
-	.get_unique_id = amdgpu_amdkfd_get_unique_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index aedf67d57449..f098e88d3a0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -60,3 +60,6 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 
 bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 					uint8_t vmid, uint16_t *p_pasid);
+
+void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t page_table_base);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index aa2b328c6202..b6b821500d30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -148,8 +148,12 @@ static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 
+	if (kfd_mem_limit.system_mem_used + system_mem_needed >
+	    kfd_mem_limit.max_system_mem_limit)
+		pr_debug("Set no_system_mem_limit=1 if using shared memory\n");
+
 	if ((kfd_mem_limit.system_mem_used + system_mem_needed >
-	     kfd_mem_limit.max_system_mem_limit) ||
+	     kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) ||
 	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
 	     kfd_mem_limit.max_ttm_mem_limit) ||
 	    (adev->kfd.vram_used + vram_needed >
@@ -1668,7 +1672,7 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 		return -EINVAL;
 
 	obj = dma_buf->priv;
-	if (obj->dev->dev_private != adev)
+	if (drm_to_adev(obj->dev) != adev)
 		/* Can't handle buffers from other devices */
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 29f767e026e4..469352e2d6ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -148,7 +148,7 @@ void amdgpu_atombios_i2c_init(struct amdgpu_device *adev)
 
 			if (i2c.valid) {
 				sprintf(stmp, "0x%x", i2c.i2c_id);
-				adev->i2c_bus[i] = amdgpu_i2c_create(adev->ddev, &i2c, stmp);
+				adev->i2c_bus[i] = amdgpu_i2c_create(adev_to_drm(adev), &i2c, stmp);
 			}
 			gpio = (ATOM_GPIO_I2C_ASSIGMENT *)
 				((u8 *)gpio + sizeof(ATOM_GPIO_I2C_ASSIGMENT));
@@ -541,7 +541,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 		}
 	}
 
-	amdgpu_link_encoder_connector(adev->ddev);
+	amdgpu_link_encoder_connector(adev_to_drm(adev));
 
 	return true;
 }
@@ -1786,9 +1786,9 @@ static int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
 			(uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION <<
 			ATOM_VRAM_OPERATION_FLAGS_SHIFT)) {
 			/* Firmware request VRAM reservation for SR-IOV */
-			adev->fw_vram_usage.start_offset = (start_addr &
+			adev->mman.fw_vram_usage_start_offset = (start_addr &
 				(~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10;
-			adev->fw_vram_usage.size = size << 10;
+			adev->mman.fw_vram_usage_size = size << 10;
 			/* Use the default scratch size */
 			usage_bytes = 0;
 		} else {
@@ -1882,7 +1882,7 @@ static void cail_mc_write(struct card_info *info, uint32_t reg, uint32_t val)
  */
 static void cail_reg_write(struct card_info *info, uint32_t reg, uint32_t val)
 {
-	struct amdgpu_device *adev = info->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(info->dev);
 
 	WREG32(reg, val);
 }
@@ -1898,7 +1898,7 @@ static void cail_reg_write(struct card_info *info, uint32_t reg, uint32_t val)
  */
 static uint32_t cail_reg_read(struct card_info *info, uint32_t reg)
 {
-	struct amdgpu_device *adev = info->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(info->dev);
 	uint32_t r;
 
 	r = RREG32(reg);
@@ -1916,7 +1916,7 @@ static uint32_t cail_reg_read(struct card_info *info, uint32_t reg)
  */
 static void cail_ioreg_write(struct card_info *info, uint32_t reg, uint32_t val)
 {
-	struct amdgpu_device *adev = info->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(info->dev);
 
 	WREG32_IO(reg, val);
 }
@@ -1932,7 +1932,7 @@ static void cail_ioreg_write(struct card_info *info, uint32_t reg, uint32_t val)
  */
 static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg)
 {
-	struct amdgpu_device *adev = info->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(info->dev);
 	uint32_t r;
 
 	r = RREG32_IO(reg);
@@ -1944,7 +1944,7 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev,
 						 char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct atom_context *ctx = adev->mode_info.atom_context;
 
 	return snprintf(buf, PAGE_SIZE, "%s\n", ctx->vbios_version);
@@ -1995,7 +1995,7 @@ int amdgpu_atombios_init(struct amdgpu_device *adev)
 		return -ENOMEM;
 
 	adev->mode_info.atom_card_info = atom_card_info;
-	atom_card_info->dev = adev->ddev;
+	atom_card_info->dev = adev_to_drm(adev);
 	atom_card_info->reg_read = cail_reg_read;
 	atom_card_info->reg_write = cail_reg_write;
 	/* needed for iio ops */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 1279053324f9..17c010d0431f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -89,9 +89,9 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
 			(uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION <<
 			ATOM_VRAM_OPERATION_FLAGS_SHIFT)) {
 			/* Firmware request VRAM reservation for SR-IOV */
-			adev->fw_vram_usage.start_offset = (start_addr &
+			adev->mman.fw_vram_usage_start_offset = (start_addr &
 				(~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10;
-			adev->fw_vram_usage.size = size << 10;
+			adev->mman.fw_vram_usage_size = size << 10;
 			/* Use the default scratch size */
 			usage_bytes = 0;
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index b1172d93c99c..6333cada1e09 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -417,26 +417,40 @@ static inline bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
 
 bool amdgpu_get_bios(struct amdgpu_device *adev)
 {
-	if (amdgpu_atrm_get_bios(adev))
+	if (amdgpu_atrm_get_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from ATRM\n");
 		goto success;
+	}
 
-	if (amdgpu_acpi_vfct_bios(adev))
+	if (amdgpu_acpi_vfct_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from VFCT\n");
 		goto success;
+	}
 
-	if (igp_read_bios_from_vram(adev))
+	if (igp_read_bios_from_vram(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n");
 		goto success;
+	}
 
-	if (amdgpu_read_bios(adev))
+	if (amdgpu_read_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
 		goto success;
+	}
 
-	if (amdgpu_read_bios_from_rom(adev))
+	if (amdgpu_read_bios_from_rom(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from ROM\n");
 		goto success;
+	}
 
-	if (amdgpu_read_disabled_bios(adev))
+	if (amdgpu_read_disabled_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from disabled ROM BAR\n");
 		goto success;
+	}
 
-	if (amdgpu_read_platform_bios(adev))
+	if (amdgpu_read_platform_bios(adev)) {
+		dev_info(adev->dev, "Fetched VBIOS from platform\n");
 		goto success;
+	}
 
 	DRM_ERROR("Unable to locate a BIOS ROM\n");
 	return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 4053597b3af2..15c45b2a3983 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -265,7 +265,7 @@ error_free:
 int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	union drm_amdgpu_bo_list *args = data;
 	uint32_t handle = args->in.list_handle;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 93160a849af4..65d1b23d7e74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -42,7 +42,7 @@
 void amdgpu_connector_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 	/* bail if the connector does not have hpd pin, e.g.,
@@ -280,7 +280,7 @@ amdgpu_connector_get_hardcoded_edid(struct amdgpu_device *adev)
 static void amdgpu_connector_get_edid(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 	if (amdgpu_connector->edid)
@@ -464,7 +464,7 @@ static int amdgpu_connector_set_property(struct drm_connector *connector,
 					  uint64_t val)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
@@ -835,7 +835,7 @@ static enum drm_mode_status amdgpu_connector_vga_mode_valid(struct drm_connector
 					    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* XXX check mode bandwidth */
 
@@ -942,7 +942,7 @@ static bool
 amdgpu_connector_check_hpd_status_unchanged(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	enum drm_connector_status status;
 
@@ -973,7 +973,7 @@ static enum drm_connector_status
 amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	const struct drm_encoder_helper_funcs *encoder_funcs;
 	int r;
@@ -1160,7 +1160,7 @@ static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector
 					    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 	/* XXX check mode bandwidth */
@@ -1312,7 +1312,7 @@ static bool amdgpu_connector_encoder_is_hbr2(struct drm_connector *connector)
 bool amdgpu_connector_is_dp12_capable(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if ((adev->clock.default_dispclk >= 53900) &&
 	    amdgpu_connector_encoder_is_hbr2(connector)) {
@@ -1326,7 +1326,7 @@ static enum drm_connector_status
 amdgpu_connector_dp_detect(struct drm_connector *connector, bool force)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
 	struct amdgpu_connector_atom_dig *amdgpu_dig_connector = amdgpu_connector->con_priv;
@@ -1526,7 +1526,7 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 		      struct amdgpu_hpd *hpd,
 		      struct amdgpu_router *router)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index ecd051976bce..12598a4b5c78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1275,13 +1275,24 @@ error_unlock:
 	return r;
 }
 
+static void trace_amdgpu_cs_ibs(struct amdgpu_cs_parser *parser)
+{
+	int i;
+
+	if (!trace_amdgpu_cs_enabled())
+		return;
+
+	for (i = 0; i < parser->job->num_ibs; i++)
+		trace_amdgpu_cs(parser, i);
+}
+
 int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	union drm_amdgpu_cs *cs = data;
 	struct amdgpu_cs_parser parser = {};
 	bool reserved_buffers = false;
-	int i, r;
+	int r;
 
 	if (amdgpu_ras_intr_triggered())
 		return -EHWPOISON;
@@ -1294,7 +1305,8 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
-		DRM_ERROR("Failed to initialize parser %d!\n", r);
+		if (printk_ratelimit())
+			DRM_ERROR("Failed to initialize parser %d!\n", r);
 		goto out;
 	}
 
@@ -1319,8 +1331,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	reserved_buffers = true;
 
-	for (i = 0; i < parser.job->num_ibs; i++)
-		trace_amdgpu_cs(&parser, i);
+	trace_amdgpu_cs_ibs(&parser);
 
 	r = amdgpu_cs_vm_handling(&parser);
 	if (r)
@@ -1421,7 +1432,7 @@ static struct dma_fence *amdgpu_cs_get_fence(struct amdgpu_device *adev,
 int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	union drm_amdgpu_fence_to_handle *info = data;
 	struct dma_fence *fence;
 	struct drm_syncobj *syncobj;
@@ -1597,7 +1608,7 @@ err_free_fence_array:
 int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	union drm_amdgpu_wait_fences *wait = data;
 	uint32_t fence_count = wait->in.fence_count;
 	struct drm_amdgpu_fence *fences_user;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 8842c55d4490..c80d8339f58c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -46,7 +46,7 @@ const unsigned int amdgpu_ctx_num_entities[AMDGPU_HW_IP_NUM] = {
 static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 				      enum drm_sched_priority priority)
 {
-	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
+	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_COUNT)
 		return -EINVAL;
 
 	/* NORMAL and below are accessible by everyone */
@@ -65,7 +65,7 @@ static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 static enum gfx_pipe_priority amdgpu_ctx_sched_prio_to_compute_prio(enum drm_sched_priority prio)
 {
 	switch (prio) {
-	case DRM_SCHED_PRIORITY_HIGH_HW:
+	case DRM_SCHED_PRIORITY_HIGH:
 	case DRM_SCHED_PRIORITY_KERNEL:
 		return AMDGPU_GFX_PIPE_PRIO_HIGH;
 	default:
@@ -114,7 +114,11 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 	scheds = adev->gpu_sched[hw_ip][hw_prio].sched;
 	num_scheds = adev->gpu_sched[hw_ip][hw_prio].num_scheds;
 
-	if (hw_ip == AMDGPU_HW_IP_VCN_ENC || hw_ip == AMDGPU_HW_IP_VCN_DEC) {
+	/* disable load balance if the hw engine retains context among dependent jobs */
+	if (hw_ip == AMDGPU_HW_IP_VCN_ENC ||
+	    hw_ip == AMDGPU_HW_IP_VCN_DEC ||
+	    hw_ip == AMDGPU_HW_IP_UVD_ENC ||
+	    hw_ip == AMDGPU_HW_IP_UVD) {
 		sched = drm_sched_pick_best(scheds, num_scheds);
 		scheds = &sched;
 		num_scheds = 1;
@@ -385,16 +389,15 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 	enum drm_sched_priority priority;
 
 	union drm_amdgpu_ctx *args = data;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 
-	r = 0;
 	id = args->in.ctx_id;
-	priority = amdgpu_to_sched_priority(args->in.priority);
+	r = amdgpu_to_sched_priority(args->in.priority, &priority);
 
 	/* For backwards compatibility reasons, we need to accept
 	 * ioctls with garbage in the priority field */
-	if (priority == DRM_SCHED_PRIORITY_INVALID)
+	if (r == -EINVAL)
 		priority = DRM_SCHED_PRIORITY_NORMAL;
 
 	switch (args->in.op) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 193ffdb957b6..abe0c2729e1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -34,6 +34,7 @@
 #include "amdgpu_pm.h"
 #include "amdgpu_dm_debugfs.h"
 #include "amdgpu_ras.h"
+#include "amdgpu_rap.h"
 
 /**
  * amdgpu_debugfs_add_files - Add simple debugfs entries
@@ -68,8 +69,8 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
 	adev->debugfs_count = i;
 #if defined(CONFIG_DEBUG_FS)
 	drm_debugfs_create_files(files, nfiles,
-				 adev->ddev->primary->debugfs_root,
-				 adev->ddev->primary);
+				 adev_to_drm(adev)->primary->debugfs_root,
+				 adev_to_drm(adev)->primary);
 #endif
 	return 0;
 }
@@ -100,14 +101,18 @@ static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
 
 	file->private_data = adev;
 
-	mutex_lock(&adev->lock_reset);
+	ret = down_read_killable(&adev->reset_sem);
+	if (ret)
+		return ret;
+
 	if (adev->autodump.dumping.done) {
 		reinit_completion(&adev->autodump.dumping);
 		ret = 0;
 	} else {
 		ret = -EBUSY;
 	}
-	mutex_unlock(&adev->lock_reset);
+
+	up_read(&adev->reset_sem);
 
 	return ret;
 }
@@ -126,7 +131,7 @@ static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_
 
 	poll_wait(file, &adev->autodump.gpu_hang, poll_table);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return POLLIN | POLLRDNORM | POLLWRNORM;
 
 	return 0;
@@ -146,7 +151,7 @@ static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
 	init_waitqueue_head(&adev->autodump.gpu_hang);
 
 	debugfs_create_file("amdgpu_autodump", 0600,
-		adev->ddev->primary->debugfs_root,
+		adev_to_drm(adev)->primary->debugfs_root,
 		adev, &autodump_debug_fops);
 }
 
@@ -222,23 +227,23 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 
 	*pos &= (1UL << 22) - 1;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
 		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines)) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return -EINVAL;
 		}
@@ -287,8 +292,8 @@ end:
 	if (pm_pg_lock)
 		mutex_unlock(&adev->pm.mutex);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -335,15 +340,15 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -353,8 +358,8 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 		value = RREG32_PCIE(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -365,8 +370,8 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -394,15 +399,15 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -411,8 +416,8 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 
 		r = get_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -425,8 +430,8 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -454,15 +459,15 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -472,8 +477,8 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 		value = RREG32_DIDT(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -484,8 +489,8 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -513,15 +518,15 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -530,8 +535,8 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 
 		r = get_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -544,8 +549,8 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -573,15 +578,15 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -591,8 +596,8 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 		value = RREG32_SMC(*pos);
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -603,8 +608,8 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -632,15 +637,15 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -649,8 +654,8 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 
 		r = get_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			amdgpu_virt_disable_access_debugfs(adev);
 			return r;
 		}
@@ -663,8 +668,8 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
 	return result;
@@ -791,22 +796,22 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 
 	valuesize = sizeof(values);
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_dpm_read_sensor(adev, idx, &values[0], &valuesize);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r) {
 		amdgpu_virt_disable_access_debugfs(adev);
@@ -873,15 +878,15 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
 	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_virt_enable_access_debugfs(adev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -896,8 +901,8 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (!x) {
 		amdgpu_virt_disable_access_debugfs(adev);
@@ -971,7 +976,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	if (!data)
 		return -ENOMEM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0)
 		goto err;
 
@@ -994,8 +999,8 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	while (size) {
 		uint32_t value;
@@ -1017,7 +1022,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	return result;
 
 err:
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 	kfree(data);
 	return r;
 }
@@ -1042,9 +1047,9 @@ static ssize_t amdgpu_debugfs_gfxoff_write(struct file *f, const char __user *bu
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -1053,8 +1058,8 @@ static ssize_t amdgpu_debugfs_gfxoff_write(struct file *f, const char __user *bu
 
 		r = get_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return r;
 		}
 
@@ -1066,8 +1071,8 @@ static ssize_t amdgpu_debugfs_gfxoff_write(struct file *f, const char __user *bu
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return result;
 }
@@ -1091,7 +1096,7 @@ static ssize_t amdgpu_debugfs_gfxoff_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0)
 		return r;
 
@@ -1100,15 +1105,15 @@ static ssize_t amdgpu_debugfs_gfxoff_read(struct file *f, char __user *buf,
 
 		r = amdgpu_get_gfx_off_status(adev, &value);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return r;
 		}
 
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return r;
 		}
 
@@ -1118,8 +1123,8 @@ static ssize_t amdgpu_debugfs_gfxoff_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return result;
 }
@@ -1211,7 +1216,7 @@ static const char *debugfs_regs_names[] = {
  */
 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
 {
-	struct drm_minor *minor = adev->ddev->primary;
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *ent, *root = minor->debugfs_root;
 	unsigned int i;
 
@@ -1231,17 +1236,19 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r = 0, i;
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	/* Avoid accidently unparking the sched thread during GPU reset */
-	mutex_lock(&adev->lock_reset);
+	r = down_read_killable(&adev->reset_sem);
+	if (r)
+		return r;
 
 	/* hold on the scheduler */
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
@@ -1268,7 +1275,7 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 		kthread_unpark(ring->sched.thread);
 	}
 
-	mutex_unlock(&adev->lock_reset);
+	up_read(&adev->reset_sem);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1280,7 +1287,7 @@ static int amdgpu_debugfs_get_vbios_dump(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	seq_write(m, adev->bios, adev->bios_size);
 	return 0;
@@ -1290,12 +1297,12 @@ static int amdgpu_debugfs_evict_vram(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r;
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -1311,12 +1318,12 @@ static int amdgpu_debugfs_evict_gtt(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r;
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -1458,7 +1465,9 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 		return -ENOMEM;
 
 	/* Avoid accidently unparking the sched thread during GPU reset */
-	mutex_lock(&adev->lock_reset);
+	r = down_read_killable(&adev->reset_sem);
+	if (r)
+		goto pro_end;
 
 	/* stop the scheduler */
 	kthread_park(ring->sched.thread);
@@ -1499,13 +1508,14 @@ failure:
 	/* restart the scheduler */
 	kthread_unpark(ring->sched.thread);
 
-	mutex_unlock(&adev->lock_reset);
+	up_read(&adev->reset_sem);
 
 	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
 
+pro_end:
 	kfree(fences);
 
-	return 0;
+	return r;
 }
 
 static int amdgpu_debugfs_sclk_set(void *data, u64 val)
@@ -1517,9 +1527,9 @@ static int amdgpu_debugfs_sclk_set(void *data, u64 val)
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return -EINVAL;
 
-	ret = pm_runtime_get_sync(adev->ddev->dev);
+	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
@@ -1532,8 +1542,8 @@ static int amdgpu_debugfs_sclk_set(void *data, u64 val)
 		return 0;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1553,7 +1563,7 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 
 	adev->debugfs_preempt =
 		debugfs_create_file("amdgpu_preempt_ib", 0600,
-				    adev->ddev->primary->debugfs_root, adev,
+				    adev_to_drm(adev)->primary->debugfs_root, adev,
 				    &fops_ib_preempt);
 	if (!(adev->debugfs_preempt)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
@@ -1562,7 +1572,7 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 
 	adev->smu.debugfs_sclk =
 		debugfs_create_file("amdgpu_force_sclk", 0200,
-				    adev->ddev->primary->debugfs_root, adev,
+				    adev_to_drm(adev)->primary->debugfs_root, adev,
 				    &fops_sclk_set);
 	if (!(adev->smu.debugfs_sclk)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
@@ -1623,6 +1633,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 
 	amdgpu_debugfs_autodump_init(adev);
 
+	amdgpu_rap_debugfs_init(adev);
+
 	return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list,
 					ARRAY_SIZE(amdgpu_debugfs_list));
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 4204cda680f5..f7307af76452 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -132,7 +132,7 @@ static ssize_t amdgpu_device_get_pcie_replay_count(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint64_t cnt = amdgpu_asic_get_pcie_replay_count(adev);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", cnt);
@@ -157,7 +157,7 @@ static ssize_t amdgpu_device_get_product_name(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%s\n", adev->product_name);
 }
@@ -179,7 +179,7 @@ static ssize_t amdgpu_device_get_product_number(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%s\n", adev->product_number);
 }
@@ -201,7 +201,7 @@ static ssize_t amdgpu_device_get_serial_number(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%s\n", adev->serial);
 }
@@ -219,7 +219,7 @@ static DEVICE_ATTR(serial_number, S_IRUGO,
  */
 bool amdgpu_device_supports_boco(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (adev->flags & AMD_IS_PX)
 		return true;
@@ -236,7 +236,7 @@ bool amdgpu_device_supports_boco(struct drm_device *dev)
  */
 bool amdgpu_device_supports_baco(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	return amdgpu_asic_supports_baco(adev);
 }
@@ -319,8 +319,12 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
 {
 	uint32_t ret;
 
-	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
-		return amdgpu_kiq_rreg(adev, reg);
+	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) &&
+	    down_read_trylock(&adev->reset_sem)) {
+		ret = amdgpu_kiq_rreg(adev, reg);
+		up_read(&adev->reset_sem);
+		return ret;
+	}
 
 	if ((reg * 4) < adev->rmmio_size)
 		ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
@@ -332,6 +336,7 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
 		ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
 		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
 	}
+
 	trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret);
 	return ret;
 }
@@ -378,7 +383,9 @@ void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value)
 		BUG();
 }
 
-void static inline amdgpu_mm_wreg_mmio(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t acc_flags)
+static inline void amdgpu_mm_wreg_mmio(struct amdgpu_device *adev,
+				       uint32_t reg, uint32_t v,
+				       uint32_t acc_flags)
 {
 	trace_amdgpu_mm_wreg(adev->pdev->device, reg, v);
 
@@ -407,8 +414,12 @@ void static inline amdgpu_mm_wreg_mmio(struct amdgpu_device *adev, uint32_t reg,
 void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
 		    uint32_t acc_flags)
 {
-	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
-		return amdgpu_kiq_wreg(adev, reg, v);
+	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) &&
+	    down_read_trylock(&adev->reset_sem)) {
+		amdgpu_kiq_wreg(adev, reg, v);
+		up_read(&adev->reset_sem);
+		return;
+	}
 
 	amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags);
 }
@@ -654,6 +665,20 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_device_asic_init - Wrapper for atom asic_init
+ *
+ * @dev: drm_device pointer
+ *
+ * Does any asic specific work and then calls atom asic init.
+ */
+static int amdgpu_device_asic_init(struct amdgpu_device *adev)
+{
+	amdgpu_asic_pre_asic_init(adev);
+
+	return amdgpu_atom_asic_init(adev->mode_info.atom_context);
+}
+
+/**
  * amdgpu_device_vram_scratch_init - allocate the VRAM scratch page
  *
  * @adev: amdgpu device pointer
@@ -1199,6 +1224,11 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	amdgpu_gmc_tmz_set(adev);
 
+	if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) {
+		amdgpu_num_kcq = 8;
+		dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid parameter provided by user\n");
+	}
+
 	return 0;
 }
 
@@ -1211,7 +1241,8 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
  * Callback for the switcheroo driver.  Suspends or resumes the
  * the asics before or after it is powered up using ACPI methods.
  */
-static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
+static void amdgpu_switcheroo_set_state(struct pci_dev *pdev,
+					enum vga_switcheroo_state state)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	int r;
@@ -1504,7 +1535,7 @@ static void amdgpu_device_enable_virtual_display(struct amdgpu_device *adev)
 	adev->enable_virtual_display = false;
 
 	if (amdgpu_virtual_display) {
-		struct drm_device *ddev = adev->ddev;
+		struct drm_device *ddev = adev_to_drm(adev);
 		const char *pci_address_name = pci_name(ddev->pdev);
 		char *pciaddstr, *pciaddstr_tmp, *pciaddname_tmp, *pciaddname;
 
@@ -1563,7 +1594,7 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->discovery_bin) {
+	if (adev->mman.discovery_bin) {
 		amdgpu_discovery_get_gfx_info(adev);
 
 		/*
@@ -1935,7 +1966,7 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 			if (adev->ip_blocks[i].status.hw == true)
 				break;
 
-			if (adev->in_gpu_reset || adev->in_suspend) {
+			if (amdgpu_in_reset(adev) || adev->in_suspend) {
 				r = adev->ip_blocks[i].version->funcs->resume(adev);
 				if (r) {
 					DRM_ERROR("resume of IP block <%s> failed %d\n",
@@ -2055,13 +2086,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	 * it should be called after amdgpu_device_ip_hw_init_phase2  since
 	 * for some ASICs the RAS EEPROM code relies on SMU fully functioning
 	 * for I2C communication which only true at this point.
-	 * recovery_init may fail, but it can free all resources allocated by
-	 * itself and its failure should not stop amdgpu init process.
+	 *
+	 * amdgpu_ras_recovery_init may fail, but the upper only cares the
+	 * failure from bad gpu situation and stop amdgpu init process
+	 * accordingly. For other failed cases, it will still release all
+	 * the resource and print error message, rather than returning one
+	 * negative value to upper level.
 	 *
 	 * Note: theoretically, this should be called before all vram allocations
 	 * to protect retired page from abusing
 	 */
-	amdgpu_ras_recovery_init(adev);
+	r = amdgpu_ras_recovery_init(adev);
+	if (r)
+		goto init_failed;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_add_device(adev);
@@ -2106,7 +2143,7 @@ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
 			AMDGPU_RESET_MAGIC_NUM))
 		return true;
 
-	if (!adev->in_gpu_reset)
+	if (!amdgpu_in_reset(adev))
 		return false;
 
 	/*
@@ -2217,9 +2254,7 @@ static int amdgpu_device_enable_mgpu_fan_boost(void)
 		gpu_ins = &(mgpu_info.gpu_ins[i]);
 		adev = gpu_ins->adev;
 		if (!(adev->flags & AMD_IS_APU) &&
-		    !gpu_ins->mgpu_fan_enabled &&
-		    adev->powerplay.pp_funcs &&
-		    adev->powerplay.pp_funcs->enable_mgpu_fan_boost) {
+		    !gpu_ins->mgpu_fan_enabled) {
 			ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
 			if (ret)
 				break;
@@ -2574,17 +2609,16 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 		AMD_IP_BLOCK_TYPE_IH,
 	};
 
-	for (i = 0; i < adev->num_ip_blocks; i++)
-		adev->ip_blocks[i].status.hw = false;
-
 	for (i = 0; i < ARRAY_SIZE(ip_order); i++) {
 		int j;
 		struct amdgpu_ip_block *block;
 
-		for (j = 0; j < adev->num_ip_blocks; j++) {
-			block = &adev->ip_blocks[j];
+		block = &adev->ip_blocks[i];
+		block->status.hw = false;
 
-			if (block->version->type != ip_order[i] ||
+		for (j = 0; j < ARRAY_SIZE(ip_order); j++) {
+
+			if (block->version->type != ip_order[j] ||
 				!block->status.valid)
 				continue;
 
@@ -2777,6 +2811,12 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+#endif
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
@@ -2831,7 +2871,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
  */
 bool amdgpu_device_has_dc_support(struct amdgpu_device *adev)
 {
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) || adev->enable_virtual_display)
 		return false;
 
 	return amdgpu_device_asic_has_dc_support(adev->asic_type);
@@ -2842,7 +2882,7 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 {
 	struct amdgpu_device *adev =
 		container_of(__work, struct amdgpu_device, xgmi_reset_work);
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 
 	/* It's a bug to not have a hive within this function */
 	if (WARN_ON(!hive))
@@ -2857,13 +2897,13 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 	if (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 
 		task_barrier_enter(&hive->tb);
-		adev->asic_reset_res = amdgpu_device_baco_enter(adev->ddev);
+		adev->asic_reset_res = amdgpu_device_baco_enter(adev_to_drm(adev));
 
 		if (adev->asic_reset_res)
 			goto fail;
 
 		task_barrier_exit(&hive->tb);
-		adev->asic_reset_res = amdgpu_device_baco_exit(adev->ddev);
+		adev->asic_reset_res = amdgpu_device_baco_exit(adev_to_drm(adev));
 
 		if (adev->asic_reset_res)
 			goto fail;
@@ -2879,7 +2919,8 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 fail:
 	if (adev->asic_reset_res)
 		DRM_WARN("ASIC reset failed with error, %d for drm dev, %s",
-			 adev->asic_reset_res, adev->ddev->unique);
+			 adev->asic_reset_res, adev_to_drm(adev)->unique);
+	amdgpu_put_xgmi_hive(hive);
 }
 
 static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
@@ -2962,8 +3003,6 @@ static const struct attribute *amdgpu_dev_attributes[] = {
  * amdgpu_device_init - initialize the driver
  *
  * @adev: amdgpu_device pointer
- * @ddev: drm dev pointer
- * @pdev: pci dev pointer
  * @flags: driver flags
  *
  * Initializes the driver info and hw (all asics).
@@ -2971,18 +3010,15 @@ static const struct attribute *amdgpu_dev_attributes[] = {
  * Called at driver startup.
  */
 int amdgpu_device_init(struct amdgpu_device *adev,
-		       struct drm_device *ddev,
-		       struct pci_dev *pdev,
 		       uint32_t flags)
 {
+	struct drm_device *ddev = adev_to_drm(adev);
+	struct pci_dev *pdev = adev->pdev;
 	int r, i;
 	bool boco = false;
 	u32 max_MBps;
 
 	adev->shutdown = false;
-	adev->dev = &pdev->dev;
-	adev->ddev = ddev;
-	adev->pdev = pdev;
 	adev->flags = flags;
 
 	if (amdgpu_force_asic_type >= 0 && amdgpu_force_asic_type < CHIP_LAST)
@@ -3038,7 +3074,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->mn_lock);
 	mutex_init(&adev->virt.vf_errors.lock);
 	hash_init(adev->mn_hash);
-	mutex_init(&adev->lock_reset);
+	atomic_set(&adev->in_gpu_reset, 0);
+	init_rwsem(&adev->reset_sem);
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
 
@@ -3188,7 +3225,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 			goto failed;
 		}
 		DRM_INFO("GPU posting now...\n");
-		r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
+		r = amdgpu_device_asic_init(adev);
 		if (r) {
 			dev_err(adev->dev, "gpu post error!\n");
 			goto failed;
@@ -3226,7 +3263,7 @@ fence_driver_init:
 	}
 
 	/* init the mode config */
-	drm_mode_config_init(adev->ddev);
+	drm_mode_config_init(adev_to_drm(adev));
 
 	r = amdgpu_device_ip_init(adev);
 	if (r) {
@@ -3352,9 +3389,7 @@ failed:
  */
 void amdgpu_device_fini(struct amdgpu_device *adev)
 {
-	int r;
-
-	DRM_INFO("amdgpu: finishing device.\n");
+	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
 	adev->shutdown = true;
 
@@ -3368,15 +3403,15 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	amdgpu_irq_disable_all(adev);
 	if (adev->mode_info.mode_config_initialized){
 		if (!amdgpu_device_has_dc_support(adev))
-			drm_helper_force_disable_all(adev->ddev);
+			drm_helper_force_disable_all(adev_to_drm(adev));
 		else
-			drm_atomic_helper_shutdown(adev->ddev);
+			drm_atomic_helper_shutdown(adev_to_drm(adev));
 	}
 	amdgpu_fence_driver_fini(adev);
 	if (adev->pm_sysfs_en)
 		amdgpu_pm_sysfs_fini(adev);
 	amdgpu_fbdev_fini(adev);
-	r = amdgpu_device_ip_fini(adev);
+	amdgpu_device_ip_fini(adev);
 	release_firmware(adev->firmware.gpu_info_fw);
 	adev->firmware.gpu_info_fw = NULL;
 	adev->accel_working = false;
@@ -3394,7 +3429,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	     amdgpu_has_atpx_dgpu_power_cntl()) &&
 	    !pci_is_thunderbolt_attached(adev->pdev))
 		vga_switcheroo_unregister_client(adev->pdev);
-	if (amdgpu_device_supports_boco(adev->ddev))
+	if (amdgpu_device_supports_boco(adev_to_drm(adev)))
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	vga_client_register(adev->pdev, NULL, NULL, NULL);
 	if (adev->rio_mem)
@@ -3410,7 +3445,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
-	if (adev->discovery_bin)
+	if (adev->mman.discovery_bin)
 		amdgpu_discovery_fini(adev);
 }
 
@@ -3436,11 +3471,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	struct drm_connector_list_iter iter;
 	int r;
 
-	if (dev == NULL || dev->dev_private == NULL) {
-		return -ENODEV;
-	}
-
-	adev = dev->dev_private;
+	adev = drm_to_adev(dev);
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
@@ -3528,7 +3559,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 {
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_crtc *crtc;
 	int r = 0;
 
@@ -3537,14 +3568,14 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 
 	/* post card */
 	if (amdgpu_device_need_post(adev)) {
-		r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
+		r = amdgpu_device_asic_init(adev);
 		if (r)
-			DRM_ERROR("amdgpu asic init failed\n");
+			dev_err(adev->dev, "amdgpu asic init failed\n");
 	}
 
 	r = amdgpu_device_ip_resume(adev);
 	if (r) {
-		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
+		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
 		return r;
 	}
 	amdgpu_fence_driver_resume(adev);
@@ -3568,7 +3599,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 				if (r == 0) {
 					r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 					if (r != 0)
-						DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+						dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r);
 					amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 					amdgpu_bo_unreserve(aobj);
 				}
@@ -3658,7 +3689,7 @@ static bool amdgpu_device_ip_check_soft_reset(struct amdgpu_device *adev)
 			adev->ip_blocks[i].status.hang =
 				adev->ip_blocks[i].version->funcs->check_soft_reset(adev);
 		if (adev->ip_blocks[i].status.hang) {
-			DRM_INFO("IP block:%s is hung!\n", adev->ip_blocks[i].version->funcs->name);
+			dev_info(adev->dev, "IP block:%s is hung!\n", adev->ip_blocks[i].version->funcs->name);
 			asic_hang = true;
 		}
 	}
@@ -3719,7 +3750,7 @@ static bool amdgpu_device_ip_need_full_reset(struct amdgpu_device *adev)
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) ||
 		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
 			if (adev->ip_blocks[i].status.hang) {
-				DRM_INFO("Some block need full reset!\n");
+				dev_info(adev->dev, "Some block need full reset!\n");
 				return true;
 			}
 		}
@@ -3807,7 +3838,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 	else
 		tmo = msecs_to_jiffies(100);
 
-	DRM_INFO("recover vram bo from shadow start\n");
+	dev_info(adev->dev, "recover vram bo from shadow start\n");
 	mutex_lock(&adev->shadow_list_lock);
 	list_for_each_entry(shadow, &adev->shadow_list, shadow_list) {
 
@@ -3843,11 +3874,11 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 	dma_fence_put(fence);
 
 	if (r < 0 || tmo <= 0) {
-		DRM_ERROR("recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
+		dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
 		return -EIO;
 	}
 
-	DRM_INFO("recover vram bo from shadow done\n");
+	dev_info(adev->dev, "recover vram bo from shadow done\n");
 	return 0;
 }
 
@@ -3908,6 +3939,34 @@ error:
 }
 
 /**
+ * amdgpu_device_has_job_running - check if there is any job in mirror list
+ *
+ * @adev: amdgpu device pointer
+ *
+ * check if there is any job in mirror list
+ */
+bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
+{
+	int i;
+	struct drm_sched_job *job;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+
+		spin_lock(&ring->sched.job_list_lock);
+		job = list_first_entry_or_null(&ring->sched.ring_mirror_list,
+				struct drm_sched_job, node);
+		spin_unlock(&ring->sched.job_list_lock);
+		if (job)
+			return true;
+	}
+	return false;
+}
+
+/**
  * amdgpu_device_should_recover_gpu - check if we should try GPU recovery
  *
  * @adev: amdgpu device pointer
@@ -3918,7 +3977,7 @@ error:
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 {
 	if (!amdgpu_device_ip_check_soft_reset(adev)) {
-		DRM_INFO("Timeout, but no hardware hang detected.\n");
+		dev_info(adev->dev, "Timeout, but no hardware hang detected.\n");
 		return false;
 	}
 
@@ -3958,7 +4017,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 	return true;
 
 disabled:
-		DRM_INFO("GPU recovery disabled.\n");
+		dev_info(adev->dev, "GPU recovery disabled.\n");
 		return false;
 }
 
@@ -3997,7 +4056,7 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 			r = amdgpu_device_ip_soft_reset(adev);
 			amdgpu_device_ip_post_soft_reset(adev);
 			if (r || amdgpu_device_ip_check_soft_reset(adev)) {
-				DRM_INFO("soft reset failed, will fallback to full reset!\n");
+				dev_info(adev->dev, "soft reset failed, will fallback to full reset!\n");
 				need_full_reset = true;
 			}
 		}
@@ -4033,8 +4092,8 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 				r = amdgpu_asic_reset(tmp_adev);
 
 			if (r) {
-				DRM_ERROR("ASIC reset failed with error, %d for drm dev, %s",
-					 r, tmp_adev->ddev->unique);
+				dev_err(tmp_adev->dev, "ASIC reset failed with error, %d for drm dev, %s",
+					 r, adev_to_drm(tmp_adev)->unique);
 				break;
 			}
 		}
@@ -4066,8 +4125,8 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		if (need_full_reset) {
 			/* post card */
-			if (amdgpu_atom_asic_init(tmp_adev->mode_info.atom_context))
-				DRM_WARN("asic atom init failed!");
+			if (amdgpu_device_asic_init(tmp_adev))
+				dev_warn(tmp_adev->dev, "asic atom init failed!");
 
 			if (!r) {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
@@ -4108,8 +4167,23 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 
 				amdgpu_fbdev_set_suspend(tmp_adev, 0);
 
-				/* must succeed. */
-				amdgpu_ras_resume(tmp_adev);
+				/*
+				 * The GPU enters bad state once faulty pages
+				 * by ECC has reached the threshold, and ras
+				 * recovery is scheduled next. So add one check
+				 * here to break recovery if it indeed exceeds
+				 * bad page threshold, and remind user to
+				 * retire this GPU or setting one bigger
+				 * bad_page_threshold value to fix this once
+				 * probing driver again.
+				 */
+				if (!amdgpu_ras_check_err_threshold(tmp_adev)) {
+					/* must succeed. */
+					amdgpu_ras_resume(tmp_adev);
+				} else {
+					r = -EINVAL;
+					goto out;
+				}
 
 				/* Update PSP FW topology after reset */
 				if (hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1)
@@ -4117,7 +4191,6 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 			}
 		}
 
-
 out:
 		if (!r) {
 			amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
@@ -4142,16 +4215,19 @@ end:
 	return r;
 }
 
-static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
+static bool amdgpu_device_lock_adev(struct amdgpu_device *adev,
+				struct amdgpu_hive_info *hive)
 {
-	if (trylock) {
-		if (!mutex_trylock(&adev->lock_reset))
-			return false;
-	} else
-		mutex_lock(&adev->lock_reset);
+	if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
+		return false;
+
+	if (hive) {
+		down_write_nest_lock(&adev->reset_sem, &hive->hive_lock);
+	} else {
+		down_write(&adev->reset_sem);
+	}
 
 	atomic_inc(&adev->gpu_reset_counter);
-	adev->in_gpu_reset = true;
 	switch (amdgpu_asic_reset_method(adev)) {
 	case AMD_RESET_METHOD_MODE1:
 		adev->mp1_state = PP_MP1_STATE_SHUTDOWN;
@@ -4171,8 +4247,8 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
 	amdgpu_vf_error_trans_all(adev);
 	adev->mp1_state = PP_MP1_STATE_NONE;
-	adev->in_gpu_reset = false;
-	mutex_unlock(&adev->lock_reset);
+	atomic_set(&adev->in_gpu_reset, 0);
+	up_write(&adev->reset_sem);
 }
 
 static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev)
@@ -4282,12 +4358,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 * We always reset all schedulers for device and all devices for XGMI
 	 * hive so that should take care of them too.
 	 */
-	hive = amdgpu_get_xgmi_hive(adev, true);
-	if (hive && !mutex_trylock(&hive->reset_lock)) {
-		DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
-			  job ? job->base.id : -1, hive->hive_id);
-		mutex_unlock(&hive->hive_lock);
-		return 0;
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		if (atomic_cmpxchg(&hive->in_reset, 0, 1) != 0) {
+			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
+				job ? job->base.id : -1, hive->hive_id);
+			amdgpu_put_xgmi_hive(hive);
+			return 0;
+		}
+		mutex_lock(&hive->hive_lock);
 	}
 
 	/*
@@ -4309,11 +4388,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	/* block all schedulers and reset given job's ring */
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
-		if (!amdgpu_device_lock_adev(tmp_adev, !hive)) {
-			DRM_INFO("Bailing on TDR for s_job:%llx, as another already in progress",
+		if (!amdgpu_device_lock_adev(tmp_adev, hive)) {
+			dev_info(tmp_adev->dev, "Bailing on TDR for s_job:%llx, as another already in progress",
 				  job ? job->base.id : -1);
-			mutex_unlock(&hive->hive_lock);
-			return 0;
+			r = 0;
+			goto skip_recovery;
 		}
 
 		/*
@@ -4385,8 +4464,8 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 						 &need_full_reset);
 		/*TODO Should we stop ?*/
 		if (r) {
-			DRM_ERROR("GPU pre asic reset failed with err, %d for drm dev, %s ",
-				  r, tmp_adev->ddev->unique);
+			dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
+				  r, adev_to_drm(tmp_adev)->unique);
 			tmp_adev->asic_reset_res = r;
 		}
 	}
@@ -4422,7 +4501,7 @@ skip_hw_reset:
 		}
 
 		if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
-			drm_helper_resume_force_mode(tmp_adev->ddev);
+			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 		}
 
 		tmp_adev->asic_reset_res = 0;
@@ -4446,9 +4525,11 @@ skip_sched_resume:
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
 
+skip_recovery:
 	if (hive) {
-		mutex_unlock(&hive->reset_lock);
+		atomic_set(&hive->in_reset, 0);
 		mutex_unlock(&hive->hive_lock);
+		amdgpu_put_xgmi_hive(hive);
 	}
 
 	if (r)
@@ -4594,10 +4675,10 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 
 int amdgpu_device_baco_enter(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
-	if (!amdgpu_device_supports_baco(adev->ddev))
+	if (!amdgpu_device_supports_baco(adev_to_drm(adev)))
 		return -ENOTSUPP;
 
 	if (ras && ras->supported)
@@ -4608,11 +4689,11 @@ int amdgpu_device_baco_enter(struct drm_device *dev)
 
 int amdgpu_device_baco_exit(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	int ret = 0;
 
-	if (!amdgpu_device_supports_baco(adev->ddev))
+	if (!amdgpu_device_supports_baco(adev_to_drm(adev)))
 		return -ENOTSUPP;
 
 	ret = amdgpu_dpm_baco_exit(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index a50ff2306504..bfb95143ba5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -136,7 +136,7 @@ static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *bin
 	uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET;
 
 	amdgpu_device_vram_access(adev, pos, (uint32_t *)binary,
-				  adev->discovery_tmr_size, false);
+				  adev->mman.discovery_tmr_size, false);
 	return 0;
 }
 
@@ -168,18 +168,18 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	uint16_t checksum;
 	int r;
 
-	adev->discovery_tmr_size = DISCOVERY_TMR_SIZE;
-	adev->discovery_bin = kzalloc(adev->discovery_tmr_size, GFP_KERNEL);
-	if (!adev->discovery_bin)
+	adev->mman.discovery_tmr_size = DISCOVERY_TMR_SIZE;
+	adev->mman.discovery_bin = kzalloc(adev->mman.discovery_tmr_size, GFP_KERNEL);
+	if (!adev->mman.discovery_bin)
 		return -ENOMEM;
 
-	r = amdgpu_discovery_read_binary(adev, adev->discovery_bin);
+	r = amdgpu_discovery_read_binary(adev, adev->mman.discovery_bin);
 	if (r) {
 		DRM_ERROR("failed to read ip discovery binary\n");
 		goto out;
 	}
 
-	bhdr = (struct binary_header *)adev->discovery_bin;
+	bhdr = (struct binary_header *)adev->mman.discovery_bin;
 
 	if (le32_to_cpu(bhdr->binary_signature) != BINARY_SIGNATURE) {
 		DRM_ERROR("invalid ip discovery binary signature\n");
@@ -192,7 +192,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	size = bhdr->binary_size - offset;
 	checksum = bhdr->binary_checksum;
 
-	if (!amdgpu_discovery_verify_checksum(adev->discovery_bin + offset,
+	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
 					      size, checksum)) {
 		DRM_ERROR("invalid ip discovery binary checksum\n");
 		r = -EINVAL;
@@ -202,7 +202,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	info = &bhdr->table_list[IP_DISCOVERY];
 	offset = le16_to_cpu(info->offset);
 	checksum = le16_to_cpu(info->checksum);
-	ihdr = (struct ip_discovery_header *)(adev->discovery_bin + offset);
+	ihdr = (struct ip_discovery_header *)(adev->mman.discovery_bin + offset);
 
 	if (le32_to_cpu(ihdr->signature) != DISCOVERY_TABLE_SIGNATURE) {
 		DRM_ERROR("invalid ip discovery data table signature\n");
@@ -210,7 +210,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 		goto out;
 	}
 
-	if (!amdgpu_discovery_verify_checksum(adev->discovery_bin + offset,
+	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
 					      ihdr->size, checksum)) {
 		DRM_ERROR("invalid ip discovery data table checksum\n");
 		r = -EINVAL;
@@ -220,9 +220,9 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	info = &bhdr->table_list[GC];
 	offset = le16_to_cpu(info->offset);
 	checksum = le16_to_cpu(info->checksum);
-	ghdr = (struct gpu_info_header *)(adev->discovery_bin + offset);
+	ghdr = (struct gpu_info_header *)(adev->mman.discovery_bin + offset);
 
-	if (!amdgpu_discovery_verify_checksum(adev->discovery_bin + offset,
+	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
 				              ghdr->size, checksum)) {
 		DRM_ERROR("invalid gc data table checksum\n");
 		r = -EINVAL;
@@ -232,16 +232,16 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	return 0;
 
 out:
-	kfree(adev->discovery_bin);
-	adev->discovery_bin = NULL;
+	kfree(adev->mman.discovery_bin);
+	adev->mman.discovery_bin = NULL;
 
 	return r;
 }
 
 void amdgpu_discovery_fini(struct amdgpu_device *adev)
 {
-	kfree(adev->discovery_bin);
-	adev->discovery_bin = NULL;
+	kfree(adev->mman.discovery_bin);
+	adev->mman.discovery_bin = NULL;
 }
 
 int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
@@ -265,8 +265,8 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	bhdr = (struct binary_header *)adev->discovery_bin;
-	ihdr = (struct ip_discovery_header *)(adev->discovery_bin +
+	bhdr = (struct binary_header *)adev->mman.discovery_bin;
+	ihdr = (struct ip_discovery_header *)(adev->mman.discovery_bin +
 			le16_to_cpu(bhdr->table_list[IP_DISCOVERY].offset));
 	num_dies = le16_to_cpu(ihdr->num_dies);
 
@@ -274,7 +274,7 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 
 	for (i = 0; i < num_dies; i++) {
 		die_offset = le16_to_cpu(ihdr->die_info[i].die_offset);
-		dhdr = (struct die_header *)(adev->discovery_bin + die_offset);
+		dhdr = (struct die_header *)(adev->mman.discovery_bin + die_offset);
 		num_ips = le16_to_cpu(dhdr->num_ips);
 		ip_offset = die_offset + sizeof(*dhdr);
 
@@ -288,7 +288,7 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 				le16_to_cpu(dhdr->die_id), num_ips);
 
 		for (j = 0; j < num_ips; j++) {
-			ip = (struct ip *)(adev->discovery_bin + ip_offset);
+			ip = (struct ip *)(adev->mman.discovery_bin + ip_offset);
 			num_base_address = ip->num_base_address;
 
 			DRM_DEBUG("%s(%d) #%d v%d.%d.%d:\n",
@@ -337,24 +337,24 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
 	uint16_t num_ips;
 	int i, j;
 
-	if (!adev->discovery_bin) {
+	if (!adev->mman.discovery_bin) {
 		DRM_ERROR("ip discovery uninitialized\n");
 		return -EINVAL;
 	}
 
-	bhdr = (struct binary_header *)adev->discovery_bin;
-	ihdr = (struct ip_discovery_header *)(adev->discovery_bin +
+	bhdr = (struct binary_header *)adev->mman.discovery_bin;
+	ihdr = (struct ip_discovery_header *)(adev->mman.discovery_bin +
 			le16_to_cpu(bhdr->table_list[IP_DISCOVERY].offset));
 	num_dies = le16_to_cpu(ihdr->num_dies);
 
 	for (i = 0; i < num_dies; i++) {
 		die_offset = le16_to_cpu(ihdr->die_info[i].die_offset);
-		dhdr = (struct die_header *)(adev->discovery_bin + die_offset);
+		dhdr = (struct die_header *)(adev->mman.discovery_bin + die_offset);
 		num_ips = le16_to_cpu(dhdr->num_ips);
 		ip_offset = die_offset + sizeof(*dhdr);
 
 		for (j = 0; j < num_ips; j++) {
-			ip = (struct ip *)(adev->discovery_bin + ip_offset);
+			ip = (struct ip *)(adev->mman.discovery_bin + ip_offset);
 
 			if (le16_to_cpu(ip->hw_id) == hw_id) {
 				if (major)
@@ -377,13 +377,13 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 	struct binary_header *bhdr;
 	struct gc_info_v1_0 *gc_info;
 
-	if (!adev->discovery_bin) {
+	if (!adev->mman.discovery_bin) {
 		DRM_ERROR("ip discovery uninitialized\n");
 		return -EINVAL;
 	}
 
-	bhdr = (struct binary_header *)adev->discovery_bin;
-	gc_info = (struct gc_info_v1_0 *)(adev->discovery_bin +
+	bhdr = (struct binary_header *)adev->mman.discovery_bin;
+	gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
 			le16_to_cpu(bhdr->table_list[GC].offset));
 
 	adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index d76172965199..c81206e6096f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -93,7 +93,7 @@ static void amdgpu_display_flip_work_func(struct work_struct *__work)
 	 * targeted by the flip
 	 */
 	if (amdgpu_crtc->enabled &&
-	    (amdgpu_display_get_crtc_scanoutpos(adev->ddev, work->crtc_id, 0,
+	    (amdgpu_display_get_crtc_scanoutpos(adev_to_drm(adev), work->crtc_id, 0,
 						&vpos, &hpos, NULL, NULL,
 						&crtc->hwmode)
 	     & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK)) ==
@@ -152,7 +152,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 				struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_gem_object *obj;
 	struct amdgpu_flip_work *work;
@@ -292,7 +292,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 
 	pm_runtime_mark_last_busy(dev->dev);
 
-	adev = dev->dev_private;
+	adev = drm_to_adev(dev);
 	/* if we have active crtcs and we don't have a power ref,
 	   take the current one */
 	if (active && !adev->have_disp_power_ref) {
@@ -619,51 +619,51 @@ int amdgpu_display_modeset_create_props(struct amdgpu_device *adev)
 	int sz;
 
 	adev->mode_info.coherent_mode_property =
-		drm_property_create_range(adev->ddev, 0 , "coherent", 0, 1);
+		drm_property_create_range(adev_to_drm(adev), 0, "coherent", 0, 1);
 	if (!adev->mode_info.coherent_mode_property)
 		return -ENOMEM;
 
 	adev->mode_info.load_detect_property =
-		drm_property_create_range(adev->ddev, 0, "load detection", 0, 1);
+		drm_property_create_range(adev_to_drm(adev), 0, "load detection", 0, 1);
 	if (!adev->mode_info.load_detect_property)
 		return -ENOMEM;
 
-	drm_mode_create_scaling_mode_property(adev->ddev);
+	drm_mode_create_scaling_mode_property(adev_to_drm(adev));
 
 	sz = ARRAY_SIZE(amdgpu_underscan_enum_list);
 	adev->mode_info.underscan_property =
-		drm_property_create_enum(adev->ddev, 0,
-				    "underscan",
-				    amdgpu_underscan_enum_list, sz);
+		drm_property_create_enum(adev_to_drm(adev), 0,
+					 "underscan",
+					 amdgpu_underscan_enum_list, sz);
 
 	adev->mode_info.underscan_hborder_property =
-		drm_property_create_range(adev->ddev, 0,
-					"underscan hborder", 0, 128);
+		drm_property_create_range(adev_to_drm(adev), 0,
+					  "underscan hborder", 0, 128);
 	if (!adev->mode_info.underscan_hborder_property)
 		return -ENOMEM;
 
 	adev->mode_info.underscan_vborder_property =
-		drm_property_create_range(adev->ddev, 0,
-					"underscan vborder", 0, 128);
+		drm_property_create_range(adev_to_drm(adev), 0,
+					  "underscan vborder", 0, 128);
 	if (!adev->mode_info.underscan_vborder_property)
 		return -ENOMEM;
 
 	sz = ARRAY_SIZE(amdgpu_audio_enum_list);
 	adev->mode_info.audio_property =
-		drm_property_create_enum(adev->ddev, 0,
+		drm_property_create_enum(adev_to_drm(adev), 0,
 					 "audio",
 					 amdgpu_audio_enum_list, sz);
 
 	sz = ARRAY_SIZE(amdgpu_dither_enum_list);
 	adev->mode_info.dither_property =
-		drm_property_create_enum(adev->ddev, 0,
+		drm_property_create_enum(adev_to_drm(adev), 0,
 					 "dither",
 					 amdgpu_dither_enum_list, sz);
 
 	if (amdgpu_device_has_dc_support(adev)) {
 		adev->mode_info.abm_level_property =
-			drm_property_create_range(adev->ddev, 0,
-						"abm level", 0, 4);
+			drm_property_create_range(adev_to_drm(adev), 0,
+						  "abm level", 0, 4);
 		if (!adev->mode_info.abm_level_property)
 			return -ENOMEM;
 	}
@@ -813,7 +813,7 @@ int amdgpu_display_get_crtc_scanoutpos(struct drm_device *dev,
 	int vbl_start, vbl_end, vtotal, ret = 0;
 	bool in_vbl = true;
 
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index d7050ab95946..957934926b24 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -35,6 +35,7 @@
 #include "amdgpu_display.h"
 #include "amdgpu_gem.h"
 #include "amdgpu_dma_buf.h"
+#include "amdgpu_xgmi.h"
 #include <drm/amdgpu_drm.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
@@ -455,7 +456,7 @@ static struct drm_gem_object *
 amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 {
 	struct dma_resv *resv = dma_buf->resv;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_bo *bo;
 	struct amdgpu_bo_param bp;
 	int ret;
@@ -596,3 +597,36 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 	obj->import_attach = attach;
 	return obj;
 }
+
+/**
+ * amdgpu_dmabuf_is_xgmi_accessible - Check if xgmi available for P2P transfer
+ *
+ * @adev: amdgpu_device pointer of the importer
+ * @bo: amdgpu buffer object
+ *
+ * Returns:
+ * True if dmabuf accessible over xgmi, false otherwise.
+ */
+bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
+				      struct amdgpu_bo *bo)
+{
+	struct drm_gem_object *obj = &bo->tbo.base;
+	struct drm_gem_object *gobj;
+
+	if (obj->import_attach) {
+		struct dma_buf *dma_buf = obj->import_attach->dmabuf;
+
+		if (dma_buf->ops != &amdgpu_dmabuf_ops)
+			/* No XGMI with non AMD GPUs */
+			return false;
+
+		gobj = dma_buf->priv;
+		bo = gem_to_amdgpu_bo(gobj);
+	}
+
+	if (amdgpu_xgmi_same_hive(adev, amdgpu_ttm_adev(bo->tbo.bdev)) &&
+			(bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM))
+		return true;
+
+	return false;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
index ec447a7b6b28..2c5c84a06bb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
@@ -29,6 +29,8 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 					int flags);
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 					    struct dma_buf *dma_buf);
+bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
+				      struct amdgpu_bo *bo);
 void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj);
 void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int amdgpu_gem_prime_mmap(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 81a79760ca61..6edde2b9e402 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -26,6 +26,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_managed.h>
 #include "amdgpu_drv.h"
 
 #include <drm/drm_pciids.h>
@@ -88,9 +89,10 @@
  * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  * - 3.39.0 - DMABUF implicit sync does a full pipeline sync
+ * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	39
+#define KMS_DRIVER_MINOR	40
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -150,12 +152,14 @@ int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
 int amdgpu_reset_method = -1; /* auto */
+int amdgpu_num_kcq = -1;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
 };
 int amdgpu_ras_enable = -1;
 uint amdgpu_ras_mask = 0xffffffff;
+int amdgpu_bad_page_threshold = -1;
 
 /**
  * DOC: vramlimit (int)
@@ -676,11 +680,14 @@ MODULE_PARM_DESC(debug_largebar,
  * Ignore CRAT table during KFD initialization. By default, KFD uses the ACPI CRAT
  * table to get information about AMD APUs. This option can serve as a workaround on
  * systems with a broken CRAT table.
+ *
+ * Default is auto (according to asic type, iommu_v2, and crat table, to decide
+ * whehter use CRAT)
  */
 int ignore_crat;
 module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
-	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
+	"Ignore CRAT table during KFD initialization (0 = auto (default), 1 = ignore CRAT)");
 
 /**
  * DOC: halt_if_hws_hang (int)
@@ -715,6 +722,15 @@ MODULE_PARM_DESC(queue_preemption_timeout_ms, "queue preemption timeout in ms (1
 bool debug_evictions;
 module_param(debug_evictions, bool, 0644);
 MODULE_PARM_DESC(debug_evictions, "enable eviction debug messages (false = default)");
+
+/**
+ * DOC: no_system_mem_limit(bool)
+ * Disable system memory limit, to support multiple process shared memory
+ */
+bool no_system_mem_limit;
+module_param(no_system_mem_limit, bool, 0644);
+MODULE_PARM_DESC(no_system_mem_limit, "disable system memory limit (false = default)");
+
 #endif
 
 /**
@@ -765,6 +781,19 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
 MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)");
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
+/**
+ * DOC: bad_page_threshold (int)
+ * Bad page threshold is to specify the threshold value of faulty pages
+ * detected by RAS ECC, that may result in GPU entering bad status if total
+ * faulty pages by ECC exceed threshold value and leave it for user's further
+ * check.
+ */
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
+
+MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
+module_param_named(num_kcq, amdgpu_num_kcq, int, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -1057,7 +1086,7 @@ static struct drm_driver kms_driver;
 static int amdgpu_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
-	struct drm_device *dev;
+	struct drm_device *ddev;
 	struct amdgpu_device *adev;
 	unsigned long flags = ent->driver_data;
 	int ret, retry = 0;
@@ -1113,36 +1142,44 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	dev = drm_dev_alloc(&kms_driver, &pdev->dev);
-	if (IS_ERR(dev))
-		return PTR_ERR(dev);
+	adev = kzalloc(sizeof(*adev), GFP_KERNEL);
+	if (!adev)
+		return -ENOMEM;
+
+	adev->dev  = &pdev->dev;
+	adev->pdev = pdev;
+	ddev = adev_to_drm(adev);
+	ret = drm_dev_init(ddev, &kms_driver, &pdev->dev);
+	if (ret)
+		goto err_free;
+
+	drmm_add_final_kfree(ddev, adev);
 
 	if (!supports_atomic)
-		dev->driver_features &= ~DRIVER_ATOMIC;
+		ddev->driver_features &= ~DRIVER_ATOMIC;
 
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto err_free;
 
-	dev->pdev = pdev;
-
-	pci_set_drvdata(pdev, dev);
+	ddev->pdev = pdev;
+	pci_set_drvdata(pdev, ddev);
 
-	ret = amdgpu_driver_load_kms(dev, ent->driver_data);
+	ret = amdgpu_driver_load_kms(adev, ent->driver_data);
 	if (ret)
 		goto err_pci;
 
 retry_init:
-	ret = drm_dev_register(dev, ent->driver_data);
+	ret = drm_dev_register(ddev, ent->driver_data);
 	if (ret == -EAGAIN && ++retry <= 3) {
 		DRM_INFO("retry init %d\n", retry);
 		/* Don't request EX mode too frequently which is attacking */
 		msleep(5000);
 		goto retry_init;
-	} else if (ret)
+	} else if (ret) {
 		goto err_pci;
+	}
 
-	adev = dev->dev_private;
 	ret = amdgpu_debugfs_init(adev);
 	if (ret)
 		DRM_ERROR("Creating debugfs files failed (%d).\n", ret);
@@ -1152,7 +1189,7 @@ retry_init:
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_put(dev);
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -1176,7 +1213,7 @@ static void
 amdgpu_pci_shutdown(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (amdgpu_ras_intr_triggered())
 		return;
@@ -1209,7 +1246,7 @@ static int amdgpu_pmops_resume(struct device *dev)
 static int amdgpu_pmops_freeze(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
 	adev->in_hibernate = true;
@@ -1245,7 +1282,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret, i;
 
 	if (!adev->runpm) {
@@ -1296,7 +1333,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret;
 
 	if (!adev->runpm)
@@ -1332,7 +1369,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 static int amdgpu_pmops_runtime_idle(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
 	int ret = 1;
 
@@ -1500,8 +1537,6 @@ static struct pci_driver amdgpu_kms_pci_driver = {
 	.driver.pm = &amdgpu_pm_ops,
 };
 
-
-
 static int __init amdgpu_init(void)
 {
 	int r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
index 61fcf247a638..af4ef84e27a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
@@ -35,7 +35,7 @@
 void
 amdgpu_link_encoder_connector(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index db731f573f98..e2c2eb45a793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -135,7 +135,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 			       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
 			       AMDGPU_GEM_CREATE_VRAM_CLEARED;
 
-	info = drm_get_format_info(adev->ddev, mode_cmd);
+	info = drm_get_format_info(adev_to_drm(adev), mode_cmd);
 	cpp = info->cpp[0];
 
 	/* need to align pitch with crtc limits */
@@ -231,7 +231,7 @@ static int amdgpufb_create(struct drm_fb_helper *helper,
 		goto out;
 	}
 
-	ret = amdgpu_display_framebuffer_init(adev->ddev, &rfbdev->rfb,
+	ret = amdgpu_display_framebuffer_init(adev_to_drm(adev), &rfbdev->rfb,
 					      &mode_cmd, gobj);
 	if (ret) {
 		DRM_ERROR("failed to initialize framebuffer %d\n", ret);
@@ -254,7 +254,7 @@ static int amdgpufb_create(struct drm_fb_helper *helper,
 	drm_fb_helper_fill_info(info, &rfbdev->helper, sizes);
 
 	/* setup aperture base/size for vesafb takeover */
-	info->apertures->ranges[0].base = adev->ddev->mode_config.fb_base;
+	info->apertures->ranges[0].base = adev_to_drm(adev)->mode_config.fb_base;
 	info->apertures->ranges[0].size = adev->gmc.aper_size;
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -270,7 +270,7 @@ static int amdgpufb_create(struct drm_fb_helper *helper,
 	DRM_INFO("fb depth is %d\n", fb->format->depth);
 	DRM_INFO("   pitch is %d\n", fb->pitches[0]);
 
-	vga_switcheroo_client_fb_set(adev->ddev->pdev, info);
+	vga_switcheroo_client_fb_set(adev_to_drm(adev)->pdev, info);
 	return 0;
 
 out:
@@ -318,7 +318,7 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 		return 0;
 
 	/* don't init fbdev if there are no connectors */
-	if (list_empty(&adev->ddev->mode_config.connector_list))
+	if (list_empty(&adev_to_drm(adev)->mode_config.connector_list))
 		return 0;
 
 	/* select 8 bpp console on low vram cards */
@@ -332,10 +332,10 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 	rfbdev->adev = adev;
 	adev->mode_info.rfbdev = rfbdev;
 
-	drm_fb_helper_prepare(adev->ddev, &rfbdev->helper,
-			&amdgpu_fb_helper_funcs);
+	drm_fb_helper_prepare(adev_to_drm(adev), &rfbdev->helper,
+			      &amdgpu_fb_helper_funcs);
 
-	ret = drm_fb_helper_init(adev->ddev, &rfbdev->helper);
+	ret = drm_fb_helper_init(adev_to_drm(adev), &rfbdev->helper);
 	if (ret) {
 		kfree(rfbdev);
 		return ret;
@@ -343,7 +343,7 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	if (!amdgpu_device_has_dc_support(adev))
-		drm_helper_disable_unused_functions(adev->ddev);
+		drm_helper_disable_unused_functions(adev_to_drm(adev));
 
 	drm_fb_helper_initial_config(&rfbdev->helper, bpp_sel);
 	return 0;
@@ -354,7 +354,7 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev)
 	if (!adev->mode_info.rfbdev)
 		return;
 
-	amdgpu_fbdev_destroy(adev->ddev, adev->mode_info.rfbdev);
+	amdgpu_fbdev_destroy(adev_to_drm(adev), adev->mode_info.rfbdev);
 	kfree(adev->mode_info.rfbdev);
 	adev->mode_info.rfbdev = NULL;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 58d4c219178a..fe2d495d08ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -155,7 +155,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 		       seq);
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
-	pm_runtime_get_noresume(adev->ddev->dev);
+	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
 		struct dma_fence *old;
@@ -284,8 +284,8 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 			BUG();
 
 		dma_fence_put(fence);
-		pm_runtime_mark_last_busy(adev->ddev->dev);
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 	} while (last_seq != seq);
 
 	return true;
@@ -700,7 +700,7 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i;
 
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -749,7 +749,7 @@ static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r;
 
 	r = pm_runtime_get_sync(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 6b1eb9d045ae..aa7f230c71bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -93,7 +93,7 @@ retry:
 
 void amdgpu_gem_force_release(struct amdgpu_device *adev)
 {
-	struct drm_device *ddev = adev->ddev;
+	struct drm_device *ddev = adev_to_drm(adev);
 	struct drm_file *file;
 
 	mutex_lock(&ddev->filelist_mutex);
@@ -217,7 +217,7 @@ out_unlock:
 int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
 	union drm_amdgpu_gem_create *args = data;
@@ -298,7 +298,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *filp)
 {
 	struct ttm_operation_ctx ctx = { true, false };
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_amdgpu_gem_userptr *args = data;
 	struct drm_gem_object *gobj;
 	struct amdgpu_bo *bo;
@@ -587,7 +587,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	struct drm_amdgpu_gem_va *args = data;
 	struct drm_gem_object *gobj;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo *abo;
 	struct amdgpu_bo_va *bo_va;
@@ -711,7 +711,7 @@ error_unref:
 int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_amdgpu_gem_op *args = data;
 	struct drm_gem_object *gobj;
 	struct amdgpu_vm_bo_base *base;
@@ -788,7 +788,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_device *dev,
 			    struct drm_mode_create_dumb *args)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_gem_object *gobj;
 	uint32_t handle;
 	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 78d37f92c7be..d6981425ec51 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -202,40 +202,29 @@ bool amdgpu_gfx_is_high_priority_compute_queue(struct amdgpu_device *adev,
 
 void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
 {
-	int i, queue, pipe, mec;
+	int i, queue, pipe;
 	bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
-
-	/* policy for amdgpu compute queue ownership */
-	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
-		queue = i % adev->gfx.mec.num_queue_per_pipe;
-		pipe = (i / adev->gfx.mec.num_queue_per_pipe)
-			% adev->gfx.mec.num_pipe_per_mec;
-		mec = (i / adev->gfx.mec.num_queue_per_pipe)
-			/ adev->gfx.mec.num_pipe_per_mec;
-
-		/* we've run out of HW */
-		if (mec >= adev->gfx.mec.num_mec)
-			break;
-
-		if (multipipe_policy) {
-			/* policy: amdgpu owns the first two queues of the first MEC */
-			if (mec == 0 && queue < 2)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
-		} else {
-			/* policy: amdgpu owns all queues in the first pipe */
-			if (mec == 0 && pipe == 0)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
+	int max_queues_per_mec = min(adev->gfx.mec.num_pipe_per_mec *
+				     adev->gfx.mec.num_queue_per_pipe,
+				     adev->gfx.num_compute_rings);
+
+	if (multipipe_policy) {
+		/* policy: make queues evenly cross all pipes on MEC1 only */
+		for (i = 0; i < max_queues_per_mec; i++) {
+			pipe = i % adev->gfx.mec.num_pipe_per_mec;
+			queue = (i / adev->gfx.mec.num_pipe_per_mec) %
+				adev->gfx.mec.num_queue_per_pipe;
+
+			set_bit(pipe * adev->gfx.mec.num_queue_per_pipe + queue,
+					adev->gfx.mec.queue_bitmap);
 		}
+	} else {
+		/* policy: amdgpu owns all queues in the given pipe */
+		for (i = 0; i < max_queues_per_mec; ++i)
+			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
-	/* update the number of active compute rings */
-	adev->gfx.num_compute_rings =
-		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
-
-	/* If you hit this case and edited the policy, you probably just
-	 * need to increase AMDGPU_MAX_COMPUTE_RINGS */
-	if (WARN_ON(adev->gfx.num_compute_rings > AMDGPU_MAX_COMPUTE_RINGS))
-		adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	dev_dbg(adev->dev, "mec queue bitmap weight=%d\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES));
 }
 
 void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev)
@@ -571,8 +560,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 	if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
 		schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
 	} else if (!enable && adev->gfx.gfx_off_state) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false))
+		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
 			adev->gfx.gfx_off_state = false;
+
+			if (adev->gfx.funcs->init_spm_golden) {
+				dev_dbg(adev->dev, "GFXOFF is disabled, re-init SPM golden settings\n");
+				amdgpu_gfx_init_spm_golden(adev);
+			}
+		}
 	}
 
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
@@ -724,7 +719,7 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 	 *
 	 * also don't wait anymore for IRQ context
 	 * */
-	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+	if (r < 1 && (amdgpu_in_reset(adev) || in_interrupt()))
 		goto failed_kiq_read;
 
 	might_sleep();
@@ -748,7 +743,7 @@ failed_unlock:
 failed_kiq_read:
 	if (reg_val_offs)
 		amdgpu_device_wb_free(adev, reg_val_offs);
-	pr_err("failed to read reg:%x\n", reg);
+	dev_err(adev->dev, "failed to read reg:%x\n", reg);
 	return ~0;
 }
 
@@ -782,7 +777,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 	 *
 	 * also don't wait anymore for IRQ context
 	 * */
-	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+	if (r < 1 && (amdgpu_in_reset(adev) || in_interrupt()))
 		goto failed_kiq_write;
 
 	might_sleep();
@@ -801,5 +796,5 @@ failed_undo:
 	amdgpu_ring_undo(ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_write:
-	pr_err("failed to write reg:%x\n", reg);
+	dev_err(adev->dev, "failed to write reg:%x\n", reg);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 1e7a2b0997c5..a611e78dd4ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -216,6 +216,7 @@ struct amdgpu_gfx_funcs {
 	int (*ras_error_inject)(struct amdgpu_device *adev, void *inject_if);
 	int (*query_ras_error_count) (struct amdgpu_device *adev, void *ras_error_status);
 	void (*reset_ras_error_count) (struct amdgpu_device *adev);
+	void (*init_spm_golden)(struct amdgpu_device *adev);
 };
 
 struct sq_work {
@@ -324,6 +325,7 @@ struct amdgpu_gfx {
 #define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev))
 #define amdgpu_gfx_select_se_sh(adev, se, sh, instance) (adev)->gfx.funcs->select_se_sh((adev), (se), (sh), (instance))
 #define amdgpu_gfx_select_me_pipe_q(adev, me, pipe, q, vmid) (adev)->gfx.funcs->select_me_pipe_q((adev), (me), (pipe), (q), (vmid))
+#define amdgpu_gfx_init_spm_golden(adev) (adev)->gfx.funcs->init_spm_golden((adev))
 
 /**
  * amdgpu_gfx_create_bitmask - create a bitmask
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 34cbd6f6a56b..213ef090bb0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -27,6 +27,7 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "amdgpu.h"
+#include "amdgpu_gmc.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_xgmi.h"
 
@@ -411,3 +412,64 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	}
 }
+
+void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
+				   bool enable)
+{
+	struct amdgpu_vmhub *hub;
+	u32 tmp, reg, i;
+
+	hub = &adev->vmhub[hub_type];
+	for (i = 0; i < 16; i++) {
+		reg = hub->vm_context0_cntl + hub->ctx_distance * i;
+
+		tmp = RREG32(reg);
+		if (enable)
+			tmp |= hub->vm_cntx_cntl_vm_fault;
+		else
+			tmp &= ~hub->vm_cntx_cntl_vm_fault;
+
+		WREG32(reg, tmp);
+	}
+}
+
+void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev)
+{
+	unsigned size;
+
+	/*
+	 * TODO:
+	 * Currently there is a bug where some memory client outside
+	 * of the driver writes to first 8M of VRAM on S3 resume,
+	 * this overrides GART which by default gets placed in first 8M and
+	 * causes VM_FAULTS once GTT is accessed.
+	 * Keep the stolen memory reservation until the while this is not solved.
+	 */
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+	case CHIP_RENOIR:
+		adev->mman.keep_stolen_vga_memory = true;
+		break;
+	default:
+		adev->mman.keep_stolen_vga_memory = false;
+		break;
+	}
+
+	if (!amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_DCE))
+		size = 0;
+	else
+		size = amdgpu_gmc_get_vbios_fb_size(adev);
+
+	/* set to 0 if the pre-OS buffer uses up most of vram */
+	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
+		size = 0;
+
+	if (size > AMDGPU_VBIOS_VGA_ALLOCATION) {
+		adev->mman.stolen_vga_size = AMDGPU_VBIOS_VGA_ALLOCATION;
+		adev->mman.stolen_extended_size = size - adev->mman.stolen_vga_size;
+	} else {
+		adev->mman.stolen_vga_size = size;
+		adev->mman.stolen_extended_size = 0;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index acdb61cfa24c..d61bbde4c7d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -74,6 +74,12 @@ struct amdgpu_gmc_fault {
 /*
  * VMHUB structures, functions & helpers
  */
+struct amdgpu_vmhub_funcs {
+	void (*print_l2_protection_fault_status)(struct amdgpu_device *adev,
+						 uint32_t status);
+	uint32_t (*get_invalidate_req)(unsigned int vmid, uint32_t flush_type);
+};
+
 struct amdgpu_vmhub {
 	uint32_t	ctx0_ptb_addr_lo32;
 	uint32_t	ctx0_ptb_addr_hi32;
@@ -92,6 +98,10 @@ struct amdgpu_vmhub {
 	uint32_t	ctx_addr_distance; /* include LO32/HI32 */
 	uint32_t	eng_distance;
 	uint32_t	eng_addr_distance; /* include LO32/HI32 */
+
+	uint32_t	vm_cntx_cntl_vm_fault;
+
+	const struct amdgpu_vmhub_funcs *vmhub_funcs;
 };
 
 /*
@@ -121,6 +131,8 @@ struct amdgpu_gmc_funcs {
 	void (*get_vm_pte)(struct amdgpu_device *adev,
 			   struct amdgpu_bo_va_mapping *mapping,
 			   uint64_t *flags);
+	/* get the amount of memory used by the vbios for pre-OS console */
+	unsigned int (*get_vbios_fb_size)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_xgmi {
@@ -203,7 +215,6 @@ struct amdgpu_gmc {
 	uint8_t			vram_vendor;
 	uint32_t                srbm_soft_reset;
 	bool			prt_warning;
-	uint64_t		stolen_size;
 	uint32_t		sdpif_register;
 	/* apertures */
 	u64			shared_aperture_start;
@@ -239,6 +250,7 @@ struct amdgpu_gmc {
 #define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags))
 #define amdgpu_gmc_get_vm_pde(adev, level, dst, flags) (adev)->gmc.gmc_funcs->get_vm_pde((adev), (level), (dst), (flags))
 #define amdgpu_gmc_get_vm_pte(adev, mapping, flags) (adev)->gmc.gmc_funcs->get_vm_pte((adev), (mapping), (flags))
+#define amdgpu_gmc_get_vbios_fb_size(adev) (adev)->gmc.gmc_funcs->get_vbios_fb_size((adev))
 
 /**
  * amdgpu_gmc_vram_full_visible - Check if full VRAM is visible through the BAR
@@ -289,4 +301,10 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
 extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev);
 
+extern void
+amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
+			      bool enable);
+
+void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 697bc2c6fdb2..2b1b7c136343 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -46,8 +46,9 @@ static ssize_t amdgpu_mem_info_gtt_total_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			man->size * PAGE_SIZE);
 }
@@ -64,8 +65,9 @@ static ssize_t amdgpu_mem_info_gtt_used_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_gtt_mgr_usage(man));
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index 70dbe343f51d..47cad23a6b9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -40,7 +40,7 @@
 static int amdgpu_i2c_pre_xfer(struct i2c_adapter *i2c_adap)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_get_adapdata(i2c_adap);
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t temp;
 
@@ -82,7 +82,7 @@ static int amdgpu_i2c_pre_xfer(struct i2c_adapter *i2c_adap)
 static void amdgpu_i2c_post_xfer(struct i2c_adapter *i2c_adap)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_get_adapdata(i2c_adap);
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t temp;
 
@@ -101,7 +101,7 @@ static void amdgpu_i2c_post_xfer(struct i2c_adapter *i2c_adap)
 static int amdgpu_i2c_get_clock(void *i2c_priv)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_priv;
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t val;
 
@@ -116,7 +116,7 @@ static int amdgpu_i2c_get_clock(void *i2c_priv)
 static int amdgpu_i2c_get_data(void *i2c_priv)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_priv;
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t val;
 
@@ -130,7 +130,7 @@ static int amdgpu_i2c_get_data(void *i2c_priv)
 static void amdgpu_i2c_set_clock(void *i2c_priv, int clock)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_priv;
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t val;
 
@@ -143,7 +143,7 @@ static void amdgpu_i2c_set_clock(void *i2c_priv, int clock)
 static void amdgpu_i2c_set_data(void *i2c_priv, int data)
 {
 	struct amdgpu_i2c_chan *i2c = i2c_priv;
-	struct amdgpu_device *adev = i2c->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(i2c->dev);
 	struct amdgpu_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t val;
 
@@ -253,7 +253,7 @@ void amdgpu_i2c_add(struct amdgpu_device *adev,
 		    const struct amdgpu_i2c_bus_rec *rec,
 		    const char *name)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	int i;
 
 	for (i = 0; i < AMDGPU_MAX_I2C_BUS; i++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index dcd492170598..2f53fa0ae9a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -445,7 +445,7 @@ static int amdgpu_debugfs_sa_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	seq_printf(m, "--------------------- DELAYED --------------------- \n");
 	amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_DELAYED],
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 0cc4c67f95f7..300ac73b4738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -85,7 +85,7 @@ static void amdgpu_hotplug_work_func(struct work_struct *work)
 {
 	struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
 						  hotplug_work);
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
@@ -151,7 +151,7 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev)
 irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	irqreturn_t ret;
 
 	ret = amdgpu_ih_process(adev, &adev->irq.ih);
@@ -268,9 +268,9 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 		if (!adev->enable_virtual_display)
 			/* Disable vblank IRQs aggressively for power-saving */
 			/* XXX: can this be enabled for DC? */
-			adev->ddev->vblank_disable_immediate = true;
+			adev_to_drm(adev)->vblank_disable_immediate = true;
 
-		r = drm_vblank_init(adev->ddev, adev->mode_info.num_crtc);
+		r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc);
 		if (r)
 			return r;
 
@@ -284,14 +284,14 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 
 	adev->irq.installed = true;
 	/* Use vector 0 for MSI-X */
-	r = drm_irq_install(adev->ddev, pci_irq_vector(adev->pdev, 0));
+	r = drm_irq_install(adev_to_drm(adev), pci_irq_vector(adev->pdev, 0));
 	if (r) {
 		adev->irq.installed = false;
 		if (!amdgpu_device_has_dc_support(adev))
 			flush_work(&adev->hotplug_work);
 		return r;
 	}
-	adev->ddev->max_vblank_count = 0x00ffffff;
+	adev_to_drm(adev)->max_vblank_count = 0x00ffffff;
 
 	DRM_DEBUG("amdgpu: irq initialized.\n");
 	return 0;
@@ -311,7 +311,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 	unsigned i, j;
 
 	if (adev->irq.installed) {
-		drm_irq_uninstall(adev->ddev);
+		drm_irq_uninstall(adev_to_drm(adev));
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
 			pci_free_irq_vectors(adev->pdev);
@@ -522,7 +522,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev->ddev->irq_enabled)
+	if (!adev_to_drm(adev)->irq_enabled)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -552,7 +552,7 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev->ddev->irq_enabled)
+	if (!adev_to_drm(adev)->irq_enabled)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -583,7 +583,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type)
 {
-	if (!adev->ddev->irq_enabled)
+	if (!adev_to_drm(adev)->irq_enabled)
 		return false;
 
 	if (type >= src->num_types)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 937029ad5271..dcfe8a3b03ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -251,7 +251,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	int i;
 
 	/* Signal all jobs not yet scheduled */
-	for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = &sched->sched_rq[i];
 
 		if (!rq)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 55ff071217a9..456a4a93b337 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -78,7 +78,7 @@ void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev)
  */
 void amdgpu_driver_unload_kms(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (adev == NULL)
 		return;
@@ -86,7 +86,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 	amdgpu_unregister_gpu_instance(adev);
 
 	if (adev->rmmio == NULL)
-		goto done_free;
+		return;
 
 	if (adev->runpm) {
 		pm_runtime_get_sync(dev->dev);
@@ -94,12 +94,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 	}
 
 	amdgpu_acpi_fini(adev);
-
 	amdgpu_device_fini(adev);
-
-done_free:
-	kfree(adev);
-	dev->dev_private = NULL;
 }
 
 void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
@@ -130,22 +125,18 @@ void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
 /**
  * amdgpu_driver_load_kms - Main load function for KMS.
  *
- * @dev: drm dev pointer
+ * @adev: pointer to struct amdgpu_device
  * @flags: device flags
  *
  * This is the main load function for KMS (all asics).
  * Returns 0 on success, error on failure.
  */
-int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
+int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags)
 {
-	struct amdgpu_device *adev;
+	struct drm_device *dev;
 	int r, acpi_status;
 
-	adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
-	if (adev == NULL) {
-		return -ENOMEM;
-	}
-	dev->dev_private = (void *)adev;
+	dev = adev_to_drm(adev);
 
 	if (amdgpu_has_atpx() &&
 	    (amdgpu_is_atpx_hybrid() ||
@@ -160,7 +151,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	 * properly initialize the GPU MC controller and permit
 	 * VRAM allocation
 	 */
-	r = amdgpu_device_init(adev, dev, dev->pdev, flags);
+	r = amdgpu_device_init(adev, flags);
 	if (r) {
 		dev_err(&dev->pdev->dev, "Fatal error during GPU init\n");
 		goto out;
@@ -179,6 +170,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		case CHIP_VEGA20:
 		case CHIP_ARCTURUS:
 		case CHIP_SIENNA_CICHLID:
+		case CHIP_NAVY_FLOUNDER:
 			/* enable runpm if runpm=1 */
 			if (amdgpu_runtime_pm > 0)
 				adev->runpm = true;
@@ -479,7 +471,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
  */
 static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_amdgpu_info *info = data;
 	struct amdgpu_mode_info *minfo = &adev->mode_info;
 	void __user *out = (void __user *)(uintptr_t)info->return_pointer;
@@ -681,8 +673,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		 * in the bitfields */
 		if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK)
 			se_num = 0xffffffff;
+		else if (se_num >= AMDGPU_GFX_MAX_SE)
+			return -EINVAL;
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
+		else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE)
+			return -EINVAL;
 
 		if (info->read_mmr_reg.count > 128)
 			return -EINVAL;
@@ -740,6 +736,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
 		if (amdgpu_mcbp || amdgpu_sriov_vf(adev))
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
+		if (amdgpu_is_tmz(adev))
+			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
 
 		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		vm_size -= AMDGPU_VA_RESERVED_SIZE;
@@ -993,7 +991,7 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev)
  */
 int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv;
 	int r, pasid;
 
@@ -1078,7 +1076,7 @@ pm_put:
 void amdgpu_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 	struct amdgpu_bo_list *list;
 	struct amdgpu_bo *pd;
@@ -1143,7 +1141,7 @@ u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	unsigned int pipe = crtc->index;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int vpos, hpos, stat;
 	u32 count;
 
@@ -1211,7 +1209,7 @@ int amdgpu_enable_vblank_kms(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	unsigned int pipe = crtc->index;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int idx = amdgpu_display_crtc_idx_to_irq_type(adev, pipe);
 
 	return amdgpu_irq_get(adev, &adev->crtc_irq, idx);
@@ -1228,7 +1226,7 @@ void amdgpu_disable_vblank_kms(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	unsigned int pipe = crtc->index;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int idx = amdgpu_display_crtc_idx_to_irq_type(adev, pipe);
 
 	amdgpu_irq_put(adev, &adev->crtc_irq, idx);
@@ -1264,7 +1262,7 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_amdgpu_info_firmware fw_info;
 	struct drm_amdgpu_query_fw query_fw;
 	struct atom_context *ctx = adev->mode_info.atom_context;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
index e89fb35fec71..0c43d7fe893c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
@@ -27,6 +27,19 @@ struct amdgpu_mmhub_funcs {
 	void (*query_ras_error_count)(struct amdgpu_device *adev,
 					void *ras_error_status);
 	void (*reset_ras_error_count)(struct amdgpu_device *adev);
+	u64 (*get_fb_location)(struct amdgpu_device *adev);
+	void (*init)(struct amdgpu_device *adev);
+	int (*gart_enable)(struct amdgpu_device *adev);
+	void (*set_fault_enable_default)(struct amdgpu_device *adev,
+			bool value);
+	void (*gart_disable)(struct amdgpu_device *adev);
+	int (*set_clockgating)(struct amdgpu_device *adev,
+			       enum amd_clockgating_state state);
+	void (*get_clockgating)(struct amdgpu_device *adev, u32 *flags);
+	void (*setup_vm_pt_regs)(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base);
+	void (*update_power_gating)(struct amdgpu_device *adev,
+                                bool enable);
 };
 
 struct amdgpu_mmhub {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index eaff4c4506eb..ac043baac05d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -380,6 +380,9 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	if ((*bo_ptr) == NULL)
+		return 0;
+
 	/*
 	 * Remove the original mem node and create a new one at the request
 	 * position.
@@ -558,7 +561,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
-	drm_gem_private_object_init(adev->ddev, &bo->tbo.base, size);
+	drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size);
 	INIT_LIST_HEAD(&bo->shadow_list);
 	bo->vm_bo = NULL;
 	bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain :
@@ -1305,7 +1308,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_bo_move_notify - notification about a BO being released
+ * amdgpu_bo_release_notify - notification about a BO being released
  * @bo: pointer to a buffer object
  *
  * Wipes VRAM buffers whose contents should not be leaked before the
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
index 1311d6aec5d4..69af462db34d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
@@ -226,7 +226,7 @@ static int init_pmu_by_type(struct amdgpu_device *adev,
 	pmu_entry->pmu.attr_groups = attr_groups;
 	pmu_entry->pmu_perf_type = pmu_perf_type;
 	snprintf(pmu_name, PMU_NAME_SIZE, "%s_%d",
-				pmu_file_prefix, adev->ddev->primary->index);
+				pmu_file_prefix, adev_to_drm(adev)->primary->index);
 
 	ret = perf_pmu_register(&pmu_entry->pmu, pmu_name, -1);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7fe564275457..d6c38e24f130 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -522,8 +522,7 @@ static int psp_asd_load(struct psp_context *psp)
 	 * add workaround to bypass it for sriov now.
 	 * TODO: add version check to make it common
 	 */
-	if (amdgpu_sriov_vf(psp->adev) ||
-	    (psp->adev->asic_type == CHIP_NAVY_FLOUNDER))
+	if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw)
 		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
@@ -1430,6 +1429,168 @@ static int psp_dtm_terminate(struct psp_context *psp)
 }
 // DTM end
 
+// RAP start
+static int psp_rap_init_shared_buf(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
+	 * physical) for rap ta <-> Driver
+	 */
+	ret = amdgpu_bo_create_kernel(psp->adev, PSP_RAP_SHARED_MEM_SIZE,
+				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
+				      &psp->rap_context.rap_shared_bo,
+				      &psp->rap_context.rap_shared_mc_addr,
+				      &psp->rap_context.rap_shared_buf);
+
+	return ret;
+}
+
+static int psp_rap_load(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
+	memcpy(psp->fw_pri_buf, psp->ta_rap_start_addr, psp->ta_rap_ucode_size);
+
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_rap_ucode_size,
+				 psp->rap_context.rap_shared_mc_addr,
+				 PSP_RAP_SHARED_MEM_SIZE);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	if (!ret) {
+		psp->rap_context.rap_initialized = true;
+		psp->rap_context.session_id = cmd->resp.session_id;
+		mutex_init(&psp->rap_context.mutex);
+	}
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_rap_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_unload_cmd_buf(cmd, psp->rap_context.session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_rap_initialize(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->adev->psp.ta_rap_ucode_size ||
+	    !psp->adev->psp.ta_rap_start_addr) {
+		dev_info(psp->adev->dev, "RAP: optional rap ta ucode is not available\n");
+		return 0;
+	}
+
+	if (!psp->rap_context.rap_initialized) {
+		ret = psp_rap_init_shared_buf(psp);
+		if (ret)
+			return ret;
+	}
+
+	ret = psp_rap_load(psp);
+	if (ret)
+		return ret;
+
+	ret = psp_rap_invoke(psp, TA_CMD_RAP__INITIALIZE);
+	if (ret != TA_RAP_STATUS__SUCCESS) {
+		psp_rap_unload(psp);
+
+		amdgpu_bo_free_kernel(&psp->rap_context.rap_shared_bo,
+			      &psp->rap_context.rap_shared_mc_addr,
+			      &psp->rap_context.rap_shared_buf);
+
+		psp->rap_context.rap_initialized = false;
+
+		dev_warn(psp->adev->dev, "RAP TA initialize fail.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int psp_rap_terminate(struct psp_context *psp)
+{
+	int ret;
+
+	if (!psp->rap_context.rap_initialized)
+		return 0;
+
+	ret = psp_rap_unload(psp);
+
+	psp->rap_context.rap_initialized = false;
+
+	/* free rap shared memory */
+	amdgpu_bo_free_kernel(&psp->rap_context.rap_shared_bo,
+			      &psp->rap_context.rap_shared_mc_addr,
+			      &psp->rap_context.rap_shared_buf);
+
+	return ret;
+}
+
+int psp_rap_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
+{
+	struct ta_rap_shared_memory *rap_cmd;
+	int ret;
+
+	if (!psp->rap_context.rap_initialized)
+		return -EINVAL;
+
+	if (ta_cmd_id != TA_CMD_RAP__INITIALIZE &&
+	    ta_cmd_id != TA_CMD_RAP__VALIDATE_L0)
+		return -EINVAL;
+
+	mutex_lock(&psp->rap_context.mutex);
+
+	rap_cmd = (struct ta_rap_shared_memory *)
+		  psp->rap_context.rap_shared_buf;
+	memset(rap_cmd, 0, sizeof(struct ta_rap_shared_memory));
+
+	rap_cmd->cmd_id = ta_cmd_id;
+	rap_cmd->validation_method_id = METHOD_A;
+
+	ret = psp_ta_invoke(psp, rap_cmd->cmd_id, psp->rap_context.session_id);
+	if (ret) {
+		mutex_unlock(&psp->rap_context.mutex);
+		return ret;
+	}
+
+	mutex_unlock(&psp->rap_context.mutex);
+
+	return rap_cmd->rap_status;
+}
+// RAP end
+
 static int psp_hw_start(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -1707,7 +1868,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 		return 0;
 
 
-	if (adev->in_gpu_reset && ras && ras->supported) {
+	if (amdgpu_in_reset(adev) && ras && ras->supported) {
 		ret = amdgpu_dpm_set_mp1_state(adev, PP_MP1_STATE_UNLOAD);
 		if (ret) {
 			DRM_WARN("Failed to set MP1 state prepare for reload\n");
@@ -1822,7 +1983,7 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	int ret;
 	struct psp_context *psp = &adev->psp;
 
-	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset) {
+	if (amdgpu_sriov_vf(adev) && amdgpu_in_reset(adev)) {
 		psp_ring_stop(psp, PSP_RING_TYPE__KM); /* should not destroy ring, only stop */
 		goto skip_memalloc;
 	}
@@ -1892,6 +2053,11 @@ skip_memalloc:
 		if (ret)
 			dev_err(psp->adev->dev,
 				"DTM: Failed to initialize DTM\n");
+
+		ret = psp_rap_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"RAP: Failed to initialize RAP\n");
 	}
 
 	return 0;
@@ -1942,6 +2108,7 @@ static int psp_hw_fini(void *handle)
 
 	if (psp->adev->psp.ta_fw) {
 		psp_ras_terminate(psp);
+		psp_rap_terminate(psp);
 		psp_dtm_terminate(psp);
 		psp_hdcp_terminate(psp);
 	}
@@ -2000,6 +2167,11 @@ static int psp_suspend(void *handle)
 			DRM_ERROR("Failed to terminate dtm ta\n");
 			return ret;
 		}
+		ret = psp_rap_terminate(psp);
+		if (ret) {
+			DRM_ERROR("Failed to terminate rap ta\n");
+			return ret;
+		}
 	}
 
 	ret = psp_asd_unload(psp);
@@ -2078,6 +2250,11 @@ static int psp_resume(void *handle)
 		if (ret)
 			dev_err(psp->adev->dev,
 				"DTM: Failed to initialize DTM\n");
+
+		ret = psp_rap_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"RAP: Failed to initialize RAP\n");
 	}
 
 	mutex_unlock(&adev->firmware.mutex);
@@ -2343,6 +2520,11 @@ int parse_ta_bin_descriptor(struct psp_context *psp,
 		psp->ta_dtm_ucode_size     = le32_to_cpu(desc->size_bytes);
 		psp->ta_dtm_start_addr     = ucode_start_addr;
 		break;
+	case TA_FW_TYPE_PSP_RAP:
+		psp->ta_rap_ucode_version  = le32_to_cpu(desc->fw_version);
+		psp->ta_rap_ucode_size     = le32_to_cpu(desc->size_bytes);
+		psp->ta_rap_start_addr     = ucode_start_addr;
+		break;
 	default:
 		dev_warn(psp->adev->dev, "Unsupported TA type: %d\n", desc->fw_type);
 		break;
@@ -2421,7 +2603,7 @@ static ssize_t psp_usbc_pd_fw_sysfs_read(struct device *dev,
 					 char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t fw_ver;
 	int ret;
 
@@ -2448,7 +2630,7 @@ static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev,
 						       size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	void *cpu_addr;
 	dma_addr_t dma_addr;
 	int ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 623888bf30cb..919d2fb7427b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -29,6 +29,7 @@
 #include "psp_gfx_if.h"
 #include "ta_xgmi_if.h"
 #include "ta_ras_if.h"
+#include "ta_rap_if.h"
 
 #define PSP_FENCE_BUFFER_SIZE	0x1000
 #define PSP_CMD_BUFFER_SIZE	0x1000
@@ -38,6 +39,7 @@
 #define PSP_TMR_SIZE	0x400000
 #define PSP_HDCP_SHARED_MEM_SIZE	0x4000
 #define PSP_DTM_SHARED_MEM_SIZE	0x4000
+#define PSP_RAP_SHARED_MEM_SIZE	0x4000
 #define PSP_SHARED_MEM_SIZE		0x4000
 
 struct psp_context;
@@ -159,6 +161,15 @@ struct psp_dtm_context {
 	struct mutex		mutex;
 };
 
+struct psp_rap_context {
+	bool			rap_initialized;
+	uint32_t		session_id;
+	struct amdgpu_bo	*rap_shared_bo;
+	uint64_t		rap_shared_mc_addr;
+	void			*rap_shared_buf;
+	struct mutex		mutex;
+};
+
 #define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
 #define GDDR6_MEM_TRAINING_DATA_SIZE_IN_BYTES	0x1000
 #define GDDR6_MEM_TRAINING_OFFSET		0x8000
@@ -277,11 +288,16 @@ struct psp_context
 	uint32_t			ta_dtm_ucode_size;
 	uint8_t				*ta_dtm_start_addr;
 
+	uint32_t			ta_rap_ucode_version;
+	uint32_t			ta_rap_ucode_size;
+	uint8_t				*ta_rap_start_addr;
+
 	struct psp_asd_context		asd_context;
 	struct psp_xgmi_context		xgmi_context;
 	struct psp_ras_context		ras;
 	struct psp_hdcp_context 	hdcp_context;
 	struct psp_dtm_context		dtm_context;
+	struct psp_rap_context		rap_context;
 	struct mutex			mutex;
 	struct psp_memory_training_context mem_train_ctx;
 };
@@ -357,6 +373,7 @@ int psp_ras_trigger_error(struct psp_context *psp,
 
 int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
+int psp_rap_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 
 int psp_rlc_autoload_start(struct psp_context *psp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
new file mode 100644
index 000000000000..8da5356c36f1
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/pm_runtime.h>
+
+#include "amdgpu.h"
+#include "amdgpu_rap.h"
+
+/**
+ * DOC: AMDGPU RAP debugfs test interface
+ *
+ * how to use?
+ * echo opcode > <debugfs_dir>/dri/xxx/rap_test
+ *
+ * opcode:
+ * currently, only 2 is supported by Linux host driver,
+ * opcode 2 stands for TA_CMD_RAP__VALIDATE_L0, used to
+ * trigger L0 policy validation, you can refer more detail
+ * from header file ta_rap_if.h
+ *
+ */
+static ssize_t amdgpu_rap_debugfs_write(struct file *f, const char __user *buf,
+		size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	struct ta_rap_shared_memory *rap_shared_mem;
+	struct ta_rap_cmd_output_data *rap_cmd_output;
+	struct drm_device *dev = adev_to_drm(adev);
+	uint32_t op;
+	int ret;
+
+	if (*pos || size != 2)
+		return -EINVAL;
+
+	ret = kstrtouint_from_user(buf, size, *pos, &op);
+	if (ret)
+		return ret;
+
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
+		return ret;
+	}
+
+	/* make sure gfx core is on, RAP TA cann't handle
+	 * GFX OFF case currently.
+	 */
+	amdgpu_gfx_off_ctrl(adev, false);
+
+	switch (op) {
+	case 2:
+		ret = psp_rap_invoke(&adev->psp, op);
+
+		if (ret == TA_RAP_STATUS__SUCCESS) {
+			dev_info(adev->dev, "RAP L0 validate test success.\n");
+		} else {
+			rap_shared_mem = (struct ta_rap_shared_memory *)
+					 adev->psp.rap_context.rap_shared_buf;
+			rap_cmd_output = &(rap_shared_mem->rap_out_message.output);
+
+			dev_info(adev->dev, "RAP test failed, the output is:\n");
+			dev_info(adev->dev, "\tlast_subsection: 0x%08x.\n",
+				 rap_cmd_output->last_subsection);
+			dev_info(adev->dev, "\tnum_total_validate: 0x%08x.\n",
+				 rap_cmd_output->num_total_validate);
+			dev_info(adev->dev, "\tnum_valid: 0x%08x.\n",
+				 rap_cmd_output->num_valid);
+			dev_info(adev->dev, "\tlast_validate_addr: 0x%08x.\n",
+				 rap_cmd_output->last_validate_addr);
+			dev_info(adev->dev, "\tlast_validate_val: 0x%08x.\n",
+				 rap_cmd_output->last_validate_val);
+			dev_info(adev->dev, "\tlast_validate_val_exptd: 0x%08x.\n",
+				 rap_cmd_output->last_validate_val_exptd);
+		}
+		break;
+	default:
+		dev_info(adev->dev, "Unsupported op id: %d, ", op);
+		dev_info(adev->dev, "Only support op 2(L0 validate test).\n");
+	}
+
+	amdgpu_gfx_off_ctrl(adev, true);
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
+	return size;
+}
+
+static const struct file_operations amdgpu_rap_debugfs_ops = {
+	.owner = THIS_MODULE,
+	.read = NULL,
+	.write = amdgpu_rap_debugfs_write,
+	.llseek = default_llseek
+};
+
+void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
+{
+#if defined(CONFIG_DEBUG_FS)
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
+
+	if (!adev->psp.rap_context.rap_initialized)
+		return;
+
+	debugfs_create_file("rap_test", S_IWUSR, minor->debugfs_root,
+				adev, &amdgpu_rap_debugfs_ops);
+#endif
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.h
new file mode 100644
index 000000000000..ec6d7632d3a0
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ */
+#ifndef _AMDGPU_RAP_H
+#define _AMDGPU_RAP_H
+
+#include "amdgpu.h"
+
+void amdgpu_rap_debugfs_init(struct amdgpu_device *adev);
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index bcce4c0be462..e5ea14774c0c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -34,6 +34,8 @@
 #include "amdgpu_xgmi.h"
 #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 
+static const char *RAS_FS_NAME = "ras";
+
 const char *ras_error_string[] = {
 	"none",
 	"parity",
@@ -62,13 +64,14 @@ const char *ras_block_string[] = {
 #define ras_err_str(i) (ras_error_string[ffs(i)])
 #define ras_block_str(i) (ras_block_string[i])
 
-#define AMDGPU_RAS_FLAG_INIT_BY_VBIOS		1
-#define AMDGPU_RAS_FLAG_INIT_NEED_RESET		2
 #define RAS_DEFAULT_FLAGS (AMDGPU_RAS_FLAG_INIT_BY_VBIOS)
 
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
+/* typical ECC bad page rate(1 bad page per 100MB VRAM) */
+#define RAS_BAD_PAGE_RATE		(100 * 1024 * 1024ULL)
+
 enum amdgpu_ras_retire_page_reservation {
 	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 	AMDGPU_RAS_RETIRE_PAGE_PENDING,
@@ -367,12 +370,19 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 static ssize_t amdgpu_ras_debugfs_eeprom_write(struct file *f, const char __user *buf,
 		size_t size, loff_t *pos)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	struct amdgpu_device *adev =
+		(struct amdgpu_device *)file_inode(f)->i_private;
 	int ret;
 
-	ret = amdgpu_ras_eeprom_reset_table(&adev->psp.ras.ras->eeprom_control);
+	ret = amdgpu_ras_eeprom_reset_table(
+			&(amdgpu_ras_get_context(adev)->eeprom_control));
 
-	return ret == 1 ? size : -EIO;
+	if (ret == 1) {
+		amdgpu_ras_get_context(adev)->flags = RAS_DEFAULT_FLAGS;
+		return size;
+	} else {
+		return -EIO;
+	}
 }
 
 static const struct file_operations amdgpu_ras_debugfs_ctrl_ops = {
@@ -1017,6 +1027,33 @@ static ssize_t amdgpu_ras_sysfs_features_read(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "feature mask: 0x%x\n", con->features);
 }
 
+static void amdgpu_ras_sysfs_add_bad_page_node(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct attribute_group group;
+	struct bin_attribute *bin_attrs[] = {
+		&con->badpages_attr,
+		NULL,
+	};
+
+	con->badpages_attr = (struct bin_attribute) {
+		.attr = {
+			.name = "gpu_vram_bad_pages",
+			.mode = S_IRUGO,
+		},
+		.size = 0,
+		.private = NULL,
+		.read = amdgpu_ras_sysfs_badpages_read,
+	};
+
+	group.name = RAS_FS_NAME;
+	group.bin_attrs = bin_attrs;
+
+	sysfs_bin_attr_init(bin_attrs[0]);
+
+	sysfs_update_group(&adev->dev->kobj, &group);
+}
+
 static int amdgpu_ras_sysfs_create_feature_node(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -1024,14 +1061,9 @@ static int amdgpu_ras_sysfs_create_feature_node(struct amdgpu_device *adev)
 		&con->features_attr.attr,
 		NULL
 	};
-	struct bin_attribute *bin_attrs[] = {
-		&con->badpages_attr,
-		NULL
-	};
 	struct attribute_group group = {
-		.name = "ras",
+		.name = RAS_FS_NAME,
 		.attrs = attrs,
-		.bin_attrs = bin_attrs,
 	};
 
 	con->features_attr = (struct device_attribute) {
@@ -1042,22 +1074,20 @@ static int amdgpu_ras_sysfs_create_feature_node(struct amdgpu_device *adev)
 			.show = amdgpu_ras_sysfs_features_read,
 	};
 
-	con->badpages_attr = (struct bin_attribute) {
-		.attr = {
-			.name = "gpu_vram_bad_pages",
-			.mode = S_IRUGO,
-		},
-		.size = 0,
-		.private = NULL,
-		.read = amdgpu_ras_sysfs_badpages_read,
-	};
-
 	sysfs_attr_init(attrs[0]);
-	sysfs_bin_attr_init(bin_attrs[0]);
 
 	return sysfs_create_group(&adev->dev->kobj, &group);
 }
 
+static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	sysfs_remove_file_from_group(&adev->dev->kobj,
+				&con->badpages_attr.attr,
+				RAS_FS_NAME);
+}
+
 static int amdgpu_ras_sysfs_remove_feature_node(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -1065,14 +1095,9 @@ static int amdgpu_ras_sysfs_remove_feature_node(struct amdgpu_device *adev)
 		&con->features_attr.attr,
 		NULL
 	};
-	struct bin_attribute *bin_attrs[] = {
-		&con->badpages_attr,
-		NULL
-	};
 	struct attribute_group group = {
-		.name = "ras",
+		.name = RAS_FS_NAME,
 		.attrs = attrs,
-		.bin_attrs = bin_attrs,
 	};
 
 	sysfs_remove_group(&adev->dev->kobj, &group);
@@ -1105,7 +1130,7 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev,
 
 	if (sysfs_add_file_to_group(&adev->dev->kobj,
 				&obj->sysfs_attr.attr,
-				"ras")) {
+				RAS_FS_NAME)) {
 		put_obj(obj);
 		return -EINVAL;
 	}
@@ -1125,7 +1150,7 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev,
 
 	sysfs_remove_file_from_group(&adev->dev->kobj,
 				&obj->sysfs_attr.attr,
-				"ras");
+				RAS_FS_NAME);
 	obj->attr_inuse = 0;
 	put_obj(obj);
 
@@ -1141,6 +1166,9 @@ static int amdgpu_ras_sysfs_remove_all(struct amdgpu_device *adev)
 		amdgpu_ras_sysfs_remove(adev, &obj->head);
 	}
 
+	if (amdgpu_bad_page_threshold != 0)
+		amdgpu_ras_sysfs_remove_bad_page_node(adev);
+
 	amdgpu_ras_sysfs_remove_feature_node(adev);
 
 	return 0;
@@ -1169,9 +1197,9 @@ static int amdgpu_ras_sysfs_remove_all(struct amdgpu_device *adev)
 static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	struct drm_minor *minor = adev->ddev->primary;
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
 
-	con->dir = debugfs_create_dir("ras", minor->debugfs_root);
+	con->dir = debugfs_create_dir(RAS_FS_NAME, minor->debugfs_root);
 	debugfs_create_file("ras_ctrl", S_IWUGO | S_IRUGO, con->dir,
 				adev, &amdgpu_ras_debugfs_ctrl_ops);
 	debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO, con->dir,
@@ -1187,6 +1215,13 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 	 */
 	debugfs_create_bool("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
 				&con->reboot);
+
+	/*
+	 * User could set this not to clean up hardware's error count register
+	 * of RAS IPs during ras recovery.
+	 */
+	debugfs_create_bool("disable_ras_err_cnt_harvest", 0644,
+			con->dir, &con->disable_ras_err_cnt_harvest);
 }
 
 void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
@@ -1211,6 +1246,7 @@ void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
 
 void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev)
 {
+#if defined(CONFIG_DEBUG_FS)
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_manager *obj;
 	struct ras_fs_if fs_info;
@@ -1233,6 +1269,7 @@ void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev)
 			amdgpu_ras_debugfs_create(adev, &fs_info);
 		}
 	}
+#endif
 }
 
 void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
@@ -1243,13 +1280,13 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
 	if (!obj || !obj->ent)
 		return;
 
-	debugfs_remove(obj->ent);
 	obj->ent = NULL;
 	put_obj(obj);
 }
 
 static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 {
+#if defined(CONFIG_DEBUG_FS)
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_manager *obj, *tmp;
 
@@ -1257,8 +1294,8 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 		amdgpu_ras_debugfs_remove(adev, &obj->head);
 	}
 
-	debugfs_remove_recursive(con->dir);
 	con->dir = NULL;
+#endif
 }
 /* debugfs end */
 
@@ -1268,6 +1305,9 @@ static int amdgpu_ras_fs_init(struct amdgpu_device *adev)
 {
 	amdgpu_ras_sysfs_create_feature_node(adev);
 
+	if (amdgpu_bad_page_threshold != 0)
+		amdgpu_ras_sysfs_add_bad_page_node(adev);
+
 	return 0;
 }
 
@@ -1514,23 +1554,28 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 	struct amdgpu_device *remote_adev = NULL;
 	struct amdgpu_device *adev = ras->adev;
 	struct list_head device_list, *device_list_handle =  NULL;
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false);
-
-	/* Build list of devices to query RAS related errors */
-	if  (hive && adev->gmc.xgmi.num_physical_nodes > 1)
-		device_list_handle = &hive->device_list;
-	else {
-		INIT_LIST_HEAD(&device_list);
-		list_add_tail(&adev->gmc.xgmi.head, &device_list);
-		device_list_handle = &device_list;
-	}
 
-	list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) {
-		amdgpu_ras_log_on_err_counter(remote_adev);
+	if (!ras->disable_ras_err_cnt_harvest) {
+		struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
+
+		/* Build list of devices to query RAS related errors */
+		if  (hive && adev->gmc.xgmi.num_physical_nodes > 1) {
+			device_list_handle = &hive->device_list;
+		} else {
+			INIT_LIST_HEAD(&device_list);
+			list_add_tail(&adev->gmc.xgmi.head, &device_list);
+			device_list_handle = &device_list;
+		}
+
+		list_for_each_entry(remote_adev,
+				device_list_handle, gmc.xgmi.head)
+			amdgpu_ras_log_on_err_counter(remote_adev);
+
+		amdgpu_put_xgmi_hive(hive);
 	}
 
 	if (amdgpu_device_should_recover_gpu(ras->adev))
-		amdgpu_device_gpu_recover(ras->adev, 0);
+		amdgpu_device_gpu_recover(ras->adev, NULL);
 	atomic_set(&ras->in_recovery, 0);
 }
 
@@ -1645,7 +1690,7 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 	int ret = 0;
 
 	/* no bad page record, skip eeprom access */
-	if (!control->num_recs)
+	if (!control->num_recs || (amdgpu_bad_page_threshold == 0))
 		return ret;
 
 	bps = kcalloc(control->num_recs, sizeof(*bps), GFP_KERNEL);
@@ -1699,6 +1744,47 @@ out:
 	return ret;
 }
 
+static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
+					uint32_t max_length)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	int tmp_threshold = amdgpu_bad_page_threshold;
+	u64 val;
+
+	/*
+	 * Justification of value bad_page_cnt_threshold in ras structure
+	 *
+	 * Generally, -1 <= amdgpu_bad_page_threshold <= max record length
+	 * in eeprom, and introduce two scenarios accordingly.
+	 *
+	 * Bad page retirement enablement:
+	 *    - If amdgpu_bad_page_threshold = -1,
+	 *      bad_page_cnt_threshold = typical value by formula.
+	 *
+	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <
+	 *      max record length in eeprom, use it directly.
+	 *
+	 * Bad page retirement disablement:
+	 *    - If amdgpu_bad_page_threshold = 0, bad page retirement
+	 *      functionality is disabled, and bad_page_cnt_threshold will
+	 *      take no effect.
+	 */
+
+	if (tmp_threshold < -1)
+		tmp_threshold = -1;
+	else if (tmp_threshold > max_length)
+		tmp_threshold = max_length;
+
+	if (tmp_threshold == -1) {
+		val = adev->gmc.mc_vram_size;
+		do_div(val, RAS_BAD_PAGE_RATE);
+		con->bad_page_cnt_threshold = min(lower_32_bits(val),
+						max_length);
+	} else {
+		con->bad_page_cnt_threshold = tmp_threshold;
+	}
+}
+
 /* called in gpu recovery/init */
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 {
@@ -1708,7 +1794,8 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 	struct amdgpu_bo *bo = NULL;
 	int i, ret = 0;
 
-	if (!con || !con->eh_data)
+	/* Not reserve bad page when amdgpu_bad_page_threshold == 0. */
+	if (!con || !con->eh_data || (amdgpu_bad_page_threshold == 0))
 		return 0;
 
 	mutex_lock(&con->recovery_lock);
@@ -1776,6 +1863,8 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data **data;
+	uint32_t max_eeprom_records_len = 0;
+	bool exc_err_limit = false;
 	int ret;
 
 	if (con)
@@ -1794,8 +1883,15 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	atomic_set(&con->in_recovery, 0);
 	con->adev = adev;
 
-	ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
-	if (ret)
+	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
+	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
+
+	ret = amdgpu_ras_eeprom_init(&con->eeprom_control, &exc_err_limit);
+	/*
+	 * This calling fails when exc_err_limit is true or
+	 * ret != 0.
+	 */
+	if (exc_err_limit || ret)
 		goto free;
 
 	if (con->eeprom_control.num_recs) {
@@ -1819,6 +1915,15 @@ free:
 out:
 	dev_warn(adev->dev, "Failed to initialize ras recovery!\n");
 
+	/*
+	 * Except error threshold exceeding case, other failure cases in this
+	 * function would not fail amdgpu driver init.
+	 */
+	if (!exc_err_limit)
+		ret = 0;
+	else
+		ret = -EINVAL;
+
 	return ret;
 }
 
@@ -1858,6 +1963,17 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int amdgpu_ras_check_asic_type(struct amdgpu_device *adev)
+{
+	if (adev->asic_type != CHIP_VEGA10 &&
+		adev->asic_type != CHIP_VEGA20 &&
+		adev->asic_type != CHIP_ARCTURUS &&
+		adev->asic_type != CHIP_SIENNA_CICHLID)
+		return 1;
+	else
+		return 0;
+}
+
 /*
  * check hardware's ras ability which will be saved in hw_supported.
  * if hardware does not support ras, we can skip some ras initializtion and
@@ -1874,8 +1990,7 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 	*supported = 0;
 
 	if (amdgpu_sriov_vf(adev) || !adev->is_atom_fw ||
-	    (adev->asic_type != CHIP_VEGA20 &&
-	     adev->asic_type != CHIP_ARCTURUS))
+		amdgpu_ras_check_asic_type(adev))
 		return;
 
 	if (amdgpu_atomfirmware_mem_ecc_supported(adev)) {
@@ -1897,6 +2012,7 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 
 	*supported = amdgpu_ras_enable == 0 ?
 			0 : *hw_supported & amdgpu_ras_mask;
+	adev->ras_features = *supported;
 }
 
 int amdgpu_ras_init(struct amdgpu_device *adev)
@@ -1919,9 +2035,9 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 
 	amdgpu_ras_check_supported(adev, &con->hw_supported,
 			&con->supported);
-	if (!con->hw_supported) {
+	if (!con->hw_supported || (adev->asic_type == CHIP_VEGA10)) {
 		r = 0;
-		goto err_out;
+		goto release_con;
 	}
 
 	con->features = 0;
@@ -1932,25 +2048,25 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	if (adev->nbio.funcs->init_ras_controller_interrupt) {
 		r = adev->nbio.funcs->init_ras_controller_interrupt(adev);
 		if (r)
-			goto err_out;
+			goto release_con;
 	}
 
 	if (adev->nbio.funcs->init_ras_err_event_athub_interrupt) {
 		r = adev->nbio.funcs->init_ras_err_event_athub_interrupt(adev);
 		if (r)
-			goto err_out;
+			goto release_con;
 	}
 
 	if (amdgpu_ras_fs_init(adev)) {
 		r = -EINVAL;
-		goto err_out;
+		goto release_con;
 	}
 
 	dev_info(adev->dev, "RAS INFO: ras initialized successfully, "
 			"hardware ability[%x] ras_mask[%x]\n",
 			con->hw_supported, con->supported);
 	return 0;
-err_out:
+release_con:
 	amdgpu_ras_set_context(adev, NULL);
 	kfree(con);
 
@@ -1978,7 +2094,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev,
 			amdgpu_ras_request_reset_on_boot(adev,
 					ras_block->block);
 			return 0;
-		} else if (adev->in_suspend || adev->in_gpu_reset) {
+		} else if (adev->in_suspend || amdgpu_in_reset(adev)) {
 			/* in resume phase, if fail to enable ras,
 			 * clean up all ras fs nodes, and disable ras */
 			goto cleanup;
@@ -1987,7 +2103,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev,
 	}
 
 	/* in resume phase, no need to create ras fs node */
-	if (adev->in_suspend || adev->in_gpu_reset)
+	if (adev->in_suspend || amdgpu_in_reset(adev))
 		return 0;
 
 	if (ih_info->cb) {
@@ -2145,3 +2261,19 @@ bool amdgpu_ras_need_emergency_restart(struct amdgpu_device *adev)
 
 	return false;
 }
+
+bool amdgpu_ras_check_err_threshold(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	bool exc_err_limit = false;
+
+	if (con && (amdgpu_bad_page_threshold != 0))
+		amdgpu_ras_eeprom_check_err_threshold(&con->eeprom_control,
+						&exc_err_limit);
+
+	/*
+	 * We are only interested in variable exc_err_limit,
+	 * as it says if GPU is in bad state or not.
+	 */
+	return exc_err_limit;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index b2667342cf67..6b8d7bb83bb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -31,6 +31,10 @@
 #include "ta_ras_if.h"
 #include "amdgpu_ras_eeprom.h"
 
+#define AMDGPU_RAS_FLAG_INIT_BY_VBIOS		(0x1 << 0)
+#define AMDGPU_RAS_FLAG_INIT_NEED_RESET		(0x1 << 1)
+#define AMDGPU_RAS_FLAG_SKIP_BAD_PAGE_RESV	(0x1 << 2)
+
 enum amdgpu_ras_block {
 	AMDGPU_RAS_BLOCK__UMC = 0,
 	AMDGPU_RAS_BLOCK__SDMA,
@@ -336,6 +340,12 @@ struct amdgpu_ras {
 	struct amdgpu_ras_eeprom_control eeprom_control;
 
 	bool error_query_ready;
+
+	/* bad page count threshold */
+	uint32_t bad_page_cnt_threshold;
+
+	/* disable ras error count harvest in recovery */
+	bool disable_ras_err_cnt_harvest;
 };
 
 struct ras_fs_data {
@@ -490,6 +500,8 @@ void amdgpu_ras_suspend(struct amdgpu_device *adev);
 unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 		bool is_ce);
 
+bool amdgpu_ras_check_err_threshold(struct amdgpu_device *adev);
+
 /* error handling functions */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 		struct eeprom_table_record *bps, int pages);
@@ -500,10 +512,14 @@ static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
-	/* save bad page to eeprom before gpu reset,
-	 * i2c may be unstable in gpu reset
+	/*
+	 * Save bad page to eeprom before gpu reset, i2c may be unstable
+	 * in gpu reset.
+	 *
+	 * Also, exclude the case when ras recovery issuer is
+	 * eeprom page write itself.
 	 */
-	if (in_task())
+	if (!(ras->flags & AMDGPU_RAS_FLAG_SKIP_BAD_PAGE_RESV) && in_task())
 		amdgpu_ras_reserve_bad_pages(adev);
 
 	if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index c0096097bbcf..0e64c39a2372 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -46,6 +46,9 @@
 #define EEPROM_TABLE_HDR_VAL 0x414d4452
 #define EEPROM_TABLE_VER 0x00010000
 
+/* Bad GPU tag ‘BADG’ */
+#define EEPROM_TABLE_HDR_BAD 0x42414447
+
 /* Assume 2 Mbit size */
 #define EEPROM_SIZE_BYTES 256000
 #define EEPROM_PAGE__SIZE_BYTES 256
@@ -56,6 +59,15 @@
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_ras, eeprom_control))->adev
 
+static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
+{
+	if ((adev->asic_type == CHIP_VEGA20) ||
+	    (adev->asic_type == CHIP_ARCTURUS))
+		return true;
+
+	return false;
+}
+
 static bool __get_eeprom_i2c_addr_arct(struct amdgpu_device *adev,
 				       uint16_t *i2c_addr)
 {
@@ -213,6 +225,24 @@ static bool __validate_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
 	return true;
 }
 
+static int amdgpu_ras_eeprom_correct_header_tag(
+				struct amdgpu_ras_eeprom_control *control,
+				uint32_t header)
+{
+	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE];
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	int ret = 0;
+
+	memset(buff, 0, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE);
+
+	mutex_lock(&control->tbl_mutex);
+	hdr->header = header;
+	ret = __update_table_header(control, buff);
+	mutex_unlock(&control->tbl_mutex);
+
+	return ret;
+}
+
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 {
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
@@ -238,12 +268,14 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 
 }
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *exceed_err_limit)
 {
 	int ret = 0;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	struct i2c_msg msg = {
 			.addr	= 0,
 			.flags	= I2C_M_RD,
@@ -251,6 +283,11 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 			.buf	= buff,
 	};
 
+	*exceed_err_limit = false;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
 	/* Verify i2c adapter is initialized */
 	if (!adev->pm.smu_i2c.algo)
 		return -ENOENT;
@@ -279,6 +316,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->num_recs);
 
+	} else if ((hdr->header == EEPROM_TABLE_HDR_BAD) &&
+			(amdgpu_bad_page_threshold != 0)) {
+		if (ras->bad_page_cnt_threshold > control->num_recs) {
+			dev_info(adev->dev, "Using one valid bigger bad page "
+				"threshold and correcting eeprom header tag.\n");
+			ret = amdgpu_ras_eeprom_correct_header_tag(control,
+							EEPROM_TABLE_HDR_VAL);
+		} else {
+			*exceed_err_limit = true;
+			dev_err(adev->dev, "Exceeding the bad_page_threshold parameter, "
+				"disabling the GPU.\n");
+		}
 	} else {
 		DRM_INFO("Creating new EEPROM table");
 
@@ -375,6 +424,49 @@ static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
 	return curr_address;
 }
 
+int amdgpu_ras_eeprom_check_err_threshold(
+				struct amdgpu_ras_eeprom_control *control,
+				bool *exceed_err_limit)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	unsigned char buff[EEPROM_ADDRESS_SIZE +
+			EEPROM_TABLE_HEADER_SIZE] = { 0 };
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct i2c_msg msg = {
+			.addr = control->i2c_address,
+			.flags = I2C_M_RD,
+			.len = EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
+			.buf = buff,
+	};
+	int ret;
+
+	*exceed_err_limit = false;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
+	/* read EEPROM table header */
+	mutex_lock(&control->tbl_mutex);
+	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	if (ret < 1) {
+		dev_err(adev->dev, "Failed to read EEPROM table header.\n");
+		goto err;
+	}
+
+	__decode_table_header_from_buff(hdr, &buff[2]);
+
+	if (hdr->header == EEPROM_TABLE_HDR_BAD) {
+		dev_warn(adev->dev, "This GPU is in BAD status.");
+		dev_warn(adev->dev, "Please retire it or setting one bigger "
+				"threshold value when reloading driver.\n");
+		*exceed_err_limit = true;
+	}
+
+err:
+	mutex_unlock(&control->tbl_mutex);
+	return 0;
+}
+
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
@@ -383,10 +475,12 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 	int i, ret = 0;
 	struct i2c_msg *msgs, *msg;
 	unsigned char *buffs, *buff;
+	bool sched_ras_recovery = false;
 	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
-	if (adev->asic_type != CHIP_VEGA20 && adev->asic_type != CHIP_ARCTURUS)
+	if (!__is_ras_eeprom_supported(adev))
 		return 0;
 
 	buffs = kcalloc(num, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE,
@@ -402,11 +496,30 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		goto free_buff;
 	}
 
+	/*
+	 * If saved bad pages number exceeds the bad page threshold for
+	 * the whole VRAM, update table header to mark the BAD GPU tag
+	 * and schedule one ras recovery after eeprom write is done,
+	 * this can avoid the missing for latest records.
+	 *
+	 * This new header will be picked up and checked in the bootup
+	 * by ras recovery, which may break bootup process to notify
+	 * user this GPU is in bad state and to retire such GPU for
+	 * further check.
+	 */
+	if (write && (amdgpu_bad_page_threshold != 0) &&
+		((control->num_recs + num) >= ras->bad_page_cnt_threshold)) {
+		dev_warn(adev->dev,
+			"Saved bad pages(%d) reaches threshold value(%d).\n",
+			control->num_recs + num, ras->bad_page_cnt_threshold);
+		control->tbl_hdr.header = EEPROM_TABLE_HDR_BAD;
+		sched_ras_recovery = true;
+	}
+
 	/* In case of overflow just start from beginning to not lose newest records */
 	if (write && (control->next_addr + EEPROM_TABLE_RECORD_SIZE * num > EEPROM_SIZE_BYTES))
 		control->next_addr = EEPROM_RECORD_START;
 
-
 	/*
 	 * TODO Currently makes EEPROM writes for each record, this creates
 	 * internal fragmentation. Optimized the code to do full page write of
@@ -482,6 +595,20 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		__update_tbl_checksum(control, records, num, old_hdr_byte_sum);
 
 		__update_table_header(control, buffs);
+
+		if (sched_ras_recovery) {
+			/*
+			 * Before scheduling ras recovery, assert the related
+			 * flag first, which shall bypass common bad page
+			 * reservation execution in amdgpu_ras_reset_gpu.
+			 */
+			amdgpu_ras_get_context(adev)->flags |=
+				AMDGPU_RAS_FLAG_SKIP_BAD_PAGE_RESV;
+
+			dev_warn(adev->dev, "Conduct ras recovery due to bad "
+				"page threshold reached.\n");
+			amdgpu_ras_reset_gpu(adev);
+		}
 	} else if (!__validate_tbl_checksum(control, records, num)) {
 		DRM_WARN("EEPROM Table checksum mismatch!");
 		/* TODO Uncomment when EEPROM read/write is relliable */
@@ -499,6 +626,11 @@ free_buff:
 	return ret == num ? 0 : -EIO;
 }
 
+inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void)
+{
+	return EEPROM_MAX_RECORD_NUM;
+}
+
 /* Used for testing if bugs encountered */
 #if 0
 void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index 9e7d640920fb..c7a5e5c7c61e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -76,14 +76,21 @@ struct eeprom_table_record {
 	unsigned char mcumc_id;
 }__attribute__((__packed__));
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control);
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *exceed_err_limit);
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control);
 
+int amdgpu_ras_eeprom_check_err_threshold(
+				struct amdgpu_ras_eeprom_control *control,
+				bool *exceed_err_limit);
+
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
 					    int num);
 
+inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void);
+
 void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control);
 
 #endif // _AMDGPU_RAS_EEPROM_H
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 13ea8ebc421c..15ee13c3bd9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -267,7 +267,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			&ring->sched;
 	}
 
-	for (i = 0; i < DRM_SCHED_PRIORITY_MAX; ++i)
+	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; ++i)
 		atomic_set(&ring->num_jobs[i], 0);
 
 	return 0;
@@ -420,7 +420,7 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 			     struct amdgpu_ring *ring)
 {
 #if defined(CONFIG_DEBUG_FS)
-	struct drm_minor *minor = adev->ddev->primary;
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *ent, *root = minor->debugfs_root;
 	char name[32];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index da871d84b742..7112137689db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -243,7 +243,7 @@ struct amdgpu_ring {
 	bool			has_compute_vm_bug;
 	bool			no_scheduler;
 
-	atomic_t		num_jobs[DRM_SCHED_PRIORITY_MAX];
+	atomic_t		num_jobs[DRM_SCHED_PRIORITY_COUNT];
 	struct mutex		priority_mutex;
 	/* protected by priority_mutex */
 	int			priority;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index c799691dfa84..0da0a0d98672 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -32,24 +32,32 @@
 
 #include "amdgpu_vm.h"
 
-enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+int amdgpu_to_sched_priority(int amdgpu_priority,
+			     enum drm_sched_priority *prio)
 {
 	switch (amdgpu_priority) {
 	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH_HW;
+		*prio = DRM_SCHED_PRIORITY_HIGH;
+		break;
 	case AMDGPU_CTX_PRIORITY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH_SW;
+		*prio = DRM_SCHED_PRIORITY_HIGH;
+		break;
 	case AMDGPU_CTX_PRIORITY_NORMAL:
-		return DRM_SCHED_PRIORITY_NORMAL;
+		*prio = DRM_SCHED_PRIORITY_NORMAL;
+		break;
 	case AMDGPU_CTX_PRIORITY_LOW:
 	case AMDGPU_CTX_PRIORITY_VERY_LOW:
-		return DRM_SCHED_PRIORITY_LOW;
+		*prio = DRM_SCHED_PRIORITY_MIN;
+		break;
 	case AMDGPU_CTX_PRIORITY_UNSET:
-		return DRM_SCHED_PRIORITY_UNSET;
+		*prio = DRM_SCHED_PRIORITY_UNSET;
+		break;
 	default:
 		WARN(1, "Invalid context priority %d\n", amdgpu_priority);
-		return DRM_SCHED_PRIORITY_INVALID;
+		return -EINVAL;
 	}
+
+	return 0;
 }
 
 static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
@@ -115,13 +123,24 @@ int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp)
 {
 	union drm_amdgpu_sched *args = data;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	enum drm_sched_priority priority;
 	int r;
 
-	priority = amdgpu_to_sched_priority(args->in.priority);
-	if (priority == DRM_SCHED_PRIORITY_INVALID)
+	/* First check the op, then the op's argument.
+	 */
+	switch (args->in.op) {
+	case AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE:
+	case AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE:
+		break;
+	default:
+		DRM_ERROR("Invalid sched op specified: %d\n", args->in.op);
 		return -EINVAL;
+	}
+
+	r = amdgpu_to_sched_priority(args->in.priority, &priority);
+	if (r)
+		return r;
 
 	switch (args->in.op) {
 	case AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE:
@@ -136,7 +155,8 @@ int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 							   priority);
 		break;
 	default:
-		DRM_ERROR("Invalid sched op specified: %d\n", args->in.op);
+		/* Impossible.
+		 */
 		r = -EINVAL;
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
index 12299fd95691..67e5b2472f6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
@@ -30,7 +30,8 @@ enum drm_sched_priority;
 struct drm_device;
 struct drm_file;
 
-enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority);
+int amdgpu_to_sched_priority(int amdgpu_priority,
+			     enum drm_sched_priority *prio);
 int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 651365183e75..6fc3af082f6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1704,8 +1704,8 @@ static struct ttm_bo_driver amdgpu_bo_driver = {
  */
 static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev)
 {
-	amdgpu_bo_free_kernel(&adev->fw_vram_usage.reserved_bo,
-		NULL, &adev->fw_vram_usage.va);
+	amdgpu_bo_free_kernel(&adev->mman.fw_vram_usage_reserved_bo,
+		NULL, &adev->mman.fw_vram_usage_va);
 }
 
 /**
@@ -1719,19 +1719,19 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 {
 	uint64_t vram_size = adev->gmc.visible_vram_size;
 
-	adev->fw_vram_usage.va = NULL;
-	adev->fw_vram_usage.reserved_bo = NULL;
+	adev->mman.fw_vram_usage_va = NULL;
+	adev->mman.fw_vram_usage_reserved_bo = NULL;
 
-	if (adev->fw_vram_usage.size == 0 ||
-	    adev->fw_vram_usage.size > vram_size)
+	if (adev->mman.fw_vram_usage_size == 0 ||
+	    adev->mman.fw_vram_usage_size > vram_size)
 		return 0;
 
 	return amdgpu_bo_create_kernel_at(adev,
-					  adev->fw_vram_usage.start_offset,
-					  adev->fw_vram_usage.size,
+					  adev->mman.fw_vram_usage_start_offset,
+					  adev->mman.fw_vram_usage_size,
 					  AMDGPU_GEM_DOMAIN_VRAM,
-					  &adev->fw_vram_usage.reserved_bo,
-					  &adev->fw_vram_usage.va);
+					  &adev->mman.fw_vram_usage_reserved_bo,
+					  &adev->mman.fw_vram_usage_va);
 }
 
 /*
@@ -1763,7 +1763,7 @@ static void amdgpu_ttm_training_data_block_init(struct amdgpu_device *adev)
 	memset(ctx, 0, sizeof(*ctx));
 
 	ctx->c2p_train_data_offset =
-		ALIGN((adev->gmc.mc_vram_size - adev->discovery_tmr_size - SZ_1M), SZ_1M);
+		ALIGN((adev->gmc.mc_vram_size - adev->mman.discovery_tmr_size - SZ_1M), SZ_1M);
 	ctx->p2c_train_data_offset =
 		(adev->gmc.mc_vram_size - GDDR6_MEM_TRAINING_OFFSET);
 	ctx->train_data_size =
@@ -1802,10 +1802,10 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev)
 	 * Otherwise, fallback to legacy approach to check and reserve tmr block for ip
 	 * discovery data and G6 memory training data respectively
 	 */
-	adev->discovery_tmr_size =
+	adev->mman.discovery_tmr_size =
 		amdgpu_atomfirmware_get_fw_reserved_fb_size(adev);
-	if (!adev->discovery_tmr_size)
-		adev->discovery_tmr_size = DISCOVERY_TMR_OFFSET;
+	if (!adev->mman.discovery_tmr_size)
+		adev->mman.discovery_tmr_size = DISCOVERY_TMR_OFFSET;
 
 	if (mem_train_support) {
 		/* reserve vram for mem train according to TMR location */
@@ -1825,14 +1825,14 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev)
 	}
 
 	ret = amdgpu_bo_create_kernel_at(adev,
-				adev->gmc.real_vram_size - adev->discovery_tmr_size,
-				adev->discovery_tmr_size,
+				adev->gmc.real_vram_size - adev->mman.discovery_tmr_size,
+				adev->mman.discovery_tmr_size,
 				AMDGPU_GEM_DOMAIN_VRAM,
-				&adev->discovery_memory,
+				&adev->mman.discovery_memory,
 				NULL);
 	if (ret) {
 		DRM_ERROR("alloc tmr failed(%d)!\n", ret);
-		amdgpu_bo_free_kernel(&adev->discovery_memory, NULL, NULL);
+		amdgpu_bo_free_kernel(&adev->mman.discovery_memory, NULL, NULL);
 		return ret;
 	}
 
@@ -1853,15 +1853,14 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	uint64_t gtt_size;
 	int r;
 	u64 vis_vram_limit;
-	void *stolen_vga_buf;
 
 	mutex_init(&adev->mman.gtt_window_lock);
 
 	/* No others user of address space so set it to 0 */
 	r = ttm_bo_device_init(&adev->mman.bdev,
 			       &amdgpu_bo_driver,
-			       adev->ddev->anon_inode->i_mapping,
-			       adev->ddev->vma_offset_manager,
+			       adev_to_drm(adev)->anon_inode->i_mapping,
+			       adev_to_drm(adev)->vma_offset_manager,
 			       dma_addressing_limited(adev->dev));
 	if (r) {
 		DRM_ERROR("failed initializing buffer object driver(%d).\n", r);
@@ -1906,7 +1905,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	 * If IP discovery enabled, a block of memory should be
 	 * reserved for IP discovey.
 	 */
-	if (adev->discovery_bin) {
+	if (adev->mman.discovery_bin) {
 		r = amdgpu_ttm_reserve_tmr(adev);
 		if (r)
 			return r;
@@ -1916,10 +1915,17 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	 * This is used for VGA emulation and pre-OS scanout buffers to
 	 * avoid display artifacts while transitioning between pre-OS
 	 * and driver.  */
-	r = amdgpu_bo_create_kernel(adev, adev->gmc.stolen_size, PAGE_SIZE,
-				    AMDGPU_GEM_DOMAIN_VRAM,
-				    &adev->stolen_vga_memory,
-				    NULL, &stolen_vga_buf);
+	r = amdgpu_bo_create_kernel_at(adev, 0, adev->mman.stolen_vga_size,
+				       AMDGPU_GEM_DOMAIN_VRAM,
+				       &adev->mman.stolen_vga_memory,
+				       NULL);
+	if (r)
+		return r;
+	r = amdgpu_bo_create_kernel_at(adev, adev->mman.stolen_vga_size,
+				       adev->mman.stolen_extended_size,
+				       AMDGPU_GEM_DOMAIN_VRAM,
+				       &adev->mman.stolen_extended_memory,
+				       NULL);
 	if (r)
 		return r;
 
@@ -1975,9 +1981,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
  */
 void amdgpu_ttm_late_init(struct amdgpu_device *adev)
 {
-	void *stolen_vga_buf;
 	/* return the VGA stolen memory (if any) back to VRAM */
-	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
+	if (!adev->mman.keep_stolen_vga_memory)
+		amdgpu_bo_free_kernel(&adev->mman.stolen_vga_memory, NULL, NULL);
+	amdgpu_bo_free_kernel(&adev->mman.stolen_extended_memory, NULL, NULL);
 }
 
 /**
@@ -1989,8 +1996,11 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 		return;
 
 	amdgpu_ttm_training_reserve_vram_fini(adev);
+	/* return the stolen vga memory back to VRAM */
+	if (adev->mman.keep_stolen_vga_memory)
+		amdgpu_bo_free_kernel(&adev->mman.stolen_vga_memory, NULL, NULL);
 	/* return the IP Discovery TMR memory back to VRAM */
-	amdgpu_bo_free_kernel(&adev->discovery_memory, NULL, NULL);
+	amdgpu_bo_free_kernel(&adev->mman.discovery_memory, NULL, NULL);
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
 
 	if (adev->mman.aper_base_kaddr)
@@ -2022,7 +2032,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 	uint64_t size;
 	int r;
 
-	if (!adev->mman.initialized || adev->in_gpu_reset ||
+	if (!adev->mman.initialized || amdgpu_in_reset(adev) ||
 	    adev->mman.buffer_funcs_enabled == enable)
 		return;
 
@@ -2033,7 +2043,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 		ring = adev->mman.buffer_funcs_ring;
 		sched = &ring->sched;
 		r = drm_sched_entity_init(&adev->mman.entity,
-				          DRM_SCHED_PRIORITY_KERNEL, &sched,
+					  DRM_SCHED_PRIORITY_KERNEL, &sched,
 					  1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
@@ -2058,7 +2068,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *file_priv = filp->private_data;
-	struct amdgpu_device *adev = file_priv->minor->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(file_priv->minor->dev);
 
 	if (adev == NULL)
 		return -EINVAL;
@@ -2239,7 +2249,7 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	unsigned ttm_pl = (uintptr_t)node->info_ent->data;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, ttm_pl);
 	struct drm_printer p = drm_seq_file_printer(m);
 
@@ -2530,7 +2540,7 @@ int amdgpu_ttm_debugfs_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DEBUG_FS)
 	unsigned count;
 
-	struct drm_minor *minor = adev->ddev->primary;
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *ent, *root = minor->debugfs_root;
 
 	for (count = 0; count < ARRAY_SIZE(ttm_debugfs_entries); count++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 4f9426ecf039..a87951b2f06d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,6 +73,23 @@ struct amdgpu_mman {
 
 	struct amdgpu_vram_mgr vram_mgr;
 	struct amdgpu_gtt_mgr gtt_mgr;
+
+	uint64_t		stolen_vga_size;
+	struct amdgpu_bo	*stolen_vga_memory;
+	uint64_t		stolen_extended_size;
+	struct amdgpu_bo	*stolen_extended_memory;
+	bool			keep_stolen_vga_memory;
+
+	/* discovery */
+	uint8_t				*discovery_bin;
+	uint32_t			discovery_tmr_size;
+	struct amdgpu_bo		*discovery_memory;
+
+	/* firmware VRAM reservation */
+	u64		fw_vram_usage_start_offset;
+	u64		fw_vram_usage_size;
+	struct amdgpu_bo	*fw_vram_usage_reserved_bo;
+	void		*fw_vram_usage_va;
 };
 
 struct amdgpu_copy_mem {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 183743c5fb7b..55fe19a2f332 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -408,7 +408,7 @@ static ssize_t show_##name(struct device *dev,				\
 			  char *buf)					\
 {									\
 	struct drm_device *ddev = dev_get_drvdata(dev);			\
-	struct amdgpu_device *adev = ddev->dev_private;			\
+	struct amdgpu_device *adev = drm_to_adev(ddev);			\
 									\
 	return snprintf(buf, PAGE_SIZE, "0x%08x\n", adev->field);	\
 }									\
@@ -628,7 +628,7 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 	struct amdgpu_firmware_info *ucode = NULL;
 
  /* for baremetal, the ucode is allocated in gtt, so don't need to fill the bo when reset/suspend */
-	if (!amdgpu_sriov_vf(adev) && (adev->in_gpu_reset || adev->in_suspend))
+	if (!amdgpu_sriov_vf(adev) && (amdgpu_in_reset(adev) || adev->in_suspend))
 		return 0;
 	/*
 	 * if SMU loaded firmware, it needn't add SMC, UVD, and VCE
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 12a8bc8fca0b..3c23c6293ff9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -131,6 +131,7 @@ enum ta_fw_type {
 	TA_FW_TYPE_PSP_RAS,
 	TA_FW_TYPE_PSP_HDCP,
 	TA_FW_TYPE_PSP_DTM,
+	TA_FW_TYPE_PSP_RAP,
 };
 
 struct ta_fw_bin_desc {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index af1b1ccf613c..262baf0f61ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -125,8 +125,9 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 				"detected in UMC block\n",
 				err_data->ue_count);
 
-		if (err_data->err_addr_cnt &&
-		    amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
+		if ((amdgpu_bad_page_threshold != 0) &&
+			err_data->err_addr_cnt &&
+			amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
 						err_data->err_addr_cnt))
 			dev_warn(adev->dev, "Failed to add ras bad page!\n");
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index a615a1eb750b..183814493658 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -21,6 +21,20 @@
 #ifndef __AMDGPU_UMC_H__
 #define __AMDGPU_UMC_H__
 
+/*
+ * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
+ * is the index of 8KB block
+ */
+#define ADDR_OF_8KB_BLOCK(addr)			(((addr) & ~0xffULL) << 5)
+/* channel index is the index of 256B block */
+#define ADDR_OF_256B_BLOCK(channel_index)	((channel_index) << 8)
+/* offset in 256B block */
+#define OFFSET_IN_256B_BLOCK(addr)		((addr) & 0xffULL)
+
+#define LOOP_UMC_INST(umc_inst) for ((umc_inst) = 0; (umc_inst) < adev->umc.umc_inst_num; (umc_inst)++)
+#define LOOP_UMC_CH_INST(ch_inst) for ((ch_inst) = 0; (ch_inst) < adev->umc.channel_inst_num; (ch_inst)++)
+#define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst))
+
 struct amdgpu_umc_funcs {
 	void (*err_cnt_init)(struct amdgpu_device *adev);
 	int (*ras_late_init)(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 1203c20491e6..f76961d17246 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -45,7 +45,7 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 	if (adev->mode_info.num_crtc == 0)
 		adev->mode_info.num_crtc = 1;
 	adev->enable_virtual_display = true;
-	adev->ddev->driver->driver_features &= ~DRIVER_ATOMIC;
+	adev_to_drm(adev)->driver->driver_features &= ~DRIVER_ATOMIC;
 	adev->cg_flags = 0;
 	adev->pg_flags = 0;
 }
@@ -93,7 +93,7 @@ failed_undo:
 	amdgpu_ring_undo(ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq:
-	pr_err("failed to write reg %x wait reg %x\n", reg0, reg1);
+	dev_err(adev->dev, "failed to write reg %x wait reg %x\n", reg0, reg1);
 }
 
 /**
@@ -401,7 +401,7 @@ static void amdgpu_virt_add_bad_page(struct amdgpu_device *adev,
 	if (bp_block_size) {
 		bp_cnt = bp_block_size / sizeof(uint64_t);
 		for (bp_idx = 0; bp_idx < bp_cnt; bp_idx++) {
-			retired_page = *(uint64_t *)(adev->fw_vram_usage.va +
+			retired_page = *(uint64_t *)(adev->mman.fw_vram_usage_va +
 					bp_block_offset + bp_idx * sizeof(uint64_t));
 			bp.retired_page = retired_page;
 
@@ -428,10 +428,10 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 	adev->virt.fw_reserve.p_pf2vf = NULL;
 	adev->virt.fw_reserve.p_vf2pf = NULL;
 
-	if (adev->fw_vram_usage.va != NULL) {
+	if (adev->mman.fw_vram_usage_va != NULL) {
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amd_sriov_msg_pf2vf_info_header *)(
-			adev->fw_vram_usage.va + AMDGIM_DATAEXCHANGE_OFFSET);
+			adev->mman.fw_vram_usage_va + AMDGIM_DATAEXCHANGE_OFFSET);
 		AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size);
 		AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum);
 		AMDGPU_FW_VRAM_PF2VF_READ(adev, feature_flags, &adev->virt.gim_feature);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index f826945989c7..b2046c3a404d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -325,9 +325,9 @@ static inline bool is_virtual_machine(void)
 #define amdgpu_sriov_is_pp_one_vf(adev) \
 	((adev)->virt.gim_feature & AMDGIM_FEATURE_PP_ONE_VF)
 #define amdgpu_sriov_is_debug(adev) \
-	((!adev->in_gpu_reset) && adev->virt.tdr_debug)
+	((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug)
 #define amdgpu_sriov_is_normal(adev) \
-	((!adev->in_gpu_reset) && (!adev->virt.tdr_debug))
+	((!amdgpu_in_reset(adev)) && (!adev->virt.tdr_debug))
 
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 8bc2253939be..420931d36732 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -28,6 +28,7 @@
 #include <linux/dma-fence-array.h>
 #include <linux/interval_tree_generic.h>
 #include <linux/idr.h>
+#include <linux/dma-buf.h>
 
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
@@ -35,6 +36,7 @@
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_gmc.h"
 #include "amdgpu_xgmi.h"
+#include "amdgpu_dma_buf.h"
 
 /**
  * DOC: GPUVM
@@ -1691,13 +1693,13 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		uint64_t max_entries;
 		uint64_t addr, last;
 
+		max_entries = mapping->last - start + 1;
 		if (nodes) {
 			addr = nodes->start << PAGE_SHIFT;
-			max_entries = (nodes->size - pfn) *
-				AMDGPU_GPU_PAGES_IN_CPU_PAGE;
+			max_entries = min((nodes->size - pfn) *
+				AMDGPU_GPU_PAGES_IN_CPU_PAGE, max_entries);
 		} else {
 			addr = 0;
-			max_entries = S64_MAX;
 		}
 
 		if (pages_addr) {
@@ -1727,7 +1729,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 			addr += pfn << PAGE_SHIFT;
 		}
 
-		last = min((uint64_t)mapping->last, start + max_entries - 1);
+		last = start + max_entries - 1;
 		r = amdgpu_vm_bo_update_mapping(adev, vm, false, false, resv,
 						start, last, flags, addr,
 						dma_addr, fence);
@@ -1778,15 +1780,24 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 		nodes = NULL;
 		resv = vm->root.base.bo->tbo.base.resv;
 	} else {
+		struct drm_gem_object *obj = &bo->tbo.base;
 		struct ttm_dma_tt *ttm;
 
+		resv = bo->tbo.base.resv;
+		if (obj->import_attach && bo_va->is_xgmi) {
+			struct dma_buf *dma_buf = obj->import_attach->dmabuf;
+			struct drm_gem_object *gobj = dma_buf->priv;
+			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
+
+			if (abo->tbo.mem.mem_type == TTM_PL_VRAM)
+				bo = gem_to_amdgpu_bo(gobj);
+		}
 		mem = &bo->tbo.mem;
 		nodes = mem->mm_node;
 		if (mem->mem_type == TTM_PL_TT) {
 			ttm = container_of(bo->tbo.ttm, struct ttm_dma_tt, ttm);
 			pages_addr = ttm->dma_address;
 		}
-		resv = bo->tbo.base.resv;
 	}
 
 	if (bo) {
@@ -2132,8 +2143,10 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 
-	if (bo && amdgpu_xgmi_same_hive(adev, amdgpu_ttm_adev(bo->tbo.bdev)) &&
-	    (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)) {
+	if (!bo)
+		return bo_va;
+
+	if (amdgpu_dmabuf_is_xgmi_accessible(adev, bo)) {
 		bo_va->is_xgmi = true;
 		/* Power up XGMI if it can be potentially used */
 		amdgpu_xgmi_set_pstate(adev, AMDGPU_XGMI_PSTATE_MAX_VEGA20);
@@ -3209,7 +3222,7 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	union drm_amdgpu_vm *args = data;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	long timeout = msecs_to_jiffies(2000);
 	int r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 7574be6cd7a0..b2adc2abc581 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -50,7 +50,7 @@ static ssize_t amdgpu_mem_info_vram_total_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.real_vram_size);
 }
@@ -67,7 +67,7 @@ static ssize_t amdgpu_mem_info_vis_vram_total_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.visible_vram_size);
 }
@@ -84,8 +84,9 @@ static ssize_t amdgpu_mem_info_vram_used_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_vram_mgr_usage(man));
 }
@@ -102,8 +103,9 @@ static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_vram_mgr_vis_usage(man));
 }
@@ -113,7 +115,7 @@ static ssize_t amdgpu_mem_info_vram_vendor(struct device *dev,
 						 char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	switch (adev->gmc.vram_vendor) {
 	case SAMSUNG:
@@ -478,7 +480,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
 	unsigned int pages;
 	int i, r;
 
-	*sgt = kmalloc(sizeof(*sg), GFP_KERNEL);
+	*sgt = kmalloc(sizeof(**sgt), GFP_KERNEL);
 	if (!*sgt)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index e3a3755cb999..1162913c8bf4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -35,11 +35,9 @@
 
 static DEFINE_MUTEX(xgmi_mutex);
 
-#define AMDGPU_MAX_XGMI_HIVE			8
 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4
 
-static struct amdgpu_hive_info xgmi_hives[AMDGPU_MAX_XGMI_HIVE];
-static unsigned hive_count = 0;
+static LIST_HEAD(xgmi_hive_list);
 
 static const int xgmi_pcs_err_status_reg_vg20[] = {
 	smnXGMI0_PCS_GOPX16_PCS_ERROR_STATUS,
@@ -171,65 +169,53 @@ static const struct amdgpu_pcs_ras_field wafl_pcs_ras_fields[] = {
  *
  */
 
+static struct attribute amdgpu_xgmi_hive_id = {
+	.name = "xgmi_hive_id",
+	.mode = S_IRUGO
+};
 
-static ssize_t amdgpu_xgmi_show_hive_id(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct amdgpu_hive_info *hive =
-			container_of(attr, struct amdgpu_hive_info, dev_attr);
-
-	return snprintf(buf, PAGE_SIZE, "%llu\n", hive->hive_id);
-}
+static struct attribute *amdgpu_xgmi_hive_attrs[] = {
+	&amdgpu_xgmi_hive_id,
+	NULL
+};
 
-static int amdgpu_xgmi_sysfs_create(struct amdgpu_device *adev,
-				    struct amdgpu_hive_info *hive)
+static ssize_t amdgpu_xgmi_show_attrs(struct kobject *kobj,
+	struct attribute *attr, char *buf)
 {
-	int ret = 0;
+	struct amdgpu_hive_info *hive = container_of(
+		kobj, struct amdgpu_hive_info, kobj);
 
-	if (WARN_ON(hive->kobj))
-		return -EINVAL;
-
-	hive->kobj = kobject_create_and_add("xgmi_hive_info", &adev->dev->kobj);
-	if (!hive->kobj) {
-		dev_err(adev->dev, "XGMI: Failed to allocate sysfs entry!\n");
-		return -EINVAL;
-	}
-
-	hive->dev_attr = (struct device_attribute) {
-		.attr = {
-			.name = "xgmi_hive_id",
-			.mode = S_IRUGO,
-
-		},
-		.show = amdgpu_xgmi_show_hive_id,
-	};
+	if (attr == &amdgpu_xgmi_hive_id)
+		return snprintf(buf, PAGE_SIZE, "%llu\n", hive->hive_id);
 
-	ret = sysfs_create_file(hive->kobj, &hive->dev_attr.attr);
-	if (ret) {
-		dev_err(adev->dev, "XGMI: Failed to create device file xgmi_hive_id\n");
-		kobject_del(hive->kobj);
-		kobject_put(hive->kobj);
-		hive->kobj = NULL;
-	}
-
-	return ret;
+	return 0;
 }
 
-static void amdgpu_xgmi_sysfs_destroy(struct amdgpu_device *adev,
-				    struct amdgpu_hive_info *hive)
+static void amdgpu_xgmi_hive_release(struct kobject *kobj)
 {
-	sysfs_remove_file(hive->kobj, &hive->dev_attr.attr);
-	kobject_del(hive->kobj);
-	kobject_put(hive->kobj);
-	hive->kobj = NULL;
+	struct amdgpu_hive_info *hive = container_of(
+		kobj, struct amdgpu_hive_info, kobj);
+
+	mutex_destroy(&hive->hive_lock);
+	kfree(hive);
 }
 
+static const struct sysfs_ops amdgpu_xgmi_hive_ops = {
+	.show = amdgpu_xgmi_show_attrs,
+};
+
+struct kobj_type amdgpu_xgmi_hive_type = {
+	.release = amdgpu_xgmi_hive_release,
+	.sysfs_ops = &amdgpu_xgmi_hive_ops,
+	.default_attrs = amdgpu_xgmi_hive_attrs,
+};
+
 static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
 				     struct device_attribute *attr,
 				     char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.xgmi.node_id);
 
@@ -241,7 +227,7 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 				      char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t ficaa_pie_ctl_in, ficaa_pie_status_in;
 	uint64_t fica_out;
 	unsigned int error_count = 0;
@@ -287,8 +273,8 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 
 
 	/* Create sysfs link to hive info folder on the first device */
-	if (adev != hive->adev) {
-		ret = sysfs_create_link(&adev->dev->kobj, hive->kobj,
+	if (hive->kobj.parent != (&adev->dev->kobj)) {
+		ret = sysfs_create_link(&adev->dev->kobj, &hive->kobj,
 					"xgmi_hive_info");
 		if (ret) {
 			dev_err(adev->dev, "XGMI: Failed to create link to hive info");
@@ -296,9 +282,9 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 		}
 	}
 
-	sprintf(node, "node%d", hive->number_devices);
+	sprintf(node, "node%d", atomic_read(&hive->number_devices));
 	/* Create sysfs link form the hive folder to yourself */
-	ret = sysfs_create_link(hive->kobj, &adev->dev->kobj, node);
+	ret = sysfs_create_link(&hive->kobj, &adev->dev->kobj, node);
 	if (ret) {
 		dev_err(adev->dev, "XGMI: Failed to create link from hive info");
 		goto remove_link;
@@ -308,7 +294,7 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 
 
 remove_link:
-	sysfs_remove_link(&adev->dev->kobj, adev->ddev->unique);
+	sysfs_remove_link(&adev->dev->kobj, adev_to_drm(adev)->unique);
 
 remove_file:
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
@@ -326,78 +312,96 @@ static void amdgpu_xgmi_sysfs_rem_dev_info(struct amdgpu_device *adev,
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
 	device_remove_file(adev->dev, &dev_attr_xgmi_error);
 
-	if (adev != hive->adev)
+	if (hive->kobj.parent != (&adev->dev->kobj))
 		sysfs_remove_link(&adev->dev->kobj,"xgmi_hive_info");
 
-	sprintf(node, "node%d", hive->number_devices);
-	sysfs_remove_link(hive->kobj, node);
+	sprintf(node, "node%d", atomic_read(&hive->number_devices));
+	sysfs_remove_link(&hive->kobj, node);
 
 }
 
 
 
-struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock)
+struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 {
-	int i;
-	struct amdgpu_hive_info *tmp;
+	struct amdgpu_hive_info *hive = NULL, *tmp = NULL;
+	int ret;
 
 	if (!adev->gmc.xgmi.hive_id)
 		return NULL;
 
+	if (adev->hive) {
+		kobject_get(&adev->hive->kobj);
+		return adev->hive;
+	}
+
 	mutex_lock(&xgmi_mutex);
 
-	for (i = 0 ; i < hive_count; ++i) {
-		tmp = &xgmi_hives[i];
-		if (tmp->hive_id == adev->gmc.xgmi.hive_id) {
-			if (lock)
-				mutex_lock(&tmp->hive_lock);
-			mutex_unlock(&xgmi_mutex);
-			return tmp;
+	if (!list_empty(&xgmi_hive_list)) {
+		list_for_each_entry_safe(hive, tmp, &xgmi_hive_list, node)  {
+			if (hive->hive_id == adev->gmc.xgmi.hive_id)
+				goto pro_end;
 		}
 	}
-	if (i >= AMDGPU_MAX_XGMI_HIVE) {
-		mutex_unlock(&xgmi_mutex);
-		return NULL;
+
+	hive = kzalloc(sizeof(*hive), GFP_KERNEL);
+	if (!hive) {
+		dev_err(adev->dev, "XGMI: allocation failed\n");
+		hive = NULL;
+		goto pro_end;
 	}
 
 	/* initialize new hive if not exist */
-	tmp = &xgmi_hives[hive_count++];
-
-	if (amdgpu_xgmi_sysfs_create(adev, tmp)) {
-		mutex_unlock(&xgmi_mutex);
-		return NULL;
+	ret = kobject_init_and_add(&hive->kobj,
+			&amdgpu_xgmi_hive_type,
+			&adev->dev->kobj,
+			"%s", "xgmi_hive_info");
+	if (ret) {
+		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+		kfree(hive);
+		hive = NULL;
+		goto pro_end;
 	}
 
-	tmp->adev = adev;
-	tmp->hive_id = adev->gmc.xgmi.hive_id;
-	INIT_LIST_HEAD(&tmp->device_list);
-	mutex_init(&tmp->hive_lock);
-	mutex_init(&tmp->reset_lock);
-	task_barrier_init(&tmp->tb);
-
-	if (lock)
-		mutex_lock(&tmp->hive_lock);
-	tmp->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
-	tmp->hi_req_gpu = NULL;
+	hive->hive_id = adev->gmc.xgmi.hive_id;
+	INIT_LIST_HEAD(&hive->device_list);
+	INIT_LIST_HEAD(&hive->node);
+	mutex_init(&hive->hive_lock);
+	atomic_set(&hive->in_reset, 0);
+	atomic_set(&hive->number_devices, 0);
+	task_barrier_init(&hive->tb);
+	hive->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
+	hive->hi_req_gpu = NULL;
 	/*
 	 * hive pstate on boot is high in vega20 so we have to go to low
 	 * pstate on after boot.
 	 */
-	tmp->hi_req_count = AMDGPU_MAX_XGMI_DEVICE_PER_HIVE;
+	hive->hi_req_count = AMDGPU_MAX_XGMI_DEVICE_PER_HIVE;
+	list_add_tail(&hive->node, &xgmi_hive_list);
+
+pro_end:
+	if (hive)
+		kobject_get(&hive->kobj);
 	mutex_unlock(&xgmi_mutex);
+	return hive;
+}
 
-	return tmp;
+void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive)
+{
+	if (hive)
+		kobject_put(&hive->kobj);
 }
 
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 {
 	int ret = 0;
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 	struct amdgpu_device *request_adev = hive->hi_req_gpu ?
 						hive->hi_req_gpu : adev;
 	bool is_hi_req = pstate == AMDGPU_XGMI_PSTATE_MAX_VEGA20;
 	bool init_low = hive->pstate == AMDGPU_XGMI_PSTATE_UNKNOWN;
 
+	amdgpu_put_xgmi_hive(hive);
 	/* fw bug so temporarily disable pstate switching */
 	return 0;
 
@@ -449,7 +453,7 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
 
 	/* Each psp need to set the latest topology */
 	ret = psp_xgmi_set_topology_info(&adev->psp,
-					 hive->number_devices,
+					 atomic_read(&hive->number_devices),
 					 &adev->psp.xgmi_context.top_info);
 	if (ret)
 		dev_err(adev->dev,
@@ -511,7 +515,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		adev->gmc.xgmi.node_id = adev->gmc.xgmi.physical_node_id + 16;
 	}
 
-	hive = amdgpu_get_xgmi_hive(adev, 1);
+	hive = amdgpu_get_xgmi_hive(adev);
 	if (!hive) {
 		ret = -EINVAL;
 		dev_err(adev->dev,
@@ -519,6 +523,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			adev->gmc.xgmi.node_id, adev->gmc.xgmi.hive_id);
 		goto exit;
 	}
+	mutex_lock(&hive->hive_lock);
 
 	top_info = &adev->psp.xgmi_context.top_info;
 
@@ -526,7 +531,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	list_for_each_entry(entry, &hive->device_list, head)
 		top_info->nodes[count++].node_id = entry->node_id;
 	top_info->num_nodes = count;
-	hive->number_devices = count;
+	atomic_set(&hive->number_devices, count);
 
 	task_barrier_add_task(&hive->tb);
 
@@ -541,7 +546,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			}
 			ret = amdgpu_xgmi_update_topology(hive, tmp_adev);
 			if (ret)
-				goto exit;
+				goto exit_unlock;
 		}
 
 		/* get latest topology info for each device from psp */
@@ -554,7 +559,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 					tmp_adev->gmc.xgmi.node_id,
 					tmp_adev->gmc.xgmi.hive_id, ret);
 				/* To do : continue with some node failed or disable the whole hive */
-				goto exit;
+				goto exit_unlock;
 			}
 		}
 	}
@@ -562,39 +567,51 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	if (!ret)
 		ret = amdgpu_xgmi_sysfs_add_dev_info(adev, hive);
 
-
+exit_unlock:
 	mutex_unlock(&hive->hive_lock);
 exit:
-	if (!ret)
+	if (!ret) {
+		adev->hive = hive;
 		dev_info(adev->dev, "XGMI: Add node %d, hive 0x%llx.\n",
 			 adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id);
-	else
+	} else {
+		amdgpu_put_xgmi_hive(hive);
 		dev_err(adev->dev, "XGMI: Failed to add node %d, hive 0x%llx ret: %d\n",
 			adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id,
 			ret);
+	}
 
 	return ret;
 }
 
 int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 {
-	struct amdgpu_hive_info *hive;
+	struct amdgpu_hive_info *hive = adev->hive;
 
 	if (!adev->gmc.xgmi.supported)
 		return -EINVAL;
 
-	hive = amdgpu_get_xgmi_hive(adev, 1);
 	if (!hive)
 		return -EINVAL;
 
+	mutex_lock(&hive->hive_lock);
 	task_barrier_rem_task(&hive->tb);
 	amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
+	if (hive->hi_req_gpu == adev)
+		hive->hi_req_gpu = NULL;
+	list_del(&adev->gmc.xgmi.head);
 	mutex_unlock(&hive->hive_lock);
 
-	if(!(--hive->number_devices)){
-		amdgpu_xgmi_sysfs_destroy(adev, hive);
-		mutex_destroy(&hive->hive_lock);
-		mutex_destroy(&hive->reset_lock);
+	amdgpu_put_xgmi_hive(hive);
+	adev->hive = NULL;
+
+	if (atomic_dec_return(&hive->number_devices) == 0) {
+		/* Remove the hive from global hive list */
+		mutex_lock(&xgmi_mutex);
+		list_del(&hive->node);
+		mutex_unlock(&xgmi_mutex);
+
+		amdgpu_put_xgmi_hive(hive);
 	}
 
 	return psp_xgmi_terminate(&adev->psp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6999eab16a72..148560d63554 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -27,13 +27,13 @@
 
 
 struct amdgpu_hive_info {
-	uint64_t		hive_id;
-	struct list_head	device_list;
-	int number_devices;
-	struct mutex hive_lock, reset_lock;
-	struct kobject *kobj;
-	struct device_attribute dev_attr;
-	struct amdgpu_device *adev;
+	struct kobject kobj;
+	uint64_t hive_id;
+	struct list_head device_list;
+	struct list_head node;
+	atomic_t number_devices;
+	struct mutex hive_lock;
+	atomic_t in_reset;
 	int hi_req_count;
 	struct amdgpu_device *hi_req_gpu;
 	struct task_barrier tb;
@@ -50,7 +50,8 @@ struct amdgpu_pcs_ras_field {
 	uint32_t pcs_err_shift;
 };
 
-struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock);
+struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev);
+void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive);
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
 int amdgpu_xgmi_add_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v1_0.c
index 847ca9b3ce4e..3ea557864320 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v1_0.c
@@ -73,6 +73,7 @@ int athub_v1_0_set_clockgating(struct amdgpu_device *adev,
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 		athub_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		athub_update_medium_grain_light_sleep(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
index 213e62a28ba0..159a2a4385a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
@@ -41,7 +41,7 @@ void amdgpu_atombios_crtc_overscan_setup(struct drm_crtc *crtc,
 				  struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	SET_CRTC_OVERSCAN_PS_ALLOCATION args;
 	int index = GetIndexIntoMasterTable(COMMAND, SetCRTC_OverScan);
@@ -84,7 +84,7 @@ void amdgpu_atombios_crtc_overscan_setup(struct drm_crtc *crtc,
 void amdgpu_atombios_crtc_scaler_setup(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	ENABLE_SCALER_PS_ALLOCATION args;
 	int index = GetIndexIntoMasterTable(COMMAND, EnableScaler);
@@ -114,7 +114,7 @@ void amdgpu_atombios_crtc_lock(struct drm_crtc *crtc, int lock)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int index =
 	    GetIndexIntoMasterTable(COMMAND, UpdateCRTC_DoubleBufferRegisters);
 	ENABLE_CRTC_PS_ALLOCATION args;
@@ -131,7 +131,7 @@ void amdgpu_atombios_crtc_enable(struct drm_crtc *crtc, int state)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int index = GetIndexIntoMasterTable(COMMAND, EnableCRTC);
 	ENABLE_CRTC_PS_ALLOCATION args;
 
@@ -147,7 +147,7 @@ void amdgpu_atombios_crtc_blank(struct drm_crtc *crtc, int state)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int index = GetIndexIntoMasterTable(COMMAND, BlankCRTC);
 	BLANK_CRTC_PS_ALLOCATION args;
 
@@ -163,7 +163,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating);
 	ENABLE_DISP_POWER_GATING_PS_ALLOCATION args;
 
@@ -192,7 +192,7 @@ void amdgpu_atombios_crtc_set_dtd_timing(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	SET_CRTC_USING_DTD_TIMING_PARAMETERS args;
 	int index = GetIndexIntoMasterTable(COMMAND, SetCRTC_UsingDTDTiming);
 	u16 misc = 0;
@@ -307,7 +307,7 @@ static u32 amdgpu_atombios_crtc_adjust_pll(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_encoder *encoder = amdgpu_crtc->encoder;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -588,7 +588,7 @@ void amdgpu_atombios_crtc_program_pll(struct drm_crtc *crtc,
 				      struct amdgpu_atom_ss *ss)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u8 frev, crev;
 	int index = GetIndexIntoMasterTable(COMMAND, SetPixelClock);
 	union set_pixel_clock args;
@@ -749,7 +749,7 @@ int amdgpu_atombios_crtc_prepare_pll(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder =
 		to_amdgpu_encoder(amdgpu_crtc->encoder);
 	int encoder_mode = amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder);
@@ -818,7 +818,7 @@ void amdgpu_atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder =
 		to_amdgpu_encoder(amdgpu_crtc->encoder);
 	u32 pll_clock = mode->clock;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 900b2727f432..a3ba9ca11e98 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -60,7 +60,7 @@ static int amdgpu_atombios_dp_process_aux_ch(struct amdgpu_i2c_chan *chan,
 				      u8 delay, u8 *ack)
 {
 	struct drm_device *dev = chan->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	union aux_channel_transaction args;
 	int index = GetIndexIntoMasterTable(COMMAND, ProcessAuxChannelTransaction);
 	unsigned char *base;
@@ -305,7 +305,7 @@ static u8 amdgpu_atombios_dp_encoder_service(struct amdgpu_device *adev,
 u8 amdgpu_atombios_dp_get_sinktype(struct amdgpu_connector *amdgpu_connector)
 {
 	struct drm_device *dev = amdgpu_connector->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	return amdgpu_atombios_dp_encoder_service(adev, ATOM_DP_ACTION_GET_SINK_TYPE, 0,
 					   amdgpu_connector->ddc_bus->rec.i2c_id, 0);
@@ -718,7 +718,7 @@ void amdgpu_atombios_dp_link_train(struct drm_encoder *encoder,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_connector *amdgpu_connector;
 	struct amdgpu_connector_atom_dig *dig_connector;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index 1e94a9b652f7..8339c8c3a328 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -70,7 +70,7 @@ u8
 amdgpu_atombios_encoder_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder)
 {
 	struct drm_device *dev = amdgpu_encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (!(adev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
 		return 0;
@@ -84,7 +84,7 @@ amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encode
 {
 	struct drm_encoder *encoder = &amdgpu_encoder->base;
 	struct drm_device *dev = amdgpu_encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder_atom_dig *dig;
 
 	if (!(adev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
@@ -152,7 +152,7 @@ amdgpu_atombios_encoder_get_backlight_brightness(struct backlight_device *bd)
 	struct amdgpu_backlight_privdata *pdata = bl_get_data(bd);
 	struct amdgpu_encoder *amdgpu_encoder = pdata->encoder;
 	struct drm_device *dev = amdgpu_encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	return amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
 }
@@ -166,7 +166,7 @@ void amdgpu_atombios_encoder_init_backlight(struct amdgpu_encoder *amdgpu_encode
 				     struct drm_connector *drm_connector)
 {
 	struct drm_device *dev = amdgpu_encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct backlight_device *bd;
 	struct backlight_properties props;
 	struct amdgpu_backlight_privdata *pdata;
@@ -229,7 +229,7 @@ void
 amdgpu_atombios_encoder_fini_backlight(struct amdgpu_encoder *amdgpu_encoder)
 {
 	struct drm_device *dev = amdgpu_encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct backlight_device *bd = NULL;
 	struct amdgpu_encoder_atom_dig *dig;
 
@@ -319,7 +319,7 @@ static void
 amdgpu_atombios_encoder_setup_dac(struct drm_encoder *encoder, int action)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	DAC_ENCODER_CONTROL_PS_ALLOCATION args;
 	int index = 0;
@@ -382,7 +382,7 @@ static void
 amdgpu_atombios_encoder_setup_dvo(struct drm_encoder *encoder, int action)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	union dvo_encoder_control args;
 	int index = GetIndexIntoMasterTable(COMMAND, DVOEncoderControl);
@@ -573,7 +573,7 @@ amdgpu_atombios_encoder_setup_dig_encoder(struct drm_encoder *encoder,
 				   int action, int panel_mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -762,7 +762,7 @@ amdgpu_atombios_encoder_setup_dig_transmitter(struct drm_encoder *encoder, int a
 					      uint8_t lane_num, uint8_t lane_set)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1178,7 +1178,7 @@ amdgpu_atombios_encoder_set_edp_panel_power(struct drm_connector *connector,
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct drm_device *dev = amdgpu_connector->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	union dig_transmitter_control args;
 	int index = GetIndexIntoMasterTable(COMMAND, UNIPHYTransmitterControl);
 	uint8_t frev, crev;
@@ -1225,7 +1225,7 @@ amdgpu_atombios_encoder_setup_external_encoder(struct drm_encoder *encoder,
 					int action)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder *ext_amdgpu_encoder = to_amdgpu_encoder(ext_encoder);
 	union external_encoder_control args;
@@ -1466,7 +1466,7 @@ void
 amdgpu_atombios_encoder_set_crtc_source(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
 	union crtc_source_param args;
@@ -1673,7 +1673,7 @@ amdgpu_atombios_encoder_set_crtc_source(struct drm_encoder *encoder)
 void
 amdgpu_atombios_encoder_init_dig(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_encoder *encoder;
 
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
@@ -1701,7 +1701,7 @@ amdgpu_atombios_encoder_dac_load_detect(struct drm_encoder *encoder,
 				 struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
@@ -1751,7 +1751,7 @@ amdgpu_atombios_encoder_dac_detect(struct drm_encoder *encoder,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	uint32_t bios_0_scratch;
@@ -1790,7 +1790,7 @@ amdgpu_atombios_encoder_dig_detect(struct drm_encoder *encoder,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct drm_encoder *ext_encoder = amdgpu_get_external_encoder(encoder);
@@ -1848,7 +1848,7 @@ amdgpu_atombios_encoder_set_bios_scratch_regs(struct drm_connector *connector,
 				       bool connected)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector =
 	    to_amdgpu_connector(connector);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
@@ -1999,7 +1999,7 @@ struct amdgpu_encoder_atom_dig *
 amdgpu_atombios_encoder_get_lcd_info(struct amdgpu_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
 	int index = GetIndexIntoMasterTable(DATA, LVDS_Info);
 	uint16_t data_offset, misc;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
index b4cc7c55fa16..09a538465ffd 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
@@ -40,7 +40,7 @@ static int amdgpu_atombios_i2c_process_i2c_ch(struct amdgpu_i2c_chan *chan,
 				       u8 *buf, u8 num)
 {
 	struct drm_device *dev = chan->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args;
 	int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction);
 	unsigned char *base;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index c2c67ab68a43..03ff8bd1fee8 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1366,8 +1366,10 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		dev_info(adev->dev, "BACO reset\n");
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
+		dev_info(adev->dev, "PCI CONFIG reset\n");
 		r = cik_asic_pci_config_reset(adev);
 	}
 
@@ -1919,6 +1921,10 @@ static uint64_t cik_get_pcie_replay_count(struct amdgpu_device *adev)
 	return (nak_r + nak_g);
 }
 
+static void cik_pre_asic_init(struct amdgpu_device *adev)
+{
+}
+
 static const struct amdgpu_asic_funcs cik_asic_funcs =
 {
 	.read_disabled_bios = &cik_read_disabled_bios,
@@ -1939,6 +1945,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.need_reset_on_init = &cik_need_reset_on_init,
 	.get_pcie_replay_count = &cik_get_pcie_replay_count,
 	.supports_baco = &cik_asic_supports_baco,
+	.pre_asic_init = &cik_pre_asic_init,
 };
 
 static int cik_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 84b45a019a36..5963cbe0d455 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -328,7 +328,7 @@ static void dce_v10_0_hpd_set_polarity(struct amdgpu_device *adev,
  */
 static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -383,7 +383,7 @@ static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
  */
 static void dce_v10_0_hpd_fini(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -504,7 +504,7 @@ void dce_v10_0_disable_dce(struct amdgpu_device *adev)
 static void dce_v10_0_program_fmt(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1209,7 +1209,7 @@ static struct amdgpu_audio_pin *dce_v10_0_audio_get_pin(struct amdgpu_device *ad
 
 static void dce_v10_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1226,7 +1226,7 @@ static void dce_v10_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1272,7 +1272,7 @@ static void dce_v10_0_audio_write_latency_fields(struct drm_encoder *encoder,
 static void dce_v10_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1328,7 +1328,7 @@ static void dce_v10_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 static void dce_v10_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1483,7 +1483,7 @@ static void dce_v10_0_audio_fini(struct amdgpu_device *adev)
 static void dce_v10_0_afmt_update_ACR(struct drm_encoder *encoder, uint32_t clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_afmt_acr acr = amdgpu_afmt_acr(clock);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -1519,7 +1519,7 @@ static void dce_v10_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 					       void *buffer, size_t size)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	uint8_t *frame = buffer + 3;
@@ -1538,7 +1538,7 @@ static void dce_v10_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 static void dce_v10_0_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
@@ -1569,7 +1569,7 @@ static void dce_v10_0_afmt_setmode(struct drm_encoder *encoder,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1749,7 +1749,7 @@ static void dce_v10_0_afmt_setmode(struct drm_encoder *encoder,
 static void dce_v10_0_afmt_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 
@@ -1822,7 +1822,7 @@ static void dce_v10_0_vga_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 vga_control;
 
 	vga_control = RREG32(vga_control_regs[amdgpu_crtc->crtc_id]) & ~1;
@@ -1836,7 +1836,7 @@ static void dce_v10_0_grph_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (enable)
 		WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, 1);
@@ -1850,7 +1850,7 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -2095,7 +2095,7 @@ static void dce_v10_0_set_interleave(struct drm_crtc *crtc,
 				     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	u32 tmp;
 
@@ -2111,7 +2111,7 @@ static void dce_v10_0_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u16 *r, *g, *b;
 	int i;
 	u32 tmp;
@@ -2250,7 +2250,7 @@ static u32 dce_v10_0_pick_pll(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 pll_in_use;
 	int pll;
 
@@ -2285,7 +2285,7 @@ static u32 dce_v10_0_pick_pll(struct drm_crtc *crtc)
 
 static void dce_v10_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint32_t cur_lock;
 
@@ -2300,7 +2300,7 @@ static void dce_v10_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 static void dce_v10_0_hide_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	u32 tmp;
 
 	tmp = RREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset);
@@ -2311,7 +2311,7 @@ static void dce_v10_0_hide_cursor(struct drm_crtc *crtc)
 static void dce_v10_0_show_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	u32 tmp;
 
 	WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2329,7 +2329,7 @@ static int dce_v10_0_cursor_move_locked(struct drm_crtc *crtc,
 					int x, int y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	int xorigin = 0, yorigin = 0;
 
 	amdgpu_crtc->cursor_x = x;
@@ -2503,7 +2503,7 @@ static const struct drm_crtc_funcs dce_v10_0_crtc_funcs = {
 static void dce_v10_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	unsigned type;
 
@@ -2557,7 +2557,7 @@ static void dce_v10_0_crtc_disable(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_atom_ss ss;
 	int i;
 
@@ -2701,7 +2701,7 @@ static int dce_v10_0_crtc_init(struct amdgpu_device *adev, int index)
 	if (amdgpu_crtc == NULL)
 		return -ENOMEM;
 
-	drm_crtc_init(adev->ddev, &amdgpu_crtc->base, &dce_v10_0_crtc_funcs);
+	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_v10_0_crtc_funcs);
 
 	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
 	amdgpu_crtc->crtc_id = index;
@@ -2709,8 +2709,8 @@ static int dce_v10_0_crtc_init(struct amdgpu_device *adev, int index)
 
 	amdgpu_crtc->max_cursor_width = 128;
 	amdgpu_crtc->max_cursor_height = 128;
-	adev->ddev->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
-	adev->ddev->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
+	adev_to_drm(adev)->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
+	adev_to_drm(adev)->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
 
 	switch (amdgpu_crtc->crtc_id) {
 	case 0:
@@ -2792,24 +2792,24 @@ static int dce_v10_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
 
-	adev->ddev->mode_config.async_page_flip = true;
+	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	r = amdgpu_display_modeset_create_props(adev);
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	/* allocate crtcs */
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
@@ -2819,7 +2819,7 @@ static int dce_v10_0_sw_init(void *handle)
 	}
 
 	if (amdgpu_atombios_get_connector_info_from_object_table(adev))
-		amdgpu_display_print_display_setup(adev->ddev);
+		amdgpu_display_print_display_setup(adev_to_drm(adev));
 	else
 		return -EINVAL;
 
@@ -2832,7 +2832,7 @@ static int dce_v10_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	drm_kms_helper_poll_init(adev->ddev);
+	drm_kms_helper_poll_init(adev_to_drm(adev));
 
 	adev->mode_info.mode_config_initialized = true;
 	return 0;
@@ -2844,13 +2844,13 @@ static int dce_v10_0_sw_fini(void *handle)
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 
-	drm_kms_helper_poll_fini(adev->ddev);
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
 
 	dce_v10_0_audio_fini(adev);
 
 	dce_v10_0_afmt_fini(adev);
 
-	drm_mode_config_cleanup(adev->ddev);
+	drm_mode_config_cleanup(adev_to_drm(adev));
 	adev->mode_info.mode_config_initialized = false;
 
 	return 0;
@@ -3157,14 +3157,14 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev,
 	if (amdgpu_crtc == NULL)
 		return 0;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	works = amdgpu_crtc->pflip_works;
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED) {
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
 						 "AMDGPU_FLIP_SUBMITTED(%d)\n",
 						 amdgpu_crtc->pflip_status,
 						 AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return 0;
 	}
 
@@ -3176,7 +3176,7 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev,
 	if (works->event)
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
@@ -3245,7 +3245,7 @@ static int dce_v10_0_crtc_irq(struct amdgpu_device *adev,
 			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
 
 		if (amdgpu_irq_enabled(adev, source, irq_type)) {
-			drm_handle_vblank(adev->ddev, crtc);
+			drm_handle_vblank(adev_to_drm(adev), crtc);
 		}
 		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
 
@@ -3345,7 +3345,7 @@ dce_v10_0_encoder_mode_set(struct drm_encoder *encoder,
 
 static void dce_v10_0_encoder_prepare(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
 
@@ -3385,7 +3385,7 @@ static void dce_v10_0_encoder_prepare(struct drm_encoder *encoder)
 static void dce_v10_0_encoder_commit(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* need to call this here as we need the crtc set up */
 	amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
@@ -3485,7 +3485,7 @@ static void dce_v10_0_encoder_add(struct amdgpu_device *adev,
 				 uint32_t supported_device,
 				 u16 caps)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 01ce52266966..1954472c8e8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -346,7 +346,7 @@ static void dce_v11_0_hpd_set_polarity(struct amdgpu_device *adev,
  */
 static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -400,7 +400,7 @@ static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
  */
 static void dce_v11_0_hpd_fini(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -530,7 +530,7 @@ void dce_v11_0_disable_dce(struct amdgpu_device *adev)
 static void dce_v11_0_program_fmt(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1235,7 +1235,7 @@ static struct amdgpu_audio_pin *dce_v11_0_audio_get_pin(struct amdgpu_device *ad
 
 static void dce_v11_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1252,7 +1252,7 @@ static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1298,7 +1298,7 @@ static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder,
 static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1354,7 +1354,7 @@ static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 static void dce_v11_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1525,7 +1525,7 @@ static void dce_v11_0_audio_fini(struct amdgpu_device *adev)
 static void dce_v11_0_afmt_update_ACR(struct drm_encoder *encoder, uint32_t clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_afmt_acr acr = amdgpu_afmt_acr(clock);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -1561,7 +1561,7 @@ static void dce_v11_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 					       void *buffer, size_t size)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	uint8_t *frame = buffer + 3;
@@ -1580,7 +1580,7 @@ static void dce_v11_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 static void dce_v11_0_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
@@ -1611,7 +1611,7 @@ static void dce_v11_0_afmt_setmode(struct drm_encoder *encoder,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1791,7 +1791,7 @@ static void dce_v11_0_afmt_setmode(struct drm_encoder *encoder,
 static void dce_v11_0_afmt_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 
@@ -1864,7 +1864,7 @@ static void dce_v11_0_vga_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 vga_control;
 
 	vga_control = RREG32(vga_control_regs[amdgpu_crtc->crtc_id]) & ~1;
@@ -1878,7 +1878,7 @@ static void dce_v11_0_grph_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (enable)
 		WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, 1);
@@ -1892,7 +1892,7 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -2137,7 +2137,7 @@ static void dce_v11_0_set_interleave(struct drm_crtc *crtc,
 				     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	u32 tmp;
 
@@ -2153,7 +2153,7 @@ static void dce_v11_0_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u16 *r, *g, *b;
 	int i;
 	u32 tmp;
@@ -2283,7 +2283,7 @@ static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 pll_in_use;
 	int pll;
 
@@ -2364,7 +2364,7 @@ static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc)
 
 static void dce_v11_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint32_t cur_lock;
 
@@ -2379,7 +2379,7 @@ static void dce_v11_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 static void dce_v11_0_hide_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	u32 tmp;
 
 	tmp = RREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset);
@@ -2390,7 +2390,7 @@ static void dce_v11_0_hide_cursor(struct drm_crtc *crtc)
 static void dce_v11_0_show_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	u32 tmp;
 
 	WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2408,7 +2408,7 @@ static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc,
 					int x, int y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	int xorigin = 0, yorigin = 0;
 
 	amdgpu_crtc->cursor_x = x;
@@ -2582,7 +2582,7 @@ static const struct drm_crtc_funcs dce_v11_0_crtc_funcs = {
 static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	unsigned type;
 
@@ -2636,7 +2636,7 @@ static void dce_v11_0_crtc_disable(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_atom_ss ss;
 	int i;
 
@@ -2706,7 +2706,7 @@ static int dce_v11_0_crtc_mode_set(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (!amdgpu_crtc->adjusted_clock)
 		return -EINVAL;
@@ -2809,7 +2809,7 @@ static int dce_v11_0_crtc_init(struct amdgpu_device *adev, int index)
 	if (amdgpu_crtc == NULL)
 		return -ENOMEM;
 
-	drm_crtc_init(adev->ddev, &amdgpu_crtc->base, &dce_v11_0_crtc_funcs);
+	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_v11_0_crtc_funcs);
 
 	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
 	amdgpu_crtc->crtc_id = index;
@@ -2817,8 +2817,8 @@ static int dce_v11_0_crtc_init(struct amdgpu_device *adev, int index)
 
 	amdgpu_crtc->max_cursor_width = 128;
 	amdgpu_crtc->max_cursor_height = 128;
-	adev->ddev->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
-	adev->ddev->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
+	adev_to_drm(adev)->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
+	adev_to_drm(adev)->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
 
 	switch (amdgpu_crtc->crtc_id) {
 	case 0:
@@ -2913,24 +2913,24 @@ static int dce_v11_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
 
-	adev->ddev->mode_config.async_page_flip = true;
+	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	r = amdgpu_display_modeset_create_props(adev);
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 
 	/* allocate crtcs */
@@ -2941,7 +2941,7 @@ static int dce_v11_0_sw_init(void *handle)
 	}
 
 	if (amdgpu_atombios_get_connector_info_from_object_table(adev))
-		amdgpu_display_print_display_setup(adev->ddev);
+		amdgpu_display_print_display_setup(adev_to_drm(adev));
 	else
 		return -EINVAL;
 
@@ -2954,7 +2954,7 @@ static int dce_v11_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	drm_kms_helper_poll_init(adev->ddev);
+	drm_kms_helper_poll_init(adev_to_drm(adev));
 
 	adev->mode_info.mode_config_initialized = true;
 	return 0;
@@ -2966,13 +2966,13 @@ static int dce_v11_0_sw_fini(void *handle)
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 
-	drm_kms_helper_poll_fini(adev->ddev);
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
 
 	dce_v11_0_audio_fini(adev);
 
 	dce_v11_0_afmt_fini(adev);
 
-	drm_mode_config_cleanup(adev->ddev);
+	drm_mode_config_cleanup(adev_to_drm(adev));
 	adev->mode_info.mode_config_initialized = false;
 
 	return 0;
@@ -3283,14 +3283,14 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev,
 	if(amdgpu_crtc == NULL)
 		return 0;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	works = amdgpu_crtc->pflip_works;
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
 						 "AMDGPU_FLIP_SUBMITTED(%d)\n",
 						 amdgpu_crtc->pflip_status,
 						 AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return 0;
 	}
 
@@ -3302,7 +3302,7 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev,
 	if(works->event)
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
@@ -3372,7 +3372,7 @@ static int dce_v11_0_crtc_irq(struct amdgpu_device *adev,
 			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
 
 		if (amdgpu_irq_enabled(adev, source, irq_type)) {
-			drm_handle_vblank(adev->ddev, crtc);
+			drm_handle_vblank(adev_to_drm(adev), crtc);
 		}
 		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
 
@@ -3471,7 +3471,7 @@ dce_v11_0_encoder_mode_set(struct drm_encoder *encoder,
 
 static void dce_v11_0_encoder_prepare(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
 
@@ -3511,7 +3511,7 @@ static void dce_v11_0_encoder_prepare(struct drm_encoder *encoder)
 static void dce_v11_0_encoder_commit(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* need to call this here as we need the crtc set up */
 	amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
@@ -3611,7 +3611,7 @@ static void dce_v11_0_encoder_add(struct amdgpu_device *adev,
 				 uint32_t supported_device,
 				 u16 caps)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index cbddead3dafb..3a44753a80d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -279,7 +279,7 @@ static void dce_v6_0_hpd_set_polarity(struct amdgpu_device *adev,
  */
 static void dce_v6_0_hpd_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -324,7 +324,7 @@ static void dce_v6_0_hpd_init(struct amdgpu_device *adev)
  */
 static void dce_v6_0_hpd_fini(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -401,7 +401,7 @@ static void dce_v6_0_program_fmt(struct drm_encoder *encoder)
 {
 
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
@@ -1114,7 +1114,7 @@ static struct amdgpu_audio_pin *dce_v6_0_audio_get_pin(struct amdgpu_device *ade
 
 static void dce_v6_0_audio_select_pin(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 
@@ -1130,7 +1130,7 @@ static void dce_v6_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1174,7 +1174,7 @@ static void dce_v6_0_audio_write_latency_fields(struct drm_encoder *encoder,
 static void dce_v6_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1235,7 +1235,7 @@ static void dce_v6_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 static void dce_v6_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1392,7 +1392,7 @@ static void dce_v6_0_audio_fini(struct amdgpu_device *adev)
 static void dce_v6_0_audio_set_vbi_packet(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1408,7 +1408,7 @@ static void dce_v6_0_audio_set_acr(struct drm_encoder *encoder,
 				   uint32_t clock, int bpc)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_afmt_acr acr = amdgpu_afmt_acr(clock);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -1446,7 +1446,7 @@ static void dce_v6_0_audio_set_avi_infoframe(struct drm_encoder *encoder,
 					       struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1488,7 +1488,7 @@ static void dce_v6_0_audio_set_avi_infoframe(struct drm_encoder *encoder,
 static void dce_v6_0_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
 	int em = amdgpu_atombios_encoder_get_encoder_mode(encoder);
 	u32 tmp;
@@ -1522,7 +1522,7 @@ static void dce_v6_0_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 static void dce_v6_0_audio_set_packet(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1566,7 +1566,7 @@ static void dce_v6_0_audio_set_packet(struct drm_encoder *encoder)
 static void dce_v6_0_audio_set_mute(struct drm_encoder *encoder, bool mute)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1579,7 +1579,7 @@ static void dce_v6_0_audio_set_mute(struct drm_encoder *encoder, bool mute)
 static void dce_v6_0_audio_hdmi_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1616,7 +1616,7 @@ static void dce_v6_0_audio_hdmi_enable(struct drm_encoder *encoder, bool enable)
 static void dce_v6_0_audio_dp_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 tmp;
@@ -1645,7 +1645,7 @@ static void dce_v6_0_afmt_setmode(struct drm_encoder *encoder,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1714,7 +1714,7 @@ static void dce_v6_0_afmt_setmode(struct drm_encoder *encoder,
 static void dce_v6_0_afmt_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 
@@ -1788,7 +1788,7 @@ static void dce_v6_0_vga_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 vga_control;
 
 	vga_control = RREG32(vga_control_regs[amdgpu_crtc->crtc_id]) & ~1;
@@ -1799,7 +1799,7 @@ static void dce_v6_0_grph_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, enable ? 1 : 0);
 }
@@ -1810,7 +1810,7 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -2033,7 +2033,7 @@ static void dce_v6_0_set_interleave(struct drm_crtc *crtc,
 				    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -2048,7 +2048,7 @@ static void dce_v6_0_crtc_load_lut(struct drm_crtc *crtc)
 
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u16 *r, *g, *b;
 	int i;
 
@@ -2148,7 +2148,7 @@ static u32 dce_v6_0_pick_pll(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 pll_in_use;
 	int pll;
 
@@ -2177,7 +2177,7 @@ static u32 dce_v6_0_pick_pll(struct drm_crtc *crtc)
 
 static void dce_v6_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint32_t cur_lock;
 
@@ -2192,7 +2192,7 @@ static void dce_v6_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 static void dce_v6_0_hide_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 
 	WREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset,
 	       (CURSOR_24_8_PRE_MULT << CUR_CONTROL__CURSOR_MODE__SHIFT) |
@@ -2204,7 +2204,7 @@ static void dce_v6_0_hide_cursor(struct drm_crtc *crtc)
 static void dce_v6_0_show_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 
 	WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(amdgpu_crtc->cursor_addr));
@@ -2222,7 +2222,7 @@ static int dce_v6_0_cursor_move_locked(struct drm_crtc *crtc,
 				       int x, int y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	int xorigin = 0, yorigin = 0;
 
 	int w = amdgpu_crtc->cursor_width;
@@ -2397,7 +2397,7 @@ static const struct drm_crtc_funcs dce_v6_0_crtc_funcs = {
 static void dce_v6_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	unsigned type;
 
@@ -2447,7 +2447,7 @@ static void dce_v6_0_crtc_disable(struct drm_crtc *crtc)
 
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_atom_ss ss;
 	int i;
 
@@ -2591,7 +2591,7 @@ static int dce_v6_0_crtc_init(struct amdgpu_device *adev, int index)
 	if (amdgpu_crtc == NULL)
 		return -ENOMEM;
 
-	drm_crtc_init(adev->ddev, &amdgpu_crtc->base, &dce_v6_0_crtc_funcs);
+	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_v6_0_crtc_funcs);
 
 	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
 	amdgpu_crtc->crtc_id = index;
@@ -2599,8 +2599,8 @@ static int dce_v6_0_crtc_init(struct amdgpu_device *adev, int index)
 
 	amdgpu_crtc->max_cursor_width = CURSOR_WIDTH;
 	amdgpu_crtc->max_cursor_height = CURSOR_HEIGHT;
-	adev->ddev->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
-	adev->ddev->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
+	adev_to_drm(adev)->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
+	adev_to_drm(adev)->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
 
 	amdgpu_crtc->crtc_offset = crtc_offsets[amdgpu_crtc->crtc_id];
 
@@ -2669,20 +2669,20 @@ static int dce_v6_0_sw_init(void *handle)
 
 	adev->mode_info.mode_config_initialized = true;
 
-	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
-	adev->ddev->mode_config.async_page_flip = true;
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
+	adev_to_drm(adev)->mode_config.async_page_flip = true;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	r = amdgpu_display_modeset_create_props(adev);
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	/* allocate crtcs */
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
@@ -2693,7 +2693,7 @@ static int dce_v6_0_sw_init(void *handle)
 
 	ret = amdgpu_atombios_get_connector_info_from_object_table(adev);
 	if (ret)
-		amdgpu_display_print_display_setup(adev->ddev);
+		amdgpu_display_print_display_setup(adev_to_drm(adev));
 	else
 		return -EINVAL;
 
@@ -2706,7 +2706,7 @@ static int dce_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	drm_kms_helper_poll_init(adev->ddev);
+	drm_kms_helper_poll_init(adev_to_drm(adev));
 
 	return r;
 }
@@ -2717,12 +2717,12 @@ static int dce_v6_0_sw_fini(void *handle)
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 
-	drm_kms_helper_poll_fini(adev->ddev);
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
 
 	dce_v6_0_audio_fini(adev);
 	dce_v6_0_afmt_fini(adev);
 
-	drm_mode_config_cleanup(adev->ddev);
+	drm_mode_config_cleanup(adev_to_drm(adev));
 	adev->mode_info.mode_config_initialized = false;
 
 	return 0;
@@ -2967,7 +2967,7 @@ static int dce_v6_0_crtc_irq(struct amdgpu_device *adev,
 			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
 
 		if (amdgpu_irq_enabled(adev, source, irq_type)) {
-			drm_handle_vblank(adev->ddev, crtc);
+			drm_handle_vblank(adev_to_drm(adev), crtc);
 		}
 		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
 		break;
@@ -3036,14 +3036,14 @@ static int dce_v6_0_pageflip_irq(struct amdgpu_device *adev,
 	if (amdgpu_crtc == NULL)
 		return 0;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	works = amdgpu_crtc->pflip_works;
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
 						"AMDGPU_FLIP_SUBMITTED(%d)\n",
 						amdgpu_crtc->pflip_status,
 						AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return 0;
 	}
 
@@ -3055,7 +3055,7 @@ static int dce_v6_0_pageflip_irq(struct amdgpu_device *adev,
 	if (works->event)
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
@@ -3146,7 +3146,7 @@ dce_v6_0_encoder_mode_set(struct drm_encoder *encoder,
 static void dce_v6_0_encoder_prepare(struct drm_encoder *encoder)
 {
 
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
 
@@ -3187,7 +3187,7 @@ static void dce_v6_0_encoder_commit(struct drm_encoder *encoder)
 {
 
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* need to call this here as we need the crtc set up */
 	amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
@@ -3297,7 +3297,7 @@ static void dce_v6_0_encoder_add(struct amdgpu_device *adev,
 				 uint32_t supported_device,
 				 u16 caps)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index fa0ad50b628c..3603e5f13077 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -273,7 +273,7 @@ static void dce_v8_0_hpd_set_polarity(struct amdgpu_device *adev,
  */
 static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -318,7 +318,7 @@ static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
  */
 static void dce_v8_0_hpd_fini(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	u32 tmp;
@@ -444,7 +444,7 @@ void dce_v8_0_disable_dce(struct amdgpu_device *adev)
 static void dce_v8_0_program_fmt(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1146,7 +1146,7 @@ static struct amdgpu_audio_pin *dce_v8_0_audio_get_pin(struct amdgpu_device *ade
 
 static void dce_v8_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 offset;
@@ -1164,7 +1164,7 @@ static void dce_v8_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1225,7 +1225,7 @@ static void dce_v8_0_audio_write_latency_fields(struct drm_encoder *encoder,
 static void dce_v8_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
@@ -1278,7 +1278,7 @@ static void dce_v8_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 static void dce_v8_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 offset;
@@ -1446,7 +1446,7 @@ static void dce_v8_0_audio_fini(struct amdgpu_device *adev)
 static void dce_v8_0_afmt_update_ACR(struct drm_encoder *encoder, uint32_t clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_afmt_acr acr = amdgpu_afmt_acr(clock);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -1469,7 +1469,7 @@ static void dce_v8_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 					       void *buffer, size_t size)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	uint32_t offset = dig->afmt->offset;
@@ -1489,7 +1489,7 @@ static void dce_v8_0_afmt_update_avi_infoframe(struct drm_encoder *encoder,
 static void dce_v8_0_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc);
@@ -1516,7 +1516,7 @@ static void dce_v8_0_afmt_setmode(struct drm_encoder *encoder,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
@@ -1678,7 +1678,7 @@ static void dce_v8_0_afmt_setmode(struct drm_encoder *encoder,
 static void dce_v8_0_afmt_enable(struct drm_encoder *encoder, bool enable)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 
@@ -1751,7 +1751,7 @@ static void dce_v8_0_vga_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 vga_control;
 
 	vga_control = RREG32(vga_control_regs[amdgpu_crtc->crtc_id]) & ~1;
@@ -1765,7 +1765,7 @@ static void dce_v8_0_grph_enable(struct drm_crtc *crtc, bool enable)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (enable)
 		WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, 1);
@@ -1779,7 +1779,7 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -2004,7 +2004,7 @@ static void dce_v8_0_set_interleave(struct drm_crtc *crtc,
 				    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -2018,7 +2018,7 @@ static void dce_v8_0_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u16 *r, *g, *b;
 	int i;
 
@@ -2140,7 +2140,7 @@ static u32 dce_v8_0_pick_pll(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 pll_in_use;
 	int pll;
 
@@ -2188,7 +2188,7 @@ static u32 dce_v8_0_pick_pll(struct drm_crtc *crtc)
 
 static void dce_v8_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint32_t cur_lock;
 
@@ -2203,7 +2203,7 @@ static void dce_v8_0_lock_cursor(struct drm_crtc *crtc, bool lock)
 static void dce_v8_0_hide_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 
 	WREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset,
 	       (CURSOR_24_8_PRE_MULT << CUR_CONTROL__CURSOR_MODE__SHIFT) |
@@ -2213,7 +2213,7 @@ static void dce_v8_0_hide_cursor(struct drm_crtc *crtc)
 static void dce_v8_0_show_cursor(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 
 	WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(amdgpu_crtc->cursor_addr));
@@ -2230,7 +2230,7 @@ static int dce_v8_0_cursor_move_locked(struct drm_crtc *crtc,
 				       int x, int y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	int xorigin = 0, yorigin = 0;
 
 	amdgpu_crtc->cursor_x = x;
@@ -2404,7 +2404,7 @@ static const struct drm_crtc_funcs dce_v8_0_crtc_funcs = {
 static void dce_v8_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	unsigned type;
 
@@ -2458,7 +2458,7 @@ static void dce_v8_0_crtc_disable(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_atom_ss ss;
 	int i;
 
@@ -2609,7 +2609,7 @@ static int dce_v8_0_crtc_init(struct amdgpu_device *adev, int index)
 	if (amdgpu_crtc == NULL)
 		return -ENOMEM;
 
-	drm_crtc_init(adev->ddev, &amdgpu_crtc->base, &dce_v8_0_crtc_funcs);
+	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_v8_0_crtc_funcs);
 
 	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
 	amdgpu_crtc->crtc_id = index;
@@ -2617,8 +2617,8 @@ static int dce_v8_0_crtc_init(struct amdgpu_device *adev, int index)
 
 	amdgpu_crtc->max_cursor_width = CIK_CURSOR_WIDTH;
 	amdgpu_crtc->max_cursor_height = CIK_CURSOR_HEIGHT;
-	adev->ddev->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
-	adev->ddev->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
+	adev_to_drm(adev)->mode_config.cursor_width = amdgpu_crtc->max_cursor_width;
+	adev_to_drm(adev)->mode_config.cursor_height = amdgpu_crtc->max_cursor_height;
 
 	amdgpu_crtc->crtc_offset = crtc_offsets[amdgpu_crtc->crtc_id];
 
@@ -2689,24 +2689,24 @@ static int dce_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
 
-	adev->ddev->mode_config.async_page_flip = true;
+	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	r = amdgpu_display_modeset_create_props(adev);
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	/* allocate crtcs */
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
@@ -2716,7 +2716,7 @@ static int dce_v8_0_sw_init(void *handle)
 	}
 
 	if (amdgpu_atombios_get_connector_info_from_object_table(adev))
-		amdgpu_display_print_display_setup(adev->ddev);
+		amdgpu_display_print_display_setup(adev_to_drm(adev));
 	else
 		return -EINVAL;
 
@@ -2729,7 +2729,7 @@ static int dce_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	drm_kms_helper_poll_init(adev->ddev);
+	drm_kms_helper_poll_init(adev_to_drm(adev));
 
 	adev->mode_info.mode_config_initialized = true;
 	return 0;
@@ -2741,13 +2741,13 @@ static int dce_v8_0_sw_fini(void *handle)
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 
-	drm_kms_helper_poll_fini(adev->ddev);
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
 
 	dce_v8_0_audio_fini(adev);
 
 	dce_v8_0_afmt_fini(adev);
 
-	drm_mode_config_cleanup(adev->ddev);
+	drm_mode_config_cleanup(adev_to_drm(adev));
 	adev->mode_info.mode_config_initialized = false;
 
 	return 0;
@@ -3057,7 +3057,7 @@ static int dce_v8_0_crtc_irq(struct amdgpu_device *adev,
 			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
 
 		if (amdgpu_irq_enabled(adev, source, irq_type)) {
-			drm_handle_vblank(adev->ddev, crtc);
+			drm_handle_vblank(adev_to_drm(adev), crtc);
 		}
 		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
 		break;
@@ -3126,14 +3126,14 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev,
 	if (amdgpu_crtc == NULL)
 		return 0;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	works = amdgpu_crtc->pflip_works;
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
 						"AMDGPU_FLIP_SUBMITTED(%d)\n",
 						amdgpu_crtc->pflip_status,
 						AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return 0;
 	}
 
@@ -3145,7 +3145,7 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev,
 	if (works->event)
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
@@ -3233,7 +3233,7 @@ dce_v8_0_encoder_mode_set(struct drm_encoder *encoder,
 
 static void dce_v8_0_encoder_prepare(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(encoder->dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder);
 
@@ -3273,7 +3273,7 @@ static void dce_v8_0_encoder_prepare(struct drm_encoder *encoder)
 static void dce_v8_0_encoder_commit(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	/* need to call this here as we need the crtc set up */
 	amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
@@ -3373,7 +3373,7 @@ static void dce_v8_0_encoder_add(struct amdgpu_device *adev,
 				 uint32_t supported_device,
 				 u16 caps)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index d5ff7b6331ff..cc93577dee03 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -132,7 +132,7 @@ static const struct drm_crtc_funcs dce_virtual_crtc_funcs = {
 static void dce_virtual_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	unsigned type;
 
@@ -235,7 +235,7 @@ static int dce_virtual_crtc_init(struct amdgpu_device *adev, int index)
 	if (amdgpu_crtc == NULL)
 		return -ENOMEM;
 
-	drm_crtc_init(adev->ddev, &amdgpu_crtc->base, &dce_virtual_crtc_funcs);
+	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_virtual_crtc_funcs);
 
 	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
 	amdgpu_crtc->crtc_id = index;
@@ -374,24 +374,24 @@ static int dce_virtual_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->ddev->max_vblank_count = 0;
+	adev_to_drm(adev)->max_vblank_count = 0;
 
-	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	r = amdgpu_display_modeset_create_props(adev);
 	if (r)
 		return r;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	/* allocate crtcs, encoders, connectors */
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
@@ -403,7 +403,7 @@ static int dce_virtual_sw_init(void *handle)
 			return r;
 	}
 
-	drm_kms_helper_poll_init(adev->ddev);
+	drm_kms_helper_poll_init(adev_to_drm(adev));
 
 	adev->mode_info.mode_config_initialized = true;
 	return 0;
@@ -415,9 +415,9 @@ static int dce_virtual_sw_fini(void *handle)
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 
-	drm_kms_helper_poll_fini(adev->ddev);
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
 
-	drm_mode_config_cleanup(adev->ddev);
+	drm_mode_config_cleanup(adev_to_drm(adev));
 	/* clear crtcs pointer to avoid dce irq finish routine access freed data */
 	memset(adev->mode_info.crtcs, 0, sizeof(adev->mode_info.crtcs[0]) * AMDGPU_MAX_CRTCS);
 	adev->mode_info.mode_config_initialized = false;
@@ -602,7 +602,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 	if (!encoder)
 		return -ENOMEM;
 	encoder->possible_crtcs = 1 << index;
-	drm_encoder_init(adev->ddev, encoder, &dce_virtual_encoder_funcs,
+	drm_encoder_init(adev_to_drm(adev), encoder, &dce_virtual_encoder_funcs,
 			 DRM_MODE_ENCODER_VIRTUAL, NULL);
 	drm_encoder_helper_add(encoder, &dce_virtual_encoder_helper_funcs);
 
@@ -613,7 +613,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 	}
 
 	/* add a new connector */
-	drm_connector_init(adev->ddev, connector, &dce_virtual_connector_funcs,
+	drm_connector_init(adev_to_drm(adev), connector, &dce_virtual_connector_funcs,
 			   DRM_MODE_CONNECTOR_VIRTUAL);
 	drm_connector_helper_add(connector, &dce_virtual_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
@@ -663,14 +663,14 @@ static int dce_virtual_pageflip(struct amdgpu_device *adev,
 	if (amdgpu_crtc == NULL)
 		return 0;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	works = amdgpu_crtc->pflip_works;
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED) {
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
 			"AMDGPU_FLIP_SUBMITTED(%d)\n",
 			amdgpu_crtc->pflip_status,
 			AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return 0;
 	}
 
@@ -682,7 +682,7 @@ static int dce_virtual_pageflip(struct amdgpu_device *adev,
 	if (works->event)
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	amdgpu_bo_unref(&works->old_abo);
@@ -697,7 +697,7 @@ static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vbla
 	struct amdgpu_crtc *amdgpu_crtc = container_of(vblank_timer,
 						       struct amdgpu_crtc, vblank_timer);
 	struct drm_device *ddev = amdgpu_crtc->base.dev;
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
 	dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 1ab261836983..2eab808fffeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -251,7 +251,7 @@ static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 	int i, count;
 
 	ddev = dev_get_drvdata(dev);
-	adev = ddev->dev_private;
+	adev = drm_to_adev(ddev);
 	count = 0;
 
 	for (i = 0; i < DF_V3_6_MAX_COUNTERS; i++) {
@@ -646,7 +646,7 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 				  uint64_t config,
 				  uint64_t *count)
 {
-	uint32_t lo_base_addr, hi_base_addr, lo_val = 0, hi_val = 0;
+	uint32_t lo_base_addr = 0, hi_base_addr = 0, lo_val = 0, hi_val = 0;
 	*count = 0;
 
 	switch (adev->asic_type) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 65997ffaed45..d502e30f67d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3307,6 +3307,29 @@ static void gfx_v10_0_set_kiq_pm4_funcs(struct amdgpu_device *adev)
 	adev->gfx.kiq.pmf = &gfx_v10_0_kiq_pm4_funcs;
 }
 
+static void gfx_v10_0_init_spm_golden_registers(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_rlc_spm_10_0_nv10,
+						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_0_nv10));
+		break;
+	case CHIP_NAVI14:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_rlc_spm_10_1_nv14,
+						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_1_nv14));
+		break;
+	case CHIP_NAVI12:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_rlc_spm_10_1_2_nv12,
+						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_1_2_nv12));
+		break;
+	default:
+		break;
+	}
+}
+
 static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
@@ -3317,9 +3340,6 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 		soc15_program_register_sequence(adev,
 						golden_settings_gc_10_0_nv10,
 						(const u32)ARRAY_SIZE(golden_settings_gc_10_0_nv10));
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_rlc_spm_10_0_nv10,
-						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_0_nv10));
 		break;
 	case CHIP_NAVI14:
 		soc15_program_register_sequence(adev,
@@ -3328,9 +3348,6 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 		soc15_program_register_sequence(adev,
 						golden_settings_gc_10_1_nv14,
 						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_nv14));
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_rlc_spm_10_1_nv14,
-						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_1_nv14));
 		break;
 	case CHIP_NAVI12:
 		soc15_program_register_sequence(adev,
@@ -3339,9 +3356,6 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 		soc15_program_register_sequence(adev,
 						golden_settings_gc_10_1_2_nv12,
 						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_2_nv12));
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_rlc_spm_10_1_2_nv12,
-						(const u32)ARRAY_SIZE(golden_settings_gc_rlc_spm_10_1_2_nv12));
 		break;
 	case CHIP_SIENNA_CICHLID:
 		soc15_program_register_sequence(adev,
@@ -3360,6 +3374,7 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+	gfx_v10_0_init_spm_golden_registers(adev);
 }
 
 static void gfx_v10_0_scratch_init(struct amdgpu_device *adev)
@@ -4022,21 +4037,23 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev)
 	amdgpu_gfx_compute_queue_acquire(adev);
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX10_MEC_HPD_SIZE;
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_GTT,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		gfx_v10_0_mec_fini(adev);
-		return r;
-	}
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_GTT,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			gfx_v10_0_mec_fini(adev);
+			return r;
+		}
 
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
 		mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
@@ -4147,6 +4164,7 @@ static const struct amdgpu_gfx_funcs gfx_v10_0_gfx_funcs = {
 	.read_wave_sgprs = &gfx_v10_0_read_wave_sgprs,
 	.read_wave_vgprs = &gfx_v10_0_read_wave_vgprs,
 	.select_me_pipe_q = &gfx_v10_0_select_me_pipe_q,
+	.init_spm_golden = &gfx_v10_0_init_spm_golden_registers,
 };
 
 static void gfx_v10_0_gpu_early_init(struct amdgpu_device *adev)
@@ -6180,7 +6198,7 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 	struct v10_gfx_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.gfx_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->in_suspend) {
+	if (!amdgpu_in_reset(adev) && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
 		mutex_lock(&adev->srbm_mutex);
 		nv_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
@@ -6192,7 +6210,7 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 		mutex_unlock(&adev->srbm_mutex);
 		if (adev->gfx.me.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
-	} else if (adev->in_gpu_reset) {
+	} else if (amdgpu_in_reset(adev)) {
 		/* reset mqd with the backup copy */
 		if (adev->gfx.me.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
@@ -6433,6 +6451,10 @@ static int gfx_v10_0_kiq_init_register(struct amdgpu_ring *ring)
 	struct v10_compute_mqd *mqd = ring->mqd_ptr;
 	int j;
 
+	/* inactivate the queue */
+	if (amdgpu_sriov_vf(adev))
+		WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, 0);
+
 	/* disable wptr polling */
 	WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
@@ -6541,7 +6563,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring)
 
 	gfx_v10_0_kiq_setting(ring);
 
-	if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
@@ -6577,7 +6599,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct v10_compute_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->in_suspend) {
+	if (!amdgpu_in_reset(adev) && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
 		mutex_lock(&adev->srbm_mutex);
 		nv_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
@@ -6587,7 +6609,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
-	} else if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	} else if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
@@ -7033,8 +7055,7 @@ static int gfx_v10_0_soft_reset(void *handle)
 		   GRBM_STATUS__BCI_BUSY_MASK | GRBM_STATUS__SX_BUSY_MASK |
 		   GRBM_STATUS__TA_BUSY_MASK | GRBM_STATUS__DB_BUSY_MASK |
 		   GRBM_STATUS__CB_BUSY_MASK | GRBM_STATUS__GDS_BUSY_MASK |
-		   GRBM_STATUS__SPI_BUSY_MASK | GRBM_STATUS__GE_BUSY_NO_DMA_MASK
-		   | GRBM_STATUS__BCI_BUSY_MASK)) {
+		   GRBM_STATUS__SPI_BUSY_MASK | GRBM_STATUS__GE_BUSY_NO_DMA_MASK)) {
 		grbm_soft_reset = REG_SET_FIELD(grbm_soft_reset,
 						GRBM_SOFT_RESET, SOFT_RESET_CP,
 						1);
@@ -7159,7 +7180,7 @@ static int gfx_v10_0_early_init(void *handle)
 		break;
 	}
 
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 
 	gfx_v10_0_set_kiq_pm4_funcs(adev);
 	gfx_v10_0_set_ring_funcs(adev);
@@ -7263,10 +7284,8 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
-			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
-
-		/* only for Vega10 & Raven1 */
-		data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK;
+			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			  RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
@@ -7429,7 +7448,6 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 	    (AMD_CG_SUPPORT_GFX_MGCG |
 	     AMD_CG_SUPPORT_GFX_CGLS |
 	     AMD_CG_SUPPORT_GFX_CGCG |
-	     AMD_CG_SUPPORT_GFX_CGLS |
 	     AMD_CG_SUPPORT_GFX_3D_CGCG |
 	     AMD_CG_SUPPORT_GFX_3D_CGLS))
 		gfx_v10_0_enable_gui_idle_interrupt(adev, enable);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 33f1c4a46ebe..94b7e0531d09 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1343,21 +1343,22 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 	amdgpu_gfx_compute_queue_acquire(adev);
 
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX8_MEC_HPD_SIZE;
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_VRAM,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			return r;
+		}
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		return r;
-	}
-
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	return 0;
 }
@@ -3250,7 +3251,7 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev)
 		dev_warn(adev->dev,
 			 "Unknown chip type (%d) in function gfx_v8_0_tiling_mode_table_init() falling through to CHIP_CARRIZO\n",
 			 adev->asic_type);
-		/* fall through */
+		fallthrough;
 
 	case CHIP_CARRIZO:
 		modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
@@ -4632,7 +4633,7 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 
 	gfx_v8_0_kiq_setting(ring);
 
-	if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation));
@@ -4669,7 +4670,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->in_suspend) {
+	if (!amdgpu_in_reset(adev) && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct vi_mqd_allocation));
 		((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -4681,7 +4682,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(struct vi_mqd_allocation));
-	} else if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	} else if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation));
@@ -5294,7 +5295,7 @@ static int gfx_v8_0_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->gfx.num_gfx_rings = GFX8_NUM_GFX_RINGS;
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 	adev->gfx.funcs = &gfx_v8_0_gfx_funcs;
 	gfx_v8_0_set_ring_funcs(adev);
 	gfx_v8_0_set_irq_funcs(adev);
@@ -5342,10 +5343,9 @@ static int gfx_v8_0_late_init(void *handle)
 static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 						       bool enable)
 {
-	if (((adev->asic_type == CHIP_POLARIS11) ||
+	if ((adev->asic_type == CHIP_POLARIS11) ||
 	    (adev->asic_type == CHIP_POLARIS12) ||
-	    (adev->asic_type == CHIP_VEGAM)) &&
-	    adev->powerplay.pp_funcs->set_powergating_by_smu)
+	    (adev->asic_type == CHIP_VEGAM))
 		/* Send msg to SMU via Powerplay */
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, enable);
 
@@ -5879,8 +5879,7 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_CG,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
@@ -5901,8 +5900,7 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_MG,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	return 0;
@@ -5931,8 +5929,7 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_CG,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS)) {
@@ -5951,8 +5948,7 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_3D,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
@@ -5973,8 +5969,7 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_MG,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_GFX_RLC_LS) {
@@ -5989,8 +5984,7 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 				PP_BLOCK_GFX_RLC,
 				pp_support_state,
 				pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
@@ -6004,8 +5998,7 @@ static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 			PP_BLOCK_GFX_CP,
 			pp_support_state,
 			pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index cb9d60a4e05e..93c63ff3b35e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -691,6 +691,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_UTCL1_CNTL1, 0x30000000, 0x30000000)
 };
 
 static const struct soc15_reg_rlcg rlcg_access_gc_9_0[] = {
@@ -1938,22 +1939,23 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
 	/* take ownership of the relevant compute queues */
 	amdgpu_gfx_compute_queue_acquire(adev);
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX9_MEC_HPD_SIZE;
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_VRAM,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			gfx_v9_0_mec_fini(adev);
+			return r;
+		}
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		gfx_v9_0_mec_fini(adev);
-		return r;
-	}
-
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 
@@ -3684,7 +3686,7 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)
 
 	gfx_v9_0_kiq_setting(ring);
 
-	if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct v9_mqd_allocation));
@@ -3722,7 +3724,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct v9_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->in_suspend) {
+	if (!amdgpu_in_reset(adev) && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct v9_mqd_allocation));
 		((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -3734,7 +3736,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(struct v9_mqd_allocation));
-	} else if (adev->in_gpu_reset) { /* for GPU_RESET case */
+	} else if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct v9_mqd_allocation));
@@ -3928,7 +3930,7 @@ static int gfx_v9_0_hw_fini(void *handle)
 	/* Use deinitialize sequence from CAIL when unbinding device from driver,
 	 * otherwise KIQ is hanging when binding back
 	 */
-	if (!adev->in_gpu_reset && !adev->in_suspend) {
+	if (!amdgpu_in_reset(adev) && !adev->in_suspend) {
 		mutex_lock(&adev->srbm_mutex);
 		soc15_grbm_select(adev, adev->gfx.kiq.ring.me,
 				adev->gfx.kiq.ring.pipe,
@@ -4086,7 +4088,7 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
 	 *
 	 * also don't wait anymore for IRQ context
 	 * */
-	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+	if (r < 1 && (amdgpu_in_reset(adev) || in_interrupt()))
 		goto failed_kiq_read;
 
 	might_sleep();
@@ -4625,7 +4627,7 @@ static int gfx_v9_0_early_init(void *handle)
 		adev->gfx.num_gfx_rings = 0;
 	else
 		adev->gfx.num_gfx_rings = GFX9_NUM_GFX_RINGS;
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 	gfx_v9_0_set_kiq_pm4_funcs(adev);
 	gfx_v9_0_set_ring_funcs(adev);
 	gfx_v9_0_set_irq_funcs(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
index 46351db36922..bd85aed3523a 100755..100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
@@ -57,10 +57,10 @@ static const struct soc15_reg_entry gfx_v9_4_edc_counter_regs[] = {
 	/* SPI */
 	{ SOC15_REG_ENTRY(GC, 0, mmSPI_EDC_CNT), 0, 4, 1 },
 	/* SQ */
-	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 0, 4, 16 },
-	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_DED_CNT), 0, 4, 16 },
-	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_INFO), 0, 4, 16 },
-	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_SEC_CNT), 0, 4, 16 },
+	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 0, 8, 16 },
+	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_DED_CNT), 0, 8, 16 },
+	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_INFO), 0, 8, 16 },
+	{ SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_SEC_CNT), 0, 8, 16 },
 	/* SQC */
 	{ SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT), 0, 4, 6 },
 	{ SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 0, 4, 6 },
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 394e6f56948a..b882ac59879a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -31,6 +31,77 @@
 
 #include "soc15_common.h"
 
+static const char *gfxhub_client_ids[] = {
+	"CB/DB",
+	"Reserved",
+	"GE1",
+	"GE2",
+	"CPF",
+	"CPC",
+	"CPG",
+	"RLC",
+	"TCP",
+	"SQC (inst)",
+	"SQC (data)",
+	"SQG",
+	"Reserved",
+	"SDMA0",
+	"SDMA1",
+	"GCR",
+	"SDMA2",
+	"SDMA3",
+};
+
+static uint32_t gfxhub_v2_0_get_invalidate_req(unsigned int vmid,
+					       uint32_t flush_type)
+{
+	u32 req = 0;
+
+	/* invalidate using legacy mode on vmid*/
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
+			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
+
+	return req;
+}
+
+static void
+gfxhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
+					     uint32_t status)
+{
+	u32 cid = REG_GET_FIELD(status,
+				GCVM_L2_PROTECTION_FAULT_STATUS, CID);
+
+	dev_err(adev->dev,
+		"GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
+		status);
+	dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+		cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" : gfxhub_client_ids[cid],
+		cid);
+	dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
+	dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
+	dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
+	dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
+	dev_err(adev->dev, "\t RW: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, RW));
+}
+
 u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE);
@@ -360,6 +431,11 @@ void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
 	WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
 }
 
+static const struct amdgpu_vmhub_funcs gfxhub_v2_0_vmhub_funcs = {
+	.print_l2_protection_fault_status = gfxhub_v2_0_print_l2_protection_fault_status,
+	.get_invalidate_req = gfxhub_v2_0_get_invalidate_req,
+};
+
 void gfxhub_v2_0_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
@@ -390,4 +466,14 @@ void gfxhub_v2_0_init(struct amdgpu_device *adev)
 		mmGCVM_INVALIDATE_ENG0_REQ;
 	hub->eng_addr_distance = mmGCVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 -
 		mmGCVM_INVALIDATE_ENG0_ADDR_RANGE_LO32;
+
+	hub->vm_cntx_cntl_vm_fault = GCVM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__EXECUTE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK;
+
+	hub->vmhub_funcs = &gfxhub_v2_0_vmhub_funcs;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index fa0bca3e1f73..237a9ff5afa0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -31,6 +31,77 @@
 
 #include "soc15_common.h"
 
+static const char *gfxhub_client_ids[] = {
+	"CB/DB",
+	"Reserved",
+	"GE1",
+	"GE2",
+	"CPF",
+	"CPC",
+	"CPG",
+	"RLC",
+	"TCP",
+	"SQC (inst)",
+	"SQC (data)",
+	"SQG",
+	"Reserved",
+	"SDMA0",
+	"SDMA1",
+	"GCR",
+	"SDMA2",
+	"SDMA3",
+};
+
+static uint32_t gfxhub_v2_1_get_invalidate_req(unsigned int vmid,
+					       uint32_t flush_type)
+{
+	u32 req = 0;
+
+	/* invalidate using legacy mode on vmid*/
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
+	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
+			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
+
+	return req;
+}
+
+static void
+gfxhub_v2_1_print_l2_protection_fault_status(struct amdgpu_device *adev,
+					     uint32_t status)
+{
+	u32 cid = REG_GET_FIELD(status,
+				GCVM_L2_PROTECTION_FAULT_STATUS, CID);
+
+	dev_err(adev->dev,
+		"GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
+		status);
+	dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+		cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" : gfxhub_client_ids[cid],
+		cid);
+	dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
+	dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
+	dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
+	dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
+	dev_err(adev->dev, "\t RW: 0x%lx\n",
+		REG_GET_FIELD(status,
+		GCVM_L2_PROTECTION_FAULT_STATUS, RW));
+}
+
 u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE);
@@ -135,6 +206,12 @@ static void gfxhub_v2_1_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
 
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* Setup L2 cache */
 	tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_CNTL);
 	tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL, ENABLE_L2_CACHE, 1);
@@ -190,6 +267,12 @@ static void gfxhub_v2_1_enable_system_domain(struct amdgpu_device *adev)
 
 static void gfxhub_v2_1_disable_identity_aperture(struct amdgpu_device *adev)
 {
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32,
 		     0xFFFFFFFF);
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_HI32,
@@ -326,6 +409,13 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
 					  bool value)
 {
 	u32 tmp;
+
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL);
 	tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL,
 			    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
@@ -359,6 +449,11 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
 	WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
 }
 
+static const struct amdgpu_vmhub_funcs gfxhub_v2_1_vmhub_funcs = {
+	.print_l2_protection_fault_status = gfxhub_v2_1_print_l2_protection_fault_status,
+	.get_invalidate_req = gfxhub_v2_1_get_invalidate_req,
+};
+
 void gfxhub_v2_1_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
@@ -389,6 +484,16 @@ void gfxhub_v2_1_init(struct amdgpu_device *adev)
 		mmGCVM_INVALIDATE_ENG0_REQ;
 	hub->eng_addr_distance = mmGCVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 -
 		mmGCVM_INVALIDATE_ENG0_ADDR_RANGE_LO32;
+
+	hub->vm_cntx_cntl_vm_fault = GCVM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		GCVM_CONTEXT1_CNTL__EXECUTE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK;
+
+	hub->vmhub_funcs = &gfxhub_v2_1_vmhub_funcs;
 }
 
 int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index ec90c62078d9..31359e519d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -25,11 +25,10 @@
 #include "amdgpu.h"
 #include "amdgpu_atomfirmware.h"
 #include "gmc_v10_0.h"
+#include "umc_v8_7.h"
 
 #include "hdp/hdp_5_0_0_offset.h"
 #include "hdp/hdp_5_0_0_sh_mask.h"
-#include "gc/gc_10_1_0_sh_mask.h"
-#include "mmhub/mmhub_2_0_0_sh_mask.h"
 #include "athub/athub_2_0_0_sh_mask.h"
 #include "athub/athub_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_offset.h"
@@ -57,68 +56,31 @@ static const struct soc15_reg_golden golden_settings_navi10_hdp[] =
 };
 #endif
 
+static int gmc_v10_0_ecc_interrupt_state(struct amdgpu_device *adev,
+					 struct amdgpu_irq_src *src,
+					 unsigned type,
+					 enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
 static int
 gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 				   struct amdgpu_irq_src *src, unsigned type,
 				   enum amdgpu_interrupt_state state)
 {
-	struct amdgpu_vmhub *hub;
-	u32 tmp, reg, bits[AMDGPU_MAX_VMHUBS], i;
-
-	bits[AMDGPU_GFXHUB_0] = GCVM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		GCVM_CONTEXT1_CNTL__EXECUTE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK;
-
-	bits[AMDGPU_MMHUB_0] = MMVM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-		MMVM_CONTEXT1_CNTL__EXECUTE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK;
-
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
 		/* MM HUB */
-		hub = &adev->vmhub[AMDGPU_MMHUB_0];
-		for (i = 0; i < 16; i++) {
-			reg = hub->vm_context0_cntl + hub->ctx_distance * i;
-			tmp = RREG32(reg);
-			tmp &= ~bits[AMDGPU_MMHUB_0];
-			WREG32(reg, tmp);
-		}
-
+		amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, false);
 		/* GFX HUB */
-		hub = &adev->vmhub[AMDGPU_GFXHUB_0];
-		for (i = 0; i < 16; i++) {
-			reg = hub->vm_context0_cntl + hub->ctx_distance * i;
-			tmp = RREG32(reg);
-			tmp &= ~bits[AMDGPU_GFXHUB_0];
-			WREG32(reg, tmp);
-		}
+		amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, false);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
 		/* MM HUB */
-		hub = &adev->vmhub[AMDGPU_MMHUB_0];
-		for (i = 0; i < 16; i++) {
-			reg = hub->vm_context0_cntl + hub->ctx_distance * i;
-			tmp = RREG32(reg);
-			tmp |= bits[AMDGPU_MMHUB_0];
-			WREG32(reg, tmp);
-		}
-
+		amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, true);
 		/* GFX HUB */
-		hub = &adev->vmhub[AMDGPU_GFXHUB_0];
-		for (i = 0; i < 16; i++) {
-			reg = hub->vm_context0_cntl + hub->ctx_distance * i;
-			tmp = RREG32(reg);
-			tmp |= bits[AMDGPU_GFXHUB_0];
-			WREG32(reg, tmp);
-		}
+		amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, true);
 		break;
 	default:
 		break;
@@ -166,29 +128,8 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 			task_info.task_name, task_info.pid);
 		dev_err(adev->dev, "  in page starting at address 0x%016llx from client %d\n",
 			addr, entry->client_id);
-		if (!amdgpu_sriov_vf(adev)) {
-			dev_err(adev->dev,
-				"GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
-				status);
-			dev_err(adev->dev, "\t Faulty UTCL2 client ID: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, CID));
-			dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
-			dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
-			dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
-			dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
-			dev_err(adev->dev, "\t RW: 0x%lx\n",
-				REG_GET_FIELD(status,
-				GCVM_L2_PROTECTION_FAULT_STATUS, RW));
-		}
+		if (!amdgpu_sriov_vf(adev))
+			hub->vmhub_funcs->print_l2_protection_fault_status(adev, status);
 	}
 
 	return 0;
@@ -199,30 +140,20 @@ static const struct amdgpu_irq_src_funcs gmc_v10_0_irq_funcs = {
 	.process = gmc_v10_0_process_interrupt,
 };
 
-static void gmc_v10_0_set_irq_funcs(struct amdgpu_device *adev)
+static const struct amdgpu_irq_src_funcs gmc_v10_0_ecc_funcs = {
+	.set = gmc_v10_0_ecc_interrupt_state,
+	.process = amdgpu_umc_process_ecc_irq,
+};
+
+ static void gmc_v10_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->gmc.vm_fault.num_types = 1;
 	adev->gmc.vm_fault.funcs = &gmc_v10_0_irq_funcs;
-}
 
-static uint32_t gmc_v10_0_get_invalidate_req(unsigned int vmid,
-					     uint32_t flush_type)
-{
-	u32 req = 0;
-
-	/* invalidate using legacy mode on vmid*/
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
-			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
-	req = REG_SET_FIELD(req, GCVM_INVALIDATE_ENG0_REQ,
-			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
-
-	return req;
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->gmc.ecc_irq.num_types = 1;
+		adev->gmc.ecc_irq.funcs = &gmc_v10_0_ecc_funcs;
+	}
 }
 
 /**
@@ -265,7 +196,7 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 {
 	bool use_semaphore = gmc_v10_0_use_invalidate_semaphore(adev, vmhub);
 	struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
-	u32 inv_req = gmc_v10_0_get_invalidate_req(vmid, flush_type);
+	u32 inv_req = hub->vmhub_funcs->get_invalidate_req(vmid, flush_type);
 	u32 tmp;
 	/* Use register 17 for GART */
 	const unsigned eng = 17;
@@ -356,16 +287,17 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	 */
 	if (adev->gfx.kiq.ring.sched.ready &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev)) &&
-	    !adev->in_gpu_reset) {
-
+	    down_read_trylock(&adev->reset_sem)) {
 		struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
 		const unsigned eng = 17;
-		u32 inv_req = gmc_v10_0_get_invalidate_req(vmid, flush_type);
+		u32 inv_req = hub->vmhub_funcs->get_invalidate_req(vmid, flush_type);
 		u32 req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 		u32 ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
 				1 << vmid);
+
+		up_read(&adev->reset_sem);
 		return;
 	}
 
@@ -381,7 +313,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	if (!adev->mman.buffer_funcs_enabled ||
 	    !adev->ib_pool_ready ||
-	    adev->in_gpu_reset ||
+	    amdgpu_in_reset(adev) ||
 	    ring->sched.ready == false) {
 		gmc_v10_0_flush_vm_hub(adev, vmid, AMDGPU_GFXHUB_0, 0);
 		mutex_unlock(&adev->mman.gtt_window_lock);
@@ -459,7 +391,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 		spin_unlock(&adev->gfx.kiq.ring_lock);
 		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
 		if (r < 1) {
-			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			return -ETIME;
 		}
 
@@ -491,7 +423,7 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 {
 	bool use_semaphore = gmc_v10_0_use_invalidate_semaphore(ring->adev, ring->funcs->vmhub);
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0);
+	uint32_t req = hub->vmhub_funcs->get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
 	/*
@@ -641,6 +573,28 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev,
 	}
 }
 
+static unsigned gmc_v10_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+	u32 d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL);
+	unsigned size;
+
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = AMDGPU_VBIOS_VGA_ALLOCATION;
+	} else {
+		u32 viewport;
+		u32 pitch;
+
+		viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION);
+		pitch = RREG32_SOC15(DCE, 0, mmHUBPREQ0_DCSURF_SURFACE_PITCH);
+		size = (REG_GET_FIELD(viewport,
+					HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) *
+				REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) *
+				4);
+	}
+
+	return size;
+}
+
 static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v10_0_flush_gpu_tlb,
 	.flush_gpu_tlb_pasid = gmc_v10_0_flush_gpu_tlb_pasid,
@@ -648,7 +602,8 @@ static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.emit_pasid_mapping = gmc_v10_0_emit_pasid_mapping,
 	.map_mtype = gmc_v10_0_map_mtype,
 	.get_vm_pde = gmc_v10_0_get_vm_pde,
-	.get_vm_pte = gmc_v10_0_get_vm_pte
+	.get_vm_pte = gmc_v10_0_get_vm_pte,
+	.get_vbios_fb_size = gmc_v10_0_get_vbios_fb_size,
 };
 
 static void gmc_v10_0_set_gmc_funcs(struct amdgpu_device *adev)
@@ -657,12 +612,36 @@ static void gmc_v10_0_set_gmc_funcs(struct amdgpu_device *adev)
 		adev->gmc.gmc_funcs = &gmc_v10_0_gmc_funcs;
 }
 
+static void gmc_v10_0_set_umc_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+		adev->umc.max_ras_err_cnt_per_query = UMC_V8_7_TOTAL_CHANNEL_NUM;
+		adev->umc.channel_inst_num = UMC_V8_7_CHANNEL_INSTANCE_NUM;
+		adev->umc.umc_inst_num = UMC_V8_7_UMC_INSTANCE_NUM;
+		adev->umc.channel_offs = UMC_V8_7_PER_CHANNEL_OFFSET_SIENNA;
+		adev->umc.channel_idx_tbl = &umc_v8_7_channel_idx_tbl[0][0];
+		adev->umc.funcs = &umc_v8_7_funcs;
+		break;
+	default:
+		break;
+	}
+}
+
+
+static void gmc_v10_0_set_mmhub_funcs(struct amdgpu_device *adev)
+{
+	adev->mmhub.funcs = &mmhub_v2_0_funcs;
+}
+
 static int gmc_v10_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v10_0_set_mmhub_funcs(adev);
 	gmc_v10_0_set_gmc_funcs(adev);
 	gmc_v10_0_set_irq_funcs(adev);
+	gmc_v10_0_set_umc_funcs(adev);
 
 	adev->gmc.shared_aperture_start = 0x2000000000000000ULL;
 	adev->gmc.shared_aperture_end =
@@ -685,6 +664,10 @@ static int gmc_v10_0_late_init(void *handle)
 	if (r)
 		return r;
 
+	r = amdgpu_gmc_ras_late_init(adev);
+	if (r)
+		return r;
+
 	return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 }
 
@@ -789,36 +772,6 @@ static int gmc_v10_0_gart_init(struct amdgpu_device *adev)
 	return amdgpu_gart_table_vram_alloc(adev);
 }
 
-static unsigned gmc_v10_0_get_vbios_fb_size(struct amdgpu_device *adev)
-{
-	u32 d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL);
-	unsigned size;
-
-	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
-		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
-	} else {
-		u32 viewport;
-		u32 pitch;
-
-		viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION);
-		pitch = RREG32_SOC15(DCE, 0, mmHUBPREQ0_DCSURF_SURFACE_PITCH);
-		size = (REG_GET_FIELD(viewport,
-					HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) *
-				REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) *
-				4);
-	}
-	/* return 0 if the pre-OS buffer uses up most of vram */
-	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024)) {
-		DRM_ERROR("Warning: pre-OS buffer uses most of vram, \
-				be aware of gart table overwrite\n");
-		return 0;
-	}
-
-	return size;
-}
-
-
-
 static int gmc_v10_0_sw_init(void *handle)
 {
 	int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
@@ -830,7 +783,7 @@ static int gmc_v10_0_sw_init(void *handle)
 	else
 		gfxhub_v2_0_init(adev);
 
-	mmhub_v2_0_init(adev);
+	adev->mmhub.funcs->init(adev);
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
@@ -878,6 +831,14 @@ static int gmc_v10_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	if (!amdgpu_sriov_vf(adev)) {
+		/* interrupt sent to DF. */
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0,
+				      &adev->gmc.ecc_irq);
+		if (r)
+			return r;
+	}
+
 	/*
 	 * Set the internal MC address mask This is the max address of the GPU's
 	 * internal address space.
@@ -900,7 +861,7 @@ static int gmc_v10_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->gmc.stolen_size = gmc_v10_0_get_vbios_fb_size(adev);
+	amdgpu_gmc_get_vbios_allocations(adev);
 
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
@@ -991,7 +952,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	r = mmhub_v2_0_gart_enable(adev);
+	r = adev->mmhub.funcs->gart_enable(adev);
 	if (r)
 		return r;
 
@@ -1013,7 +974,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 		gfxhub_v2_1_set_fault_enable_default(adev, value);
 	else
 		gfxhub_v2_0_set_fault_enable_default(adev, value);
-	mmhub_v2_0_set_fault_enable_default(adev, value);
+	adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB_0, 0);
 	gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_GFXHUB_0, 0);
 
@@ -1038,6 +999,9 @@ static int gmc_v10_0_hw_init(void *handle)
 	if (r)
 		return r;
 
+	if (adev->umc.funcs && adev->umc.funcs->init_registers)
+		adev->umc.funcs->init_registers(adev);
+
 	return 0;
 }
 
@@ -1055,7 +1019,7 @@ static void gmc_v10_0_gart_disable(struct amdgpu_device *adev)
 		gfxhub_v2_1_gart_disable(adev);
 	else
 		gfxhub_v2_0_gart_disable(adev);
-	mmhub_v2_0_gart_disable(adev);
+	adev->mmhub.funcs->gart_disable(adev);
 	amdgpu_gart_table_vram_unpin(adev);
 }
 
@@ -1069,6 +1033,7 @@ static int gmc_v10_0_hw_fini(void *handle)
 		return 0;
 	}
 
+	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 	gmc_v10_0_gart_disable(adev);
 
@@ -1121,7 +1086,7 @@ static int gmc_v10_0_set_clockgating_state(void *handle,
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = mmhub_v2_0_set_clockgating(adev, state);
+	r = adev->mmhub.funcs->set_clockgating(adev, state);
 	if (r)
 		return r;
 
@@ -1136,7 +1101,7 @@ static void gmc_v10_0_get_clockgating_state(void *handle, u32 *flags)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	mmhub_v2_0_get_clockgating(adev, flags);
+	adev->mmhub.funcs->get_clockgating(adev, flags);
 
 	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
 	    adev->asic_type == CHIP_NAVY_FLOUNDER)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 538e7ee35cdf..95a9117e9564 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -805,16 +805,13 @@ static unsigned gmc_v6_0_get_vbios_fb_size(struct amdgpu_device *adev)
 	unsigned size;
 
 	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
-		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+		size = AMDGPU_VBIOS_VGA_ALLOCATION;
 	} else {
 		u32 viewport = RREG32(mmVIEWPORT_SIZE);
 		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
 			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
 			4);
 	}
-	/* return 0 if the pre-OS buffer uses up most of vram */
-	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
-		return 0;
 	return size;
 }
 
@@ -862,7 +859,7 @@ static int gmc_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->gmc.stolen_size = gmc_v6_0_get_vbios_fb_size(adev);
+	amdgpu_gmc_get_vbios_allocations(adev);
 
 	r = amdgpu_bo_init(adev);
 	if (r)
@@ -1136,6 +1133,7 @@ static const struct amdgpu_gmc_funcs gmc_v6_0_gmc_funcs = {
 	.set_prt = gmc_v6_0_set_prt,
 	.get_vm_pde = gmc_v6_0_get_vm_pde,
 	.get_vm_pte = gmc_v6_0_get_vm_pte,
+	.get_vbios_fb_size = gmc_v6_0_get_vbios_fb_size,
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v6_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index e18296dc1386..80c146df338a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -434,7 +434,7 @@ static int gmc_v7_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	int vmid;
 	unsigned int tmp;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	for (vmid = 1; vmid < 16; vmid++) {
@@ -970,16 +970,14 @@ static unsigned gmc_v7_0_get_vbios_fb_size(struct amdgpu_device *adev)
 	unsigned size;
 
 	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
-		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+		size = AMDGPU_VBIOS_VGA_ALLOCATION;
 	} else {
 		u32 viewport = RREG32(mmVIEWPORT_SIZE);
 		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
 			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
 			4);
 	}
-	/* return 0 if the pre-OS buffer uses up most of vram */
-	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
-		return 0;
+
 	return size;
 }
 
@@ -1035,7 +1033,7 @@ static int gmc_v7_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->gmc.stolen_size = gmc_v7_0_get_vbios_fb_size(adev);
+	amdgpu_gmc_get_vbios_allocations(adev);
 
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
@@ -1372,7 +1370,8 @@ static const struct amdgpu_gmc_funcs gmc_v7_0_gmc_funcs = {
 	.emit_pasid_mapping = gmc_v7_0_emit_pasid_mapping,
 	.set_prt = gmc_v7_0_set_prt,
 	.get_vm_pde = gmc_v7_0_get_vm_pde,
-	.get_vm_pte = gmc_v7_0_get_vm_pte
+	.get_vm_pte = gmc_v7_0_get_vm_pte,
+	.get_vbios_fb_size = gmc_v7_0_get_vbios_fb_size,
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v7_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index a9e722b8a458..9ab65ca7df77 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -635,7 +635,7 @@ static int gmc_v8_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	int vmid;
 	unsigned int tmp;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	for (vmid = 1; vmid < 16; vmid++) {
@@ -1087,16 +1087,14 @@ static unsigned gmc_v8_0_get_vbios_fb_size(struct amdgpu_device *adev)
 	unsigned size;
 
 	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
-		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+		size = AMDGPU_VBIOS_VGA_ALLOCATION;
 	} else {
 		u32 viewport = RREG32(mmVIEWPORT_SIZE);
 		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
 			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
 			4);
 	}
-	/* return 0 if the pre-OS buffer uses up most of vram */
-	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
-		return 0;
+
 	return size;
 }
 
@@ -1160,7 +1158,7 @@ static int gmc_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->gmc.stolen_size = gmc_v8_0_get_vbios_fb_size(adev);
+	amdgpu_gmc_get_vbios_allocations(adev);
 
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
@@ -1739,7 +1737,8 @@ static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
 	.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
 	.set_prt = gmc_v8_0_set_prt,
 	.get_vm_pde = gmc_v8_0_get_vm_pde,
-	.get_vm_pte = gmc_v8_0_get_vm_pte
+	.get_vm_pte = gmc_v8_0_get_vm_pte,
+	.get_vbios_fb_size = gmc_v8_0_get_vbios_fb_size,
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v8_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 6e4f3ff4810f..91629c2b1d5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -67,6 +67,222 @@
 #define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_HEIGHT__SHIFT                                       0x10
 #define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_WIDTH_MASK                                          0x00003FFFL
 #define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_HEIGHT_MASK                                         0x3FFF0000L
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0                                                                  0x049d
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX                                                         2
+
+
+static const char *gfxhub_client_ids[] = {
+	"CB",
+	"DB",
+	"IA",
+	"WD",
+	"CPF",
+	"CPC",
+	"CPG",
+	"RLC",
+	"TCP",
+	"SQC (inst)",
+	"SQC (data)",
+	"SQG",
+	"PA",
+};
+
+static const char *mmhub_client_ids_raven[][2] = {
+	[0][0] = "MP1",
+	[1][0] = "MP0",
+	[2][0] = "VCN",
+	[3][0] = "VCNU",
+	[4][0] = "HDP",
+	[5][0] = "DCE",
+	[13][0] = "UTCL2",
+	[19][0] = "TLS",
+	[26][0] = "OSS",
+	[27][0] = "SDMA0",
+	[0][1] = "MP1",
+	[1][1] = "MP0",
+	[2][1] = "VCN",
+	[3][1] = "VCNU",
+	[4][1] = "HDP",
+	[5][1] = "XDP",
+	[6][1] = "DBGU0",
+	[7][1] = "DCE",
+	[8][1] = "DCEDWB0",
+	[9][1] = "DCEDWB1",
+	[26][1] = "OSS",
+	[27][1] = "SDMA0",
+};
+
+static const char *mmhub_client_ids_renoir[][2] = {
+	[0][0] = "MP1",
+	[1][0] = "MP0",
+	[2][0] = "HDP",
+	[4][0] = "DCEDMC",
+	[5][0] = "DCEVGA",
+	[13][0] = "UTCL2",
+	[19][0] = "TLS",
+	[26][0] = "OSS",
+	[27][0] = "SDMA0",
+	[28][0] = "VCN",
+	[29][0] = "VCNU",
+	[30][0] = "JPEG",
+	[0][1] = "MP1",
+	[1][1] = "MP0",
+	[2][1] = "HDP",
+	[3][1] = "XDP",
+	[6][1] = "DBGU0",
+	[7][1] = "DCEDMC",
+	[8][1] = "DCEVGA",
+	[9][1] = "DCEDWB",
+	[26][1] = "OSS",
+	[27][1] = "SDMA0",
+	[28][1] = "VCN",
+	[29][1] = "VCNU",
+	[30][1] = "JPEG",
+};
+
+static const char *mmhub_client_ids_vega10[][2] = {
+	[0][0] = "MP0",
+	[1][0] = "UVD",
+	[2][0] = "UVDU",
+	[3][0] = "HDP",
+	[13][0] = "UTCL2",
+	[14][0] = "OSS",
+	[15][0] = "SDMA1",
+	[32+0][0] = "VCE0",
+	[32+1][0] = "VCE0U",
+	[32+2][0] = "XDMA",
+	[32+3][0] = "DCE",
+	[32+4][0] = "MP1",
+	[32+14][0] = "SDMA0",
+	[0][1] = "MP0",
+	[1][1] = "UVD",
+	[2][1] = "UVDU",
+	[3][1] = "DBGU0",
+	[4][1] = "HDP",
+	[5][1] = "XDP",
+	[14][1] = "OSS",
+	[15][1] = "SDMA0",
+	[32+0][1] = "VCE0",
+	[32+1][1] = "VCE0U",
+	[32+2][1] = "XDMA",
+	[32+3][1] = "DCE",
+	[32+4][1] = "DCEDWB",
+	[32+5][1] = "MP1",
+	[32+6][1] = "DBGU1",
+	[32+14][1] = "SDMA1",
+};
+
+static const char *mmhub_client_ids_vega12[][2] = {
+	[0][0] = "MP0",
+	[1][0] = "VCE0",
+	[2][0] = "VCE0U",
+	[3][0] = "HDP",
+	[13][0] = "UTCL2",
+	[14][0] = "OSS",
+	[15][0] = "SDMA1",
+	[32+0][0] = "DCE",
+	[32+1][0] = "XDMA",
+	[32+2][0] = "UVD",
+	[32+3][0] = "UVDU",
+	[32+4][0] = "MP1",
+	[32+15][0] = "SDMA0",
+	[0][1] = "MP0",
+	[1][1] = "VCE0",
+	[2][1] = "VCE0U",
+	[3][1] = "DBGU0",
+	[4][1] = "HDP",
+	[5][1] = "XDP",
+	[14][1] = "OSS",
+	[15][1] = "SDMA0",
+	[32+0][1] = "DCE",
+	[32+1][1] = "DCEDWB",
+	[32+2][1] = "XDMA",
+	[32+3][1] = "UVD",
+	[32+4][1] = "UVDU",
+	[32+5][1] = "MP1",
+	[32+6][1] = "DBGU1",
+	[32+15][1] = "SDMA1",
+};
+
+static const char *mmhub_client_ids_vega20[][2] = {
+	[0][0] = "XDMA",
+	[1][0] = "DCE",
+	[2][0] = "VCE0",
+	[3][0] = "VCE0U",
+	[4][0] = "UVD",
+	[5][0] = "UVD1U",
+	[13][0] = "OSS",
+	[14][0] = "HDP",
+	[15][0] = "SDMA0",
+	[32+0][0] = "UVD",
+	[32+1][0] = "UVDU",
+	[32+2][0] = "MP1",
+	[32+3][0] = "MP0",
+	[32+12][0] = "UTCL2",
+	[32+14][0] = "SDMA1",
+	[0][1] = "XDMA",
+	[1][1] = "DCE",
+	[2][1] = "DCEDWB",
+	[3][1] = "VCE0",
+	[4][1] = "VCE0U",
+	[5][1] = "UVD1",
+	[6][1] = "UVD1U",
+	[7][1] = "DBGU0",
+	[8][1] = "XDP",
+	[13][1] = "OSS",
+	[14][1] = "HDP",
+	[15][1] = "SDMA0",
+	[32+0][1] = "UVD",
+	[32+1][1] = "UVDU",
+	[32+2][1] = "DBGU1",
+	[32+3][1] = "MP1",
+	[32+4][1] = "MP0",
+	[32+14][1] = "SDMA1",
+};
+
+static const char *mmhub_client_ids_arcturus[][2] = {
+	[2][0] = "MP1",
+	[3][0] = "MP0",
+	[10][0] = "UTCL2",
+	[13][0] = "OSS",
+	[14][0] = "HDP",
+	[15][0] = "SDMA0",
+	[32+15][0] = "SDMA1",
+	[64+15][0] = "SDMA2",
+	[96+15][0] = "SDMA3",
+	[128+15][0] = "SDMA4",
+	[160+11][0] = "JPEG",
+	[160+12][0] = "VCN",
+	[160+13][0] = "VCNU",
+	[160+15][0] = "SDMA5",
+	[192+10][0] = "UTCL2",
+	[192+11][0] = "JPEG1",
+	[192+12][0] = "VCN1",
+	[192+13][0] = "VCN1U",
+	[192+15][0] = "SDMA6",
+	[224+15][0] = "SDMA7",
+	[0][1] = "DBGU1",
+	[1][1] = "XDP",
+	[2][1] = "MP1",
+	[3][1] = "MP0",
+	[13][1] = "OSS",
+	[14][1] = "HDP",
+	[15][1] = "SDMA0",
+	[32+15][1] = "SDMA1",
+	[32+15][1] = "SDMA1",
+	[64+15][1] = "SDMA2",
+	[96+15][1] = "SDMA3",
+	[128+15][1] = "SDMA4",
+	[160+11][1] = "JPEG",
+	[160+12][1] = "VCN",
+	[160+13][1] = "VCNU",
+	[160+15][1] = "SDMA5",
+	[192+11][1] = "JPEG1",
+	[192+12][1] = "VCN1",
+	[192+13][1] = "VCN1U",
+	[192+15][1] = "SDMA6",
+	[224+15][1] = "SDMA7",
+};
 
 static const u32 golden_settings_vega10_hdp[] =
 {
@@ -300,9 +516,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 {
 	struct amdgpu_vmhub *hub;
 	bool retry_fault = !!(entry->src_data[1] & 0x80);
-	uint32_t status = 0;
+	uint32_t status = 0, cid = 0, rw = 0;
 	u64 addr;
 	char hub_name[10];
+	const char *mmhub_cid;
 
 	addr = (u64)entry->src_data[0] << 12;
 	addr |= ((u64)entry->src_data[1] & 0xf) << 44;
@@ -337,6 +554,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			RREG32(hub->vm_l2_pro_fault_status);
 
 		status = RREG32(hub->vm_l2_pro_fault_status);
+		cid = REG_GET_FIELD(status,
+				    VM_L2_PROTECTION_FAULT_STATUS, CID);
+		rw = REG_GET_FIELD(status,
+				   VM_L2_PROTECTION_FAULT_STATUS, RW);
 		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
 	}
 
@@ -359,9 +580,37 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			dev_err(adev->dev,
 				"VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
 				status);
-			dev_err(adev->dev, "\t Faulty UTCL2 client ID: 0x%lx\n",
-				REG_GET_FIELD(status,
-				VM_L2_PROTECTION_FAULT_STATUS, CID));
+			if (hub == &adev->vmhub[AMDGPU_GFXHUB_0]) {
+				dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+					cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" : gfxhub_client_ids[cid],
+					cid);
+			} else {
+				switch (adev->asic_type) {
+				case CHIP_VEGA10:
+					mmhub_cid = mmhub_client_ids_vega10[cid][rw];
+					break;
+				case CHIP_VEGA12:
+					mmhub_cid = mmhub_client_ids_vega12[cid][rw];
+					break;
+				case CHIP_VEGA20:
+					mmhub_cid = mmhub_client_ids_vega20[cid][rw];
+					break;
+				case CHIP_ARCTURUS:
+					mmhub_cid = mmhub_client_ids_arcturus[cid][rw];
+					break;
+				case CHIP_RAVEN:
+					mmhub_cid = mmhub_client_ids_raven[cid][rw];
+					break;
+				case CHIP_RENOIR:
+					mmhub_cid = mmhub_client_ids_renoir[cid][rw];
+					break;
+				default:
+					mmhub_cid = NULL;
+					break;
+				}
+				dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+					mmhub_cid ? mmhub_cid : "unknown", cid);
+			}
 			dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
 				REG_GET_FIELD(status,
 				VM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
@@ -374,10 +623,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
 				REG_GET_FIELD(status,
 				VM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
-			dev_err(adev->dev, "\t RW: 0x%lx\n",
-				REG_GET_FIELD(status,
-				VM_L2_PROTECTION_FAULT_STATUS, RW));
-
+			dev_err(adev->dev, "\t RW: 0x%x\n", rw);
 		}
 	}
 
@@ -500,13 +746,14 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	 * as GFXOFF under bare metal
 	 */
 	if (adev->gfx.kiq.ring.sched.ready &&
-			(amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev)) &&
-			!adev->in_gpu_reset) {
+	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev)) &&
+	    down_read_trylock(&adev->reset_sem)) {
 		uint32_t req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 		uint32_t ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
 						   1 << vmid);
+		up_read(&adev->reset_sem);
 		return;
 	}
 
@@ -596,10 +843,10 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
-	if (ring->sched.ready) {
+	if (ring->sched.ready && down_read_trylock(&adev->reset_sem)) {
 		/* Vega20+XGMI caches PTEs in TC and TLB. Add a
 		 * heavy-weight TLB flush (type 2), which flushes
 		 * both. Due to a race condition with concurrent
@@ -626,6 +873,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 		if (r) {
 			amdgpu_ring_undo(ring);
 			spin_unlock(&adev->gfx.kiq.ring_lock);
+			up_read(&adev->reset_sem);
 			return -ETIME;
 		}
 
@@ -633,10 +881,11 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 		spin_unlock(&adev->gfx.kiq.ring_lock);
 		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
 		if (r < 1) {
-			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
+			up_read(&adev->reset_sem);
 			return -ETIME;
 		}
-
+		up_read(&adev->reset_sem);
 		return 0;
 	}
 
@@ -826,6 +1075,41 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags |= AMDGPU_PTE_SNOOPED;
 }
 
+static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+	u32 d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL);
+	unsigned size;
+
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = AMDGPU_VBIOS_VGA_ALLOCATION;
+	} else {
+		u32 viewport;
+
+		switch (adev->asic_type) {
+		case CHIP_RAVEN:
+		case CHIP_RENOIR:
+			viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION);
+			size = (REG_GET_FIELD(viewport,
+					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) *
+				REG_GET_FIELD(viewport,
+					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH) *
+				4);
+			break;
+		case CHIP_VEGA10:
+		case CHIP_VEGA12:
+		case CHIP_VEGA20:
+		default:
+			viewport = RREG32_SOC15(DCE, 0, mmSCL0_VIEWPORT_SIZE);
+			size = (REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
+				REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_WIDTH) *
+				4);
+			break;
+		}
+	}
+
+	return size;
+}
+
 static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
 	.flush_gpu_tlb_pasid = gmc_v9_0_flush_gpu_tlb_pasid,
@@ -833,7 +1117,8 @@ static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
 	.map_mtype = gmc_v9_0_map_mtype,
 	.get_vm_pde = gmc_v9_0_get_vm_pde,
-	.get_vm_pte = gmc_v9_0_get_vm_pte
+	.get_vm_pte = gmc_v9_0_get_vm_pte,
+	.get_vbios_fb_size = gmc_v9_0_get_vbios_fb_size,
 };
 
 static void gmc_v9_0_set_gmc_funcs(struct amdgpu_device *adev)
@@ -871,13 +1156,11 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
-	case CHIP_VEGA20:
-		adev->mmhub.funcs = &mmhub_v1_0_funcs;
-		break;
 	case CHIP_ARCTURUS:
 		adev->mmhub.funcs = &mmhub_v9_4_funcs;
 		break;
 	default:
+		adev->mmhub.funcs = &mmhub_v1_0_funcs;
 		break;
 	}
 }
@@ -901,38 +1184,12 @@ static int gmc_v9_0_early_init(void *handle)
 	return 0;
 }
 
-static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
-{
-
-	/*
-	 * TODO:
-	 * Currently there is a bug where some memory client outside
-	 * of the driver writes to first 8M of VRAM on S3 resume,
-	 * this overrides GART which by default gets placed in first 8M and
-	 * causes VM_FAULTS once GTT is accessed.
-	 * Keep the stolen memory reservation until the while this is not solved.
-	 * Also check code in gmc_v9_0_get_vbios_fb_size and gmc_v9_0_late_init
-	 */
-	switch (adev->asic_type) {
-	case CHIP_VEGA10:
-	case CHIP_RAVEN:
-	case CHIP_ARCTURUS:
-	case CHIP_RENOIR:
-		return true;
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	default:
-		return false;
-	}
-}
-
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
-	if (!gmc_v9_0_keep_stolen_memory(adev))
-		amdgpu_bo_late_init(adev);
+	amdgpu_bo_late_init(adev);
 
 	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
 	if (r)
@@ -969,10 +1226,8 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 {
 	u64 base = 0;
 
-	if (adev->asic_type == CHIP_ARCTURUS)
-		base = mmhub_v9_4_get_fb_location(adev);
-	else if (!amdgpu_sriov_vf(adev))
-		base = mmhub_v1_0_get_fb_location(adev);
+	if (!amdgpu_sriov_vf(adev))
+		base = adev->mmhub.funcs->get_fb_location(adev);
 
 	/* add the xgmi offset of the physical node */
 	base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
@@ -1066,50 +1321,18 @@ static int gmc_v9_0_gart_init(struct amdgpu_device *adev)
 	return amdgpu_gart_table_vram_alloc(adev);
 }
 
-static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev)
+/**
+ * gmc_v9_0_save_registers - saves regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This saves potential register values that should be
+ * restored upon resume
+ */
+static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
 {
-	u32 d1vga_control;
-	unsigned size;
-
-	/*
-	 * TODO Remove once GART corruption is resolved
-	 * Check related code in gmc_v9_0_sw_fini
-	 * */
-	if (gmc_v9_0_keep_stolen_memory(adev))
-		return 9 * 1024 * 1024;
-
-	d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL);
-	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
-		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
-	} else {
-		u32 viewport;
-
-		switch (adev->asic_type) {
-		case CHIP_RAVEN:
-		case CHIP_RENOIR:
-			viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION);
-			size = (REG_GET_FIELD(viewport,
-					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) *
-				REG_GET_FIELD(viewport,
-					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH) *
-				4);
-			break;
-		case CHIP_VEGA10:
-		case CHIP_VEGA12:
-		case CHIP_VEGA20:
-		default:
-			viewport = RREG32_SOC15(DCE, 0, mmSCL0_VIEWPORT_SIZE);
-			size = (REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
-				REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_WIDTH) *
-				4);
-			break;
-		}
-	}
-	/* return 0 if the pre-OS buffer uses up most of vram */
-	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
-		return 0;
-
-	return size;
+	if (adev->asic_type == CHIP_RAVEN)
+		adev->gmc.sdpif_register = RREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
 }
 
 static int gmc_v9_0_sw_init(void *handle)
@@ -1118,10 +1341,8 @@ static int gmc_v9_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	gfxhub_v1_0_init(adev);
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_init(adev);
-	else
-		mmhub_v1_0_init(adev);
+
+	adev->mmhub.funcs->init(adev);
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
@@ -1242,7 +1463,7 @@ static int gmc_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->gmc.stolen_size = gmc_v9_0_get_vbios_fb_size(adev);
+	amdgpu_gmc_get_vbios_allocations(adev);
 
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
@@ -1268,21 +1489,18 @@ static int gmc_v9_0_sw_init(void *handle)
 
 	amdgpu_vm_manager_init(adev);
 
+	gmc_v9_0_save_registers(adev);
+
 	return 0;
 }
 
 static int gmc_v9_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	void *stolen_vga_buf;
 
 	amdgpu_gmc_ras_fini(adev);
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
-
-	if (gmc_v9_0_keep_stolen_memory(adev))
-		amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
-
 	amdgpu_gart_table_vram_free(adev);
 	amdgpu_bo_fini(adev);
 	amdgpu_gart_fini(adev);
@@ -1297,7 +1515,7 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
 	case CHIP_VEGA10:
 		if (amdgpu_sriov_vf(adev))
 			break;
-		/* fall through */
+		fallthrough;
 	case CHIP_VEGA20:
 		soc15_program_register_sequence(adev,
 						golden_settings_mmhub_1_0_0,
@@ -1326,10 +1544,10 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
  *
  * This restores register values, saved at suspend.
  */
-static void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
+void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
 {
 	if (adev->asic_type == CHIP_RAVEN)
-		WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
+		WREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
 }
 
 /**
@@ -1353,10 +1571,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	if (adev->asic_type == CHIP_ARCTURUS)
-		r = mmhub_v9_4_gart_enable(adev);
-	else
-		r = mmhub_v1_0_gart_enable(adev);
+	r = adev->mmhub.funcs->gart_enable(adev);
 	if (r)
 		return r;
 
@@ -1391,11 +1606,10 @@ static int gmc_v9_0_hw_init(void *handle)
 						golden_settings_vega10_hdp,
 						ARRAY_SIZE(golden_settings_vega10_hdp));
 
+	if (adev->mmhub.funcs->update_power_gating)
+		adev->mmhub.funcs->update_power_gating(adev, true);
+
 	switch (adev->asic_type) {
-	case CHIP_RAVEN:
-		/* TODO for renoir */
-		mmhub_v1_0_update_power_gating(adev, true);
-		break;
 	case CHIP_ARCTURUS:
 		WREG32_FIELD15(HDP, 0, HDP_MMHUB_CNTL, HDP_MMHUB_GCC, 1);
 		break;
@@ -1421,10 +1635,7 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (!amdgpu_sriov_vf(adev)) {
 		gfxhub_v1_0_set_fault_enable_default(adev, value);
-		if (adev->asic_type == CHIP_ARCTURUS)
-			mmhub_v9_4_set_fault_enable_default(adev, value);
-		else
-			mmhub_v1_0_set_fault_enable_default(adev, value);
+		adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	}
 	for (i = 0; i < adev->num_vmhubs; ++i)
 		gmc_v9_0_flush_gpu_tlb(adev, 0, i, 0);
@@ -1438,20 +1649,6 @@ static int gmc_v9_0_hw_init(void *handle)
 }
 
 /**
- * gmc_v9_0_save_registers - saves regs
- *
- * @adev: amdgpu_device pointer
- *
- * This saves potential register values that should be
- * restored upon resume
- */
-static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
-{
-	if (adev->asic_type == CHIP_RAVEN)
-		adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
-}
-
-/**
  * gmc_v9_0_gart_disable - gart disable
  *
  * @adev: amdgpu_device pointer
@@ -1461,10 +1658,7 @@ static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
 static void gmc_v9_0_gart_disable(struct amdgpu_device *adev)
 {
 	gfxhub_v1_0_gart_disable(adev);
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_gart_disable(adev);
-	else
-		mmhub_v1_0_gart_disable(adev);
+	adev->mmhub.funcs->gart_disable(adev);
 	amdgpu_gart_table_vram_unpin(adev);
 }
 
@@ -1494,8 +1688,6 @@ static int gmc_v9_0_suspend(void *handle)
 	if (r)
 		return r;
 
-	gmc_v9_0_save_registers(adev);
-
 	return 0;
 }
 
@@ -1504,7 +1696,6 @@ static int gmc_v9_0_resume(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	gmc_v9_0_restore_registers(adev);
 	r = gmc_v9_0_hw_init(adev);
 	if (r)
 		return r;
@@ -1537,10 +1728,7 @@ static int gmc_v9_0_set_clockgating_state(void *handle,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_set_clockgating(adev, state);
-	else
-		mmhub_v1_0_set_clockgating(adev, state);
+	adev->mmhub.funcs->set_clockgating(adev, state);
 
 	athub_v1_0_set_clockgating(adev, state);
 
@@ -1551,10 +1739,7 @@ static void gmc_v9_0_get_clockgating_state(void *handle, u32 *flags)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_get_clockgating(adev, flags);
-	else
-		mmhub_v1_0_get_clockgating(adev, flags);
+	adev->mmhub.funcs->get_clockgating(adev, flags);
 
 	athub_v1_0_get_clockgating(adev, flags);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
index e0585e8c6c1b..c415c439f690 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
@@ -26,4 +26,6 @@
 
 extern const struct amd_ip_funcs gmc_v9_0_ip_funcs;
 extern const struct amdgpu_ip_block_version gmc_v9_0_ip_block;
+
+void gmc_v9_0_restore_registers(struct amdgpu_device *adev);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 7a51c615d22d..845306f63cdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -55,22 +55,18 @@ static int amdgpu_ih_clientid_jpeg[] = {
 static int jpeg_v2_5_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	if (adev->asic_type == CHIP_ARCTURUS) {
-		u32 harvest;
-		int i;
-
-		adev->jpeg.num_jpeg_inst = JPEG25_MAX_HW_INSTANCES_ARCTURUS;
-		for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
-			harvest = RREG32_SOC15(JPEG, i, mmCC_UVD_HARVESTING);
-			if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
-				adev->jpeg.harvest_config |= 1 << i;
-		}
+	u32 harvest;
+	int i;
 
-		if (adev->jpeg.harvest_config == (AMDGPU_JPEG_HARVEST_JPEG0 |
-						 AMDGPU_JPEG_HARVEST_JPEG1))
-			return -ENOENT;
-	} else
-		adev->jpeg.num_jpeg_inst = 1;
+	adev->jpeg.num_jpeg_inst = JPEG25_MAX_HW_INSTANCES_ARCTURUS;
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+		harvest = RREG32_SOC15(JPEG, i, mmCC_UVD_HARVESTING);
+		if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
+			adev->jpeg.harvest_config |= 1 << i;
+	}
+	if (adev->jpeg.harvest_config == (AMDGPU_JPEG_HARVEST_JPEG0 |
+					 AMDGPU_JPEG_HARVEST_JPEG1))
+		return -ENOENT;
 
 	jpeg_v2_5_set_dec_ring_funcs(adev);
 	jpeg_v2_5_set_irq_funcs(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index c41e5590a701..3a0dff53654d 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -460,15 +460,10 @@ static bool jpeg_v3_0_is_idle(void *handle)
 static int jpeg_v3_0_wait_for_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int ret;
 
-	ret = SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_JRBC_STATUS,
+	return SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_JRBC_STATUS,
 		UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
 		UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
-	if (ret)
-		return ret;
-
-	return ret;
 }
 
 static int jpeg_v3_0_set_clockgating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index dffcb93ecee5..45a902b1acb7 100755..100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -34,7 +34,7 @@
 #define mmDAGB0_CNTL_MISC2_RV 0x008f
 #define mmDAGB0_CNTL_MISC2_RV_BASE_IDX 0
 
-u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev)
+static u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(MMHUB, 0, mmMC_VM_FB_LOCATION_BASE);
 	u64 top = RREG32_SOC15(MMHUB, 0, mmMC_VM_FB_LOCATION_TOP);
@@ -51,7 +51,7 @@ u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev)
 	return base;
 }
 
-void mmhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+static void mmhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
@@ -297,20 +297,19 @@ static void mmhub_v1_0_program_invalidation(struct amdgpu_device *adev)
 	}
 }
 
-void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
+static void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 				bool enable)
 {
 	if (amdgpu_sriov_vf(adev))
 		return;
 
 	if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) {
-		if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_powergating_by_smu)
-			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
 
 	}
 }
 
-int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
+static int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
 {
 	if (amdgpu_sriov_vf(adev)) {
 		/*
@@ -338,7 +337,7 @@ int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
-void mmhub_v1_0_gart_disable(struct amdgpu_device *adev)
+static void mmhub_v1_0_gart_disable(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	u32 tmp;
@@ -373,7 +372,7 @@ void mmhub_v1_0_gart_disable(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  * @value: true redirects VM faults to the default page
  */
-void mmhub_v1_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
+static void mmhub_v1_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 {
 	u32 tmp;
 
@@ -415,7 +414,7 @@ void mmhub_v1_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 	WREG32_SOC15(MMHUB, 0, mmVM_L2_PROTECTION_FAULT_CNTL, tmp);
 }
 
-void mmhub_v1_0_init(struct amdgpu_device *adev)
+static void mmhub_v1_0_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 
@@ -525,7 +524,7 @@ static void mmhub_v1_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 		WREG32_SOC15(MMHUB, 0, mmATC_L2_MISC_CG, data);
 }
 
-int mmhub_v1_0_set_clockgating(struct amdgpu_device *adev,
+static int mmhub_v1_0_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state)
 {
 	if (amdgpu_sriov_vf(adev))
@@ -549,7 +548,7 @@ int mmhub_v1_0_set_clockgating(struct amdgpu_device *adev,
 	return 0;
 }
 
-void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
+static void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
 	int data, data1;
 
@@ -781,4 +780,13 @@ const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = {
 	.ras_late_init = amdgpu_mmhub_ras_late_init,
 	.query_ras_error_count = mmhub_v1_0_query_ras_error_count,
 	.reset_ras_error_count = mmhub_v1_0_reset_ras_error_count,
+	.get_fb_location = mmhub_v1_0_get_fb_location,
+	.init = mmhub_v1_0_init,
+	.gart_enable = mmhub_v1_0_gart_enable,
+	.set_fault_enable_default = mmhub_v1_0_set_fault_enable_default,
+	.gart_disable = mmhub_v1_0_gart_disable,
+	.set_clockgating = mmhub_v1_0_set_clockgating,
+	.get_clockgating = mmhub_v1_0_get_clockgating,
+	.setup_vm_pt_regs = mmhub_v1_0_setup_vm_pt_regs,
+	.update_power_gating = mmhub_v1_0_update_power_gating,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h
index c43319e8f945..d77f5b65a618 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h
@@ -25,18 +25,4 @@
 
 extern const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs;
 
-u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev);
-int mmhub_v1_0_gart_enable(struct amdgpu_device *adev);
-void mmhub_v1_0_gart_disable(struct amdgpu_device *adev);
-void mmhub_v1_0_set_fault_enable_default(struct amdgpu_device *adev,
-					 bool value);
-void mmhub_v1_0_init(struct amdgpu_device *adev);
-int mmhub_v1_0_set_clockgating(struct amdgpu_device *adev,
-			       enum amd_clockgating_state state);
-void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags);
-void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
-                                bool enable);
-void mmhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t page_table_base);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 757fa8e83f5b..2d88278c50bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -36,7 +36,130 @@
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid                       0x0070
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid_BASE_IDX              0
 
-void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+static const char *mmhub_client_ids_navi1x[][2] = {
+	[3][0] = "DCEDMC",
+	[4][0] = "DCEVGA",
+	[5][0] = "MP0",
+	[6][0] = "MP1",
+	[13][0] = "VMC",
+	[14][0] = "HDP",
+	[15][0] = "OSS",
+	[16][0] = "VCNU",
+	[17][0] = "JPEG",
+	[18][0] = "VCN",
+	[3][1] = "DCEDMC",
+	[4][1] = "DCEXFC",
+	[5][1] = "DCEVGA",
+	[6][1] = "DCEDWB",
+	[7][1] = "MP0",
+	[8][1] = "MP1",
+	[9][1] = "DBGU1",
+	[10][1] = "DBGU0",
+	[11][1] = "XDP",
+	[14][1] = "HDP",
+	[15][1] = "OSS",
+	[16][1] = "VCNU",
+	[17][1] = "JPEG",
+	[18][1] = "VCN",
+};
+
+static const char *mmhub_client_ids_sienna_cichlid[][2] = {
+	[3][0] = "DCEDMC",
+	[4][0] = "DCEVGA",
+	[5][0] = "MP0",
+	[6][0] = "MP1",
+	[8][0] = "VMC",
+	[9][0] = "VCNU0",
+	[10][0] = "JPEG",
+	[12][0] = "VCNU1",
+	[13][0] = "VCN1",
+	[14][0] = "HDP",
+	[15][0] = "OSS",
+	[32+11][0] = "VCN0",
+	[0][1] = "DBGU0",
+	[1][1] = "DBGU1",
+	[2][1] = "DCEDWB",
+	[3][1] = "DCEDMC",
+	[4][1] = "DCEVGA",
+	[5][1] = "MP0",
+	[6][1] = "MP1",
+	[7][1] = "XDP",
+	[9][1] = "VCNU0",
+	[10][1] = "JPEG",
+	[11][1] = "VCN0",
+	[12][1] = "VCNU1",
+	[13][1] = "VCN1",
+	[14][1] = "HDP",
+	[15][1] = "OSS",
+};
+
+static uint32_t mmhub_v2_0_get_invalidate_req(unsigned int vmid,
+					      uint32_t flush_type)
+{
+	u32 req = 0;
+
+	/* invalidate using legacy mode on vmid*/
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ,
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
+	req = REG_SET_FIELD(req, MMVM_INVALIDATE_ENG0_REQ,
+			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
+
+	return req;
+}
+
+static void
+mmhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
+					     uint32_t status)
+{
+	uint32_t cid, rw;
+	const char *mmhub_cid = NULL;
+
+	cid = REG_GET_FIELD(status,
+			    MMVM_L2_PROTECTION_FAULT_STATUS, CID);
+	rw = REG_GET_FIELD(status,
+			   MMVM_L2_PROTECTION_FAULT_STATUS, RW);
+
+	dev_err(adev->dev,
+		"MMVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
+		status);
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
+		mmhub_cid = mmhub_client_ids_navi1x[cid][rw];
+		break;
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		mmhub_cid = mmhub_client_ids_sienna_cichlid[cid][rw];
+		break;
+	default:
+		mmhub_cid = NULL;
+		break;
+	}
+	dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+		mmhub_cid ? mmhub_cid : "unknown", cid);
+	dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		MMVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
+	dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		MMVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
+	dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+		REG_GET_FIELD(status,
+		MMVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
+	dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+		REG_GET_FIELD(status,
+		MMVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
+	dev_err(adev->dev, "\t RW: 0x%x\n", rw);
+}
+
+static void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
@@ -134,6 +257,12 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
 
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* Setup L2 cache */
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL);
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL, ENABLE_L2_CACHE, 1);
@@ -189,6 +318,12 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
 
 static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev)
 {
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	WREG32_SOC15(MMHUB, 0,
 		     mmMMVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32,
 		     0xFFFFFFFF);
@@ -268,7 +403,7 @@ static void mmhub_v2_0_program_invalidation(struct amdgpu_device *adev)
 	}
 }
 
-int mmhub_v2_0_gart_enable(struct amdgpu_device *adev)
+static int mmhub_v2_0_gart_enable(struct amdgpu_device *adev)
 {
 	/* GART Enable. */
 	mmhub_v2_0_init_gart_aperture_regs(adev);
@@ -284,7 +419,7 @@ int mmhub_v2_0_gart_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
-void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
+static void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	u32 tmp;
@@ -315,9 +450,16 @@ void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  * @value: true redirects VM faults to the default page
  */
-void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
+static void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 {
 	u32 tmp;
+
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL);
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_PROTECTION_FAULT_CNTL,
 			    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
@@ -351,7 +493,12 @@ void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL, tmp);
 }
 
-void mmhub_v2_0_init(struct amdgpu_device *adev)
+static const struct amdgpu_vmhub_funcs mmhub_v2_0_vmhub_funcs = {
+	.print_l2_protection_fault_status = mmhub_v2_0_print_l2_protection_fault_status,
+	.get_invalidate_req = mmhub_v2_0_get_invalidate_req,
+};
+
+static void mmhub_v2_0_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 
@@ -381,6 +528,16 @@ void mmhub_v2_0_init(struct amdgpu_device *adev)
 		mmMMVM_INVALIDATE_ENG0_REQ;
 	hub->eng_addr_distance = mmMMVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 -
 		mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_LO32;
+
+	hub->vm_cntx_cntl_vm_fault = MMVM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
+		MMVM_CONTEXT1_CNTL__EXECUTE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK;
+
+	hub->vmhub_funcs = &mmhub_v2_0_vmhub_funcs;
 }
 
 static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
@@ -471,7 +628,7 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	}
 }
 
-int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
+static int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state)
 {
 	if (amdgpu_sriov_vf(adev))
@@ -495,7 +652,7 @@ int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
 	return 0;
 }
 
-void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
+static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
 	int data, data1;
 
@@ -528,3 +685,14 @@ void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 	if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
+
+const struct amdgpu_mmhub_funcs mmhub_v2_0_funcs = {
+	.ras_late_init = amdgpu_mmhub_ras_late_init,
+	.init = mmhub_v2_0_init,
+	.gart_enable = mmhub_v2_0_gart_enable,
+	.set_fault_enable_default = mmhub_v2_0_set_fault_enable_default,
+	.gart_disable = mmhub_v2_0_gart_disable,
+	.set_clockgating = mmhub_v2_0_set_clockgating,
+	.get_clockgating = mmhub_v2_0_get_clockgating,
+	.setup_vm_pt_regs = mmhub_v2_0_setup_vm_pt_regs,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
index 3ea4344f0315..f80f461d67da 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
@@ -23,15 +23,6 @@
 #ifndef __MMHUB_V2_0_H__
 #define __MMHUB_V2_0_H__
 
-int mmhub_v2_0_gart_enable(struct amdgpu_device *adev);
-void mmhub_v2_0_gart_disable(struct amdgpu_device *adev);
-void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
-					 bool value);
-void mmhub_v2_0_init(struct amdgpu_device *adev);
-int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
-			       enum amd_clockgating_state state);
-void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags);
-void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t page_table_base);
+extern const struct amdgpu_mmhub_funcs mmhub_v2_0_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 9979f54fef57..6c6ad529c65c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -36,7 +36,7 @@
 #define MMHUB_NUM_INSTANCES			2
 #define MMHUB_INSTANCE_REGISTER_OFFSET		0x3000
 
-u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev)
+static u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev)
 {
 	/* The base should be same b/t 2 mmhubs on Acrturus. Read one here. */
 	u64 base = RREG32_SOC15(MMHUB, 0, mmVMSHAREDVC0_MC_VM_FB_LOCATION_BASE);
@@ -97,7 +97,7 @@ static void mmhub_v9_4_init_gart_aperture_regs(struct amdgpu_device *adev,
 			    (u32)(adev->gmc.gart_end >> 44));
 }
 
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+static void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
 	int i;
@@ -375,7 +375,7 @@ static void mmhub_v9_4_program_invalidation(struct amdgpu_device *adev,
 	}
 }
 
-int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
+static int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 {
 	int i;
 
@@ -397,7 +397,7 @@ int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
-void mmhub_v9_4_gart_disable(struct amdgpu_device *adev)
+static void mmhub_v9_4_gart_disable(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	u32 tmp;
@@ -442,7 +442,7 @@ void mmhub_v9_4_gart_disable(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  * @value: true redirects VM faults to the default page
  */
-void mmhub_v9_4_set_fault_enable_default(struct amdgpu_device *adev, bool value)
+static void mmhub_v9_4_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 {
 	u32 tmp;
 	int i;
@@ -500,7 +500,7 @@ void mmhub_v9_4_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 	}
 }
 
-void mmhub_v9_4_init(struct amdgpu_device *adev)
+static void mmhub_v9_4_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub[MMHUB_NUM_INSTANCES] =
 		{&adev->vmhub[AMDGPU_MMHUB_0], &adev->vmhub[AMDGPU_MMHUB_1]};
@@ -630,7 +630,7 @@ static void mmhub_v9_4_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	}
 }
 
-int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
+static int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state)
 {
 	if (amdgpu_sriov_vf(adev))
@@ -650,7 +650,7 @@ int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
 	return 0;
 }
 
-void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags)
+static void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
 	int data, data1;
 
@@ -1628,4 +1628,12 @@ const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
 	.ras_late_init = amdgpu_mmhub_ras_late_init,
 	.query_ras_error_count = mmhub_v9_4_query_ras_error_count,
 	.reset_ras_error_count = mmhub_v9_4_reset_ras_error_count,
+	.get_fb_location = mmhub_v9_4_get_fb_location,
+	.init = mmhub_v9_4_init,
+	.gart_enable = mmhub_v9_4_gart_enable,
+	.set_fault_enable_default = mmhub_v9_4_set_fault_enable_default,
+	.gart_disable = mmhub_v9_4_gart_disable,
+	.set_clockgating = mmhub_v9_4_set_clockgating,
+	.get_clockgating = mmhub_v9_4_get_clockgating,
+	.setup_vm_pt_regs = mmhub_v9_4_setup_vm_pt_regs,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
index 1b979773776c..92404a8f66f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
@@ -25,16 +25,4 @@
 
 extern const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs;
 
-u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev);
-int mmhub_v9_4_gart_enable(struct amdgpu_device *adev);
-void mmhub_v9_4_gart_disable(struct amdgpu_device *adev);
-void mmhub_v9_4_set_fault_enable_default(struct amdgpu_device *adev,
-					 bool value);
-void mmhub_v9_4_init(struct amdgpu_device *adev);
-int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
-			       enum amd_clockgating_state state);
-void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags);
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t page_table_base);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 5fd67e1cc2a0..9c07014d9bd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -238,19 +238,15 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 	int timeout = AI_MAILBOX_POLL_FLR_TIMEDOUT;
-	int locked;
 
 	/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
-	 *
-	 * we can unlock the lock_reset to allow "amdgpu_job_timedout"
-	 * to run gpu_recover() after FLR_NOTIFICATION_CMPL received
-	 * which means host side had finished this VF's FLR.
 	 */
-	locked = mutex_trylock(&adev->lock_reset);
-	if (locked)
-		adev->in_gpu_reset = true;
+	if (!down_read_trylock(&adev->reset_sem))
+		return;
+
+	atomic_set(&adev->in_gpu_reset, 1);
 
 	do {
 		if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -261,14 +257,12 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	} while (timeout > 1);
 
 flr_done:
-	if (locked) {
-		adev->in_gpu_reset = false;
-		mutex_unlock(&adev->lock_reset);
-	}
+	atomic_set(&adev->in_gpu_reset, 0);
+	up_read(&adev->reset_sem);
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
-		&& adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)
+		&& (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index ce2bf1fb79ed..9c23abf9b140 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -259,19 +259,15 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 	int timeout = NV_MAILBOX_POLL_FLR_TIMEDOUT;
-	int locked;
 
 	/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
-	 *
-	 * we can unlock the lock_reset to allow "amdgpu_job_timedout"
-	 * to run gpu_recover() after FLR_NOTIFICATION_CMPL received
-	 * which means host side had finished this VF's FLR.
 	 */
-	locked = mutex_trylock(&adev->lock_reset);
-	if (locked)
-		adev->in_gpu_reset = true;
+	if (!down_read_trylock(&adev->reset_sem))
+		return;
+
+	atomic_set(&adev->in_gpu_reset, 1);
 
 	do {
 		if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -282,14 +278,13 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	} while (timeout > 1);
 
 flr_done:
-	if (locked) {
-		adev->in_gpu_reset = false;
-		mutex_unlock(&adev->lock_reset);
-	}
+	atomic_set(&adev->in_gpu_reset, 0);
+	up_read(&adev->reset_sem);
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
-		&& (adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
+		&& (amdgpu_device_has_job_running(adev) ||
+		adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 350f1bf063c6..74b1e7dc49a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -306,7 +306,8 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	} else {
 		WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 	}
-	navi10_ih_reroute_ih(adev);
+	if (adev->irq.ih1.ring_size)
+		navi10_ih_reroute_ih(adev);
 
 	if (unlikely(adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT)) {
 		if (ih->use_bus_addr) {
@@ -668,19 +669,26 @@ static int navi10_ih_sw_init(void *handle)
 	adev->irq.ih.use_doorbell = true;
 	adev->irq.ih.doorbell_index = adev->doorbell_index.ih << 1;
 
-	r = amdgpu_ih_ring_init(adev, &adev->irq.ih1, PAGE_SIZE, true);
-	if (r)
-		return r;
+	adev->irq.ih1.ring_size = 0;
+	adev->irq.ih2.ring_size = 0;
 
-	adev->irq.ih1.use_doorbell = true;
-	adev->irq.ih1.doorbell_index = (adev->doorbell_index.ih + 1) << 1;
+	if (adev->asic_type < CHIP_NAVI10) {
+		r = amdgpu_ih_ring_init(adev, &adev->irq.ih1, PAGE_SIZE, true);
+		if (r)
+			return r;
 
-	r = amdgpu_ih_ring_init(adev, &adev->irq.ih2, PAGE_SIZE, true);
-	if (r)
-		return r;
+		adev->irq.ih1.use_doorbell = true;
+		adev->irq.ih1.doorbell_index =
+					(adev->doorbell_index.ih + 1) << 1;
+
+		r = amdgpu_ih_ring_init(adev, &adev->irq.ih2, PAGE_SIZE, true);
+		if (r)
+			return r;
 
-	adev->irq.ih2.use_doorbell = true;
-	adev->irq.ih2.doorbell_index = (adev->doorbell_index.ih + 2) << 1;
+		adev->irq.ih2.use_doorbell = true;
+		adev->irq.ih2.doorbell_index =
+					(adev->doorbell_index.ih + 2) << 1;
+	}
 
 	r = amdgpu_irq_init(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index e629156173d3..eadc9526d33f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -302,6 +302,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 	uint32_t bif_doorbell_intr_cntl;
 	struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if);
 	struct ras_err_data err_data = {0, 0, 0, NULL};
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
 	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
@@ -312,28 +313,31 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 						RAS_CNTLR_INTERRUPT_CLEAR, 1);
 		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
 
-		/*
-		 * clear error status after ras_controller_intr according to
-		 * hw team and count ue number for query
-		 */
-		nbio_v7_4_query_ras_error_count(adev, &err_data);
-
-		/* logging on error counter and printing for awareness */
-		obj->err_data.ue_count += err_data.ue_count;
-		obj->err_data.ce_count += err_data.ce_count;
-
-		if (err_data.ce_count)
-			dev_info(adev->dev, "%ld correctable hardware "
-					"errors detected in %s block, "
-					"no user action is needed.\n",
-					obj->err_data.ce_count,
-					adev->nbio.ras_if->name);
-
-		if (err_data.ue_count)
-			dev_info(adev->dev, "%ld uncorrectable hardware "
-					"errors detected in %s block\n",
-					obj->err_data.ue_count,
-					adev->nbio.ras_if->name);
+		if (!ras->disable_ras_err_cnt_harvest) {
+			/*
+			 * clear error status after ras_controller_intr
+			 * according to hw team and count ue number
+			 * for query
+			 */
+			nbio_v7_4_query_ras_error_count(adev, &err_data);
+
+			/* logging on error cnt and printing for awareness */
+			obj->err_data.ue_count += err_data.ue_count;
+			obj->err_data.ce_count += err_data.ce_count;
+
+			if (err_data.ce_count)
+				dev_info(adev->dev, "%ld correctable hardware "
+						"errors detected in %s block, "
+						"no user action is needed.\n",
+						obj->err_data.ce_count,
+						adev->nbio.ras_if->name);
+
+			if (err_data.ue_count)
+				dev_info(adev->dev, "%ld uncorrectable hardware "
+						"errors detected in %s block\n",
+						obj->err_data.ue_count,
+						adev->nbio.ras_if->name);
+		}
 
 		dev_info(adev->dev, "RAS controller interrupt triggered "
 					"by NBIF error\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index da8024c2826e..4d1402356262 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -364,6 +364,7 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		return AMD_RESET_METHOD_MODE1;
 	default:
 		if (smu_baco_is_support(smu))
@@ -379,7 +380,7 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		dev_info(adev->dev, "GPU BACO reset\n");
+		dev_info(adev->dev, "BACO reset\n");
 
 		ret = smu_baco_enter(smu);
 		if (ret)
@@ -387,8 +388,10 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 		ret = smu_baco_exit(smu);
 		if (ret)
 			return ret;
-	} else
+	} else {
+		dev_info(adev->dev, "MODE1 reset\n");
 		ret = nv_asic_mode1_reset(adev);
+	}
 
 	return ret;
 }
@@ -689,6 +692,10 @@ static void nv_init_doorbell_index(struct amdgpu_device *adev)
 	adev->doorbell_index.sdma_doorbell_range = 20;
 }
 
+static void nv_pre_asic_init(struct amdgpu_device *adev)
+{
+}
+
 static const struct amdgpu_asic_funcs nv_asic_funcs =
 {
 	.read_disabled_bios = &nv_read_disabled_bios,
@@ -708,6 +715,7 @@ static const struct amdgpu_asic_funcs nv_asic_funcs =
 	.need_reset_on_init = &nv_need_reset_on_init,
 	.get_pcie_replay_count = &nv_get_pcie_replay_count,
 	.supports_baco = &nv_asic_supports_baco,
+	.pre_asic_init = &nv_pre_asic_init,
 };
 
 static int nv_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index d488d250805d..e16874f30d5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -179,12 +179,11 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 		}
 		break;
 	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		err = psp_init_ta_microcode(&adev->psp, chip_name);
 		if (err)
 			return err;
 		break;
-	case CHIP_NAVY_FLOUNDER:
-		break;
 	default:
 		BUG();
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 6c9614f77d33..75489313dbad 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -38,6 +38,8 @@
 #include "oss/osssys_4_0_sh_mask.h"
 
 MODULE_FIRMWARE("amdgpu/renoir_asd.bin");
+MODULE_FIRMWARE("amdgpu/renoir_ta.bin");
+
 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
 
@@ -45,7 +47,10 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
 	const char *chip_name;
+	char fw_name[30];
 	int err = 0;
+	const struct ta_firmware_header_v1_0 *ta_hdr;
+	DRM_DEBUG("\n");
 
 	switch (adev->asic_type) {
 	case CHIP_RENOIR:
@@ -56,6 +61,55 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 	}
 
 	err = psp_init_asd_microcode(psp, chip_name);
+	if (err)
+		goto out;
+
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
+	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
+	if (err) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+		dev_info(adev->dev,
+			 "psp v12.0: Failed to load firmware \"%s\"\n",
+			 fw_name);
+	} else {
+		err = amdgpu_ucode_validate(adev->psp.ta_fw);
+		if (err)
+			goto out2;
+
+		ta_hdr = (const struct ta_firmware_header_v1_0 *)
+				 adev->psp.ta_fw->data;
+		adev->psp.ta_hdcp_ucode_version =
+			le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
+		adev->psp.ta_hdcp_ucode_size =
+			le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
+		adev->psp.ta_hdcp_start_addr =
+			(uint8_t *)ta_hdr +
+			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+
+		adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
+
+		adev->psp.ta_dtm_ucode_version =
+			le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
+		adev->psp.ta_dtm_ucode_size =
+			le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
+		adev->psp.ta_dtm_start_addr =
+			(uint8_t *)adev->psp.ta_hdcp_start_addr +
+			le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+	}
+
+	return 0;
+
+out2:
+	release_firmware(adev->psp.ta_fw);
+	adev->psp.ta_fw = NULL;
+out:
+	if (err) {
+		dev_err(adev->dev,
+			"psp v12.0: Failed to load firmware \"%s\"\n",
+			fw_name);
+	}
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 1b449291f068..455d5e366c69 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -52,6 +52,8 @@
 #include "bif/bif_3_0_d.h"
 #include "bif/bif_3_0_sh_mask.h"
 
+#include "amdgpu_dm.h"
+
 static const u32 tahiti_golden_registers[] =
 {
 	mmAZALIA_SCLK_CONTROL, 0x00000030, 0x00000011,
@@ -1215,10 +1217,100 @@ static bool si_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
-//xxx: not implemented
+static void si_set_clk_bypass_mode(struct amdgpu_device *adev)
+{
+	u32 tmp, i;
+
+	tmp = RREG32(CG_SPLL_FUNC_CNTL);
+	tmp |= SPLL_BYPASS_EN;
+	WREG32(CG_SPLL_FUNC_CNTL, tmp);
+
+	tmp = RREG32(CG_SPLL_FUNC_CNTL_2);
+	tmp |= SPLL_CTLREQ_CHG;
+	WREG32(CG_SPLL_FUNC_CNTL_2, tmp);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (RREG32(SPLL_STATUS) & SPLL_CHG_STATUS)
+			break;
+		udelay(1);
+	}
+
+	tmp = RREG32(CG_SPLL_FUNC_CNTL_2);
+	tmp &= ~(SPLL_CTLREQ_CHG | SCLK_MUX_UPDATE);
+	WREG32(CG_SPLL_FUNC_CNTL_2, tmp);
+
+	tmp = RREG32(MPLL_CNTL_MODE);
+	tmp &= ~MPLL_MCLK_SEL;
+	WREG32(MPLL_CNTL_MODE, tmp);
+}
+
+static void si_spll_powerdown(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	tmp = RREG32(SPLL_CNTL_MODE);
+	tmp |= SPLL_SW_DIR_CONTROL;
+	WREG32(SPLL_CNTL_MODE, tmp);
+
+	tmp = RREG32(CG_SPLL_FUNC_CNTL);
+	tmp |= SPLL_RESET;
+	WREG32(CG_SPLL_FUNC_CNTL, tmp);
+
+	tmp = RREG32(CG_SPLL_FUNC_CNTL);
+	tmp |= SPLL_SLEEP;
+	WREG32(CG_SPLL_FUNC_CNTL, tmp);
+
+	tmp = RREG32(SPLL_CNTL_MODE);
+	tmp &= ~SPLL_SW_DIR_CONTROL;
+	WREG32(SPLL_CNTL_MODE, tmp);
+}
+
+static int si_gpu_pci_config_reset(struct amdgpu_device *adev)
+{
+	u32 i;
+	int r = -EINVAL;
+
+	dev_info(adev->dev, "GPU pci config reset\n");
+
+	/* set mclk/sclk to bypass */
+	si_set_clk_bypass_mode(adev);
+	/* powerdown spll */
+	si_spll_powerdown(adev);
+	/* disable BM */
+	pci_clear_master(adev->pdev);
+	/* reset */
+	amdgpu_device_pci_config_reset(adev);
+
+	udelay(100);
+
+	/* wait for asic to come out of reset */
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) {
+			/* enable BM */
+			pci_set_master(adev->pdev);
+			adev->has_hw_reset = true;
+			r = 0;
+			break;
+		}
+		udelay(1);
+	}
+
+	return r;
+}
+
 static int si_asic_reset(struct amdgpu_device *adev)
 {
-	return 0;
+	int r;
+
+	dev_info(adev->dev, "PCI CONFIG reset\n");
+
+	amdgpu_atombios_scratch_regs_engine_hung(adev, true);
+
+	r = si_gpu_pci_config_reset(adev);
+
+	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
+
+	return r;
 }
 
 static bool si_asic_supports_baco(struct amdgpu_device *adev)
@@ -1779,6 +1871,10 @@ static int si_set_vce_clocks(struct amdgpu_device *adev, u32 evclk, u32 ecclk)
 	return 0;
 }
 
+static void si_pre_asic_init(struct amdgpu_device *adev)
+{
+}
+
 static const struct amdgpu_asic_funcs si_asic_funcs =
 {
 	.read_disabled_bios = &si_read_disabled_bios,
@@ -1800,6 +1896,7 @@ static const struct amdgpu_asic_funcs si_asic_funcs =
 	.need_reset_on_init = &si_need_reset_on_init,
 	.get_pcie_replay_count = &si_get_pcie_replay_count,
 	.supports_baco = &si_asic_supports_baco,
+	.pre_asic_init = &si_pre_asic_init,
 };
 
 static uint32_t si_get_rev_id(struct amdgpu_device *adev)
@@ -2546,6 +2643,10 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+#if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
+		else if (amdgpu_device_has_dc_support(adev))
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
+#endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v6_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block);
@@ -2560,6 +2661,10 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+#if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
+		else if (amdgpu_device_has_dc_support(adev))
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
+#endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v6_4_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index d55bf64770c4..7fb240c4990c 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -508,14 +508,9 @@ static bool smu_v11_0_i2c_bus_lock(struct i2c_adapter *control)
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
 	/* Send  PPSMC_MSG_RequestI2CBus */
-	if (!adev->powerplay.pp_funcs->smu_i2c_bus_access)
-		goto Fail;
-
-
-	if (!adev->powerplay.pp_funcs->smu_i2c_bus_access(adev->powerplay.pp_handle, true))
+	if (!amdgpu_dpm_smu_i2c_bus_access(adev, true))
 		return true;
 
-Fail:
 	return false;
 }
 
@@ -523,16 +518,10 @@ static bool smu_v11_0_i2c_bus_unlock(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
-	/* Send  PPSMC_MSG_RequestI2CBus */
-	if (!adev->powerplay.pp_funcs->smu_i2c_bus_access)
-		goto Fail;
-
 	/* Send  PPSMC_MSG_ReleaseI2CBus */
-	if (!adev->powerplay.pp_funcs->smu_i2c_bus_access(adev->powerplay.pp_handle,
-							     false))
+	if (!amdgpu_dpm_smu_i2c_bus_access(adev, false))
 		return true;
 
-Fail:
 	return false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 84d811b6e48b..2f93c475d6d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -580,10 +580,13 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
+			dev_info(adev->dev, "BACO reset\n");
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
+			dev_info(adev->dev, "MODE2 reset\n");
 			return amdgpu_dpm_mode2_reset(adev);
 		default:
+			dev_info(adev->dev, "MODE1 reset\n");
 			return soc15_asic_mode1_reset(adev);
 	}
 }
@@ -1026,6 +1029,11 @@ static uint64_t soc15_get_pcie_replay_count(struct amdgpu_device *adev)
 	return (nak_r + nak_g);
 }
 
+static void soc15_pre_asic_init(struct amdgpu_device *adev)
+{
+	gmc_v9_0_restore_registers(adev);
+}
+
 static const struct amdgpu_asic_funcs soc15_asic_funcs =
 {
 	.read_disabled_bios = &soc15_read_disabled_bios,
@@ -1046,6 +1054,7 @@ static const struct amdgpu_asic_funcs soc15_asic_funcs =
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
 	.supports_baco = &soc15_supports_baco,
+	.pre_asic_init = &soc15_pre_asic_init,
 };
 
 static const struct amdgpu_asic_funcs vega20_asic_funcs =
@@ -1069,6 +1078,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
 	.supports_baco = &soc15_supports_baco,
+	.pre_asic_init = &soc15_pre_asic_init,
 };
 
 static int soc15_common_early_init(void *handle)
@@ -1449,7 +1459,8 @@ static void soc15_update_hdp_light_sleep(struct amdgpu_device *adev, bool enable
 	uint32_t def, data;
 
 	if (adev->asic_type == CHIP_VEGA20 ||
-		adev->asic_type == CHIP_ARCTURUS) {
+		adev->asic_type == CHIP_ARCTURUS ||
+		adev->asic_type == CHIP_RENOIR) {
 		def = data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_CTRL));
 
 		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
diff --git a/drivers/gpu/drm/amd/amdgpu/ta_rap_if.h b/drivers/gpu/drm/amd/amdgpu/ta_rap_if.h
new file mode 100644
index 000000000000..f14833fae07c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/ta_rap_if.h
@@ -0,0 +1,84 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _TA_RAP_IF_H
+#define _TA_RAP_IF_H
+
+/* Responses have bit 31 set */
+#define RSP_ID_MASK (1U << 31)
+#define RSP_ID(cmdId) (((uint32_t)(cmdId)) | RSP_ID_MASK)
+
+enum ta_rap_status {
+	TA_RAP_STATUS__SUCCESS                              = 1,
+	TA_RAP_STATUS__ERROR_GENERIC_FAILURE                = 2,
+	TA_RAP_STATUS__ERROR_CMD_NOT_SUPPORTED              = 3,
+	TA_RAP_STATUS__ERROR_INVALID_VALIDATION_METHOD      = 4,
+	TA_RAP_STATUS__ERROR_NULL_POINTER                   = 5,
+	TA_RAP_STATUS__ERROR_NOT_INITIALIZED                = 6,
+	TA_RAP_STATUS__ERROR_VALIDATION_FAILED              = 7,
+	TA_RAP_STATUS__ERROR_ASIC_NOT_SUPPORTED             = 8,
+	TA_RAP_STATUS__ERROR_OPERATION_NOT_PERMISSABLE      = 9,
+	TA_RAP_STATUS__ERROR_ALREADY_INIT                   = 10,
+};
+
+enum ta_rap_cmd {
+	TA_CMD_RAP__INITIALIZE              = 1,
+	TA_CMD_RAP__VALIDATE_L0             = 2,
+};
+
+enum ta_rap_validation_method {
+	METHOD_A           = 1,
+};
+
+struct ta_rap_cmd_input_data {
+	uint8_t reserved[8];
+};
+
+struct ta_rap_cmd_output_data {
+	uint32_t    last_subsection;
+	uint32_t    num_total_validate;
+	uint32_t    num_valid;
+	uint32_t    last_validate_addr;
+	uint32_t    last_validate_val;
+	uint32_t    last_validate_val_exptd;
+};
+
+union ta_rap_cmd_input {
+	struct ta_rap_cmd_input_data input;
+};
+
+union ta_rap_cmd_output {
+	struct ta_rap_cmd_output_data output;
+};
+
+struct ta_rap_shared_memory {
+	uint32_t                    cmd_id;
+	uint32_t                    validation_method_id;
+	uint32_t                    resp_id;
+	enum ta_rap_status          rap_status;
+	union ta_rap_cmd_input      rap_in_message;
+	union ta_rap_cmd_output     rap_out_message;
+	uint8_t                     reserved[64];
+};
+
+#endif  // #define _TA_RAP_IF_H
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
index 418cf097c918..5288617ca552 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -32,20 +32,6 @@
 
 #define UMC_6_INST_DIST			0x40000
 
-/*
- * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
- * is the index of 8KB block
- */
-#define ADDR_OF_8KB_BLOCK(addr)			(((addr) & ~0xffULL) << 5)
-/* channel index is the index of 256B block */
-#define ADDR_OF_256B_BLOCK(channel_index)	((channel_index) << 8)
-/* offset in 256B block */
-#define OFFSET_IN_256B_BLOCK(addr)		((addr) & 0xffULL)
-
-#define LOOP_UMC_INST(umc_inst) for ((umc_inst) = 0; (umc_inst) < adev->umc.umc_inst_num; (umc_inst)++)
-#define LOOP_UMC_CH_INST(ch_inst) for ((ch_inst) = 0; (ch_inst) < adev->umc.channel_inst_num; (ch_inst)++)
-#define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst))
-
 const uint32_t
 	umc_v6_1_channel_idx_tbl[UMC_V6_1_UMC_INSTANCE_NUM][UMC_V6_1_CHANNEL_INSTANCE_NUM] = {
 		{2, 18, 11, 27},	{4, 20, 13, 29},
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c
new file mode 100644
index 000000000000..5665c77a9d58
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c
@@ -0,0 +1,331 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "umc_v8_7.h"
+#include "amdgpu_ras.h"
+#include "amdgpu.h"
+
+#include "rsmu/rsmu_0_0_2_offset.h"
+#include "rsmu/rsmu_0_0_2_sh_mask.h"
+#include "umc/umc_8_7_0_offset.h"
+#include "umc/umc_8_7_0_sh_mask.h"
+
+#define UMC_8_INST_DIST			0x40000
+
+const uint32_t
+	umc_v8_7_channel_idx_tbl[UMC_V8_7_UMC_INSTANCE_NUM][UMC_V8_7_CHANNEL_INSTANCE_NUM] = {
+		{2, 11},  {4, 13},
+		{1, 8},   {7, 14},
+		{10, 3},  {12, 5},
+		{9, 0},   {15, 6}
+};
+
+static inline uint32_t get_umc_8_reg_offset(struct amdgpu_device *adev,
+					    uint32_t umc_inst,
+					    uint32_t ch_inst)
+{
+	return adev->umc.channel_offs*ch_inst + UMC_8_INST_DIST*umc_inst;
+}
+
+static void umc_v8_7_clear_error_count_per_channel(struct amdgpu_device *adev,
+					uint32_t umc_reg_offset)
+{
+	uint32_t ecc_err_cnt_addr;
+	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
+
+	ecc_err_cnt_sel_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCntSel);
+	ecc_err_cnt_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCnt);
+
+	/* select the lower chip */
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr +
+					umc_reg_offset) * 4);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel,
+					UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 0);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4,
+			ecc_err_cnt_sel);
+
+	/* clear lower chip error count */
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4,
+			UMC_V8_7_CE_CNT_INIT);
+
+	/* select the higher chip */
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr +
+					umc_reg_offset) * 4);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel,
+					UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 1);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4,
+			ecc_err_cnt_sel);
+
+	/* clear higher chip error count */
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4,
+			UMC_V8_7_CE_CNT_INIT);
+}
+
+static void umc_v8_7_clear_error_count(struct amdgpu_device *adev)
+{
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_8_reg_offset(adev,
+						umc_inst,
+						ch_inst);
+
+		umc_v8_7_clear_error_count_per_channel(adev,
+						umc_reg_offset);
+	}
+}
+
+static void umc_v8_7_query_correctable_error_count(struct amdgpu_device *adev,
+						   uint32_t umc_reg_offset,
+						   unsigned long *error_count)
+{
+	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
+	uint32_t ecc_err_cnt, ecc_err_cnt_addr;
+	uint64_t mc_umc_status;
+	uint32_t mc_umc_status_addr;
+
+	/* UMC 8_7_2 registers */
+	ecc_err_cnt_sel_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCntSel);
+	ecc_err_cnt_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCnt);
+	mc_umc_status_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+
+	/* select the lower chip and check the error count */
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 0);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
+	*error_count +=
+		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_GeccErrCnt, GeccErrCnt) -
+		 UMC_V8_7_CE_CNT_INIT);
+
+	/* select the higher chip and check the err counter */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 1);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
+	*error_count +=
+		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_GeccErrCnt, GeccErrCnt) -
+		 UMC_V8_7_CE_CNT_INIT);
+
+	/* check for SRAM correctable error
+	  MCUMC_STATUS is a 64 bit register */
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
+	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 6 &&
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
+		*error_count += 1;
+}
+
+static void umc_v8_7_querry_uncorrectable_error_count(struct amdgpu_device *adev,
+						      uint32_t umc_reg_offset,
+						      unsigned long *error_count)
+{
+	uint64_t mc_umc_status;
+	uint32_t mc_umc_status_addr;
+
+	mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+
+	/* check the MCUMC_STATUS */
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
+	if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
+		*error_count += 1;
+}
+
+static void umc_v8_7_query_ras_error_count(struct amdgpu_device *adev,
+					   void *ras_error_status)
+{
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_8_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v8_7_query_correctable_error_count(adev,
+						       umc_reg_offset,
+						       &(err_data->ce_count));
+		umc_v8_7_querry_uncorrectable_error_count(adev,
+							  umc_reg_offset,
+							  &(err_data->ue_count));
+	}
+
+	umc_v8_7_clear_error_count(adev);
+}
+
+static void umc_v8_7_query_error_address(struct amdgpu_device *adev,
+					 struct ras_err_data *err_data,
+					 uint32_t umc_reg_offset,
+					 uint32_t ch_inst,
+					 uint32_t umc_inst)
+{
+	uint32_t lsb, mc_umc_status_addr;
+	uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0;
+	struct eeprom_table_record *err_rec;
+	uint32_t channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst];
+
+	mc_umc_status_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	mc_umc_addrt0 =
+		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0);
+
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
+
+	if (mc_umc_status == 0)
+		return;
+
+	if (!err_data->err_addr) {
+		/* clear umc status */
+		WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
+		return;
+	}
+
+	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
+
+	/* calculate error address if ue/ce error is detected */
+	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) {
+
+		err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4);
+		/* the lowest lsb bits should be ignored */
+		lsb = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, LSB);
+		err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr);
+		err_addr &= ~((0x1ULL << lsb) - 1);
+
+		/* translate umc channel address to soc pa, 3 parts are included */
+		retired_page = ADDR_OF_8KB_BLOCK(err_addr) |
+				ADDR_OF_256B_BLOCK(channel_index) |
+				OFFSET_IN_256B_BLOCK(err_addr);
+
+		/* we only save ue error information currently, ce is skipped */
+		if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC)
+				== 1) {
+			err_rec->address = err_addr;
+			/* page frame address is saved */
+			err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT;
+			err_rec->ts = (uint64_t)ktime_get_real_seconds();
+			err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
+			err_rec->cu = 0;
+			err_rec->mem_channel = channel_index;
+			err_rec->mcumc_id = umc_inst;
+
+			err_data->err_addr_cnt++;
+		}
+	}
+
+	/* clear umc status */
+	WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
+}
+
+static void umc_v8_7_query_ras_error_address(struct amdgpu_device *adev,
+					     void *ras_error_status)
+{
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_8_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v8_7_query_error_address(adev,
+					     err_data,
+					     umc_reg_offset,
+					     ch_inst,
+					     umc_inst);
+	}
+}
+
+static void umc_v8_7_err_cnt_init_per_channel(struct amdgpu_device *adev,
+					      uint32_t umc_reg_offset)
+{
+	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
+	uint32_t ecc_err_cnt_addr;
+
+	ecc_err_cnt_sel_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCntSel);
+	ecc_err_cnt_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_GeccErrCnt);
+
+	/* select the lower chip and check the error count */
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 0);
+	/* set ce error interrupt type to APIC based interrupt */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_GeccErrCntSel,
+					GeccErrInt, 0x1);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	/* set error count to initial value */
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V8_7_CE_CNT_INIT);
+
+	/* select the higher chip and check the err counter */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_GeccErrCntSel,
+					GeccErrCntCsSel, 1);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V8_7_CE_CNT_INIT);
+}
+
+static void umc_v8_7_err_cnt_init(struct amdgpu_device *adev)
+{
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_8_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v8_7_err_cnt_init_per_channel(adev, umc_reg_offset);
+	}
+}
+
+const struct amdgpu_umc_funcs umc_v8_7_funcs = {
+	.err_cnt_init = umc_v8_7_err_cnt_init,
+	.ras_late_init = amdgpu_umc_ras_late_init,
+	.query_ras_error_count = umc_v8_7_query_ras_error_count,
+	.query_ras_error_address = umc_v8_7_query_ras_error_address,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h
new file mode 100644
index 000000000000..d4d0468e3df5
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __UMC_V8_7_H__
+#define __UMC_V8_7_H__
+
+#include "soc15_common.h"
+#include "amdgpu.h"
+
+/* HBM  Memory Channel Width */
+#define UMC_V8_7_HBM_MEMORY_CHANNEL_WIDTH	128
+/* number of umc channel instance with memory map register access */
+#define UMC_V8_7_CHANNEL_INSTANCE_NUM		2
+/* number of umc instance with memory map register access */
+#define UMC_V8_7_UMC_INSTANCE_NUM		8
+/* total channel instances in one umc block */
+#define UMC_V8_7_TOTAL_CHANNEL_NUM	(UMC_V8_7_CHANNEL_INSTANCE_NUM * UMC_V8_7_UMC_INSTANCE_NUM)
+/* UMC regiser per channel offset */
+#define UMC_V8_7_PER_CHANNEL_OFFSET_SIENNA	0x400
+
+/* EccErrCnt max value */
+#define UMC_V8_7_CE_CNT_MAX		0xffff
+/* umc ce interrupt threshold */
+#define UMC_V8_7_CE_INT_THRESHOLD	0xffff
+/* umc ce count initial value */
+#define UMC_V8_7_CE_CNT_INIT	(UMC_V8_7_CE_CNT_MAX - UMC_V8_7_CE_INT_THRESHOLD)
+
+extern const struct amdgpu_umc_funcs umc_v8_7_funcs;
+extern const uint32_t
+	umc_v8_7_channel_idx_tbl[UMC_V8_7_UMC_INSTANCE_NUM][UMC_V8_7_CHANNEL_INSTANCE_NUM];
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index e99bef6e2354..139fac0d8e76 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -80,23 +80,18 @@ static int vcn_v2_5_early_init(void *handle)
 		adev->vcn.harvest_config = 0;
 		adev->vcn.num_enc_rings = 1;
 	} else {
-		if (adev->asic_type == CHIP_ARCTURUS) {
-			u32 harvest;
-			int i;
-
-			adev->vcn.num_vcn_inst = VCN25_MAX_HW_INSTANCES_ARCTURUS;
-			for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-				harvest = RREG32_SOC15(VCN, i, mmCC_UVD_HARVESTING);
-				if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
-					adev->vcn.harvest_config |= 1 << i;
-			}
-
-			if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 |
-						AMDGPU_VCN_HARVEST_VCN1))
-				/* both instances are harvested, disable the block */
-				return -ENOENT;
-		} else
-			adev->vcn.num_vcn_inst = 1;
+		u32 harvest;
+		int i;
+		adev->vcn.num_vcn_inst = VCN25_MAX_HW_INSTANCES_ARCTURUS;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+			harvest = RREG32_SOC15(VCN, i, mmCC_UVD_HARVESTING);
+			if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
+				adev->vcn.harvest_config |= 1 << i;
+		}
+		if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 |
+					AMDGPU_VCN_HARVEST_VCN1))
+			/* both instances are harvested, disable the block */
+			return -ENOENT;
 
 		adev->vcn.num_enc_rings = 2;
 	}
@@ -1108,7 +1103,7 @@ static int vcn_v2_5_mmsch_start(struct amdgpu_device *adev,
 {
 	uint32_t data = 0, loop = 0, size = 0;
 	uint64_t addr = table->gpu_addr;
-	struct mmsch_v1_1_init_header *header = NULL;;
+	struct mmsch_v1_1_init_header *header = NULL;
 
 	header = (struct mmsch_v1_1_init_header *)table->cpu_addr;
 	size = header->total_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 63e5547cfb16..589d6cd8adec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -198,7 +198,7 @@ static int vcn_v3_0_sw_init(void *handle)
 		} else {
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i;
 		}
-		if (i != 0)
+		if (adev->asic_type == CHIP_SIENNA_CICHLID && i != 0)
 			ring->no_scheduler = true;
 		sprintf(ring->name, "vcn_dec_%d", i);
 		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
@@ -222,7 +222,7 @@ static int vcn_v3_0_sw_init(void *handle)
 			} else {
 				ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i;
 			}
-			if (i != 1)
+			if (adev->asic_type == CHIP_SIENNA_CICHLID && i != 1)
 				ring->no_scheduler = true;
 			sprintf(ring->name, "vcn_enc_%d.%d", i, j);
 			r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index f6f2ed0830b1..9bcd0eebc6d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -752,8 +752,10 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		dev_info(adev->dev, "BACO reset\n");
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
+		dev_info(adev->dev, "PCI CONFIG reset\n");
 		r = vi_asic_pci_config_reset(adev);
 	}
 
@@ -1066,6 +1068,10 @@ static bool vi_need_reset_on_init(struct amdgpu_device *adev)
 	return false;
 }
 
+static void vi_pre_asic_init(struct amdgpu_device *adev)
+{
+}
+
 static const struct amdgpu_asic_funcs vi_asic_funcs =
 {
 	.read_disabled_bios = &vi_read_disabled_bios,
@@ -1086,6 +1092,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.need_reset_on_init = &vi_need_reset_on_init,
 	.get_pcie_replay_count = &vi_get_pcie_replay_count,
 	.supports_baco = &vi_asic_supports_baco,
+	.pre_asic_init = &vi_pre_asic_init,
 };
 
 #define CZ_REV_BRISTOL(rev)	 \
@@ -1507,8 +1514,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_MC,
 			       pp_support_state,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
@@ -1526,8 +1532,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_SDMA,
 			       pp_support_state,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
@@ -1545,8 +1550,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_HDP,
 			       pp_support_state,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 
@@ -1560,8 +1564,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_BIF,
 			       PP_STATE_SUPPORT_LS,
 			        pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 	if (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG) {
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1573,8 +1576,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_BIF,
 			       PP_STATE_SUPPORT_CG,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_DRM_LS) {
@@ -1588,8 +1590,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_DRM,
 			       PP_STATE_SUPPORT_LS,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG) {
@@ -1603,8 +1604,7 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 			       PP_BLOCK_SYS_ROM,
 			       PP_STATE_SUPPORT_CG,
 			       pp_state);
-		if (adev->powerplay.pp_funcs->set_clockgating_by_smu)
-			amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
+		amdgpu_dpm_set_clockgating_by_smu(adev, msg_id);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 577d901fdb63..affbca7c0050 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -911,7 +911,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0x705d0000, 0x807c817c,
 	0x8070ff70, 0x00000080,
 	0xbf0a7b7c, 0xbf85fff8,
-	0xbf82014f, 0xbef4037e,
+	0xbf820151, 0xbef4037e,
 	0x8775ff7f, 0x0000ffff,
 	0x8875ff75, 0x00040000,
 	0xbef60380, 0xbef703ff,
@@ -1024,61 +1024,62 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0xbe883108, 0xbe8a310a,
 	0xbe8c310c, 0xbe8e310e,
 	0xbf06807c, 0xbf84fff0,
-	0xb9782a05, 0x80788178,
-	0xbf0d9972, 0xbf850002,
-	0x8f788978, 0xbf820001,
-	0x8f788a78, 0xb96e1e06,
-	0x8f6e8a6e, 0x80786e78,
-	0x8078ff78, 0x00000200,
-	0xbef603ff, 0x01000000,
-	0xf4211bfa, 0xf0000000,
-	0x80788478, 0xf4211b3a,
+	0xba80f801, 0x00000000,
+	0xbf8a0000, 0xb9782a05,
+	0x80788178, 0xbf0d9972,
+	0xbf850002, 0x8f788978,
+	0xbf820001, 0x8f788a78,
+	0xb96e1e06, 0x8f6e8a6e,
+	0x80786e78, 0x8078ff78,
+	0x00000200, 0xbef603ff,
+	0x01000000, 0xf4211bfa,
 	0xf0000000, 0x80788478,
-	0xf4211b7a, 0xf0000000,
-	0x80788478, 0xf4211c3a,
+	0xf4211b3a, 0xf0000000,
+	0x80788478, 0xf4211b7a,
 	0xf0000000, 0x80788478,
-	0xf4211c7a, 0xf0000000,
-	0x80788478, 0xf4211eba,
+	0xf4211c3a, 0xf0000000,
+	0x80788478, 0xf4211c7a,
 	0xf0000000, 0x80788478,
-	0xf4211efa, 0xf0000000,
-	0x80788478, 0xf4211e7a,
+	0xf4211eba, 0xf0000000,
+	0x80788478, 0xf4211efa,
 	0xf0000000, 0x80788478,
-	0xf4211cfa, 0xf0000000,
-	0x80788478, 0xf4211bba,
+	0xf4211e7a, 0xf0000000,
+	0x80788478, 0xf4211cfa,
 	0xf0000000, 0x80788478,
-	0xbf8cc07f, 0xb9eef814,
 	0xf4211bba, 0xf0000000,
 	0x80788478, 0xbf8cc07f,
-	0xb9eef815, 0xbefc036f,
-	0xbefe0370, 0xbeff0371,
-	0x876f7bff, 0x000003ff,
-	0xb9ef4803, 0xb9f9f816,
-	0x876f7bff, 0xfffff800,
-	0x906f8b6f, 0xb9efa2c3,
-	0xb9f3f801, 0xb96e2a05,
-	0x806e816e, 0xbf0d9972,
-	0xbf850002, 0x8f6e896e,
-	0xbf820001, 0x8f6e8a6e,
-	0x806eff6e, 0x00000200,
-	0x806e746e, 0x826f8075,
-	0x876fff6f, 0x0000ffff,
-	0xf4091c37, 0xfa000050,
-	0xf4091d37, 0xfa000060,
-	0xf4011e77, 0xfa000074,
-	0xbf8cc07f, 0x876fff6d,
-	0xfc000000, 0x906f9a6f,
-	0x8f6f906f, 0xbeee0380,
+	0xb9eef814, 0xf4211bba,
+	0xf0000000, 0x80788478,
+	0xbf8cc07f, 0xb9eef815,
+	0xbefc036f, 0xbefe0370,
+	0xbeff0371, 0x876f7bff,
+	0x000003ff, 0xb9ef4803,
+	0xb9f9f816, 0x876f7bff,
+	0xfffff800, 0x906f8b6f,
+	0xb9efa2c3, 0xb9f3f801,
+	0xb96e2a05, 0x806e816e,
+	0xbf0d9972, 0xbf850002,
+	0x8f6e896e, 0xbf820001,
+	0x8f6e8a6e, 0x806eff6e,
+	0x00000200, 0x806e746e,
+	0x826f8075, 0x876fff6f,
+	0x0000ffff, 0xf4091c37,
+	0xfa000050, 0xf4091d37,
+	0xfa000060, 0xf4011e77,
+	0xfa000074, 0xbf8cc07f,
+	0x876fff6d, 0xfc000000,
+	0x906f9a6f, 0x8f6f906f,
+	0xbeee0380, 0x886e6f6e,
+	0x876fff6d, 0x02000000,
+	0x906f996f, 0x8f6f8f6f,
 	0x886e6f6e, 0x876fff6d,
-	0x02000000, 0x906f996f,
-	0x8f6f8f6f, 0x886e6f6e,
-	0x876fff6d, 0x01000000,
-	0x906f986f, 0x8f6f996f,
-	0x886e6f6e, 0x876fff7a,
-	0x00800000, 0x906f976f,
-	0xb9eef807, 0x876dff6d,
-	0x0000ffff, 0x87fe7e7e,
-	0x87ea6a6a, 0xb9faf802,
-	0xbf8a0000, 0xbe80226c,
+	0x01000000, 0x906f986f,
+	0x8f6f996f, 0x886e6f6e,
+	0x876fff7a, 0x00800000,
+	0x906f976f, 0xb9eef807,
+	0x876dff6d, 0x0000ffff,
+	0x87fe7e7e, 0x87ea6a6a,
+	0xb9faf802, 0xbe80226c,
 	0xbf810000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
@@ -1807,7 +1808,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x705d0000, 0x807c817c,
 	0x8070ff70, 0x00000080,
 	0xbf0a7b7c, 0xbf85fff8,
-	0xbf82013a, 0xbef4037e,
+	0xbf82013c, 0xbef4037e,
 	0x8775ff7f, 0x0000ffff,
 	0x8875ff75, 0x00040000,
 	0xbef60380, 0xbef703ff,
@@ -1920,50 +1921,51 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0xbe883108, 0xbe8a310a,
 	0xbe8c310c, 0xbe8e310e,
 	0xbf06807c, 0xbf84fff0,
-	0xb9782a05, 0x80788178,
-	0xbf0d9972, 0xbf850002,
-	0x8f788978, 0xbf820001,
-	0x8f788a78, 0xb96e1e06,
-	0x8f6e8a6e, 0x80786e78,
-	0x8078ff78, 0x00000200,
-	0xbef603ff, 0x01000000,
-	0xf4211bfa, 0xf0000000,
-	0x80788478, 0xf4211b3a,
+	0xba80f801, 0x00000000,
+	0xbf8a0000, 0xb9782a05,
+	0x80788178, 0xbf0d9972,
+	0xbf850002, 0x8f788978,
+	0xbf820001, 0x8f788a78,
+	0xb96e1e06, 0x8f6e8a6e,
+	0x80786e78, 0x8078ff78,
+	0x00000200, 0xbef603ff,
+	0x01000000, 0xf4211bfa,
 	0xf0000000, 0x80788478,
-	0xf4211b7a, 0xf0000000,
-	0x80788478, 0xf4211c3a,
+	0xf4211b3a, 0xf0000000,
+	0x80788478, 0xf4211b7a,
 	0xf0000000, 0x80788478,
-	0xf4211c7a, 0xf0000000,
-	0x80788478, 0xf4211eba,
+	0xf4211c3a, 0xf0000000,
+	0x80788478, 0xf4211c7a,
 	0xf0000000, 0x80788478,
-	0xf4211efa, 0xf0000000,
-	0x80788478, 0xf4211e7a,
+	0xf4211eba, 0xf0000000,
+	0x80788478, 0xf4211efa,
 	0xf0000000, 0x80788478,
-	0xf4211cfa, 0xf0000000,
-	0x80788478, 0xf4211bba,
+	0xf4211e7a, 0xf0000000,
+	0x80788478, 0xf4211cfa,
 	0xf0000000, 0x80788478,
-	0xbf8cc07f, 0xb9eef814,
 	0xf4211bba, 0xf0000000,
 	0x80788478, 0xbf8cc07f,
-	0xb9eef815, 0xbefc036f,
-	0xbefe0370, 0xbeff0371,
-	0x876f7bff, 0x000003ff,
-	0xb9ef4803, 0x876f7bff,
-	0xfffff800, 0x906f8b6f,
-	0xb9efa2c3, 0xb9f3f801,
-	0xb96e2a05, 0x806e816e,
-	0xbf0d9972, 0xbf850002,
-	0x8f6e896e, 0xbf820001,
-	0x8f6e8a6e, 0x806eff6e,
-	0x00000200, 0x806e746e,
-	0x826f8075, 0x876fff6f,
-	0x0000ffff, 0xf4091c37,
-	0xfa000050, 0xf4091d37,
-	0xfa000060, 0xf4011e77,
-	0xfa000074, 0xbf8cc07f,
-	0x876dff6d, 0x0000ffff,
-	0x87fe7e7e, 0x87ea6a6a,
-	0xb9faf802, 0xbf8a0000,
+	0xb9eef814, 0xf4211bba,
+	0xf0000000, 0x80788478,
+	0xbf8cc07f, 0xb9eef815,
+	0xbefc036f, 0xbefe0370,
+	0xbeff0371, 0x876f7bff,
+	0x000003ff, 0xb9ef4803,
+	0x876f7bff, 0xfffff800,
+	0x906f8b6f, 0xb9efa2c3,
+	0xb9f3f801, 0xb96e2a05,
+	0x806e816e, 0xbf0d9972,
+	0xbf850002, 0x8f6e896e,
+	0xbf820001, 0x8f6e8a6e,
+	0x806eff6e, 0x00000200,
+	0x806e746e, 0x826f8075,
+	0x876fff6f, 0x0000ffff,
+	0xf4091c37, 0xfa000050,
+	0xf4091d37, 0xfa000060,
+	0xf4011e77, 0xfa000074,
+	0xbf8cc07f, 0x876dff6d,
+	0x0000ffff, 0x87fe7e7e,
+	0x87ea6a6a, 0xb9faf802,
 	0xbe80226c, 0xbf810000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index 5b220f2a7501..5081f91190b8 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -894,6 +894,11 @@ L_RESTORE_SGPR:
 	s_cmp_eq_u32	m0, 0							//scc = (m0 < s_sgpr_save_num) ? 1 : 0
 	s_cbranch_scc0	L_RESTORE_SGPR_LOOP
 
+	// s_barrier with MODE.DEBUG_EN=1, STATUS.PRIV=1 incorrectly asserts debug exception.
+	// Clear DEBUG_EN before and restore MODE after the barrier.
+	s_setreg_imm32_b32	hwreg(HW_REG_MODE), 0
+	s_barrier								//barrier to ensure the readiness of LDS before access attemps from any other wave in the same TG
+
 	/* restore HW registers */
 L_RESTORE_HWREG:
 	// HWREG SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)
@@ -976,8 +981,6 @@ L_RESTORE_HWREG:
 	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
 	s_setreg_b32	hwreg(HW_REG_STATUS), s_restore_status			// SCC is included, which is changed by previous salu
 
-	s_barrier								//barrier to ensure the readiness of LDS before access attemps from any other wave in the same TG
-
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e9b96ad3d9a5..b7b16adb0615 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1254,7 +1254,7 @@ bool kfd_dev_is_large_bar(struct kfd_dev *dev)
 		return true;
 	}
 
-	if (dev->device_info->needs_iommu_device)
+	if (dev->use_iommu_v2)
 		return false;
 
 	amdgpu_amdkfd_get_local_mem_info(dev->kgd, &mem_info);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 6a250f8fcfb8..3fac06b281ce 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -742,6 +742,22 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 	return 0;
 }
 
+static bool kfd_ignore_crat(void)
+{
+	bool ret;
+
+	if (ignore_crat)
+		return true;
+
+#ifndef KFD_SUPPORT_IOMMU_V2
+	ret = true;
+#else
+	ret = false;
+#endif
+
+	return ret;
+}
+
 /*
  * kfd_create_crat_image_acpi - Allocates memory for CRAT image and
  * copies CRAT from ACPI (if available).
@@ -776,7 +792,7 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
 		return -EINVAL;
 	}
 
-	if (ignore_crat) {
+	if (kfd_ignore_crat()) {
 		pr_info("CRAT table disabled by module option\n");
 		return -ENODATA;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 4bfedaab183f..0e71a0543f98 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -29,6 +29,7 @@
 #include "cwsr_trap_handler.h"
 #include "kfd_iommu.h"
 #include "amdgpu_amdkfd.h"
+#include "kfd_smi_events.h"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -115,6 +116,7 @@ static const struct kfd_device_info carrizo_device_info = {
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
+#endif
 
 static const struct kfd_device_info raven_device_info = {
 	.asic_family = CHIP_RAVEN,
@@ -133,7 +135,6 @@ static const struct kfd_device_info raven_device_info = {
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
-#endif
 
 static const struct kfd_device_info hawaii_device_info = {
 	.asic_family = CHIP_HAWAII,
@@ -711,11 +712,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 		goto kfd_doorbell_error;
 	}
 
-	if (kfd->kfd2kgd->get_hive_id)
-		kfd->hive_id = kfd->kfd2kgd->get_hive_id(kfd->kgd);
+	kfd->hive_id = amdgpu_amdkfd_get_hive_id(kfd->kgd);
 
-	if (kfd->kfd2kgd->get_unique_id)
-		kfd->unique_id = kfd->kfd2kgd->get_unique_id(kfd->kgd);
+	kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd);
 
 	if (kfd_interrupt_init(kfd)) {
 		dev_err(kfd_device, "Error initializing interrupts\n");
@@ -737,6 +736,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 		goto gws_error;
 	}
 
+	/* If CRAT is broken, won't set iommu enabled */
+	kfd_double_confirm_iommu_support(kfd);
+
 	if (kfd_iommu_device_init(kfd)) {
 		dev_err(kfd_device, "Error initializing iommuv2\n");
 		goto device_iommu_error;
@@ -810,6 +812,8 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 	if (!kfd->init_complete)
 		return 0;
 
+	kfd_smi_event_update_gpu_reset(kfd, false);
+
 	kfd->dqm->ops.pre_reset(kfd->dqm);
 
 	kgd2kfd_suspend(kfd, false);
@@ -838,6 +842,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
+	kfd_smi_event_update_gpu_reset(kfd, true);
+
 	return 0;
 }
 
@@ -1245,6 +1251,12 @@ void kfd_dec_compute_active(struct kfd_dev *kfd)
 	WARN_ONCE(count < 0, "Compute profile ref. count error");
 }
 
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+{
+	if (kfd)
+		kfd_smi_event_update_thermal_throttling(kfd, throttle_bitmask);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 /* This function will send a package to HIQ to hang the HWS
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e0e60b0d0669..560adc57a050 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -153,30 +153,6 @@ static void decrement_queue_count(struct device_queue_manager *dqm,
 		dqm->active_cp_queue_count--;
 }
 
-int read_sdma_queue_counter(uint64_t q_rptr, uint64_t *val)
-{
-	int ret;
-	uint64_t tmp = 0;
-
-	if (!val)
-		return -EINVAL;
-	/*
-	 * SDMA activity counter is stored at queue's RPTR + 0x8 location.
-	 */
-	if (!access_ok((const void __user *)(q_rptr +
-					sizeof(uint64_t)), sizeof(uint64_t))) {
-		pr_err("Can't access sdma queue activity counter\n");
-		return -EFAULT;
-	}
-
-	ret = get_user(tmp, (uint64_t *)(q_rptr + sizeof(uint64_t)));
-	if (!ret) {
-		*val = tmp;
-	}
-
-	return ret;
-}
-
 static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 {
 	struct kfd_dev *dev = qpd->dqm->dev;
@@ -552,7 +528,7 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 	/* Get the SDMA queue stats */
 	if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
 	    (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
-		retval = read_sdma_queue_counter((uint64_t)q->properties.read_ptr,
+		retval = read_sdma_queue_counter((uint64_t __user *)q->properties.read_ptr,
 							&sdma_val);
 		if (retval)
 			pr_err("Failed to read SDMA queue counter for queue: %d\n",
@@ -1473,7 +1449,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	/* Get the SDMA queue stats */
 	if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
 	    (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
-		retval = read_sdma_queue_counter((uint64_t)q->properties.read_ptr,
+		retval = read_sdma_queue_counter((uint64_t __user *)q->properties.read_ptr,
 							&sdma_val);
 		if (retval)
 			pr_err("Failed to read SDMA queue counter for queue: %d\n",
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 49d8e324c636..16262e5d93f5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -251,5 +251,11 @@ static inline void dqm_unlock(struct device_queue_manager *dqm)
 	mutex_unlock(&dqm->lock_hidden);
 }
 
-int read_sdma_queue_counter(uint64_t q_rptr, uint64_t *val);
+static inline int read_sdma_queue_counter(uint64_t __user *q_rptr, uint64_t *val)
+{
+        /*
+         * SDMA activity counter is stored at queue's RPTR + 0x8 location.
+         */
+	return get_user(*val, q_rptr + 1);
+}
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 95a82ac455f2..309f63a0b34a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -62,7 +62,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
 		if (amdgpu_noretry &&
-		    !dqm->dev->device_info->needs_iommu_device)
+		    !dqm->dev->use_iommu_v2)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index c1166c40ac15..3c22909470f2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -321,7 +321,7 @@ static void kfd_init_apertures_vi(struct kfd_process_device *pdd, uint8_t id)
 	pdd->lds_base = MAKE_LDS_APP_BASE_VI();
 	pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
 
-	if (!pdd->dev->device_info->needs_iommu_device) {
+	if (!pdd->dev->use_iommu_v2) {
 		/* dGPUs: SVM aperture starting at 0
 		 * with small reserved space for kernel.
 		 * Set them to CANONICAL addresses.
@@ -425,7 +425,7 @@ int kfd_init_apertures(struct kfd_process *process)
 				return -EINVAL;
 			}
 
-			if (!dev->device_info->needs_iommu_device) {
+			if (!dev->use_iommu_v2) {
 				/* dGPUs: the reserved space for kernel
 				 * before SVM
 				 */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 7c8786b9eb0a..5a64915abaf7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -41,7 +41,7 @@ int kfd_iommu_check_device(struct kfd_dev *kfd)
 	struct amd_iommu_device_info iommu_info;
 	int err;
 
-	if (!kfd->device_info->needs_iommu_device)
+	if (!kfd->use_iommu_v2)
 		return -ENODEV;
 
 	iommu_info.flags = 0;
@@ -63,7 +63,7 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
 	unsigned int pasid_limit;
 	int err;
 
-	if (!kfd->device_info->needs_iommu_device)
+	if (!kfd->use_iommu_v2)
 		return 0;
 
 	iommu_info.flags = 0;
@@ -109,7 +109,7 @@ int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd)
 	struct kfd_process *p = pdd->process;
 	int err;
 
-	if (!dev->device_info->needs_iommu_device || pdd->bound == PDD_BOUND)
+	if (!dev->use_iommu_v2 || pdd->bound == PDD_BOUND)
 		return 0;
 
 	if (unlikely(pdd->bound == PDD_BOUND_SUSPENDED)) {
@@ -284,7 +284,7 @@ static void kfd_unbind_processes_from_device(struct kfd_dev *kfd)
  */
 void kfd_iommu_suspend(struct kfd_dev *kfd)
 {
-	if (!kfd->device_info->needs_iommu_device)
+	if (!kfd->use_iommu_v2)
 		return;
 
 	kfd_unbind_processes_from_device(kfd);
@@ -304,7 +304,7 @@ int kfd_iommu_resume(struct kfd_dev *kfd)
 	unsigned int pasid_limit;
 	int err;
 
-	if (!kfd->device_info->needs_iommu_device)
+	if (!kfd->use_iommu_v2)
 		return 0;
 
 	pasid_limit = kfd_get_pasid_limit();
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6727e9de5b8b..023629f28495 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -297,6 +297,9 @@ struct kfd_dev {
 
 	bool pci_atomic_requested;
 
+	/* Use IOMMU v2 flag */
+	bool use_iommu_v2;
+
 	/* SRAM ECC flag */
 	atomic_t sram_ecc_flag;
 
@@ -309,6 +312,8 @@ struct kfd_dev {
 	/* Clients watching SMI events */
 	struct list_head smi_clients;
 	spinlock_t smi_lock;
+
+	uint32_t reset_seq_num;
 };
 
 enum kfd_mempool {
@@ -892,6 +897,7 @@ struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
 struct kfd_dev *kfd_device_by_kgd(const struct kgd_dev *kgd);
 int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);
 int kfd_numa_node_to_apic_id(int numa_node_id);
+void kfd_double_confirm_iommu_support(struct kfd_dev *gpu);
 
 /* Interrupts */
 int kfd_interrupt_init(struct kfd_dev *dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40695d52e9a8..a0e12a79ab7d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -87,7 +87,7 @@ struct kfd_sdma_activity_handler_workarea {
 };
 
 struct temp_sdma_queue_list {
-	uint64_t rptr;
+	uint64_t __user *rptr;
 	uint64_t sdma_val;
 	unsigned int queue_id;
 	struct list_head list;
@@ -159,7 +159,7 @@ static void kfd_sdma_activity_worker(struct work_struct *work)
 		}
 
 		INIT_LIST_HEAD(&sdma_q->list);
-		sdma_q->rptr = (uint64_t)q->properties.read_ptr;
+		sdma_q->rptr = (uint64_t __user *)q->properties.read_ptr;
 		sdma_q->queue_id = q->properties.queue_id;
 		list_add_tail(&sdma_q->list, &sdma_q_list.list);
 	}
@@ -218,7 +218,7 @@ static void kfd_sdma_activity_worker(struct work_struct *work)
 			continue;
 
 		list_for_each_entry_safe(sdma_q, next, &sdma_q_list.list, list) {
-			if (((uint64_t)q->properties.read_ptr == sdma_q->rptr) &&
+			if (((uint64_t __user *)q->properties.read_ptr == sdma_q->rptr) &&
 			     (sdma_q->queue_id == q->properties.queue_id)) {
 				list_del(&sdma_q->list);
 				kfree(sdma_q);
@@ -270,6 +270,7 @@ static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,
 					kfd_sdma_activity_worker);
 
 		sdma_activity_work_handler.pdd = pdd;
+		sdma_activity_work_handler.sdma_activity_counter = 0;
 
 		schedule_work(&sdma_activity_work_handler.sdma_activity_work);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 7b348bf9df21..17d1736367ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -24,6 +24,7 @@
 #include <linux/wait.h>
 #include <linux/anon_inodes.h>
 #include <uapi/linux/kfd_ioctl.h>
+#include "amdgpu.h"
 #include "amdgpu_vm.h"
 #include "kfd_priv.h"
 #include "kfd_smi_events.h"
@@ -148,15 +149,94 @@ static int kfd_smi_ev_release(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
+			      char *event_msg, int len)
+{
+	struct kfd_smi_client *client;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
+		if (!(READ_ONCE(client->events) &
+				KFD_SMI_EVENT_MASK_FROM_INDEX(smi_event)))
+			continue;
+		spin_lock(&client->lock);
+		if (kfifo_avail(&client->fifo) >= len) {
+			kfifo_in(&client->fifo, event_msg, len);
+			wake_up_all(&client->wait_queue);
+		} else {
+			pr_debug("smi_event(EventID: %u): no space left\n",
+					smi_event);
+		}
+		spin_unlock(&client->lock);
+	}
+
+	rcu_read_unlock();
+}
+
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset)
+{
+	/*
+	 * GpuReset msg = Reset seq number (incremented for
+	 * every reset message sent before GPU reset).
+	 * 1 byte event + 1 byte space + 8 bytes seq num +
+	 * 1 byte \n + 1 byte \0 = 12
+	 */
+	char fifo_in[12];
+	int len;
+	unsigned int event;
+
+	if (list_empty(&dev->smi_clients))
+		return;
+
+	memset(fifo_in, 0x0, sizeof(fifo_in));
+
+	if (post_reset) {
+		event = KFD_SMI_EVENT_GPU_POST_RESET;
+	} else {
+		event = KFD_SMI_EVENT_GPU_PRE_RESET;
+		++(dev->reset_seq_num);
+	}
+
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x\n", event,
+						dev->reset_seq_num);
+
+	add_event_to_kfifo(dev, event, fifo_in, len);
+}
+
+void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
+					     uint32_t throttle_bitmask)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
+	/*
+	 * ThermalThrottle msg = throttle_bitmask(8):
+	 * 			 thermal_interrupt_count(16):
+	 * 1 byte event + 1 byte space + 8 byte throttle_bitmask +
+	 * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n +
+	 * 1 byte \0 = 29
+	 */
+	char fifo_in[29];
+	int len;
+
+	if (list_empty(&dev->smi_clients))
+		return;
+
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%llx\n",
+		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
+		       atomic64_read(&adev->smu.throttle_int_counter));
+
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE,	fifo_in, len);
+}
+
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
 	struct amdgpu_task_info task_info;
 	/* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */
-	/* 16 bytes event + 1 byte space + 25 bytes msg + 1 byte \n = 43
+	/* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n +
+	 * 1 byte \0 = 29
 	 */
-	char fifo_in[43];
-	struct kfd_smi_client *client;
+	char fifo_in[29];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
@@ -168,25 +248,10 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	if (!task_info.pid)
 		return;
 
-	len = snprintf(fifo_in, 43, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
-		if (!(READ_ONCE(client->events) & KFD_SMI_EVENT_VMFAULT))
-			continue;
-		spin_lock(&client->lock);
-		if (kfifo_avail(&client->fifo) >= len) {
-			kfifo_in(&client->fifo, fifo_in, len);
-			wake_up_all(&client->wait_queue);
-		}
-		else
-			pr_debug("smi_event(vmfault): no space left\n");
-		spin_unlock(&client->lock);
-	}
-
-	rcu_read_unlock();
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
 }
 
 int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index a9cb218fef96..b9b0438202e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -25,5 +25,8 @@
 
 int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
+void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
+					     uint32_t throttle_bitmask);
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index f185f6cbc05c..2b31c3066aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -446,7 +446,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 	sysfs_show_32bit_prop(buffer, offs, "cpu_cores_count",
 			      dev->node_props.cpu_cores_count);
 	sysfs_show_32bit_prop(buffer, offs, "simd_count",
-			      dev->node_props.simd_count);
+			      dev->gpu ? dev->node_props.simd_count : 0);
 	sysfs_show_32bit_prop(buffer, offs, "mem_banks_count",
 			      dev->node_props.mem_banks_count);
 	sysfs_show_32bit_prop(buffer, offs, "caches_count",
@@ -1139,7 +1139,7 @@ static struct kfd_topology_device *kfd_assign_gpu(struct kfd_dev *gpu)
 		/* Discrete GPUs need their own topology device list
 		 * entries. Don't assign them to CPU/APU nodes.
 		 */
-		if (!gpu->device_info->needs_iommu_device &&
+		if (!gpu->use_iommu_v2 &&
 		    dev->node_props.cpu_cores_count)
 			continue;
 
@@ -1239,7 +1239,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	void *crat_image = NULL;
 	size_t image_size = 0;
 	int proximity_domain;
-	struct amdgpu_ras *ctx;
+	struct amdgpu_device *adev;
 
 	INIT_LIST_HEAD(&temp_topology_device_list);
 
@@ -1388,7 +1388,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	* Overwrite ATS capability according to needs_iommu_device to fix
 	* potential missing corresponding bit in CRAT of BIOS.
 	*/
-	if (dev->gpu->device_info->needs_iommu_device)
+	if (dev->gpu->use_iommu_v2)
 		dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
 	else
 		dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT;
@@ -1404,19 +1404,17 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 		dev->node_props.max_waves_per_simd = 10;
 	}
 
-	ctx = amdgpu_ras_get_context((struct amdgpu_device *)(dev->gpu->kgd));
-	if (ctx) {
-		/* kfd only concerns sram ecc on GFX/SDMA and HBM ecc on UMC */
-		dev->node_props.capability |=
-			(((ctx->features & BIT(AMDGPU_RAS_BLOCK__SDMA)) != 0) ||
-			 ((ctx->features & BIT(AMDGPU_RAS_BLOCK__GFX)) != 0)) ?
-			HSA_CAP_SRAM_EDCSUPPORTED : 0;
-		dev->node_props.capability |= ((ctx->features & BIT(AMDGPU_RAS_BLOCK__UMC)) != 0) ?
-			HSA_CAP_MEM_EDCSUPPORTED : 0;
-
-		dev->node_props.capability |= (ctx->features != 0) ?
+	adev = (struct amdgpu_device *)(dev->gpu->kgd);
+	/* kfd only concerns sram ecc on GFX and HBM ecc on UMC */
+	dev->node_props.capability |=
+		((adev->ras_features & BIT(AMDGPU_RAS_BLOCK__GFX)) != 0) ?
+		HSA_CAP_SRAM_EDCSUPPORTED : 0;
+	dev->node_props.capability |= ((adev->ras_features & BIT(AMDGPU_RAS_BLOCK__UMC)) != 0) ?
+		HSA_CAP_MEM_EDCSUPPORTED : 0;
+
+	if (adev->asic_type != CHIP_VEGA10)
+		dev->node_props.capability |= (adev->ras_features != 0) ?
 			HSA_CAP_RASEVENTNOTIFY : 0;
-	}
 
 	kfd_debug_print_topology();
 
@@ -1515,6 +1513,29 @@ int kfd_numa_node_to_apic_id(int numa_node_id)
 	return kfd_cpumask_to_apic_id(cpumask_of_node(numa_node_id));
 }
 
+void kfd_double_confirm_iommu_support(struct kfd_dev *gpu)
+{
+	struct kfd_topology_device *dev;
+
+	gpu->use_iommu_v2 = false;
+
+	if (!gpu->device_info->needs_iommu_device)
+		return;
+
+	down_read(&topology_lock);
+
+	/* Only use IOMMUv2 if there is an APU topology node with no GPU
+	 * assigned yet. This GPU will be assigned to it.
+	 */
+	list_for_each_entry(dev, &topology_device_list, list)
+		if (dev->node_props.cpu_cores_count &&
+		    dev->node_props.simd_count &&
+		    !dev->gpu)
+			gpu->use_iommu_v2 = true;
+
+	up_read(&topology_lock);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 int kfd_debugfs_hqds_by_device(struct seq_file *m, void *data)
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 34ae4f3a32f4..f24abf428534 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@ config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
 	select SND_HDA_COMPONENT if SND_HDA_CORE
-	select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+	select DRM_AMD_DC_DCN if (X86 || PPC64 || (ARM64 && KERNEL_MODE_NEON)) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
@@ -31,6 +31,14 @@ config DRM_AMD_DC_HDCP
 	help
 	  Choose this option if you want to support HDCP authentication.
 
+config DRM_AMD_DC_SI
+	bool "AMD DC support for Southern Islands ASICs"
+	default n
+	help
+	  Choose this option to enable new AMD DC support for SI asics
+	  by default. This includes Tahiti, Pitcairn, Cape Verde, Oland.
+	  Hainan is not supported by AMD DC and it has no physical DCE6.
+
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
 	depends on DRM_AMD_DC
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index fd96fafec5b8..ec29376667df 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -207,7 +207,7 @@ static void amdgpu_dm_set_psr_caps(struct dc_link *link);
 static bool amdgpu_dm_psr_enable(struct dc_stream_state *stream);
 static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream);
 static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream);
-
+static bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm);
 
 /*
  * dm_vblank_get_counter
@@ -304,7 +304,7 @@ static struct amdgpu_crtc *
 get_crtc_by_otg_inst(struct amdgpu_device *adev,
 		     int otg_inst)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
 
@@ -356,7 +356,7 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		return;
 	}
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
 	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){
 		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d !=AMDGPU_FLIP_SUBMITTED(%d) on crtc:%d[%p] \n",
@@ -364,7 +364,7 @@ static void dm_pflip_high_irq(void *interrupt_params)
 						 AMDGPU_FLIP_SUBMITTED,
 						 amdgpu_crtc->crtc_id,
 						 amdgpu_crtc);
-		spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 		return;
 	}
 
@@ -416,7 +416,7 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		e->sequence = drm_crtc_vblank_count(&amdgpu_crtc->base);
 		e->pipe = amdgpu_crtc->crtc_id;
 
-		list_add_tail(&e->base.link, &adev->ddev->vblank_event_list);
+		list_add_tail(&e->base.link, &adev_to_drm(adev)->vblank_event_list);
 		e = NULL;
 	}
 
@@ -429,7 +429,7 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		amdgpu_get_vblank_counter_kms(&amdgpu_crtc->base);
 
 	amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE;
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	DRM_DEBUG_DRIVER("crtc:%d[%p], pflip_stat:AMDGPU_FLIP_NONE, vrr[%d]-fp %d\n",
 			 amdgpu_crtc->crtc_id, amdgpu_crtc,
@@ -465,7 +465,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 			/* BTR processing for pre-DCE12 ASICs */
 			if (acrtc_state->stream &&
 			    adev->family < AMDGPU_FAMILY_AI) {
-				spin_lock_irqsave(&adev->ddev->event_lock, flags);
+				spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 				mod_freesync_handle_v_update(
 				    adev->dm.freesync_module,
 				    acrtc_state->stream,
@@ -475,7 +475,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 				    adev->dm.dc,
 				    acrtc_state->stream,
 				    &acrtc_state->vrr_params.adjust);
-				spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+				spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 			}
 		}
 	}
@@ -525,7 +525,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	if (adev->family < AMDGPU_FAMILY_AI)
 		return;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
 	if (acrtc_state->stream && acrtc_state->vrr_params.supported &&
 	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
@@ -558,7 +558,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
 		acrtc->pflip_status = AMDGPU_FLIP_NONE;
 	}
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 }
 
 static int dm_set_clockgating_state(void *handle,
@@ -580,7 +580,7 @@ static int dm_early_init(void* handle);
 static void amdgpu_dm_fbc_init(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct dm_comressor_info *compressor = &adev->dm.compressor;
 	struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector);
 	struct drm_display_mode *mode;
@@ -622,7 +622,7 @@ static int amdgpu_dm_audio_component_get_eld(struct device *kdev, int port,
 					  unsigned char *buf, int max_bytes)
 {
 	struct drm_device *dev = dev_get_drvdata(kdev);
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct amdgpu_dm_connector *aconnector;
@@ -661,7 +661,7 @@ static int amdgpu_dm_audio_component_bind(struct device *kdev,
 				       struct device *hda_kdev, void *data)
 {
 	struct drm_device *dev = dev_get_drvdata(kdev);
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_audio_component *acomp = data;
 
 	acomp->ops = &amdgpu_dm_audio_component_ops;
@@ -675,7 +675,7 @@ static void amdgpu_dm_audio_component_unbind(struct device *kdev,
 					  struct device *hda_kdev, void *data)
 {
 	struct drm_device *dev = dev_get_drvdata(kdev);
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_audio_component *acomp = data;
 
 	acomp->ops = NULL;
@@ -886,7 +886,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 #endif
 	int r;
 
-	adev->dm.ddev = adev->ddev;
+	adev->dm.ddev = adev_to_drm(adev);
 	adev->dm.adev = adev;
 
 	/* Zero all the fields */
@@ -1022,10 +1022,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	/* TODO: Add_display_info? */
 
 	/* TODO use dynamic cursor width */
-	adev->ddev->mode_config.cursor_width = adev->dm.dc->caps.max_cursor_size;
-	adev->ddev->mode_config.cursor_height = adev->dm.dc->caps.max_cursor_size;
+	adev_to_drm(adev)->mode_config.cursor_width = adev->dm.dc->caps.max_cursor_size;
+	adev_to_drm(adev)->mode_config.cursor_height = adev->dm.dc->caps.max_cursor_size;
 
-	if (drm_vblank_init(adev->ddev, adev->dm.display_indexes_num)) {
+	if (drm_vblank_init(adev_to_drm(adev), adev->dm.display_indexes_num)) {
 		DRM_ERROR(
 		"amdgpu: failed to initialize sw for display support.\n");
 		goto error;
@@ -1102,6 +1102,12 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	const struct dmcu_firmware_header_v1_0 *hdr;
 
 	switch(adev->asic_type) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+#endif
 	case CHIP_BONAIRE:
 	case CHIP_HAWAII:
 	case CHIP_KAVERI:
@@ -1420,7 +1426,7 @@ static int dm_late_init(void *handle)
 	bool ret = true;
 
 	if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
-		return detect_mst_link_for_all_connectors(adev->ddev);
+		return detect_mst_link_for_all_connectors(adev_to_drm(adev));
 
 	dmcu = adev->dm.dc->res_pool->dmcu;
 
@@ -1445,12 +1451,12 @@ static int dm_late_init(void *handle)
 	if (dmcu)
 		ret = dmcu_load_iram(dmcu, params);
 	else if (adev->dm.dc->ctx->dmub_srv)
-		ret = dmub_init_abm_config(adev->dm.dc->res_pool->abm, params);
+		ret = dmub_init_abm_config(adev->dm.dc->res_pool, params);
 
 	if (!ret)
 		return -EINVAL;
 
-	return detect_mst_link_for_all_connectors(adev->ddev);
+	return detect_mst_link_for_all_connectors(adev_to_drm(adev));
 }
 
 static void s3_handle_mst(struct drm_device *dev, bool suspend)
@@ -1688,7 +1694,7 @@ static int dm_suspend(void *handle)
 	struct amdgpu_display_manager *dm = &adev->dm;
 	int ret = 0;
 
-	if (adev->in_gpu_reset) {
+	if (amdgpu_in_reset(adev)) {
 		mutex_lock(&dm->dc_lock);
 		dm->cached_dc_state = dc_copy_state(dm->dc->current_state);
 
@@ -1702,9 +1708,9 @@ static int dm_suspend(void *handle)
 	}
 
 	WARN_ON(adev->dm.cached_state);
-	adev->dm.cached_state = drm_atomic_helper_suspend(adev->ddev);
+	adev->dm.cached_state = drm_atomic_helper_suspend(adev_to_drm(adev));
 
-	s3_handle_mst(adev->ddev, true);
+	s3_handle_mst(adev_to_drm(adev), true);
 
 	amdgpu_dm_irq_suspend(adev);
 
@@ -1858,7 +1864,7 @@ cleanup:
 static int dm_resume(void *handle)
 {
 	struct amdgpu_device *adev = handle;
-	struct drm_device *ddev = adev->ddev;
+	struct drm_device *ddev = adev_to_drm(adev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
@@ -1874,7 +1880,7 @@ static int dm_resume(void *handle)
 	struct dc_state *dc_state;
 	int i, r, j;
 
-	if (adev->in_gpu_reset) {
+	if (amdgpu_in_reset(adev)) {
 		dc_state = dm->cached_dc_state;
 
 		r = dm_dmub_hw_init(adev);
@@ -2080,7 +2086,7 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 		return;
 
 	conn_base = &aconnector->base;
-	adev = conn_base->dev->dev_private;
+	adev = drm_to_adev(conn_base->dev);
 	dm = &adev->dm;
 	caps = &dm->backlight_caps;
 	caps->ext_caps = &aconnector->dc_link->dpcd_sink_ext_caps;
@@ -2231,6 +2237,7 @@ void amdgpu_dm_update_connector_after_detect(
 
 			drm_connector_update_edid_property(connector,
 							   aconnector->edid);
+			drm_add_edid_modes(connector, aconnector->edid);
 
 			if (aconnector->dc_link->aux_mode)
 				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
@@ -2269,7 +2276,7 @@ static void handle_hpd_irq(void *param)
 	struct drm_device *dev = connector->dev;
 	enum dc_connection_type new_connection_type = dc_connection_none;
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 #endif
 
 	/*
@@ -2402,7 +2409,7 @@ static void handle_hpd_rx_irq(void *param)
 	enum dc_connection_type new_connection_type = dc_connection_none;
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	union hpd_irq_data hpd_irq_data;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	memset(&hpd_irq_data, 0, sizeof(hpd_irq_data));
 #endif
@@ -2473,7 +2480,7 @@ static void handle_hpd_rx_irq(void *param)
 
 static void register_hpd_handlers(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct amdgpu_dm_connector *aconnector;
 	const struct dc_link *dc_link;
@@ -2510,6 +2517,89 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/* Register IRQ sources and initialize IRQ callbacks */
+static int dce60_register_irq_handlers(struct amdgpu_device *adev)
+{
+	struct dc *dc = adev->dm.dc;
+	struct common_irq_params *c_irq_params;
+	struct dc_interrupt_params int_params = {0};
+	int r;
+	int i;
+	unsigned client_id = AMDGPU_IRQ_CLIENTID_LEGACY;
+
+	int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT;
+	int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT;
+
+	/*
+	 * Actions of amdgpu_irq_add_id():
+	 * 1. Register a set() function with base driver.
+	 *    Base driver will call set() function to enable/disable an
+	 *    interrupt in DC hardware.
+	 * 2. Register amdgpu_dm_irq_handler().
+	 *    Base driver will call amdgpu_dm_irq_handler() for ALL interrupts
+	 *    coming from DC hardware.
+	 *    amdgpu_dm_irq_handler() will re-direct the interrupt to DC
+	 *    for acknowledging and handling. */
+
+	/* Use VBLANK interrupt */
+	for (i = 0; i < adev->mode_info.num_crtc; i++) {
+		r = amdgpu_irq_add_id(adev, client_id, i+1 , &adev->crtc_irq);
+		if (r) {
+			DRM_ERROR("Failed to add crtc irq id!\n");
+			return r;
+		}
+
+		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
+		int_params.irq_source =
+			dc_interrupt_to_irq_source(dc, i+1 , 0);
+
+		c_irq_params = &adev->dm.vblank_params[int_params.irq_source - DC_IRQ_SOURCE_VBLANK1];
+
+		c_irq_params->adev = adev;
+		c_irq_params->irq_src = int_params.irq_source;
+
+		amdgpu_dm_irq_register_interrupt(adev, &int_params,
+				dm_crtc_high_irq, c_irq_params);
+	}
+
+	/* Use GRPH_PFLIP interrupt */
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP;
+			i <= VISLANDS30_IV_SRCID_D6_GRPH_PFLIP; i += 2) {
+		r = amdgpu_irq_add_id(adev, client_id, i, &adev->pageflip_irq);
+		if (r) {
+			DRM_ERROR("Failed to add page flip irq id!\n");
+			return r;
+		}
+
+		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
+		int_params.irq_source =
+			dc_interrupt_to_irq_source(dc, i, 0);
+
+		c_irq_params = &adev->dm.pflip_params[int_params.irq_source - DC_IRQ_SOURCE_PFLIP_FIRST];
+
+		c_irq_params->adev = adev;
+		c_irq_params->irq_src = int_params.irq_source;
+
+		amdgpu_dm_irq_register_interrupt(adev, &int_params,
+				dm_pflip_high_irq, c_irq_params);
+
+	}
+
+	/* HPD */
+	r = amdgpu_irq_add_id(adev, client_id,
+			VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
+	if (r) {
+		DRM_ERROR("Failed to add hpd irq id!\n");
+		return r;
+	}
+
+	register_hpd_handlers(adev);
+
+	return 0;
+}
+#endif
+
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -2740,7 +2830,7 @@ static int dm_atomic_get_state(struct drm_atomic_state *state,
 			       struct dm_atomic_state **dm_state)
 {
 	struct drm_device *dev = state->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct drm_private_state *priv_state;
 
@@ -2760,7 +2850,7 @@ static struct dm_atomic_state *
 dm_atomic_get_new_state(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct drm_private_obj *obj;
 	struct drm_private_state *new_obj_state;
@@ -2774,24 +2864,6 @@ dm_atomic_get_new_state(struct drm_atomic_state *state)
 	return NULL;
 }
 
-static struct dm_atomic_state *
-dm_atomic_get_old_state(struct drm_atomic_state *state)
-{
-	struct drm_device *dev = state->dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_display_manager *dm = &adev->dm;
-	struct drm_private_obj *obj;
-	struct drm_private_state *old_obj_state;
-	int i;
-
-	for_each_old_private_obj_in_state(state, obj, old_obj_state, i) {
-		if (obj->funcs == dm->atomic_obj.funcs)
-			return to_dm_atomic_state(old_obj_state);
-	}
-
-	return NULL;
-}
-
 static struct drm_private_state *
 dm_atomic_duplicate_state(struct drm_private_obj *obj)
 {
@@ -2839,18 +2911,18 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 
 	adev->mode_info.mode_config_initialized = true;
 
-	adev->ddev->mode_config.funcs = (void *)&amdgpu_dm_mode_funcs;
-	adev->ddev->mode_config.helper_private = &amdgpu_dm_mode_config_helperfuncs;
+	adev_to_drm(adev)->mode_config.funcs = (void *)&amdgpu_dm_mode_funcs;
+	adev_to_drm(adev)->mode_config.helper_private = &amdgpu_dm_mode_config_helperfuncs;
 
-	adev->ddev->mode_config.max_width = 16384;
-	adev->ddev->mode_config.max_height = 16384;
+	adev_to_drm(adev)->mode_config.max_width = 16384;
+	adev_to_drm(adev)->mode_config.max_height = 16384;
 
-	adev->ddev->mode_config.preferred_depth = 24;
-	adev->ddev->mode_config.prefer_shadow = 1;
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	/* indicates support for immediate flip */
-	adev->ddev->mode_config.async_page_flip = true;
+	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
-	adev->ddev->mode_config.fb_base = adev->gmc.aper_base;
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state)
@@ -2864,18 +2936,24 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 
 	dc_resource_state_copy_construct_current(adev->dm.dc, state->context);
 
-	drm_atomic_private_obj_init(adev->ddev,
+	drm_atomic_private_obj_init(adev_to_drm(adev),
 				    &adev->dm.atomic_obj,
 				    &state->base,
 				    &dm_atomic_state_funcs);
 
 	r = amdgpu_display_modeset_create_props(adev);
-	if (r)
+	if (r) {
+		dc_release_state(state->context);
+		kfree(state);
 		return r;
+	}
 
 	r = amdgpu_dm_audio_init(adev);
-	if (r)
+	if (r) {
+		dc_release_state(state->context);
+		kfree(state);
 		return r;
+	}
 
 	return 0;
 }
@@ -2892,6 +2970,8 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm)
 #if defined(CONFIG_ACPI)
 	struct amdgpu_dm_backlight_caps caps;
 
+	memset(&caps, 0, sizeof(caps));
+
 	if (dm->backlight_caps.caps_valid)
 		return;
 
@@ -2930,51 +3010,50 @@ static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness)
 	return rc ? 0 : 1;
 }
 
-static u32 convert_brightness(const struct amdgpu_dm_backlight_caps *caps,
-			      const uint32_t user_brightness)
+static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
+				unsigned *min, unsigned *max)
 {
-	u32 min, max, conversion_pace;
-	u32 brightness = user_brightness;
-
 	if (!caps)
-		goto out;
+		return 0;
 
-	if (!caps->aux_support) {
-		max = caps->max_input_signal;
-		min = caps->min_input_signal;
-		/*
-		 * The brightness input is in the range 0-255
-		 * It needs to be rescaled to be between the
-		 * requested min and max input signal
-		 * It also needs to be scaled up by 0x101 to
-		 * match the DC interface which has a range of
-		 * 0 to 0xffff
-		 */
-		conversion_pace = 0x101;
-		brightness =
-			user_brightness
-			* conversion_pace
-			* (max - min)
-			/ AMDGPU_MAX_BL_LEVEL
-			+ min * conversion_pace;
+	if (caps->aux_support) {
+		// Firmware limits are in nits, DC API wants millinits.
+		*max = 1000 * caps->aux_max_input_signal;
+		*min = 1000 * caps->aux_min_input_signal;
 	} else {
-		/* TODO
-		 * We are doing a linear interpolation here, which is OK but
-		 * does not provide the optimal result. We probably want
-		 * something close to the Perceptual Quantizer (PQ) curve.
-		 */
-		max = caps->aux_max_input_signal;
-		min = caps->aux_min_input_signal;
-
-		brightness = (AMDGPU_MAX_BL_LEVEL - user_brightness) * min
-			       + user_brightness * max;
-		// Multiple the value by 1000 since we use millinits
-		brightness *= 1000;
-		brightness = DIV_ROUND_CLOSEST(brightness, AMDGPU_MAX_BL_LEVEL);
+		// Firmware limits are 8-bit, PWM control is 16-bit.
+		*max = 0x101 * caps->max_input_signal;
+		*min = 0x101 * caps->min_input_signal;
 	}
+	return 1;
+}
+
+static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *caps,
+					uint32_t brightness)
+{
+	unsigned min, max;
 
-out:
-	return brightness;
+	if (!get_brightness_range(caps, &min, &max))
+		return brightness;
+
+	// Rescale 0..255 to min..max
+	return min + DIV_ROUND_CLOSEST((max - min) * brightness,
+				       AMDGPU_MAX_BL_LEVEL);
+}
+
+static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps,
+				      uint32_t brightness)
+{
+	unsigned min, max;
+
+	if (!get_brightness_range(caps, &min, &max))
+		return brightness;
+
+	if (brightness < min)
+		return 0;
+	// Rescale min..max to 0..255
+	return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min),
+				 max - min);
 }
 
 static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
@@ -2990,7 +3069,7 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 
 	link = (struct dc_link *)dm->backlight_link;
 
-	brightness = convert_brightness(&caps, bd->props.brightness);
+	brightness = convert_brightness_from_user(&caps, bd->props.brightness);
 	// Change brightness based on AUX property
 	if (caps.aux_support)
 		return set_backlight_via_aux(link, brightness);
@@ -3007,7 +3086,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 
 	if (ret == DC_ERROR_UNEXPECTED)
 		return bd->props.brightness;
-	return ret;
+	return convert_brightness_to_user(&dm->backlight_caps, ret);
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
@@ -3029,13 +3108,13 @@ amdgpu_dm_register_backlight_device(struct amdgpu_display_manager *dm)
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",
-			dm->adev->ddev->primary->index);
+		 adev_to_drm(dm->adev)->primary->index);
 
 	dm->backlight_dev = backlight_device_register(bl_name,
-			dm->adev->ddev->dev,
-			dm,
-			&amdgpu_dm_backlight_ops,
-			&props);
+						      adev_to_drm(dm->adev)->dev,
+						      dm,
+						      &amdgpu_dm_backlight_ops,
+						      &props);
 
 	if (IS_ERR(dm->backlight_dev))
 		DRM_ERROR("DM: Backlight registration failed!\n");
@@ -3241,6 +3320,17 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 
 	/* Software is initialized. Now we can register interrupt handlers. */
 	switch (adev->asic_type) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+		if (dce60_register_irq_handlers(dm->adev)) {
+			DRM_ERROR("DM: Failed to initialize IRQ\n");
+			goto fail;
+		}
+		break;
+#endif
 	case CHIP_BONAIRE:
 	case CHIP_HAWAII:
 	case CHIP_KAVERI:
@@ -3341,14 +3431,14 @@ static ssize_t s3_debug_store(struct device *device,
 	int ret;
 	int s3_state;
 	struct drm_device *drm_dev = dev_get_drvdata(device);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
 	ret = kstrtoint(buf, 0, &s3_state);
 
 	if (ret == 0) {
 		if (s3_state) {
 			dm_resume(adev);
-			drm_kms_helper_hotplug_event(adev->ddev);
+			drm_kms_helper_hotplug_event(adev_to_drm(adev));
 		} else
 			dm_suspend(adev);
 	}
@@ -3365,6 +3455,20 @@ static int dm_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	switch (adev->asic_type) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+		adev->mode_info.num_crtc = 6;
+		adev->mode_info.num_hpd = 6;
+		adev->mode_info.num_dig = 6;
+		break;
+	case CHIP_OLAND:
+		adev->mode_info.num_crtc = 2;
+		adev->mode_info.num_hpd = 2;
+		adev->mode_info.num_dig = 2;
+		break;
+#endif
 	case CHIP_BONAIRE:
 	case CHIP_HAWAII:
 		adev->mode_info.num_crtc = 6;
@@ -3461,7 +3565,7 @@ static int dm_early_init(void *handle)
 	 */
 #if defined(CONFIG_DEBUG_KERNEL_DC)
 	device_create_file(
-		adev->ddev->dev,
+		adev_to_drm(adev)->dev,
 		&dev_attr_s3_debug);
 #endif
 
@@ -3472,21 +3576,12 @@ static bool modeset_required(struct drm_crtc_state *crtc_state,
 			     struct dc_stream_state *new_stream,
 			     struct dc_stream_state *old_stream)
 {
-	if (!drm_atomic_crtc_needs_modeset(crtc_state))
-		return false;
-
-	if (!crtc_state->enable)
-		return false;
-
-	return crtc_state->active;
+	return crtc_state->active && drm_atomic_crtc_needs_modeset(crtc_state);
 }
 
 static bool modereset_required(struct drm_crtc_state *crtc_state)
 {
-	if (!drm_atomic_crtc_needs_modeset(crtc_state))
-		return false;
-
-	return !crtc_state->enable || !crtc_state->active;
+	return !crtc_state->active && drm_atomic_crtc_needs_modeset(crtc_state);
 }
 
 static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
@@ -3559,8 +3654,17 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state,
 static int get_fb_info(const struct amdgpu_framebuffer *amdgpu_fb,
 		       uint64_t *tiling_flags, bool *tmz_surface)
 {
-	struct amdgpu_bo *rbo = gem_to_amdgpu_bo(amdgpu_fb->base.obj[0]);
-	int r = amdgpu_bo_reserve(rbo, false);
+	struct amdgpu_bo *rbo;
+	int r;
+
+	if (!amdgpu_fb) {
+		*tiling_flags = 0;
+		*tmz_surface = false;
+		return 0;
+	}
+
+	rbo = gem_to_amdgpu_bo(amdgpu_fb->base.obj[0]);
+	r = amdgpu_bo_reserve(rbo, false);
 
 	if (unlikely(r)) {
 		/* Don't show error message when returning -ERESTARTSYS */
@@ -3983,13 +4087,10 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 				    struct drm_crtc_state *crtc_state)
 {
 	struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
-	const struct amdgpu_framebuffer *amdgpu_fb =
-		to_amdgpu_framebuffer(plane_state->fb);
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
 	struct dc_scaling_info scaling_info;
 	struct dc_plane_info plane_info;
-	uint64_t tiling_flags;
 	int ret;
-	bool tmz_surface = false;
 	bool force_disable_dcc = false;
 
 	ret = fill_dc_scaling_info(plane_state, &scaling_info);
@@ -4001,15 +4102,12 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	dc_plane_state->clip_rect = scaling_info.clip_rect;
 	dc_plane_state->scaling_quality = scaling_info.scaling_quality;
 
-	ret = get_fb_info(amdgpu_fb, &tiling_flags, &tmz_surface);
-	if (ret)
-		return ret;
-
 	force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
-	ret = fill_dc_plane_info_and_addr(adev, plane_state, tiling_flags,
+	ret = fill_dc_plane_info_and_addr(adev, plane_state,
+					  dm_plane_state->tiling_flags,
 					  &plane_info,
 					  &dc_plane_state->address,
-					  tmz_surface,
+					  dm_plane_state->tmz_surface,
 					  force_disable_dcc);
 	if (ret)
 		return ret;
@@ -4591,7 +4689,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 							     dc_link_get_link_cap(aconnector->dc_link));
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-		if (dsc_caps.is_dsc_supported)
+		if (dsc_caps.is_dsc_supported) {
+			/* Set DSC policy according to dsc_clock_en */
+			dc_dsc_policy_set_enable_dsc_when_not_needed(aconnector->dsc_settings.dsc_clock_en);
+
 			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0],
 						  &dsc_caps,
 						  aconnector->dc_link->ctx->dc->debug.dsc_min_slice_height_override,
@@ -4599,6 +4700,21 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 						  &stream->timing,
 						  &stream->timing.dsc_cfg))
 				stream->timing.flags.DSC = 1;
+			/* Overwrite the stream flag if DSC is enabled through debugfs */
+			if (aconnector->dsc_settings.dsc_clock_en)
+				stream->timing.flags.DSC = 1;
+
+			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_width)
+				stream->timing.dsc_cfg.num_slices_h = DIV_ROUND_UP(stream->timing.h_addressable,
+									aconnector->dsc_settings.dsc_slice_width);
+
+			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_height)
+				stream->timing.dsc_cfg.num_slices_v = DIV_ROUND_UP(stream->timing.v_addressable,
+									aconnector->dsc_settings.dsc_slice_height);
+
+			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel)
+				stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel;
+		}
 #endif
 	}
 
@@ -4612,7 +4728,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	update_stream_signal(stream, sink);
 
 	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket, false, false);
+		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
+
 	if (stream->link->psr_settings.psr_feature_enabled) {
 		//
 		// should decide stream support vsc sdp colorimetry capability
@@ -4710,7 +4827,7 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 {
 	enum dc_irq_source irq_source;
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	int rc;
 
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
@@ -4726,7 +4843,7 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 {
 	enum dc_irq_source irq_source;
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state);
 	int rc = 0;
 
@@ -4805,7 +4922,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector,
 					    uint64_t val)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct dm_connector_state *dm_old_state =
 		to_dm_connector_state(connector->state);
 	struct dm_connector_state *dm_new_state =
@@ -4860,7 +4977,7 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector,
 					    uint64_t *val)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct dm_connector_state *dm_state =
 		to_dm_connector_state(state);
 	int ret = -EINVAL;
@@ -4910,9 +5027,10 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 	const struct dc_link *link = aconnector->dc_link;
-	struct amdgpu_device *adev = connector->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(connector->dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 
+	drm_atomic_private_obj_fini(&aconnector->mst_mgr.base);
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
@@ -5095,7 +5213,7 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 				const struct dc_stream_state *old_stream)
 {
 	struct drm_connector *connector = &aconnector->base;
-	struct amdgpu_device *adev = connector->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(connector->dev);
 	struct dc_stream_state *stream;
 	const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL;
 	int requested_bpc = drm_state ? drm_state->max_requested_bpc : 8;
@@ -5372,7 +5490,7 @@ static void dm_update_crtc_active_planes(struct drm_crtc *crtc,
 static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc,
 				       struct drm_crtc_state *state)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct dc *dc = adev->dm.dc;
 	struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(state);
 	int ret = -EINVAL;
@@ -5592,6 +5710,10 @@ dm_drm_plane_duplicate_state(struct drm_plane *plane)
 		dc_plane_state_retain(dm_plane_state->dc_state);
 	}
 
+	/* Framebuffer hasn't been updated yet, so retain old flags. */
+	dm_plane_state->tiling_flags = old_dm_plane_state->tiling_flags;
+	dm_plane_state->tmz_surface = old_dm_plane_state->tmz_surface;
+
 	return &dm_plane_state->base;
 }
 
@@ -5626,14 +5748,8 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	struct list_head list;
 	struct ttm_validate_buffer tv;
 	struct ww_acquire_ctx ticket;
-	uint64_t tiling_flags;
 	uint32_t domain;
 	int r;
-	bool tmz_surface = false;
-	bool force_disable_dcc = false;
-
-	dm_plane_state_old = to_dm_plane_state(plane->state);
-	dm_plane_state_new = to_dm_plane_state(new_state);
 
 	if (!new_state->fb) {
 		DRM_DEBUG_DRIVER("No FB bound\n");
@@ -5677,27 +5793,35 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 		return r;
 	}
 
-	amdgpu_bo_get_tiling_flags(rbo, &tiling_flags);
-
-	tmz_surface = amdgpu_bo_encrypted(rbo);
-
 	ttm_eu_backoff_reservation(&ticket, &list);
 
 	afb->address = amdgpu_bo_gpu_offset(rbo);
 
 	amdgpu_bo_ref(rbo);
 
+	/**
+	 * We don't do surface updates on planes that have been newly created,
+	 * but we also don't have the afb->address during atomic check.
+	 *
+	 * Fill in buffer attributes depending on the address here, but only on
+	 * newly created planes since they're not being used by DC yet and this
+	 * won't modify global state.
+	 */
+	dm_plane_state_old = to_dm_plane_state(plane->state);
+	dm_plane_state_new = to_dm_plane_state(new_state);
+
 	if (dm_plane_state_new->dc_state &&
-			dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
-		struct dc_plane_state *plane_state = dm_plane_state_new->dc_state;
+	    dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
+		struct dc_plane_state *plane_state =
+			dm_plane_state_new->dc_state;
+		bool force_disable_dcc = !plane_state->dcc.enable;
 
-		force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 		fill_plane_buffer_attributes(
 			adev, afb, plane_state->format, plane_state->rotation,
-			tiling_flags, &plane_state->tiling_info,
-			&plane_state->plane_size, &plane_state->dcc,
-			&plane_state->address, tmz_surface,
-			force_disable_dcc);
+			dm_plane_state_new->tiling_flags,
+			&plane_state->tiling_info, &plane_state->plane_size,
+			&plane_state->dcc, &plane_state->address,
+			dm_plane_state_new->tmz_surface, force_disable_dcc);
 	}
 
 	return 0;
@@ -5738,7 +5862,7 @@ static int dm_plane_helper_check_state(struct drm_plane_state *state,
 static int dm_plane_atomic_check(struct drm_plane *plane,
 				 struct drm_plane_state *state)
 {
-	struct amdgpu_device *adev = plane->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
 	struct dc *dc = adev->dm.dc;
 	struct dm_plane_state *dm_plane_state;
 	struct dc_scaling_info scaling_info;
@@ -5907,7 +6031,7 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 	num_formats = get_plane_formats(plane, plane_cap, formats,
 					ARRAY_SIZE(formats));
 
-	res = drm_universal_plane_init(dm->adev->ddev, plane, possible_crtcs,
+	res = drm_universal_plane_init(adev_to_drm(dm->adev), plane, possible_crtcs,
 				       &dm_plane_funcs, formats, num_formats,
 				       NULL, plane->type, NULL);
 	if (res)
@@ -5941,8 +6065,9 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 		DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 |
 		DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270;
 
-	drm_plane_create_rotation_property(plane, DRM_MODE_ROTATE_0,
-					   supported_rotations);
+	if (dm->adev->asic_type >= CHIP_BONAIRE)
+		drm_plane_create_rotation_property(plane, DRM_MODE_ROTATE_0,
+						   supported_rotations);
 
 	drm_plane_helper_add(plane, &dm_plane_helper_funcs);
 
@@ -6212,7 +6337,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 				     struct dc_link *link,
 				     int link_index)
 {
-	struct amdgpu_device *adev = dm->ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dm->ddev);
 
 	/*
 	 * Some of the properties below require access to state, like bpc.
@@ -6463,7 +6588,7 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev,
 				  struct amdgpu_encoder *aencoder,
 				  uint32_t link_index)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	int res = drm_encoder_init(dev,
 				   &aencoder->base,
@@ -6648,7 +6773,7 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc,
 static void handle_cursor_update(struct drm_plane *plane,
 				 struct drm_plane_state *old_plane_state)
 {
-	struct amdgpu_device *adev = plane->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
 	struct amdgpu_framebuffer *afb = to_amdgpu_framebuffer(plane->state->fb);
 	struct drm_crtc *crtc = afb ? plane->state->crtc : old_plane_state->crtc;
 	struct dm_crtc_state *crtc_state = crtc ? to_dm_crtc_state(crtc->state) : NULL;
@@ -6750,7 +6875,7 @@ static void update_freesync_state_on_stream(
 	if (!new_stream->timing.h_total || !new_stream->timing.v_total)
 		return;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	vrr_params = new_crtc_state->vrr_params;
 
 	if (surface) {
@@ -6803,7 +6928,7 @@ static void update_freesync_state_on_stream(
 			      (int)new_crtc_state->base.vrr_enabled,
 			      (int)vrr_params.state);
 
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 }
 
 static void pre_update_freesync_state_on_stream(
@@ -6826,7 +6951,7 @@ static void pre_update_freesync_state_on_stream(
 	if (!new_stream->timing.h_total || !new_stream->timing.v_total)
 		return;
 
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	vrr_params = new_crtc_state->vrr_params;
 
 	if (new_crtc_state->vrr_supported &&
@@ -6849,7 +6974,7 @@ static void pre_update_freesync_state_on_stream(
 			sizeof(vrr_params.adjust)) != 0);
 
 	new_crtc_state->vrr_params = vrr_params;
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 }
 
 static void amdgpu_dm_handle_vrr_transition(struct dm_crtc_state *old_state,
@@ -6919,8 +7044,6 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	long r;
 	unsigned long flags;
 	struct amdgpu_bo *abo;
-	uint64_t tiling_flags;
-	bool tmz_surface = false;
 	uint32_t target_vblank, last_flip_vblank;
 	bool vrr_active = amdgpu_dm_vrr_active(acrtc_state);
 	bool pflip_present = false;
@@ -7004,28 +7127,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		if (unlikely(r <= 0))
 			DRM_ERROR("Waiting for fences timed out!");
 
-		/*
-		 * TODO This might fail and hence better not used, wait
-		 * explicitly on fences instead
-		 * and in general should be called for
-		 * blocking commit to as per framework helpers
-		 */
-		r = amdgpu_bo_reserve(abo, true);
-		if (unlikely(r != 0))
-			DRM_ERROR("failed to reserve buffer before flip\n");
-
-		amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
-
-		tmz_surface = amdgpu_bo_encrypted(abo);
-
-		amdgpu_bo_unreserve(abo);
-
 		fill_dc_plane_info_and_addr(
-			dm->adev, new_plane_state, tiling_flags,
+			dm->adev, new_plane_state,
+			dm_new_plane_state->tiling_flags,
 			&bundle->plane_infos[planes_count],
 			&bundle->flip_addrs[planes_count].address,
-			tmz_surface,
-			false);
+			dm_new_plane_state->tmz_surface, false);
 
 		DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n",
 				 new_plane_state->plane->index,
@@ -7203,9 +7310,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		 * on some ASICs).
 		 */
 		if (dm_old_crtc_state->active_planes != acrtc_state->active_planes)
-			dm_update_pflip_irq_state(
-				(struct amdgpu_device *)dev->dev_private,
-				acrtc_attach);
+			dm_update_pflip_irq_state(drm_to_adev(dev),
+						  acrtc_attach);
 
 		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
 				acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
@@ -7235,7 +7341,7 @@ cleanup:
 static void amdgpu_dm_commit_audio(struct drm_device *dev,
 				   struct drm_atomic_state *state)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
 	struct drm_connector_state *old_con_state, *new_con_state;
@@ -7327,7 +7433,7 @@ static int amdgpu_dm_atomic_commit(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i;
 
 	/*
@@ -7374,7 +7480,7 @@ static int amdgpu_dm_atomic_commit(struct drm_device *dev,
 static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct dm_atomic_state *dm_state;
 	struct dc_state *dc_state = NULL, *dc_state_temp = NULL;
@@ -7387,6 +7493,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_connector_state *old_con_state, *new_con_state;
 	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
 	int crtc_disable_count = 0;
+	bool mode_set_reset_required = false;
 
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 
@@ -7463,19 +7570,21 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			acrtc->enabled = true;
 			acrtc->hw_mode = new_crtc_state->mode;
 			crtc->hwmode = new_crtc_state->mode;
+			mode_set_reset_required = true;
 		} else if (modereset_required(new_crtc_state)) {
 			DRM_DEBUG_DRIVER("Atomic commit: RESET. crtc id %d:[%p]\n", acrtc->crtc_id, acrtc);
 			/* i.e. reset mode */
-			if (dm_old_crtc_state->stream) {
-				if (dm_old_crtc_state->stream->link->psr_settings.psr_allow_active)
-					amdgpu_dm_psr_disable(dm_old_crtc_state->stream);
-
+			if (dm_old_crtc_state->stream)
 				remove_stream(adev, acrtc, dm_old_crtc_state->stream);
-			}
+			mode_set_reset_required = true;
 		}
 	} /* for_each_crtc_in_state() */
 
 	if (dc_state) {
+		/* if there mode set or reset, disable eDP PSR */
+		if (mode_set_reset_required)
+			amdgpu_dm_psr_disable_all(dm);
+
 		dm_enable_per_frame_crtc_master_sync(dc_state);
 		mutex_lock(&dm->dc_lock);
 		WARN_ON(!dc_commit_state(dm->dc, dc_state));
@@ -7677,7 +7786,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	 * send vblank event on all events not handled in flip and
 	 * mark consumed event for drm_atomic_helper_commit_hw_done
 	 */
-	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
 
 		if (new_crtc_state->event)
@@ -7685,7 +7794,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 		new_crtc_state->event = NULL;
 	}
-	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 
 	/* Signal HW programming completion */
 	drm_atomic_helper_commit_hw_done(state);
@@ -7957,6 +8066,13 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
 			goto fail;
 		}
 
+		/*
+		 * TODO: Check VSDB bits to decide whether this should
+		 * be enabled or not.
+		 */
+		new_stream->triggered_crtc_reset.enabled =
+			dm->force_timing_sync;
+
 		dm_new_crtc_state->abm_level = dm_new_conn_state->abm_level;
 
 		ret = fill_hdr_info_packet(drm_new_conn_state,
@@ -8076,8 +8192,7 @@ skip_modeset:
 	 * We want to do dc stream updates that do not require a
 	 * full modeset below.
 	 */
-	if (!(enable && aconnector && new_crtc_state->enable &&
-	      new_crtc_state->active))
+	if (!(enable && aconnector && new_crtc_state->active))
 		return 0;
 	/*
 	 * Given above conditions, the dc state cannot be NULL because:
@@ -8168,6 +8283,8 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	 * TODO: Come up with a more elegant solution for this.
 	 */
 	for_each_oldnew_plane_in_state(state, other, old_other_state, new_other_state, i) {
+		struct dm_plane_state *old_dm_plane_state, *new_dm_plane_state;
+
 		if (other->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
 
@@ -8178,9 +8295,45 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 		if (old_other_state->crtc != new_other_state->crtc)
 			return true;
 
-		/* TODO: Remove this once we can handle fast format changes. */
-		if (old_other_state->fb && new_other_state->fb &&
-		    old_other_state->fb->format != new_other_state->fb->format)
+		/* Src/dst size and scaling updates. */
+		if (old_other_state->src_w != new_other_state->src_w ||
+		    old_other_state->src_h != new_other_state->src_h ||
+		    old_other_state->crtc_w != new_other_state->crtc_w ||
+		    old_other_state->crtc_h != new_other_state->crtc_h)
+			return true;
+
+		/* Rotation / mirroring updates. */
+		if (old_other_state->rotation != new_other_state->rotation)
+			return true;
+
+		/* Blending updates. */
+		if (old_other_state->pixel_blend_mode !=
+		    new_other_state->pixel_blend_mode)
+			return true;
+
+		/* Alpha updates. */
+		if (old_other_state->alpha != new_other_state->alpha)
+			return true;
+
+		/* Colorspace changes. */
+		if (old_other_state->color_range != new_other_state->color_range ||
+		    old_other_state->color_encoding != new_other_state->color_encoding)
+			return true;
+
+		/* Framebuffer checks fall at the end. */
+		if (!old_other_state->fb || !new_other_state->fb)
+			continue;
+
+		/* Pixel format changes can require bandwidth updates. */
+		if (old_other_state->fb->format != new_other_state->fb->format)
+			return true;
+
+		old_dm_plane_state = to_dm_plane_state(old_other_state);
+		new_dm_plane_state = to_dm_plane_state(new_other_state);
+
+		/* Tiling and DCC changes also require bandwidth updates. */
+		if (old_dm_plane_state->tiling_flags !=
+		    new_dm_plane_state->tiling_flags)
 			return true;
 	}
 
@@ -8260,8 +8413,7 @@ static int dm_update_plane_state(struct dc *dc,
 				dm_old_plane_state->dc_state,
 				dm_state->context)) {
 
-			ret = EINVAL;
-			return ret;
+			return -EINVAL;
 		}
 
 
@@ -8302,7 +8454,7 @@ static int dm_update_plane_state(struct dc *dc,
 				plane->base.id, new_plane_crtc->base.id);
 
 		ret = fill_dc_plane_attributes(
-			new_plane_crtc->dev->dev_private,
+			drm_to_adev(new_plane_crtc->dev),
 			dc_new_plane_state,
 			new_plane_state,
 			new_crtc_state);
@@ -8348,169 +8500,6 @@ static int dm_update_plane_state(struct dc *dc,
 	return ret;
 }
 
-static int
-dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
-				    struct drm_atomic_state *state,
-				    enum surface_update_type *out_type)
-{
-	struct dc *dc = dm->dc;
-	struct dm_atomic_state *dm_state = NULL, *old_dm_state = NULL;
-	int i, j, num_plane, ret = 0;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
-	struct dm_plane_state *new_dm_plane_state, *old_dm_plane_state;
-	struct drm_crtc *new_plane_crtc;
-	struct drm_plane *plane;
-
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *new_crtc_state, *old_crtc_state;
-	struct dm_crtc_state *new_dm_crtc_state, *old_dm_crtc_state;
-	struct dc_stream_status *status = NULL;
-	enum surface_update_type update_type = UPDATE_TYPE_FAST;
-	struct surface_info_bundle {
-		struct dc_surface_update surface_updates[MAX_SURFACES];
-		struct dc_plane_info plane_infos[MAX_SURFACES];
-		struct dc_scaling_info scaling_infos[MAX_SURFACES];
-		struct dc_flip_addrs flip_addrs[MAX_SURFACES];
-		struct dc_stream_update stream_update;
-	} *bundle;
-
-	bundle = kzalloc(sizeof(*bundle), GFP_KERNEL);
-
-	if (!bundle) {
-		DRM_ERROR("Failed to allocate update bundle\n");
-		/* Set type to FULL to avoid crashing in DC*/
-		update_type = UPDATE_TYPE_FULL;
-		goto cleanup;
-	}
-
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-
-		memset(bundle, 0, sizeof(struct surface_info_bundle));
-
-		new_dm_crtc_state = to_dm_crtc_state(new_crtc_state);
-		old_dm_crtc_state = to_dm_crtc_state(old_crtc_state);
-		num_plane = 0;
-
-		if (new_dm_crtc_state->stream != old_dm_crtc_state->stream) {
-			update_type = UPDATE_TYPE_FULL;
-			goto cleanup;
-		}
-
-		if (!new_dm_crtc_state->stream)
-			continue;
-
-		for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, j) {
-			const struct amdgpu_framebuffer *amdgpu_fb =
-				to_amdgpu_framebuffer(new_plane_state->fb);
-			struct dc_plane_info *plane_info = &bundle->plane_infos[num_plane];
-			struct dc_flip_addrs *flip_addr = &bundle->flip_addrs[num_plane];
-			struct dc_scaling_info *scaling_info = &bundle->scaling_infos[num_plane];
-			uint64_t tiling_flags;
-			bool tmz_surface = false;
-
-			new_plane_crtc = new_plane_state->crtc;
-			new_dm_plane_state = to_dm_plane_state(new_plane_state);
-			old_dm_plane_state = to_dm_plane_state(old_plane_state);
-
-			if (plane->type == DRM_PLANE_TYPE_CURSOR)
-				continue;
-
-			if (new_dm_plane_state->dc_state != old_dm_plane_state->dc_state) {
-				update_type = UPDATE_TYPE_FULL;
-				goto cleanup;
-			}
-
-			if (crtc != new_plane_crtc)
-				continue;
-
-			bundle->surface_updates[num_plane].surface =
-					new_dm_plane_state->dc_state;
-
-			if (new_crtc_state->mode_changed) {
-				bundle->stream_update.dst = new_dm_crtc_state->stream->dst;
-				bundle->stream_update.src = new_dm_crtc_state->stream->src;
-			}
-
-			if (new_crtc_state->color_mgmt_changed) {
-				bundle->surface_updates[num_plane].gamma =
-						new_dm_plane_state->dc_state->gamma_correction;
-				bundle->surface_updates[num_plane].in_transfer_func =
-						new_dm_plane_state->dc_state->in_transfer_func;
-				bundle->surface_updates[num_plane].gamut_remap_matrix =
-						&new_dm_plane_state->dc_state->gamut_remap_matrix;
-				bundle->stream_update.gamut_remap =
-						&new_dm_crtc_state->stream->gamut_remap_matrix;
-				bundle->stream_update.output_csc_transform =
-						&new_dm_crtc_state->stream->csc_color_matrix;
-				bundle->stream_update.out_transfer_func =
-						new_dm_crtc_state->stream->out_transfer_func;
-			}
-
-			ret = fill_dc_scaling_info(new_plane_state,
-						   scaling_info);
-			if (ret)
-				goto cleanup;
-
-			bundle->surface_updates[num_plane].scaling_info = scaling_info;
-
-			if (amdgpu_fb) {
-				ret = get_fb_info(amdgpu_fb, &tiling_flags, &tmz_surface);
-				if (ret)
-					goto cleanup;
-
-				ret = fill_dc_plane_info_and_addr(
-					dm->adev, new_plane_state, tiling_flags,
-					plane_info,
-					&flip_addr->address, tmz_surface,
-					false);
-				if (ret)
-					goto cleanup;
-
-				bundle->surface_updates[num_plane].plane_info = plane_info;
-				bundle->surface_updates[num_plane].flip_addr = flip_addr;
-			}
-
-			num_plane++;
-		}
-
-		if (num_plane == 0)
-			continue;
-
-		ret = dm_atomic_get_state(state, &dm_state);
-		if (ret)
-			goto cleanup;
-
-		old_dm_state = dm_atomic_get_old_state(state);
-		if (!old_dm_state) {
-			ret = -EINVAL;
-			goto cleanup;
-		}
-
-		status = dc_stream_get_status_from_state(old_dm_state->context,
-							 new_dm_crtc_state->stream);
-		bundle->stream_update.stream = new_dm_crtc_state->stream;
-		/*
-		 * TODO: DC modifies the surface during this call so we need
-		 * to lock here - find a way to do this without locking.
-		 */
-		mutex_lock(&dm->dc_lock);
-		update_type = dc_check_update_surfaces_for_stream(
-				dc,	bundle->surface_updates, num_plane,
-				&bundle->stream_update, status);
-		mutex_unlock(&dm->dc_lock);
-
-		if (update_type > UPDATE_TYPE_MED) {
-			update_type = UPDATE_TYPE_FULL;
-			goto cleanup;
-		}
-	}
-
-cleanup:
-	kfree(bundle);
-
-	*out_type = update_type;
-	return ret;
-}
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc)
 {
@@ -8551,8 +8540,7 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm
  * acquired. For full updates case which removes/adds/updates streams on one
  * CRTC while flipping on another CRTC, acquiring global lock will guarantee
  * that any such full update commit will wait for completion of any outstanding
- * flip using DRMs synchronization events. See
- * dm_determine_update_type_for_commit()
+ * flip using DRMs synchronization events.
  *
  * Note that DM adds the affected connectors for all CRTCs in state, when that
  * might not seem necessary. This is because DC stream creation requires the
@@ -8564,7 +8552,7 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm
 static int amdgpu_dm_atomic_check(struct drm_device *dev,
 				  struct drm_atomic_state *state)
 {
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct dm_atomic_state *dm_state = NULL;
 	struct dc *dc = adev->dm.dc;
 	struct drm_connector *connector;
@@ -8573,15 +8561,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct drm_plane *plane;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
-	enum surface_update_type update_type = UPDATE_TYPE_FAST;
-	enum surface_update_type overall_update_type = UPDATE_TYPE_FAST;
 	enum dc_status status;
 	int ret, i;
-
-	/*
-	 * This bool will be set for true for any modeset/reset
-	 * or plane update which implies non fast surface update.
-	 */
 	bool lock_and_validation_needed = false;
 
 	ret = drm_atomic_helper_check_modeset(dev, state);
@@ -8676,6 +8657,17 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		}
 	}
 
+	/* Prepass for updating tiling flags on new planes. */
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct dm_plane_state *new_dm_plane_state = to_dm_plane_state(new_plane_state);
+		struct amdgpu_framebuffer *new_afb = to_amdgpu_framebuffer(new_plane_state->fb);
+
+		ret = get_fb_info(new_afb, &new_dm_plane_state->tiling_flags,
+				  &new_dm_plane_state->tmz_surface);
+		if (ret)
+			goto fail;
+	}
+
 	/* Remove exiting planes if they are modified */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
@@ -8764,27 +8756,23 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		if (!is_scaling_state_different(dm_new_con_state, dm_old_con_state))
 			continue;
 
-		overall_update_type = UPDATE_TYPE_FULL;
 		lock_and_validation_needed = true;
 	}
 
-	ret = dm_determine_update_type_for_commit(&adev->dm, state, &update_type);
-	if (ret)
-		goto fail;
-
-	if (overall_update_type < update_type)
-		overall_update_type = update_type;
-
-	/*
-	 * lock_and_validation_needed was an old way to determine if we need to set
-	 * the global lock. Leaving it in to check if we broke any corner cases
-	 * lock_and_validation_needed true = UPDATE_TYPE_FULL or UPDATE_TYPE_MED
-	 * lock_and_validation_needed false = UPDATE_TYPE_FAST
+	/**
+	 * Streams and planes are reset when there are changes that affect
+	 * bandwidth. Anything that affects bandwidth needs to go through
+	 * DC global validation to ensure that the configuration can be applied
+	 * to hardware.
+	 *
+	 * We have to currently stall out here in atomic_check for outstanding
+	 * commits to finish in this case because our IRQ handlers reference
+	 * DRM state directly - we can end up disabling interrupts too early
+	 * if we don't.
+	 *
+	 * TODO: Remove this stall and drop DM state private objects.
 	 */
-	if (lock_and_validation_needed && overall_update_type <= UPDATE_TYPE_FAST)
-		WARN(1, "Global lock should be Set, overall_update_type should be UPDATE_TYPE_MED or UPDATE_TYPE_FULL");
-
-	if (overall_update_type > UPDATE_TYPE_FAST) {
+	if (lock_and_validation_needed) {
 		ret = dm_atomic_get_state(state, &dm_state);
 		if (ret)
 			goto fail;
@@ -8866,7 +8854,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		struct dm_crtc_state *dm_new_crtc_state =
 			to_dm_crtc_state(new_crtc_state);
 
-		dm_new_crtc_state->update_type = (int)overall_update_type;
+		dm_new_crtc_state->update_type = lock_and_validation_needed ?
+							 UPDATE_TYPE_FULL :
+							 UPDATE_TYPE_FAST;
 	}
 
 	/* Must be success */
@@ -8915,7 +8905,7 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 	struct dm_connector_state *dm_con_state = NULL;
 
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	bool freesync_capable = false;
 
 	if (!connector->state) {
@@ -9114,3 +9104,34 @@ static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream)
 
 	return dc_link_set_psr_allow_active(stream->link, false, true);
 }
+
+/*
+ * amdgpu_dm_psr_disable() - disable psr f/w
+ * if psr is enabled on any stream
+ *
+ * Return: true if success
+ */
+static bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm)
+{
+	DRM_DEBUG_DRIVER("Disabling psr if psr is enabled on any stream\n");
+	return dc_set_psr_allow_active(dm->dc, false);
+}
+
+void amdgpu_dm_trigger_timing_sync(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	struct dc *dc = adev->dm.dc;
+	int i;
+
+	mutex_lock(&adev->dm.dc_lock);
+	if (dc->current_state) {
+		for (i = 0; i < dc->current_state->stream_count; ++i)
+			dc->current_state->streams[i]
+				->triggered_crtc_reset.enabled =
+				adev->dm.force_timing_sync;
+
+		dm_enable_per_frame_crtc_master_sync(dc->current_state);
+		dc_trigger_sync(dc, dc->current_state);
+	}
+	mutex_unlock(&adev->dm.dc_lock);
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index dd1559c743c2..a7856ae2e5f5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -340,6 +340,14 @@ struct amdgpu_display_manager {
 	 * fake encoders used for DP MST.
 	 */
 	struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC];
+        bool force_timing_sync;
+};
+
+struct dsc_preferred_settings {
+	bool dsc_clock_en;
+	uint32_t dsc_slice_width;
+	uint32_t dsc_slice_height;
+	uint32_t dsc_bits_per_pixel;
 };
 
 struct amdgpu_dm_connector {
@@ -389,6 +397,7 @@ struct amdgpu_dm_connector {
 	uint32_t debugfs_dpcd_size;
 #endif
 	bool force_yuv420_output;
+	struct dsc_preferred_settings dsc_settings;
 };
 
 #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base)
@@ -403,6 +412,8 @@ struct dc_plane_state;
 struct dm_plane_state {
 	struct drm_plane_state base;
 	struct dc_plane_state *dc_state;
+	uint64_t tiling_flags;
+	bool tmz_surface;
 };
 
 struct dm_crtc_state {
@@ -485,6 +496,8 @@ void dm_restore_drm_connector_state(struct drm_device *dev,
 void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 					struct edid *edid);
 
+void amdgpu_dm_trigger_timing_sync(struct drm_device *dev);
+
 #define MAX_COLOR_LUT_ENTRIES 4096
 /* Legacy gamm LUT users such as X doesn't like large LUT sizes */
 #define MAX_COLOR_LEGACY_LUT_ENTRIES 256
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index b321ff654df4..5df05f0d18bc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -308,8 +308,7 @@ static int __set_input_tf(struct dc_transfer_func *func,
 int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 {
 	struct dc_stream_state *stream = crtc->stream;
-	struct amdgpu_device *adev =
-		(struct amdgpu_device *)crtc->base.state->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
 	bool has_rom = adev->asic_type <= CHIP_RAVEN;
 	struct drm_color_ctm *ctm = NULL;
 	const struct drm_color_lut *degamma_lut, *regamma_lut;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index eaad9099bc0b..d0699e98db92 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -101,7 +101,7 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 					struct dm_crtc_state *dm_crtc_state,
 					enum amdgpu_dm_pipe_crc_source source)
 {
-	struct amdgpu_device *adev = crtc->dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct dc_stream_state *stream_state = dm_crtc_state->stream;
 	bool enable = amdgpu_dm_is_valid_crc_source(source);
 	int ret = 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index e5a6d9115949..94fcb086154c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -49,6 +49,10 @@ struct dmub_debugfs_trace_entry {
 	uint32_t param1;
 };
 
+static inline const char *yesno(bool v)
+{
+	return v ? "yes" : "no";
+}
 
 /* parse_write_buffer_into_params - Helper function to parse debugfs write buffer into an array
  *
@@ -980,6 +984,161 @@ static ssize_t dp_dpcd_data_read(struct file *f, char __user *buf,
 	return read_size - r;
 }
 
+/* function: Read link's DSC & FEC capabilities
+ *
+ *
+ * Access it with the following command (you need to specify
+ * connector like DP-1):
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dp_dsc_fec_support
+ *
+ */
+static int dp_dsc_fec_support_show(struct seq_file *m, void *data)
+{
+	struct drm_connector *connector = m->private;
+	struct drm_modeset_acquire_ctx ctx;
+	struct drm_device *dev = connector->dev;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	int ret = 0;
+	bool try_again = false;
+	bool is_fec_supported = false;
+	bool is_dsc_supported = false;
+	struct dpcd_caps dpcd_caps;
+
+	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
+	do {
+		try_again = false;
+		ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
+		if (ret) {
+			if (ret == -EDEADLK) {
+				ret = drm_modeset_backoff(&ctx);
+				if (!ret) {
+					try_again = true;
+					continue;
+				}
+			}
+			break;
+		}
+		if (connector->status != connector_status_connected) {
+			ret = -ENODEV;
+			break;
+		}
+		dpcd_caps = aconnector->dc_link->dpcd_caps;
+		if (aconnector->port) {
+			/* aconnector sets dsc_aux during get_modes call
+			 * if MST connector has it means it can either
+			 * enable DSC on the sink device or on MST branch
+			 * its connected to.
+			 */
+			if (aconnector->dsc_aux) {
+				is_fec_supported = true;
+				is_dsc_supported = true;
+			}
+		} else {
+			is_fec_supported = dpcd_caps.fec_cap.raw & 0x1;
+			is_dsc_supported = dpcd_caps.dsc_caps.dsc_basic_caps.raw[0] & 0x1;
+		}
+	} while (try_again);
+
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+
+	seq_printf(m, "FEC_Sink_Support: %s\n", yesno(is_fec_supported));
+	seq_printf(m, "DSC_Sink_Support: %s\n", yesno(is_dsc_supported));
+
+	return ret;
+}
+
+/* function: Trigger virtual HPD redetection on connector
+ *
+ * This function will perform link rediscovery, link disable
+ * and enable, and dm connector state update.
+ *
+ * Retrigger HPD on an existing connector by echoing 1 into
+ * its respectful "trigger_hotplug" debugfs entry:
+ *
+ *	echo 1 > /sys/kernel/debug/dri/0/DP-X/trigger_hotplug
+ *
+ */
+static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf,
+							size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct drm_connector *connector = &aconnector->base;
+	struct drm_device *dev = connector->dev;
+	enum dc_connection_type new_connection_type = dc_connection_none;
+	char *wr_buf = NULL;
+	uint32_t wr_buf_size = 42;
+	int max_param_num = 1;
+	long param[1] = {0};
+	uint8_t param_nums = 0;
+
+	if (!aconnector || !aconnector->dc_link)
+		return -EINVAL;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+
+	if (!wr_buf) {
+		DRM_DEBUG_DRIVER("no memory to allocate write buffer\n");
+		return -ENOSPC;
+	}
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+						(long *)param, buf,
+						max_param_num,
+						&param_nums))
+		return -EINVAL;
+
+	if (param_nums <= 0) {
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param[0] == 1) {
+		mutex_lock(&aconnector->hpd_lock);
+
+		if (!dc_link_detect_sink(aconnector->dc_link, &new_connection_type) &&
+			new_connection_type != dc_connection_none)
+			goto unlock;
+
+		if (!dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD))
+			goto unlock;
+
+		amdgpu_dm_update_connector_after_detect(aconnector);
+
+		drm_modeset_lock_all(dev);
+		dm_restore_drm_connector_state(dev, connector);
+		drm_modeset_unlock_all(dev);
+
+		drm_kms_helper_hotplug_event(dev);
+
+unlock:
+		mutex_unlock(&aconnector->hpd_lock);
+	}
+
+	kfree(wr_buf);
+	return size;
+}
+
+/* function: read DSC status on the connector
+ *
+ * The read function: dp_dsc_clock_en_read
+ * returns current status of DSC clock on the connector.
+ * The return is a boolean flag: 1 or 0.
+ *
+ * Access it with the following command (you need to specify
+ * connector like DP-1):
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_clock_en
+ *
+ * Expected output:
+ * 1 - means that DSC is currently enabled
+ * 0 - means that DSC is disabled
+ */
 static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1037,6 +1196,95 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: write force DSC on the connector
+ *
+ * The write function: dp_dsc_clock_en_write
+ * enables to force DSC on the connector.
+ * User can write to either force enable DSC
+ * on the next modeset or set it to driver default
+ *
+ * Writing DSC settings is done with the following command:
+ * - To force enable DSC (you need to specify
+ * connector like DP-1):
+ *
+ *	echo 0x1 > /sys/kernel/debug/dri/0/DP-X/dsc_clock_en
+ *
+ * - To return to default state set the flag to zero and
+ * let driver deal with DSC automatically
+ * (you need to specify connector like DP-1):
+ *
+ *	echo 0x0 > /sys/kernel/debug/dri/0/DP-X/dsc_clock_en
+ *
+ */
+static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
+				     size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct pipe_ctx *pipe_ctx;
+	int i;
+	char *wr_buf = NULL;
+	uint32_t wr_buf_size = 42;
+	int max_param_num = 1;
+	long param[1] = {0};
+	uint8_t param_nums = 0;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+
+	if (!wr_buf) {
+		DRM_DEBUG_DRIVER("no memory to allocate write buffer\n");
+		return -ENOSPC;
+	}
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+					    (long *)param, buf,
+					    max_param_num,
+					    &param_nums)) {
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param_nums <= 0) {
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream &&
+			    pipe_ctx->stream->link == aconnector->dc_link)
+				break;
+	}
+
+	if (!pipe_ctx || !pipe_ctx->stream)
+		goto done;
+
+	aconnector->dsc_settings.dsc_clock_en = param[0];
+
+done:
+	kfree(wr_buf);
+	return size;
+}
+
+/* function: read DSC slice width parameter on the connector
+ *
+ * The read function: dp_dsc_slice_width_read
+ * returns dsc slice width used in the current configuration
+ * The return is an integer: 0 or other positive number
+ *
+ * Access the status with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_slice_width
+ *
+ * 0 - means that DSC is disabled
+ *
+ * Any other number more than zero represents the
+ * slice width currently used by DSC in pixels
+ *
+ */
 static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1094,6 +1342,98 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: write DSC slice width parameter
+ *
+ * The write function: dp_dsc_slice_width_write
+ * overwrites automatically generated DSC configuration
+ * of slice width.
+ *
+ * The user has to write the slice width divisible by the
+ * picture width.
+ *
+ * Also the user has to write width in hexidecimal
+ * rather than in decimal.
+ *
+ * Writing DSC settings is done with the following command:
+ * - To force overwrite slice width: (example sets to 1920 pixels)
+ *
+ *	echo 0x780 > /sys/kernel/debug/dri/0/DP-X/dsc_slice_width
+ *
+ *  - To stop overwriting and let driver find the optimal size,
+ * set the width to zero:
+ *
+ *	echo 0x0 > /sys/kernel/debug/dri/0/DP-X/dsc_slice_width
+ *
+ */
+static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
+				     size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct pipe_ctx *pipe_ctx;
+	int i;
+	char *wr_buf = NULL;
+	uint32_t wr_buf_size = 42;
+	int max_param_num = 1;
+	long param[1] = {0};
+	uint8_t param_nums = 0;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+
+	if (!wr_buf) {
+		DRM_DEBUG_DRIVER("no memory to allocate write buffer\n");
+		return -ENOSPC;
+	}
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+					    (long *)param, buf,
+					    max_param_num,
+					    &param_nums)) {
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param_nums <= 0) {
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream &&
+			    pipe_ctx->stream->link == aconnector->dc_link)
+				break;
+	}
+
+	if (!pipe_ctx || !pipe_ctx->stream)
+		goto done;
+
+	aconnector->dsc_settings.dsc_slice_width = param[0];
+
+done:
+	kfree(wr_buf);
+	return size;
+}
+
+/* function: read DSC slice height parameter on the connector
+ *
+ * The read function: dp_dsc_slice_height_read
+ * returns dsc slice height used in the current configuration
+ * The return is an integer: 0 or other positive number
+ *
+ * Access the status with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_slice_height
+ *
+ * 0 - means that DSC is disabled
+ *
+ * Any other number more than zero represents the
+ * slice height currently used by DSC in pixels
+ *
+ */
 static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1151,6 +1491,94 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: write DSC slice height parameter
+ *
+ * The write function: dp_dsc_slice_height_write
+ * overwrites automatically generated DSC configuration
+ * of slice height.
+ *
+ * The user has to write the slice height divisible by the
+ * picture height.
+ *
+ * Also the user has to write height in hexidecimal
+ * rather than in decimal.
+ *
+ * Writing DSC settings is done with the following command:
+ * - To force overwrite slice height (example sets to 128 pixels):
+ *
+ *	echo 0x80 > /sys/kernel/debug/dri/0/DP-X/dsc_slice_height
+ *
+ *  - To stop overwriting and let driver find the optimal size,
+ * set the height to zero:
+ *
+ *	echo 0x0 > /sys/kernel/debug/dri/0/DP-X/dsc_slice_height
+ *
+ */
+static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
+				     size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct pipe_ctx *pipe_ctx;
+	int i;
+	char *wr_buf = NULL;
+	uint32_t wr_buf_size = 42;
+	int max_param_num = 1;
+	uint8_t param_nums = 0;
+	long param[1] = {0};
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+
+	if (!wr_buf) {
+		DRM_DEBUG_DRIVER("no memory to allocate write buffer\n");
+		return -ENOSPC;
+	}
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+					    (long *)param, buf,
+					    max_param_num,
+					    &param_nums)) {
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param_nums <= 0) {
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream &&
+			    pipe_ctx->stream->link == aconnector->dc_link)
+				break;
+	}
+
+	if (!pipe_ctx || !pipe_ctx->stream)
+		goto done;
+
+	aconnector->dsc_settings.dsc_slice_height = param[0];
+
+done:
+	kfree(wr_buf);
+	return size;
+}
+
+/* function: read DSC target rate on the connector in bits per pixel
+ *
+ * The read function: dp_dsc_bits_per_pixel_read
+ * returns target rate of compression in bits per pixel
+ * The return is an integer: 0 or other positive integer
+ *
+ * Access it with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_bits_per_pixel
+ *
+ *  0 - means that DSC is disabled
+ */
 static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1208,6 +1636,94 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: write DSC target rate in bits per pixel
+ *
+ * The write function: dp_dsc_bits_per_pixel_write
+ * overwrites automatically generated DSC configuration
+ * of DSC target bit rate.
+ *
+ * Also the user has to write bpp in hexidecimal
+ * rather than in decimal.
+ *
+ * Writing DSC settings is done with the following command:
+ * - To force overwrite rate (example sets to 256 bpp x 1/16):
+ *
+ *	echo 0x100 > /sys/kernel/debug/dri/0/DP-X/dsc_bits_per_pixel
+ *
+ *  - To stop overwriting and let driver find the optimal rate,
+ * set the rate to zero:
+ *
+ *	echo 0x0 > /sys/kernel/debug/dri/0/DP-X/dsc_bits_per_pixel
+ *
+ */
+static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *buf,
+				     size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct pipe_ctx *pipe_ctx;
+	int i;
+	char *wr_buf = NULL;
+	uint32_t wr_buf_size = 42;
+	int max_param_num = 1;
+	uint8_t param_nums = 0;
+	long param[1] = {0};
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+
+	if (!wr_buf) {
+		DRM_DEBUG_DRIVER("no memory to allocate write buffer\n");
+		return -ENOSPC;
+	}
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+					    (long *)param, buf,
+					    max_param_num,
+					    &param_nums)) {
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param_nums <= 0) {
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream &&
+			    pipe_ctx->stream->link == aconnector->dc_link)
+				break;
+	}
+
+	if (!pipe_ctx || !pipe_ctx->stream)
+		goto done;
+
+	aconnector->dsc_settings.dsc_bits_per_pixel = param[0];
+
+done:
+	kfree(wr_buf);
+	return size;
+}
+
+/* function: read DSC picture width parameter on the connector
+ *
+ * The read function: dp_dsc_pic_width_read
+ * returns dsc picture width used in the current configuration
+ * It is the same as h_addressable of the current
+ * display's timing
+ * The return is an integer: 0 or other positive integer
+ * If 0 then DSC is disabled.
+ *
+ * Access it with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_pic_width
+ *
+ * 0 - means that DSC is disabled
+ */
 static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1322,6 +1838,21 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: read DSC chunk size parameter on the connector
+ *
+ * The read function: dp_dsc_chunk_size_read
+ * returns dsc chunk size set in the current configuration
+ * The value is calculated automatically by DSC code
+ * and depends on slice parameters and bpp target rate
+ * The return is an integer: 0 or other positive integer
+ * If 0 then DSC is disabled.
+ *
+ * Access it with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_chunk_size
+ *
+ * 0 - means that DSC is disabled
+ */
 static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1379,6 +1910,21 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/* function: read DSC slice bpg offset on the connector
+ *
+ * The read function: dp_dsc_slice_bpg_offset_read
+ * returns dsc bpg slice offset set in the current configuration
+ * The value is calculated automatically by DSC code
+ * and depends on slice parameters and bpp target rate
+ * The return is an integer: 0 or other positive integer
+ * If 0 then DSC is disabled.
+ *
+ * Access it with the following command:
+ *
+ *	cat /sys/kernel/debug/dri/0/DP-X/dsc_slice_bpg_offset
+ *
+ * 0 - means that DSC is disabled
+ */
 static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1436,6 +1982,7 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
 	return result;
 }
 
+DEFINE_SHOW_ATTRIBUTE(dp_dsc_fec_support);
 DEFINE_SHOW_ATTRIBUTE(dmub_fw_state);
 DEFINE_SHOW_ATTRIBUTE(dmub_tracebuffer);
 DEFINE_SHOW_ATTRIBUTE(output_bpc);
@@ -1446,24 +1993,28 @@ DEFINE_SHOW_ATTRIBUTE(hdcp_sink_capability);
 static const struct file_operations dp_dsc_clock_en_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_dsc_clock_en_read,
+	.write = dp_dsc_clock_en_write,
 	.llseek = default_llseek
 };
 
 static const struct file_operations dp_dsc_slice_width_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_dsc_slice_width_read,
+	.write = dp_dsc_slice_width_write,
 	.llseek = default_llseek
 };
 
 static const struct file_operations dp_dsc_slice_height_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_dsc_slice_height_read,
+	.write = dp_dsc_slice_height_write,
 	.llseek = default_llseek
 };
 
 static const struct file_operations dp_dsc_bits_per_pixel_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_dsc_bits_per_pixel_read,
+	.write = dp_dsc_bits_per_pixel_write,
 	.llseek = default_llseek
 };
 
@@ -1491,6 +2042,12 @@ static const struct file_operations dp_dsc_slice_bpg_offset_debugfs_fops = {
 	.llseek = default_llseek
 };
 
+static const struct file_operations dp_trigger_hotplug_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.write = dp_trigger_hotplug,
+	.llseek = default_llseek
+};
+
 static const struct file_operations dp_link_settings_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_link_settings_read,
@@ -1557,7 +2114,8 @@ static const struct {
 		{"dsc_pic_width", &dp_dsc_pic_width_debugfs_fops},
 		{"dsc_pic_height", &dp_dsc_pic_height_debugfs_fops},
 		{"dsc_chunk_size", &dp_dsc_chunk_size_debugfs_fops},
-		{"dsc_slice_bpg", &dp_dsc_slice_bpg_offset_debugfs_fops}
+		{"dsc_slice_bpg", &dp_dsc_slice_bpg_offset_debugfs_fops},
+		{"dp_dsc_fec_support", &dp_dsc_fec_support_fops}
 };
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
@@ -1721,7 +2279,7 @@ static int current_backlight_read(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 
 	unsigned int backlight = dc_link_get_backlight_level(dm->backlight_link);
@@ -1739,7 +2297,7 @@ static int target_backlight_read(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 
 	unsigned int backlight = dc_link_get_target_backlight_pwm(dm->backlight_link);
@@ -1778,6 +2336,38 @@ static const struct drm_info_list amdgpu_dm_debugfs_list[] = {
 };
 
 /*
+ * Sets the force_timing_sync debug optino from the given string.
+ * All connected displays will be force synchronized immediately.
+ * Usage: echo 1 > /sys/kernel/debug/dri/0/amdgpu_dm_force_timing_sync
+ */
+static int force_timing_sync_set(void *data, u64 val)
+{
+	struct amdgpu_device *adev = data;
+
+	adev->dm.force_timing_sync = (bool)val;
+
+	amdgpu_dm_trigger_timing_sync(adev_to_drm(adev));
+
+	return 0;
+}
+
+/*
+ * Gets the force_timing_sync debug option value into the given buffer.
+ * Usage: cat /sys/kernel/debug/dri/0/amdgpu_dm_force_timing_sync
+ */
+static int force_timing_sync_get(void *data, u64 *val)
+{
+	struct amdgpu_device *adev = data;
+
+	*val = adev->dm.force_timing_sync;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(force_timing_sync_ops, force_timing_sync_get,
+			 force_timing_sync_set, "%llu\n");
+
+/*
  * Sets the DC visual confirm debug option from the given string.
  * Example usage: echo 1 > /sys/kernel/debug/dri/0/amdgpu_visual_confirm
  */
@@ -1815,7 +2405,7 @@ int dtn_debugfs_init(struct amdgpu_device *adev)
 		.llseek = default_llseek
 	};
 
-	struct drm_minor *minor = adev->ddev->primary;
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *root = minor->debugfs_root;
 	int ret;
 
@@ -1836,5 +2426,8 @@ int dtn_debugfs_init(struct amdgpu_device *adev)
 	debugfs_create_file_unsafe("amdgpu_dm_dmub_fw_state", 0644, root,
 				   adev, &dmub_fw_state_fops);
 
+	debugfs_create_file_unsafe("amdgpu_dm_force_timing_sync", 0644, root,
+				   adev, &force_timing_sync_ops);
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index cbcf504f73a5..357778556b06 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -719,7 +719,7 @@ void amdgpu_dm_set_irq_funcs(struct amdgpu_device *adev)
  */
 void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 
@@ -755,7 +755,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
  */
 void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index a61a294caebe..adbb44822e94 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -68,7 +68,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
-	if (payload.write)
+	if (payload.write && result >= 0)
 		result = msg->size;
 
 	if (result < 0)
@@ -242,7 +242,7 @@ dm_mst_atomic_best_encoder(struct drm_connector *connector,
 			   struct drm_connector_state *connector_state)
 {
 	struct drm_device *dev = connector->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(connector_state->crtc);
 
 	return &adev->dm.mst_encoders[acrtc->crtc_id].base;
@@ -311,7 +311,7 @@ static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = {
 void
 dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	int i;
 
 	for (i = 0; i < adev->dm.display_indexes_num; i++) {
@@ -338,7 +338,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 {
 	struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr);
 	struct drm_device *dev = master->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
 	int i;
@@ -427,7 +427,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 	aconnector->mst_mgr.cbs = &dm_mst_cbs;
 	drm_dp_mst_topology_mgr_init(
 		&aconnector->mst_mgr,
-		dm->adev->ddev,
+		adev_to_drm(dm->adev),
 		&aconnector->dm_dp_aux.aux,
 		16,
 		4,
@@ -453,6 +453,10 @@ struct dsc_mst_fairness_params {
 	struct dc_dsc_bw_range bw_range;
 	bool compression_possible;
 	struct drm_dp_mst_port *port;
+	bool clock_overwrite;
+	uint32_t slice_width_overwrite;
+	uint32_t slice_height_overwrite;
+	uint32_t bpp_overwrite;
 };
 
 struct dsc_mst_fairness_vars {
@@ -486,7 +490,21 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p
 					params[i].timing,
 					&params[i].timing->dsc_cfg)) {
 			params[i].timing->flags.DSC = 1;
-			params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+
+			if (params[i].bpp_overwrite)
+				params[i].timing->dsc_cfg.bits_per_pixel = params[i].bpp_overwrite;
+			else
+				params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+
+			if (params[i].slice_width_overwrite)
+				params[i].timing->dsc_cfg.num_slices_h = DIV_ROUND_UP(
+										params[i].timing->h_addressable,
+										params[i].slice_width_overwrite);
+
+			if (params[i].slice_height_overwrite)
+				params[i].timing->dsc_cfg.num_slices_v = DIV_ROUND_UP(
+										params[i].timing->v_addressable,
+										params[i].slice_height_overwrite);
 		} else {
 			params[i].timing->flags.DSC = 0;
 		}
@@ -618,7 +636,9 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 	int remaining_to_try = 0;
 
 	for (i = 0; i < count; i++) {
-		if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16) {
+		if (vars[i].dsc_enabled
+				&& vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16
+				&& !params[i].clock_overwrite) {
 			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
 			tried[i] = false;
 			remaining_to_try += 1;
@@ -679,6 +699,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	struct dsc_mst_fairness_vars vars[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
 	int count = 0;
+	bool debugfs_overwrite = false;
 
 	memset(params, 0, sizeof(params));
 
@@ -697,6 +718,12 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		params[count].sink = stream->sink;
 		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 		params[count].port = aconnector->port;
+		params[count].clock_overwrite = aconnector->dsc_settings.dsc_clock_en;
+		if (params[count].clock_overwrite)
+			debugfs_overwrite = true;
+		params[count].slice_width_overwrite = aconnector->dsc_settings.dsc_slice_width;
+		params[count].slice_height_overwrite = aconnector->dsc_settings.dsc_slice_height;
+		params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel;
 		params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported;
 		dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy);
 		if (!dc_dsc_compute_bandwidth_range(
@@ -722,7 +749,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 						 dm_mst_get_pbn_divider(dc_link)) < 0)
 			return false;
 	}
-	if (!drm_dp_mst_atomic_check(state)) {
+	if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) {
 		set_dsc_configs_from_fairness_vars(params, vars, count);
 		return true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index e0f4f1be1618..047b1e2dd8f1 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -43,6 +43,10 @@ DC_LIBS += dce110
 DC_LIBS += dce100
 DC_LIBS += dce80
 
+ifdef CONFIG_DRM_AMD_DC_SI
+DC_LIBS += dce60
+endif
+
 ifdef CONFIG_DRM_AMD_DC_HDCP
 DC_LIBS += hdcp
 endif
diff --git a/drivers/gpu/drm/amd/display/dc/bios/Makefile b/drivers/gpu/drm/amd/display/dc/bios/Makefile
index 239e86bbec5a..ed6b5e9763f6 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/bios/Makefile
@@ -32,6 +32,15 @@ AMD_DAL_BIOS = $(addprefix $(AMDDALPATH)/dc/bios/,$(BIOS))
 AMD_DISPLAY_FILES += $(AMD_DAL_BIOS)
 
 ###############################################################################
+# DCE 6x
+###############################################################################
+# All DCE6.x are derived from DCE6.0, so 6.0 MUST be defined if ANY of
+# DCE6.x is compiled.
+ifdef CONFIG_DRM_AMD_DC_SI
+AMD_DISPLAY_FILES += $(AMDDALPATH)/dc/bios/dce60/command_table_helper_dce60.o
+endif
+
+###############################################################################
 # DCE 8x
 ###############################################################################
 # All DCE8.x are derived from DCE8.0, so 8.0 MUST be defined if ANY of
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 078b7e344185..2d5c7daaee23 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1108,6 +1108,18 @@ static enum bp_result bios_parser_enable_disp_power_gating(
 		action);
 }
 
+static enum bp_result bios_parser_enable_lvtma_control(
+	struct dc_bios *dcb,
+	uint8_t uc_pwr_on)
+{
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+
+	if (!bp->cmd_tbl.enable_lvtma_control)
+		return BP_RESULT_FAILURE;
+
+	return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on);
+}
+
 static bool bios_parser_is_accelerated_mode(
 	struct dc_bios *dcb)
 {
@@ -2208,7 +2220,9 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.get_board_layout_info = bios_get_board_layout_info,
 	.pack_data_tables = bios_parser_pack_data_tables,
 
-	.get_atom_dc_golden_table = bios_get_atom_dc_golden_table
+	.get_atom_dc_golden_table = bios_get_atom_dc_golden_table,
+
+	.enable_lvtma_control = bios_parser_enable_lvtma_control
 };
 
 static bool bios_parser2_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 5815983caaf8..070459e3e407 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -1877,9 +1877,7 @@ static enum bp_result set_crtc_using_dtd_timing_v3(
 			 * but it is 4 either from Edid data (spec CEA 861)
 			 * or CEA timing table.
 			 */
-			params.usV_SyncOffset =
-					cpu_to_le16(le16_to_cpu(params.usV_SyncOffset) + 1);
-
+			le16_add_cpu(&params.usV_SyncOffset, 1);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index bed91572f82a..25bdf1c38e0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -569,10 +569,7 @@ static enum bp_result set_crtc_using_dtd_timing_v3(
 			 * but it is 4 either from Edid data (spec CEA 861)
 			 * or CEA timing table.
 			 */
-			params.v_syncoffset =
-				cpu_to_le16(le16_to_cpu(params.v_syncoffset) +
-						1);
-
+			le16_add_cpu(&params.v_syncoffset, 1);
 		}
 	}
 
@@ -904,6 +901,61 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id)
 	return 0;
 }
 
+/******************************************************************************
+ ******************************************************************************
+ **
+ **                  LVTMA CONTROL
+ **
+ ******************************************************************************
+ *****************************************************************************/
+
+static enum bp_result enable_lvtma_control(
+	struct bios_parser *bp,
+	uint8_t uc_pwr_on);
+
+static void init_enable_lvtma_control(struct bios_parser *bp)
+{
+	/* TODO add switch for table vrsion */
+	bp->cmd_tbl.enable_lvtma_control = enable_lvtma_control;
+
+}
+
+static void enable_lvtma_control_dmcub(
+	struct dc_dmub_srv *dmcub,
+	uint8_t uc_pwr_on)
+{
+
+	union dmub_rb_cmd cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	cmd.cmd_common.header.type = DMUB_CMD__VBIOS;
+	cmd.cmd_common.header.sub_type =
+			DMUB_CMD__VBIOS_LVTMA_CONTROL;
+	cmd.cmd_common.cmd_buffer[0] =
+			uc_pwr_on;
+
+	dc_dmub_srv_cmd_queue(dmcub, &cmd);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+
+}
+
+static enum bp_result enable_lvtma_control(
+	struct bios_parser *bp,
+	uint8_t uc_pwr_on)
+{
+	enum bp_result result = BP_RESULT_FAILURE;
+
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		enable_lvtma_control_dmcub(bp->base.ctx->dmub_srv,
+				uc_pwr_on);
+		return BP_RESULT_OK;
+	}
+	return result;
+}
+
 void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
 {
 	init_dig_encoder_control(bp);
@@ -919,4 +971,5 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
 	init_set_dce_clock(bp);
 	init_get_smu_clock_info(bp);
 
+	init_enable_lvtma_control(bp);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h
index 7a2af24dfe60..7bdce013cde5 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h
@@ -94,7 +94,8 @@ struct cmd_tbl {
 		struct bp_set_dce_clock_parameters *bp_params);
 	unsigned int (*get_smu_clock_info)(
 			struct bios_parser *bp, uint8_t id);
-
+	enum bp_result (*enable_lvtma_control)(struct bios_parser *bp,
+			uint8_t uc_pwr_on);
 };
 
 void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp);
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
index 253bbb1eea60..48b4ef03fc8f 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
@@ -36,6 +36,14 @@ bool dal_bios_parser_init_cmd_tbl_helper(
 	enum dce_version dce)
 {
 	switch (dce) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case DCE_VERSION_6_0:
+	case DCE_VERSION_6_1:
+	case DCE_VERSION_6_4:
+		*h = dal_cmd_tbl_helper_dce60_get_table();
+		return true;
+#endif
+
 	case DCE_VERSION_8_0:
 	case DCE_VERSION_8_1:
 	case DCE_VERSION_8_3:
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h
index 4c3789df253d..dfd30aaf4032 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h
@@ -26,6 +26,9 @@
 #ifndef __DAL_COMMAND_TABLE_HELPER_H__
 #define __DAL_COMMAND_TABLE_HELPER_H__
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/command_table_helper_dce60.h"
+#endif
 #include "dce80/command_table_helper_dce80.h"
 #include "dce110/command_table_helper_dce110.h"
 #include "dce112/command_table_helper_dce112.h"
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index 21ff6b686f5f..74c498b6774d 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -37,6 +37,14 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 	enum dce_version dce)
 {
 	switch (dce) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case DCE_VERSION_6_0:
+	case DCE_VERSION_6_1:
+	case DCE_VERSION_6_4:
+		*h = dal_cmd_tbl_helper_dce60_get_table();
+		return true;
+#endif
+
 	case DCE_VERSION_8_0:
 	case DCE_VERSION_8_1:
 	case DCE_VERSION_8_3:
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.h
index 785fcb20a1b9..66e0a3e73768 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.h
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.h
@@ -26,6 +26,9 @@
 #ifndef __DAL_COMMAND_TABLE_HELPER2_H__
 #define __DAL_COMMAND_TABLE_HELPER2_H__
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/command_table_helper_dce60.h"
+#endif
 #include "dce80/command_table_helper_dce80.h"
 #include "dce110/command_table_helper_dce110.h"
 #include "dce112/command_table_helper2_dce112.h"
diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c
new file mode 100644
index 000000000000..710221b4f5c5
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c
@@ -0,0 +1,354 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+
+#include "atom.h"
+
+#include "include/grph_object_id.h"
+#include "include/grph_object_defs.h"
+#include "include/bios_parser_types.h"
+
+#include "../command_table_helper.h"
+
+static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action)
+{
+	uint8_t atom_action = 0;
+
+	switch (action) {
+	case ENCODER_CONTROL_ENABLE:
+		atom_action = ATOM_ENABLE;
+		break;
+	case ENCODER_CONTROL_DISABLE:
+		atom_action = ATOM_DISABLE;
+		break;
+	case ENCODER_CONTROL_SETUP:
+		atom_action = ATOM_ENCODER_CMD_SETUP;
+		break;
+	case ENCODER_CONTROL_INIT:
+		atom_action = ATOM_ENCODER_INIT;
+		break;
+	default:
+		BREAK_TO_DEBUGGER(); /* Unhandle action in driver.!! */
+		break;
+	}
+
+	return atom_action;
+}
+
+static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id)
+{
+	bool result = false;
+
+	if (atom_engine_id != NULL)
+		switch (id) {
+		case ENGINE_ID_DIGA:
+			*atom_engine_id = ASIC_INT_DIG1_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGB:
+			*atom_engine_id = ASIC_INT_DIG2_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGC:
+			*atom_engine_id = ASIC_INT_DIG3_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGD:
+			*atom_engine_id = ASIC_INT_DIG4_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGE:
+			*atom_engine_id = ASIC_INT_DIG5_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGF:
+			*atom_engine_id = ASIC_INT_DIG6_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DIGG:
+			*atom_engine_id = ASIC_INT_DIG7_ENCODER_ID;
+			result = true;
+			break;
+		case ENGINE_ID_DACA:
+			*atom_engine_id = ASIC_INT_DAC1_ENCODER_ID;
+			result = true;
+			break;
+		default:
+			break;
+		}
+
+	return result;
+}
+
+static bool clock_source_id_to_atom(
+	enum clock_source_id id,
+	uint32_t *atom_pll_id)
+{
+	bool result = true;
+
+	if (atom_pll_id != NULL)
+		switch (id) {
+		case CLOCK_SOURCE_ID_PLL0:
+			*atom_pll_id = ATOM_PPLL0;
+			break;
+		case CLOCK_SOURCE_ID_PLL1:
+			*atom_pll_id = ATOM_PPLL1;
+			break;
+		case CLOCK_SOURCE_ID_PLL2:
+			*atom_pll_id = ATOM_PPLL2;
+			break;
+		case CLOCK_SOURCE_ID_EXTERNAL:
+			*atom_pll_id = ATOM_PPLL_INVALID;
+			break;
+		case CLOCK_SOURCE_ID_DFS:
+			*atom_pll_id = ATOM_EXT_PLL1;
+			break;
+		case CLOCK_SOURCE_ID_VCE:
+			/* for VCE encoding,
+			 * we need to pass in ATOM_PPLL_INVALID
+			 */
+			*atom_pll_id = ATOM_PPLL_INVALID;
+			break;
+		case CLOCK_SOURCE_ID_DP_DTO:
+			/* When programming DP DTO PLL ID should be invalid */
+			*atom_pll_id = ATOM_PPLL_INVALID;
+			break;
+		case CLOCK_SOURCE_ID_UNDEFINED:
+			BREAK_TO_DEBUGGER(); /* check when this will happen! */
+			*atom_pll_id = ATOM_PPLL_INVALID;
+			result = false;
+			break;
+		default:
+			result = false;
+			break;
+		}
+
+	return result;
+}
+
+static uint8_t clock_source_id_to_atom_phy_clk_src_id(
+		enum clock_source_id id)
+{
+	uint8_t atom_phy_clk_src_id = 0;
+
+	switch (id) {
+	case CLOCK_SOURCE_ID_PLL0:
+		atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL;
+		break;
+	case CLOCK_SOURCE_ID_PLL1:
+		atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL;
+		break;
+	case CLOCK_SOURCE_ID_PLL2:
+		atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL;
+		break;
+	case CLOCK_SOURCE_ID_EXTERNAL:
+		atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT;
+		break;
+	default:
+		atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL;
+		break;
+	}
+
+	return atom_phy_clk_src_id >> 2;
+}
+
+static uint8_t signal_type_to_atom_dig_mode(enum signal_type s)
+{
+	uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP;
+
+	switch (s) {
+	case SIGNAL_TYPE_DISPLAY_PORT:
+	case SIGNAL_TYPE_EDP:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP;
+		break;
+	case SIGNAL_TYPE_LVDS:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_LVDS;
+		break;
+	case SIGNAL_TYPE_DVI_SINGLE_LINK:
+	case SIGNAL_TYPE_DVI_DUAL_LINK:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DVI;
+		break;
+	case SIGNAL_TYPE_HDMI_TYPE_A:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_HDMI;
+		break;
+	case SIGNAL_TYPE_DISPLAY_PORT_MST:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP_MST;
+		break;
+	default:
+		atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DVI;
+		break;
+	}
+
+	return atom_dig_mode;
+}
+
+static uint8_t hpd_sel_to_atom(enum hpd_source_id id)
+{
+	uint8_t atom_hpd_sel = 0;
+
+	switch (id) {
+	case HPD_SOURCEID1:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD1_SEL;
+		break;
+	case HPD_SOURCEID2:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD2_SEL;
+		break;
+	case HPD_SOURCEID3:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD3_SEL;
+		break;
+	case HPD_SOURCEID4:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD4_SEL;
+		break;
+	case HPD_SOURCEID5:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD5_SEL;
+		break;
+	case HPD_SOURCEID6:
+		atom_hpd_sel = ATOM_TRANSMITTER_CONFIG_V5_HPD6_SEL;
+		break;
+	case HPD_SOURCEID_UNKNOWN:
+	default:
+		atom_hpd_sel = 0;
+		break;
+	}
+	return atom_hpd_sel >> 4;
+}
+
+static uint8_t dig_encoder_sel_to_atom(enum engine_id id)
+{
+	uint8_t atom_dig_encoder_sel = 0;
+
+	switch (id) {
+	case ENGINE_ID_DIGA:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGA_SEL;
+		break;
+	case ENGINE_ID_DIGB:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGB_SEL;
+		break;
+	case ENGINE_ID_DIGC:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGC_SEL;
+		break;
+	case ENGINE_ID_DIGD:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGD_SEL;
+		break;
+	case ENGINE_ID_DIGE:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGE_SEL;
+		break;
+	case ENGINE_ID_DIGF:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGF_SEL;
+		break;
+	case ENGINE_ID_DIGG:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGG_SEL;
+		break;
+	default:
+		atom_dig_encoder_sel = ATOM_TRANMSITTER_V5__DIGA_SEL;
+		break;
+	}
+
+	return atom_dig_encoder_sel;
+}
+
+static uint8_t phy_id_to_atom(enum transmitter t)
+{
+	uint8_t atom_phy_id;
+
+	switch (t) {
+	case TRANSMITTER_UNIPHY_A:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYA;
+		break;
+	case TRANSMITTER_UNIPHY_B:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYB;
+		break;
+	case TRANSMITTER_UNIPHY_C:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYC;
+		break;
+	case TRANSMITTER_UNIPHY_D:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYD;
+		break;
+	case TRANSMITTER_UNIPHY_E:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYE;
+		break;
+	case TRANSMITTER_UNIPHY_F:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYF;
+		break;
+	case TRANSMITTER_UNIPHY_G:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYG;
+		break;
+	default:
+		atom_phy_id = ATOM_PHY_ID_UNIPHYA;
+		break;
+	}
+	return atom_phy_id;
+}
+
+static uint8_t disp_power_gating_action_to_atom(
+	enum bp_pipe_control_action action)
+{
+	uint8_t atom_pipe_action = 0;
+
+	switch (action) {
+	case ASIC_PIPE_DISABLE:
+		atom_pipe_action = ATOM_DISABLE;
+		break;
+	case ASIC_PIPE_ENABLE:
+		atom_pipe_action = ATOM_ENABLE;
+		break;
+	case ASIC_PIPE_INIT:
+		atom_pipe_action = ATOM_INIT;
+		break;
+	default:
+		BREAK_TO_DEBUGGER(); /* Unhandle action in driver! */
+		break;
+	}
+
+	return atom_pipe_action;
+}
+
+static const struct command_table_helper command_table_helper_funcs = {
+	.controller_id_to_atom = dal_cmd_table_helper_controller_id_to_atom,
+	.encoder_action_to_atom = encoder_action_to_atom,
+	.engine_bp_to_atom = engine_bp_to_atom,
+	.clock_source_id_to_atom = clock_source_id_to_atom,
+	.clock_source_id_to_atom_phy_clk_src_id =
+		clock_source_id_to_atom_phy_clk_src_id,
+	.signal_type_to_atom_dig_mode = signal_type_to_atom_dig_mode,
+	.hpd_sel_to_atom = hpd_sel_to_atom,
+	.dig_encoder_sel_to_atom = dig_encoder_sel_to_atom,
+	.phy_id_to_atom = phy_id_to_atom,
+	.disp_power_gating_action_to_atom = disp_power_gating_action_to_atom,
+	.assign_control_parameter =
+		dal_cmd_table_helper_assign_control_parameter,
+	.clock_source_id_to_ref_clk_src =
+		dal_cmd_table_helper_clock_source_id_to_ref_clk_src,
+	.transmitter_bp_to_atom = dal_cmd_table_helper_transmitter_bp_to_atom,
+	.encoder_id_to_atom = dal_cmd_table_helper_encoder_id_to_atom,
+	.encoder_mode_bp_to_atom =
+		dal_cmd_table_helper_encoder_mode_bp_to_atom,
+};
+
+const struct command_table_helper *dal_cmd_tbl_helper_dce60_get_table(void)
+{
+	return &command_table_helper_funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.h b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.h
new file mode 100644
index 000000000000..f733be553d5a
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_COMMAND_TABLE_HELPER_DCE60_H__
+#define __DAL_COMMAND_TABLE_HELPER_DCE60_H__
+
+struct command_table_helper;
+
+const struct command_table_helper *dal_cmd_tbl_helper_dce60_get_table(void);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 4674aca8f206..64f515d74410 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -33,6 +33,10 @@ ifdef CONFIG_PPC64
 calcs_ccflags := -mhard-float -maltivec
 endif
 
+ifdef CONFIG_ARM64
+calcs_rcflags := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
@@ -53,6 +57,9 @@ endif
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_rcflags)
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index 6874276bb2a1..1a495759a034 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -30,6 +30,17 @@ AMD_DAL_CLK_MGR = $(addprefix $(AMDDALPATH)/dc/clk_mgr/,$(CLK_MGR))
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR)
 
 
+ifdef CONFIG_DRM_AMD_DC_SI
+###############################################################################
+# DCE 60
+###############################################################################
+CLK_MGR_DCE60 = dce60_clk_mgr.o
+
+AMD_DAL_CLK_MGR_DCE60 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dce60/,$(CLK_MGR_DCE60))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCE60)
+endif
+
 ###############################################################################
 # DCE 100 and DCE8x
 ###############################################################################
@@ -93,6 +104,13 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
 endif
 
+# prevent build errors:
+# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
+# this file is unused on arm64, just like on ppc64
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := -mgeneral-regs-only
+endif
+
 AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 6a345d43028c..efb909ef7a0f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -34,6 +34,7 @@
 #include "dce110/dce110_clk_mgr.h"
 #include "dce112/dce112_clk_mgr.h"
 #include "dce120/dce120_clk_mgr.h"
+#include "dce60/dce60_clk_mgr.h"
 #include "dcn10/rv1_clk_mgr.h"
 #include "dcn10/rv2_clk_mgr.h"
 #include "dcn20/dcn20_clk_mgr.h"
@@ -123,6 +124,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 	}
 
 	switch (asic_id.chip_family) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case FAMILY_SI:
+		dce60_clk_mgr_construct(ctx, clk_mgr);
+		break;
+#endif
 	case FAMILY_CI:
 	case FAMILY_KV:
 		dce_clk_mgr_construct(ctx, clk_mgr);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
new file mode 100644
index 000000000000..c11c6b3a787d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -0,0 +1,174 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+
+#include "dccg.h"
+#include "clk_mgr_internal.h"
+#include "dce100/dce_clk_mgr.h"
+#include "dce110/dce110_clk_mgr.h"
+#include "dce60_clk_mgr.h"
+#include "reg_helper.h"
+#include "dmcu.h"
+#include "core_types.h"
+#include "dal_asic_id.h"
+
+/*
+ * Currently the register shifts and masks in this file are used for dce60
+ * which has no DPREFCLK_CNTL register
+ * TODO: remove this when DENTIST_DISPCLK_CNTL
+ * is moved to dccg, where it belongs
+ */
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+#define REG(reg) \
+	(clk_mgr->regs->reg)
+
+#undef FN
+#define FN(reg_name, field_name) \
+	clk_mgr->clk_mgr_shift->field_name, clk_mgr->clk_mgr_mask->field_name
+
+/* set register offset */
+#define SR(reg_name)\
+	.reg_name = mm ## reg_name
+
+static const struct clk_mgr_registers disp_clk_regs = {
+		CLK_COMMON_REG_LIST_DCE60_BASE()
+};
+
+static const struct clk_mgr_shift disp_clk_shift = {
+		CLK_COMMON_MASK_SH_LIST_DCE60_COMMON_BASE(__SHIFT)
+};
+
+static const struct clk_mgr_mask disp_clk_mask = {
+		CLK_COMMON_MASK_SH_LIST_DCE60_COMMON_BASE(_MASK)
+};
+
+
+/* Max clock values for each state indexed by "enum clocks_state": */
+static const struct state_dependent_clocks dce60_max_clks_by_state[] = {
+/* ClocksStateInvalid - should not be used */
+{ .display_clk_khz = 0, .pixel_clk_khz = 0 },
+/* ClocksStateUltraLow - not expected to be used for DCE 6.0 */
+{ .display_clk_khz = 0, .pixel_clk_khz = 0 },
+/* ClocksStateLow */
+{ .display_clk_khz = 352000, .pixel_clk_khz = 330000},
+/* ClocksStateNominal */
+{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 },
+/* ClocksStatePerformance */
+{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 } };
+
+int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	int dprefclk_wdivider;
+	int dp_ref_clk_khz;
+	int target_div;
+
+	/* DCE6 has no DPREFCLK_CNTL to read DP Reference Clock source */
+
+	/* Read the mmDENTIST_DISPCLK_CNTL to get the currently
+	 * programmed DID DENTIST_DPREFCLK_WDIVIDER*/
+	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
+
+	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
+	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
+
+	/* Calculate the current DFS clock, in kHz.*/
+	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+		* clk_mgr->base.dentist_vco_freq_khz) / target_div;
+
+	return dce_adjust_dp_ref_freq_for_ss(clk_mgr, dp_ref_clk_khz);
+}
+
+static void dce60_pplib_apply_display_requirements(
+	struct dc *dc,
+	struct dc_state *context)
+{
+	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
+
+	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
+
+	dce110_fill_display_configs(context, pp_display_cfg);
+
+	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
+		dm_pp_apply_display_requirements(dc->ctx, pp_display_cfg);
+}
+
+static void dce60_update_clocks(struct clk_mgr *clk_mgr_base,
+			struct dc_state *context,
+			bool safe_to_lower)
+{
+	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	struct dm_pp_power_level_change_request level_change_req;
+	int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz;
+
+	/*TODO: W/A for dal3 linux, investigate why this works */
+	if (!clk_mgr_dce->dfs_bypass_active)
+		patched_disp_clk = patched_disp_clk * 115 / 100;
+
+	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context);
+	/* get max clock state from PPLIB */
+	if ((level_change_req.power_level < clk_mgr_dce->cur_min_clks_state && safe_to_lower)
+			|| level_change_req.power_level > clk_mgr_dce->cur_min_clks_state) {
+		if (dm_pp_apply_power_level_change_request(clk_mgr_base->ctx, &level_change_req))
+			clk_mgr_dce->cur_min_clks_state = level_change_req.power_level;
+	}
+
+	if (should_set_clock(safe_to_lower, patched_disp_clk, clk_mgr_base->clks.dispclk_khz)) {
+		patched_disp_clk = dce_set_clock(clk_mgr_base, patched_disp_clk);
+		clk_mgr_base->clks.dispclk_khz = patched_disp_clk;
+	}
+	dce60_pplib_apply_display_requirements(clk_mgr_base->ctx->dc, context);
+}
+
+
+
+
+
+
+
+
+static struct clk_mgr_funcs dce60_funcs = {
+	.get_dp_ref_clk_frequency = dce60_get_dp_ref_freq_khz,
+	.update_clocks = dce60_update_clocks
+};
+
+void dce60_clk_mgr_construct(
+		struct dc_context *ctx,
+		struct clk_mgr_internal *clk_mgr)
+{
+	dce_clk_mgr_construct(ctx, clk_mgr);
+
+	memcpy(clk_mgr->max_clks_by_state,
+		dce60_max_clks_by_state,
+		sizeof(dce60_max_clks_by_state));
+
+	clk_mgr->regs = &disp_clk_regs;
+	clk_mgr->clk_mgr_shift = &disp_clk_shift;
+	clk_mgr->clk_mgr_mask = &disp_clk_mask;
+	clk_mgr->base.funcs = &dce60_funcs;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.h
new file mode 100644
index 000000000000..eca3e5168089
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.h
@@ -0,0 +1,36 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+
+#ifndef DAL_DC_DCE_DCE60_CLK_MGR_H_
+#define DAL_DC_DCE_DCE60_CLK_MGR_H_
+
+#include "dc.h"
+
+void dce60_clk_mgr_construct(
+		struct dc_context *ctx,
+		struct clk_mgr_internal *clk_mgr_dce);
+
+#endif /* DAL_DC_DCE_DCE60_CLK_MGR_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index c664404a75d4..543afa34d87a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -94,6 +94,15 @@ int rn_get_active_display_cnt_wa(
 	return display_count;
 }
 
+void rn_set_low_power_state(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER);
+	/* update power state */
+	clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER;
+}
+
 void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower)
@@ -516,6 +525,7 @@ static struct clk_mgr_funcs dcn21_funcs = {
 	.init_clocks = rn_init_clocks,
 	.enable_pme_wa = rn_enable_pme_wa,
 	.are_clock_states_equal = rn_are_clock_states_equal,
+	.set_low_power_state = rn_set_low_power_state,
 	.notify_wm_ranges = rn_notify_wm_ranges,
 	.notify_link_rate_change = rn_notify_link_rate_change,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index 9133646f6d5f..b0e9b0509568 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -554,8 +554,7 @@ void dcn3_clk_mgr_construct(
 
 void dcn3_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr)
 {
-	if (clk_mgr->base.bw_params)
-		kfree(clk_mgr->base.bw_params);
+	kfree(clk_mgr->base.bw_params);
 
 	if (clk_mgr->wm_range_table)
 		dm_helpers_free_gpu_mem(clk_mgr->base.ctx, DC_MEM_ALLOC_TYPE_GART,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 92eb1ca1634f..dc463d99ef50 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1238,6 +1238,14 @@ bool dc_enable_stereo(
 	return ret;
 }
 
+void dc_trigger_sync(struct dc *dc, struct dc_state *context)
+{
+	if (context->stream_count > 1 && !dc->debug.disable_timing_sync) {
+		enable_timing_multisync(dc, context);
+		program_timing_sync(dc, context);
+	}
+}
+
 /*
  * Applies given context to HW and copy it into current context.
  * It's up to the user to release the src context afterwards.
@@ -1297,10 +1305,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	if (result != DC_OK)
 		return result;
 
-	if (context->stream_count > 1 && !dc->debug.disable_timing_sync) {
-		enable_timing_multisync(dc, context);
-		program_timing_sync(dc, context);
-	}
+	dc_trigger_sync(dc, context);
 
 	/* Program all planes within new context*/
 	if (dc->hwss.program_front_end_for_ctx) {
@@ -2295,6 +2300,7 @@ static void commit_planes_for_stream(struct dc *dc,
 		enum surface_update_type update_type,
 		struct dc_state *context)
 {
+	bool mpcc_disconnected = false;
 	int i, j;
 	struct pipe_ctx *top_pipe_to_program = NULL;
 
@@ -2325,6 +2331,15 @@ static void commit_planes_for_stream(struct dc *dc,
 		context_clock_trace(dc, context);
 	}
 
+	if (update_type != UPDATE_TYPE_FAST && dc->hwss.interdependent_update_lock &&
+		dc->hwss.disconnect_pipes && dc->hwss.wait_for_pending_cleared){
+		dc->hwss.interdependent_update_lock(dc, context, true);
+		mpcc_disconnected = dc->hwss.disconnect_pipes(dc, context);
+		dc->hwss.interdependent_update_lock(dc, context, false);
+		if (mpcc_disconnected)
+			dc->hwss.wait_for_pending_cleared(dc, context);
+	}
+
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 
@@ -2621,7 +2636,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 
 	copy_stream_update_to_stream(dc, context, stream, stream_update);
 
-	if (update_type > UPDATE_TYPE_FAST) {
+	if (update_type >= UPDATE_TYPE_FULL) {
 		if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
 			DC_ERROR("Mode validation failed for stream update!\n");
 			dc_release_state(context);
@@ -2933,6 +2948,30 @@ void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_
 		dc->hwss.get_clock(dc, clock_type, clock_cfg);
 }
 
+/* enable/disable eDP PSR without specify stream for eDP */
+bool dc_set_psr_allow_active(struct dc *dc, bool enable)
+{
+	int i;
+
+	for (i = 0; i < dc->current_state->stream_count ; i++) {
+		struct dc_link *link;
+		struct dc_stream_state *stream = dc->current_state->streams[i];
+
+		link = stream->link;
+		if (!link)
+			continue;
+
+		if (link->psr_settings.psr_feature_enabled) {
+			if (enable && !link->psr_settings.psr_allow_active)
+				return dc_link_set_psr_allow_active(link, true, false);
+			else if (!enable && link->psr_settings.psr_allow_active)
+				return dc_link_set_psr_allow_active(link, false, false);
+		}
+	}
+
+	return true;
+}
+
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 
 void dc_allow_idle_optimizations(struct dc *dc, bool allow)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 4bd6e03a7ef3..437d1a7a16fe 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -763,6 +763,7 @@ static bool detect_dp(struct dc_link *link,
 		sink_caps->signal = dp_passive_dongle_detection(link->ddc,
 								sink_caps,
 								audio_support);
+		link->dpcd_caps.dongle_type = sink_caps->dongle_type;
 	}
 
 	return true;
@@ -3289,7 +3290,6 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 	update_psp_stream_config(pipe_ctx, true);
 #endif
-
 	dc->hwss.blank_stream(pipe_ctx);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 9bc03f26efda..d1d95d3e248a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2431,6 +2431,12 @@ static bool decide_edp_link_settings(struct dc_link *link, struct dc_link_settin
 	return false;
 }
 
+static bool decide_mst_link_settings(const struct dc_link *link, struct dc_link_settings *link_setting)
+{
+	*link_setting = link->verified_link_cap;
+	return true;
+}
+
 void decide_link_settings(struct dc_stream_state *stream,
 	struct dc_link_settings *link_setting)
 {
@@ -2456,11 +2462,9 @@ void decide_link_settings(struct dc_stream_state *stream,
 	 * TODO: add MST specific link training routine
 	 */
 	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-		*link_setting = link->verified_link_cap;
-		return;
-	}
-
-	if (link->connector_signal == SIGNAL_TYPE_EDP) {
+		if (decide_mst_link_settings(link, link_setting))
+			return;
+	} else if (link->connector_signal == SIGNAL_TYPE_EDP) {
 		if (decide_edp_link_settings(link, link_setting, req_bw))
 			return;
 	} else if (decide_dp_link_settings(link, link_setting, req_bw))
@@ -4409,9 +4413,9 @@ bool dc_link_get_backlight_level_nits(struct dc_link *link,
 			link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT))
 		return false;
 
-	if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK,
+	if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK,
 			dpcd_backlight_get.raw,
-			sizeof(union dpcd_source_backlight_get)))
+			sizeof(union dpcd_source_backlight_get)) != DC_OK)
 		return false;
 
 	*backlight_millinits_avg =
@@ -4450,9 +4454,9 @@ bool dc_link_read_default_bl_aux(struct dc_link *link, uint32_t *backlight_milli
 		link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT))
 		return false;
 
-	if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL,
+	if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL,
 		(uint8_t *) backlight_millinits,
-		sizeof(uint32_t)))
+		sizeof(uint32_t)) != DC_OK)
 		return false;
 
 	return true;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 7b5f90ebb133..c6b737dd8425 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -42,6 +42,9 @@
 #include "virtual/virtual_stream_encoder.h"
 #include "dpcd_defs.h"
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/dce60_resource.h"
+#endif
 #include "dce80/dce80_resource.h"
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
@@ -63,6 +66,18 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
 	switch (asic_id.chip_family) {
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case FAMILY_SI:
+		if (ASIC_REV_IS_TAHITI_P(asic_id.hw_internal_rev) ||
+		    ASIC_REV_IS_PITCAIRN_PM(asic_id.hw_internal_rev) ||
+		    ASIC_REV_IS_CAPEVERDE_M(asic_id.hw_internal_rev))
+			dc_version = DCE_VERSION_6_0;
+		else if (ASIC_REV_IS_OLAND_M(asic_id.hw_internal_rev))
+			dc_version = DCE_VERSION_6_4;
+		else
+			dc_version = DCE_VERSION_6_1;
+		break;
+#endif
 	case FAMILY_CI:
 		dc_version = DCE_VERSION_8_0;
 		break;
@@ -129,6 +144,20 @@ struct resource_pool *dc_create_resource_pool(struct dc  *dc,
 	struct resource_pool *res_pool = NULL;
 
 	switch (dc_version) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case DCE_VERSION_6_0:
+		res_pool = dce60_create_resource_pool(
+			init_data->num_virtual_links, dc);
+		break;
+	case DCE_VERSION_6_1:
+		res_pool = dce61_create_resource_pool(
+			init_data->num_virtual_links, dc);
+		break;
+	case DCE_VERSION_6_4:
+		res_pool = dce64_create_resource_pool(
+			init_data->num_virtual_links, dc);
+		break;
+#endif
 	case DCE_VERSION_8_0:
 		res_pool = dce80_create_resource_pool(
 				init_data->num_virtual_links, dc);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 0257a900fe2b..f42a17d765e3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -708,3 +708,4 @@ void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 			"\tlink: %d\n",
 			stream->link->link_index);
 }
+
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f50ef4255020..1d9c8e09c08b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -42,7 +42,7 @@
 #include "inc/hw/dmcu.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.2.95"
+#define DC_VER "3.2.99"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -1265,6 +1265,9 @@ void dc_unlock_memory_clock_frequency(struct dc *dc);
 void dc_lock_memory_clock_frequency(struct dc *dc);
 
 #endif
+
+bool dc_set_psr_allow_active(struct dc *dc, bool enable);
+
 /*******************************************************************************
  * DSC Interfaces
  ******************************************************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index d06d07042a12..0811f941f430 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -136,6 +136,10 @@ struct dc_vbios_funcs {
 
 	enum bp_result (*get_atom_dc_golden_table)(
 			struct dc_bios *dcb);
+
+	enum bp_result (*enable_lvtma_control)(
+		struct dc_bios *bios,
+		uint8_t uc_pwr_on);
 };
 
 struct bios_registers {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
index 3800340a5b4f..768ab38d41cf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
@@ -51,6 +51,7 @@ struct dc_dsc_policy {
 	int min_slice_height; // Must not be less than 8
 	uint32_t max_target_bpp;
 	uint32_t min_target_bpp;
+	bool enable_dsc_when_not_needed;
 };
 
 bool dc_dsc_parse_dsc_dpcd(const struct dc *dc,
@@ -80,4 +81,6 @@ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
 
 void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit);
 
+void dc_dsc_policy_set_enable_dsc_when_not_needed(bool enable);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 633442bc7ef2..c246af7c584b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -233,7 +233,7 @@ struct dc_stream_state {
 	union stream_update_flags update_flags;
 };
 
-#define ABM_LEVEL_IMMEDIATE_DISABLE 0xFFFFFFFF
+#define ABM_LEVEL_IMMEDIATE_DISABLE 255
 
 struct dc_stream_update {
 	struct dc_stream_state *stream;
@@ -397,6 +397,8 @@ bool dc_enable_stereo(
 	struct dc_stream_state *streams[],
 	uint8_t stream_count);
 
+/* Triggers multi-stream synchronization. */
+void dc_trigger_sync(struct dc *dc, struct dc_state *context);
 
 enum surface_update_type dc_check_update_surfaces_for_stream(
 		struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 946ba929c6f6..aa8e0955db48 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -233,6 +233,7 @@ struct dc_panel_patch {
 	unsigned int skip_scdc_overwrite;
 	unsigned int delay_ignore_msa;
 	unsigned int disable_fec;
+	unsigned int extra_t3_ms;
 };
 
 struct dc_edid_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index a44effcda49f..e84d21605854 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -46,6 +46,8 @@
 	SR(BL1_PWM_USER_LEVEL), \
 	SR(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES), \
 	SR(DC_ABM1_HGLS_REG_READ_PROGRESS), \
+	SR(DC_ABM1_ACE_OFFSET_SLOPE_0), \
+	SR(DC_ABM1_ACE_THRES_12), \
 	SR(BIOS_SCRATCH_2)
 
 #define ABM_DCN10_REG_LIST(id)\
@@ -60,6 +62,8 @@
 	SRI(BL1_PWM_USER_LEVEL, ABM, id), \
 	SRI(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES, ABM, id), \
 	SRI(DC_ABM1_HGLS_REG_READ_PROGRESS, ABM, id), \
+	SRI(DC_ABM1_ACE_OFFSET_SLOPE_0, ABM, id), \
+	SRI(DC_ABM1_ACE_THRES_12, ABM, id), \
 	NBIO_SR(BIOS_SCRATCH_2)
 
 #define ABM_DCN20_REG_LIST() \
@@ -74,10 +78,12 @@
 	SR(BL1_PWM_USER_LEVEL), \
 	SR(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES), \
 	SR(DC_ABM1_HGLS_REG_READ_PROGRESS), \
+	SR(DC_ABM1_ACE_OFFSET_SLOPE_0), \
+	SR(DC_ABM1_ACE_THRES_12), \
 	NBIO_SR(BIOS_SCRATCH_2)
 
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
-#define ABM_DCN301_REG_LIST(id)\
+#define ABM_DCN30_REG_LIST(id)\
 	ABM_COMMON_REG_LIST_DCE_BASE(), \
 	SRI(DC_ABM1_HG_SAMPLE_RATE, ABM, id), \
 	SRI(DC_ABM1_LS_SAMPLE_RATE, ABM, id), \
@@ -89,6 +95,8 @@
 	SRI(BL1_PWM_USER_LEVEL, ABM, id), \
 	SRI(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES, ABM, id), \
 	SRI(DC_ABM1_HGLS_REG_READ_PROGRESS, ABM, id), \
+	SRI(DC_ABM1_ACE_OFFSET_SLOPE_0, ABM, id), \
+	SRI(DC_ABM1_ACE_THRES_12, ABM, id), \
 	NBIO_SR(BIOS_SCRATCH_2)
 #endif
 
@@ -208,6 +216,8 @@ struct dce_abm_registers {
 	uint32_t BL1_PWM_USER_LEVEL;
 	uint32_t DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES;
 	uint32_t DC_ABM1_HGLS_REG_READ_PROGRESS;
+	uint32_t DC_ABM1_ACE_OFFSET_SLOPE_0;
+	uint32_t DC_ABM1_ACE_THRES_12;
 	uint32_t MASTER_COMM_CNTL_REG;
 	uint32_t MASTER_COMM_CMD_REG;
 	uint32_t MASTER_COMM_DATA_REG1;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 408046579712..2a2a0fdb9253 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -867,6 +867,98 @@ void dce_aud_wall_dto_setup(
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_aud_wall_dto_setup(
+	struct audio *audio,
+	enum signal_type signal,
+	const struct audio_crtc_info *crtc_info,
+	const struct audio_pll_info *pll_info)
+{
+	struct dce_audio *aud = DCE_AUD(audio);
+
+	struct azalia_clock_info clock_info = { 0 };
+
+	if (dc_is_hdmi_signal(signal)) {
+		uint32_t src_sel;
+
+		/*DTO0 Programming goal:
+		-generate 24MHz, 128*Fs from 24MHz
+		-use DTO0 when an active HDMI port is connected
+		(optionally a DP is connected) */
+
+		/* calculate DTO settings */
+		get_azalia_clock_info_hdmi(
+			crtc_info->requested_pixel_clock_100Hz,
+			crtc_info->calculated_pixel_clock_100Hz,
+			&clock_info);
+
+		DC_LOG_HW_AUDIO("\n%s:Input::requested_pixel_clock_100Hz = %d"\
+				"calculated_pixel_clock_100Hz =%d\n"\
+				"audio_dto_module = %d audio_dto_phase =%d \n\n", __func__,\
+				crtc_info->requested_pixel_clock_100Hz,\
+				crtc_info->calculated_pixel_clock_100Hz,\
+				clock_info.audio_dto_module,\
+				clock_info.audio_dto_phase);
+
+		/* On TN/SI, Program DTO source select and DTO select before
+		programming DTO modulo and DTO phase. These bits must be
+		programmed first, otherwise there will be no HDMI audio at boot
+		up. This is a HW sequence change (different from old ASICs).
+		Caution when changing this programming sequence.
+
+		HDMI enabled, using DTO0
+		program master CRTC for DTO0 */
+		src_sel = pll_info->dto_source - DTO_SOURCE_ID0;
+		REG_UPDATE_2(DCCG_AUDIO_DTO_SOURCE,
+			DCCG_AUDIO_DTO0_SOURCE_SEL, src_sel,
+			DCCG_AUDIO_DTO_SEL, 0);
+
+		/* module */
+		REG_UPDATE(DCCG_AUDIO_DTO0_MODULE,
+			DCCG_AUDIO_DTO0_MODULE, clock_info.audio_dto_module);
+
+		/* phase */
+		REG_UPDATE(DCCG_AUDIO_DTO0_PHASE,
+			DCCG_AUDIO_DTO0_PHASE, clock_info.audio_dto_phase);
+	} else {
+		/*DTO1 Programming goal:
+		-generate 24MHz, 128*Fs from 24MHz (DCE6 does not support 512*Fs)
+		-default is to used DTO1, and switch to DTO0 when an audio
+		master HDMI port is connected
+		-use as default for DP
+
+		calculate DTO settings */
+		get_azalia_clock_info_dp(
+			crtc_info->requested_pixel_clock_100Hz,
+			pll_info,
+			&clock_info);
+
+		/* Program DTO select before programming DTO modulo and DTO
+		phase. default to use DTO1 */
+
+		REG_UPDATE(DCCG_AUDIO_DTO_SOURCE,
+				DCCG_AUDIO_DTO_SEL, 1);
+
+			/* DCCG_AUDIO_DTO2_USE_512FBR_DTO, 1)
+			 * Cannot select 512fs for DP
+			 *
+			 * DCE6 has no DCCG_AUDIO_DTO2_USE_512FBR_DTO mask
+			*/
+
+		/* module */
+		REG_UPDATE(DCCG_AUDIO_DTO1_MODULE,
+				DCCG_AUDIO_DTO1_MODULE, clock_info.audio_dto_module);
+
+		/* phase */
+		REG_UPDATE(DCCG_AUDIO_DTO1_PHASE,
+				DCCG_AUDIO_DTO1_PHASE, clock_info.audio_dto_phase);
+
+		/* DCE6 has no DCCG_AUDIO_DTO2_USE_512FBR_DTO mask in DCCG_AUDIO_DTO_SOURCE reg */
+
+	}
+}
+#endif
+
 static bool dce_aud_endpoint_valid(struct audio *audio)
 {
 	uint32_t value;
@@ -926,6 +1018,19 @@ static const struct audio_funcs funcs = {
 	.az_configure = dce_aud_az_configure,
 	.destroy = dce_aud_destroy,
 };
+
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct audio_funcs dce60_funcs = {
+	.endpoint_valid = dce_aud_endpoint_valid,
+	.hw_init = dce_aud_hw_init,
+	.wall_dto_setup = dce60_aud_wall_dto_setup,
+	.az_enable = dce_aud_az_enable,
+	.az_disable = dce_aud_az_disable,
+	.az_configure = dce_aud_az_configure,
+	.destroy = dce_aud_destroy,
+};
+#endif
+
 void dce_aud_destroy(struct audio **audio)
 {
 	struct dce_audio *aud = DCE_AUD(*audio);
@@ -959,3 +1064,29 @@ struct audio *dce_audio_create(
 	return &audio->base;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+struct audio *dce60_audio_create(
+		struct dc_context *ctx,
+		unsigned int inst,
+		const struct dce_audio_registers *reg,
+		const struct dce_audio_shift *shifts,
+		const struct dce_audio_mask *masks
+		)
+{
+	struct dce_audio *audio = kzalloc(sizeof(*audio), GFP_KERNEL);
+
+	if (audio == NULL) {
+		ASSERT_CRITICAL(audio);
+		return NULL;
+	}
+
+	audio->base.ctx = ctx;
+	audio->base.inst = inst;
+	audio->base.funcs = &dce60_funcs;
+
+	audio->regs = reg;
+	audio->shifts = shifts;
+	audio->masks = masks;
+	return &audio->base;
+}
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.h b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.h
index 1392fab0860b..5622d5e32d81 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.h
@@ -64,6 +64,20 @@
 		SF(AZALIA_F0_CODEC_ENDPOINT_INDEX, AZALIA_ENDPOINT_REG_INDEX, mask_sh),\
 		SF(AZALIA_F0_CODEC_ENDPOINT_DATA, AZALIA_ENDPOINT_REG_DATA, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define AUD_DCE60_MASK_SH_LIST(mask_sh)\
+		SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, mask_sh),\
+		SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO_SEL, mask_sh),\
+		SF(DCCG_AUDIO_DTO0_MODULE, DCCG_AUDIO_DTO0_MODULE, mask_sh),\
+		SF(DCCG_AUDIO_DTO0_PHASE, DCCG_AUDIO_DTO0_PHASE, mask_sh),\
+		SF(DCCG_AUDIO_DTO1_MODULE, DCCG_AUDIO_DTO1_MODULE, mask_sh),\
+		SF(DCCG_AUDIO_DTO1_PHASE, DCCG_AUDIO_DTO1_PHASE, mask_sh),\
+		SF(AZALIA_F0_CODEC_FUNCTION_PARAMETER_SUPPORTED_SIZE_RATES, AUDIO_RATE_CAPABILITIES, mask_sh),\
+		SF(AZALIA_F0_CODEC_FUNCTION_PARAMETER_POWER_STATES, CLKSTOP, mask_sh),\
+		SF(AZALIA_F0_CODEC_FUNCTION_PARAMETER_POWER_STATES, EPSS, mask_sh), \
+		SF(AZALIA_F0_CODEC_ENDPOINT_INDEX, AZALIA_ENDPOINT_REG_INDEX, mask_sh),\
+		SF(AZALIA_F0_CODEC_ENDPOINT_DATA, AZALIA_ENDPOINT_REG_DATA, mask_sh)
+#endif
 
 struct dce_audio_registers {
 	uint32_t AZALIA_F0_CODEC_ENDPOINT_INDEX;
@@ -135,6 +149,15 @@ struct audio *dce_audio_create(
 		const struct dce_audio_shift *shifts,
 		const struct dce_audio_mask *masks);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+struct audio *dce60_audio_create(
+		struct dc_context *ctx,
+		unsigned int inst,
+		const struct dce_audio_registers *reg,
+		const struct dce_audio_shift *shifts,
+		const struct dce_audio_mask *masks);
+#endif
+
 void dce_aud_destroy(struct audio **audio);
 
 void dce_aud_hw_init(struct audio *audio);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
index 5e044c2d3d6d..93e7f34d4775 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
@@ -46,6 +46,24 @@
 	SR(SMU_INTERRUPT_CONTROL), \
 	SR(DC_DMCU_SCRATCH)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define DMCU_DCE60_REG_LIST() \
+	SR(DMCU_CTRL), \
+	SR(DMCU_STATUS), \
+	SR(DMCU_RAM_ACCESS_CTRL), \
+	SR(DMCU_IRAM_WR_CTRL), \
+	SR(DMCU_IRAM_WR_DATA), \
+	SR(MASTER_COMM_DATA_REG1), \
+	SR(MASTER_COMM_DATA_REG2), \
+	SR(MASTER_COMM_DATA_REG3), \
+	SR(MASTER_COMM_CMD_REG), \
+	SR(MASTER_COMM_CNTL_REG), \
+	SR(DMCU_IRAM_RD_CTRL), \
+	SR(DMCU_IRAM_RD_DATA), \
+	SR(DMCU_INTERRUPT_TO_UC_EN_MASK), \
+	SR(DC_DMCU_SCRATCH)
+#endif
+
 #define DMCU_DCE80_REG_LIST() \
 	SR(DMCU_CTRL), \
 	SR(DMCU_STATUS), \
@@ -104,6 +122,25 @@
 			STATIC_SCREEN4_INT_TO_UC_EN, mask_sh), \
 	DMCU_SF(SMU_INTERRUPT_CONTROL, DC_SMU_INT_ENABLE, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define DMCU_MASK_SH_LIST_DCE60(mask_sh) \
+	DMCU_SF(DMCU_CTRL, \
+			DMCU_ENABLE, mask_sh), \
+	DMCU_SF(DMCU_STATUS, \
+			UC_IN_STOP_MODE, mask_sh), \
+	DMCU_SF(DMCU_STATUS, \
+			UC_IN_RESET, mask_sh), \
+	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
+			IRAM_HOST_ACCESS_EN, mask_sh), \
+	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
+			IRAM_WR_ADDR_AUTO_INC, mask_sh), \
+	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
+			IRAM_RD_ADDR_AUTO_INC, mask_sh), \
+	DMCU_SF(MASTER_COMM_CMD_REG, \
+			MASTER_COMM_CMD_REG_BYTE0, mask_sh), \
+	DMCU_SF(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, mask_sh)
+#endif
+
 #define DMCU_MASK_SH_LIST_DCE80(mask_sh) \
 	DMCU_SF(DMCU_CTRL, \
 			DMCU_ENABLE, mask_sh), \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
index e1c5839a80dc..4202fadb2c0e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
@@ -85,6 +85,15 @@ void dce_pipe_control_lock(struct dc *dc,
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_pipe_control_lock(struct dc *dc,
+		struct pipe_ctx *pipe,
+		bool lock)
+{
+	/* DCE6 has no BLND_V_UPDATE_LOCK register */
+}
+#endif
+
 void dce_set_blender_mode(struct dce_hwseq *hws,
 	unsigned int blnd_inst,
 	enum blnd_mode mode)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 66b88d6ba398..70bbc1311327 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -110,6 +110,12 @@
 	SR(BLNDV_CONTROL),\
 	HWSEQ_PIXEL_RATE_REG_LIST(CRTC)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define HWSEQ_DCE6_REG_LIST() \
+	HWSEQ_DCEF_REG_LIST_DCE8(), \
+	HWSEQ_PIXEL_RATE_REG_LIST(CRTC)
+#endif
+
 #define HWSEQ_DCE8_REG_LIST() \
 	HWSEQ_DCEF_REG_LIST_DCE8(), \
 	HWSEQ_BLND_REG_LIST(), \
@@ -488,6 +494,12 @@ struct dce_hwseq_registers {
 	HWS_SF1(blk, PHYPLL_PIXEL_RATE_CNTL, PHYPLL_PIXEL_RATE_SOURCE, mask_sh),\
 	HWS_SF1(blk, PHYPLL_PIXEL_RATE_CNTL, PIXEL_RATE_PLL_SOURCE, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define HWSEQ_DCE6_MASK_SH_LIST(mask_sh)\
+	.DCFE_CLOCK_ENABLE = CRTC_DCFE_CLOCK_CONTROL__CRTC_DCFE_CLOCK_ENABLE ## mask_sh, \
+	HWSEQ_PIXEL_RATE_MASK_SH_LIST(mask_sh, CRTC0_)
+#endif
+
 #define HWSEQ_DCE8_MASK_SH_LIST(mask_sh)\
 	.DCFE_CLOCK_ENABLE = CRTC_DCFE_CLOCK_CONTROL__CRTC_DCFE_CLOCK_ENABLE ## mask_sh, \
 	HWS_SF(BLND_, V_UPDATE_LOCK, BLND_DCP_GRPH_V_UPDATE_LOCK, mask_sh),\
@@ -836,6 +848,12 @@ void dce_pipe_control_lock(struct dc *dc,
 void dce_set_blender_mode(struct dce_hwseq *hws,
 	unsigned int blnd_inst, enum blnd_mode mode);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_pipe_control_lock(struct dc *dc,
+		struct pipe_ctx *pipe,
+		bool lock);
+#endif
+
 void dce_clock_gating_power_up(struct dce_hwseq *hws,
 		bool enable);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
index ce30dbf579d4..80569a2734eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
@@ -231,6 +231,22 @@ static void dce_ipp_set_degamma(
 		  CURSOR2_DEGAMMA_MODE, degamma_type);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_ipp_set_degamma(
+	struct input_pixel_processor *ipp,
+	enum ipp_degamma_mode mode)
+{
+	struct dce_ipp *ipp_dce = TO_DCE_IPP(ipp);
+	uint32_t degamma_type = (mode == IPP_DEGAMMA_MODE_HW_sRGB) ? 1 : 0;
+
+	ASSERT(mode == IPP_DEGAMMA_MODE_BYPASS || mode == IPP_DEGAMMA_MODE_HW_sRGB);
+	/* DCE6 does not have CURSOR2_DEGAMMA_MODE bit in DEGAMMA_CONTROL reg */
+	REG_SET_2(DEGAMMA_CONTROL, 0,
+		  GRPH_DEGAMMA_MODE, degamma_type,
+		  CURSOR_DEGAMMA_MODE, degamma_type);
+}
+#endif
+
 static const struct ipp_funcs dce_ipp_funcs = {
 	.ipp_cursor_set_attributes = dce_ipp_cursor_set_attributes,
 	.ipp_cursor_set_position = dce_ipp_cursor_set_position,
@@ -239,6 +255,17 @@ static const struct ipp_funcs dce_ipp_funcs = {
 	.ipp_set_degamma = dce_ipp_set_degamma
 };
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct ipp_funcs dce60_ipp_funcs = {
+	.ipp_cursor_set_attributes = dce_ipp_cursor_set_attributes,
+	.ipp_cursor_set_position = dce_ipp_cursor_set_position,
+	.ipp_program_prescale = dce_ipp_program_prescale,
+	.ipp_program_input_lut = dce_ipp_program_input_lut,
+	.ipp_set_degamma = dce60_ipp_set_degamma
+};
+#endif
+
+
 /*****************************************/
 /* Constructor, Destructor               */
 /*****************************************/
@@ -260,6 +287,25 @@ void dce_ipp_construct(
 	ipp_dce->ipp_mask = ipp_mask;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_ipp_construct(
+	struct dce_ipp *ipp_dce,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_ipp_registers *regs,
+	const struct dce_ipp_shift *ipp_shift,
+	const struct dce_ipp_mask *ipp_mask)
+{
+	ipp_dce->base.ctx = ctx;
+	ipp_dce->base.inst = inst;
+	ipp_dce->base.funcs = &dce60_ipp_funcs;
+
+	ipp_dce->regs = regs;
+	ipp_dce->ipp_shift = ipp_shift;
+	ipp_dce->ipp_mask = ipp_mask;
+}
+#endif
+
 void dce_ipp_destroy(struct input_pixel_processor **ipp)
 {
 	kfree(TO_DCE_IPP(*ipp));
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.h b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.h
index ca04e97d44c3..0028d4bdd81b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.h
@@ -147,6 +147,46 @@
 	IPP_SF(DCP0_DEGAMMA_CONTROL, CURSOR_DEGAMMA_MODE, mask_sh), \
 	IPP_SF(DCP0_DEGAMMA_CONTROL, CURSOR2_DEGAMMA_MODE, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define IPP_DCE60_MASK_SH_LIST_DCE_COMMON_BASE(mask_sh) \
+	IPP_SF(CUR_UPDATE, CURSOR_UPDATE_LOCK, mask_sh), \
+	IPP_SF(CUR_CONTROL, CURSOR_EN, mask_sh), \
+	IPP_SF(CUR_CONTROL, CURSOR_MODE, mask_sh), \
+	IPP_SF(CUR_CONTROL, CURSOR_2X_MAGNIFY, mask_sh), \
+	IPP_SF(CUR_CONTROL, CUR_INV_TRANS_CLAMP, mask_sh), \
+	IPP_SF(CUR_POSITION, CURSOR_X_POSITION, mask_sh), \
+	IPP_SF(CUR_POSITION, CURSOR_Y_POSITION, mask_sh), \
+	IPP_SF(CUR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
+	IPP_SF(CUR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
+	IPP_SF(CUR_COLOR1, CUR_COLOR1_BLUE, mask_sh), \
+	IPP_SF(CUR_COLOR1, CUR_COLOR1_GREEN, mask_sh), \
+	IPP_SF(CUR_COLOR1, CUR_COLOR1_RED, mask_sh), \
+	IPP_SF(CUR_COLOR2, CUR_COLOR2_BLUE, mask_sh), \
+	IPP_SF(CUR_COLOR2, CUR_COLOR2_GREEN, mask_sh), \
+	IPP_SF(CUR_COLOR2, CUR_COLOR2_RED, mask_sh), \
+	IPP_SF(CUR_SIZE, CURSOR_WIDTH, mask_sh), \
+	IPP_SF(CUR_SIZE, CURSOR_HEIGHT, mask_sh), \
+	IPP_SF(CUR_SURFACE_ADDRESS_HIGH, CURSOR_SURFACE_ADDRESS_HIGH, mask_sh), \
+	IPP_SF(CUR_SURFACE_ADDRESS, CURSOR_SURFACE_ADDRESS, mask_sh), \
+	IPP_SF(PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_BYPASS, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_R, GRPH_PRESCALE_SCALE_R, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_R, GRPH_PRESCALE_BIAS_R, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_G, GRPH_PRESCALE_SCALE_G, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_G, GRPH_PRESCALE_BIAS_G, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_B, GRPH_PRESCALE_SCALE_B, mask_sh), \
+	IPP_SF(PRESCALE_VALUES_GRPH_B, GRPH_PRESCALE_BIAS_B, mask_sh), \
+	IPP_SF(INPUT_GAMMA_CONTROL, GRPH_INPUT_GAMMA_MODE, mask_sh), \
+	IPP_SF(DC_LUT_WRITE_EN_MASK, DC_LUT_WRITE_EN_MASK, mask_sh), \
+	IPP_SF(DC_LUT_RW_MODE, DC_LUT_RW_MODE, mask_sh), \
+	IPP_SF(DC_LUT_CONTROL, DC_LUT_DATA_R_FORMAT, mask_sh), \
+	IPP_SF(DC_LUT_CONTROL, DC_LUT_DATA_G_FORMAT, mask_sh), \
+	IPP_SF(DC_LUT_CONTROL, DC_LUT_DATA_B_FORMAT, mask_sh), \
+	IPP_SF(DC_LUT_RW_INDEX, DC_LUT_RW_INDEX, mask_sh), \
+	IPP_SF(DC_LUT_SEQ_COLOR, DC_LUT_SEQ_COLOR, mask_sh), \
+	IPP_SF(DEGAMMA_CONTROL, GRPH_DEGAMMA_MODE, mask_sh), \
+	IPP_SF(DEGAMMA_CONTROL, CURSOR_DEGAMMA_MODE, mask_sh)
+#endif
+
 #define IPP_REG_FIELD_LIST(type) \
 	type CURSOR_UPDATE_LOCK; \
 	type CURSOR_EN; \
@@ -233,6 +273,15 @@ void dce_ipp_construct(struct dce_ipp *ipp_dce,
 	const struct dce_ipp_shift *ipp_shift,
 	const struct dce_ipp_mask *ipp_mask);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_ipp_construct(struct dce_ipp *ipp_dce,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_ipp_registers *regs,
+	const struct dce_ipp_shift *ipp_shift,
+	const struct dce_ipp_mask *ipp_mask);
+#endif
+
 void dce_ipp_destroy(struct input_pixel_processor **ipp);
 
 #endif /* _DCE_IPP_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 8d8c84c81b34..b409f6b2bfd8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -425,6 +425,59 @@ static void set_dp_phy_pattern_hbr2_compliance_cp2520_2(
 	enable_phy_bypass_mode(enc110, false);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_set_dp_phy_pattern_hbr2_compliance_cp2520_2(
+	struct dce110_link_encoder *enc110,
+	unsigned int cp2520_pattern)
+{
+
+	/* previously there is a register DP_HBR2_EYE_PATTERN
+	 * that is enabled to get the pattern.
+	 * But it does not work with the latest spec change,
+	 * so we are programming the following registers manually.
+	 *
+	 * The following settings have been confirmed
+	 * by Nick Chorney and Sandra Liu */
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+
+	enable_phy_bypass_mode(enc110, false);
+
+	/* Setup DIG encoder in DP SST mode */
+	enc110->base.funcs->setup(&enc110->base, SIGNAL_TYPE_DISPLAY_PORT);
+
+	/* ensure normal panel mode. */
+	setup_panel_mode(enc110, DP_PANEL_MODE_DEFAULT);
+
+	/* no vbid after BS (SR)
+	 * DP_LINK_FRAMING_CNTL changed history Sandra Liu
+	 * 11000260 / 11000104 / 110000FC */
+	REG_UPDATE_3(DP_LINK_FRAMING_CNTL,
+			DP_IDLE_BS_INTERVAL, 0xFC,
+			DP_VBID_DISABLE, 1,
+			DP_VID_ENHANCED_FRAME_MODE, 1);
+
+	/* DCE6 has no DP_DPHY_SCRAM_CNTL register, skip swap BS with SR */
+
+	/* select cp2520 patterns */
+	if (REG(DP_DPHY_HBR2_PATTERN_CONTROL))
+		REG_UPDATE(DP_DPHY_HBR2_PATTERN_CONTROL,
+				DP_DPHY_HBR2_PATTERN_CONTROL, cp2520_pattern);
+	else
+		/* pre-DCE11 can only generate CP2520 pattern 2 */
+		ASSERT(cp2520_pattern == 2);
+
+	/* set link training complete */
+	set_link_training_complete(enc110, true);
+
+	/* disable video stream */
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0);
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc110, false);
+}
+#endif
+
 static void set_dp_phy_pattern_passthrough_mode(
 	struct dce110_link_encoder *enc110,
 	enum dp_panel_mode panel_mode)
@@ -452,6 +505,35 @@ static void set_dp_phy_pattern_passthrough_mode(
 	disable_prbs_mode(enc110);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_set_dp_phy_pattern_passthrough_mode(
+	struct dce110_link_encoder *enc110,
+	enum dp_panel_mode panel_mode)
+{
+	/* program correct panel mode */
+	setup_panel_mode(enc110, panel_mode);
+
+	/* restore LINK_FRAMING_CNTL
+	 * in case we were doing HBR2 compliance pattern before
+	 */
+	REG_UPDATE_3(DP_LINK_FRAMING_CNTL,
+			DP_IDLE_BS_INTERVAL, 0x2000,
+			DP_VBID_DISABLE, 0,
+			DP_VID_ENHANCED_FRAME_MODE, 1);
+
+	/* DCE6 has no DP_DPHY_SCRAM_CNTL register, skip DPHY_SCRAMBLER_BS_COUNT restore */
+
+	/* set link training complete */
+	set_link_training_complete(enc110, true);
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc110, false);
+
+	/* Disable PRBS mode */
+	disable_prbs_mode(enc110);
+}
+#endif
+
 /* return value is bit-vector */
 static uint8_t get_frontend_source(
 	enum engine_id engine)
@@ -490,6 +572,20 @@ static void configure_encoder(
 	REG_UPDATE(DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_ADVANCE, 1);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_configure_encoder(
+	struct dce110_link_encoder *enc110,
+	const struct dc_link_settings *link_settings)
+{
+	/* set number of lanes */
+
+	REG_SET(DP_CONFIG, 0,
+			DP_UDI_LANES, link_settings->lane_count - LANE_COUNT_ONE);
+
+	/* DCE6 has no DP_DPHY_SCRAM_CNTL register, skip setup scrambler */
+}
+#endif
+
 static void aux_initialize(
 	struct dce110_link_encoder *enc110)
 {
@@ -1059,6 +1155,87 @@ void dce110_link_encoder_enable_dp_mst_output(
 		BREAK_TO_DEBUGGER();
 	}
 }
+
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/* enables DP PHY output */
+void dce60_link_encoder_enable_dp_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	/* Enable the PHY */
+
+	/* number_of_lanes is used for pixel clock adjust,
+	 * but it's not passed to asic_control.
+	 * We need to set number of lanes manually.
+	 */
+	dce60_configure_encoder(enc110, link_settings);
+	cntl.connector_obj_id = enc110->base.connector;
+	cntl.action = TRANSMITTER_CONTROL_ENABLE;
+	cntl.engine_id = enc->preferred_engine;
+	cntl.transmitter = enc110->base.transmitter;
+	cntl.pll_id = clock_source;
+	cntl.signal = SIGNAL_TYPE_DISPLAY_PORT;
+	cntl.lanes_number = link_settings->lane_count;
+	cntl.hpd_sel = enc110->base.hpd_source;
+	cntl.pixel_clock = link_settings->link_rate
+						* LINK_RATE_REF_FREQ_IN_KHZ;
+	/* TODO: check if undefined works */
+	cntl.color_depth = COLOR_DEPTH_UNDEFINED;
+
+	result = link_transmitter_control(enc110, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+	}
+}
+
+/* enables DP PHY output in MST mode */
+void dce60_link_encoder_enable_dp_mst_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	/* Enable the PHY */
+
+	/* number_of_lanes is used for pixel clock adjust,
+	 * but it's not passed to asic_control.
+	 * We need to set number of lanes manually.
+	 */
+	dce60_configure_encoder(enc110, link_settings);
+
+	cntl.action = TRANSMITTER_CONTROL_ENABLE;
+	cntl.engine_id = ENGINE_ID_UNKNOWN;
+	cntl.transmitter = enc110->base.transmitter;
+	cntl.pll_id = clock_source;
+	cntl.signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
+	cntl.lanes_number = link_settings->lane_count;
+	cntl.hpd_sel = enc110->base.hpd_source;
+	cntl.pixel_clock = link_settings->link_rate
+						* LINK_RATE_REF_FREQ_IN_KHZ;
+	/* TODO: check if undefined works */
+	cntl.color_depth = COLOR_DEPTH_UNDEFINED;
+
+	result = link_transmitter_control(enc110, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+	}
+}
+#endif
+
 /*
  * @brief
  * Disable transmitter and its encoder
@@ -1208,6 +1385,63 @@ void dce110_link_encoder_dp_set_phy_pattern(
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/* set DP PHY test and training patterns */
+void dce60_link_encoder_dp_set_phy_pattern(
+	struct link_encoder *enc,
+	const struct encoder_set_dp_phy_pattern_param *param)
+{
+	struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc);
+
+	switch (param->dp_phy_pattern) {
+	case DP_TEST_PATTERN_TRAINING_PATTERN1:
+		dce110_link_encoder_set_dp_phy_pattern_training_pattern(enc, 0);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN2:
+		dce110_link_encoder_set_dp_phy_pattern_training_pattern(enc, 1);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN3:
+		dce110_link_encoder_set_dp_phy_pattern_training_pattern(enc, 2);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN4:
+		dce110_link_encoder_set_dp_phy_pattern_training_pattern(enc, 3);
+		break;
+	case DP_TEST_PATTERN_D102:
+		set_dp_phy_pattern_d102(enc110);
+		break;
+	case DP_TEST_PATTERN_SYMBOL_ERROR:
+		set_dp_phy_pattern_symbol_error(enc110);
+		break;
+	case DP_TEST_PATTERN_PRBS7:
+		set_dp_phy_pattern_prbs7(enc110);
+		break;
+	case DP_TEST_PATTERN_80BIT_CUSTOM:
+		set_dp_phy_pattern_80bit_custom(
+			enc110, param->custom_pattern);
+		break;
+	case DP_TEST_PATTERN_CP2520_1:
+		dce60_set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc110, 1);
+		break;
+	case DP_TEST_PATTERN_CP2520_2:
+		dce60_set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc110, 2);
+		break;
+	case DP_TEST_PATTERN_CP2520_3:
+		dce60_set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc110, 3);
+		break;
+	case DP_TEST_PATTERN_VIDEO_MODE: {
+		dce60_set_dp_phy_pattern_passthrough_mode(
+			enc110, param->dp_panel_mode);
+		break;
+	}
+
+	default:
+		/* invalid phy pattern */
+		ASSERT_CRITICAL(false);
+		break;
+	}
+}
+#endif
+
 static void fill_stream_allocation_row_info(
 	const struct link_mst_stream_allocation *stream_allocation,
 	uint32_t *src,
@@ -1407,3 +1641,138 @@ void dce110_link_encoder_get_max_link_cap(struct link_encoder *enc,
 
 	*link_settings = max_link_cap;
 }
+
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct link_encoder_funcs dce60_lnk_enc_funcs = {
+	.validate_output_with_stream =
+		dce110_link_encoder_validate_output_with_stream,
+	.hw_init = dce110_link_encoder_hw_init,
+	.setup = dce110_link_encoder_setup,
+	.enable_tmds_output = dce110_link_encoder_enable_tmds_output,
+	.enable_dp_output = dce60_link_encoder_enable_dp_output,
+	.enable_dp_mst_output = dce60_link_encoder_enable_dp_mst_output,
+	.enable_lvds_output = dce110_link_encoder_enable_lvds_output,
+	.disable_output = dce110_link_encoder_disable_output,
+	.dp_set_lane_settings = dce110_link_encoder_dp_set_lane_settings,
+	.dp_set_phy_pattern = dce60_link_encoder_dp_set_phy_pattern,
+	.update_mst_stream_allocation_table =
+		dce110_link_encoder_update_mst_stream_allocation_table,
+	.psr_program_dp_dphy_fast_training =
+			dce110_psr_program_dp_dphy_fast_training,
+	.psr_program_secondary_packet = dce110_psr_program_secondary_packet,
+	.connect_dig_be_to_fe = dce110_link_encoder_connect_dig_be_to_fe,
+	.enable_hpd = dce110_link_encoder_enable_hpd,
+	.disable_hpd = dce110_link_encoder_disable_hpd,
+	.is_dig_enabled = dce110_is_dig_enabled,
+	.destroy = dce110_link_encoder_destroy,
+	.get_max_link_cap = dce110_link_encoder_get_max_link_cap
+};
+
+void dce60_link_encoder_construct(
+	struct dce110_link_encoder *enc110,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dce110_link_enc_registers *link_regs,
+	const struct dce110_link_enc_aux_registers *aux_regs,
+	const struct dce110_link_enc_hpd_registers *hpd_regs)
+{
+	struct bp_encoder_cap_info bp_cap_info = {0};
+	const struct dc_vbios_funcs *bp_funcs = init_data->ctx->dc_bios->funcs;
+	enum bp_result result = BP_RESULT_OK;
+
+	enc110->base.funcs = &dce60_lnk_enc_funcs;
+	enc110->base.ctx = init_data->ctx;
+	enc110->base.id = init_data->encoder;
+
+	enc110->base.hpd_source = init_data->hpd_source;
+	enc110->base.connector = init_data->connector;
+
+	enc110->base.preferred_engine = ENGINE_ID_UNKNOWN;
+
+	enc110->base.features = *enc_features;
+
+	enc110->base.transmitter = init_data->transmitter;
+
+	/* set the flag to indicate whether driver poll the I2C data pin
+	 * while doing the DP sink detect
+	 */
+
+/*	if (dal_adapter_service_is_feature_supported(as,
+		FEATURE_DP_SINK_DETECT_POLL_DATA_PIN))
+		enc110->base.features.flags.bits.
+			DP_SINK_DETECT_POLL_DATA_PIN = true;*/
+
+	enc110->base.output_signals =
+		SIGNAL_TYPE_DVI_SINGLE_LINK |
+		SIGNAL_TYPE_DVI_DUAL_LINK |
+		SIGNAL_TYPE_LVDS |
+		SIGNAL_TYPE_DISPLAY_PORT |
+		SIGNAL_TYPE_DISPLAY_PORT_MST |
+		SIGNAL_TYPE_EDP |
+		SIGNAL_TYPE_HDMI_TYPE_A;
+
+	/* For DCE 8.0 and 8.1, by design, UNIPHY is hardwired to DIG_BE.
+	 * SW always assign DIG_FE 1:1 mapped to DIG_FE for non-MST UNIPHY.
+	 * SW assign DIG_FE to non-MST UNIPHY first and MST last. So prefer
+	 * DIG is per UNIPHY and used by SST DP, eDP, HDMI, DVI and LVDS.
+	 * Prefer DIG assignment is decided by board design.
+	 * For DCE 8.0, there are only max 6 UNIPHYs, we assume board design
+	 * and VBIOS will filter out 7 UNIPHY for DCE 8.0.
+	 * By this, adding DIGG should not hurt DCE 8.0.
+	 * This will let DCE 8.1 share DCE 8.0 as much as possible
+	 */
+
+	enc110->link_regs = link_regs;
+	enc110->aux_regs = aux_regs;
+	enc110->hpd_regs = hpd_regs;
+
+	switch (enc110->base.transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		enc110->base.preferred_engine = ENGINE_ID_DIGA;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		enc110->base.preferred_engine = ENGINE_ID_DIGB;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		enc110->base.preferred_engine = ENGINE_ID_DIGC;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		enc110->base.preferred_engine = ENGINE_ID_DIGD;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		enc110->base.preferred_engine = ENGINE_ID_DIGE;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		enc110->base.preferred_engine = ENGINE_ID_DIGF;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		enc110->base.preferred_engine = ENGINE_ID_DIGG;
+	break;
+	default:
+		ASSERT_CRITICAL(false);
+		enc110->base.preferred_engine = ENGINE_ID_UNKNOWN;
+	}
+
+	/* default to one to mirror Windows behavior */
+	enc110->base.features.flags.bits.HDMI_6GB_EN = 1;
+
+	result = bp_funcs->get_encoder_cap_info(enc110->base.ctx->dc_bios,
+						enc110->base.id, &bp_cap_info);
+
+	/* Override features with DCE-specific values */
+	if (BP_RESULT_OK == result) {
+		enc110->base.features.flags.bits.IS_HBR2_CAPABLE =
+				bp_cap_info.DP_HBR2_EN;
+		enc110->base.features.flags.bits.IS_HBR3_CAPABLE =
+				bp_cap_info.DP_HBR3_EN;
+		enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
+	} else {
+		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
+				__func__,
+				result);
+	}
+	if (enc110->base.ctx->dc->debug.hdmi20_disable) {
+		enc110->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
+}
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
index 66027d496778..cb714a48b171 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
@@ -76,6 +76,34 @@
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
 	SR(DCI_MEM_PWR_STATUS)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define LE_DCE60_REG_LIST(id)\
+	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
+	SR(DMCU_RAM_ACCESS_CTRL), \
+	SR(DMCU_IRAM_RD_CTRL), \
+	SR(DMCU_IRAM_RD_DATA), \
+	SR(DMCU_INTERRUPT_TO_UC_EN_MASK), \
+	SRI(DIG_BE_CNTL, DIG, id), \
+	SRI(DIG_BE_EN_CNTL, DIG, id), \
+	SRI(DP_CONFIG, DP, id), \
+	SRI(DP_DPHY_CNTL, DP, id), \
+	SRI(DP_DPHY_PRBS_CNTL, DP, id), \
+	SRI(DP_DPHY_SYM0, DP, id), \
+	SRI(DP_DPHY_SYM1, DP, id), \
+	SRI(DP_DPHY_SYM2, DP, id), \
+	SRI(DP_DPHY_TRAINING_PATTERN_SEL, DP, id), \
+	SRI(DP_LINK_CNTL, DP, id), \
+	SRI(DP_LINK_FRAMING_CNTL, DP, id), \
+	SRI(DP_MSE_SAT0, DP, id), \
+	SRI(DP_MSE_SAT1, DP, id), \
+	SRI(DP_MSE_SAT2, DP, id), \
+	SRI(DP_MSE_SAT_UPDATE, DP, id), \
+	SRI(DP_SEC_CNTL, DP, id), \
+	SRI(DP_VID_STREAM_CNTL, DP, id), \
+	SRI(DP_DPHY_FAST_TRAINING, DP, id), \
+	SRI(DP_SEC_CNTL1, DP, id)
+#endif
+
 #define LE_DCE80_REG_LIST(id)\
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
 	LE_COMMON_REG_LIST_BASE(id)
@@ -171,6 +199,16 @@ void dce110_link_encoder_construct(
 	const struct dce110_link_enc_aux_registers *aux_regs,
 	const struct dce110_link_enc_hpd_registers *hpd_regs);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_link_encoder_construct(
+	struct dce110_link_encoder *enc110,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dce110_link_enc_registers *link_regs,
+	const struct dce110_link_enc_aux_registers *aux_regs,
+	const struct dce110_link_enc_hpd_registers *hpd_regs);
+#endif
+
 bool dce110_link_encoder_validate_dvi_output(
 	const struct dce110_link_encoder *enc110,
 	enum signal_type connector_signal,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index 51481e922eb9..79a6f261a0da 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -174,6 +174,22 @@ static void program_urgency_watermark(
 		URGENCY_HIGH_WATERMARK, urgency_high_wm);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_program_urgency_watermark(
+	struct dce_mem_input *dce_mi,
+	uint32_t wm_select,
+	uint32_t urgency_low_wm,
+	uint32_t urgency_high_wm)
+{
+	REG_UPDATE(DPG_PIPE_ARBITRATION_CONTROL3,
+		URGENCY_WATERMARK_MASK, wm_select);
+
+	REG_SET_2(DPG_PIPE_URGENCY_CONTROL, 0,
+		URGENCY_LOW_WATERMARK, urgency_low_wm,
+		URGENCY_HIGH_WATERMARK, urgency_high_wm);
+}
+#endif
+
 static void dce120_program_urgency_watermark(
 	struct dce_mem_input *dce_mi,
 	uint32_t wm_select,
@@ -193,6 +209,25 @@ static void dce120_program_urgency_watermark(
 
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_program_nbp_watermark(
+	struct dce_mem_input *dce_mi,
+	uint32_t wm_select,
+	uint32_t nbp_wm)
+{
+	REG_UPDATE(DPG_PIPE_NB_PSTATE_CHANGE_CONTROL,
+		NB_PSTATE_CHANGE_WATERMARK_MASK, wm_select);
+
+	REG_UPDATE_3(DPG_PIPE_NB_PSTATE_CHANGE_CONTROL,
+		NB_PSTATE_CHANGE_ENABLE, 1,
+		NB_PSTATE_CHANGE_URGENT_DURING_REQUEST, 1,
+		NB_PSTATE_CHANGE_NOT_SELF_REFRESH_DURING_REQUEST, 1);
+
+	REG_UPDATE(DPG_PIPE_NB_PSTATE_CHANGE_CONTROL,
+		NB_PSTATE_CHANGE_WATERMARK, nbp_wm);
+}
+#endif
+
 static void program_nbp_watermark(
 	struct dce_mem_input *dce_mi,
 	uint32_t wm_select,
@@ -225,6 +260,20 @@ static void program_nbp_watermark(
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_program_stutter_watermark(
+	struct dce_mem_input *dce_mi,
+	uint32_t wm_select,
+	uint32_t stutter_mark)
+{
+	REG_UPDATE(DPG_PIPE_STUTTER_CONTROL,
+		STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK, wm_select);
+
+	REG_UPDATE(DPG_PIPE_STUTTER_CONTROL,
+		STUTTER_EXIT_SELF_REFRESH_WATERMARK, stutter_mark);
+}
+#endif
+
 static void dce120_program_stutter_watermark(
 	struct dce_mem_input *dce_mi,
 	uint32_t wm_select,
@@ -286,6 +335,34 @@ static void dce_mi_program_display_marks(
 	program_stutter_watermark(dce_mi, 1, stutter_exit.d_mark); /* set d */
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_mi_program_display_marks(
+	struct mem_input *mi,
+	struct dce_watermarks nbp,
+	struct dce_watermarks stutter_exit,
+	struct dce_watermarks stutter_enter,
+	struct dce_watermarks urgent,
+	uint32_t total_dest_line_time_ns)
+{
+	struct dce_mem_input *dce_mi = TO_DCE_MEM_INPUT(mi);
+	uint32_t stutter_en = mi->ctx->dc->debug.disable_stutter ? 0 : 1;
+
+	dce60_program_urgency_watermark(dce_mi, 2, /* set a */
+			urgent.a_mark, total_dest_line_time_ns);
+	dce60_program_urgency_watermark(dce_mi, 1, /* set d */
+			urgent.d_mark, total_dest_line_time_ns);
+
+	REG_UPDATE_2(DPG_PIPE_STUTTER_CONTROL,
+		STUTTER_ENABLE, stutter_en,
+		STUTTER_IGNORE_FBC, 1);
+	dce60_program_nbp_watermark(dce_mi, 2, nbp.a_mark); /* set a */
+	dce60_program_nbp_watermark(dce_mi, 1, nbp.d_mark); /* set d */
+
+	dce60_program_stutter_watermark(dce_mi, 2, stutter_exit.a_mark); /* set a */
+	dce60_program_stutter_watermark(dce_mi, 1, stutter_exit.d_mark); /* set d */
+}
+#endif
+
 static void dce112_mi_program_display_marks(struct mem_input *mi,
 	struct dce_watermarks nbp,
 	struct dce_watermarks stutter_exit,
@@ -369,7 +446,7 @@ static void program_tiling(
 		 */
 	}
 
-	if (dce_mi->masks->GRPH_ARRAY_MODE) { /* GFX8 */
+	if (dce_mi->masks->GRPH_MICRO_TILE_MODE) { /* GFX8 */
 		REG_UPDATE_9(GRPH_CONTROL,
 				GRPH_NUM_BANKS, info->gfx8.num_banks,
 				GRPH_BANK_WIDTH, info->gfx8.bank_width,
@@ -385,6 +462,23 @@ static void program_tiling(
 				GRPH_Z, 0);
 				*/
 	}
+
+	if (dce_mi->masks->GRPH_ARRAY_MODE) { /* GFX6 but reuses gfx8 struct */
+		REG_UPDATE_8(GRPH_CONTROL,
+				GRPH_NUM_BANKS, info->gfx8.num_banks,
+				GRPH_BANK_WIDTH, info->gfx8.bank_width,
+				GRPH_BANK_HEIGHT, info->gfx8.bank_height,
+				GRPH_MACRO_TILE_ASPECT, info->gfx8.tile_aspect,
+				GRPH_TILE_SPLIT, info->gfx8.tile_split,
+				/* DCE6 has no GRPH_MICRO_TILE_MODE mask */
+				GRPH_PIPE_CONFIG, info->gfx8.pipe_config,
+				GRPH_ARRAY_MODE, info->gfx8.array_mode,
+				GRPH_COLOR_EXPANSION_MODE, 1);
+		/* 01 - DCP_GRPH_COLOR_EXPANSION_MODE_ZEXP: zero expansion for YCbCr */
+		/*
+				GRPH_Z, 0);
+				*/
+	}
 }
 
 
@@ -429,6 +523,36 @@ static void program_size_and_rotation(
 			GRPH_ROTATION_ANGLE, rotation_angles[rotation]);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_program_size(
+	struct dce_mem_input *dce_mi,
+	enum dc_rotation_angle rotation, /* not used in DCE6 */
+	const struct plane_size *plane_size)
+{
+	struct rect hw_rect = plane_size->surface_size;
+	/* DCE6 has no HW rotation, skip rotation_angles declaration */
+
+	/* DCE6 has no HW rotation, skip ROTATION_ANGLE_* processing */
+
+	REG_SET(GRPH_X_START, 0,
+			GRPH_X_START, hw_rect.x);
+
+	REG_SET(GRPH_Y_START, 0,
+			GRPH_Y_START, hw_rect.y);
+
+	REG_SET(GRPH_X_END, 0,
+			GRPH_X_END, hw_rect.width);
+
+	REG_SET(GRPH_Y_END, 0,
+			GRPH_Y_END, hw_rect.height);
+
+	REG_SET(GRPH_PITCH, 0,
+			GRPH_PITCH, plane_size->surface_pitch);
+
+	/* DCE6 has no HW_ROTATION register, skip setting rotation_angles */
+}
+#endif
+
 static void program_grph_pixel_format(
 	struct dce_mem_input *dce_mi,
 	enum surface_pixel_format format)
@@ -521,6 +645,28 @@ static void dce_mi_program_surface_config(
 		program_grph_pixel_format(dce_mi, format);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_mi_program_surface_config(
+	struct mem_input *mi,
+	enum surface_pixel_format format,
+	union dc_tiling_info *tiling_info,
+	struct plane_size *plane_size,
+	enum dc_rotation_angle rotation, /* not used in DCE6 */
+	struct dc_plane_dcc_param *dcc,
+	bool horizontal_mirror)
+{
+	struct dce_mem_input *dce_mi = TO_DCE_MEM_INPUT(mi);
+	REG_UPDATE(GRPH_ENABLE, GRPH_ENABLE, 1);
+
+	program_tiling(dce_mi, tiling_info);
+	dce60_program_size(dce_mi, rotation, plane_size);
+
+	if (format >= SURFACE_PIXEL_FORMAT_GRPH_BEGIN &&
+		format < SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
+		program_grph_pixel_format(dce_mi, format);
+}
+#endif
+
 static uint32_t get_dmif_switch_time_us(
 	uint32_t h_total,
 	uint32_t v_total,
@@ -741,6 +887,20 @@ static const struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct mem_input_funcs dce60_mi_funcs = {
+	.mem_input_program_display_marks = dce60_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce60_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
+#endif
+
 static const struct mem_input_funcs dce112_mi_funcs = {
 	.mem_input_program_display_marks = dce112_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
@@ -783,6 +943,20 @@ void dce_mem_input_construct(
 	dce_mi->masks = mi_mask;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_mem_input_construct(
+	struct dce_mem_input *dce_mi,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_mem_input_registers *regs,
+	const struct dce_mem_input_shift *mi_shift,
+	const struct dce_mem_input_mask *mi_mask)
+{
+	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
+	dce_mi->base.funcs = &dce60_mi_funcs;
+}
+#endif
+
 void dce112_mem_input_construct(
 	struct dce_mem_input *dce_mi,
 	struct dc_context *ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
index d15b0d7f47fc..23db5c72f07e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
@@ -58,6 +58,31 @@
 	SRI(DVMM_PTE_CONTROL, DCP, id),\
 	SRI(DVMM_PTE_ARB_CONTROL, DCP, id)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define MI_DCE6_REG_LIST(id)\
+	SRI(GRPH_ENABLE, DCP, id),\
+	SRI(GRPH_CONTROL, DCP, id),\
+	SRI(GRPH_X_START, DCP, id),\
+	SRI(GRPH_Y_START, DCP, id),\
+	SRI(GRPH_X_END, DCP, id),\
+	SRI(GRPH_Y_END, DCP, id),\
+	SRI(GRPH_PITCH, DCP, id),\
+	SRI(GRPH_SWAP_CNTL, DCP, id),\
+	SRI(PRESCALE_GRPH_CONTROL, DCP, id),\
+	SRI(GRPH_UPDATE, DCP, id),\
+	SRI(GRPH_FLIP_CONTROL, DCP, id),\
+	SRI(GRPH_PRIMARY_SURFACE_ADDRESS, DCP, id),\
+	SRI(GRPH_PRIMARY_SURFACE_ADDRESS_HIGH, DCP, id),\
+	SRI(GRPH_SECONDARY_SURFACE_ADDRESS, DCP, id),\
+	SRI(GRPH_SECONDARY_SURFACE_ADDRESS_HIGH, DCP, id),\
+	SRI(DPG_PIPE_ARBITRATION_CONTROL1, DMIF_PG, id),\
+	SRI(DPG_PIPE_ARBITRATION_CONTROL3, DMIF_PG, id),\
+	SRI(DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, DMIF_PG, id),\
+	SRI(DPG_PIPE_URGENCY_CONTROL, DMIF_PG, id),\
+	SRI(DPG_PIPE_STUTTER_CONTROL, DMIF_PG, id),\
+	SRI(DMIF_BUFFER_CONTROL, PIPE, id)
+#endif
+
 #define MI_DCE8_REG_LIST(id)\
 	MI_DCE_BASE_REG_LIST(id),\
 	SRI(DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, DMIF_PG, id)
@@ -104,6 +129,9 @@ struct dce_mem_input_registers {
 	uint32_t GRPH_SECONDARY_SURFACE_ADDRESS_HIGH;
 	/* DMIF_PG */
 	uint32_t DPG_PIPE_ARBITRATION_CONTROL1;
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t DPG_PIPE_ARBITRATION_CONTROL3;
+#endif
 	uint32_t DPG_WATERMARK_MASK_CONTROL;
 	uint32_t DPG_PIPE_URGENCY_CONTROL;
 	uint32_t DPG_PIPE_URGENT_LEVEL_CONTROL;
@@ -126,6 +154,18 @@ struct dce_mem_input_registers {
 #define SFB(blk_name, reg_name, field_name, post_fix)\
 	.field_name = blk_name ## reg_name ## __ ## field_name ## post_fix
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define MI_GFX6_TILE_MASK_SH_LIST(mask_sh, blk)\
+	SFB(blk, GRPH_CONTROL, GRPH_NUM_BANKS, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_BANK_WIDTH, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_BANK_HEIGHT, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_MACRO_TILE_ASPECT, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_TILE_SPLIT, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_PIPE_CONFIG, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_ARRAY_MODE, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_COLOR_EXPANSION_MODE, mask_sh)
+#endif
+
 #define MI_GFX8_TILE_MASK_SH_LIST(mask_sh, blk)\
 	SFB(blk, GRPH_CONTROL, GRPH_NUM_BANKS, mask_sh),\
 	SFB(blk, GRPH_CONTROL, GRPH_BANK_WIDTH, mask_sh),\
@@ -162,6 +202,32 @@ struct dce_mem_input_registers {
 	SFB(blk, GRPH_UPDATE, GRPH_UPDATE_LOCK, mask_sh),\
 	SFB(blk, GRPH_FLIP_CONTROL, GRPH_SURFACE_UPDATE_H_RETRACE_EN, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define MI_DCP_MASK_SH_LIST_DCE6(mask_sh, blk)\
+	SFB(blk, GRPH_ENABLE, GRPH_ENABLE, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_DEPTH, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_FORMAT, mask_sh),\
+	SFB(blk, GRPH_CONTROL, GRPH_NUM_BANKS, mask_sh),\
+	SFB(blk, GRPH_X_START, GRPH_X_START, mask_sh),\
+	SFB(blk, GRPH_Y_START, GRPH_Y_START, mask_sh),\
+	SFB(blk, GRPH_X_END, GRPH_X_END, mask_sh),\
+	SFB(blk, GRPH_Y_END, GRPH_Y_END, mask_sh),\
+	SFB(blk, GRPH_PITCH, GRPH_PITCH, mask_sh),\
+	SFB(blk, GRPH_SWAP_CNTL, GRPH_RED_CROSSBAR, mask_sh),\
+	SFB(blk, GRPH_SWAP_CNTL, GRPH_BLUE_CROSSBAR, mask_sh),\
+	SFB(blk, PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_SELECT, mask_sh),\
+	SFB(blk, PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_R_SIGN, mask_sh),\
+	SFB(blk, PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_G_SIGN, mask_sh),\
+	SFB(blk, PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_B_SIGN, mask_sh),\
+	SFB(blk, GRPH_SECONDARY_SURFACE_ADDRESS_HIGH, GRPH_SECONDARY_SURFACE_ADDRESS_HIGH, mask_sh),\
+	SFB(blk, GRPH_SECONDARY_SURFACE_ADDRESS, GRPH_SECONDARY_SURFACE_ADDRESS, mask_sh),\
+	SFB(blk, GRPH_PRIMARY_SURFACE_ADDRESS_HIGH, GRPH_PRIMARY_SURFACE_ADDRESS_HIGH, mask_sh),\
+	SFB(blk, GRPH_PRIMARY_SURFACE_ADDRESS, GRPH_PRIMARY_SURFACE_ADDRESS, mask_sh),\
+	SFB(blk, GRPH_UPDATE, GRPH_SURFACE_UPDATE_PENDING, mask_sh),\
+	SFB(blk, GRPH_UPDATE, GRPH_UPDATE_LOCK, mask_sh),\
+	SFB(blk, GRPH_FLIP_CONTROL, GRPH_SURFACE_UPDATE_H_RETRACE_EN, mask_sh)
+#endif
+
 #define MI_DCP_DCE11_MASK_SH_LIST(mask_sh, blk)\
 	SFB(blk, GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, mask_sh)
 
@@ -172,6 +238,33 @@ struct dce_mem_input_registers {
 	SFB(blk, DVMM_PTE_ARB_CONTROL, DVMM_PTE_REQ_PER_CHUNK, mask_sh),\
 	SFB(blk, DVMM_PTE_ARB_CONTROL, DVMM_MAX_PTE_REQ_OUTSTANDING, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define MI_DMIF_PG_MASK_SH_LIST_DCE6(mask_sh, blk)\
+	SFB(blk, DPG_PIPE_ARBITRATION_CONTROL1, PIXEL_DURATION, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENCY_CONTROL, URGENCY_LOW_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENCY_CONTROL, URGENCY_HIGH_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_STUTTER_CONTROL, STUTTER_ENABLE, mask_sh),\
+	SFB(blk, DPG_PIPE_STUTTER_CONTROL, STUTTER_IGNORE_FBC, mask_sh),\
+	SF(PIPE0_DMIF_BUFFER_CONTROL, DMIF_BUFFERS_ALLOCATED, mask_sh),\
+	SF(PIPE0_DMIF_BUFFER_CONTROL, DMIF_BUFFERS_ALLOCATION_COMPLETED, mask_sh)
+
+#define MI_DMIF_PG_MASK_SH_DCE6(mask_sh, blk)\
+	SFB(blk, DPG_PIPE_ARBITRATION_CONTROL3, URGENCY_WATERMARK_MASK, mask_sh),\
+	SFB(blk, DPG_PIPE_STUTTER_CONTROL, STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK, mask_sh),\
+	SFB(blk, DPG_PIPE_STUTTER_CONTROL, STUTTER_EXIT_SELF_REFRESH_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, NB_PSTATE_CHANGE_WATERMARK_MASK, mask_sh),\
+	SFB(blk, DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, NB_PSTATE_CHANGE_ENABLE, mask_sh),\
+	SFB(blk, DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, NB_PSTATE_CHANGE_URGENT_DURING_REQUEST, mask_sh),\
+	SFB(blk, DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, NB_PSTATE_CHANGE_NOT_SELF_REFRESH_DURING_REQUEST, mask_sh),\
+	SFB(blk, DPG_PIPE_NB_PSTATE_CHANGE_CONTROL, NB_PSTATE_CHANGE_WATERMARK, mask_sh)
+
+#define MI_DCE6_MASK_SH_LIST(mask_sh)\
+	MI_DCP_MASK_SH_LIST_DCE6(mask_sh, ),\
+	MI_DMIF_PG_MASK_SH_LIST_DCE6(mask_sh, ),\
+	MI_DMIF_PG_MASK_SH_DCE6(mask_sh, ),\
+	MI_GFX6_TILE_MASK_SH_LIST(mask_sh, )
+#endif
+
 #define MI_DMIF_PG_MASK_SH_LIST(mask_sh, blk)\
 	SFB(blk, DPG_PIPE_ARBITRATION_CONTROL1, PIXEL_DURATION, mask_sh),\
 	SFB(blk, DPG_WATERMARK_MASK_CONTROL, URGENCY_WATERMARK_MASK, mask_sh),\
@@ -345,6 +438,16 @@ void dce_mem_input_construct(
 	const struct dce_mem_input_shift *mi_shift,
 	const struct dce_mem_input_mask *mi_mask);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_mem_input_construct(
+	struct dce_mem_input *dce_mi,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_mem_input_registers *regs,
+	const struct dce_mem_input_shift *mi_shift,
+	const struct dce_mem_input_mask *mi_mask);
+#endif
+
 void dce112_mem_input_construct(
 	struct dce_mem_input *dce_mi,
 	struct dc_context *ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c
index 51081d9ae3fb..e459ae65aaf7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c
@@ -141,6 +141,47 @@ static void set_truncation(
 				params->flags.TRUNCATE_MODE);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/**
+ *	dce60_set_truncation
+ *	1) set truncation depth: 0 for 18 bpp or 1 for 24 bpp
+ *	2) enable truncation
+ *	3) HW remove 12bit FMT support for DCE11 power saving reason.
+ */
+static void dce60_set_truncation(
+		struct dce110_opp *opp110,
+		const struct bit_depth_reduction_params *params)
+{
+	/* DCE6 has no FMT_TRUNCATE_MODE bit in FMT_BIT_DEPTH_CONTROL reg */
+
+	/*Disable truncation*/
+	REG_UPDATE_2(FMT_BIT_DEPTH_CONTROL,
+			FMT_TRUNCATE_EN, 0,
+			FMT_TRUNCATE_DEPTH, 0);
+
+	if (params->pixel_encoding == PIXEL_ENCODING_YCBCR422) {
+		/*  8bpc trunc on YCbCr422*/
+		if (params->flags.TRUNCATE_DEPTH == 1)
+			REG_UPDATE_2(FMT_BIT_DEPTH_CONTROL,
+					FMT_TRUNCATE_EN, 1,
+					FMT_TRUNCATE_DEPTH, 1);
+		else if (params->flags.TRUNCATE_DEPTH == 2)
+			/*  10bpc trunc on YCbCr422*/
+			REG_UPDATE_2(FMT_BIT_DEPTH_CONTROL,
+					FMT_TRUNCATE_EN, 1,
+					FMT_TRUNCATE_DEPTH, 2);
+		return;
+	}
+	/* on other format-to do */
+	if (params->flags.TRUNCATE_ENABLED == 0)
+		return;
+	/*Set truncation depth and Enable truncation*/
+	REG_UPDATE_2(FMT_BIT_DEPTH_CONTROL,
+				FMT_TRUNCATE_EN, 1,
+				FMT_TRUNCATE_DEPTH,
+				params->flags.TRUNCATE_DEPTH);
+}
+#endif
 
 /**
  *	set_spatial_dither
@@ -373,6 +414,57 @@ void dce110_opp_set_clamping(
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/**
+ *	Set Clamping for DCE6 parts
+ *	1) Set clamping format based on bpc - 0 for 6bpc (No clamping)
+ *		1 for 8 bpc
+ *		2 for 10 bpc
+ *		3 for 12 bpc
+ *		7 for programable
+ *	2) Enable clamp if Limited range requested
+ */
+void dce60_opp_set_clamping(
+	struct dce110_opp *opp110,
+	const struct clamping_and_pixel_encoding_params *params)
+{
+	REG_SET_2(FMT_CLAMP_CNTL, 0,
+		FMT_CLAMP_DATA_EN, 0,
+		FMT_CLAMP_COLOR_FORMAT, 0);
+
+	switch (params->clamping_level) {
+	case CLAMPING_FULL_RANGE:
+		break;
+	case CLAMPING_LIMITED_RANGE_8BPC:
+		REG_SET_2(FMT_CLAMP_CNTL, 0,
+			FMT_CLAMP_DATA_EN, 1,
+			FMT_CLAMP_COLOR_FORMAT, 1);
+		break;
+	case CLAMPING_LIMITED_RANGE_10BPC:
+		REG_SET_2(FMT_CLAMP_CNTL, 0,
+			FMT_CLAMP_DATA_EN, 1,
+			FMT_CLAMP_COLOR_FORMAT, 2);
+		break;
+	case CLAMPING_LIMITED_RANGE_12BPC:
+		REG_SET_2(FMT_CLAMP_CNTL, 0,
+			FMT_CLAMP_DATA_EN, 1,
+			FMT_CLAMP_COLOR_FORMAT, 3);
+		break;
+	case CLAMPING_LIMITED_RANGE_PROGRAMMABLE:
+		/*Set clamp control*/
+		REG_SET_2(FMT_CLAMP_CNTL, 0,
+			FMT_CLAMP_DATA_EN, 1,
+			FMT_CLAMP_COLOR_FORMAT, 7);
+
+		/* DCE6 does have FMT_CLAMP_COMPONENT_{R,G,B} registers */
+
+		break;
+	default:
+		break;
+	}
+}
+#endif
+
 /**
  *	set_pixel_encoding
  *
@@ -408,6 +500,39 @@ static void set_pixel_encoding(
 
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/**
+ *	dce60_set_pixel_encoding
+ *	DCE6 has no FMT_SUBSAMPLING_{MODE,ORDER} bits in FMT_CONTROL reg
+ *	Set Pixel Encoding
+ *		0: RGB 4:4:4 or YCbCr 4:4:4 or YOnly
+ *		1: YCbCr 4:2:2
+ */
+static void dce60_set_pixel_encoding(
+	struct dce110_opp *opp110,
+	const struct clamping_and_pixel_encoding_params *params)
+{
+	if (opp110->opp_mask->FMT_CBCR_BIT_REDUCTION_BYPASS)
+		REG_UPDATE_2(FMT_CONTROL,
+				FMT_PIXEL_ENCODING, 0,
+				FMT_CBCR_BIT_REDUCTION_BYPASS, 0);
+	else
+		REG_UPDATE(FMT_CONTROL,
+				FMT_PIXEL_ENCODING, 0);
+
+	if (params->pixel_encoding == PIXEL_ENCODING_YCBCR422) {
+		REG_UPDATE(FMT_CONTROL,
+				FMT_PIXEL_ENCODING, 1);
+	}
+	if (params->pixel_encoding == PIXEL_ENCODING_YCBCR420) {
+		REG_UPDATE_2(FMT_CONTROL,
+				FMT_PIXEL_ENCODING, 2,
+				FMT_CBCR_BIT_REDUCTION_BYPASS, 1);
+	}
+
+}
+#endif
+
 void dce110_opp_program_bit_depth_reduction(
 	struct output_pixel_processor *opp,
 	const struct bit_depth_reduction_params *params)
@@ -419,6 +544,19 @@ void dce110_opp_program_bit_depth_reduction(
 	set_temporal_dither(opp110, params);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_opp_program_bit_depth_reduction(
+	struct output_pixel_processor *opp,
+	const struct bit_depth_reduction_params *params)
+{
+	struct dce110_opp *opp110 = TO_DCE110_OPP(opp);
+
+	dce60_set_truncation(opp110, params);
+	set_spatial_dither(opp110, params);
+	set_temporal_dither(opp110, params);
+}
+#endif
+
 void dce110_opp_program_clamping_and_pixel_encoding(
 	struct output_pixel_processor *opp,
 	const struct clamping_and_pixel_encoding_params *params)
@@ -429,6 +567,19 @@ void dce110_opp_program_clamping_and_pixel_encoding(
 	set_pixel_encoding(opp110, params);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_opp_program_clamping_and_pixel_encoding(
+	struct output_pixel_processor *opp,
+	const struct clamping_and_pixel_encoding_params *params)
+{
+	struct dce110_opp *opp110 = TO_DCE110_OPP(opp);
+
+	dce60_opp_set_clamping(opp110, params);
+	dce60_set_pixel_encoding(opp110, params);
+}
+#endif
+
+
 static void program_formatter_420_memory(struct output_pixel_processor *opp)
 {
 	struct dce110_opp *opp110 = TO_DCE110_OPP(opp);
@@ -526,7 +677,32 @@ void dce110_opp_program_fmt(
 	return;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_opp_program_fmt(
+	struct output_pixel_processor *opp,
+	struct bit_depth_reduction_params *fmt_bit_depth,
+	struct clamping_and_pixel_encoding_params *clamping)
+{
+	/* dithering is affected by <CrtcSourceSelect>, hence should be
+	 * programmed afterwards */
+
+	if (clamping->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		program_formatter_420_memory(opp);
+
+	dce60_opp_program_bit_depth_reduction(
+		opp,
+		fmt_bit_depth);
+
+	dce60_opp_program_clamping_and_pixel_encoding(
+		opp,
+		clamping);
+
+	if (clamping->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		program_formatter_reset_dig_resync_fifo(opp);
 
+	return;
+}
+#endif
 
 
 
@@ -541,6 +717,15 @@ static const struct opp_funcs funcs = {
 	.opp_program_bit_depth_reduction = dce110_opp_program_bit_depth_reduction
 };
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct opp_funcs dce60_opp_funcs = {
+	.opp_set_dyn_expansion = dce110_opp_set_dyn_expansion,
+	.opp_destroy = dce110_opp_destroy,
+	.opp_program_fmt = dce60_opp_program_fmt,
+	.opp_program_bit_depth_reduction = dce60_opp_program_bit_depth_reduction
+};
+#endif
+
 void dce110_opp_construct(struct dce110_opp *opp110,
 	struct dc_context *ctx,
 	uint32_t inst,
@@ -559,6 +744,26 @@ void dce110_opp_construct(struct dce110_opp *opp110,
 	opp110->opp_mask = opp_mask;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_opp_construct(struct dce110_opp *opp110,
+	struct dc_context *ctx,
+	uint32_t inst,
+	const struct dce_opp_registers *regs,
+	const struct dce_opp_shift *opp_shift,
+	const struct dce_opp_mask *opp_mask)
+{
+	opp110->base.funcs = &dce60_opp_funcs;
+
+	opp110->base.ctx = ctx;
+
+	opp110->base.inst = inst;
+
+	opp110->regs = regs;
+	opp110->opp_shift = opp_shift;
+	opp110->opp_mask = opp_mask;
+}
+#endif
+
 void dce110_opp_destroy(struct output_pixel_processor **opp)
 {
 	if (*opp)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.h b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.h
index 2ab0147cbd9d..4d484ef60f35 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.h
@@ -81,6 +81,17 @@ enum dce110_opp_reg_type {
 	OPP_COMMON_REG_LIST_BASE(id), \
 	SRI(CONTROL, FMT_MEMORY, id)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define OPP_DCE_60_REG_LIST(id) \
+	SRI(FMT_DYNAMIC_EXP_CNTL, FMT, id), \
+	SRI(FMT_BIT_DEPTH_CONTROL, FMT, id), \
+	SRI(FMT_CONTROL, FMT, id), \
+	SRI(FMT_DITHER_RAND_R_SEED, FMT, id), \
+	SRI(FMT_DITHER_RAND_G_SEED, FMT, id), \
+	SRI(FMT_DITHER_RAND_B_SEED, FMT, id), \
+	SRI(FMT_CLAMP_CNTL, FMT, id)
+#endif
+
 #define OPP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -192,6 +203,35 @@ enum dce110_opp_reg_type {
 	OPP_SF(FMT0_FMT_CONTROL, FMT_SUBSAMPLING_ORDER, mask_sh),\
 	OPP_SF(FMT0_FMT_CONTROL, FMT_CBCR_BIT_REDUCTION_BYPASS, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define OPP_COMMON_MASK_SH_LIST_DCE_60(mask_sh)\
+	OPP_SF(FMT_DYNAMIC_EXP_CNTL, FMT_DYNAMIC_EXP_EN, mask_sh),\
+	OPP_SF(FMT_DYNAMIC_EXP_CNTL, FMT_DYNAMIC_EXP_MODE, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_DEPTH, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_EN, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_DEPTH, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_MODE, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_HIGHPASS_RANDOM_ENABLE, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_FRAME_RANDOM_ENABLE, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_RGB_RANDOM_ENABLE, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_DITHER_EN, mask_sh),\
+	OPP_SF(FMT_DITHER_RAND_R_SEED, FMT_RAND_R_SEED, mask_sh),\
+	OPP_SF(FMT_DITHER_RAND_G_SEED, FMT_RAND_G_SEED, mask_sh),\
+	OPP_SF(FMT_DITHER_RAND_B_SEED, FMT_RAND_B_SEED, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_DITHER_EN, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_DITHER_RESET, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_DITHER_OFFSET, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_DITHER_DEPTH, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_TEMPORAL_LEVEL, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_25FRC_SEL, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_50FRC_SEL, mask_sh),\
+	OPP_SF(FMT_BIT_DEPTH_CONTROL, FMT_75FRC_SEL, mask_sh),\
+	OPP_SF(FMT_CLAMP_CNTL, FMT_CLAMP_DATA_EN, mask_sh),\
+	OPP_SF(FMT_CLAMP_CNTL, FMT_CLAMP_COLOR_FORMAT, mask_sh),\
+	OPP_SF(FMT_CONTROL, FMT_PIXEL_ENCODING, mask_sh)
+#endif
+
 #define OPP_REG_FIELD_LIST(type) \
 	type FMT_DYNAMIC_EXP_EN; \
 	type FMT_DYNAMIC_EXP_MODE; \
@@ -279,6 +319,15 @@ void dce110_opp_construct(struct dce110_opp *opp110,
 	const struct dce_opp_shift *opp_shift,
 	const struct dce_opp_mask *opp_mask);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_opp_construct(struct dce110_opp *opp110,
+	struct dc_context *ctx,
+	uint32_t inst,
+	const struct dce_opp_registers *regs,
+	const struct dce_opp_shift *opp_shift,
+	const struct dce_opp_mask *opp_mask);
+#endif
+
 void dce110_opp_destroy(struct output_pixel_processor **opp);
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index 43781e77be43..df7f826eebd8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -46,13 +46,14 @@
 #define FN(reg_name, field_name) \
 	dce_panel_cntl->shift->field_name, dce_panel_cntl->mask->field_name
 
-static unsigned int calculate_16_bit_backlight_from_pwm(struct dce_panel_cntl *dce_panel_cntl)
+static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_cntl)
 {
 	uint64_t current_backlight;
 	uint32_t round_result;
 	uint32_t pwm_period_cntl, bl_period, bl_int_count;
 	uint32_t bl_pwm_cntl, bl_pwm, fractional_duty_cycle_en;
 	uint32_t bl_period_mask, bl_pwm_mask;
+	struct dce_panel_cntl *dce_panel_cntl = TO_DCE_PANEL_CNTL(panel_cntl);
 
 	pwm_period_cntl = REG_READ(BL_PWM_PERIOD_CNTL);
 	REG_GET(BL_PWM_PERIOD_CNTL, BL_PWM_PERIOD, &bl_period);
@@ -75,7 +76,7 @@ static unsigned int calculate_16_bit_backlight_from_pwm(struct dce_panel_cntl *d
 	else
 		bl_pwm &= 0xFFFF;
 
-	current_backlight = bl_pwm << (1 + bl_int_count);
+	current_backlight = (uint64_t)bl_pwm << (1 + bl_int_count);
 
 	if (bl_period == 0)
 		bl_period = 0xFFFF;
@@ -150,7 +151,7 @@ static uint32_t dce_panel_cntl_hw_init(struct panel_cntl *panel_cntl)
 	REG_UPDATE(BL_PWM_GRP1_REG_LOCK,
 			BL_PWM_GRP1_REG_LOCK, 0);
 
-	current_backlight = calculate_16_bit_backlight_from_pwm(dce_panel_cntl);
+	current_backlight = dce_get_16_bit_backlight_from_pwm(panel_cntl);
 
 	return current_backlight;
 }
@@ -273,6 +274,7 @@ static const struct panel_cntl_funcs dce_link_panel_cntl_funcs = {
 	.is_panel_powered_on = dce_is_panel_powered_on,
 	.store_backlight_level = dce_store_backlight_level,
 	.driver_set_backlight = dce_driver_set_backlight,
+	.get_current_backlight = dce_get_16_bit_backlight_from_pwm,
 };
 
 void dce_panel_cntl_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
index 70ec691e14d2..99c68ca9c7e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
@@ -49,7 +49,7 @@
 #define DCN_PANEL_CNTL_REG_LIST()\
 	DCN_PANEL_CNTL_SR(PWRSEQ_CNTL, LVTMA), \
 	DCN_PANEL_CNTL_SR(PWRSEQ_STATE, LVTMA), \
-	DCE_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \
+	DCN_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \
 	SR(BL_PWM_CNTL), \
 	SR(BL_PWM_CNTL2), \
 	SR(BL_PWM_PERIOD_CNTL), \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index ab63d0d0304c..2a32b66959ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -146,6 +146,33 @@ static bool setup_scaling_configuration(
 	return true;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static bool dce60_setup_scaling_configuration(
+	struct dce_transform *xfm_dce,
+	const struct scaler_data *data)
+{
+	REG_SET(SCL_BYPASS_CONTROL, 0, SCL_BYPASS_MODE, 0);
+
+	if (data->taps.h_taps + data->taps.v_taps <= 2) {
+		/* Set bypass */
+
+		/* DCE6 has no SCL_MODE register, skip scale mode programming */
+
+		return false;
+	}
+
+	REG_SET_2(SCL_TAP_CONTROL, 0,
+			SCL_H_NUM_OF_TAPS, data->taps.h_taps - 1,
+			SCL_V_NUM_OF_TAPS, data->taps.v_taps - 1);
+
+	/* DCE6 has no SCL_MODE register, skip scale mode programming */
+
+	/* DCE6 has no SCL_BOUNDARY_MODE bit, skip replace out of bound pixels */
+
+	return true;
+}
+#endif
+
 static void program_overscan(
 		struct dce_transform *xfm_dce,
 		const struct scaler_data *data)
@@ -279,6 +306,36 @@ static void calculate_inits(
 	inits->v_init.fraction = dc_fixpt_u0d19(v_init) << 5;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_calculate_inits(
+	struct dce_transform *xfm_dce,
+	const struct scaler_data *data,
+	struct sclh_ratios_inits *inits)
+{
+	struct fixed31_32 v_init;
+
+	inits->h_int_scale_ratio =
+		dc_fixpt_u2d19(data->ratios.horz) << 5;
+	inits->v_int_scale_ratio =
+		dc_fixpt_u2d19(data->ratios.vert) << 5;
+
+	/* DCE6 h_init_luma setting inspired by DCE110 */
+	inits->h_init_luma.integer = 1;
+
+	/* DCE6 h_init_chroma setting inspired by DCE110 */
+	inits->h_init_chroma.integer = 1;
+
+	v_init =
+		dc_fixpt_div_int(
+			dc_fixpt_add(
+				data->ratios.vert,
+				dc_fixpt_from_int(data->taps.v_taps + 1)),
+				2);
+	inits->v_init.integer = dc_fixpt_floor(v_init);
+	inits->v_init.fraction = dc_fixpt_u0d19(v_init) << 5;
+}
+#endif
+
 static void program_scl_ratios_inits(
 	struct dce_transform *xfm_dce,
 	struct scl_ratios_inits *inits)
@@ -301,6 +358,36 @@ static void program_scl_ratios_inits(
 	REG_WRITE(SCL_AUTOMATIC_MODE_CONTROL, 0);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_program_scl_ratios_inits(
+	struct dce_transform *xfm_dce,
+	struct sclh_ratios_inits *inits)
+{
+
+	REG_SET(SCL_HORZ_FILTER_SCALE_RATIO, 0,
+			SCL_H_SCALE_RATIO, inits->h_int_scale_ratio);
+
+	REG_SET(SCL_VERT_FILTER_SCALE_RATIO, 0,
+			SCL_V_SCALE_RATIO, inits->v_int_scale_ratio);
+
+	/* DCE6 has SCL_HORZ_FILTER_INIT_RGB_LUMA register */
+	REG_SET_2(SCL_HORZ_FILTER_INIT_RGB_LUMA, 0,
+			SCL_H_INIT_INT_RGB_Y, inits->h_init_luma.integer,
+			SCL_H_INIT_FRAC_RGB_Y, inits->h_init_luma.fraction);
+
+	/* DCE6 has SCL_HORZ_FILTER_INIT_CHROMA register */
+	REG_SET_2(SCL_HORZ_FILTER_INIT_CHROMA, 0,
+			SCL_H_INIT_INT_CBCR, inits->h_init_chroma.integer,
+			SCL_H_INIT_FRAC_CBCR, inits->h_init_chroma.fraction);
+
+	REG_SET_2(SCL_VERT_FILTER_INIT, 0,
+			SCL_V_INIT_INT, inits->v_init.integer,
+			SCL_V_INIT_FRAC, inits->v_init.fraction);
+
+	REG_WRITE(SCL_AUTOMATIC_MODE_CONTROL, 0);
+}
+#endif
+
 static const uint16_t *get_filter_coeffs_16p(int taps, struct fixed31_32 ratio)
 {
 	if (taps == 4)
@@ -399,6 +486,91 @@ static void dce_transform_set_scaler(
 	REG_UPDATE(LB_DATA_FORMAT, ALPHA_EN, data->lb_params.alpha_en);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_transform_set_scaler(
+	struct transform *xfm,
+	const struct scaler_data *data)
+{
+	struct dce_transform *xfm_dce = TO_DCE_TRANSFORM(xfm);
+	bool is_scaling_required;
+	bool filter_updated = false;
+	const uint16_t *coeffs_v, *coeffs_h;
+
+	/*Use whole line buffer memory always*/
+	REG_SET(DC_LB_MEMORY_SPLIT, 0,
+		DC_LB_MEMORY_CONFIG, 0);
+
+	REG_SET(DC_LB_MEM_SIZE, 0,
+		DC_LB_MEM_SIZE, xfm_dce->lb_memory_size);
+
+	/* Clear SCL_F_SHARP_CONTROL value to 0 */
+	REG_WRITE(SCL_F_SHARP_CONTROL, 0);
+
+	/* 1. Program overscan */
+	program_overscan(xfm_dce, data);
+
+	/* 2. Program taps and configuration */
+	is_scaling_required = dce60_setup_scaling_configuration(xfm_dce, data);
+
+	if (is_scaling_required) {
+		/* 3. Calculate and program ratio, DCE6 filter initialization */
+		struct sclh_ratios_inits inits = { 0 };
+
+		/* DCE6 has specific calculate_inits() function */
+		dce60_calculate_inits(xfm_dce, data, &inits);
+
+		/* DCE6 has specific program_scl_ratios_inits() function */
+		dce60_program_scl_ratios_inits(xfm_dce, &inits);
+
+		coeffs_v = get_filter_coeffs_16p(data->taps.v_taps, data->ratios.vert);
+		coeffs_h = get_filter_coeffs_16p(data->taps.h_taps, data->ratios.horz);
+
+		if (coeffs_v != xfm_dce->filter_v || coeffs_h != xfm_dce->filter_h) {
+			/* 4. Program vertical filters */
+			if (xfm_dce->filter_v == NULL)
+				REG_SET(SCL_VERT_FILTER_CONTROL, 0,
+						SCL_V_2TAP_HARDCODE_COEF_EN, 0);
+			program_multi_taps_filter(
+					xfm_dce,
+					data->taps.v_taps,
+					coeffs_v,
+					FILTER_TYPE_RGB_Y_VERTICAL);
+			program_multi_taps_filter(
+					xfm_dce,
+					data->taps.v_taps,
+					coeffs_v,
+					FILTER_TYPE_ALPHA_VERTICAL);
+
+			/* 5. Program horizontal filters */
+			if (xfm_dce->filter_h == NULL)
+				REG_SET(SCL_HORZ_FILTER_CONTROL, 0,
+						SCL_H_2TAP_HARDCODE_COEF_EN, 0);
+			program_multi_taps_filter(
+					xfm_dce,
+					data->taps.h_taps,
+					coeffs_h,
+					FILTER_TYPE_RGB_Y_HORIZONTAL);
+			program_multi_taps_filter(
+					xfm_dce,
+					data->taps.h_taps,
+					coeffs_h,
+					FILTER_TYPE_ALPHA_HORIZONTAL);
+
+			xfm_dce->filter_v = coeffs_v;
+			xfm_dce->filter_h = coeffs_h;
+			filter_updated = true;
+		}
+	}
+
+	/* 6. Program the viewport */
+	program_viewport(xfm_dce, &data->viewport);
+
+	/* DCE6 has no SCL_COEF_UPDATE_COMPLETE bit to flip to new coefficient memory */
+
+	/* DCE6 DATA_FORMAT register does not support ALPHA_EN */
+}
+#endif
+
 /*****************************************************************************
  * set_clamp
  *
@@ -664,6 +836,67 @@ static void program_bit_depth_reduction(
 		   bit_depth_params->flags.HIGHPASS_RANDOM);
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+/*****************************************************************************
+ * dce60_transform_bit_depth_reduction program
+ *
+ * @brief
+ *     Programs the DCP bit depth reduction registers (Clamp, Round/Truncate,
+ *      Dither) for dce
+ *
+ * @param depth : bit depth to set the clamp to (should match denorm)
+ *
+ ******************************************************************************/
+static void dce60_program_bit_depth_reduction(
+	struct dce_transform *xfm_dce,
+	enum dc_color_depth depth,
+	const struct bit_depth_reduction_params *bit_depth_params)
+{
+	enum dcp_out_trunc_round_depth trunc_round_depth;
+	enum dcp_out_trunc_round_mode trunc_mode;
+	bool spatial_dither_enable;
+
+	ASSERT(depth < COLOR_DEPTH_121212); /* Invalid clamp bit depth */
+
+	spatial_dither_enable = bit_depth_params->flags.SPATIAL_DITHER_ENABLED;
+	/* Default to 12 bit truncation without rounding */
+	trunc_round_depth = DCP_OUT_TRUNC_ROUND_DEPTH_12BIT;
+	trunc_mode = DCP_OUT_TRUNC_ROUND_MODE_TRUNCATE;
+
+	if (bit_depth_params->flags.TRUNCATE_ENABLED) {
+		/* Don't enable dithering if truncation is enabled */
+		spatial_dither_enable = false;
+		trunc_mode = bit_depth_params->flags.TRUNCATE_MODE ?
+			     DCP_OUT_TRUNC_ROUND_MODE_ROUND :
+			     DCP_OUT_TRUNC_ROUND_MODE_TRUNCATE;
+
+		if (bit_depth_params->flags.TRUNCATE_DEPTH == 0 ||
+		    bit_depth_params->flags.TRUNCATE_DEPTH == 1)
+			trunc_round_depth = DCP_OUT_TRUNC_ROUND_DEPTH_8BIT;
+		else if (bit_depth_params->flags.TRUNCATE_DEPTH == 2)
+			trunc_round_depth = DCP_OUT_TRUNC_ROUND_DEPTH_10BIT;
+		else {
+			/*
+			 * Invalid truncate/round depth. Setting here to 12bit
+			 * to prevent use-before-initialize errors.
+			 */
+			trunc_round_depth = DCP_OUT_TRUNC_ROUND_DEPTH_12BIT;
+			BREAK_TO_DEBUGGER();
+		}
+	}
+
+	/* DCE6 has no OUT_CLAMP_CONTROL_* registers - set_clamp() is skipped */
+	set_round(xfm_dce, trunc_mode, trunc_round_depth);
+	set_dither(xfm_dce,
+		   spatial_dither_enable,
+		   DCP_SPATIAL_DITHER_MODE_A_AA_A,
+		   DCP_SPATIAL_DITHER_DEPTH_30BPP,
+		   bit_depth_params->flags.FRAME_RANDOM,
+		   bit_depth_params->flags.RGB_RANDOM,
+		   bit_depth_params->flags.HIGHPASS_RANDOM);
+}
+#endif
+
 static int dce_transform_get_max_num_of_supported_lines(
 	struct dce_transform *xfm_dce,
 	enum lb_pixel_depth depth,
@@ -797,6 +1030,59 @@ static void dce_transform_set_pixel_storage_depth(
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static void dce60_transform_set_pixel_storage_depth(
+	struct transform *xfm,
+	enum lb_pixel_depth depth,
+	const struct bit_depth_reduction_params *bit_depth_params)
+{
+	struct dce_transform *xfm_dce = TO_DCE_TRANSFORM(xfm);
+	int pixel_depth, expan_mode;
+	enum dc_color_depth color_depth;
+
+	switch (depth) {
+	case LB_PIXEL_DEPTH_18BPP:
+		color_depth = COLOR_DEPTH_666;
+		pixel_depth = 2;
+		expan_mode  = 1;
+		break;
+	case LB_PIXEL_DEPTH_24BPP:
+		color_depth = COLOR_DEPTH_888;
+		pixel_depth = 1;
+		expan_mode  = 1;
+		break;
+	case LB_PIXEL_DEPTH_30BPP:
+		color_depth = COLOR_DEPTH_101010;
+		pixel_depth = 0;
+		expan_mode  = 1;
+		break;
+	case LB_PIXEL_DEPTH_36BPP:
+		color_depth = COLOR_DEPTH_121212;
+		pixel_depth = 3;
+		expan_mode  = 0;
+		break;
+	default:
+		color_depth = COLOR_DEPTH_101010;
+		pixel_depth = 0;
+		expan_mode  = 1;
+		BREAK_TO_DEBUGGER();
+		break;
+	}
+
+	set_denormalization(xfm_dce, color_depth);
+	dce60_program_bit_depth_reduction(xfm_dce, color_depth, bit_depth_params);
+
+	/* DATA_FORMAT in DCE6 does not have PIXEL_DEPTH and PIXEL_EXPAN_MODE masks */
+
+	if (!(xfm_dce->lb_pixel_depth_supported & depth)) {
+		/*we should use unsupported capabilities
+		 *  unless it is required by w/a*/
+		DC_LOG_WARNING("%s: Capability not supported",
+			__func__);
+	}
+}
+#endif
+
 static void program_gamut_remap(
 	struct dce_transform *xfm_dce,
 	const uint16_t *reg_val)
@@ -1335,6 +1621,21 @@ static const struct transform_funcs dce_transform_funcs = {
 	.transform_get_optimal_number_of_taps = dce_transform_get_optimal_number_of_taps
 };
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+static const struct transform_funcs dce60_transform_funcs = {
+	.transform_reset = dce_transform_reset,
+	.transform_set_scaler = dce60_transform_set_scaler,
+	.transform_set_gamut_remap = dce_transform_set_gamut_remap,
+	.opp_set_csc_adjustment = dce110_opp_set_csc_adjustment,
+	.opp_set_csc_default = dce110_opp_set_csc_default,
+	.opp_power_on_regamma_lut = dce110_opp_power_on_regamma_lut,
+	.opp_program_regamma_pwl = dce110_opp_program_regamma_pwl,
+	.opp_set_regamma_mode = dce110_opp_set_regamma_mode,
+	.transform_set_pixel_storage_depth = dce60_transform_set_pixel_storage_depth,
+	.transform_get_optimal_number_of_taps = dce_transform_get_optimal_number_of_taps
+};
+#endif
+
 /*****************************************/
 /* Constructor, Destructor               */
 /*****************************************/
@@ -1365,3 +1666,32 @@ void dce_transform_construct(
 	xfm_dce->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	xfm_dce->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x6B0*/
 }
+
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_transform_construct(
+	struct dce_transform *xfm_dce,
+	struct dc_context *ctx,
+	uint32_t inst,
+	const struct dce_transform_registers *regs,
+	const struct dce_transform_shift *xfm_shift,
+	const struct dce_transform_mask *xfm_mask)
+{
+	xfm_dce->base.ctx = ctx;
+
+	xfm_dce->base.inst = inst;
+	xfm_dce->base.funcs = &dce60_transform_funcs;
+
+	xfm_dce->regs = regs;
+	xfm_dce->xfm_shift = xfm_shift;
+	xfm_dce->xfm_mask = xfm_mask;
+
+	xfm_dce->prescaler_on = true;
+	xfm_dce->lb_pixel_depth_supported =
+			LB_PIXEL_DEPTH_18BPP |
+			LB_PIXEL_DEPTH_24BPP |
+			LB_PIXEL_DEPTH_30BPP;
+
+	xfm_dce->lb_bits_per_entry = LB_BITS_PER_ENTRY;
+	xfm_dce->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x6B0*/
+}
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
index 948281d8b6af..cbce194ec7b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
@@ -108,6 +108,68 @@
 	SRI(DCFE_MEM_PWR_CTRL, DCFE, id), \
 	SRI(DCFE_MEM_PWR_STATUS, DCFE, id)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define XFM_COMMON_REG_LIST_DCE60_BASE(id) \
+	SRI(DATA_FORMAT, LB, id), \
+	SRI(GAMUT_REMAP_CONTROL, DCP, id), \
+	SRI(GAMUT_REMAP_C11_C12, DCP, id), \
+	SRI(GAMUT_REMAP_C13_C14, DCP, id), \
+	SRI(GAMUT_REMAP_C21_C22, DCP, id), \
+	SRI(GAMUT_REMAP_C23_C24, DCP, id), \
+	SRI(GAMUT_REMAP_C31_C32, DCP, id), \
+	SRI(GAMUT_REMAP_C33_C34, DCP, id), \
+	SRI(OUTPUT_CSC_C11_C12, DCP, id), \
+	SRI(OUTPUT_CSC_C13_C14, DCP, id), \
+	SRI(OUTPUT_CSC_C21_C22, DCP, id), \
+	SRI(OUTPUT_CSC_C23_C24, DCP, id), \
+	SRI(OUTPUT_CSC_C31_C32, DCP, id), \
+	SRI(OUTPUT_CSC_C33_C34, DCP, id), \
+	SRI(OUTPUT_CSC_CONTROL, DCP, id), \
+	SRI(REGAMMA_CNTLA_START_CNTL, DCP, id), \
+	SRI(REGAMMA_CNTLA_SLOPE_CNTL, DCP, id), \
+	SRI(REGAMMA_CNTLA_END_CNTL1, DCP, id), \
+	SRI(REGAMMA_CNTLA_END_CNTL2, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_0_1, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_2_3, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_4_5, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_6_7, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_8_9, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_10_11, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_12_13, DCP, id), \
+	SRI(REGAMMA_CNTLA_REGION_14_15, DCP, id), \
+	SRI(REGAMMA_LUT_WRITE_EN_MASK, DCP, id), \
+	SRI(REGAMMA_LUT_INDEX, DCP, id), \
+	SRI(REGAMMA_LUT_DATA, DCP, id), \
+	SRI(REGAMMA_CONTROL, DCP, id), \
+	SRI(DENORM_CONTROL, DCP, id), \
+	SRI(DCP_SPATIAL_DITHER_CNTL, DCP, id), \
+	SRI(OUT_ROUND_CONTROL, DCP, id), \
+	SRI(SCL_TAP_CONTROL, SCL, id), \
+	SRI(SCL_CONTROL, SCL, id), \
+	SRI(SCL_BYPASS_CONTROL, SCL, id), \
+	SRI(EXT_OVERSCAN_LEFT_RIGHT, SCL, id), \
+	SRI(EXT_OVERSCAN_TOP_BOTTOM, SCL, id), \
+	SRI(SCL_VERT_FILTER_CONTROL, SCL, id), \
+	SRI(SCL_HORZ_FILTER_CONTROL, SCL, id), \
+	SRI(SCL_COEF_RAM_SELECT, SCL, id), \
+	SRI(SCL_COEF_RAM_TAP_DATA, SCL, id), \
+	SRI(VIEWPORT_START, SCL, id), \
+	SRI(VIEWPORT_SIZE, SCL, id), \
+	SRI(SCL_HORZ_FILTER_SCALE_RATIO, SCL, id), \
+	SRI(SCL_VERT_FILTER_SCALE_RATIO, SCL, id), \
+	SRI(SCL_VERT_FILTER_INIT, SCL, id), \
+	SRI(SCL_AUTOMATIC_MODE_CONTROL, SCL, id), \
+	SRI(DC_LB_MEMORY_SPLIT, LB, id), \
+	SRI(DC_LB_MEM_SIZE, LB, id), \
+	SRI(DCFE_MEM_LIGHT_SLEEP_CNTL, CRTC, id), \
+	SRI(SCL_UPDATE, SCL, id), \
+	SRI(SCL_F_SHARP_CONTROL, SCL, id)
+
+#define XFM_COMMON_REG_LIST_DCE60(id) \
+	XFM_COMMON_REG_LIST_DCE60_BASE(id), \
+	SRI(DCFE_MEM_LIGHT_SLEEP_CNTL, CRTC, id)
+#endif
+
 #define XFM_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -204,6 +266,83 @@
 	XFM_SF(DCFE_MEM_PWR_STATUS, DCP_REGAMMA_MEM_PWR_STATE, mask_sh),\
 	XFM_SF(SCL_MODE, SCL_PSCL_EN, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define XFM_COMMON_MASK_SH_LIST_DCE60(mask_sh) \
+	XFM_COMMON_MASK_SH_LIST_DCE60_COMMON_BASE(mask_sh), \
+	OPP_SF(DCFE_MEM_LIGHT_SLEEP_CNTL, REGAMMA_LUT_LIGHT_SLEEP_DIS, mask_sh),\
+	OPP_SF(DCFE_MEM_LIGHT_SLEEP_CNTL, DCP_LUT_LIGHT_SLEEP_DIS, mask_sh),\
+	OPP_SF(DCFE_MEM_LIGHT_SLEEP_CNTL, REGAMMA_LUT_MEM_PWR_STATE, mask_sh)
+
+#define XFM_COMMON_MASK_SH_LIST_DCE60_COMMON_BASE(mask_sh) \
+	XFM_SF(OUT_ROUND_CONTROL, OUT_ROUND_TRUNC_MODE, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_SPATIAL_DITHER_EN, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_SPATIAL_DITHER_MODE, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_SPATIAL_DITHER_DEPTH, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_FRAME_RANDOM_ENABLE, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_RGB_RANDOM_ENABLE, mask_sh), \
+	XFM_SF(DCP_SPATIAL_DITHER_CNTL, DCP_HIGHPASS_RANDOM_ENABLE, mask_sh), \
+	XFM_SF(DENORM_CONTROL, DENORM_MODE, mask_sh), \
+	XFM_SF(DATA_FORMAT, INTERLEAVE_EN, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C11_C12, GAMUT_REMAP_C11, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C11_C12, GAMUT_REMAP_C12, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C13_C14, GAMUT_REMAP_C13, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C13_C14, GAMUT_REMAP_C14, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C21_C22, GAMUT_REMAP_C21, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C21_C22, GAMUT_REMAP_C22, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C23_C24, GAMUT_REMAP_C23, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C23_C24, GAMUT_REMAP_C24, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C31_C32, GAMUT_REMAP_C31, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C31_C32, GAMUT_REMAP_C32, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C33_C34, GAMUT_REMAP_C33, mask_sh), \
+	XFM_SF(GAMUT_REMAP_C33_C34, GAMUT_REMAP_C34, mask_sh), \
+	XFM_SF(GAMUT_REMAP_CONTROL, GRPH_GAMUT_REMAP_MODE, mask_sh), \
+	XFM_SF(OUTPUT_CSC_C11_C12, OUTPUT_CSC_C11, mask_sh),\
+	XFM_SF(OUTPUT_CSC_C11_C12, OUTPUT_CSC_C12, mask_sh),\
+	XFM_SF(OUTPUT_CSC_CONTROL, OUTPUT_CSC_GRPH_MODE, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_START_CNTL, REGAMMA_CNTLA_EXP_REGION_START, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_START_CNTL, REGAMMA_CNTLA_EXP_REGION_START_SEGMENT, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_SLOPE_CNTL, REGAMMA_CNTLA_EXP_REGION_LINEAR_SLOPE, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_END_CNTL1, REGAMMA_CNTLA_EXP_REGION_END, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_END_CNTL2, REGAMMA_CNTLA_EXP_REGION_END_BASE, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_END_CNTL2, REGAMMA_CNTLA_EXP_REGION_END_SLOPE, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_REGION_0_1, REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_REGION_0_1, REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_REGION_0_1, REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, mask_sh),\
+	XFM_SF(REGAMMA_CNTLA_REGION_0_1, REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, mask_sh),\
+	XFM_SF(REGAMMA_LUT_WRITE_EN_MASK, REGAMMA_LUT_WRITE_EN_MASK, mask_sh),\
+	XFM_SF(REGAMMA_CONTROL, GRPH_REGAMMA_MODE, mask_sh),\
+	XFM_SF(SCL_TAP_CONTROL, SCL_H_NUM_OF_TAPS, mask_sh), \
+	XFM_SF(SCL_TAP_CONTROL, SCL_V_NUM_OF_TAPS, mask_sh), \
+	XFM_SF(SCL_BYPASS_CONTROL, SCL_BYPASS_MODE, mask_sh), \
+	XFM_SF(EXT_OVERSCAN_LEFT_RIGHT, EXT_OVERSCAN_LEFT, mask_sh), \
+	XFM_SF(EXT_OVERSCAN_LEFT_RIGHT, EXT_OVERSCAN_RIGHT, mask_sh), \
+	XFM_SF(EXT_OVERSCAN_TOP_BOTTOM, EXT_OVERSCAN_TOP, mask_sh), \
+	XFM_SF(EXT_OVERSCAN_TOP_BOTTOM, EXT_OVERSCAN_BOTTOM, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_SELECT, SCL_C_RAM_FILTER_TYPE, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_SELECT, SCL_C_RAM_PHASE, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_SELECT, SCL_C_RAM_TAP_PAIR_IDX, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_TAP_DATA, SCL_C_RAM_EVEN_TAP_COEF_EN, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_TAP_DATA, SCL_C_RAM_EVEN_TAP_COEF, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_TAP_DATA, SCL_C_RAM_ODD_TAP_COEF_EN, mask_sh), \
+	XFM_SF(SCL_COEF_RAM_TAP_DATA, SCL_C_RAM_ODD_TAP_COEF, mask_sh), \
+	XFM_SF(VIEWPORT_START, VIEWPORT_X_START, mask_sh), \
+	XFM_SF(VIEWPORT_START, VIEWPORT_Y_START, mask_sh), \
+	XFM_SF(VIEWPORT_SIZE, VIEWPORT_HEIGHT, mask_sh), \
+	XFM_SF(VIEWPORT_SIZE, VIEWPORT_WIDTH, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_SCALE_RATIO, SCL_H_SCALE_RATIO, mask_sh), \
+	XFM_SF(SCL_VERT_FILTER_SCALE_RATIO, SCL_V_SCALE_RATIO, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL_H_INIT_INT_RGB_Y, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL_H_INIT_FRAC_RGB_Y, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_INIT_CHROMA, SCL_H_INIT_INT_CBCR, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_INIT_CHROMA, SCL_H_INIT_FRAC_CBCR, mask_sh), \
+	XFM_SF(SCL_VERT_FILTER_INIT, SCL_V_INIT_INT, mask_sh), \
+	XFM_SF(SCL_VERT_FILTER_INIT, SCL_V_INIT_FRAC, mask_sh), \
+	XFM_SF(SCL_HORZ_FILTER_CONTROL, SCL_H_FILTER_PICK_NEAREST, mask_sh), \
+	XFM_SF(SCL_VERT_FILTER_CONTROL, SCL_V_FILTER_PICK_NEAREST, mask_sh), \
+	XFM_SF(DC_LB_MEMORY_SPLIT, DC_LB_MEMORY_CONFIG, mask_sh), \
+	XFM_SF(DC_LB_MEM_SIZE, DC_LB_MEM_SIZE, mask_sh)
+#endif
+
 #define XFM_COMMON_MASK_SH_LIST_SOC_BASE(mask_sh) \
 	XFM_SF(DCP0_OUT_CLAMP_CONTROL_B_CB, OUT_CLAMP_MIN_B_CB, mask_sh), \
 	XFM_SF(DCP0_OUT_CLAMP_CONTROL_B_CB, OUT_CLAMP_MAX_B_CB, mask_sh), \
@@ -302,6 +441,7 @@
 	type DCP_RGB_RANDOM_ENABLE; \
 	type DCP_HIGHPASS_RANDOM_ENABLE; \
 	type DENORM_MODE; \
+	type INTERLEAVE_EN; \
 	type PIXEL_DEPTH; \
 	type PIXEL_EXPAN_MODE; \
 	type GAMUT_REMAP_C11; \
@@ -365,12 +505,20 @@
 	type SCL_V_SCALE_RATIO; \
 	type SCL_H_INIT_INT; \
 	type SCL_H_INIT_FRAC; \
+	type SCL_H_INIT_INT_RGB_Y; \
+	type SCL_H_INIT_FRAC_RGB_Y; \
+	type SCL_H_INIT_INT_CBCR; \
+	type SCL_H_INIT_FRAC_CBCR; \
 	type SCL_V_INIT_INT; \
 	type SCL_V_INIT_FRAC; \
+	type DC_LB_MEMORY_CONFIG; \
+	type DC_LB_MEM_SIZE; \
 	type LB_MEMORY_CONFIG; \
 	type LB_MEMORY_SIZE; \
 	type SCL_V_2TAP_HARDCODE_COEF_EN; \
 	type SCL_H_2TAP_HARDCODE_COEF_EN; \
+	type SCL_V_FILTER_PICK_NEAREST; \
+	type SCL_H_FILTER_PICK_NEAREST; \
 	type SCL_COEF_UPDATE_COMPLETE; \
 	type ALPHA_EN
 
@@ -383,6 +531,9 @@ struct dce_transform_mask {
 };
 
 struct dce_transform_registers {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t DATA_FORMAT;
+#endif
 	uint32_t LB_DATA_FORMAT;
 	uint32_t GAMUT_REMAP_CONTROL;
 	uint32_t GAMUT_REMAP_C11_C12;
@@ -438,8 +589,16 @@ struct dce_transform_registers {
 	uint32_t SCL_HORZ_FILTER_SCALE_RATIO;
 	uint32_t SCL_VERT_FILTER_SCALE_RATIO;
 	uint32_t SCL_HORZ_FILTER_INIT;
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t SCL_HORZ_FILTER_INIT_RGB_LUMA;
+	uint32_t SCL_HORZ_FILTER_INIT_CHROMA;
+#endif
 	uint32_t SCL_VERT_FILTER_INIT;
 	uint32_t SCL_AUTOMATIC_MODE_CONTROL;
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t DC_LB_MEMORY_SPLIT;
+	uint32_t DC_LB_MEM_SIZE;
+#endif
 	uint32_t LB_MEMORY_CTRL;
 	uint32_t SCL_UPDATE;
 	uint32_t SCL_F_SHARP_CONTROL;
@@ -457,6 +616,16 @@ struct scl_ratios_inits {
 	struct init_int_and_frac v_init;
 };
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+struct sclh_ratios_inits {
+	uint32_t h_int_scale_ratio;
+	uint32_t v_int_scale_ratio;
+	struct init_int_and_frac h_init_luma;
+	struct init_int_and_frac h_init_chroma;
+	struct init_int_and_frac v_init;
+};
+#endif
+
 enum ram_filter_type {
 	FILTER_TYPE_RGB_Y_VERTICAL	= 0, /* 0 - RGB/Y Vertical filter */
 	FILTER_TYPE_CBCR_VERTICAL	= 1, /* 1 - CbCr  Vertical filter */
@@ -489,6 +658,15 @@ void dce_transform_construct(struct dce_transform *xfm_dce,
 	const struct dce_transform_shift *xfm_shift,
 	const struct dce_transform_mask *xfm_mask);
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+void dce60_transform_construct(struct dce_transform *xfm_dce,
+	struct dc_context *ctx,
+	uint32_t inst,
+	const struct dce_transform_registers *regs,
+	const struct dce_transform_shift *xfm_shift,
+	const struct dce_transform_mask *xfm_mask);
+#endif
+
 bool dce_transform_get_optimal_number_of_taps(
 	struct transform *xfm,
 	struct scaler_data *scl_data,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 49380ed3aeae..0603ddca7bd0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -720,6 +720,7 @@ void dce110_edp_wait_for_hpd_ready(
 	struct dc_context *ctx = link->ctx;
 	struct graphics_object_id connector = link->link_enc->connector;
 	struct gpio *hpd;
+	struct dc_sink *sink = link->local_sink;
 	bool edp_hpd_high = false;
 	uint32_t time_elapsed = 0;
 	uint32_t timeout = power_up ?
@@ -752,6 +753,14 @@ void dce110_edp_wait_for_hpd_ready(
 		return;
 	}
 
+	if (sink != NULL) {
+		if (sink->edid_caps.panel_patch.extra_t3_ms > 0) {
+			int extra_t3_in_ms = sink->edid_caps.panel_patch.extra_t3_ms;
+
+			msleep(extra_t3_in_ms);
+		}
+	}
+
 	dal_gpio_open(hpd, GPIO_MODE_INTERRUPT);
 
 	/* wait until timeout or panel detected */
@@ -842,6 +851,17 @@ void dce110_edp_power_control(
 		cntl.coherent = false;
 		cntl.lanes_number = LANE_COUNT_FOUR;
 		cntl.hpd_sel = link->link_enc->hpd_source;
+
+		if (ctx->dc->ctx->dmub_srv &&
+				ctx->dc->debug.dmub_command_table) {
+			if (cntl.action == TRANSMITTER_CONTROL_POWER_ON)
+				bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios,
+						LVTMA_CONTROL_POWER_ON);
+			else
+				bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios,
+						LVTMA_CONTROL_POWER_OFF);
+		}
+
 		bp_result = link_transmitter_control(ctx->dc_bios, &cntl);
 
 		if (!power_up)
@@ -919,8 +939,21 @@ void dce110_edp_backlight_control(
 		/*edp 1.2*/
 	if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON)
 		edp_receiver_ready_T7(link);
+
+	if (ctx->dc->ctx->dmub_srv &&
+			ctx->dc->debug.dmub_command_table) {
+		if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON)
+			ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios,
+					LVTMA_CONTROL_LCD_BLON);
+		else
+			ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios,
+					LVTMA_CONTROL_LCD_BLOFF);
+	}
+
 	link_transmitter_control(ctx->dc_bios, &cntl);
 
+
+
 	if (enable && link->dpcd_sink_ext_caps.bits.oled)
 		msleep(OLED_POST_T7_DELAY);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 5d83e8174005..0853bc9917c7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -1017,7 +1017,7 @@ enum dc_status dce112_add_stream_to_ctx(
 		struct dc_state *new_ctx,
 		struct dc_stream_state *dc_stream)
 {
-	enum dc_status result = DC_ERROR_UNEXPECTED;
+	enum dc_status result;
 
 	result = resource_map_pool_resources(dc, new_ctx, dc_stream);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
new file mode 100644
index 000000000000..7036c3bd0f87
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
@@ -0,0 +1,34 @@
+#
+# Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
+# Makefile for the 'controller' sub-component of DAL.
+# It provides the control and status of HW CRTC block.
+
+DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \
+	dce60_resource.o
+
+AMD_DAL_DCE60 = $(addprefix $(AMDDALPATH)/dc/dce60/,$(DCE60))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_DCE60)
+
+
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.c
new file mode 100644
index 000000000000..920c7ae29d53
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.c
@@ -0,0 +1,432 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "dc.h"
+#include "core_types.h"
+#include "dce60_hw_sequencer.h"
+
+#include "dce/dce_hwseq.h"
+#include "dce110/dce110_hw_sequencer.h"
+#include "dce100/dce100_hw_sequencer.h"
+
+/* include DCE6 register header files */
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+#define DC_LOGGER_INIT()
+
+/*******************************************************************************
+ * Private definitions
+ ******************************************************************************/
+
+/***************************PIPE_CONTROL***********************************/
+
+/*
+ *  Check if FBC can be enabled
+ */
+static bool dce60_should_enable_fbc(struct dc *dc,
+		struct dc_state *context,
+		uint32_t *pipe_idx)
+{
+	uint32_t i;
+	struct pipe_ctx *pipe_ctx = NULL;
+	struct resource_context *res_ctx = &context->res_ctx;
+	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
+
+
+	ASSERT(dc->fbc_compressor);
+
+	/* FBC memory should be allocated */
+	if (!dc->ctx->fbc_gpu_addr)
+		return false;
+
+	/* Only supports single display */
+	if (context->stream_count != 1)
+		return false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (res_ctx->pipe_ctx[i].stream) {
+
+			pipe_ctx = &res_ctx->pipe_ctx[i];
+
+			if (!pipe_ctx)
+				continue;
+
+			/* fbc not applicable on underlay pipe */
+			if (pipe_ctx->pipe_idx != underlay_idx) {
+				*pipe_idx = i;
+				break;
+			}
+		}
+	}
+
+	if (i == dc->res_pool->pipe_count)
+		return false;
+
+	if (!pipe_ctx->stream->link)
+		return false;
+
+	/* Only supports eDP */
+	if (pipe_ctx->stream->link->connector_signal != SIGNAL_TYPE_EDP)
+		return false;
+
+	/* PSR should not be enabled */
+	if (pipe_ctx->stream->link->psr_settings.psr_feature_enabled)
+		return false;
+
+	/* Nothing to compress */
+	if (!pipe_ctx->plane_state)
+		return false;
+
+	/* Only for non-linear tiling */
+	if (pipe_ctx->plane_state->tiling_info.gfx8.array_mode == DC_ARRAY_LINEAR_GENERAL)
+		return false;
+
+	return true;
+}
+
+/*
+ *  Enable FBC
+ */
+static void dce60_enable_fbc(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	uint32_t pipe_idx = 0;
+
+	if (dce60_should_enable_fbc(dc, context, &pipe_idx)) {
+		/* Program GRPH COMPRESSED ADDRESS and PITCH */
+		struct compr_addr_and_pitch_params params = {0, 0, 0};
+		struct compressor *compr = dc->fbc_compressor;
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
+
+		params.source_view_width = pipe_ctx->stream->timing.h_addressable;
+		params.source_view_height = pipe_ctx->stream->timing.v_addressable;
+		params.inst = pipe_ctx->stream_res.tg->inst;
+		compr->compr_surface_address.quad_part = dc->ctx->fbc_gpu_addr;
+
+		compr->funcs->surface_address_and_pitch(compr, &params);
+		compr->funcs->set_fbc_invalidation_triggers(compr, 1);
+
+		compr->funcs->enable_fbc(compr, &params);
+	}
+}
+
+
+/*******************************************************************************
+ * Front End programming
+ ******************************************************************************/
+
+static void dce60_set_default_colors(struct pipe_ctx *pipe_ctx)
+{
+	struct default_adjustment default_adjust = { 0 };
+
+	default_adjust.force_hw_default = false;
+	default_adjust.in_color_space = pipe_ctx->plane_state->color_space;
+	default_adjust.out_color_space = pipe_ctx->stream->output_color_space;
+	default_adjust.csc_adjust_type = GRAPHICS_CSC_ADJUST_TYPE_SW;
+	default_adjust.surface_pixel_format = pipe_ctx->plane_res.scl_data.format;
+
+	/* display color depth */
+	default_adjust.color_depth =
+		pipe_ctx->stream->timing.display_color_depth;
+
+	/* Lb color depth */
+	default_adjust.lb_color_depth = pipe_ctx->plane_res.scl_data.lb_params.depth;
+
+	pipe_ctx->plane_res.xfm->funcs->opp_set_csc_default(
+					pipe_ctx->plane_res.xfm, &default_adjust);
+}
+
+/*******************************************************************************
+ * In order to turn on surface we will program
+ * CRTC
+ *
+ * DCE6 has no bottom_pipe and no Blender HW
+ * We need to set 'blank_target' to false in order to turn on the display
+ *
+ * |-----------|------------|---------|
+ * |curr pipe  | set_blank  |         |
+ * |Surface    |blank_target|  CRCT   |
+ * |visibility |  argument  |         |
+ * |-----------|------------|---------|
+ * |    off    |   true     | blank   |
+ * |    on     |   false    | unblank |
+ * |-----------|------------|---------|
+ *
+ ******************************************************************************/
+static void dce60_program_surface_visibility(const struct dc *dc,
+		struct pipe_ctx *pipe_ctx)
+{
+	bool blank_target = false;
+
+	/* DCE6 has no bottom_pipe and no Blender HW */
+
+	if (!pipe_ctx->plane_state->visible)
+		blank_target = true;
+
+	/* DCE6 skip dce_set_blender_mode() but then proceed to 'unblank' CRTC */
+	pipe_ctx->stream_res.tg->funcs->set_blank(pipe_ctx->stream_res.tg, blank_target);
+
+}
+
+
+static void dce60_get_surface_visual_confirm_color(const struct pipe_ctx *pipe_ctx,
+		struct tg_color *color)
+{
+	uint32_t color_value = MAX_TG_COLOR_VALUE * (4 - pipe_ctx->stream_res.tg->inst) / 4;
+
+	switch (pipe_ctx->plane_res.scl_data.format) {
+	case PIXEL_FORMAT_ARGB8888:
+		/* set boarder color to red */
+		color->color_r_cr = color_value;
+		break;
+
+	case PIXEL_FORMAT_ARGB2101010:
+		/* set boarder color to blue */
+		color->color_b_cb = color_value;
+		break;
+	case PIXEL_FORMAT_420BPP8:
+		/* set boarder color to green */
+		color->color_g_y = color_value;
+		break;
+	case PIXEL_FORMAT_420BPP10:
+		/* set boarder color to yellow */
+		color->color_g_y = color_value;
+		color->color_r_cr = color_value;
+		break;
+	case PIXEL_FORMAT_FP16:
+		/* set boarder color to white */
+		color->color_r_cr = color_value;
+		color->color_b_cb = color_value;
+		color->color_g_y = color_value;
+		break;
+	default:
+		break;
+	}
+}
+
+static void dce60_program_scaler(const struct dc *dc,
+		const struct pipe_ctx *pipe_ctx)
+{
+	struct tg_color color = {0};
+
+	/* DCE6 skips DCN TOFPGA check for transform_set_pixel_storage_depth == NULL */
+
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE)
+		dce60_get_surface_visual_confirm_color(pipe_ctx, &color);
+	else
+		color_space_to_black_color(dc,
+				pipe_ctx->stream->output_color_space,
+				&color);
+
+	pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth(
+		pipe_ctx->plane_res.xfm,
+		pipe_ctx->plane_res.scl_data.lb_params.depth,
+		&pipe_ctx->stream->bit_depth_params);
+
+	if (pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color) {
+		/*
+		 * The way 420 is packed, 2 channels carry Y component, 1 channel
+		 * alternate between Cb and Cr, so both channels need the pixel
+		 * value for Y
+		 */
+		if (pipe_ctx->stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			color.color_r_cr = color.color_g_y;
+
+		pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color(
+				pipe_ctx->stream_res.tg,
+				&color);
+	}
+
+	pipe_ctx->plane_res.xfm->funcs->transform_set_scaler(pipe_ctx->plane_res.xfm,
+		&pipe_ctx->plane_res.scl_data);
+}
+
+static void
+dce60_program_front_end_for_pipe(
+		struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	struct mem_input *mi = pipe_ctx->plane_res.mi;
+	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
+	struct xfm_grph_csc_adjustment adjust;
+	struct out_csc_color_matrix tbl_entry;
+	unsigned int i;
+	struct dce_hwseq *hws = dc->hwseq;
+
+	DC_LOGGER_INIT();
+	memset(&tbl_entry, 0, sizeof(tbl_entry));
+
+	memset(&adjust, 0, sizeof(adjust));
+	adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
+
+	dce_enable_fe_clock(dc->hwseq, mi->inst, true);
+
+	dce60_set_default_colors(pipe_ctx);
+	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment
+			== true) {
+		tbl_entry.color_space =
+			pipe_ctx->stream->output_color_space;
+
+		for (i = 0; i < 12; i++)
+			tbl_entry.regval[i] =
+			pipe_ctx->stream->csc_color_matrix.matrix[i];
+
+		pipe_ctx->plane_res.xfm->funcs->opp_set_csc_adjustment
+				(pipe_ctx->plane_res.xfm, &tbl_entry);
+	}
+
+	if (pipe_ctx->stream->gamut_remap_matrix.enable_remap == true) {
+		adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
+
+		for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
+			adjust.temperature_matrix[i] =
+				pipe_ctx->stream->gamut_remap_matrix.matrix[i];
+	}
+
+	pipe_ctx->plane_res.xfm->funcs->transform_set_gamut_remap(pipe_ctx->plane_res.xfm, &adjust);
+
+	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->bottom_pipe != 0;
+
+	dce60_program_scaler(dc, pipe_ctx);
+
+	mi->funcs->mem_input_program_surface_config(
+			mi,
+			plane_state->format,
+			&plane_state->tiling_info,
+			&plane_state->plane_size,
+			plane_state->rotation,
+			NULL,
+			false);
+	if (mi->funcs->set_blank)
+		mi->funcs->set_blank(mi, pipe_ctx->plane_state->visible);
+
+	if (dc->config.gpu_vm_support)
+		mi->funcs->mem_input_program_pte_vm(
+				pipe_ctx->plane_res.mi,
+				plane_state->format,
+				&plane_state->tiling_info,
+				plane_state->rotation);
+
+	/* Moved programming gamma from dc to hwss */
+	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
+			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
+			pipe_ctx->plane_state->update_flags.bits.gamma_change)
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
+
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
+
+	DC_LOG_SURFACE(
+			"Pipe:%d %p: addr hi:0x%x, "
+			"addr low:0x%x, "
+			"src: %d, %d, %d,"
+			" %d; dst: %d, %d, %d, %d;"
+			"clip: %d, %d, %d, %d\n",
+			pipe_ctx->pipe_idx,
+			(void *) pipe_ctx->plane_state,
+			pipe_ctx->plane_state->address.grph.addr.high_part,
+			pipe_ctx->plane_state->address.grph.addr.low_part,
+			pipe_ctx->plane_state->src_rect.x,
+			pipe_ctx->plane_state->src_rect.y,
+			pipe_ctx->plane_state->src_rect.width,
+			pipe_ctx->plane_state->src_rect.height,
+			pipe_ctx->plane_state->dst_rect.x,
+			pipe_ctx->plane_state->dst_rect.y,
+			pipe_ctx->plane_state->dst_rect.width,
+			pipe_ctx->plane_state->dst_rect.height,
+			pipe_ctx->plane_state->clip_rect.x,
+			pipe_ctx->plane_state->clip_rect.y,
+			pipe_ctx->plane_state->clip_rect.width,
+			pipe_ctx->plane_state->clip_rect.height);
+
+	DC_LOG_SURFACE(
+			"Pipe %d: width, height, x, y\n"
+			"viewport:%d, %d, %d, %d\n"
+			"recout:  %d, %d, %d, %d\n",
+			pipe_ctx->pipe_idx,
+			pipe_ctx->plane_res.scl_data.viewport.width,
+			pipe_ctx->plane_res.scl_data.viewport.height,
+			pipe_ctx->plane_res.scl_data.viewport.x,
+			pipe_ctx->plane_res.scl_data.viewport.y,
+			pipe_ctx->plane_res.scl_data.recout.width,
+			pipe_ctx->plane_res.scl_data.recout.height,
+			pipe_ctx->plane_res.scl_data.recout.x,
+			pipe_ctx->plane_res.scl_data.recout.y);
+}
+
+static void dce60_apply_ctx_for_surface(
+		struct dc *dc,
+		const struct dc_stream_state *stream,
+		int num_planes,
+		struct dc_state *context)
+{
+	int i;
+
+	if (num_planes == 0)
+		return;
+
+	if (dc->fbc_compressor)
+		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream != stream)
+			continue;
+
+		/* Need to allocate mem before program front end for Fiji */
+		pipe_ctx->plane_res.mi->funcs->allocate_mem_input(
+				pipe_ctx->plane_res.mi,
+				pipe_ctx->stream->timing.h_total,
+				pipe_ctx->stream->timing.v_total,
+				pipe_ctx->stream->timing.pix_clk_100hz / 10,
+				context->stream_count);
+
+		dce60_program_front_end_for_pipe(dc, pipe_ctx);
+
+		dc->hwss.update_plane_addr(dc, pipe_ctx);
+
+		dce60_program_surface_visibility(dc, pipe_ctx);
+
+	}
+
+	if (dc->fbc_compressor)
+		dce60_enable_fbc(dc, context);
+}
+
+void dce60_hw_sequencer_construct(struct dc *dc)
+{
+	dce110_hw_sequencer_construct(dc);
+
+	dc->hwseq->funcs.enable_display_power_gating = dce100_enable_display_power_gating;
+	dc->hwss.apply_ctx_for_surface = dce60_apply_ctx_for_surface;
+	dc->hwss.cursor_lock = dce60_pipe_control_lock;
+	dc->hwss.pipe_control_lock = dce60_pipe_control_lock;
+	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
+	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.h
new file mode 100644
index 000000000000..f3b2d8b60d5b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_hw_sequencer.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HWSS_DCE60_H__
+#define __DC_HWSS_DCE60_H__
+
+#include "core_types.h"
+#include "hw_sequencer_private.h"
+
+struct dc;
+
+void dce60_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_HWSS_DCE60_H__ */
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c
new file mode 100644
index 000000000000..5a5a9cb77acb
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c
@@ -0,0 +1,1527 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/slab.h>
+
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+#include "dm_services.h"
+
+#include "link_encoder.h"
+#include "stream_encoder.h"
+
+#include "resource.h"
+#include "include/irq_service_interface.h"
+#include "irq/dce60/irq_service_dce60.h"
+#include "dce110/dce110_timing_generator.h"
+#include "dce110/dce110_resource.h"
+#include "dce60/dce60_timing_generator.h"
+#include "dce/dce_mem_input.h"
+#include "dce/dce_link_encoder.h"
+#include "dce/dce_stream_encoder.h"
+#include "dce/dce_ipp.h"
+#include "dce/dce_transform.h"
+#include "dce/dce_opp.h"
+#include "dce/dce_clock_source.h"
+#include "dce/dce_audio.h"
+#include "dce/dce_hwseq.h"
+#include "dce60/dce60_hw_sequencer.h"
+#include "dce100/dce100_resource.h"
+#include "dce/dce_panel_cntl.h"
+
+#include "reg_helper.h"
+
+#include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
+#include "dce/dce_abm.h"
+#include "dce/dce_i2c.h"
+/* TODO remove this include */
+
+#ifndef mmMC_HUB_RDREQ_DMIF_LIMIT
+#include "gmc/gmc_6_0_d.h"
+#include "gmc/gmc_6_0_sh_mask.h"
+#endif
+
+#ifndef mmDP_DPHY_INTERNAL_CTRL
+#define mmDP_DPHY_INTERNAL_CTRL                         0x1CDE
+#define mmDP0_DP_DPHY_INTERNAL_CTRL                     0x1CDE
+#define mmDP1_DP_DPHY_INTERNAL_CTRL                     0x1FDE
+#define mmDP2_DP_DPHY_INTERNAL_CTRL                     0x42DE
+#define mmDP3_DP_DPHY_INTERNAL_CTRL                     0x45DE
+#define mmDP4_DP_DPHY_INTERNAL_CTRL                     0x48DE
+#define mmDP5_DP_DPHY_INTERNAL_CTRL                     0x4BDE
+#endif
+
+
+#ifndef mmBIOS_SCRATCH_2
+	#define mmBIOS_SCRATCH_2 0x05CB
+	#define mmBIOS_SCRATCH_3 0x05CC
+	#define mmBIOS_SCRATCH_6 0x05CF
+#endif
+
+#ifndef mmDP_DPHY_FAST_TRAINING
+	#define mmDP_DPHY_FAST_TRAINING                         0x1CCE
+	#define mmDP0_DP_DPHY_FAST_TRAINING                     0x1CCE
+	#define mmDP1_DP_DPHY_FAST_TRAINING                     0x1FCE
+	#define mmDP2_DP_DPHY_FAST_TRAINING                     0x42CE
+	#define mmDP3_DP_DPHY_FAST_TRAINING                     0x45CE
+	#define mmDP4_DP_DPHY_FAST_TRAINING                     0x48CE
+	#define mmDP5_DP_DPHY_FAST_TRAINING                     0x4BCE
+#endif
+
+
+#ifndef mmHPD_DC_HPD_CONTROL
+	#define mmHPD_DC_HPD_CONTROL                            0x189A
+	#define mmHPD0_DC_HPD_CONTROL                           0x189A
+	#define mmHPD1_DC_HPD_CONTROL                           0x18A2
+	#define mmHPD2_DC_HPD_CONTROL                           0x18AA
+	#define mmHPD3_DC_HPD_CONTROL                           0x18B2
+	#define mmHPD4_DC_HPD_CONTROL                           0x18BA
+	#define mmHPD5_DC_HPD_CONTROL                           0x18C2
+#endif
+
+#define DCE11_DIG_FE_CNTL 0x4a00
+#define DCE11_DIG_BE_CNTL 0x4a47
+#define DCE11_DP_SEC 0x4ac3
+
+static const struct dce110_timing_generator_offsets dce60_tg_offsets[] = {
+		{
+			.crtc = (mmCRTC0_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp =  (mmGRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG0_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		},
+		{
+			.crtc = (mmCRTC1_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp = (mmDCP1_GRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG1_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		},
+		{
+			.crtc = (mmCRTC2_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp = (mmDCP2_GRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG2_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		},
+		{
+			.crtc = (mmCRTC3_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp = (mmDCP3_GRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG3_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		},
+		{
+			.crtc = (mmCRTC4_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp = (mmDCP4_GRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG4_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		},
+		{
+			.crtc = (mmCRTC5_CRTC_CONTROL - mmCRTC_CONTROL),
+			.dcp = (mmDCP5_GRPH_CONTROL - mmGRPH_CONTROL),
+			.dmif = (mmDMIF_PG5_DPG_PIPE_ARBITRATION_CONTROL3
+					- mmDPG_PIPE_ARBITRATION_CONTROL3),
+		}
+};
+
+/* set register offset */
+#define SR(reg_name)\
+	.reg_name = mm ## reg_name
+
+/* set register offset with instance */
+#define SRI(reg_name, block, id)\
+	.reg_name = mm ## block ## id ## _ ## reg_name
+
+#define ipp_regs(id)\
+[id] = {\
+		IPP_COMMON_REG_LIST_DCE_BASE(id)\
+}
+
+static const struct dce_ipp_registers ipp_regs[] = {
+		ipp_regs(0),
+		ipp_regs(1),
+		ipp_regs(2),
+		ipp_regs(3),
+		ipp_regs(4),
+		ipp_regs(5)
+};
+
+static const struct dce_ipp_shift ipp_shift = {
+		IPP_DCE60_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
+};
+
+static const struct dce_ipp_mask ipp_mask = {
+		IPP_DCE60_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
+};
+
+#define transform_regs(id)\
+[id] = {\
+		XFM_COMMON_REG_LIST_DCE60(id)\
+}
+
+static const struct dce_transform_registers xfm_regs[] = {
+		transform_regs(0),
+		transform_regs(1),
+		transform_regs(2),
+		transform_regs(3),
+		transform_regs(4),
+		transform_regs(5)
+};
+
+static const struct dce_transform_shift xfm_shift = {
+		XFM_COMMON_MASK_SH_LIST_DCE60(__SHIFT)
+};
+
+static const struct dce_transform_mask xfm_mask = {
+		XFM_COMMON_MASK_SH_LIST_DCE60(_MASK)
+};
+
+#define aux_regs(id)\
+[id] = {\
+	AUX_REG_LIST(id)\
+}
+
+static const struct dce110_link_enc_aux_registers link_enc_aux_regs[] = {
+	aux_regs(0),
+	aux_regs(1),
+	aux_regs(2),
+	aux_regs(3),
+	aux_regs(4),
+	aux_regs(5)
+};
+
+#define hpd_regs(id)\
+[id] = {\
+	HPD_REG_LIST(id)\
+}
+
+static const struct dce110_link_enc_hpd_registers link_enc_hpd_regs[] = {
+		hpd_regs(0),
+		hpd_regs(1),
+		hpd_regs(2),
+		hpd_regs(3),
+		hpd_regs(4),
+		hpd_regs(5)
+};
+
+#define link_regs(id)\
+[id] = {\
+	LE_DCE60_REG_LIST(id)\
+}
+
+static const struct dce110_link_enc_registers link_enc_regs[] = {
+	link_regs(0),
+	link_regs(1),
+	link_regs(2),
+	link_regs(3),
+	link_regs(4),
+	link_regs(5)
+};
+
+#define stream_enc_regs(id)\
+[id] = {\
+	SE_COMMON_REG_LIST_DCE_BASE(id),\
+	.AFMT_CNTL = 0,\
+}
+
+static const struct dce110_stream_enc_registers stream_enc_regs[] = {
+	stream_enc_regs(0),
+	stream_enc_regs(1),
+	stream_enc_regs(2),
+	stream_enc_regs(3),
+	stream_enc_regs(4),
+	stream_enc_regs(5)
+};
+
+static const struct dce_stream_encoder_shift se_shift = {
+		SE_COMMON_MASK_SH_LIST_DCE80_100(__SHIFT)
+};
+
+static const struct dce_stream_encoder_mask se_mask = {
+		SE_COMMON_MASK_SH_LIST_DCE80_100(_MASK)
+};
+
+static const struct dce_panel_cntl_registers panel_cntl_regs[] = {
+	{ DCE_PANEL_CNTL_REG_LIST() }
+};
+
+static const struct dce_panel_cntl_shift panel_cntl_shift = {
+	DCE_PANEL_CNTL_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce_panel_cntl_mask panel_cntl_mask = {
+	DCE_PANEL_CNTL_MASK_SH_LIST(_MASK)
+};
+
+#define opp_regs(id)\
+[id] = {\
+	OPP_DCE_60_REG_LIST(id),\
+}
+
+static const struct dce_opp_registers opp_regs[] = {
+	opp_regs(0),
+	opp_regs(1),
+	opp_regs(2),
+	opp_regs(3),
+	opp_regs(4),
+	opp_regs(5)
+};
+
+static const struct dce_opp_shift opp_shift = {
+	OPP_COMMON_MASK_SH_LIST_DCE_60(__SHIFT)
+};
+
+static const struct dce_opp_mask opp_mask = {
+	OPP_COMMON_MASK_SH_LIST_DCE_60(_MASK)
+};
+
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE10_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE10_AUX_MASK_SH_LIST(_MASK)
+};
+
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
+#define audio_regs(id)\
+[id] = {\
+	AUD_COMMON_REG_LIST(id)\
+}
+
+static const struct dce_audio_registers audio_regs[] = {
+	audio_regs(0),
+	audio_regs(1),
+	audio_regs(2),
+	audio_regs(3),
+	audio_regs(4),
+	audio_regs(5),
+};
+
+static const struct dce_audio_shift audio_shift = {
+		AUD_DCE60_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce_audio_mask audio_mask = {
+		AUD_DCE60_MASK_SH_LIST(_MASK)
+};
+
+#define clk_src_regs(id)\
+[id] = {\
+	CS_COMMON_REG_LIST_DCE_80(id),\
+}
+
+
+static const struct dce110_clk_src_regs clk_src_regs[] = {
+	clk_src_regs(0),
+	clk_src_regs(1),
+	clk_src_regs(2)
+};
+
+static const struct dce110_clk_src_shift cs_shift = {
+		CS_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
+};
+
+static const struct dce110_clk_src_mask cs_mask = {
+		CS_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
+};
+
+static const struct bios_registers bios_regs = {
+	.BIOS_SCRATCH_3 = mmBIOS_SCRATCH_3,
+	.BIOS_SCRATCH_6 = mmBIOS_SCRATCH_6
+};
+
+static const struct resource_caps res_cap = {
+		.num_timing_generator = 6,
+		.num_audio = 6,
+		.num_stream_encoder = 6,
+		.num_pll = 2,
+		.num_ddc = 6,
+};
+
+static const struct resource_caps res_cap_61 = {
+		.num_timing_generator = 4,
+		.num_audio = 6,
+		.num_stream_encoder = 6,
+		.num_pll = 3,
+		.num_ddc = 6,
+};
+
+static const struct resource_caps res_cap_64 = {
+		.num_timing_generator = 2,
+		.num_audio = 2,
+		.num_stream_encoder = 2,
+		.num_pll = 2,
+		.num_ddc = 2,
+};
+
+static const struct dc_plane_cap plane_cap = {
+	.type = DC_PLANE_TYPE_DCE_RGB,
+
+	.pixel_format_support = {
+			.argb8888 = true,
+			.nv12 = false,
+			.fp16 = false
+	},
+
+	.max_upscale_factor = {
+			.argb8888 = 16000,
+			.nv12 = 1,
+			.fp16 = 1
+	},
+
+	.max_downscale_factor = {
+			.argb8888 = 250,
+			.nv12 = 1,
+			.fp16 = 1
+	}
+};
+
+static const struct dce_dmcu_registers dmcu_regs = {
+		DMCU_DCE60_REG_LIST()
+};
+
+static const struct dce_dmcu_shift dmcu_shift = {
+		DMCU_MASK_SH_LIST_DCE60(__SHIFT)
+};
+
+static const struct dce_dmcu_mask dmcu_mask = {
+		DMCU_MASK_SH_LIST_DCE60(_MASK)
+};
+static const struct dce_abm_registers abm_regs = {
+		ABM_DCE110_COMMON_REG_LIST()
+};
+
+static const struct dce_abm_shift abm_shift = {
+		ABM_MASK_SH_LIST_DCE110(__SHIFT)
+};
+
+static const struct dce_abm_mask abm_mask = {
+		ABM_MASK_SH_LIST_DCE110(_MASK)
+};
+
+#define CTX  ctx
+#define REG(reg) mm ## reg
+
+#ifndef mmCC_DC_HDMI_STRAPS
+#define mmCC_DC_HDMI_STRAPS 0x1918
+#define CC_DC_HDMI_STRAPS__HDMI_DISABLE_MASK 0x40
+#define CC_DC_HDMI_STRAPS__HDMI_DISABLE__SHIFT 0x6
+#define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER_MASK 0x700
+#define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER__SHIFT 0x8
+#endif
+
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
+static void read_dce_straps(
+	struct dc_context *ctx,
+	struct resource_straps *straps)
+{
+	REG_GET_2(CC_DC_HDMI_STRAPS,
+			HDMI_DISABLE, &straps->hdmi_disable,
+			AUDIO_STREAM_NUMBER, &straps->audio_stream_number);
+
+	REG_GET(DC_PINSTRAPS, DC_PINSTRAPS_AUDIO, &straps->dc_pinstraps_audio);
+}
+
+static struct audio *create_audio(
+		struct dc_context *ctx, unsigned int inst)
+{
+	return dce60_audio_create(ctx, inst,
+			&audio_regs[inst], &audio_shift, &audio_mask);
+}
+
+static struct timing_generator *dce60_timing_generator_create(
+		struct dc_context *ctx,
+		uint32_t instance,
+		const struct dce110_timing_generator_offsets *offsets)
+{
+	struct dce110_timing_generator *tg110 =
+		kzalloc(sizeof(struct dce110_timing_generator), GFP_KERNEL);
+
+	if (!tg110)
+		return NULL;
+
+	dce60_timing_generator_construct(tg110, ctx, instance, offsets);
+	return &tg110->base;
+}
+
+static struct output_pixel_processor *dce60_opp_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct dce110_opp *opp =
+		kzalloc(sizeof(struct dce110_opp), GFP_KERNEL);
+
+	if (!opp)
+		return NULL;
+
+	dce60_opp_construct(opp,
+			     ctx, inst, &opp_regs[inst], &opp_shift, &opp_mask);
+	return &opp->base;
+}
+
+struct dce_aux *dce60_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
+
+	return &aux_engine->base;
+}
+#define i2c_inst_regs(id) { I2C_HW_ENGINE_COMMON_REG_LIST(id) }
+
+static const struct dce_i2c_registers i2c_hw_regs[] = {
+		i2c_inst_regs(1),
+		i2c_inst_regs(2),
+		i2c_inst_regs(3),
+		i2c_inst_regs(4),
+		i2c_inst_regs(5),
+		i2c_inst_regs(6),
+};
+
+static const struct dce_i2c_shift i2c_shifts = {
+		I2C_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
+};
+
+static const struct dce_i2c_mask i2c_masks = {
+		I2C_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
+};
+
+struct dce_i2c_hw *dce60_i2c_hw_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct dce_i2c_hw *dce_i2c_hw =
+		kzalloc(sizeof(struct dce_i2c_hw), GFP_KERNEL);
+
+	if (!dce_i2c_hw)
+		return NULL;
+
+	dce_i2c_hw_construct(dce_i2c_hw, ctx, inst,
+				    &i2c_hw_regs[inst], &i2c_shifts, &i2c_masks);
+
+	return dce_i2c_hw;
+}
+
+struct dce_i2c_sw *dce60_i2c_sw_create(
+	struct dc_context *ctx)
+{
+	struct dce_i2c_sw *dce_i2c_sw =
+		kzalloc(sizeof(struct dce_i2c_sw), GFP_KERNEL);
+
+	if (!dce_i2c_sw)
+		return NULL;
+
+	dce_i2c_sw_construct(dce_i2c_sw, ctx);
+
+	return dce_i2c_sw;
+}
+static struct stream_encoder *dce60_stream_encoder_create(
+	enum engine_id eng_id,
+	struct dc_context *ctx)
+{
+	struct dce110_stream_encoder *enc110 =
+		kzalloc(sizeof(struct dce110_stream_encoder), GFP_KERNEL);
+
+	if (!enc110)
+		return NULL;
+
+	dce110_stream_encoder_construct(enc110, ctx, ctx->dc_bios, eng_id,
+					&stream_enc_regs[eng_id],
+					&se_shift, &se_mask);
+	return &enc110->base;
+}
+
+#define SRII(reg_name, block, id)\
+	.reg_name[id] = mm ## block ## id ## _ ## reg_name
+
+static const struct dce_hwseq_registers hwseq_reg = {
+		HWSEQ_DCE6_REG_LIST()
+};
+
+static const struct dce_hwseq_shift hwseq_shift = {
+		HWSEQ_DCE6_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce_hwseq_mask hwseq_mask = {
+		HWSEQ_DCE6_MASK_SH_LIST(_MASK)
+};
+
+static struct dce_hwseq *dce60_hwseq_create(
+	struct dc_context *ctx)
+{
+	struct dce_hwseq *hws = kzalloc(sizeof(struct dce_hwseq), GFP_KERNEL);
+
+	if (hws) {
+		hws->ctx = ctx;
+		hws->regs = &hwseq_reg;
+		hws->shifts = &hwseq_shift;
+		hws->masks = &hwseq_mask;
+	}
+	return hws;
+}
+
+static const struct resource_create_funcs res_create_funcs = {
+	.read_dce_straps = read_dce_straps,
+	.create_audio = create_audio,
+	.create_stream_encoder = dce60_stream_encoder_create,
+	.create_hwseq = dce60_hwseq_create,
+};
+
+#define mi_inst_regs(id) { \
+	MI_DCE6_REG_LIST(id), \
+	.MC_HUB_RDREQ_DMIF_LIMIT = mmMC_HUB_RDREQ_DMIF_LIMIT \
+}
+static const struct dce_mem_input_registers mi_regs[] = {
+		mi_inst_regs(0),
+		mi_inst_regs(1),
+		mi_inst_regs(2),
+		mi_inst_regs(3),
+		mi_inst_regs(4),
+		mi_inst_regs(5),
+};
+
+static const struct dce_mem_input_shift mi_shifts = {
+		MI_DCE6_MASK_SH_LIST(__SHIFT),
+		.ENABLE = MC_HUB_RDREQ_DMIF_LIMIT__ENABLE__SHIFT
+};
+
+static const struct dce_mem_input_mask mi_masks = {
+		MI_DCE6_MASK_SH_LIST(_MASK),
+		.ENABLE = MC_HUB_RDREQ_DMIF_LIMIT__ENABLE_MASK
+};
+
+static struct mem_input *dce60_mem_input_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct dce_mem_input *dce_mi = kzalloc(sizeof(struct dce_mem_input),
+					       GFP_KERNEL);
+
+	if (!dce_mi) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dce60_mem_input_construct(dce_mi, ctx, inst, &mi_regs[inst], &mi_shifts, &mi_masks);
+	dce_mi->wa.single_head_rdreq_dmif_limit = 2;
+	return &dce_mi->base;
+}
+
+static void dce60_transform_destroy(struct transform **xfm)
+{
+	kfree(TO_DCE_TRANSFORM(*xfm));
+	*xfm = NULL;
+}
+
+static struct transform *dce60_transform_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct dce_transform *transform =
+		kzalloc(sizeof(struct dce_transform), GFP_KERNEL);
+
+	if (!transform)
+		return NULL;
+
+	dce60_transform_construct(transform, ctx, inst,
+				&xfm_regs[inst], &xfm_shift, &xfm_mask);
+	transform->prescaler_on = false;
+	return &transform->base;
+}
+
+static const struct encoder_feature_support link_enc_feature = {
+		.max_hdmi_deep_color = COLOR_DEPTH_121212,
+		.max_hdmi_pixel_clock = 297000,
+		.flags.bits.IS_HBR2_CAPABLE = true,
+		.flags.bits.IS_TPS3_CAPABLE = true
+};
+
+struct link_encoder *dce60_link_encoder_create(
+	const struct encoder_init_data *enc_init_data)
+{
+	struct dce110_link_encoder *enc110 =
+		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
+
+	if (!enc110)
+		return NULL;
+
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
+	dce60_link_encoder_construct(enc110,
+				      enc_init_data,
+				      &link_enc_feature,
+				      &link_enc_regs[link_regs_id],
+				      &link_enc_aux_regs[enc_init_data->channel - 1],
+				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+	return &enc110->base;
+}
+
+static struct panel_cntl *dce60_panel_cntl_create(const struct panel_cntl_init_data *init_data)
+{
+	struct dce_panel_cntl *panel_cntl =
+		kzalloc(sizeof(struct dce_panel_cntl), GFP_KERNEL);
+
+	if (!panel_cntl)
+		return NULL;
+
+	dce_panel_cntl_construct(panel_cntl,
+			init_data,
+			&panel_cntl_regs[init_data->inst],
+			&panel_cntl_shift,
+			&panel_cntl_mask);
+
+	return &panel_cntl->base;
+}
+
+struct clock_source *dce60_clock_source_create(
+	struct dc_context *ctx,
+	struct dc_bios *bios,
+	enum clock_source_id id,
+	const struct dce110_clk_src_regs *regs,
+	bool dp_clk_src)
+{
+	struct dce110_clk_src *clk_src =
+		kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL);
+
+	if (!clk_src)
+		return NULL;
+
+	if (dce110_clk_src_construct(clk_src, ctx, bios, id,
+			regs, &cs_shift, &cs_mask)) {
+		clk_src->base.dp_clk_src = dp_clk_src;
+		return &clk_src->base;
+	}
+
+	kfree(clk_src);
+	BREAK_TO_DEBUGGER();
+	return NULL;
+}
+
+void dce60_clock_source_destroy(struct clock_source **clk_src)
+{
+	kfree(TO_DCE110_CLK_SRC(*clk_src));
+	*clk_src = NULL;
+}
+
+static struct input_pixel_processor *dce60_ipp_create(
+	struct dc_context *ctx, uint32_t inst)
+{
+	struct dce_ipp *ipp = kzalloc(sizeof(struct dce_ipp), GFP_KERNEL);
+
+	if (!ipp) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dce60_ipp_construct(ipp, ctx, inst,
+			&ipp_regs[inst], &ipp_shift, &ipp_mask);
+	return &ipp->base;
+}
+
+static void dce60_resource_destruct(struct dce110_resource_pool *pool)
+{
+	unsigned int i;
+
+	for (i = 0; i < pool->base.pipe_count; i++) {
+		if (pool->base.opps[i] != NULL)
+			dce110_opp_destroy(&pool->base.opps[i]);
+
+		if (pool->base.transforms[i] != NULL)
+			dce60_transform_destroy(&pool->base.transforms[i]);
+
+		if (pool->base.ipps[i] != NULL)
+			dce_ipp_destroy(&pool->base.ipps[i]);
+
+		if (pool->base.mis[i] != NULL) {
+			kfree(TO_DCE_MEM_INPUT(pool->base.mis[i]));
+			pool->base.mis[i] = NULL;
+		}
+
+		if (pool->base.timing_generators[i] != NULL)	{
+			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
+			pool->base.timing_generators[i] = NULL;
+		}
+	}
+
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+		if (pool->base.hw_i2cs[i] != NULL) {
+			kfree(pool->base.hw_i2cs[i]);
+			pool->base.hw_i2cs[i] = NULL;
+		}
+		if (pool->base.sw_i2cs[i] != NULL) {
+			kfree(pool->base.sw_i2cs[i]);
+			pool->base.sw_i2cs[i] = NULL;
+		}
+	}
+
+	for (i = 0; i < pool->base.stream_enc_count; i++) {
+		if (pool->base.stream_enc[i] != NULL)
+			kfree(DCE110STRENC_FROM_STRENC(pool->base.stream_enc[i]));
+	}
+
+	for (i = 0; i < pool->base.clk_src_count; i++) {
+		if (pool->base.clock_sources[i] != NULL) {
+			dce60_clock_source_destroy(&pool->base.clock_sources[i]);
+		}
+	}
+
+	if (pool->base.abm != NULL)
+			dce_abm_destroy(&pool->base.abm);
+
+	if (pool->base.dmcu != NULL)
+			dce_dmcu_destroy(&pool->base.dmcu);
+
+	if (pool->base.dp_clock_source != NULL)
+		dce60_clock_source_destroy(&pool->base.dp_clock_source);
+
+	for (i = 0; i < pool->base.audio_count; i++)	{
+		if (pool->base.audios[i] != NULL) {
+			dce_aud_destroy(&pool->base.audios[i]);
+		}
+	}
+
+	if (pool->base.irqs != NULL) {
+		dal_irq_service_destroy(&pool->base.irqs);
+	}
+}
+
+bool dce60_validate_bandwidth(
+	struct dc *dc,
+	struct dc_state *context,
+	bool fast_validate)
+{
+	int i;
+	bool at_least_one_pipe = false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			at_least_one_pipe = true;
+	}
+
+	if (at_least_one_pipe) {
+		/* TODO implement when needed but for now hardcode max value*/
+		context->bw_ctx.bw.dce.dispclk_khz = 681000;
+		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
+	} else {
+		context->bw_ctx.bw.dce.dispclk_khz = 0;
+		context->bw_ctx.bw.dce.yclk_khz = 0;
+	}
+
+	return true;
+}
+
+static bool dce60_validate_surface_sets(
+		struct dc_state *context)
+{
+	int i;
+
+	for (i = 0; i < context->stream_count; i++) {
+		if (context->stream_status[i].plane_count == 0)
+			continue;
+
+		if (context->stream_status[i].plane_count > 1)
+			return false;
+
+		if (context->stream_status[i].plane_states[0]->format
+				>= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
+			return false;
+	}
+
+	return true;
+}
+
+enum dc_status dce60_validate_global(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	if (!dce60_validate_surface_sets(context))
+		return DC_FAIL_SURFACE_VALIDATE;
+
+	return DC_OK;
+}
+
+static void dce60_destroy_resource_pool(struct resource_pool **pool)
+{
+	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
+
+	dce60_resource_destruct(dce110_pool);
+	kfree(dce110_pool);
+	*pool = NULL;
+}
+
+static const struct resource_funcs dce60_res_pool_funcs = {
+	.destroy = dce60_destroy_resource_pool,
+	.link_enc_create = dce60_link_encoder_create,
+	.panel_cntl_create = dce60_panel_cntl_create,
+	.validate_bandwidth = dce60_validate_bandwidth,
+	.validate_plane = dce100_validate_plane,
+	.add_stream_to_ctx = dce100_add_stream_to_ctx,
+	.validate_global = dce60_validate_global,
+	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
+};
+
+static bool dce60_construct(
+	uint8_t num_virtual_links,
+	struct dc *dc,
+	struct dce110_resource_pool *pool)
+{
+	unsigned int i;
+	struct dc_context *ctx = dc->ctx;
+	struct dc_bios *bp;
+
+	ctx->dc_bios->regs = &bios_regs;
+
+	pool->base.res_cap = &res_cap;
+	pool->base.funcs = &dce60_res_pool_funcs;
+
+
+	/*************************************************
+	 *  Resource + asic cap harcoding                *
+	 *************************************************/
+	pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE;
+	pool->base.pipe_count = res_cap.num_timing_generator;
+	pool->base.timing_generator_count = res_cap.num_timing_generator;
+	dc->caps.max_downscale_ratio = 200;
+	dc->caps.i2c_speed_in_khz = 40;
+	dc->caps.max_cursor_size = 64;
+	dc->caps.dual_link_dvi = true;
+	dc->caps.extended_aux_timeout_support = false;
+
+	/*************************************************
+	 *  Create resources                             *
+	 *************************************************/
+
+	bp = ctx->dc_bios;
+
+	if (bp->fw_info_valid && bp->fw_info.external_clock_source_frequency_for_dp != 0) {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], false);
+		pool->base.clock_sources[1] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clk_src_count = 2;
+
+	} else {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clk_src_count = 1;
+	}
+
+	if (pool->base.dp_clock_source == NULL) {
+		dm_error("DC: failed to create dp clock source!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.clk_src_count; i++) {
+		if (pool->base.clock_sources[i] == NULL) {
+			dm_error("DC: failed to create clock sources!\n");
+			BREAK_TO_DEBUGGER();
+			goto res_create_fail;
+		}
+	}
+
+	pool->base.dmcu = dce_dmcu_create(ctx,
+			&dmcu_regs,
+			&dmcu_shift,
+			&dmcu_mask);
+	if (pool->base.dmcu == NULL) {
+		dm_error("DC: failed to create dmcu!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	pool->base.abm = dce_abm_create(ctx,
+			&abm_regs,
+			&abm_shift,
+			&abm_mask);
+	if (pool->base.abm == NULL) {
+		dm_error("DC: failed to create abm!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	{
+		struct irq_service_init_data init_data;
+		init_data.ctx = dc->ctx;
+		pool->base.irqs = dal_irq_service_dce60_create(&init_data);
+		if (!pool->base.irqs)
+			goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.pipe_count; i++) {
+		pool->base.timing_generators[i] = dce60_timing_generator_create(
+				ctx, i, &dce60_tg_offsets[i]);
+		if (pool->base.timing_generators[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create tg!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.mis[i] = dce60_mem_input_create(ctx, i);
+		if (pool->base.mis[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create memory input!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.ipps[i] = dce60_ipp_create(ctx, i);
+		if (pool->base.ipps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create input pixel processor!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.transforms[i] = dce60_transform_create(ctx, i);
+		if (pool->base.transforms[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create transform!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.opps[i] = dce60_opp_create(ctx, i);
+		if (pool->base.opps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create output pixel processor!\n");
+			goto res_create_fail;
+		}
+	}
+
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
+		pool->base.engines[i] = dce60_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.hw_i2cs[i] = dce60_i2c_hw_create(ctx, i);
+		if (pool->base.hw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create i2c engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.sw_i2cs[i] = dce60_i2c_sw_create(ctx);
+		if (pool->base.sw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create sw i2c!!\n");
+			goto res_create_fail;
+		}
+	}
+
+	dc->caps.max_planes =  pool->base.pipe_count;
+
+	for (i = 0; i < dc->caps.max_planes; ++i)
+		dc->caps.planes[i] = plane_cap;
+
+	dc->caps.disable_dp_clk_share = true;
+
+	if (!resource_construct(num_virtual_links, dc, &pool->base,
+			&res_create_funcs))
+		goto res_create_fail;
+
+	/* Create hardware sequencer */
+	dce60_hw_sequencer_construct(dc);
+
+	return true;
+
+res_create_fail:
+	dce60_resource_destruct(pool);
+	return false;
+}
+
+struct resource_pool *dce60_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc)
+{
+	struct dce110_resource_pool *pool =
+		kzalloc(sizeof(struct dce110_resource_pool), GFP_KERNEL);
+
+	if (!pool)
+		return NULL;
+
+	if (dce60_construct(num_virtual_links, dc, pool))
+		return &pool->base;
+
+	BREAK_TO_DEBUGGER();
+	return NULL;
+}
+
+static bool dce61_construct(
+	uint8_t num_virtual_links,
+	struct dc *dc,
+	struct dce110_resource_pool *pool)
+{
+	unsigned int i;
+	struct dc_context *ctx = dc->ctx;
+	struct dc_bios *bp;
+
+	ctx->dc_bios->regs = &bios_regs;
+
+	pool->base.res_cap = &res_cap_61;
+	pool->base.funcs = &dce60_res_pool_funcs;
+
+
+	/*************************************************
+	 *  Resource + asic cap harcoding                *
+	 *************************************************/
+	pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE;
+	pool->base.pipe_count = res_cap_61.num_timing_generator;
+	pool->base.timing_generator_count = res_cap_61.num_timing_generator;
+	dc->caps.max_downscale_ratio = 200;
+	dc->caps.i2c_speed_in_khz = 40;
+	dc->caps.max_cursor_size = 64;
+	dc->caps.is_apu = true;
+
+	/*************************************************
+	 *  Create resources                             *
+	 *************************************************/
+
+	bp = ctx->dc_bios;
+
+	if (bp->fw_info_valid && bp->fw_info.external_clock_source_frequency_for_dp != 0) {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], false);
+		pool->base.clock_sources[1] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clock_sources[2] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
+		pool->base.clk_src_count = 3;
+
+	} else {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clock_sources[1] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
+		pool->base.clk_src_count = 2;
+	}
+
+	if (pool->base.dp_clock_source == NULL) {
+		dm_error("DC: failed to create dp clock source!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.clk_src_count; i++) {
+		if (pool->base.clock_sources[i] == NULL) {
+			dm_error("DC: failed to create clock sources!\n");
+			BREAK_TO_DEBUGGER();
+			goto res_create_fail;
+		}
+	}
+
+	pool->base.dmcu = dce_dmcu_create(ctx,
+			&dmcu_regs,
+			&dmcu_shift,
+			&dmcu_mask);
+	if (pool->base.dmcu == NULL) {
+		dm_error("DC: failed to create dmcu!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	pool->base.abm = dce_abm_create(ctx,
+			&abm_regs,
+			&abm_shift,
+			&abm_mask);
+	if (pool->base.abm == NULL) {
+		dm_error("DC: failed to create abm!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	{
+		struct irq_service_init_data init_data;
+		init_data.ctx = dc->ctx;
+		pool->base.irqs = dal_irq_service_dce60_create(&init_data);
+		if (!pool->base.irqs)
+			goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.pipe_count; i++) {
+		pool->base.timing_generators[i] = dce60_timing_generator_create(
+				ctx, i, &dce60_tg_offsets[i]);
+		if (pool->base.timing_generators[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create tg!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.mis[i] = dce60_mem_input_create(ctx, i);
+		if (pool->base.mis[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create memory input!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.ipps[i] = dce60_ipp_create(ctx, i);
+		if (pool->base.ipps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create input pixel processor!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.transforms[i] = dce60_transform_create(ctx, i);
+		if (pool->base.transforms[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create transform!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.opps[i] = dce60_opp_create(ctx, i);
+		if (pool->base.opps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create output pixel processor!\n");
+			goto res_create_fail;
+		}
+	}
+
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
+		pool->base.engines[i] = dce60_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.hw_i2cs[i] = dce60_i2c_hw_create(ctx, i);
+		if (pool->base.hw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create i2c engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.sw_i2cs[i] = dce60_i2c_sw_create(ctx);
+		if (pool->base.sw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create sw i2c!!\n");
+			goto res_create_fail;
+		}
+	}
+
+	dc->caps.max_planes =  pool->base.pipe_count;
+
+	for (i = 0; i < dc->caps.max_planes; ++i)
+		dc->caps.planes[i] = plane_cap;
+
+	dc->caps.disable_dp_clk_share = true;
+
+	if (!resource_construct(num_virtual_links, dc, &pool->base,
+			&res_create_funcs))
+		goto res_create_fail;
+
+	/* Create hardware sequencer */
+	dce60_hw_sequencer_construct(dc);
+
+	return true;
+
+res_create_fail:
+	dce60_resource_destruct(pool);
+	return false;
+}
+
+struct resource_pool *dce61_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc)
+{
+	struct dce110_resource_pool *pool =
+		kzalloc(sizeof(struct dce110_resource_pool), GFP_KERNEL);
+
+	if (!pool)
+		return NULL;
+
+	if (dce61_construct(num_virtual_links, dc, pool))
+		return &pool->base;
+
+	BREAK_TO_DEBUGGER();
+	return NULL;
+}
+
+static bool dce64_construct(
+	uint8_t num_virtual_links,
+	struct dc *dc,
+	struct dce110_resource_pool *pool)
+{
+	unsigned int i;
+	struct dc_context *ctx = dc->ctx;
+	struct dc_bios *bp;
+
+	ctx->dc_bios->regs = &bios_regs;
+
+	pool->base.res_cap = &res_cap_64;
+	pool->base.funcs = &dce60_res_pool_funcs;
+
+
+	/*************************************************
+	 *  Resource + asic cap harcoding                *
+	 *************************************************/
+	pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE;
+	pool->base.pipe_count = res_cap_64.num_timing_generator;
+	pool->base.timing_generator_count = res_cap_64.num_timing_generator;
+	dc->caps.max_downscale_ratio = 200;
+	dc->caps.i2c_speed_in_khz = 40;
+	dc->caps.max_cursor_size = 64;
+	dc->caps.is_apu = true;
+
+	/*************************************************
+	 *  Create resources                             *
+	 *************************************************/
+
+	bp = ctx->dc_bios;
+
+	if (bp->fw_info_valid && bp->fw_info.external_clock_source_frequency_for_dp != 0) {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[0], false);
+		pool->base.clock_sources[1] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[1], false);
+		pool->base.clk_src_count = 2;
+
+	} else {
+		pool->base.dp_clock_source =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[0], true);
+
+		pool->base.clock_sources[0] =
+				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[1], false);
+		pool->base.clk_src_count = 1;
+	}
+
+	if (pool->base.dp_clock_source == NULL) {
+		dm_error("DC: failed to create dp clock source!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.clk_src_count; i++) {
+		if (pool->base.clock_sources[i] == NULL) {
+			dm_error("DC: failed to create clock sources!\n");
+			BREAK_TO_DEBUGGER();
+			goto res_create_fail;
+		}
+	}
+
+	pool->base.dmcu = dce_dmcu_create(ctx,
+			&dmcu_regs,
+			&dmcu_shift,
+			&dmcu_mask);
+	if (pool->base.dmcu == NULL) {
+		dm_error("DC: failed to create dmcu!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	pool->base.abm = dce_abm_create(ctx,
+			&abm_regs,
+			&abm_shift,
+			&abm_mask);
+	if (pool->base.abm == NULL) {
+		dm_error("DC: failed to create abm!\n");
+		BREAK_TO_DEBUGGER();
+		goto res_create_fail;
+	}
+
+	{
+		struct irq_service_init_data init_data;
+		init_data.ctx = dc->ctx;
+		pool->base.irqs = dal_irq_service_dce60_create(&init_data);
+		if (!pool->base.irqs)
+			goto res_create_fail;
+	}
+
+	for (i = 0; i < pool->base.pipe_count; i++) {
+		pool->base.timing_generators[i] = dce60_timing_generator_create(
+				ctx, i, &dce60_tg_offsets[i]);
+		if (pool->base.timing_generators[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create tg!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.mis[i] = dce60_mem_input_create(ctx, i);
+		if (pool->base.mis[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create memory input!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.ipps[i] = dce60_ipp_create(ctx, i);
+		if (pool->base.ipps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create input pixel processor!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.transforms[i] = dce60_transform_create(ctx, i);
+		if (pool->base.transforms[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create transform!\n");
+			goto res_create_fail;
+		}
+
+		pool->base.opps[i] = dce60_opp_create(ctx, i);
+		if (pool->base.opps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create output pixel processor!\n");
+			goto res_create_fail;
+		}
+	}
+
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
+		pool->base.engines[i] = dce60_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.hw_i2cs[i] = dce60_i2c_hw_create(ctx, i);
+		if (pool->base.hw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create i2c engine!!\n");
+			goto res_create_fail;
+		}
+		pool->base.sw_i2cs[i] = dce60_i2c_sw_create(ctx);
+		if (pool->base.sw_i2cs[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create sw i2c!!\n");
+			goto res_create_fail;
+		}
+	}
+
+	dc->caps.max_planes =  pool->base.pipe_count;
+
+	for (i = 0; i < dc->caps.max_planes; ++i)
+		dc->caps.planes[i] = plane_cap;
+
+	dc->caps.disable_dp_clk_share = true;
+
+	if (!resource_construct(num_virtual_links, dc, &pool->base,
+			&res_create_funcs))
+		goto res_create_fail;
+
+	/* Create hardware sequencer */
+	dce60_hw_sequencer_construct(dc);
+
+	return true;
+
+res_create_fail:
+	dce60_resource_destruct(pool);
+	return false;
+}
+
+struct resource_pool *dce64_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc)
+{
+	struct dce110_resource_pool *pool =
+		kzalloc(sizeof(struct dce110_resource_pool), GFP_KERNEL);
+
+	if (!pool)
+		return NULL;
+
+	if (dce64_construct(num_virtual_links, dc, pool))
+		return &pool->base;
+
+	BREAK_TO_DEBUGGER();
+	return NULL;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.h b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.h
new file mode 100644
index 000000000000..5d653a76b0b0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_RESOURCE_DCE60_H__
+#define __DC_RESOURCE_DCE60_H__
+
+#include "core_types.h"
+
+struct dc;
+struct resource_pool;
+
+struct resource_pool *dce60_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc);
+
+struct resource_pool *dce61_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc);
+
+struct resource_pool *dce64_create_resource_pool(
+	uint8_t num_virtual_links,
+	struct dc *dc);
+
+#endif /* __DC_RESOURCE_DCE60_H__ */
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
new file mode 100644
index 000000000000..fc1af0ff0ca4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
@@ -0,0 +1,266 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+
+/* include DCE6 register header files */
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+#include "dc_types.h"
+
+#include "include/grph_object_id.h"
+#include "include/logger_interface.h"
+#include "../dce110/dce110_timing_generator.h"
+#include "dce60_timing_generator.h"
+
+#include "timing_generator.h"
+
+enum black_color_format {
+	BLACK_COLOR_FORMAT_RGB_FULLRANGE = 0,	/* used as index in array */
+	BLACK_COLOR_FORMAT_RGB_LIMITED,
+	BLACK_COLOR_FORMAT_YUV_TV,
+	BLACK_COLOR_FORMAT_YUV_CV,
+	BLACK_COLOR_FORMAT_YUV_SUPER_AA,
+
+	BLACK_COLOR_FORMAT_COUNT
+};
+
+static const struct dce110_timing_generator_offsets reg_offsets[] = {
+{
+	.crtc = (mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP0_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+},
+{
+	.crtc = (mmCRTC1_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP1_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+},
+{
+	.crtc = (mmCRTC2_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP2_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+},
+{
+	.crtc = (mmCRTC3_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP3_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+},
+{
+	.crtc = (mmCRTC4_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP4_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+},
+{
+	.crtc = (mmCRTC5_DCFE_MEM_LIGHT_SLEEP_CNTL - mmCRTC0_DCFE_MEM_LIGHT_SLEEP_CNTL),
+	.dcp = (mmDCP5_GRPH_CONTROL - mmDCP0_GRPH_CONTROL),
+}
+};
+
+#define NUMBER_OF_FRAME_TO_WAIT_ON_TRIGGERED_RESET 10
+
+#define MAX_H_TOTAL (CRTC_H_TOTAL__CRTC_H_TOTAL_MASK + 1)
+#define MAX_V_TOTAL (CRTC_V_TOTAL__CRTC_V_TOTAL_MASKhw + 1)
+
+#define CRTC_REG(reg) (reg + tg110->offsets.crtc)
+#define DCP_REG(reg) (reg + tg110->offsets.dcp)
+#define DMIF_REG(reg) (reg + tg110->offsets.dmif)
+
+static void program_pix_dur(struct timing_generator *tg, uint32_t pix_clk_100hz)
+{
+	uint64_t pix_dur;
+	uint32_t addr = mmDMIF_PG0_DPG_PIPE_ARBITRATION_CONTROL1
+					+ DCE110TG_FROM_TG(tg)->offsets.dmif;
+	uint32_t value = dm_read_reg(tg->ctx, addr);
+
+	if (pix_clk_100hz == 0)
+		return;
+
+	pix_dur = div_u64(10000000000ull, pix_clk_100hz);
+
+	set_reg_field_value(
+		value,
+		pix_dur,
+		DPG_PIPE_ARBITRATION_CONTROL1,
+		PIXEL_DURATION);
+
+	dm_write_reg(tg->ctx, addr, value);
+}
+
+static void program_timing(struct timing_generator *tg,
+	const struct dc_crtc_timing *timing,
+	int vready_offset,
+	int vstartup_start,
+	int vupdate_offset,
+	int vupdate_width,
+	const enum signal_type signal,
+	bool use_vbios)
+{
+	if (!use_vbios)
+		program_pix_dur(tg, timing->pix_clk_100hz);
+
+	dce110_tg_program_timing(tg, timing, 0, 0, 0, 0, 0, use_vbios);
+}
+
+static void dce60_timing_generator_enable_advanced_request(
+	struct timing_generator *tg,
+	bool enable,
+	const struct dc_crtc_timing *timing)
+{
+	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
+	uint32_t addr = CRTC_REG(mmCRTC_START_LINE_CONTROL);
+	uint32_t value = dm_read_reg(tg->ctx, addr);
+	/* DCE6 has CRTC_PREFETCH_EN bit in CRTC_CONTROL register */
+	uint32_t addr2 = CRTC_REG(mmCRTC_CONTROL);
+	uint32_t value2 = dm_read_reg(tg->ctx, addr2);
+
+	/* DCE6 does not support CRTC_LEGACY_REQUESTOR_EN bit
+	   so here is not possible to set bit based on enable argument */
+
+	if ((timing->v_sync_width + timing->v_front_porch) <= 3) {
+		set_reg_field_value(
+			value,
+			3,
+			CRTC_START_LINE_CONTROL,
+			CRTC_ADVANCED_START_LINE_POSITION);
+		set_reg_field_value(
+			value2,
+			0,
+			CRTC_CONTROL,
+			CRTC_PREFETCH_EN);
+	} else {
+		set_reg_field_value(
+			value,
+			4,
+			CRTC_START_LINE_CONTROL,
+			CRTC_ADVANCED_START_LINE_POSITION);
+		set_reg_field_value(
+			value2,
+			1,
+			CRTC_CONTROL,
+			CRTC_PREFETCH_EN);
+	}
+
+	set_reg_field_value(
+		value,
+		1,
+		CRTC_START_LINE_CONTROL,
+		CRTC_PROGRESSIVE_START_LINE_EARLY);
+
+	set_reg_field_value(
+		value,
+		1,
+		CRTC_START_LINE_CONTROL,
+		CRTC_INTERLACE_START_LINE_EARLY);
+
+	dm_write_reg(tg->ctx, addr, value);
+	dm_write_reg(tg->ctx, addr2, value2);
+}
+
+static bool dce60_is_tg_enabled(struct timing_generator *tg)
+{
+	uint32_t addr = 0;
+	uint32_t value = 0;
+	uint32_t field = 0;
+	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
+
+	addr = CRTC_REG(mmCRTC_CONTROL);
+	value = dm_read_reg(tg->ctx, addr);
+	field = get_reg_field_value(value, CRTC_CONTROL,
+				    CRTC_CURRENT_MASTER_EN_STATE);
+	return field == 1;
+}
+
+bool dce60_configure_crc(struct timing_generator *tg,
+			  const struct crc_params *params)
+{
+	/* Cannot configure crc on a CRTC that is disabled */
+	if (!dce60_is_tg_enabled(tg))
+		return false;
+
+	/* DCE6 has no CRTC_CRC_CNTL register, nothing to do */
+
+	return true;
+}
+
+static const struct timing_generator_funcs dce60_tg_funcs = {
+		.validate_timing = dce110_tg_validate_timing,
+		.program_timing = program_timing,
+		.enable_crtc = dce110_timing_generator_enable_crtc,
+		.disable_crtc = dce110_timing_generator_disable_crtc,
+		.is_counter_moving = dce110_timing_generator_is_counter_moving,
+		.get_position = dce110_timing_generator_get_position,
+		.get_frame_count = dce110_timing_generator_get_vblank_counter,
+		.get_scanoutpos = dce110_timing_generator_get_crtc_scanoutpos,
+		.set_early_control = dce110_timing_generator_set_early_control,
+		.wait_for_state = dce110_tg_wait_for_state,
+		.set_blank = dce110_tg_set_blank,
+		.is_blanked = dce110_tg_is_blanked,
+		.set_colors = dce110_tg_set_colors,
+		.set_overscan_blank_color =
+				dce110_timing_generator_set_overscan_color_black,
+		.set_blank_color = dce110_timing_generator_program_blank_color,
+		.disable_vga = dce110_timing_generator_disable_vga,
+		.did_triggered_reset_occur =
+				dce110_timing_generator_did_triggered_reset_occur,
+		.setup_global_swap_lock =
+				dce110_timing_generator_setup_global_swap_lock,
+		.enable_reset_trigger = dce110_timing_generator_enable_reset_trigger,
+		.disable_reset_trigger = dce110_timing_generator_disable_reset_trigger,
+		.tear_down_global_swap_lock =
+				dce110_timing_generator_tear_down_global_swap_lock,
+		.set_drr = dce110_timing_generator_set_drr,
+		.set_static_screen_control =
+			dce110_timing_generator_set_static_screen_control,
+		.set_test_pattern = dce110_timing_generator_set_test_pattern,
+		.arm_vert_intr = dce110_arm_vert_intr,
+
+		/* DCE6.0 overrides */
+		.enable_advanced_request =
+				dce60_timing_generator_enable_advanced_request,
+		.configure_crc = dce60_configure_crc,
+		.get_crc = dce110_get_crc,
+};
+
+void dce60_timing_generator_construct(
+	struct dce110_timing_generator *tg110,
+	struct dc_context *ctx,
+	uint32_t instance,
+	const struct dce110_timing_generator_offsets *offsets)
+{
+	tg110->controller_id = CONTROLLER_ID_D0 + instance;
+	tg110->base.inst = instance;
+	tg110->offsets = *offsets;
+	tg110->derived_offsets = reg_offsets[instance];
+
+	tg110->base.funcs = &dce60_tg_funcs;
+
+	tg110->base.ctx = ctx;
+	tg110->base.bp = ctx->dc_bios;
+
+	tg110->max_h_total = CRTC_H_TOTAL__CRTC_H_TOTAL_MASK + 1;
+	tg110->max_v_total = CRTC_V_TOTAL__CRTC_V_TOTAL_MASK + 1;
+
+	tg110->min_h_blank = 56;
+	tg110->min_h_front_porch = 4;
+	tg110->min_h_back_porch = 4;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.h
new file mode 100644
index 000000000000..81d831233cc5
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ *  and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_TIMING_GENERATOR_DCE60_H__
+#define __DC_TIMING_GENERATOR_DCE60_H__
+
+#include "timing_generator.h"
+#include "../include/grph_object_id.h"
+
+/* DCE6.0 implementation inherits from DCE11.0 */
+void dce60_timing_generator_construct(
+	struct dce110_timing_generator *tg,
+	struct dc_context *ctx,
+	uint32_t instance,
+	const struct dce110_timing_generator_offsets *offsets);
+
+#endif /* __DC_TIMING_GENERATOR_DCE60_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 62ad1a11bff9..733e6e6e43bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -31,4 +31,11 @@ DCN10 = dcn10_init.o dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
 
 AMD_DAL_DCN10 = $(addprefix $(AMDDALPATH)/dc/dcn10/,$(DCN10))
 
+# fix:
+# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
+# aarch64 does not support soft-float, so use hard-float and handle this in code
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn10/dcn10_resource.o := -mgeneral-regs-only
+endif
+
 AMD_DISPLAY_FILES += $(AMD_DAL_DCN10)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index a643927e272b..8ca94f506195 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1450,33 +1450,42 @@ void dcn10_init_hw(struct dc *dc)
 void dcn10_power_down_on_boot(struct dc *dc)
 {
 	int i = 0;
+	struct dc_link *edp_link;
 
-	if (dc->config.power_down_display_on_boot) {
-		struct dc_link *edp_link = get_edp_link(dc);
-
-		if (edp_link &&
-				edp_link->link_enc->funcs->is_dig_enabled &&
-				edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
-				dc->hwseq->funcs.edp_backlight_control &&
-				dc->hwss.power_down &&
-				dc->hwss.edp_power_control) {
-			dc->hwseq->funcs.edp_backlight_control(edp_link, false);
-			dc->hwss.power_down(dc);
-			dc->hwss.edp_power_control(edp_link, false);
-		} else {
-			for (i = 0; i < dc->link_count; i++) {
-				struct dc_link *link = dc->links[i];
-
-				if (link->link_enc->funcs->is_dig_enabled &&
-						link->link_enc->funcs->is_dig_enabled(link->link_enc) &&
-						dc->hwss.power_down) {
-					dc->hwss.power_down(dc);
-					break;
-				}
+	if (!dc->config.power_down_display_on_boot)
+		return;
+
+	edp_link = get_edp_link(dc);
+	if (edp_link &&
+			edp_link->link_enc->funcs->is_dig_enabled &&
+			edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
+			dc->hwseq->funcs.edp_backlight_control &&
+			dc->hwss.power_down &&
+			dc->hwss.edp_power_control) {
+		dc->hwseq->funcs.edp_backlight_control(edp_link, false);
+		dc->hwss.power_down(dc);
+		dc->hwss.edp_power_control(edp_link, false);
+	} else {
+		for (i = 0; i < dc->link_count; i++) {
+			struct dc_link *link = dc->links[i];
 
+			if (link->link_enc->funcs->is_dig_enabled &&
+					link->link_enc->funcs->is_dig_enabled(link->link_enc) &&
+					dc->hwss.power_down) {
+				dc->hwss.power_down(dc);
+				break;
 			}
+
 		}
 	}
+
+	/*
+	 * Call update_clocks with empty context
+	 * to send DISPLAY_OFF
+	 * Otherwise DISPLAY_OFF may not be asserted
+	 */
+	if (dc->clk_mgr->funcs->set_low_power_state)
+		dc->clk_mgr->funcs->set_low_power_state(dc->clk_mgr);
 }
 
 void dcn10_reset_hw_ctx_wrap(
@@ -2368,14 +2377,6 @@ void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 				&blnd_cfg.black_color);
 	}
 
-	/*
-	 * The way 420 is packed, 2 channels carry Y component, 1 channel
-	 * alternate between Cb and Cr, so both channels need the pixel
-	 * value for Y
-	 */
-	if (pipe_ctx->stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420)
-		blnd_cfg.black_color.color_r_cr = blnd_cfg.black_color.color_g_y;
-
 	if (per_pixel_alpha)
 		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA;
 	else
@@ -2760,6 +2761,152 @@ static struct pipe_ctx *dcn10_find_top_pipe_for_stream(
 	return NULL;
 }
 
+bool dcn10_disconnect_pipes(
+		struct dc *dc,
+		struct dc_state *context)
+{
+		bool found_stream = false;
+		int i, j;
+		struct dce_hwseq *hws = dc->hwseq;
+		struct dc_state *old_ctx = dc->current_state;
+		bool mpcc_disconnected = false;
+		struct pipe_ctx *old_pipe;
+		struct pipe_ctx *new_pipe;
+		DC_LOGGER_INIT(dc->ctx->logger);
+
+		/* Set pipe update flags and lock pipes */
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+			new_pipe = &context->res_ctx.pipe_ctx[i];
+			new_pipe->update_flags.raw = 0;
+
+			if (!old_pipe->plane_state && !new_pipe->plane_state)
+				continue;
+
+			if (old_pipe->plane_state && !new_pipe->plane_state)
+				new_pipe->update_flags.bits.disable = 1;
+
+			/* Check for scl update */
+			if (memcmp(&old_pipe->plane_res.scl_data, &new_pipe->plane_res.scl_data, sizeof(struct scaler_data)))
+					new_pipe->update_flags.bits.scaler = 1;
+
+			/* Check for vp update */
+			if (memcmp(&old_pipe->plane_res.scl_data.viewport, &new_pipe->plane_res.scl_data.viewport, sizeof(struct rect))
+					|| memcmp(&old_pipe->plane_res.scl_data.viewport_c,
+						&new_pipe->plane_res.scl_data.viewport_c, sizeof(struct rect)))
+				new_pipe->update_flags.bits.viewport = 1;
+
+		}
+
+		if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
+			/* Disconnect mpcc here only if losing pipe split*/
+			for (i = 0; i < dc->res_pool->pipe_count; i++) {
+				if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable &&
+					old_ctx->res_ctx.pipe_ctx[i].top_pipe) {
+
+					/* Find the top pipe in the new ctx for the bottom pipe that we
+					 * want to remove by comparing the streams. If both pipes are being
+					 * disabled then do it in the regular pipe programming sequence
+					 */
+					for (j = 0; j < dc->res_pool->pipe_count; j++) {
+						if (old_ctx->res_ctx.pipe_ctx[i].top_pipe->stream == context->res_ctx.pipe_ctx[j].stream &&
+							!context->res_ctx.pipe_ctx[j].top_pipe &&
+							!context->res_ctx.pipe_ctx[j].update_flags.bits.disable) {
+							found_stream = true;
+							break;
+						}
+					}
+
+					// Disconnect if the top pipe lost it's pipe split
+					if (found_stream && !context->res_ctx.pipe_ctx[j].bottom_pipe) {
+						hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+						DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
+						mpcc_disconnected = true;
+					}
+				}
+				found_stream = false;
+			}
+		}
+
+		if (mpcc_disconnected) {
+			for (i = 0; i < dc->res_pool->pipe_count; i++) {
+				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+				struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+				struct dc_plane_state *plane_state = pipe_ctx->plane_state;
+				struct hubp *hubp = pipe_ctx->plane_res.hubp;
+
+				if (!pipe_ctx || !plane_state || !pipe_ctx->stream)
+					continue;
+
+				// Only update scaler and viewport here if we lose a pipe split.
+				// This is to prevent half the screen from being black when we
+				// unlock after disconnecting MPCC.
+				if (!(old_pipe && !pipe_ctx->top_pipe &&
+					!pipe_ctx->bottom_pipe && old_pipe->bottom_pipe))
+					continue;
+
+				if (pipe_ctx->update_flags.raw || pipe_ctx->plane_state->update_flags.raw || pipe_ctx->stream->update_flags.raw) {
+					if (pipe_ctx->update_flags.bits.scaler ||
+						plane_state->update_flags.bits.scaling_change ||
+						plane_state->update_flags.bits.position_change ||
+						plane_state->update_flags.bits.per_pixel_alpha_change ||
+						pipe_ctx->stream->update_flags.bits.scaling) {
+
+						pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->plane_state->per_pixel_alpha;
+						ASSERT(pipe_ctx->plane_res.scl_data.lb_params.depth == LB_PIXEL_DEPTH_30BPP);
+						/* scaler configuration */
+						pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
+						pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
+					}
+
+					if (pipe_ctx->update_flags.bits.viewport ||
+						(context == dc->current_state && plane_state->update_flags.bits.position_change) ||
+						(context == dc->current_state && plane_state->update_flags.bits.scaling_change) ||
+						(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) {
+
+						hubp->funcs->mem_program_viewport(
+							hubp,
+							&pipe_ctx->plane_res.scl_data.viewport,
+							&pipe_ctx->plane_res.scl_data.viewport_c);
+					}
+				}
+			}
+		}
+	return mpcc_disconnected;
+}
+
+void dcn10_wait_for_pending_cleared(struct dc *dc,
+		struct dc_state *context)
+{
+		struct pipe_ctx *pipe_ctx;
+		struct timing_generator *tg;
+		int i;
+
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			pipe_ctx = &context->res_ctx.pipe_ctx[i];
+			tg = pipe_ctx->stream_res.tg;
+
+			/*
+			 * Only wait for top pipe's tg penindg bit
+			 * Also skip if pipe is disabled.
+			 */
+			if (pipe_ctx->top_pipe ||
+			    !pipe_ctx->stream || !pipe_ctx->plane_state ||
+			    !tg->funcs->is_tg_enabled(tg))
+				continue;
+
+			/*
+			 * Wait for VBLANK then VACTIVE to ensure we get VUPDATE.
+			 * For some reason waiting for OTG_UPDATE_PENDING cleared
+			 * seems to not trigger the update right away, and if we
+			 * lock again before VUPDATE then we don't get a separated
+			 * operation.
+			 */
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+		}
+}
+
 void dcn10_apply_ctx_for_surface(
 		struct dc *dc,
 		const struct dc_stream_state *stream,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 6d891166da8a..e5691e499023 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -194,6 +194,12 @@ void dcn10_get_surface_visual_confirm_color(
 void dcn10_get_hdr_visual_confirm_color(
 		struct pipe_ctx *pipe_ctx,
 		struct tg_color *color);
+bool dcn10_disconnect_pipes(
+		struct dc *dc,
+		struct dc_state *context);
+
+void dcn10_wait_for_pending_cleared(struct dc *dc,
+		struct dc_state *context);
 void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx);
 void dcn10_verify_allow_pstate_change_high(struct dc *dc);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
index 5c98b71c1d47..a1d1559bb5d7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -34,6 +34,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
 	.post_unlock_program_front_end = dcn10_post_unlock_program_front_end,
+	.disconnect_pipes = dcn10_disconnect_pipes,
+	.wait_for_pending_cleared = dcn10_wait_for_pending_cleared,
 	.update_plane_addr = dcn10_update_plane_addr,
 	.update_dchub = dcn10_update_dchub,
 	.update_pending_status = dcn10_update_pending_status,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 17d5cb422025..1abd81e17f09 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1213,6 +1213,7 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont
 	bool video_large = false;
 	bool desktop_large = false;
 	bool dcc_disabled = false;
+	bool mpo_enabled = false;
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->stream_status[i].plane_count == 0)
@@ -1221,6 +1222,9 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont
 		if (context->stream_status[i].plane_count > 2)
 			return DC_FAIL_UNSUPPORTED_1;
 
+		if (context->stream_status[i].plane_count > 1)
+			mpo_enabled = true;
+
 		for (j = 0; j < context->stream_status[i].plane_count; j++) {
 			struct dc_plane_state *plane =
 				context->stream_status[i].plane_states[j];
@@ -1244,6 +1248,10 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont
 		}
 	}
 
+	/* Disable MPO in multi-display configurations. */
+	if (context->stream_count > 1 && mpo_enabled)
+		return DC_FAIL_UNSUPPORTED_1;
+
 	/*
 	 * Workaround: On DCN10 there is UMC issue that causes underflow when
 	 * playing 4k video on 4k desktop with video downscaled and single channel
@@ -1331,6 +1339,47 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
+/*
+ * Some architectures don't support soft-float (e.g. aarch64), on those
+ * this function has to be called with hardfloat enabled, make sure not
+ * to inline it so whatever fp stuff is done stays inside
+ */
+static noinline void dcn10_resource_construct_fp(
+	struct dc *dc)
+{
+	if (dc->ctx->dce_version == DCN_VERSION_1_01) {
+		struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
+		struct dcn_ip_params *dcn_ip = dc->dcn_ip;
+		struct display_mode_lib *dml = &dc->dml;
+
+		dml->ip.max_num_dpp = 3;
+		/* TODO how to handle 23.84? */
+		dcn_soc->dram_clock_change_latency = 23;
+		dcn_ip->max_num_dpp = 3;
+	}
+	if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+		dc->dcn_soc->urgent_latency = 3;
+		dc->debug.disable_dmcu = true;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
+	}
+
+
+	dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width / ddr4_dram_width;
+	ASSERT(dc->dcn_soc->number_of_channels < 3);
+	if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
+		dc->dcn_soc->number_of_channels = 2;
+
+	if (dc->dcn_soc->number_of_channels == 1) {
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
+		if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+			dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
+		}
+	}
+}
+
 static bool dcn10_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
@@ -1482,37 +1531,15 @@ static bool dcn10_resource_construct(
 	memcpy(dc->dcn_ip, &dcn10_ip_defaults, sizeof(dcn10_ip_defaults));
 	memcpy(dc->dcn_soc, &dcn10_soc_defaults, sizeof(dcn10_soc_defaults));
 
-	if (dc->ctx->dce_version == DCN_VERSION_1_01) {
-		struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
-		struct dcn_ip_params *dcn_ip = dc->dcn_ip;
-		struct display_mode_lib *dml = &dc->dml;
-
-		dml->ip.max_num_dpp = 3;
-		/* TODO how to handle 23.84? */
-		dcn_soc->dram_clock_change_latency = 23;
-		dcn_ip->max_num_dpp = 3;
-	}
-	if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
-		dc->dcn_soc->urgent_latency = 3;
-		dc->debug.disable_dmcu = true;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
-	}
-
-
-	dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width / ddr4_dram_width;
-	ASSERT(dc->dcn_soc->number_of_channels < 3);
-	if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
-		dc->dcn_soc->number_of_channels = 2;
-
-	if (dc->dcn_soc->number_of_channels == 1) {
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
-		if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
-			dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
-		}
-	}
+#if defined(CONFIG_ARM64)
+	/* Aarch64 does not support -msoft-float/-mfloat-abi=soft */
+	DC_FP_START();
+	dcn10_resource_construct_fp(dc);
+	DC_FP_END();
+#else
+	/* Other architectures we build for build this with soft-float */
+	dcn10_resource_construct_fp(dc);
+#endif
 
 	pool->base.pp_smu = dcn10_pp_smu_create(ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 07b2f9399671..842abb4c475b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -121,35 +121,35 @@ void enc1_update_generic_info_packet(
 	switch (packet_index) {
 	case 0:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC0_FRAME_UPDATE, 1);
+				AFMT_GENERIC0_IMMEDIATE_UPDATE, 1);
 		break;
 	case 1:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC1_FRAME_UPDATE, 1);
+				AFMT_GENERIC1_IMMEDIATE_UPDATE, 1);
 		break;
 	case 2:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC2_FRAME_UPDATE, 1);
+				AFMT_GENERIC2_IMMEDIATE_UPDATE, 1);
 		break;
 	case 3:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC3_FRAME_UPDATE, 1);
+				AFMT_GENERIC3_IMMEDIATE_UPDATE, 1);
 		break;
 	case 4:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC4_FRAME_UPDATE, 1);
+				AFMT_GENERIC4_IMMEDIATE_UPDATE, 1);
 		break;
 	case 5:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC5_FRAME_UPDATE, 1);
+				AFMT_GENERIC5_IMMEDIATE_UPDATE, 1);
 		break;
 	case 6:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC6_FRAME_UPDATE, 1);
+				AFMT_GENERIC6_IMMEDIATE_UPDATE, 1);
 		break;
 	case 7:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC7_FRAME_UPDATE, 1);
+				AFMT_GENERIC7_IMMEDIATE_UPDATE, 1);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index ed385b1477be..30eae7459d50 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -281,7 +281,14 @@ struct dcn10_stream_enc_registers {
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\
@@ -345,7 +352,14 @@ struct dcn10_stream_enc_registers {
 	type AFMT_GENERIC2_FRAME_UPDATE;\
 	type AFMT_GENERIC3_FRAME_UPDATE;\
 	type AFMT_GENERIC4_FRAME_UPDATE;\
+	type AFMT_GENERIC0_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC1_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC2_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC3_IMMEDIATE_UPDATE;\
 	type AFMT_GENERIC4_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC5_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC6_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC7_IMMEDIATE_UPDATE;\
 	type AFMT_GENERIC5_FRAME_UPDATE;\
 	type AFMT_GENERIC6_FRAME_UPDATE;\
 	type AFMT_GENERIC7_FRAME_UPDATE;\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index 5fcaf78334ff..624cb1341ef1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -17,6 +17,10 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec
 endif
 
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
index 667640c4b288..1118e33aaa2c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
@@ -94,6 +94,7 @@
 	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_CLOCK_EN, mask_sh), \
 	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DISPCLK_R_GATE_DIS, mask_sh), \
 	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DSCCLK_R_GATE_DIS, mask_sh), \
+	DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_DBG_EN, mask_sh), \
 	DSC_SF(DSCC0_DSCC_CONFIG0, ICH_RESET_AT_END_OF_LINE, mask_sh), \
 	DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_PER_LINE, mask_sh), \
 	DSC_SF(DSCC0_DSCC_CONFIG0, ALTERNATE_ICH_ENCODING_EN, mask_sh), \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 66180b4332f1..c8cfd3ba1c15 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1457,8 +1457,8 @@ static void dcn20_update_dchubp_dpp(
 
 	/* Any updates are handled in dc interface, just need to apply existing for plane enable */
 	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed ||
-			pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport)
-			&& pipe_ctx->stream->cursor_attributes.address.quad_part != 0) {
+			pipe_ctx->update_flags.bits.scaler || viewport_changed == true) &&
+			pipe_ctx->stream->cursor_attributes.address.quad_part != 0) {
 		dc->hwss.set_cursor_position(pipe_ctx);
 		dc->hwss.set_cursor_attribute(pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
index 3dde6f26de47..966e1790b9bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -34,6 +34,8 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = NULL,
 	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.disconnect_pipes = dcn10_disconnect_pipes,
+	.wait_for_pending_cleared = dcn10_wait_for_pending_cleared,
 	.post_unlock_program_front_end = dcn20_post_unlock_program_front_end,
 	.update_plane_addr = dcn20_update_plane_addr,
 	.update_dchub = dcn10_update_dchub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
index bf0044f7417e..864acd695cbb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
@@ -167,7 +167,9 @@
 	LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\
 	LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\
 	LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\
-	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh)
+	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh)
 
 #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\
 	LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\
@@ -229,8 +231,6 @@
 	SRI(RDPCSTX_PHY_FUSE3, RDPCSTX, id), \
 	SRI(DPCSTX_TX_CLOCK_CNTL, DPCSTX, id), \
 	SRI(DPCSTX_TX_CNTL, DPCSTX, id), \
-	SRI(DPCSTX_DEBUG_CONFIG, DPCSTX, id), \
-	SRI(RDPCSTX_DEBUG_CONFIG, RDPCSTX, id), \
 	SR(RDPCSTX0_RDPCSTX_SCRATCH)
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 790baf552695..1b9874445134 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -3141,7 +3141,7 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL);
+	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	BW_VAL_TRACE_COUNT();
@@ -3209,6 +3209,9 @@ static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc,
 	context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive =
 		dc->debug.enable_dram_clock_change_one_display_vactive;
 
+	/*Unsafe due to current pipe merge and split logic*/
+	ASSERT(context != dc->current_state);
+
 	if (fast_validate) {
 		return dcn20_validate_bandwidth_internal(dc, context, true);
 	}
@@ -3320,7 +3323,7 @@ enum dc_status dcn20_patch_unknown_plane_state(struct dc_plane_state *plane_stat
 	return DC_OK;
 }
 
-static struct resource_funcs dcn20_res_pool_funcs = {
+static const struct resource_funcs dcn20_res_pool_funcs = {
 	.destroy = dcn20_destroy_resource_pool,
 	.link_enc_create = dcn20_link_encoder_create,
 	.panel_cntl_create = dcn20_panel_cntl_create,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index 2c1959845c29..cdd39ee9761d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -95,7 +95,6 @@ struct display_stream_compressor *dcn20_dsc_create(
 	struct dc_context *ctx, uint32_t inst);
 void dcn20_dsc_destroy(struct display_stream_compressor **dsc);
 
-void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb);
 void dcn20_cap_soc_clocks(
 		struct _vcs_dpi_soc_bounding_box_st *bb,
 		struct pp_smu_nv_clock_table max_clocks);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 07684d3e375a..51a2f3d4c194 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -13,6 +13,10 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec
 endif
 
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
index b187f71afa65..2ba880c3943c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -35,6 +35,8 @@ static const struct hw_sequencer_funcs dcn21_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = NULL,
 	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.disconnect_pipes = dcn10_disconnect_pipes,
+	.wait_for_pending_cleared = dcn10_wait_for_pending_cleared,
 	.post_unlock_program_front_end = dcn20_post_unlock_program_front_end,
 	.update_plane_addr = dcn20_update_plane_addr,
 	.update_dchub = dcn10_update_dchub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 88d41a385add..78743ae37851 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1184,6 +1184,9 @@ bool dcn21_validate_bandwidth(struct dc *dc, struct dc_state *context,
 
 	BW_VAL_TRACE_COUNT();
 
+	/*Unsafe due to current pipe merge and split logic*/
+	ASSERT(context != dc->current_state);
+
 	out = dcn20_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel);
 
 	if (pipe_cnt == 0)
@@ -1754,7 +1757,7 @@ enum dc_status dcn21_patch_unknown_plane_state(struct dc_plane_state *plane_stat
 	return result;
 }
 
-static struct resource_funcs dcn21_res_pool_funcs = {
+static const struct resource_funcs dcn21_res_pool_funcs = {
 	.destroy = dcn21_destroy_resource_pool,
 	.link_enc_create = dcn21_link_encoder_create,
 	.panel_cntl_create = dcn21_panel_cntl_create,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
index 8e9fd59ccde8..2fbf879cd327 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
@@ -61,7 +61,10 @@
 	DPCS_DCN2_MASK_SH_LIST(mask_sh),\
 	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT_18_BIT, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\
-	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh)
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh)
+
 
 void dcn30_link_encoder_construct(
 	struct dcn20_link_encoder *enc20,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
index 9afee7160490..19daa456e3bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
@@ -35,6 +35,8 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = NULL,
 	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.disconnect_pipes = dcn10_disconnect_pipes,
+	.wait_for_pending_cleared = dcn10_wait_for_pending_cleared,
 	.post_unlock_program_front_end = dcn20_post_unlock_program_front_end,
 	.update_plane_addr = dcn20_update_plane_addr,
 	.update_dchub = dcn10_update_dchub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 653a571e366d..8be4f21169d0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -340,7 +340,7 @@ static const struct dce110_clk_src_mask cs_mask = {
 
 #define abm_regs(id)\
 [id] = {\
-		ABM_DCN301_REG_LIST(id)\
+		ABM_DCN30_REG_LIST(id)\
 }
 
 static const struct dce_abm_registers abm_regs[] = {
@@ -491,6 +491,8 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 [id] = {\
 	LE_DCN3_REG_LIST(id), \
 	UNIPHY_DCN2_REG_LIST(phyid), \
+	DPCS_DCN2_REG_LIST(id), \
+	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
 static const struct dce110_aux_registers_shift aux_shift = {
@@ -871,7 +873,7 @@ void dcn30_dpp_destroy(struct dpp **dpp)
 	*dpp = NULL;
 }
 
-struct dpp *dcn30_dpp_create(
+static struct dpp *dcn30_dpp_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -889,7 +891,8 @@ struct dpp *dcn30_dpp_create(
 	kfree(dpp);
 	return NULL;
 }
-struct output_pixel_processor *dcn30_opp_create(
+
+static struct output_pixel_processor *dcn30_opp_create(
 	struct dc_context *ctx, uint32_t inst)
 {
 	struct dcn20_opp *opp =
@@ -905,7 +908,7 @@ struct output_pixel_processor *dcn30_opp_create(
 	return &opp->base;
 }
 
-struct dce_aux *dcn30_aux_engine_create(
+static struct dce_aux *dcn30_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -924,6 +927,7 @@ struct dce_aux *dcn30_aux_engine_create(
 
 	return &aux_engine->base;
 }
+
 #define i2c_inst_regs(id) { I2C_HW_ENGINE_COMMON_REG_LIST(id) }
 
 static const struct dce_i2c_registers i2c_hw_regs[] = {
@@ -943,7 +947,7 @@ static const struct dce_i2c_mask i2c_masks = {
 		I2C_COMMON_MASK_SH_LIST_DCN2(_MASK)
 };
 
-struct dce_i2c_hw *dcn30_i2c_hw_create(
+static struct dce_i2c_hw *dcn30_i2c_hw_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -958,6 +962,7 @@ struct dce_i2c_hw *dcn30_i2c_hw_create(
 
 	return dce_i2c_hw;
 }
+
 static struct mpc *dcn30_mpc_create(
 		struct dc_context *ctx,
 		int num_mpcc,
@@ -1008,7 +1013,7 @@ struct hubbub *dcn30_hubbub_create(struct dc_context *ctx)
 	return &hubbub3->base;
 }
 
-struct timing_generator *dcn30_timing_generator_create(
+static struct timing_generator *dcn30_timing_generator_create(
 		struct dc_context *ctx,
 		uint32_t instance)
 {
@@ -1042,7 +1047,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.flags.bits.IS_TPS4_CAPABLE = true
 };
 
-struct link_encoder *dcn30_link_encoder_create(
+static struct link_encoder *dcn30_link_encoder_create(
 	const struct encoder_init_data *enc_init_data)
 {
 	struct dcn20_link_encoder *enc20 =
@@ -1063,7 +1068,7 @@ struct link_encoder *dcn30_link_encoder_create(
 	return &enc20->enc10.base;
 }
 
-struct panel_cntl *dcn30_panel_cntl_create(const struct panel_cntl_init_data *init_data)
+static struct panel_cntl *dcn30_panel_cntl_create(const struct panel_cntl_init_data *init_data)
 {
 	struct dce_panel_cntl *panel_cntl =
 		kzalloc(sizeof(struct dce_panel_cntl), GFP_KERNEL);
@@ -1311,7 +1316,7 @@ static void dcn30_resource_destruct(struct dcn30_resource_pool *pool)
 		dcn_dccg_destroy(&pool->base.dccg);
 }
 
-struct hubp *dcn30_hubp_create(
+static struct hubp *dcn30_hubp_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -1330,7 +1335,7 @@ struct hubp *dcn30_hubp_create(
 	return NULL;
 }
 
-bool dcn30_dwbc_create(struct dc_context *ctx, struct resource_pool *pool)
+static bool dcn30_dwbc_create(struct dc_context *ctx, struct resource_pool *pool)
 {
 	int i;
 	uint32_t pipe_count = pool->res_cap->num_dwb;
@@ -1355,7 +1360,7 @@ bool dcn30_dwbc_create(struct dc_context *ctx, struct resource_pool *pool)
 	return true;
 }
 
-bool dcn30_mmhubbub_create(struct dc_context *ctx, struct resource_pool *pool)
+static bool dcn30_mmhubbub_create(struct dc_context *ctx, struct resource_pool *pool)
 {
 	int i;
 	uint32_t pipe_count = pool->res_cap->num_dwb;
@@ -2292,7 +2297,7 @@ static void get_optimal_dcfclk_fclk_for_uclk(unsigned int uclk_mts,
                (dcn3_0_soc.return_bus_width_bytes * (dcn3_0_soc.max_avg_sdp_bw_use_normal_percent / 100));
 }
 
-static void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
+void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
 	unsigned int i, j;
 	unsigned int num_states = 0;
@@ -2412,7 +2417,7 @@ static void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw
 		dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
 }
 
-static struct resource_funcs dcn30_res_pool_funcs = {
+static const struct resource_funcs dcn30_res_pool_funcs = {
 	.destroy = dcn30_destroy_resource_pool,
 	.link_enc_create = dcn30_link_encoder_create,
 	.panel_cntl_create = dcn30_panel_cntl_create,
@@ -2420,6 +2425,7 @@ static struct resource_funcs dcn30_res_pool_funcs = {
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
+	.add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource,
 	.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
 	.populate_dml_writeback_from_context = dcn30_populate_dml_writeback_from_context,
 	.set_mcif_arb_params = dcn30_set_mcif_arb_params,
@@ -2683,7 +2689,7 @@ static bool dcn30_resource_construct(
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			(!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) ?
 			&res_create_funcs : &res_create_maximus_funcs)))
-			goto create_fail;
+		goto create_fail;
 
 	/* HW Sequencer and Plane caps */
 	dcn30_hw_sequencer_construct(dc);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
index 4b4a4d81c1e3..c9d5f94092a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
@@ -79,4 +79,7 @@ enum dc_status dcn30_add_stream_to_ctx(
 		struct dc *dc,
 		struct dc_state *new_ctx,
 		struct dc_stream_state *dc_stream);
+
+void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params);
+
 #endif /* _DCN30_RESOURCE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 417331438c30..dbc7e2abe379 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -33,6 +33,10 @@ ifdef CONFIG_PPC64
 dml_ccflags := -mhard-float -maltivec
 endif
 
+ifdef CONFIG_ARM64
+dml_rcflags := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
@@ -60,6 +64,13 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_rcflags)
 endif
 ifdef CONFIG_DRM_AMD_DC_DCN3_0
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) -Wframe-larger-than=2048
@@ -67,6 +78,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
 endif
 CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_ccflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_rcflags)
 
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index b54814f11b74..2beb284f89b0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -63,6 +63,7 @@ typedef struct {
 
 #define BPP_INVALID 0
 #define BPP_BLENDED_PIPE 0xffffffff
+#define DCN30_MAX_DSC_IMAGE_WIDTH 5184
 
 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib);
 static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation(
@@ -3984,6 +3985,9 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				} else if (v->PlaneRequiredDISPCLKWithoutODMCombine > v->MaxDispclkRoundedDownToDFSGranularity) {
 					v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1;
 					v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1;
+				} else if (v->DSCEnabled[k] && (v->HActive[k] > DCN30_MAX_DSC_IMAGE_WIDTH)) {
+					v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1;
+					v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1;
 				} else {
 					v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled;
 					v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithoutODMCombine;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index afdd4f0d9d71..b32093136089 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -467,7 +467,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 		mode_lib->vba.AudioSampleLayout[mode_lib->vba.NumberOfActivePlanes] =
 			1;
 		mode_lib->vba.DRAMClockChangeLatencyOverride = 0.0;
-		mode_lib->vba.DSCEnabled[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;;
+		mode_lib->vba.DSCEnabled[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;
 		mode_lib->vba.DSCEnable[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;
 		mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] =
 				dout->dsc_slices;
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index ea29cf95d470..f2624a1156e5 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -10,6 +10,10 @@ ifdef CONFIG_PPC64
 dsc_ccflags := -mhard-float -maltivec
 endif
 
+ifdef CONFIG_ARM64
+dsc_rcflags := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
@@ -28,6 +32,7 @@ endif
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_rcflags)
 
 DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 8cdaa6eef5d3..4c844cfaa956 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -34,6 +34,9 @@
 /* default DSC policy target bitrate limit is 16bpp */
 static uint32_t dsc_policy_max_target_bpp_limit = 16;
 
+/* default DSC policy enables DSC only when needed */
+static bool dsc_policy_enable_dsc_when_not_needed;
+
 static uint32_t dc_dsc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing)
 {
@@ -189,8 +192,10 @@ static bool dsc_throughput_from_dpcd(int dpcd_throughput, int *throughput)
 }
 
 
-static bool dsc_bpp_increment_div_from_dpcd(int bpp_increment_dpcd, uint32_t *bpp_increment_div)
+static bool dsc_bpp_increment_div_from_dpcd(uint8_t bpp_increment_dpcd, uint32_t *bpp_increment_div)
 {
+	// Mask bpp increment dpcd field to avoid reading other fields
+	bpp_increment_dpcd &= 0x7;
 
 	switch (bpp_increment_dpcd) {
 	case 0:
@@ -360,7 +365,7 @@ static bool decide_dsc_target_bpp_x16(
 
 	get_dsc_bandwidth_range(policy->min_target_bpp, policy->max_target_bpp,
 			dsc_common_caps, timing, &range);
-	if (target_bandwidth_kbps >= range.stream_kbps) {
+	if (!policy->enable_dsc_when_not_needed && target_bandwidth_kbps >= range.stream_kbps) {
 		/* enough bandwidth without dsc */
 		*target_bpp_x16 = 0;
 		should_use_dsc = false;
@@ -961,9 +966,20 @@ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, struct dc
 	/* internal upper limit, default 16 bpp */
 	if (policy->max_target_bpp > dsc_policy_max_target_bpp_limit)
 		policy->max_target_bpp = dsc_policy_max_target_bpp_limit;
+
+	/* enable DSC when not needed, default false */
+	if (dsc_policy_enable_dsc_when_not_needed)
+		policy->enable_dsc_when_not_needed = dsc_policy_enable_dsc_when_not_needed;
+	else
+		policy->enable_dsc_when_not_needed = false;
 }
 
 void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit)
 {
 	dsc_policy_max_target_bpp_limit = limit;
 }
+
+void dc_dsc_policy_set_enable_dsc_when_not_needed(bool enable)
+{
+	dsc_policy_enable_dsc_when_not_needed = enable;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index 0f2f4508e564..74c0943ed644 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -31,6 +31,18 @@ AMD_DAL_GPIO = $(addprefix $(AMDDALPATH)/dc/gpio/,$(GPIO))
 AMD_DISPLAY_FILES += $(AMD_DAL_GPIO)
 
 ###############################################################################
+# DCE 6x
+###############################################################################
+# all DCE6.x are derived from DCE6.0
+ifdef CONFIG_DRM_AMD_DC_SI
+GPIO_DCE60 = hw_translate_dce60.o hw_factory_dce60.o
+
+AMD_DAL_GPIO_DCE60 = $(addprefix $(AMDDALPATH)/dc/gpio/dce60/,$(GPIO_DCE60))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE60)
+endif
+
+###############################################################################
 # DCE 8x
 ###############################################################################
 # all DCE8.x are derived from DCE8.0
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.c b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.c
new file mode 100644
index 000000000000..cc69acd8ada7
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.c
@@ -0,0 +1,175 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "include/gpio_types.h"
+#include "../hw_factory.h"
+
+#include "hw_factory_dce60.h"
+
+#include "../hw_gpio.h"
+#include "../hw_ddc.h"
+#include "../hw_hpd.h"
+#include "../hw_generic.h"
+
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+
+#define REG(reg_name)\
+		mm ## reg_name
+
+#include "reg_helper.h"
+#include "../hpd_regs.h"
+
+#define HPD_REG_LIST_DCE6(id) \
+	HPD_GPIO_REG_LIST(id), \
+	.int_status = mmDC_HPD ## id ## _INT_STATUS,\
+	.toggle_filt_cntl = mmDC_HPD ## id ## _TOGGLE_FILT_CNTL
+
+#define HPD_MASK_SH_LIST_DCE6(mask_sh) \
+		.DC_HPD_SENSE_DELAYED = DC_HPD1_INT_STATUS__DC_HPD1_SENSE_DELAYED ## mask_sh,\
+		.DC_HPD_SENSE = DC_HPD1_INT_STATUS__DC_HPD1_SENSE ## mask_sh,\
+		.DC_HPD_CONNECT_INT_DELAY = DC_HPD1_TOGGLE_FILT_CNTL__DC_HPD1_CONNECT_INT_DELAY ## mask_sh,\
+		.DC_HPD_DISCONNECT_INT_DELAY = DC_HPD1_TOGGLE_FILT_CNTL__DC_HPD1_DISCONNECT_INT_DELAY ## mask_sh
+
+#define hpd_regs(id) \
+{\
+	HPD_REG_LIST_DCE6(id)\
+}
+
+static const struct hpd_registers hpd_regs[] = {
+	hpd_regs(1),
+	hpd_regs(2),
+	hpd_regs(3),
+	hpd_regs(4),
+	hpd_regs(5),
+	hpd_regs(6)
+};
+
+static const struct hpd_sh_mask hpd_shift = {
+		HPD_MASK_SH_LIST_DCE6(__SHIFT)
+};
+
+static const struct hpd_sh_mask hpd_mask = {
+		HPD_MASK_SH_LIST_DCE6(_MASK)
+};
+
+#include "../ddc_regs.h"
+
+ /* set field name */
+#define SF_DDC(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+static const struct ddc_registers ddc_data_regs[] = {
+	ddc_data_regs(1),
+	ddc_data_regs(2),
+	ddc_data_regs(3),
+	ddc_data_regs(4),
+	ddc_data_regs(5),
+	ddc_data_regs(6),
+	ddc_vga_data_regs,
+	ddc_i2c_data_regs
+};
+
+static const struct ddc_registers ddc_clk_regs[] = {
+	ddc_clk_regs(1),
+	ddc_clk_regs(2),
+	ddc_clk_regs(3),
+	ddc_clk_regs(4),
+	ddc_clk_regs(5),
+	ddc_clk_regs(6),
+	ddc_vga_clk_regs,
+	ddc_i2c_clk_regs
+};
+
+static const struct ddc_sh_mask ddc_shift = {
+		DDC_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct ddc_sh_mask ddc_mask = {
+		DDC_MASK_SH_LIST(_MASK)
+};
+
+static void define_ddc_registers(
+		struct hw_gpio_pin *pin,
+		uint32_t en)
+{
+	struct hw_ddc *ddc = HW_DDC_FROM_BASE(pin);
+
+	switch (pin->id) {
+	case GPIO_ID_DDC_DATA:
+		ddc->regs = &ddc_data_regs[en];
+		ddc->base.regs = &ddc_data_regs[en].gpio;
+		break;
+	case GPIO_ID_DDC_CLOCK:
+		ddc->regs = &ddc_clk_regs[en];
+		ddc->base.regs = &ddc_clk_regs[en].gpio;
+		break;
+	default:
+		ASSERT_CRITICAL(false);
+		return;
+	}
+
+	ddc->shifts = &ddc_shift;
+	ddc->masks = &ddc_mask;
+
+}
+
+static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en)
+{
+	struct hw_hpd *hpd = HW_HPD_FROM_BASE(pin);
+
+	hpd->regs = &hpd_regs[en];
+	hpd->shifts = &hpd_shift;
+	hpd->masks = &hpd_mask;
+	hpd->base.regs = &hpd_regs[en].gpio;
+}
+
+static const struct hw_factory_funcs funcs = {
+	.init_ddc_data = dal_hw_ddc_init,
+	.init_generic = NULL,
+	.init_hpd = dal_hw_hpd_init,
+	.get_ddc_pin = dal_hw_ddc_get_pin,
+	.get_hpd_pin = dal_hw_hpd_get_pin,
+	.get_generic_pin = NULL,
+	.define_hpd_registers = define_hpd_registers,
+	.define_ddc_registers = define_ddc_registers
+};
+
+void dal_hw_factory_dce60_init(
+	struct hw_factory *factory)
+{
+	factory->number_of_pins[GPIO_ID_DDC_DATA] = 8;
+	factory->number_of_pins[GPIO_ID_DDC_CLOCK] = 8;
+	factory->number_of_pins[GPIO_ID_GENERIC] = 7;
+	factory->number_of_pins[GPIO_ID_HPD] = 6;
+	factory->number_of_pins[GPIO_ID_GPIO_PAD] = 31;
+	factory->number_of_pins[GPIO_ID_VIP_PAD] = 0;
+	factory->number_of_pins[GPIO_ID_SYNC] = 2;
+	factory->number_of_pins[GPIO_ID_GSL] = 4;
+
+	factory->funcs = &funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.h b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.h
new file mode 100644
index 000000000000..1fd54ff8979c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_factory_dce60.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_HW_FACTORY_DCE60_H__
+#define __DAL_HW_FACTORY_DCE60_H__
+
+void dal_hw_factory_dce60_init(
+	struct hw_factory *factory);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.c b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.c
new file mode 100644
index 000000000000..255df31ec577
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.c
@@ -0,0 +1,411 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+
+/*
+ * Pre-requisites: headers required by header of this unit
+ */
+#include "include/gpio_types.h"
+#include "../hw_translate.h"
+
+#include "hw_translate_dce60.h"
+
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+#include "smu/smu_6_0_d.h"
+
+/*
+ * @brief
+ * Returns index of first bit (starting with LSB) which is set
+ */
+static uint32_t index_from_vector(
+	uint32_t vector)
+{
+	uint32_t result = 0;
+	uint32_t mask = 1;
+
+	do {
+		if (vector == mask)
+			return result;
+
+		++result;
+		mask <<= 1;
+	} while (mask);
+
+	BREAK_TO_DEBUGGER();
+
+	return GPIO_ENUM_UNKNOWN;
+}
+
+static bool offset_to_id(
+	uint32_t offset,
+	uint32_t mask,
+	enum gpio_id *id,
+	uint32_t *en)
+{
+	switch (offset) {
+	/* GENERIC */
+	case mmDC_GPIO_GENERIC_A:
+		*id = GPIO_ID_GENERIC;
+		switch (mask) {
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICA_A_MASK:
+			*en = GPIO_GENERIC_A;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICB_A_MASK:
+			*en = GPIO_GENERIC_B;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICC_A_MASK:
+			*en = GPIO_GENERIC_C;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICD_A_MASK:
+			*en = GPIO_GENERIC_D;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICE_A_MASK:
+			*en = GPIO_GENERIC_E;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICF_A_MASK:
+			*en = GPIO_GENERIC_F;
+			return true;
+		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICG_A_MASK:
+			*en = GPIO_GENERIC_G;
+			return true;
+		default:
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+	break;
+	/* HPD */
+	case mmDC_GPIO_HPD_A:
+		*id = GPIO_ID_HPD;
+		switch (mask) {
+		case DC_GPIO_HPD_A__DC_GPIO_HPD1_A_MASK:
+			*en = GPIO_HPD_1;
+			return true;
+		case DC_GPIO_HPD_A__DC_GPIO_HPD2_A_MASK:
+			*en = GPIO_HPD_2;
+			return true;
+		case DC_GPIO_HPD_A__DC_GPIO_HPD3_A_MASK:
+			*en = GPIO_HPD_3;
+			return true;
+		case DC_GPIO_HPD_A__DC_GPIO_HPD4_A_MASK:
+			*en = GPIO_HPD_4;
+			return true;
+		case DC_GPIO_HPD_A__DC_GPIO_HPD5_A_MASK:
+			*en = GPIO_HPD_5;
+			return true;
+		case DC_GPIO_HPD_A__DC_GPIO_HPD6_A_MASK:
+			*en = GPIO_HPD_6;
+			return true;
+		default:
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+	break;
+	/* SYNCA */
+	case mmDC_GPIO_SYNCA_A:
+		*id = GPIO_ID_SYNC;
+		switch (mask) {
+		case DC_GPIO_SYNCA_A__DC_GPIO_HSYNCA_A_MASK:
+			*en = GPIO_SYNC_HSYNC_A;
+			return true;
+		case DC_GPIO_SYNCA_A__DC_GPIO_VSYNCA_A_MASK:
+			*en = GPIO_SYNC_VSYNC_A;
+			return true;
+		default:
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+	break;
+	/* mmDC_GPIO_GENLK_MASK */
+	case mmDC_GPIO_GENLK_A:
+		*id = GPIO_ID_GSL;
+		switch (mask) {
+		case DC_GPIO_GENLK_A__DC_GPIO_GENLK_CLK_A_MASK:
+			*en = GPIO_GSL_GENLOCK_CLOCK;
+			return true;
+		case DC_GPIO_GENLK_A__DC_GPIO_GENLK_VSYNC_A_MASK:
+			*en = GPIO_GSL_GENLOCK_VSYNC;
+			return true;
+		case DC_GPIO_GENLK_A__DC_GPIO_SWAPLOCK_A_A_MASK:
+			*en = GPIO_GSL_SWAPLOCK_A;
+			return true;
+		case DC_GPIO_GENLK_A__DC_GPIO_SWAPLOCK_B_A_MASK:
+			*en = GPIO_GSL_SWAPLOCK_B;
+			return true;
+		default:
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+	break;
+	/* GPIOPAD */
+	case mmGPIOPAD_A:
+		*id = GPIO_ID_GPIO_PAD;
+		*en = index_from_vector(mask);
+		return (*en <= GPIO_GPIO_PAD_MAX);
+	/* DDC */
+	/* we don't care about the GPIO_ID for DDC
+	 * in DdcHandle it will use GPIO_ID_DDC_DATA/GPIO_ID_DDC_CLOCK
+	 * directly in the create method */
+	case mmDC_GPIO_DDC1_A:
+		*en = GPIO_DDC_LINE_DDC1;
+		return true;
+	case mmDC_GPIO_DDC2_A:
+		*en = GPIO_DDC_LINE_DDC2;
+		return true;
+	case mmDC_GPIO_DDC3_A:
+		*en = GPIO_DDC_LINE_DDC3;
+		return true;
+	case mmDC_GPIO_DDC4_A:
+		*en = GPIO_DDC_LINE_DDC4;
+		return true;
+	case mmDC_GPIO_DDC5_A:
+		*en = GPIO_DDC_LINE_DDC5;
+		return true;
+	case mmDC_GPIO_DDC6_A:
+		*en = GPIO_DDC_LINE_DDC6;
+		return true;
+	case mmDC_GPIO_DDCVGA_A:
+		*en = GPIO_DDC_LINE_DDC_VGA;
+		return true;
+	/* GPIO_I2CPAD */
+	case mmDC_GPIO_I2CPAD_A:
+		*en = GPIO_DDC_LINE_I2C_PAD;
+		return true;
+	/* Not implemented */
+	case mmDC_GPIO_PWRSEQ_A:
+	case mmDC_GPIO_PAD_STRENGTH_1:
+	case mmDC_GPIO_PAD_STRENGTH_2:
+	case mmDC_GPIO_DEBUG:
+		return false;
+	/* UNEXPECTED */
+	default:
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+}
+
+static bool id_to_offset(
+	enum gpio_id id,
+	uint32_t en,
+	struct gpio_pin_info *info)
+{
+	bool result = true;
+
+	switch (id) {
+	case GPIO_ID_DDC_DATA:
+		info->mask = DC_GPIO_DDC6_A__DC_GPIO_DDC6DATA_A_MASK;
+		switch (en) {
+		case GPIO_DDC_LINE_DDC1:
+			info->offset = mmDC_GPIO_DDC1_A;
+		break;
+		case GPIO_DDC_LINE_DDC2:
+			info->offset = mmDC_GPIO_DDC2_A;
+		break;
+		case GPIO_DDC_LINE_DDC3:
+			info->offset = mmDC_GPIO_DDC3_A;
+		break;
+		case GPIO_DDC_LINE_DDC4:
+			info->offset = mmDC_GPIO_DDC4_A;
+		break;
+		case GPIO_DDC_LINE_DDC5:
+			info->offset = mmDC_GPIO_DDC5_A;
+		break;
+		case GPIO_DDC_LINE_DDC6:
+			info->offset = mmDC_GPIO_DDC6_A;
+		break;
+		case GPIO_DDC_LINE_DDC_VGA:
+			info->offset = mmDC_GPIO_DDCVGA_A;
+		break;
+		case GPIO_DDC_LINE_I2C_PAD:
+			info->offset = mmDC_GPIO_I2CPAD_A;
+		break;
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_DDC_CLOCK:
+		info->mask = DC_GPIO_DDC6_A__DC_GPIO_DDC6CLK_A_MASK;
+		switch (en) {
+		case GPIO_DDC_LINE_DDC1:
+			info->offset = mmDC_GPIO_DDC1_A;
+		break;
+		case GPIO_DDC_LINE_DDC2:
+			info->offset = mmDC_GPIO_DDC2_A;
+		break;
+		case GPIO_DDC_LINE_DDC3:
+			info->offset = mmDC_GPIO_DDC3_A;
+		break;
+		case GPIO_DDC_LINE_DDC4:
+			info->offset = mmDC_GPIO_DDC4_A;
+		break;
+		case GPIO_DDC_LINE_DDC5:
+			info->offset = mmDC_GPIO_DDC5_A;
+		break;
+		case GPIO_DDC_LINE_DDC6:
+			info->offset = mmDC_GPIO_DDC6_A;
+		break;
+		case GPIO_DDC_LINE_DDC_VGA:
+			info->offset = mmDC_GPIO_DDCVGA_A;
+		break;
+		case GPIO_DDC_LINE_I2C_PAD:
+			info->offset = mmDC_GPIO_I2CPAD_A;
+		break;
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_GENERIC:
+		info->offset = mmDC_GPIO_GENERIC_A;
+		switch (en) {
+		case GPIO_GENERIC_A:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICA_A_MASK;
+		break;
+		case GPIO_GENERIC_B:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICB_A_MASK;
+		break;
+		case GPIO_GENERIC_C:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICC_A_MASK;
+		break;
+		case GPIO_GENERIC_D:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICD_A_MASK;
+		break;
+		case GPIO_GENERIC_E:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICE_A_MASK;
+		break;
+		case GPIO_GENERIC_F:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICF_A_MASK;
+		break;
+		case GPIO_GENERIC_G:
+			info->mask = DC_GPIO_GENERIC_A__DC_GPIO_GENERICG_A_MASK;
+		break;
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_HPD:
+		info->offset = mmDC_GPIO_HPD_A;
+		switch (en) {
+		case GPIO_HPD_1:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD1_A_MASK;
+		break;
+		case GPIO_HPD_2:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD2_A_MASK;
+		break;
+		case GPIO_HPD_3:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD3_A_MASK;
+		break;
+		case GPIO_HPD_4:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD4_A_MASK;
+		break;
+		case GPIO_HPD_5:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD5_A_MASK;
+		break;
+		case GPIO_HPD_6:
+			info->mask = DC_GPIO_HPD_A__DC_GPIO_HPD6_A_MASK;
+		break;
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_SYNC:
+		switch (en) {
+		case GPIO_SYNC_HSYNC_A:
+			info->offset = mmDC_GPIO_SYNCA_A;
+			info->mask = DC_GPIO_SYNCA_A__DC_GPIO_HSYNCA_A_MASK;
+		break;
+		case GPIO_SYNC_VSYNC_A:
+			info->offset = mmDC_GPIO_SYNCA_A;
+			info->mask = DC_GPIO_SYNCA_A__DC_GPIO_VSYNCA_A_MASK;
+		break;
+		case GPIO_SYNC_HSYNC_B:
+		case GPIO_SYNC_VSYNC_B:
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_GSL:
+		switch (en) {
+		case GPIO_GSL_GENLOCK_CLOCK:
+			info->offset = mmDC_GPIO_GENLK_A;
+			info->mask = DC_GPIO_GENLK_A__DC_GPIO_GENLK_CLK_A_MASK;
+		break;
+		case GPIO_GSL_GENLOCK_VSYNC:
+			info->offset = mmDC_GPIO_GENLK_A;
+			info->mask =
+				DC_GPIO_GENLK_A__DC_GPIO_GENLK_VSYNC_A_MASK;
+		break;
+		case GPIO_GSL_SWAPLOCK_A:
+			info->offset = mmDC_GPIO_GENLK_A;
+			info->mask = DC_GPIO_GENLK_A__DC_GPIO_SWAPLOCK_A_A_MASK;
+		break;
+		case GPIO_GSL_SWAPLOCK_B:
+			info->offset = mmDC_GPIO_GENLK_A;
+			info->mask = DC_GPIO_GENLK_A__DC_GPIO_SWAPLOCK_B_A_MASK;
+		break;
+		default:
+			BREAK_TO_DEBUGGER();
+			result = false;
+		}
+	break;
+	case GPIO_ID_GPIO_PAD:
+		info->offset = mmGPIOPAD_A;
+		info->mask = (1 << en);
+		result = (info->mask <= GPIO_GPIO_PAD_MAX);
+	break;
+	case GPIO_ID_VIP_PAD:
+	default:
+		BREAK_TO_DEBUGGER();
+		result = false;
+	}
+
+	if (result) {
+		info->offset_y = info->offset + 2;
+		info->offset_en = info->offset + 1;
+		info->offset_mask = info->offset - 1;
+
+		info->mask_y = info->mask;
+		info->mask_en = info->mask;
+		info->mask_mask = info->mask;
+	}
+
+	return result;
+}
+
+static const struct hw_translate_funcs funcs = {
+		.offset_to_id = offset_to_id,
+		.id_to_offset = id_to_offset,
+};
+
+void dal_hw_translate_dce60_init(
+	struct hw_translate *translate)
+{
+	translate->funcs = &funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.h b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.h
new file mode 100644
index 000000000000..1e811f35cec7
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce60/hw_translate_dce60.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_HW_TRANSLATE_DCE60_H__
+#define __DAL_HW_TRANSLATE_DCE60_H__
+
+void dal_hw_translate_dce60_init(
+	struct hw_translate *tr);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index e5cfe28bc7bf..6fc8a6e9dc15 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -42,6 +42,9 @@
  * Post-requisites: headers required by this unit
  */
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/hw_factory_dce60.h"
+#endif
 #include "dce80/hw_factory_dce80.h"
 #include "dce110/hw_factory_dce110.h"
 #include "dce120/hw_factory_dce120.h"
@@ -71,6 +74,13 @@ bool dal_hw_factory_init(
 	}
 
 	switch (dce_version) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case DCE_VERSION_6_0:
+	case DCE_VERSION_6_1:
+	case DCE_VERSION_6_4:
+		dal_hw_factory_dce60_init(factory);
+		return true;
+#endif
 	case DCE_VERSION_8_0:
 	case DCE_VERSION_8_1:
 	case DCE_VERSION_8_3:
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index efea7cb0f17c..3a93c945e57d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -40,6 +40,9 @@
  * Post-requisites: headers required by this unit
  */
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/hw_translate_dce60.h"
+#endif
 #include "dce80/hw_translate_dce80.h"
 #include "dce110/hw_translate_dce110.h"
 #include "dce120/hw_translate_dce120.h"
@@ -69,6 +72,13 @@ bool dal_hw_translate_init(
 	}
 
 	switch (dce_version) {
+#if defined(CONFIG_DRM_AMD_DC_SI)
+	case DCE_VERSION_6_0:
+	case DCE_VERSION_6_1:
+	case DCE_VERSION_6_4:
+		dal_hw_translate_dce60_init(translate);
+		return true;
+#endif
 	case DCE_VERSION_8_0:
 	case DCE_VERSION_8_1:
 	case DCE_VERSION_8_3:
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 5994d2a33c40..947d6106f341 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -230,6 +230,8 @@ struct clk_mgr_funcs {
 
 	int (*get_dp_ref_clk_frequency)(struct clk_mgr *clk_mgr);
 
+	void (*set_low_power_state)(struct clk_mgr *clk_mgr);
+
 	void (*init_clocks)(struct clk_mgr *clk_mgr);
 
 	void (*enable_pme_wa) (struct clk_mgr *clk_mgr);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index 72743058836d..949b61351ede 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -89,6 +89,11 @@ enum dentist_divider_range {
 	.DPREFCLK_CNTL = mmDPREFCLK_CNTL, \
 	.DENTIST_DISPCLK_CNTL = mmDENTIST_DISPCLK_CNTL
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define CLK_COMMON_REG_LIST_DCE60_BASE() \
+	SR(DENTIST_DISPCLK_CNTL)
+#endif
+
 #define CLK_COMMON_REG_LIST_DCN_BASE() \
 	SR(DENTIST_DISPCLK_CNTL)
 
@@ -115,6 +120,12 @@ enum dentist_divider_range {
 	CLK_SF(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, mask_sh), \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, mask_sh)
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#define CLK_COMMON_MASK_SH_LIST_DCE60_COMMON_BASE(mask_sh) \
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh)
+#endif
+
 #define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh)
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
index f9ab5abb6462..48eac622c6a0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
@@ -49,6 +49,7 @@ struct panel_cntl_funcs {
 	void (*store_backlight_level)(struct panel_cntl *panel_cntl);
 	void (*driver_set_backlight)(struct panel_cntl *panel_cntl,
 			uint32_t backlight_pwm_u16_16);
+	uint32_t (*get_current_backlight)(struct panel_cntl *panel_cntl);
 };
 
 struct panel_cntl_init_data {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 3c986717dcd5..64c1be818b0e 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -67,6 +67,10 @@ struct hw_sequencer_funcs {
 			int num_planes, struct dc_state *context);
 	void (*program_front_end_for_ctx)(struct dc *dc,
 			struct dc_state *context);
+	bool (*disconnect_pipes)(struct dc *dc,
+			struct dc_state *context);
+	void (*wait_for_pending_cleared)(struct dc *dc,
+			struct dc_state *context);
 	void (*post_unlock_program_front_end)(struct dc *dc,
 			struct dc_state *context);
 	void (*update_plane_addr)(const struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index 3352b79fb1cb..405c25322607 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -31,6 +31,17 @@ AMD_DAL_IRQ = $(addprefix $(AMDDALPATH)/dc/irq/,$(IRQ))
 AMD_DISPLAY_FILES += $(AMD_DAL_IRQ)
 
 ###############################################################################
+# DCE 6x
+###############################################################################
+ifdef CONFIG_DRM_AMD_DC_SI
+IRQ_DCE60 = irq_service_dce60.o
+
+AMD_DAL_IRQ_DCE60 = $(addprefix $(AMDDALPATH)/dc/irq/dce60/,$(IRQ_DCE60))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE60)
+endif
+
+###############################################################################
 # DCE 8x
 ###############################################################################
 IRQ_DCE80 = irq_service_dce80.o
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.c b/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.c
new file mode 100644
index 000000000000..524481885fd0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.c
@@ -0,0 +1,395 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/slab.h>
+
+#include "dm_services.h"
+
+#include "include/logger_interface.h"
+
+#include "irq_service_dce60.h"
+#include "../dce110/irq_service_dce110.h"
+
+#include "dce/dce_6_0_d.h"
+#include "dce/dce_6_0_sh_mask.h"
+
+#include "ivsrcid/ivsrcid_vislands30.h"
+
+#define VISLANDS30_IV_SRCID_D1_VBLANK                        1
+#define VISLANDS30_IV_SRCID_D2_VBLANK                        2
+#define VISLANDS30_IV_SRCID_D3_VBLANK                        3
+#define VISLANDS30_IV_SRCID_D4_VBLANK                        4
+#define VISLANDS30_IV_SRCID_D5_VBLANK                        5
+#define VISLANDS30_IV_SRCID_D6_VBLANK                        6
+
+#include "dc_types.h"
+
+static bool hpd_ack(
+	struct irq_service *irq_service,
+	const struct irq_source_info *info)
+{
+	uint32_t addr = info->status_reg;
+	uint32_t value = dm_read_reg(irq_service->ctx, addr);
+	uint32_t current_status =
+		get_reg_field_value(
+			value,
+			DC_HPD1_INT_STATUS,
+			DC_HPD1_SENSE_DELAYED);
+
+	dal_irq_service_ack_generic(irq_service, info);
+
+	value = dm_read_reg(irq_service->ctx, info->enable_reg);
+
+	set_reg_field_value(
+		value,
+		current_status ? 0 : 1,
+		DC_HPD1_INT_CONTROL,
+		DC_HPD1_INT_POLARITY);
+
+	dm_write_reg(irq_service->ctx, info->enable_reg, value);
+
+	return true;
+}
+
+static const struct irq_source_info_funcs hpd_irq_info_funcs = {
+	.set = NULL,
+	.ack = hpd_ack
+};
+
+static const struct irq_source_info_funcs hpd_rx_irq_info_funcs = {
+	.set = NULL,
+	.ack = NULL
+};
+
+static const struct irq_source_info_funcs pflip_irq_info_funcs = {
+	.set = NULL,
+	.ack = NULL
+};
+
+static const struct irq_source_info_funcs vblank_irq_info_funcs = {
+	.set = dce110_vblank_set,
+	.ack = NULL
+};
+
+static const struct irq_source_info_funcs vblank_irq_info_funcs_dce60 = {
+	.set = NULL,
+	.ack = NULL
+};
+
+#define hpd_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_INVALID + reg_num] = {\
+		.enable_reg = mmDC_HPD ## reg_num ## _INT_CONTROL,\
+		.enable_mask = DC_HPD1_INT_CONTROL__DC_HPD1_INT_EN_MASK,\
+		.enable_value = {\
+			DC_HPD1_INT_CONTROL__DC_HPD1_INT_EN_MASK,\
+			~DC_HPD1_INT_CONTROL__DC_HPD1_INT_EN_MASK\
+		},\
+		.ack_reg = mmDC_HPD ## reg_num ## _INT_CONTROL,\
+		.ack_mask = DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK,\
+		.ack_value = DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK,\
+		.status_reg = mmDC_HPD ## reg_num ## _INT_STATUS,\
+		.funcs = &hpd_irq_info_funcs\
+	}
+
+#define hpd_rx_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_HPD6 + reg_num] = {\
+		.enable_reg = mmDC_HPD ## reg_num ## _INT_CONTROL,\
+		.enable_mask = DC_HPD1_INT_CONTROL__DC_HPD1_RX_INT_EN_MASK,\
+		.enable_value = {\
+				DC_HPD1_INT_CONTROL__DC_HPD1_RX_INT_EN_MASK,\
+			~DC_HPD1_INT_CONTROL__DC_HPD1_RX_INT_EN_MASK },\
+		.ack_reg = mmDC_HPD ## reg_num ## _INT_CONTROL,\
+		.ack_mask = DC_HPD1_INT_CONTROL__DC_HPD1_RX_INT_ACK_MASK,\
+		.ack_value = DC_HPD1_INT_CONTROL__DC_HPD1_RX_INT_ACK_MASK,\
+		.status_reg = mmDC_HPD ## reg_num ## _INT_STATUS,\
+		.funcs = &hpd_rx_irq_info_funcs\
+	}
+
+#define pflip_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_PFLIP1 + reg_num] = {\
+		.enable_reg = mmDCP ## reg_num ## _GRPH_INTERRUPT_CONTROL,\
+		.enable_mask =\
+		GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK,\
+		.enable_value = {\
+			GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK,\
+			~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK},\
+		.ack_reg = mmDCP ## reg_num ## _GRPH_INTERRUPT_STATUS,\
+		.ack_mask = GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK,\
+		.ack_value = GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK,\
+		.status_reg = mmDCP ## reg_num ##_GRPH_INTERRUPT_STATUS,\
+		.funcs = &pflip_irq_info_funcs\
+ 	}
+
+#define vupdate_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_VUPDATE1 + reg_num] = {\
+		.enable_reg = mmCRTC ## reg_num ## _CRTC_INTERRUPT_CONTROL,\
+		.enable_mask =\
+		CRTC_INTERRUPT_CONTROL__CRTC_V_UPDATE_INT_MSK_MASK,\
+		.enable_value = {\
+			CRTC_INTERRUPT_CONTROL__CRTC_V_UPDATE_INT_MSK_MASK,\
+			~CRTC_INTERRUPT_CONTROL__CRTC_V_UPDATE_INT_MSK_MASK},\
+		.ack_reg = mmCRTC ## reg_num ## _CRTC_V_UPDATE_INT_STATUS,\
+		.ack_mask =\
+		CRTC_V_UPDATE_INT_STATUS__CRTC_V_UPDATE_INT_CLEAR_MASK,\
+		.ack_value =\
+		CRTC_V_UPDATE_INT_STATUS__CRTC_V_UPDATE_INT_CLEAR_MASK,\
+		.funcs = &vblank_irq_info_funcs\
+	}
+
+#define vblank_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_VBLANK1 + reg_num] = {\
+		.enable_reg = mmLB ## reg_num ## _INT_MASK,\
+		.enable_mask =\
+			INT_MASK__VBLANK_INT_MASK,\
+		.enable_value = {\
+			INT_MASK__VBLANK_INT_MASK,\
+			~INT_MASK__VBLANK_INT_MASK},\
+		.ack_reg = mmLB ## reg_num ## _VBLANK_STATUS,\
+		.ack_mask =\
+		VBLANK_STATUS__VBLANK_ACK_MASK,\
+		.ack_value =\
+		VBLANK_STATUS__VBLANK_ACK_MASK,\
+		.funcs = &vblank_irq_info_funcs_dce60\
+	}
+
+#define dummy_irq_entry() \
+	{\
+		.funcs = &dummy_irq_info_funcs\
+	}
+
+#define i2c_int_entry(reg_num) \
+	[DC_IRQ_SOURCE_I2C_DDC ## reg_num] = dummy_irq_entry()
+
+#define dp_sink_int_entry(reg_num) \
+	[DC_IRQ_SOURCE_DPSINK ## reg_num] = dummy_irq_entry()
+
+#define gpio_pad_int_entry(reg_num) \
+	[DC_IRQ_SOURCE_GPIOPAD ## reg_num] = dummy_irq_entry()
+
+#define dc_underflow_int_entry(reg_num) \
+	[DC_IRQ_SOURCE_DC ## reg_num ## UNDERFLOW] = dummy_irq_entry()
+
+
+static const struct irq_source_info_funcs dummy_irq_info_funcs = {
+	.set = dal_irq_service_dummy_set,
+	.ack = dal_irq_service_dummy_ack
+};
+
+static const struct irq_source_info
+irq_source_info_dce60[DAL_IRQ_SOURCES_NUMBER] = {
+	[DC_IRQ_SOURCE_INVALID] = dummy_irq_entry(),
+	hpd_int_entry(1),
+	hpd_int_entry(2),
+	hpd_int_entry(3),
+	hpd_int_entry(4),
+	hpd_int_entry(5),
+	hpd_int_entry(6),
+	hpd_rx_int_entry(1),
+	hpd_rx_int_entry(2),
+	hpd_rx_int_entry(3),
+	hpd_rx_int_entry(4),
+	hpd_rx_int_entry(5),
+	hpd_rx_int_entry(6),
+	i2c_int_entry(1),
+	i2c_int_entry(2),
+	i2c_int_entry(3),
+	i2c_int_entry(4),
+	i2c_int_entry(5),
+	i2c_int_entry(6),
+	dp_sink_int_entry(1),
+	dp_sink_int_entry(2),
+	dp_sink_int_entry(3),
+	dp_sink_int_entry(4),
+	dp_sink_int_entry(5),
+	dp_sink_int_entry(6),
+	[DC_IRQ_SOURCE_TIMER] = dummy_irq_entry(),
+	pflip_int_entry(0),
+	pflip_int_entry(1),
+	pflip_int_entry(2),
+	pflip_int_entry(3),
+	pflip_int_entry(4),
+	pflip_int_entry(5),
+	[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
+	gpio_pad_int_entry(0),
+	gpio_pad_int_entry(1),
+	gpio_pad_int_entry(2),
+	gpio_pad_int_entry(3),
+	gpio_pad_int_entry(4),
+	gpio_pad_int_entry(5),
+	gpio_pad_int_entry(6),
+	gpio_pad_int_entry(7),
+	gpio_pad_int_entry(8),
+	gpio_pad_int_entry(9),
+	gpio_pad_int_entry(10),
+	gpio_pad_int_entry(11),
+	gpio_pad_int_entry(12),
+	gpio_pad_int_entry(13),
+	gpio_pad_int_entry(14),
+	gpio_pad_int_entry(15),
+	gpio_pad_int_entry(16),
+	gpio_pad_int_entry(17),
+	gpio_pad_int_entry(18),
+	gpio_pad_int_entry(19),
+	gpio_pad_int_entry(20),
+	gpio_pad_int_entry(21),
+	gpio_pad_int_entry(22),
+	gpio_pad_int_entry(23),
+	gpio_pad_int_entry(24),
+	gpio_pad_int_entry(25),
+	gpio_pad_int_entry(26),
+	gpio_pad_int_entry(27),
+	gpio_pad_int_entry(28),
+	gpio_pad_int_entry(29),
+	gpio_pad_int_entry(30),
+	dc_underflow_int_entry(1),
+	dc_underflow_int_entry(2),
+	dc_underflow_int_entry(3),
+	dc_underflow_int_entry(4),
+	dc_underflow_int_entry(5),
+	dc_underflow_int_entry(6),
+	[DC_IRQ_SOURCE_DMCU_SCP] = dummy_irq_entry(),
+	[DC_IRQ_SOURCE_VBIOS_SW] = dummy_irq_entry(),
+	vupdate_int_entry(0),
+	vupdate_int_entry(1),
+	vupdate_int_entry(2),
+	vupdate_int_entry(3),
+	vupdate_int_entry(4),
+	vupdate_int_entry(5),
+	vblank_int_entry(0),
+	vblank_int_entry(1),
+	vblank_int_entry(2),
+	vblank_int_entry(3),
+	vblank_int_entry(4),
+	vblank_int_entry(5),
+};
+
+enum dc_irq_source to_dal_irq_source_dce60(
+		struct irq_service *irq_service,
+		uint32_t src_id,
+		uint32_t ext_id)
+{
+	switch (src_id) {
+	case VISLANDS30_IV_SRCID_D1_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK1;
+	case VISLANDS30_IV_SRCID_D2_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK2;
+	case VISLANDS30_IV_SRCID_D3_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK3;
+	case VISLANDS30_IV_SRCID_D4_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK4;
+	case VISLANDS30_IV_SRCID_D5_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK5;
+	case VISLANDS30_IV_SRCID_D6_VBLANK:
+		return DC_IRQ_SOURCE_VBLANK6;
+	case VISLANDS30_IV_SRCID_D1_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE1;
+	case VISLANDS30_IV_SRCID_D2_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE2;
+	case VISLANDS30_IV_SRCID_D3_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE3;
+	case VISLANDS30_IV_SRCID_D4_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE4;
+	case VISLANDS30_IV_SRCID_D5_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE5;
+	case VISLANDS30_IV_SRCID_D6_V_UPDATE_INT:
+		return DC_IRQ_SOURCE_VUPDATE6;
+	case VISLANDS30_IV_SRCID_D1_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP1;
+	case VISLANDS30_IV_SRCID_D2_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP2;
+	case VISLANDS30_IV_SRCID_D3_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP3;
+	case VISLANDS30_IV_SRCID_D4_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP4;
+	case VISLANDS30_IV_SRCID_D5_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP5;
+	case VISLANDS30_IV_SRCID_D6_GRPH_PFLIP:
+		return DC_IRQ_SOURCE_PFLIP6;
+
+	case VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A:
+		/* generic src_id for all HPD and HPDRX interrupts */
+		switch (ext_id) {
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_A:
+			return DC_IRQ_SOURCE_HPD1;
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_B:
+			return DC_IRQ_SOURCE_HPD2;
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_C:
+			return DC_IRQ_SOURCE_HPD3;
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_D:
+			return DC_IRQ_SOURCE_HPD4;
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_E:
+			return DC_IRQ_SOURCE_HPD5;
+		case VISLANDS30_IV_EXTID_HOTPLUG_DETECT_F:
+			return DC_IRQ_SOURCE_HPD6;
+		case VISLANDS30_IV_EXTID_HPD_RX_A:
+			return DC_IRQ_SOURCE_HPD1RX;
+		case VISLANDS30_IV_EXTID_HPD_RX_B:
+			return DC_IRQ_SOURCE_HPD2RX;
+		case VISLANDS30_IV_EXTID_HPD_RX_C:
+			return DC_IRQ_SOURCE_HPD3RX;
+		case VISLANDS30_IV_EXTID_HPD_RX_D:
+			return DC_IRQ_SOURCE_HPD4RX;
+		case VISLANDS30_IV_EXTID_HPD_RX_E:
+			return DC_IRQ_SOURCE_HPD5RX;
+		case VISLANDS30_IV_EXTID_HPD_RX_F:
+			return DC_IRQ_SOURCE_HPD6RX;
+		default:
+			return DC_IRQ_SOURCE_INVALID;
+		}
+		break;
+
+	default:
+		return DC_IRQ_SOURCE_INVALID;
+	}
+}
+
+static const struct irq_service_funcs irq_service_funcs_dce60 = {
+		.to_dal_irq_source = to_dal_irq_source_dce60
+};
+
+static void dce60_irq_construct(
+	struct irq_service *irq_service,
+	struct irq_service_init_data *init_data)
+{
+	dal_irq_service_construct(irq_service, init_data);
+
+	irq_service->info = irq_source_info_dce60;
+	irq_service->funcs = &irq_service_funcs_dce60;
+}
+
+struct irq_service *dal_irq_service_dce60_create(
+	struct irq_service_init_data *init_data)
+{
+	struct irq_service *irq_service = kzalloc(sizeof(*irq_service),
+						  GFP_KERNEL);
+
+	if (!irq_service)
+		return NULL;
+
+	dce60_irq_construct(irq_service, init_data);
+	return irq_service;
+}
+
+
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.h b/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.h
new file mode 100644
index 000000000000..294db29e8115
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce60/irq_service_dce60.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2020 Mauro Rossi <issor.oruam@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_IRQ_SERVICE_DCE60_H__
+#define __DAL_IRQ_SERVICE_DCE60_H__
+
+#include "../irq_service.h"
+
+enum dc_irq_source to_dal_irq_source_dce60(
+		struct irq_service *irq_service,
+		uint32_t src_id,
+		uint32_t ext_id);
+
+struct irq_service *dal_irq_service_dce60_create(
+	struct irq_service_init_data *init_data);
+
+#endif
+
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 33053b9fe6bd..6bf27bde8724 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -32,6 +32,9 @@
 
 #include "dce110/irq_service_dce110.h"
 
+#if defined(CONFIG_DRM_AMD_DC_SI)
+#include "dce60/irq_service_dce60.h"
+#endif
 
 #include "dce80/irq_service_dce80.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index c3bbfe397e8d..330acaaed79a 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -55,6 +55,10 @@
 #include <asm/fpu/api.h>
 #define DC_FP_START() kernel_fpu_begin()
 #define DC_FP_END() kernel_fpu_end()
+#elif defined(CONFIG_ARM64)
+#include <asm/neon.h>
+#define DC_FP_START() kernel_neon_begin()
+#define DC_FP_END() kernel_neon_end()
 #elif defined(CONFIG_PPC64)
 #include <asm/switch_to.h>
 #include <asm/cputable.h>
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
index b8040da94b9d..944c0327763c 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
@@ -87,6 +87,17 @@ static void virtual_enc_dp_set_odm_combine(
 	bool odm_combine)
 {}
 
+static void virtual_dig_connect_to_otg(
+		struct stream_encoder *enc,
+		int tg_inst)
+{}
+
+static void virtual_setup_stereo_sync(
+			struct stream_encoder *enc,
+			int tg_inst,
+			bool enable)
+{}
+
 static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 	.dp_set_odm_combine =
 		virtual_enc_dp_set_odm_combine,
@@ -114,6 +125,8 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 	.audio_mute_control = virtual_audio_mute_control,
 	.set_avmute = virtual_stream_encoder_set_avmute,
 	.hdmi_reset_stream_attribute = virtual_stream_encoder_reset_hdmi_stream_attribute,
+	.dig_connect_to_otg = virtual_dig_connect_to_otg,
+	.setup_stereo_sync = virtual_setup_stereo_sync,
 };
 
 bool virtual_stream_encoder_construct(
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index e013875b89ed..d7e7f2eda92f 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -36,11 +36,20 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0xe6d590b09
+#define DMUB_FW_VERSION_GIT_HASH 0x4e5b2f46f
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 25
-#define DMUB_FW_VERSION_UCODE ((DMUB_FW_VERSION_MAJOR << 24) | (DMUB_FW_VERSION_MINOR << 16) | DMUB_FW_VERSION_REVISION)
+#define DMUB_FW_VERSION_REVISION 29
+#define DMUB_FW_VERSION_TEST 0
+#define DMUB_FW_VERSION_VBIOS 0
+#define DMUB_FW_VERSION_HOTFIX 0
+#define DMUB_FW_VERSION_UCODE (((DMUB_FW_VERSION_MAJOR & 0xFF) << 24) | \
+		((DMUB_FW_VERSION_MINOR & 0xFF) << 16) | \
+		((DMUB_FW_VERSION_REVISION & 0xFF) << 8) | \
+		((DMUB_FW_VERSION_TEST & 0x1) << 7) | \
+		((DMUB_FW_VERSION_VBIOS & 0x1) << 6) | \
+		(DMUB_FW_VERSION_HOTFIX & 0x3F))
+
 #endif
 
 //<DMUB_TYPES>==================================================================
@@ -204,6 +213,7 @@ enum dmub_cmd_vbios_type {
 	DMUB_CMD__VBIOS_DIG1_TRANSMITTER_CONTROL = 1,
 	DMUB_CMD__VBIOS_SET_PIXEL_CLOCK = 2,
 	DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING = 3,
+	DMUB_CMD__VBIOS_LVTMA_CONTROL = 15,
 };
 
 //==============================================================================
diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
index c30437ae8395..21011edea337 100644
--- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h
+++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
@@ -101,6 +101,13 @@ enum bp_pipe_control_action {
 	ASIC_PIPE_INIT
 };
 
+enum bp_lvtma_control_action {
+	LVTMA_CONTROL_LCD_BLOFF = 2,
+	LVTMA_CONTROL_LCD_BLON = 3,
+	LVTMA_CONTROL_POWER_ON = 12,
+	LVTMA_CONTROL_POWER_OFF = 13
+};
+
 struct bp_encoder_control {
 	enum bp_encoder_control_action action;
 	enum engine_id engine_id;
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index abeb58d544b1..b267987aed06 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -30,6 +30,34 @@
  * ASIC internal revision ID
  */
 
+/* DCE60 (based on si_id.h in GPUOpen-Tools CodeXL) */
+#define SI_TAHITI_P_A0    0x01
+#define SI_TAHITI_P_B0    0x05
+#define SI_TAHITI_P_B1    0x06
+#define SI_PITCAIRN_PM_A0 0x14
+#define SI_PITCAIRN_PM_A1 0x15
+#define SI_CAPEVERDE_M_A0 0x28
+#define SI_CAPEVERDE_M_A1 0x29
+#define SI_OLAND_M_A0     0x3C
+#define SI_HAINAN_V_A0    0x46
+
+#define SI_UNKNOWN        0xFF
+
+#define ASIC_REV_IS_TAHITI_P(rev) \
+	((rev >= SI_TAHITI_P_A0) && (rev < SI_PITCAIRN_PM_A0))
+
+#define ASIC_REV_IS_PITCAIRN_PM(rev) \
+	((rev >= SI_PITCAIRN_PM_A0) && (rev < SI_CAPEVERDE_M_A0))
+
+#define ASIC_REV_IS_CAPEVERDE_M(rev) \
+	((rev >= SI_CAPEVERDE_M_A0) && (rev < SI_OLAND_M_A0))
+
+#define ASIC_REV_IS_OLAND_M(rev) \
+	((rev >= SI_OLAND_M_A0) && (rev < SI_HAINAN_V_A0))
+
+#define ASIC_REV_IS_HAINAN_V(rev) \
+	((rev >= SI_HAINAN_V_A0) && (rev < SI_UNKNOWN))
+
 /* DCE80 (based on ci_id.h in Perforce) */
 #define	CI_BONAIRE_M_A0 0x14
 #define	CI_BONAIRE_M_A1	0x15
@@ -181,6 +209,17 @@ enum {
 /*
  * ASIC chip ID
  */
+
+/* DCE60 */
+#define DEVICE_ID_SI_TAHITI_P_6780 0x6780
+#define DEVICE_ID_SI_PITCAIRN_PM_6800 0x6800
+#define DEVICE_ID_SI_PITCAIRN_PM_6808 0x6808
+#define DEVICE_ID_SI_CAPEVERDE_M_6820 0x6820
+#define DEVICE_ID_SI_CAPEVERDE_M_6828 0x6828
+#define DEVICE_ID_SI_OLAND_M_6600 0x6600
+#define DEVICE_ID_SI_OLAND_M_6608 0x6608
+#define DEVICE_ID_SI_HAINAN_V_6660 0x6660
+
 /* DCE80 */
 #define DEVICE_ID_KALINDI_9834 0x9834
 #define DEVICE_ID_TEMASH_9839 0x9839
@@ -190,6 +229,7 @@ enum {
 #define DEVICE_ID_RENOIR_1636 0x1636
 
 /* Asic Family IDs for different asic family. */
+#define FAMILY_SI 110 /* Southern Islands: Tahiti (P), Pitcairn (PM), Cape Verde (M), Oland (M), Hainan (V) */
 #define FAMILY_CI 120 /* Sea Islands: Hawaii (P), Bonaire (M) */
 #define FAMILY_KV 125 /* Fusion => Kaveri: Spectre, Spooky; Kabini: Kalindi */
 #define FAMILY_VI 130 /* Volcanic Islands: Iceland (V), Tonga (M) */
diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h
index b67c9fa6b9cd..8aaa3af69202 100644
--- a/drivers/gpu/drm/amd/display/include/dal_types.h
+++ b/drivers/gpu/drm/amd/display/include/dal_types.h
@@ -34,6 +34,9 @@ struct dc_bios;
 
 enum dce_version {
 	DCE_VERSION_UNKNOWN = (-1),
+	DCE_VERSION_6_0,
+	DCE_VERSION_6_1,
+	DCE_VERSION_6_4,
 	DCE_VERSION_8_0,
 	DCE_VERSION_8_1,
 	DCE_VERSION_8_3,
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index 89ef9f6860e5..16df2a485dd0 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -431,6 +431,9 @@ struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg);
  */
 static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
+	if (arg1.value == 0)
+		return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero;
+
 	return dc_fixpt_exp(
 		dc_fixpt_mul(
 			dc_fixpt_log(arg1),
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 81820f3d6b3b..d988533d4af5 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -324,22 +324,44 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 
 		/* Choose number of frames to insert based on how close it
 		 * can get to the mid point of the variable range.
+		 *  - Delta for CEIL: delta_from_mid_point_in_us_1
+		 *  - Delta for FLOOR: delta_from_mid_point_in_us_2
 		 */
-		if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us &&
-				(delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 ||
-						mid_point_frames_floor < 2)) {
+		if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) {
+			/* Check for out of range.
+			 * If using CEIL produces a value that is out of range,
+			 * then we are forced to use FLOOR.
+			 */
+			frames_to_insert = mid_point_frames_floor;
+		} else if (mid_point_frames_floor < 2) {
+			/* Check if FLOOR would result in non-LFC. In this case
+			 * choose to use CEIL
+			 */
+			frames_to_insert = mid_point_frames_ceil;
+		} else if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) {
+			/* If choosing CEIL results in a frame duration that is
+			 * closer to the mid point of the range.
+			 * Choose CEIL
+			 */
 			frames_to_insert = mid_point_frames_ceil;
-			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 -
-					delta_from_mid_point_in_us_1;
 		} else {
+			/* If choosing FLOOR results in a frame duration that is
+			 * closer to the mid point of the range.
+			 * Choose FLOOR
+			 */
 			frames_to_insert = mid_point_frames_floor;
-			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 -
-					delta_from_mid_point_in_us_2;
 		}
 
 		/* Prefer current frame multiplier when BTR is enabled unless it drifts
 		 * too far from the midpoint
 		 */
+		if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) {
+			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 -
+					delta_from_mid_point_in_us_1;
+		} else {
+			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 -
+					delta_from_mid_point_in_us_2;
+		}
 		if (in_out_vrr->btr.frames_to_insert != 0 &&
 				delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) {
 			if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) <
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
index 13c57ff2abdc..1ab813b4fd14 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
@@ -37,6 +37,6 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		struct dc_info_packet *info_packet);
 
 void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue);
+		struct dc_info_packet *info_packet);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 7cd8a43d1889..0fdf7a3e96de 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -421,15 +421,13 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
  *****************************************************************************
  */
 void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue)
+		struct dc_info_packet *info_packet)
 {
 		unsigned int length = 5;
 		bool hdmi_vic_mode = false;
 		uint8_t checksum = 0;
 		uint32_t i = 0;
 		enum dc_timing_3d_format format;
-		bool bALLM = (bool)ALLMEnabled;
-		bool bALLMVal = (bool)ALLMValue;
 
 		info_packet->valid = false;
 		format = stream->timing.timing_3d_format;
@@ -442,20 +440,13 @@ void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
 				&& format == TIMING_3D_FORMAT_NONE)
 			hdmi_vic_mode = true;
 
-		if ((format == TIMING_3D_FORMAT_NONE) && !hdmi_vic_mode && !bALLM)
+		if ((format == TIMING_3D_FORMAT_NONE) && !hdmi_vic_mode)
 			return;
 
 		info_packet->sb[1] = 0x03;
 		info_packet->sb[2] = 0x0C;
 		info_packet->sb[3] = 0x00;
 
-		if (bALLM) {
-			info_packet->sb[1] = 0xD8;
-			info_packet->sb[2] = 0x5D;
-			info_packet->sb[3] = 0xC4;
-			info_packet->sb[4] = HF_VSIF_VERSION;
-		}
-
 		if (format != TIMING_3D_FORMAT_NONE)
 			info_packet->sb[4] = (2 << 5);
 
@@ -490,9 +481,6 @@ void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
 		info_packet->hb1 = 0x01;
 		info_packet->hb2 = (uint8_t) (length);
 
-		if (bALLM)
-			info_packet->sb[5] = (info_packet->sb[5] & ~0x02) | (bALLMVal << 1);
-
 		checksum += info_packet->hb0;
 		checksum += info_packet->hb1;
 		checksum += info_packet->hb2;
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 859724771a75..61497954e67e 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -657,7 +657,7 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame
 			params, ram_table, big_endian);
 }
 
-bool dmub_init_abm_config(struct abm *abm,
+bool dmub_init_abm_config(struct resource_pool *res_pool,
 	struct dmcu_iram_parameters params)
 {
 	struct iram_table_v_2_2 ram_table;
@@ -665,8 +665,13 @@ bool dmub_init_abm_config(struct abm *abm,
 	bool result = false;
 	uint32_t i, j = 0;
 
-	if (abm == NULL)
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+	if (res_pool->abm == NULL && res_pool->multiple_abms[0] == NULL)
 		return false;
+#else
+	if (res_pool->abm == NULL)
+		return false;
+#endif
 
 	memset(&ram_table, 0, sizeof(ram_table));
 	memset(&config, 0, sizeof(config));
@@ -707,8 +712,14 @@ bool dmub_init_abm_config(struct abm *abm,
 
 	config.min_abm_backlight = ram_table.min_abm_backlight;
 
-	result = abm->funcs->init_abm_config(
-		abm, (char *)(&config), sizeof(struct abm_config_table));
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+	if (res_pool->multiple_abms[0]) {
+		result = res_pool->multiple_abms[0]->funcs->init_abm_config(
+			res_pool->multiple_abms[0], (char *)(&config), sizeof(struct abm_config_table));
+	} else
+#endif
+		result = res_pool->abm->funcs->init_abm_config(
+			res_pool->abm, (char *)(&config), sizeof(struct abm_config_table));
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index 46fbca2e2cd1..fa4728d88092 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -28,6 +28,8 @@
 #include "dc/inc/hw/dmcu.h"
 #include "dc/inc/hw/abm.h"
 
+struct resource_pool;
+
 
 enum abm_defines {
 	abm_defines_max_level = 4,
@@ -45,7 +47,7 @@ struct dmcu_iram_parameters {
 
 bool dmcu_load_iram(struct dmcu *dmcu,
 		struct dmcu_iram_parameters params);
-bool dmub_init_abm_config(struct abm *abm,
+bool dmub_init_abm_config(struct resource_pool *res_pool,
 		struct dmcu_iram_parameters params);
 
 #endif /* MODULES_POWER_POWER_HELPERS_H_ */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
index 27bb8c1ab858..b6f74bf4af02 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
@@ -7376,8 +7376,6 @@
 #define mmCRTC4_CRTC_DRR_CONTROL                                                                       0x0f3e
 #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX                                                              2
 
-#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0                                                                  0x395d
-#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX                                                         2
 
 // addressBlock: dce_dc_fmt4_dispdec
 // base address: 0x2000
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
index ae798f768853..9de01ae574c0 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
@@ -4444,14 +4444,90 @@
 
 /* Registers that spilled out of sid.h */
 #define mmDATA_FORMAT                              0x1AC0
+#define mmLB0_DATA_FORMAT                               0x1AC0
+#define mmLB1_DATA_FORMAT                               0x1DC0
+#define mmLB2_DATA_FORMAT                               0x40C0
+#define mmLB3_DATA_FORMAT                               0x43C0
+#define mmLB4_DATA_FORMAT                               0x46C0
+#define mmLB5_DATA_FORMAT                               0x49C0
 #define mmDESKTOP_HEIGHT                           0x1AC1
+#define mmLB0_DESKTOP_HEIGHT                            0x1AC1
+#define mmLB1_DESKTOP_HEIGHT                            0x1DC1
+#define mmLB2_DESKTOP_HEIGHT                            0x40C1
+#define mmLB3_DESKTOP_HEIGHT                            0x43C1
+#define mmLB4_DESKTOP_HEIGHT                            0x46C1
+#define mmLB5_DESKTOP_HEIGHT                            0x49C1
 #define mmDC_LB_MEMORY_SPLIT                       0x1AC3
+#define mmLB0_DC_LB_MEMORY_SPLIT                        0x1AC3
+#define mmLB1_DC_LB_MEMORY_SPLIT                        0x1DC3
+#define mmLB2_DC_LB_MEMORY_SPLIT                        0x40C3
+#define mmLB3_DC_LB_MEMORY_SPLIT                        0x43C3
+#define mmLB4_DC_LB_MEMORY_SPLIT                        0x46C3
+#define mmLB5_DC_LB_MEMORY_SPLIT                        0x49C3
+#define mmDC_LB_MEM_SIZE                                0x1AC4
+#define mmLB0_DC_LB_MEM_SIZE                            0x1AC4
+#define mmLB1_DC_LB_MEM_SIZE                            0x1DC4
+#define mmLB2_DC_LB_MEM_SIZE                            0x40C4
+#define mmLB3_DC_LB_MEM_SIZE                            0x43C4
+#define mmLB4_DC_LB_MEM_SIZE                            0x46C4
+#define mmLB5_DC_LB_MEM_SIZE                            0x49C4
 #define mmPRIORITY_A_CNT                           0x1AC6
+#define mmLB0_PRIORITY_A_CNT                            0x1AC6
+#define mmLB1_PRIORITY_A_CNT                            0x1DC6
+#define mmLB2_PRIORITY_A_CNT                            0x40C6
+#define mmLB3_PRIORITY_A_CNT                            0x43C6
+#define mmLB4_PRIORITY_A_CNT                            0x46C6
+#define mmLB5_PRIORITY_A_CNT                            0x49C6
 #define mmPRIORITY_B_CNT                           0x1AC7
+#define mmLB0_PRIORITY_B_CNT                            0x1AC7
+#define mmLB1_PRIORITY_B_CNT                            0x1DC7
+#define mmLB2_PRIORITY_B_CNT                            0x40C7
+#define mmLB3_PRIORITY_B_CNT                            0x43C7
+#define mmLB4_PRIORITY_B_CNT                            0x46C7
+#define mmLB5_PRIORITY_B_CNT                            0x49C7
 #define mmDPG_PIPE_ARBITRATION_CONTROL3            0x1B32
+#define mmDMIF_PG0_DPG_PIPE_ARBITRATION_CONTROL3        0x1B32
+#define mmDMIF_PG1_DPG_PIPE_ARBITRATION_CONTROL3        0x1E32
+#define mmDMIF_PG2_DPG_PIPE_ARBITRATION_CONTROL3        0x4132
+#define mmDMIF_PG3_DPG_PIPE_ARBITRATION_CONTROL3        0x4432
+#define mmDMIF_PG4_DPG_PIPE_ARBITRATION_CONTROL3        0x4732
+#define mmDMIF_PG5_DPG_PIPE_ARBITRATION_CONTROL3        0x4A32
 #define mmINT_MASK                                 0x1AD0
+#define mmLB0_INT_MASK                                  0x1AD0
+#define mmLB1_INT_MASK                                  0x1DD0
+#define mmLB2_INT_MASK                                  0x40D0
+#define mmLB3_INT_MASK                                  0x43D0
+#define mmLB4_INT_MASK                                  0x46D0
+#define mmLB5_INT_MASK                                  0x49D0
 #define mmVLINE_STATUS                             0x1AEE
+#define mmLB0_VLINE_STATUS                              0x1AEE
+#define mmLB1_VLINE_STATUS                              0x1DEE
+#define mmLB2_VLINE_STATUS                              0x40EE
+#define mmLB3_VLINE_STATUS                              0x43EE
+#define mmLB4_VLINE_STATUS                              0x46EE
+#define mmLB5_VLINE_STATUS                              0x49EE
 #define mmVBLANK_STATUS                            0x1AEF
+#define mmLB0_VBLANK_STATUS                             0x1AEF
+#define mmLB1_VBLANK_STATUS                             0x1DEF
+#define mmLB2_VBLANK_STATUS                             0x40EF
+#define mmLB3_VBLANK_STATUS                             0x43EF
+#define mmLB4_VBLANK_STATUS                             0x46EF
+#define mmLB5_VBLANK_STATUS                             0x49EF
 
+#define mmSCL_HORZ_FILTER_INIT_RGB_LUMA            0x1B4C
+#define mmSCL0_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x1B4C
+#define mmSCL1_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x1E4C
+#define mmSCL2_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x414C
+#define mmSCL3_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x444C
+#define mmSCL4_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x474C
+#define mmSCL5_SCL_HORZ_FILTER_INIT_RGB_LUMA            0x4A4C
+
+#define mmSCL_HORZ_FILTER_INIT_CHROMA              0x1B4D
+#define mmSCL0_SCL_HORZ_FILTER_INIT_CHROMA              0x1B4D
+#define mmSCL1_SCL_HORZ_FILTER_INIT_CHROMA              0x1E4D
+#define mmSCL2_SCL_HORZ_FILTER_INIT_CHROMA              0x414D
+#define mmSCL3_SCL_HORZ_FILTER_INIT_CHROMA              0x444D
+#define mmSCL4_SCL_HORZ_FILTER_INIT_CHROMA              0x474D
+#define mmSCL5_SCL_HORZ_FILTER_INIT_CHROMA              0x4A4D
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
index abe05bc80752..41c4a46ce357 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
@@ -2076,6 +2076,8 @@
 #define CRTC_CONTROL__CRTC_START_POINT_CNTL__SHIFT 0x0000000c
 #define CRTC_CONTROL__CRTC_SYNC_RESET_SEL_MASK 0x00000010L
 #define CRTC_CONTROL__CRTC_SYNC_RESET_SEL__SHIFT 0x00000004
+#define CRTC_CONTROL__CRTC_PREFETCH_EN_MASK                0x10000000L
+#define	CRTC_CONTROL__CRTC_PREFETCH_EN__SHIFT              0x0000001c
 #define CRTC_COUNT_CONTROL__CRTC_HORZ_COUNT_BY2_EN_MASK 0x00000001L
 #define CRTC_COUNT_CONTROL__CRTC_HORZ_COUNT_BY2_EN__SHIFT 0x00000000
 #define CRTC_COUNT_CONTROL__CRTC_HORZ_REPETITION_COUNT_MASK 0x0000001eL
@@ -6364,6 +6366,8 @@
 #define DPG_PIPE_ARBITRATION_CONTROL2__TIME_WEIGHT__SHIFT 0x00000000
 #define DPG_PIPE_ARBITRATION_CONTROL2__URGENCY_WEIGHT_MASK 0xffff0000L
 #define DPG_PIPE_ARBITRATION_CONTROL2__URGENCY_WEIGHT__SHIFT 0x00000010
+#define DPG_PIPE_ARBITRATION_CONTROL3__URGENCY_WATERMARK_MASK_MASK 0x00030000L
+#define	DPG_PIPE_ARBITRATION_CONTROL3__URGENCY_WATERMARK_MASK__SHIFT 0x00000010
 #define DPG_PIPE_DPM_CONTROL__DPM_ENABLE_MASK 0x00000001L
 #define DPG_PIPE_DPM_CONTROL__DPM_ENABLE__SHIFT 0x00000000
 #define DPG_PIPE_DPM_CONTROL__MCLK_CHANGE_ENABLE_MASK 0x00000010L
@@ -6384,6 +6388,8 @@
 #define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_NOT_SELF_REFRESH_DURING_REQUEST__SHIFT 0x00000008
 #define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_URGENT_DURING_REQUEST_MASK 0x00000010L
 #define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_URGENT_DURING_REQUEST__SHIFT 0x00000004
+#define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_WATERMARK_MASK_MASK 0x00003000L
+#define	DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_WATERMARK_MASK__SHIFT 0x0000000c
 #define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_WATERMARK_MASK 0xffff0000L
 #define DPG_PIPE_NB_PSTATE_CHANGE_CONTROL__NB_PSTATE_CHANGE_WATERMARK__SHIFT 0x00000010
 #define DPG_PIPE_STUTTER_CONTROL_NONLPTCH__STUTTER_ENABLE_NONLPTCH_MASK 0x00000001L
@@ -6406,6 +6412,8 @@
 #define DPG_PIPE_STUTTER_CONTROL_NONLPTCH__STUTTER_WM_HIGH_FORCE_ON_NONLPTCH__SHIFT 0x00000008
 #define DPG_PIPE_STUTTER_CONTROL__STUTTER_ENABLE_MASK 0x00000001L
 #define DPG_PIPE_STUTTER_CONTROL__STUTTER_ENABLE__SHIFT 0x00000000
+#define DPG_PIPE_STUTTER_CONTROL__STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK_MASK 0x00003000L
+#define	DPG_PIPE_STUTTER_CONTROL__STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK__SHIFT 0x0000000c
 #define DPG_PIPE_STUTTER_CONTROL__STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK 0xffff0000L
 #define DPG_PIPE_STUTTER_CONTROL__STUTTER_EXIT_SELF_REFRESH_WATERMARK__SHIFT 0x00000010
 #define DPG_PIPE_STUTTER_CONTROL__STUTTER_IGNORE_CURSOR_MASK 0x00000010L
@@ -7256,6 +7264,8 @@
 #define GRPH_CONTROL__GRPH_FORMAT__SHIFT 0x00000008
 #define GRPH_CONTROL__GRPH_MACRO_TILE_ASPECT_MASK 0x000c0000L
 #define GRPH_CONTROL__GRPH_MACRO_TILE_ASPECT__SHIFT 0x00000012
+#define GRPH_CONTROL__GRPH_ARRAY_MODE_MASK                 0x00f00000L
+#define	GRPH_CONTROL__GRPH_ARRAY_MODE__SHIFT               0x00000014
 #define GRPH_CONTROL__GRPH_NUM_BANKS_MASK 0x0000000cL
 #define GRPH_CONTROL__GRPH_NUM_BANKS__SHIFT 0x00000002
 #define GRPH_CONTROL__GRPH_PIPE_CONFIG_MASK 0x1f000000L
@@ -9835,4 +9845,98 @@
 #define XDMA_TEST_DEBUG_INDEX__XDMA_TEST_DEBUG_WRITE_EN_MASK 0x00000100L
 #define XDMA_TEST_DEBUG_INDEX__XDMA_TEST_DEBUG_WRITE_EN__SHIFT 0x00000008
 
+// DATA_FORMAT
+#define DATA_FORMAT__INTERLEAVE_EN_MASK                    0x00000001L
+#define	DATA_FORMAT__INTERLEAVE_EN__SHIFT                  0x00000000
+#define DATA_FORMAT__RESET_REQ_AT_EOL_MASK                 0x00000010L
+#define	DATA_FORMAT__RESET_REQ_AT_EOL__SHIFT               0x00000004
+#define DATA_FORMAT__PREFETCH_MASK                         0x00001000L
+#define	DATA_FORMAT__PREFETCH__SHIFT                       0x0000000c
+#define DATA_FORMAT__SOF_READ_PT_MASK                      0x001f0000L
+#define	DATA_FORMAT__SOF_READ_PT__SHIFT                    0x00000010
+#define DATA_FORMAT__REQUEST_MODE_MASK                     0x03000000L
+#define	DATA_FORMAT__REQUEST_MODE__SHIFT                   0x00000018
+#define DATA_FORMAT__ALLOW_REQ_MODE_1_2_MASK               0x10000000L
+#define	DATA_FORMAT__ALLOW_REQ_MODE_1_2__SHIFT             0x0000001c
+
+
+// DC_LB_MEMORY_SPLIT
+#define DC_LB_MEMORY_SPLIT__LB_NUM_PARTITIONS_MASK         0x000f0000L
+#define	DC_LB_MEMORY_SPLIT__LB_NUM_PARTITIONS__SHIFT       0x00000010
+#define DC_LB_MEMORY_SPLIT__DC_LB_MEMORY_CONFIG_MASK       0x00300000L
+#define	DC_LB_MEMORY_SPLIT__DC_LB_MEMORY_CONFIG__SHIFT     0x00000014
+
+// DC_LB_MEM_SIZE
+#define DC_LB_MEM_SIZE__DC_LB_MEM_SIZE_MASK                0x000007ffL
+#define	DC_LB_MEM_SIZE__DC_LB_MEM_SIZE__SHIFT              0x00000000
+
+// SCL_TAP_CONTROL
+#define SCL_TAP_CONTROL__SCL_V_NUM_OF_TAPS_MASK            0x00000007L
+#define	SCL_TAP_CONTROL__SCL_V_NUM_OF_TAPS__SHIFT          0x00000000
+#define SCL_TAP_CONTROL__SCL_H_NUM_OF_TAPS_MASK            0x00000f00L
+#define	SCL_TAP_CONTROL__SCL_H_NUM_OF_TAPS__SHIFT          0x00000008
+
+// INT_MASK
+#define INT_MASK__VBLANK_INT_MASK                          0x00000001L
+#define	INT_MASK__VBLANK_INT__SHIFT                        0x00000000
+#define INT_MASK__VLINE_INT_MASK                           0x00000010L
+#define	INT_MASK__VLINE_INT__SHIFT                         0x00000004
+
+// PRIORITY_A_CNT
+#define PRIORITY_A_CNT__PRIORITY_MARK_A_MASK               0x00007fffL
+#define	PRIORITY_A_CNT__PRIORITY_MARK_A__SHIFT             0x00000000
+#define PRIORITY_A_CNT__PRIORITY_A_OFF_MASK                0x00010000L
+#define	PRIORITY_A_CNT__PRIORITY_A_OFF__SHIFT              0x00000010
+#define PRIORITY_A_CNT__PRIORITY_A_ALWAYS_ON_MASK          0x00100000L
+#define	PRIORITY_A_CNT__PRIORITY_A_ALWAYS_ON__SHIFT        0x00000014
+#define PRIORITY_A_CNT__PRIORITY_A_FORCE_MASK_MASK         0x01000000L
+#define	PRIORITY_A_CNT__PRIORITY_A_FORCE_MASK__SHIFT       0x00000018
+
+// PRIORITY_B_CNT
+#define PRIORITY_B_CNT__PRIORITY_MARK_B_MASK               0x00007fffL
+#define	PRIORITY_B_CNT__PRIORITY_MARK_B__SHIFT             0x00000000
+#define PRIORITY_B_CNT__PRIORITY_B_OFF_MASK                0x00010000L
+#define	PRIORITY_B_CNT__PRIORITY_B_OFF__SHIFT              0x00000010
+#define PRIORITY_B_CNT__PRIORITY_B_ALWAYS_ON_MASK          0x00100000L
+#define	PRIORITY_B_CNT__PRIORITY_B_ALWAYS_ON__SHIFT        0x00000014
+#define PRIORITY_B_CNT__PRIORITY_B_FORCE_MASK_MASK         0x01000000L
+#define	PRIORITY_B_CNT__PRIORITY_B_FORCE_MASK__SHIFT       0x00000018
+
+// VLINE_STATUS
+#define VLINE_STATUS__VLINE_OCCURRED_MASK                  0x00000001L
+#define	VLINE_STATUS__VLINE_OCCURRED__SHIFT                0x00000000
+#define VLINE_STATUS__VLINE_ACK_MASK                       0x00000010L
+#define	VLINE_STATUS__VLINE_ACK__SHIFT                     0x00000004
+#define VLINE_STATUS__VLINE_STAT_MASK                      0x00001000L
+#define	VLINE_STATUS__VLINE_STAT__SHIFT                    0x0000000c
+#define VLINE_STATUS__VLINE_INTERRUPT_MASK                 0x00010000L
+#define	VLINE_STATUS__VLINE_INTERRUPT__SHIFT               0x00000010
+#define VLINE_STATUS__VLINE_INTERRUPT_TYPE_MASK            0x00020000L
+#define	VLINE_STATUS__VLINE_INTERRUPT_TYPE__SHIFT          0x00000011
+
+// VBLANK_STATUS
+#define VBLANK_STATUS__VBLANK_OCCURRED_MASK                0x00000001L
+#define	VBLANK_STATUS__VBLANK_OCCURRED__SHIFT              0x00000000
+#define VBLANK_STATUS__VBLANK_ACK_MASK                     0x00000010L
+#define	VBLANK_STATUS__VBLANK_ACK__SHIFT                   0x00000004
+#define VBLANK_STATUS__VBLANK_STAT_MASK                    0x00001000L
+#define	VBLANK_STATUS__VBLANK_STAT__SHIFT                  0x0000000c
+#define VBLANK_STATUS__VBLANK_INTERRUPT_MASK               0x00010000L
+#define	VBLANK_STATUS__VBLANK_INTERRUPT__SHIFT             0x00000010
+#define VBLANK_STATUS__VBLANK_INTERRUPT_TYPE_MASK          0x00020000L
+#define	VBLANK_STATUS__VBLANK_INTERRUPT_TYPE__SHIFT        0x00000011
+
+// SCL_HORZ_FILTER_INIT_RGB_LUMA
+#define SCL_HORZ_FILTER_INIT_RGB_LUMA__SCL_H_INIT_FRAC_RGB_Y_MASK 0x0000ffffL
+#define	SCL_HORZ_FILTER_INIT_RGB_LUMA__SCL_H_INIT_FRAC_RGB_Y__SHIFT 0x00000000
+#define SCL_HORZ_FILTER_INIT_RGB_LUMA__SCL_H_INIT_INT_RGB_Y_MASK 0x000f0000L
+#define	SCL_HORZ_FILTER_INIT_RGB_LUMA__SCL_H_INIT_INT_RGB_Y__SHIFT 0x00000010
+
+// SCL_HORZ_FILTER_INIT_CHROMA
+#define SCL_HORZ_FILTER_INIT_CHROMA__SCL_H_INIT_FRAC_CBCR_MASK 0x0000ffffL
+#define	SCL_HORZ_FILTER_INIT_CHROMA__SCL_H_INIT_FRAC_CBCR__SHIFT 0x00000000
+#define SCL_HORZ_FILTER_INIT_CHROMA__SCL_H_INIT_INT_CBCR_MASK 0x00070000L
+#define	SCL_HORZ_FILTER_INIT_CHROMA__SCL_H_INIT_INT_CBCR__SHIFT 0x00000010
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h
index cf166b591bc5..cf166b591bc5 100755..100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h
index 0e0319e98c07..ea683f452bb3 100755..100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h
@@ -50271,6 +50271,10 @@
 #define DSC_TOP0_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP0_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP0_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP0_DSC_DEBUG_CONTROL
+#define DSC_TOP0_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP0_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
+
 
 // addressBlock: dce_dc_dsc0_dispdec_dsccif_dispdec
 //DSCCIF0_DSCCIF_CONFIG0
@@ -50789,6 +50793,9 @@
 #define DSC_TOP1_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP1_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP1_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP1_DSC_DEBUG_CONTROL
+#define DSC_TOP1_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP1_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
 
 
 // addressBlock: dce_dc_dsc1_dispdec_dsccif_dispdec
@@ -51308,6 +51315,10 @@
 #define DSC_TOP2_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP2_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP2_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP2_DSC_DEBUG_CONTROL
+#define DSC_TOP2_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP2_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
+
 
 // addressBlock: dce_dc_dsc2_dispdec_dsccif_dispdec
 //DSCCIF2_DSCCIF_CONFIG0
@@ -51826,6 +51837,9 @@
 #define DSC_TOP3_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP3_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP3_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP3_DSC_DEBUG_CONTROL
+#define DSC_TOP3_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP3_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
 
 
 // addressBlock: dce_dc_dsc3_dispdec_dsccif_dispdec
@@ -52346,6 +52360,10 @@
 #define DSC_TOP4_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP4_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP4_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP4_DSC_DEBUG_CONTROL
+#define DSC_TOP4_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP4_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
+
 
 // addressBlock: dce_dc_dsc4_dispdec_dsccif_dispdec
 //DSCCIF4_DSCCIF_CONFIG0
@@ -52864,6 +52882,10 @@
 #define DSC_TOP5_DSC_TOP_CONTROL__DSC_CLOCK_EN_MASK                                                           0x00000001L
 #define DSC_TOP5_DSC_TOP_CONTROL__DSC_DISPCLK_R_GATE_DIS_MASK                                                 0x00000010L
 #define DSC_TOP5_DSC_TOP_CONTROL__DSC_DSCCLK_R_GATE_DIS_MASK                                                  0x00000100L
+//DSC_TOP5_DSC_DEBUG_CONTROL
+#define DSC_TOP5_DSC_DEBUG_CONTROL__DSC_DBG_EN__SHIFT                                                         0x0
+#define DSC_TOP5_DSC_DEBUG_CONTROL__DSC_DBG_EN_MASK                                                           0x00000001L
+
 
 // addressBlock: dce_dc_dsc5_dispdec_dsccif_dispdec
 //DSCCIF5_DSCCIF_CONFIG0
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_offset.h
index 67faaf68e9d7..67faaf68e9d7 100755..100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_sh_mask.h
index b4ef50a72868..b4ef50a72868 100755..100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_3_0_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
index 05d1b0a5f6d2..cbaad7d83194 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
@@ -9180,6 +9180,8 @@
 #define mmRLC_GPM_THREAD_ENABLE_BASE_IDX                                                               1
 #define mmRLC_RLCG_DOORBELL_RANGE                                                                      0x4c47
 #define mmRLC_RLCG_DOORBELL_RANGE_BASE_IDX                                                             1
+#define mmRLC_CGTT_MGCG_OVERRIDE                                                                       0x4c48
+#define mmRLC_CGTT_MGCG_OVERRIDE_BASE_IDX                                                              1
 #define mmRLC_CGCG_CGLS_CTRL                                                                           0x4c49
 #define mmRLC_CGCG_CGLS_CTRL_BASE_IDX                                                                  1
 #define mmRLC_CGCG_RAMP_CTRL                                                                           0x4c4a
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
index aac57f714cf1..c2d035ef3e94 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
@@ -32315,6 +32315,31 @@
 #define RLC_RLCG_DOORBELL_CNTL__DOORBELL_3_MODE_MASK                                                          0x000000C0L
 #define RLC_RLCG_DOORBELL_CNTL__DOORBELL_ID_MASK                                                              0x001F0000L
 #define RLC_RLCG_DOORBELL_CNTL__DOORBELL_ID_EN_MASK                                                           0x00200000L
+//RLC_CGTT_MGCG_OVERRIDE
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_0__SHIFT                                                             0x0
+#define RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE__SHIFT                                                 0x1
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE__SHIFT                                                    0x2
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE__SHIFT                                                    0x3
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE__SHIFT                                                    0x4
+#define RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE__SHIFT                                                0x5
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE__SHIFT                                                    0x6
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE__SHIFT                                                0x7
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE__SHIFT                                                    0x8
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_15_9__SHIFT                                                          0x9
+#define RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY__SHIFT                                                     0x10
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_31_17__SHIFT                                                         0x11
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_0_MASK                                                               0x00000001L
+#define RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK                                                   0x00000002L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK                                                      0x00000004L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK                                                      0x00000008L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK                                                      0x00000010L
+#define RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK                                                  0x00000020L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK                                                      0x00000040L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK                                                  0x00000080L
+#define RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK                                                      0x00000100L
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_15_9_MASK                                                            0x0000FE00L
+#define RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK                                                       0x00010000L
+#define RLC_CGTT_MGCG_OVERRIDE__RESERVED_31_17_MASK                                                           0xFFFE0000L
 //RLC_RLCG_DOORBELL_STAT
 #define RLC_RLCG_DOORBELL_STAT__DOORBELL_0_VALID__SHIFT                                                       0x0
 #define RLC_RLCG_DOORBELL_STAT__DOORBELL_1_VALID__SHIFT                                                       0x1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_offset.h
new file mode 100644
index 000000000000..3685766c4d56
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_offset.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2020  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _umc_8_7_0_OFFSET_HEADER
+#define _umc_8_7_0_OFFSET_HEADER
+
+#define mmUMCCH0_0_GeccErrCntSel                                  0x0328
+#define mmUMCCH0_0_GeccErrCntSel_BASE_IDX                         0
+#define mmUMCCH0_0_GeccErrCnt                                     0x0329
+#define mmUMCCH0_0_GeccErrCnt_BASE_IDX                            0
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0                             0x03c2
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0_BASE_IDX                    0
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0                               0x03c4
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_BASE_IDX      		  0
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h
new file mode 100644
index 000000000000..4c5097fa0c09
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_7_0_sh_mask.h
@@ -0,0 +1,79 @@
+#ifndef _umc_8_7_0_SH_MASK_HEADER

+#define _umc_8_7_0_SH_MASK_HEADER

+

+//UMCCH0_0_GeccErrCntSel

+#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel__SHIFT                                                        0x0

+#define UMCCH0_0_GeccErrCntSel__GeccErrInt__SHIFT                                                             0xc

+#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn__SHIFT                                                           0xf

+#define UMCCH0_0_GeccErrCntSel__PoisonCntEn__SHIFT                                                            0x10

+#define UMCCH0_0_GeccErrCntSel__GeccErrCntCsSel_MASK                                                          0x0000000FL

+#define UMCCH0_0_GeccErrCntSel__GeccErrInt_MASK                                                               0x00003000L

+#define UMCCH0_0_GeccErrCntSel__GeccErrCntEn_MASK                                                             0x00008000L

+#define UMCCH0_0_GeccErrCntSel__PoisonCntEn_MASK                                                              0x00030000L

+//UMCCH0_0_GeccErrCnt

+#define UMCCH0_0_GeccErrCnt__GeccErrCnt__SHIFT                                                                0x0

+#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt__SHIFT                                                          0x10

+#define UMCCH0_0_GeccErrCnt__GeccErrCnt_MASK                                                                  0x0000FFFFL

+#define UMCCH0_0_GeccErrCnt__GeccUnCorrErrCnt_MASK                                                            0xFFFF0000L

+//MCA_UMC_UMC0_MCUMC_STATUST0

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode__SHIFT                                                         0x0

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt__SHIFT                                                      0x10

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22__SHIFT                                                          0x16

+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb__SHIFT                                                           0x18

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30__SHIFT                                                          0x1e

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId__SHIFT                                                         0x20

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38__SHIFT                                                          0x26

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub__SHIFT                                                             0x28

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41__SHIFT                                                          0x29

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison__SHIFT                                                            0x2b

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred__SHIFT                                                          0x2c

+#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC__SHIFT                                                              0x2d

+#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC__SHIFT                                                              0x2e

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47__SHIFT                                                          0x2f

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent__SHIFT                                                       0x34

+#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV__SHIFT                                                             0x35

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54__SHIFT                                                          0x36

+#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC__SHIFT                                                               0x37

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal__SHIFT                                                      0x38

+#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC__SHIFT                                                               0x39

+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV__SHIFT                                                             0x3a

+#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV__SHIFT                                                             0x3b

+#define MCA_UMC_UMC0_MCUMC_STATUST0__En__SHIFT                                                                0x3c

+#define MCA_UMC_UMC0_MCUMC_STATUST0__UC__SHIFT                                                                0x3d

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow__SHIFT                                                          0x3e

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Val__SHIFT                                                               0x3f

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCode_MASK                                                           0x000000000000FFFFL

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrorCodeExt_MASK                                                        0x00000000003F0000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV22_MASK                                                            0x0000000000C00000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrLsb_MASK                                                             0x000000003F000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV30_MASK                                                            0x00000000C0000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreId_MASK                                                           0x0000003F00000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV38_MASK                                                            0x000000C000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Scrub_MASK                                                               0x0000010000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV41_MASK                                                            0x0000060000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Poison_MASK                                                              0x0000080000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Deferred_MASK                                                            0x0000100000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__UECC_MASK                                                                0x0000200000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__CECC_MASK                                                                0x0000400000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV47_MASK                                                            0x000F800000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Transparent_MASK                                                         0x0010000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__SyndV_MASK                                                               0x0020000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__RESERV54_MASK                                                            0x0040000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__TCC_MASK                                                                 0x0080000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__ErrCoreIdVal_MASK                                                        0x0100000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__PCC_MASK                                                                 0x0200000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__AddrV_MASK                                                               0x0400000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__MiscV_MASK                                                               0x0800000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__En_MASK                                                                  0x1000000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__UC_MASK                                                                  0x2000000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Overflow_MASK                                                            0x4000000000000000L

+#define MCA_UMC_UMC0_MCUMC_STATUST0__Val_MASK                                                                 0x8000000000000000L

+//MCA_UMC_UMC0_MCUMC_ADDRT0

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr__SHIFT                                                           0x0

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB__SHIFT                                                                 0x38

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved__SHIFT                                                            0x3e

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr_MASK                                                             0x00FFFFFFFFFFFFFFL

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__LSB_MASK                                                                   0x3F00000000000000L

+#define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved_MASK                                                              0xC000000000000000L

+

+#endif

diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index a3c238c39ef5..fc592f60e6a0 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -212,10 +212,6 @@ struct tile_config {
  * IH ring entry. This function allows the KFD ISR to get the VMID
  * from the fault status register as early as possible.
  *
- * @get_hive_id: Returns hive id of current  device,  0 if xgmi is not enabled
- *
- * @get_unique_id: Returns uuid id of current  device
- * 
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -290,9 +286,6 @@ struct kfd2kgd_calls {
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
-	uint64_t (*get_hive_id)(struct kgd_dev *kgd);
-	uint64_t (*get_unique_id)(struct kgd_dev *kgd);
-
 };
 
 #endif	/* KGD_KFD_INTERFACE_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index a7f92d0b3a90..0aec28fda058 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -322,6 +322,115 @@ struct amd_pm_funcs {
 	int (*asic_reset_mode_2)(void *handle);
 	int (*set_df_cstate)(void *handle, enum pp_df_cstate state);
 	int (*set_xgmi_pstate)(void *handle, uint32_t pstate);
+	ssize_t (*get_gpu_metrics)(void *handle, void **table);
+};
+
+struct metrics_table_header {
+	uint16_t			structure_size;
+	uint8_t				format_revision;
+	uint8_t				content_revision;
+};
+
+struct gpu_metrics_v1_0 {
+	struct metrics_table_header	common_header;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Temperature */
+	uint16_t			temperature_edge;
+	uint16_t			temperature_hotspot;
+	uint16_t			temperature_mem;
+	uint16_t			temperature_vrgfx;
+	uint16_t			temperature_vrsoc;
+	uint16_t			temperature_vrmem;
+
+	/* Utilization */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_umc_activity; // memory controller
+	uint16_t			average_mm_activity; // UVD or VCN
+
+	/* Power/Energy */
+	uint16_t			average_socket_power;
+	uint32_t			energy_accumulator;
+
+	/* Average clocks */
+	uint16_t			average_gfxclk_frequency;
+	uint16_t			average_socclk_frequency;
+	uint16_t			average_uclk_frequency;
+	uint16_t			average_vclk0_frequency;
+	uint16_t			average_dclk0_frequency;
+	uint16_t			average_vclk1_frequency;
+	uint16_t			average_dclk1_frequency;
+
+	/* Current clocks */
+	uint16_t			current_gfxclk;
+	uint16_t			current_socclk;
+	uint16_t			current_uclk;
+	uint16_t			current_vclk0;
+	uint16_t			current_dclk0;
+	uint16_t			current_vclk1;
+	uint16_t			current_dclk1;
+
+	/* Throttle status */
+	uint32_t			throttle_status;
+
+	/* Fans */
+	uint16_t			current_fan_speed;
+
+	/* Link width/speed */
+	uint8_t				pcie_link_width;
+	uint8_t				pcie_link_speed; // in 0.1 GT/s
+};
+
+struct gpu_metrics_v2_0 {
+	struct metrics_table_header	common_header;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Temperature */
+	uint16_t			temperature_gfx; // gfx temperature on APUs
+	uint16_t			temperature_soc; // soc temperature on APUs
+	uint16_t			temperature_core[8]; // CPU core temperature on APUs
+	uint16_t			temperature_l3[2];
+
+	/* Utilization */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_mm_activity; // UVD or VCN
+
+	/* Power/Energy */
+	uint16_t			average_socket_power; // dGPU + APU power on A + A platform
+	uint16_t			average_cpu_power;
+	uint16_t			average_soc_power;
+	uint16_t			average_gfx_power;
+	uint16_t			average_core_power[8]; // CPU core power on APUs
+
+	/* Average clocks */
+	uint16_t			average_gfxclk_frequency;
+	uint16_t			average_socclk_frequency;
+	uint16_t			average_uclk_frequency;
+	uint16_t			average_fclk_frequency;
+	uint16_t			average_vclk_frequency;
+	uint16_t			average_dclk_frequency;
+
+	/* Current clocks */
+	uint16_t			current_gfxclk;
+	uint16_t			current_socclk;
+	uint16_t			current_uclk;
+	uint16_t			current_fclk;
+	uint16_t			current_vclk;
+	uint16_t			current_dclk;
+	uint16_t			current_coreclk[8]; // CPU core clocks
+	uint16_t			current_l3clk[2];
+
+	/* Throttle status */
+	uint32_t			throttle_status;
+
+	/* Fans */
+	uint16_t			fan_pwm;
+
+	uint16_t			padding;
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/Makefile b/drivers/gpu/drm/amd/pm/Makefile
new file mode 100644
index 000000000000..f01e86030cd1
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/Makefile
@@ -0,0 +1,46 @@
+#
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+
+subdir-ccflags-y += \
+		-I$(FULL_AMD_PATH)/pm/inc/  \
+		-I$(FULL_AMD_PATH)/include/asic_reg  \
+		-I$(FULL_AMD_PATH)/include  \
+		-I$(FULL_AMD_PATH)/pm/swsmu \
+		-I$(FULL_AMD_PATH)/pm/swsmu/smu11 \
+		-I$(FULL_AMD_PATH)/pm/swsmu/smu12 \
+		-I$(FULL_AMD_PATH)/pm/powerplay \
+		-I$(FULL_AMD_PATH)/pm/powerplay/smumgr\
+		-I$(FULL_AMD_PATH)/pm/powerplay/hwmgr
+
+AMD_PM_PATH = ../pm
+
+PM_LIBS = swsmu powerplay
+
+AMD_PM = $(addsuffix /Makefile,$(addprefix $(FULL_AMD_PATH)/pm/,$(PM_LIBS)))
+
+include $(AMD_PM)
+
+PM_MGR = amdgpu_dpm.o amdgpu_pm.o
+
+AMD_PM_POWER = $(addprefix $(AMD_PM_PATH)/,$(PM_MGR))
+
+AMD_POWERPLAY_FILES += $(AMD_PM_POWER)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 2082c0acd216..17a45baff638 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -28,6 +28,11 @@
 #include "amdgpu_dpm.h"
 #include "atom.h"
 #include "amd_pcie.h"
+#include "amdgpu_display.h"
+#include "hwmgr.h"
+#include <linux/power_supply.h>
+
+#define WIDTH_4K 3840
 
 void amdgpu_dpm_print_class_info(u32 class, u32 class2)
 {
@@ -117,7 +122,7 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
 
 void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev)
 {
-	struct drm_device *ddev = adev->ddev;
+	struct drm_device *ddev = adev_to_drm(adev);
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
 
@@ -138,7 +143,7 @@ void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev)
 
 u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
 	u32 vblank_in_pixels;
@@ -165,7 +170,7 @@ u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 
 u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
 	u32 vrefresh = 0;
@@ -1110,8 +1115,6 @@ int amdgpu_dpm_baco_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 	int ret = 0;
 
-	dev_info(adev->dev, "GPU BACO reset\n");
-
 	if (is_support_sw_smu(adev)) {
 		ret = smu_baco_enter(smu);
 		if (ret)
@@ -1216,3 +1219,469 @@ int amdgpu_dpm_allow_xgmi_power_down(struct amdgpu_device *adev, bool en)
 
 	return 0;
 }
+
+int amdgpu_dpm_enable_mgpu_fan_boost(struct amdgpu_device *adev)
+{
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs =
+			adev->powerplay.pp_funcs;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (is_support_sw_smu(adev))
+		ret = smu_enable_mgpu_fan_boost(smu);
+	else if (pp_funcs && pp_funcs->enable_mgpu_fan_boost)
+		ret = pp_funcs->enable_mgpu_fan_boost(pp_handle);
+
+	return ret;
+}
+
+int amdgpu_dpm_set_clockgating_by_smu(struct amdgpu_device *adev,
+				      uint32_t msg_id)
+{
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs =
+			adev->powerplay.pp_funcs;
+	int ret = 0;
+
+	if (pp_funcs && pp_funcs->set_clockgating_by_smu)
+		ret = pp_funcs->set_clockgating_by_smu(pp_handle,
+						       msg_id);
+
+	return ret;
+}
+
+int amdgpu_dpm_smu_i2c_bus_access(struct amdgpu_device *adev,
+				  bool acquire)
+{
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs =
+			adev->powerplay.pp_funcs;
+	int ret = -EOPNOTSUPP;
+
+	if (pp_funcs && pp_funcs->smu_i2c_bus_access)
+		ret = pp_funcs->smu_i2c_bus_access(pp_handle,
+						   acquire);
+
+	return ret;
+}
+
+void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
+{
+	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		if (power_supply_is_system_supplied() > 0)
+			adev->pm.ac_power = true;
+		else
+			adev->pm.ac_power = false;
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->enable_bapm)
+			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
+		mutex_unlock(&adev->pm.mutex);
+
+		if (is_support_sw_smu(adev))
+			smu_set_ac_dc(&adev->smu);
+	}
+}
+
+int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors sensor,
+			   void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	if (!data || !size)
+		return -EINVAL;
+
+	if (is_support_sw_smu(adev))
+		ret = smu_read_sensor(&adev->smu, sensor, data, size);
+	else {
+		if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->read_sensor)
+			ret = adev->powerplay.pp_funcs->read_sensor((adev)->powerplay.pp_handle,
+								    sensor, data, size);
+		else
+			ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device,
+			     pm.dpm.thermal.work);
+	/* switch to the thermal state */
+	enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
+	int temp, size = sizeof(temp);
+
+	if (!adev->pm.dpm_enabled)
+		return;
+
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_TEMP,
+				    (void *)&temp, &size)) {
+		if (temp < adev->pm.dpm.thermal.min_temp)
+			/* switch back the user state */
+			dpm_state = adev->pm.dpm.user_state;
+	} else {
+		if (adev->pm.dpm.thermal.high_to_low)
+			/* switch back the user state */
+			dpm_state = adev->pm.dpm.user_state;
+	}
+	mutex_lock(&adev->pm.mutex);
+	if (dpm_state == POWER_STATE_TYPE_INTERNAL_THERMAL)
+		adev->pm.dpm.thermal_active = true;
+	else
+		adev->pm.dpm.thermal_active = false;
+	adev->pm.dpm.state = dpm_state;
+	mutex_unlock(&adev->pm.mutex);
+
+	amdgpu_pm_compute_clocks(adev);
+}
+
+static struct amdgpu_ps *amdgpu_dpm_pick_power_state(struct amdgpu_device *adev,
+						     enum amd_pm_state_type dpm_state)
+{
+	int i;
+	struct amdgpu_ps *ps;
+	u32 ui_class;
+	bool single_display = (adev->pm.dpm.new_active_crtc_count < 2) ?
+		true : false;
+
+	/* check if the vblank period is too short to adjust the mclk */
+	if (single_display && adev->powerplay.pp_funcs->vblank_too_short) {
+		if (amdgpu_dpm_vblank_too_short(adev))
+			single_display = false;
+	}
+
+	/* certain older asics have a separare 3D performance state,
+	 * so try that first if the user selected performance
+	 */
+	if (dpm_state == POWER_STATE_TYPE_PERFORMANCE)
+		dpm_state = POWER_STATE_TYPE_INTERNAL_3DPERF;
+	/* balanced states don't exist at the moment */
+	if (dpm_state == POWER_STATE_TYPE_BALANCED)
+		dpm_state = POWER_STATE_TYPE_PERFORMANCE;
+
+restart_search:
+	/* Pick the best power state based on current conditions */
+	for (i = 0; i < adev->pm.dpm.num_ps; i++) {
+		ps = &adev->pm.dpm.ps[i];
+		ui_class = ps->class & ATOM_PPLIB_CLASSIFICATION_UI_MASK;
+		switch (dpm_state) {
+		/* user states */
+		case POWER_STATE_TYPE_BATTERY:
+			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_BATTERY) {
+				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
+					if (single_display)
+						return ps;
+				} else
+					return ps;
+			}
+			break;
+		case POWER_STATE_TYPE_BALANCED:
+			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_BALANCED) {
+				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
+					if (single_display)
+						return ps;
+				} else
+					return ps;
+			}
+			break;
+		case POWER_STATE_TYPE_PERFORMANCE:
+			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_PERFORMANCE) {
+				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
+					if (single_display)
+						return ps;
+				} else
+					return ps;
+			}
+			break;
+		/* internal states */
+		case POWER_STATE_TYPE_INTERNAL_UVD:
+			if (adev->pm.dpm.uvd_ps)
+				return adev->pm.dpm.uvd_ps;
+			else
+				break;
+		case POWER_STATE_TYPE_INTERNAL_UVD_SD:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_SDSTATE)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_UVD_HD:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_HDSTATE)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_HD2STATE)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
+			if (ps->class2 & ATOM_PPLIB_CLASSIFICATION2_MVC)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_BOOT:
+			return adev->pm.dpm.boot_ps;
+		case POWER_STATE_TYPE_INTERNAL_THERMAL:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_THERMAL)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_ACPI:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_ACPI)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_ULV:
+			if (ps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV)
+				return ps;
+			break;
+		case POWER_STATE_TYPE_INTERNAL_3DPERF:
+			if (ps->class & ATOM_PPLIB_CLASSIFICATION_3DPERFORMANCE)
+				return ps;
+			break;
+		default:
+			break;
+		}
+	}
+	/* use a fallback state if we didn't match */
+	switch (dpm_state) {
+	case POWER_STATE_TYPE_INTERNAL_UVD_SD:
+		dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD;
+		goto restart_search;
+	case POWER_STATE_TYPE_INTERNAL_UVD_HD:
+	case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
+	case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
+		if (adev->pm.dpm.uvd_ps) {
+			return adev->pm.dpm.uvd_ps;
+		} else {
+			dpm_state = POWER_STATE_TYPE_PERFORMANCE;
+			goto restart_search;
+		}
+	case POWER_STATE_TYPE_INTERNAL_THERMAL:
+		dpm_state = POWER_STATE_TYPE_INTERNAL_ACPI;
+		goto restart_search;
+	case POWER_STATE_TYPE_INTERNAL_ACPI:
+		dpm_state = POWER_STATE_TYPE_BATTERY;
+		goto restart_search;
+	case POWER_STATE_TYPE_BATTERY:
+	case POWER_STATE_TYPE_BALANCED:
+	case POWER_STATE_TYPE_INTERNAL_3DPERF:
+		dpm_state = POWER_STATE_TYPE_PERFORMANCE;
+		goto restart_search;
+	default:
+		break;
+	}
+
+	return NULL;
+}
+
+static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
+{
+	struct amdgpu_ps *ps;
+	enum amd_pm_state_type dpm_state;
+	int ret;
+	bool equal = false;
+
+	/* if dpm init failed */
+	if (!adev->pm.dpm_enabled)
+		return;
+
+	if (adev->pm.dpm.user_state != adev->pm.dpm.state) {
+		/* add other state override checks here */
+		if ((!adev->pm.dpm.thermal_active) &&
+		    (!adev->pm.dpm.uvd_active))
+			adev->pm.dpm.state = adev->pm.dpm.user_state;
+	}
+	dpm_state = adev->pm.dpm.state;
+
+	ps = amdgpu_dpm_pick_power_state(adev, dpm_state);
+	if (ps)
+		adev->pm.dpm.requested_ps = ps;
+	else
+		return;
+
+	if (amdgpu_dpm == 1 && adev->powerplay.pp_funcs->print_power_state) {
+		printk("switching from power state:\n");
+		amdgpu_dpm_print_power_state(adev, adev->pm.dpm.current_ps);
+		printk("switching to power state:\n");
+		amdgpu_dpm_print_power_state(adev, adev->pm.dpm.requested_ps);
+	}
+
+	/* update whether vce is active */
+	ps->vce_active = adev->pm.dpm.vce_active;
+	if (adev->powerplay.pp_funcs->display_configuration_changed)
+		amdgpu_dpm_display_configuration_changed(adev);
+
+	ret = amdgpu_dpm_pre_set_power_state(adev);
+	if (ret)
+		return;
+
+	if (adev->powerplay.pp_funcs->check_state_equal) {
+		if (0 != amdgpu_dpm_check_state_equal(adev, adev->pm.dpm.current_ps, adev->pm.dpm.requested_ps, &equal))
+			equal = false;
+	}
+
+	if (equal)
+		return;
+
+	amdgpu_dpm_set_power_state(adev);
+	amdgpu_dpm_post_set_power_state(adev);
+
+	adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs;
+	adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count;
+
+	if (adev->powerplay.pp_funcs->force_performance_level) {
+		if (adev->pm.dpm.thermal_active) {
+			enum amd_dpm_forced_level level = adev->pm.dpm.forced_level;
+			/* force low perf level for thermal */
+			amdgpu_dpm_force_performance_level(adev, AMD_DPM_FORCED_LEVEL_LOW);
+			/* save the user's level */
+			adev->pm.dpm.forced_level = level;
+		} else {
+			/* otherwise, user selected level */
+			amdgpu_dpm_force_performance_level(adev, adev->pm.dpm.forced_level);
+		}
+	}
+}
+
+void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
+{
+	int i = 0;
+
+	if (!adev->pm.dpm_enabled)
+		return;
+
+	if (adev->mode_info.num_crtc)
+		amdgpu_display_bandwidth_update(adev);
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+		if (ring && ring->sched.ready)
+			amdgpu_fence_wait_empty(ring);
+	}
+
+	if (is_support_sw_smu(adev)) {
+		struct smu_dpm_context *smu_dpm = &adev->smu.smu_dpm;
+		smu_handle_task(&adev->smu,
+				smu_dpm->dpm_level,
+				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE,
+				true);
+	} else {
+		if (adev->powerplay.pp_funcs->dispatch_tasks) {
+			if (!amdgpu_device_has_dc_support(adev)) {
+				mutex_lock(&adev->pm.mutex);
+				amdgpu_dpm_get_active_displays(adev);
+				adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
+				adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
+				adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
+				/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
+				if (adev->pm.pm_display_cfg.vrefresh > 120)
+					adev->pm.pm_display_cfg.min_vblank_time = 0;
+				if (adev->powerplay.pp_funcs->display_configuration_change)
+					adev->powerplay.pp_funcs->display_configuration_change(
+									adev->powerplay.pp_handle,
+									&adev->pm.pm_display_cfg);
+				mutex_unlock(&adev->pm.mutex);
+			}
+			amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_DISPLAY_CONFIG_CHANGE, NULL);
+		} else {
+			mutex_lock(&adev->pm.mutex);
+			amdgpu_dpm_get_active_displays(adev);
+			amdgpu_dpm_change_power_state_locked(adev);
+			mutex_unlock(&adev->pm.mutex);
+		}
+	}
+}
+
+void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
+{
+	int ret = 0;
+
+	if (adev->family == AMDGPU_FAMILY_SI) {
+		mutex_lock(&adev->pm.mutex);
+		if (enable) {
+			adev->pm.dpm.uvd_active = true;
+			adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD;
+		} else {
+			adev->pm.dpm.uvd_active = false;
+		}
+		mutex_unlock(&adev->pm.mutex);
+
+		amdgpu_pm_compute_clocks(adev);
+	} else {
+		ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
+		if (ret)
+			DRM_ERROR("Dpm %s uvd failed, ret = %d. \n",
+				  enable ? "enable" : "disable", ret);
+
+		/* enable/disable Low Memory PState for UVD (4k videos) */
+		if (adev->asic_type == CHIP_STONEY &&
+			adev->uvd.decode_image_width >= WIDTH_4K) {
+			struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+
+			if (hwmgr && hwmgr->hwmgr_func &&
+			    hwmgr->hwmgr_func->update_nbdpm_pstate)
+				hwmgr->hwmgr_func->update_nbdpm_pstate(hwmgr,
+								       !enable,
+								       true);
+		}
+	}
+}
+
+void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
+{
+	int ret = 0;
+
+	if (adev->family == AMDGPU_FAMILY_SI) {
+		mutex_lock(&adev->pm.mutex);
+		if (enable) {
+			adev->pm.dpm.vce_active = true;
+			/* XXX select vce level based on ring/task */
+			adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL;
+		} else {
+			adev->pm.dpm.vce_active = false;
+		}
+		mutex_unlock(&adev->pm.mutex);
+
+		amdgpu_pm_compute_clocks(adev);
+	} else {
+		ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
+		if (ret)
+			DRM_ERROR("Dpm %s vce failed, ret = %d. \n",
+				  enable ? "enable" : "disable", ret);
+	}
+}
+
+void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
+{
+	int i;
+
+	if (adev->powerplay.pp_funcs->print_power_state == NULL)
+		return;
+
+	for (i = 0; i < adev->pm.dpm.num_ps; i++)
+		amdgpu_dpm_print_power_state(adev, &adev->pm.dpm.ps[i]);
+
+}
+
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable)
+{
+	int ret = 0;
+
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_JPEG, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s jpeg failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
+}
+
+int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version)
+{
+	int r;
+
+	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->load_firmware) {
+		r = adev->powerplay.pp_funcs->load_firmware(adev->powerplay.pp_handle);
+		if (r) {
+			pr_err("smu firmware loading failed\n");
+			return r;
+		}
+		*smu_version = adev->pm.fw_version;
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index e4dbf14320b6..2d924e88a215 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -29,17 +29,14 @@
 #include "amdgpu_drv.h"
 #include "amdgpu_pm.h"
 #include "amdgpu_dpm.h"
-#include "amdgpu_display.h"
 #include "amdgpu_smu.h"
 #include "atom.h"
-#include <linux/power_supply.h>
 #include <linux/pci.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/nospec.h>
 #include <linux/pm_runtime.h>
 #include "hwmgr.h"
-#define WIDTH_4K 3840
 
 static const struct cg_flag_name clocks[] = {
 	{AMD_CG_SUPPORT_GFX_MGCG, "Graphics Medium Grain Clock Gating"},
@@ -81,45 +78,6 @@ static const struct hwmon_temp_label {
 	{PP_TEMP_MEM, "mem"},
 };
 
-void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
-{
-	if (adev->pm.dpm_enabled) {
-		mutex_lock(&adev->pm.mutex);
-		if (power_supply_is_system_supplied() > 0)
-			adev->pm.ac_power = true;
-		else
-			adev->pm.ac_power = false;
-		if (adev->powerplay.pp_funcs &&
-		    adev->powerplay.pp_funcs->enable_bapm)
-			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
-		mutex_unlock(&adev->pm.mutex);
-
-		if (is_support_sw_smu(adev))
-			smu_set_ac_dc(&adev->smu);
-	}
-}
-
-int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors sensor,
-			   void *data, uint32_t *size)
-{
-	int ret = 0;
-
-	if (!data || !size)
-		return -EINVAL;
-
-	if (is_support_sw_smu(adev))
-		ret = smu_read_sensor(&adev->smu, sensor, data, size);
-	else {
-		if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->read_sensor)
-			ret = adev->powerplay.pp_funcs->read_sensor((adev)->powerplay.pp_handle,
-								    sensor, data, size);
-		else
-			ret = -EINVAL;
-	}
-
-	return ret;
-}
-
 /**
  * DOC: power_dpm_state
  *
@@ -159,11 +117,11 @@ static ssize_t amdgpu_get_power_dpm_state(struct device *dev,
 					  char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	enum amd_pm_state_type pm;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -197,11 +155,11 @@ static ssize_t amdgpu_set_power_dpm_state(struct device *dev,
 					  size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	enum amd_pm_state_type  state;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (strncmp("battery", buf, strlen("battery")) == 0)
@@ -303,11 +261,11 @@ static ssize_t amdgpu_get_power_dpm_force_performance_level(struct device *dev,
 							    char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	enum amd_dpm_forced_level level = 0xff;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -344,12 +302,12 @@ static ssize_t amdgpu_set_power_dpm_force_performance_level(struct device *dev,
 							    size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	enum amd_dpm_forced_level level;
 	enum amd_dpm_forced_level current_level = 0xff;
 	int ret = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (strncmp("low", buf, strlen("low")) == 0) {
@@ -449,11 +407,11 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct pp_states_info data;
 	int i, buf_len, ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -491,13 +449,13 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	struct pp_states_info data;
 	struct smu_context *smu = &adev->smu;
 	enum amd_pm_state_type pm = 0;
 	int i = 0, ret = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -536,9 +494,9 @@ static ssize_t amdgpu_get_pp_force_state(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (adev->pp_force_state_enabled)
@@ -553,12 +511,12 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	enum amd_pm_state_type state = 0;
 	unsigned long idx;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (strlen(buf) == 1)
@@ -614,11 +572,11 @@ static ssize_t amdgpu_get_pp_table(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	char *table = NULL;
 	int size, ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -659,10 +617,10 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -694,6 +652,52 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * in each power level within a power state.  The pp_od_clk_voltage is used for
  * this.
  *
+ * Note that the actual memory controller clock rate are exposed, not
+ * the effective memory clock of the DRAMs. To translate it, use the
+ * following formula:
+ *
+ * Clock conversion (Mhz):
+ *
+ * HBM: effective_memory_clock = memory_controller_clock * 1
+ *
+ * G5: effective_memory_clock = memory_controller_clock * 1
+ *
+ * G6: effective_memory_clock = memory_controller_clock * 2
+ *
+ * DRAM data rate (MT/s):
+ *
+ * HBM: effective_memory_clock * 2 = data_rate
+ *
+ * G5: effective_memory_clock * 4 = data_rate
+ *
+ * G6: effective_memory_clock * 8 = data_rate
+ *
+ * Bandwidth (MB/s):
+ *
+ * data_rate * vram_bit_width / 8 = memory_bandwidth
+ *
+ * Some examples:
+ *
+ * G5 on RX460:
+ *
+ * memory_controller_clock = 1750 Mhz
+ *
+ * effective_memory_clock = 1750 Mhz * 1 = 1750 Mhz
+ *
+ * data rate = 1750 * 4 = 7000 MT/s
+ *
+ * memory_bandwidth = 7000 * 128 bits / 8 = 112000 MB/s
+ *
+ * G6 on RX5700:
+ *
+ * memory_controller_clock = 875 Mhz
+ *
+ * effective_memory_clock = 875 Mhz * 2 = 1750 Mhz
+ *
+ * data rate = 1750 * 8 = 14000 MT/s
+ *
+ * memory_bandwidth = 14000 * 256 bits / 8 = 448000 MB/s
+ *
  * < For Vega10 and previous ASICs >
  *
  * Reading the file will display:
@@ -759,7 +763,7 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t parameter_size = 0;
 	long parameter[64];
@@ -769,7 +773,7 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 	const char delimiter[3] = {' ', '\n', '\0'};
 	uint32_t type;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (count > 127)
@@ -796,7 +800,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 		tmp_str++;
 	while (isspace(*++tmp_str));
 
-	while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
+	while (tmp_str[0]) {
+		sub_str = strsep(&tmp_str, delimiter);
 		ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 		if (ret)
 			return -EINVAL;
@@ -858,11 +863,11 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -912,11 +917,11 @@ static ssize_t amdgpu_set_pp_features(struct device *dev,
 				      size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint64_t featuremask;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = kstrtou64(buf, 0, &featuremask);
@@ -957,11 +962,11 @@ static ssize_t amdgpu_get_pp_features(struct device *dev,
 				      char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1018,11 +1023,11 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1066,7 +1071,8 @@ static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 	memcpy(buf_cpy, buf, bytes);
 	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
-	while ((sub_str = strsep(&tmp, delimiter)) != NULL) {
+	while (tmp[0]) {
+		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
 			if (ret)
@@ -1085,11 +1091,11 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t mask = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1121,11 +1127,11 @@ static ssize_t amdgpu_get_pp_dpm_mclk(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1153,11 +1159,11 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t mask = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1189,11 +1195,11 @@ static ssize_t amdgpu_get_pp_dpm_socclk(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1221,11 +1227,11 @@ static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t mask = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1259,11 +1265,11 @@ static ssize_t amdgpu_get_pp_dpm_fclk(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1291,11 +1297,11 @@ static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t mask = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1329,11 +1335,11 @@ static ssize_t amdgpu_get_pp_dpm_dcefclk(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1361,11 +1367,11 @@ static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t mask = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1399,11 +1405,11 @@ static ssize_t amdgpu_get_pp_dpm_pcie(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1431,11 +1437,11 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	uint32_t mask = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
@@ -1469,11 +1475,11 @@ static ssize_t amdgpu_get_pp_sclk_od(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t value = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1499,11 +1505,11 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	long int value;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = kstrtol(buf, 0, &value);
@@ -1542,11 +1548,11 @@ static ssize_t amdgpu_get_pp_mclk_od(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t value = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1572,11 +1578,11 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
 		size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int ret;
 	long int value;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = kstrtol(buf, 0, &value);
@@ -1635,11 +1641,11 @@ static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	ssize_t size;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	ret = pm_runtime_get_sync(ddev->dev);
@@ -1669,7 +1675,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 {
 	int ret;
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t parameter_size = 0;
 	long parameter[64];
 	char *sub_str, buf_cpy[128];
@@ -1679,7 +1685,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 	long int profile_mode = 0;
 	const char delimiter[3] = {' ', '\n', '\0'};
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	tmp[0] = *(buf);
@@ -1695,7 +1701,8 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 			i++;
 		memcpy(buf_cpy, buf, count-i);
 		tmp_str = buf_cpy;
-		while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
+		while (tmp_str[0]) {
+			sub_str = strsep(&tmp_str, delimiter);
 			ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 			if (ret)
 				return -EINVAL;
@@ -1739,10 +1746,10 @@ static ssize_t amdgpu_get_gpu_busy_percent(struct device *dev,
 					   char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int r, value, size = sizeof(value);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	r = pm_runtime_get_sync(ddev->dev);
@@ -1777,10 +1784,10 @@ static ssize_t amdgpu_get_mem_busy_percent(struct device *dev,
 					   char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	int r, value, size = sizeof(value);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	r = pm_runtime_get_sync(ddev->dev);
@@ -1819,11 +1826,11 @@ static ssize_t amdgpu_get_pcie_bw(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint64_t count0 = 0, count1 = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (adev->flags & AMD_IS_APU)
@@ -1862,9 +1869,9 @@ static ssize_t amdgpu_get_unique_id(struct device *dev,
 		char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (adev->unique_id)
@@ -1893,10 +1900,10 @@ static ssize_t amdgpu_get_thermal_throttling_logging(struct device *dev,
 						     char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%s: thermal throttling logging %s, with interval %d seconds\n",
-			adev->ddev->unique,
+			adev_to_drm(adev)->unique,
 			atomic_read(&adev->throttling_logging_enabled) ? "enabled" : "disabled",
 			adev->throttling_logging_rs.interval / HZ + 1);
 }
@@ -1907,7 +1914,7 @@ static ssize_t amdgpu_set_thermal_throttling_logging(struct device *dev,
 						     size_t count)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	long throttling_logging_interval;
 	unsigned long flags;
 	int ret = 0;
@@ -1940,6 +1947,57 @@ static ssize_t amdgpu_set_thermal_throttling_logging(struct device *dev,
 	return count;
 }
 
+/**
+ * DOC: gpu_metrics
+ *
+ * The amdgpu driver provides a sysfs API for retrieving current gpu
+ * metrics data. The file gpu_metrics is used for this. Reading the
+ * file will dump all the current gpu metrics data.
+ *
+ * These data include temperature, frequency, engines utilization,
+ * power consume, throttler status, fan speed and cpu core statistics(
+ * available for APU only). That's it will give a snapshot of all sensors
+ * at the same time.
+ */
+static ssize_t amdgpu_get_gpu_metrics(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	void *gpu_metrics;
+	ssize_t size = 0;
+	int ret;
+
+	if (amdgpu_in_reset(adev))
+		return -EPERM;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(ddev->dev);
+		return ret;
+	}
+
+	if (is_support_sw_smu(adev))
+		size = smu_sys_get_gpu_metrics(&adev->smu, &gpu_metrics);
+	else if (adev->powerplay.pp_funcs->get_gpu_metrics)
+		size = amdgpu_dpm_get_gpu_metrics(adev, &gpu_metrics);
+
+	if (size <= 0)
+		goto out;
+
+	if (size >= PAGE_SIZE)
+		size = PAGE_SIZE - 1;
+
+	memcpy(buf, gpu_metrics, size);
+
+out:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
+}
+
 static struct amdgpu_device_attr amdgpu_device_attrs[] = {
 	AMDGPU_DEVICE_ATTR_RW(power_dpm_state,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(power_dpm_force_performance_level,	ATTR_FLAG_BASIC),
@@ -1963,6 +2021,7 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = {
 	AMDGPU_DEVICE_ATTR_RW(pp_features,				ATTR_FLAG_BASIC),
 	AMDGPU_DEVICE_ATTR_RO(unique_id,				ATTR_FLAG_BASIC),
 	AMDGPU_DEVICE_ATTR_RW(thermal_throttling_logging,		ATTR_FLAG_BASIC),
+	AMDGPU_DEVICE_ATTR_RO(gpu_metrics,				ATTR_FLAG_BASIC),
 };
 
 static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_attr *attr,
@@ -2012,6 +2071,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	} else if (DEVICE_ATTR_IS(pp_features)) {
 		if (adev->flags & AMD_IS_APU || asic_type < CHIP_VEGA10)
 			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(gpu_metrics)) {
+		if (asic_type < CHIP_VEGA12)
+			*states = ATTR_STATE_UNSUPPORTED;
 	}
 
 	if (asic_type == CHIP_ARCTURUS) {
@@ -2131,15 +2193,15 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 	int channel = to_sensor_dev_attr(attr)->index;
 	int r, temp = 0, size = sizeof(temp);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (channel >= PP_TEMP_MAX)
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2164,8 +2226,8 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 		break;
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2267,12 +2329,12 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev,
 	u32 pwm_mode = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	ret = pm_runtime_get_sync(adev->ddev->dev);
+	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
@@ -2280,16 +2342,16 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev,
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
 		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return -EINVAL;
 		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return sprintf(buf, "%i\n", pwm_mode);
 }
@@ -2303,16 +2365,16 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 	int err, ret;
 	int value;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	err = kstrtoint(buf, 10, &value);
 	if (err)
 		return err;
 
-	ret = pm_runtime_get_sync(adev->ddev->dev);
+	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
@@ -2320,16 +2382,16 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 		smu_set_fan_control_mode(&adev->smu, value);
 	} else {
 		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return -EINVAL;
 		}
 
 		amdgpu_dpm_set_fan_control_mode(adev, value);
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return count;
 }
@@ -2357,12 +2419,12 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2373,15 +2435,15 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 
 	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
 		pr_info("manual fan speed control should be enabled first\n");
-		pm_runtime_mark_last_busy(adev->ddev->dev);
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return -EINVAL;
 	}
 
 	err = kstrtou32(buf, 10, &value);
 	if (err) {
-		pm_runtime_mark_last_busy(adev->ddev->dev);
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2394,8 +2456,8 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2411,12 +2473,12 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2427,8 +2489,8 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2446,12 +2508,12 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2462,8 +2524,8 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2480,20 +2542,20 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev,
 	u32 size = sizeof(min_rpm);
 	int r;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM,
 				   (void *)&min_rpm, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2510,20 +2572,20 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev,
 	u32 size = sizeof(max_rpm);
 	int r;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM,
 				   (void *)&max_rpm, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2539,12 +2601,12 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
 	int err;
 	u32 rpm = 0;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2555,8 +2617,8 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2573,12 +2635,12 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2588,15 +2650,15 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 
 	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
-		pm_runtime_mark_last_busy(adev->ddev->dev);
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return -ENODATA;
 	}
 
 	err = kstrtou32(buf, 10, &value);
 	if (err) {
-		pm_runtime_mark_last_busy(adev->ddev->dev);
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2607,8 +2669,8 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2624,12 +2686,12 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
 	u32 pwm_mode = 0;
 	int ret;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	ret = pm_runtime_get_sync(adev->ddev->dev);
+	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
@@ -2637,16 +2699,16 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
 		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return -EINVAL;
 		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return sprintf(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
 }
@@ -2661,7 +2723,7 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	int value;
 	u32 pwm_mode;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	err = kstrtoint(buf, 10, &value);
@@ -2675,9 +2737,9 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	else
 		return -EINVAL;
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2685,15 +2747,15 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 		smu_set_fan_control_mode(&adev->smu, pwm_mode);
 	} else {
 		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 			return -EINVAL;
 		}
 		amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return count;
 }
@@ -2706,12 +2768,12 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev,
 	u32 vddgfx;
 	int r, size = sizeof(vddgfx);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2719,8 +2781,8 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev,
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDGFX,
 				   (void *)&vddgfx, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2743,16 +2805,16 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	u32 vddnb;
 	int r, size = sizeof(vddnb);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	/* only APUs have vddnb */
 	if  (!(adev->flags & AMD_IS_APU))
 		return -EINVAL;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2760,8 +2822,8 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB,
 				   (void *)&vddnb, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2785,12 +2847,12 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 	int r, size = sizeof(u32);
 	unsigned uw;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2798,8 +2860,8 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_POWER,
 				   (void *)&query, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2826,12 +2888,12 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 	ssize_t size;
 	int r;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2845,8 +2907,8 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return size;
 }
@@ -2860,12 +2922,12 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 	ssize_t size;
 	int r;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2879,8 +2941,8 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return size;
 }
@@ -2895,7 +2957,7 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	int err;
 	u32 value;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	if (amdgpu_sriov_vf(adev))
@@ -2908,9 +2970,9 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	value = value / 1000000; /* convert to Watt */
 
 
-	err = pm_runtime_get_sync(adev->ddev->dev);
+	err = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (err < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return err;
 	}
 
@@ -2921,8 +2983,8 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	else
 		err = -EINVAL;
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (err)
 		return err;
@@ -2938,12 +3000,12 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 	uint32_t sclk;
 	int r, size = sizeof(sclk);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2951,8 +3013,8 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_SCLK,
 				   (void *)&sclk, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -2975,12 +3037,12 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 	uint32_t mclk;
 	int r, size = sizeof(mclk);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
-	r = pm_runtime_get_sync(adev->ddev->dev);
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
@@ -2988,8 +3050,8 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_MCLK,
 				   (void *)&mclk, &size);
 
-	pm_runtime_mark_last_busy(adev->ddev->dev);
-	pm_runtime_put_autosuspend(adev->ddev->dev);
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	if (r)
 		return r;
@@ -3249,14 +3311,18 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	}
 
 	if (((adev->flags & AMD_IS_APU) ||
-	     adev->family == AMDGPU_FAMILY_SI ||	/* not implemented yet */
-	     adev->family == AMDGPU_FAMILY_KV) &&	/* not implemented yet */
-	    (attr == &sensor_dev_attr_power1_average.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+	     adev->family == AMDGPU_FAMILY_SI) &&	/* not implemented yet */
+	    (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
 	     attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr||
 	     attr == &sensor_dev_attr_power1_cap.dev_attr.attr))
 		return 0;
 
+	if (((adev->family == AMDGPU_FAMILY_SI) ||
+	     ((adev->flags & AMD_IS_APU) &&
+	      (adev->asic_type < CHIP_RENOIR))) &&	/* not implemented yet */
+	    (attr == &sensor_dev_attr_power1_average.dev_attr.attr))
+		return 0;
+
 	if (!is_support_sw_smu(adev)) {
 		/* hide max/min values if we can't both query and manage the fan */
 		if ((!adev->powerplay.pp_funcs->set_fan_speed_percent &&
@@ -3321,338 +3387,6 @@ static const struct attribute_group *hwmon_groups[] = {
 	NULL
 };
 
-void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
-{
-	struct amdgpu_device *adev =
-		container_of(work, struct amdgpu_device,
-			     pm.dpm.thermal.work);
-	/* switch to the thermal state */
-	enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
-	int temp, size = sizeof(temp);
-
-	if (!adev->pm.dpm_enabled)
-		return;
-
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_TEMP,
-				    (void *)&temp, &size)) {
-		if (temp < adev->pm.dpm.thermal.min_temp)
-			/* switch back the user state */
-			dpm_state = adev->pm.dpm.user_state;
-	} else {
-		if (adev->pm.dpm.thermal.high_to_low)
-			/* switch back the user state */
-			dpm_state = adev->pm.dpm.user_state;
-	}
-	mutex_lock(&adev->pm.mutex);
-	if (dpm_state == POWER_STATE_TYPE_INTERNAL_THERMAL)
-		adev->pm.dpm.thermal_active = true;
-	else
-		adev->pm.dpm.thermal_active = false;
-	adev->pm.dpm.state = dpm_state;
-	mutex_unlock(&adev->pm.mutex);
-
-	amdgpu_pm_compute_clocks(adev);
-}
-
-static struct amdgpu_ps *amdgpu_dpm_pick_power_state(struct amdgpu_device *adev,
-						     enum amd_pm_state_type dpm_state)
-{
-	int i;
-	struct amdgpu_ps *ps;
-	u32 ui_class;
-	bool single_display = (adev->pm.dpm.new_active_crtc_count < 2) ?
-		true : false;
-
-	/* check if the vblank period is too short to adjust the mclk */
-	if (single_display && adev->powerplay.pp_funcs->vblank_too_short) {
-		if (amdgpu_dpm_vblank_too_short(adev))
-			single_display = false;
-	}
-
-	/* certain older asics have a separare 3D performance state,
-	 * so try that first if the user selected performance
-	 */
-	if (dpm_state == POWER_STATE_TYPE_PERFORMANCE)
-		dpm_state = POWER_STATE_TYPE_INTERNAL_3DPERF;
-	/* balanced states don't exist at the moment */
-	if (dpm_state == POWER_STATE_TYPE_BALANCED)
-		dpm_state = POWER_STATE_TYPE_PERFORMANCE;
-
-restart_search:
-	/* Pick the best power state based on current conditions */
-	for (i = 0; i < adev->pm.dpm.num_ps; i++) {
-		ps = &adev->pm.dpm.ps[i];
-		ui_class = ps->class & ATOM_PPLIB_CLASSIFICATION_UI_MASK;
-		switch (dpm_state) {
-		/* user states */
-		case POWER_STATE_TYPE_BATTERY:
-			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_BATTERY) {
-				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
-					if (single_display)
-						return ps;
-				} else
-					return ps;
-			}
-			break;
-		case POWER_STATE_TYPE_BALANCED:
-			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_BALANCED) {
-				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
-					if (single_display)
-						return ps;
-				} else
-					return ps;
-			}
-			break;
-		case POWER_STATE_TYPE_PERFORMANCE:
-			if (ui_class == ATOM_PPLIB_CLASSIFICATION_UI_PERFORMANCE) {
-				if (ps->caps & ATOM_PPLIB_SINGLE_DISPLAY_ONLY) {
-					if (single_display)
-						return ps;
-				} else
-					return ps;
-			}
-			break;
-		/* internal states */
-		case POWER_STATE_TYPE_INTERNAL_UVD:
-			if (adev->pm.dpm.uvd_ps)
-				return adev->pm.dpm.uvd_ps;
-			else
-				break;
-		case POWER_STATE_TYPE_INTERNAL_UVD_SD:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_SDSTATE)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_UVD_HD:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_HDSTATE)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_HD2STATE)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
-			if (ps->class2 & ATOM_PPLIB_CLASSIFICATION2_MVC)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_BOOT:
-			return adev->pm.dpm.boot_ps;
-		case POWER_STATE_TYPE_INTERNAL_THERMAL:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_THERMAL)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_ACPI:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_ACPI)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_ULV:
-			if (ps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV)
-				return ps;
-			break;
-		case POWER_STATE_TYPE_INTERNAL_3DPERF:
-			if (ps->class & ATOM_PPLIB_CLASSIFICATION_3DPERFORMANCE)
-				return ps;
-			break;
-		default:
-			break;
-		}
-	}
-	/* use a fallback state if we didn't match */
-	switch (dpm_state) {
-	case POWER_STATE_TYPE_INTERNAL_UVD_SD:
-		dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD;
-		goto restart_search;
-	case POWER_STATE_TYPE_INTERNAL_UVD_HD:
-	case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
-	case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
-		if (adev->pm.dpm.uvd_ps) {
-			return adev->pm.dpm.uvd_ps;
-		} else {
-			dpm_state = POWER_STATE_TYPE_PERFORMANCE;
-			goto restart_search;
-		}
-	case POWER_STATE_TYPE_INTERNAL_THERMAL:
-		dpm_state = POWER_STATE_TYPE_INTERNAL_ACPI;
-		goto restart_search;
-	case POWER_STATE_TYPE_INTERNAL_ACPI:
-		dpm_state = POWER_STATE_TYPE_BATTERY;
-		goto restart_search;
-	case POWER_STATE_TYPE_BATTERY:
-	case POWER_STATE_TYPE_BALANCED:
-	case POWER_STATE_TYPE_INTERNAL_3DPERF:
-		dpm_state = POWER_STATE_TYPE_PERFORMANCE;
-		goto restart_search;
-	default:
-		break;
-	}
-
-	return NULL;
-}
-
-static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
-{
-	struct amdgpu_ps *ps;
-	enum amd_pm_state_type dpm_state;
-	int ret;
-	bool equal = false;
-
-	/* if dpm init failed */
-	if (!adev->pm.dpm_enabled)
-		return;
-
-	if (adev->pm.dpm.user_state != adev->pm.dpm.state) {
-		/* add other state override checks here */
-		if ((!adev->pm.dpm.thermal_active) &&
-		    (!adev->pm.dpm.uvd_active))
-			adev->pm.dpm.state = adev->pm.dpm.user_state;
-	}
-	dpm_state = adev->pm.dpm.state;
-
-	ps = amdgpu_dpm_pick_power_state(adev, dpm_state);
-	if (ps)
-		adev->pm.dpm.requested_ps = ps;
-	else
-		return;
-
-	if (amdgpu_dpm == 1 && adev->powerplay.pp_funcs->print_power_state) {
-		printk("switching from power state:\n");
-		amdgpu_dpm_print_power_state(adev, adev->pm.dpm.current_ps);
-		printk("switching to power state:\n");
-		amdgpu_dpm_print_power_state(adev, adev->pm.dpm.requested_ps);
-	}
-
-	/* update whether vce is active */
-	ps->vce_active = adev->pm.dpm.vce_active;
-	if (adev->powerplay.pp_funcs->display_configuration_changed)
-		amdgpu_dpm_display_configuration_changed(adev);
-
-	ret = amdgpu_dpm_pre_set_power_state(adev);
-	if (ret)
-		return;
-
-	if (adev->powerplay.pp_funcs->check_state_equal) {
-		if (0 != amdgpu_dpm_check_state_equal(adev, adev->pm.dpm.current_ps, adev->pm.dpm.requested_ps, &equal))
-			equal = false;
-	}
-
-	if (equal)
-		return;
-
-	amdgpu_dpm_set_power_state(adev);
-	amdgpu_dpm_post_set_power_state(adev);
-
-	adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs;
-	adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count;
-
-	if (adev->powerplay.pp_funcs->force_performance_level) {
-		if (adev->pm.dpm.thermal_active) {
-			enum amd_dpm_forced_level level = adev->pm.dpm.forced_level;
-			/* force low perf level for thermal */
-			amdgpu_dpm_force_performance_level(adev, AMD_DPM_FORCED_LEVEL_LOW);
-			/* save the user's level */
-			adev->pm.dpm.forced_level = level;
-		} else {
-			/* otherwise, user selected level */
-			amdgpu_dpm_force_performance_level(adev, adev->pm.dpm.forced_level);
-		}
-	}
-}
-
-void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
-{
-	int ret = 0;
-
-	if (adev->family == AMDGPU_FAMILY_SI) {
-		mutex_lock(&adev->pm.mutex);
-		if (enable) {
-			adev->pm.dpm.uvd_active = true;
-			adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD;
-		} else {
-			adev->pm.dpm.uvd_active = false;
-		}
-		mutex_unlock(&adev->pm.mutex);
-
-		amdgpu_pm_compute_clocks(adev);
-	} else {
-		ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
-		if (ret)
-			DRM_ERROR("Dpm %s uvd failed, ret = %d. \n",
-				  enable ? "enable" : "disable", ret);
-
-		/* enable/disable Low Memory PState for UVD (4k videos) */
-		if (adev->asic_type == CHIP_STONEY &&
-			adev->uvd.decode_image_width >= WIDTH_4K) {
-			struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-
-			if (hwmgr && hwmgr->hwmgr_func &&
-			    hwmgr->hwmgr_func->update_nbdpm_pstate)
-				hwmgr->hwmgr_func->update_nbdpm_pstate(hwmgr,
-								       !enable,
-								       true);
-		}
-	}
-}
-
-void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
-{
-	int ret = 0;
-
-	if (adev->family == AMDGPU_FAMILY_SI) {
-		mutex_lock(&adev->pm.mutex);
-		if (enable) {
-			adev->pm.dpm.vce_active = true;
-			/* XXX select vce level based on ring/task */
-			adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL;
-		} else {
-			adev->pm.dpm.vce_active = false;
-		}
-		mutex_unlock(&adev->pm.mutex);
-
-		amdgpu_pm_compute_clocks(adev);
-	} else {
-		ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
-		if (ret)
-			DRM_ERROR("Dpm %s vce failed, ret = %d. \n",
-				  enable ? "enable" : "disable", ret);
-	}
-}
-
-void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
-{
-	int i;
-
-	if (adev->powerplay.pp_funcs->print_power_state == NULL)
-		return;
-
-	for (i = 0; i < adev->pm.dpm.num_ps; i++)
-		amdgpu_dpm_print_power_state(adev, &adev->pm.dpm.ps[i]);
-
-}
-
-void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable)
-{
-	int ret = 0;
-
-	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_JPEG, !enable);
-	if (ret)
-		DRM_ERROR("Dpm %s jpeg failed, ret = %d. \n",
-			  enable ? "enable" : "disable", ret);
-}
-
-int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version)
-{
-	int r;
-
-	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->load_firmware) {
-		r = adev->powerplay.pp_funcs->load_firmware(adev->powerplay.pp_handle);
-		if (r) {
-			pr_err("smu firmware loading failed\n");
-			return r;
-		}
-		*smu_version = adev->pm.fw_version;
-	}
-	return 0;
-}
-
 int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 {
 	int ret;
@@ -3713,55 +3447,6 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 	amdgpu_device_attr_remove_groups(adev, &adev->pm.pm_attr_list);
 }
 
-void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
-{
-	int i = 0;
-
-	if (!adev->pm.dpm_enabled)
-		return;
-
-	if (adev->mode_info.num_crtc)
-		amdgpu_display_bandwidth_update(adev);
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		if (ring && ring->sched.ready)
-			amdgpu_fence_wait_empty(ring);
-	}
-
-	if (is_support_sw_smu(adev)) {
-		struct smu_dpm_context *smu_dpm = &adev->smu.smu_dpm;
-		smu_handle_task(&adev->smu,
-				smu_dpm->dpm_level,
-				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE,
-				true);
-	} else {
-		if (adev->powerplay.pp_funcs->dispatch_tasks) {
-			if (!amdgpu_device_has_dc_support(adev)) {
-				mutex_lock(&adev->pm.mutex);
-				amdgpu_dpm_get_active_displays(adev);
-				adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
-				adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
-				adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
-				/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
-				if (adev->pm.pm_display_cfg.vrefresh > 120)
-					adev->pm.pm_display_cfg.min_vblank_time = 0;
-				if (adev->powerplay.pp_funcs->display_configuration_change)
-					adev->powerplay.pp_funcs->display_configuration_change(
-									adev->powerplay.pp_handle,
-									&adev->pm.pm_display_cfg);
-				mutex_unlock(&adev->pm.mutex);
-			}
-			amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_DISPLAY_CONFIG_CHANGE, NULL);
-		} else {
-			mutex_lock(&adev->pm.mutex);
-			amdgpu_dpm_get_active_displays(adev);
-			amdgpu_dpm_change_power_state_locked(adev);
-			mutex_unlock(&adev->pm.mutex);
-		}
-	}
-}
-
 /*
  * Debugfs info
  */
@@ -3869,11 +3554,11 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	u32 flags = 0;
 	int r;
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EPERM;
 
 	r = pm_runtime_get_sync(dev->dev);
@@ -3882,11 +3567,6 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 		return r;
 	}
 
-	amdgpu_device_ip_get_clockgating_state(adev, &flags);
-	seq_printf(m, "Clock Gating Flags Mask: 0x%x\n", flags);
-	amdgpu_parse_cg_state(m, flags);
-	seq_printf(m, "\n");
-
 	if (!adev->pm.dpm_enabled) {
 		seq_printf(m, "dpm not enabled\n");
 		pm_runtime_mark_last_busy(dev->dev);
@@ -3906,7 +3586,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	} else {
 		r = amdgpu_debugfs_pm_info_pp(m, adev);
 	}
+	if (r)
+		goto out;
+
+	amdgpu_device_ip_get_clockgating_state(adev, &flags);
+
+	seq_printf(m, "Clock Gating Flags Mask: 0x%x\n", flags);
+	amdgpu_parse_cg_state(m, flags);
+	seq_printf(m, "\n");
 
+out:
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h b/drivers/gpu/drm/amd/pm/inc/amd_powerplay.h
index fe3665965416..fe3665965416 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
+++ b/drivers/gpu/drm/amd/pm/inc/amd_powerplay.h
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index aa27fe65cdfa..dff4a5f99bb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -341,10 +341,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->reset_power_profile_state(\
 			(adev)->powerplay.pp_handle, request))
 
-#define amdgpu_dpm_set_clockgating_by_smu(adev, msg_id) \
-		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
-			(adev)->powerplay.pp_handle, msg_id))
-
 #define amdgpu_dpm_get_power_profile_mode(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_power_profile_mode(\
 			(adev)->powerplay.pp_handle, buf))
@@ -357,10 +353,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
-#define amdgpu_dpm_enable_mgpu_fan_boost(adev) \
-		((adev)->powerplay.pp_funcs->enable_mgpu_fan_boost(\
-			(adev)->powerplay.pp_handle))
-
 #define amdgpu_dpm_get_ppfeature_status(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_ppfeature_status(\
 			(adev)->powerplay.pp_handle, (buf)))
@@ -369,6 +361,9 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_ppfeature_status(\
 			(adev)->powerplay.pp_handle, (ppfeatures)))
 
+#define amdgpu_dpm_get_gpu_metrics(adev, table) \
+		((adev)->powerplay.pp_funcs->get_gpu_metrics((adev)->powerplay.pp_handle, table))
+
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
@@ -545,4 +540,26 @@ int amdgpu_dpm_set_df_cstate(struct amdgpu_device *adev,
 
 int amdgpu_dpm_allow_xgmi_power_down(struct amdgpu_device *adev, bool en);
 
+int amdgpu_dpm_enable_mgpu_fan_boost(struct amdgpu_device *adev);
+
+int amdgpu_dpm_set_clockgating_by_smu(struct amdgpu_device *adev,
+				      uint32_t msg_id);
+
+int amdgpu_dpm_smu_i2c_bus_access(struct amdgpu_device *adev,
+				  bool acquire);
+
+void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev);
+
+int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors sensor,
+			   void *data, uint32_t *size);
+
+void amdgpu_dpm_thermal_work_handler(struct work_struct *work);
+
+void amdgpu_pm_compute_clocks(struct amdgpu_device *adev);
+void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable);
+void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable);
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable);
+void amdgpu_pm_print_power_states(struct amdgpu_device *adev);
+int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_pm.h
index d9ae2b49a402..45a22e101d15 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_pm.h
@@ -79,18 +79,10 @@ struct amdgpu_device_attr_entry {
 			     amdgpu_get_##_name, NULL,			\
 			     _flags, ##__VA_ARGS__)
 
-void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev);
 int amdgpu_pm_sysfs_init(struct amdgpu_device *adev);
 int amdgpu_pm_virt_sysfs_init(struct amdgpu_device *adev);
 void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev);
 void amdgpu_pm_virt_sysfs_fini(struct amdgpu_device *adev);
-void amdgpu_pm_print_power_states(struct amdgpu_device *adev);
-int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version);
-void amdgpu_pm_compute_clocks(struct amdgpu_device *adev);
-void amdgpu_dpm_thermal_work_handler(struct work_struct *work);
-void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable);
-void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable);
-void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable);
 
 int amdgpu_debugfs_pm_init(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 074458eb5407..d22a759b6b43 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -274,6 +274,9 @@ struct smu_table_context
 
 	void				*overdrive_table;
 	void                            *boot_overdrive_table;
+
+	uint32_t			gpu_metrics_table_size;
+	void				*gpu_metrics_table;
 };
 
 struct smu_dpm_context {
@@ -448,6 +451,10 @@ struct smu_context
 	bool dc_controlled_by_gpio;
 
 	struct work_struct throttling_logging_work;
+	atomic64_t throttle_int_counter;
+
+	unsigned fan_max_rpm;
+	unsigned manual_fan_speed_rpm;
 };
 
 struct i2c_adapter;
@@ -491,7 +498,6 @@ struct pptable_funcs {
 	int (*notify_smc_display_config)(struct smu_context *smu);
 	int (*set_cpu_power_state)(struct smu_context *smu);
 	bool (*is_dpm_running)(struct smu_context *smu);
-	int (*get_fan_speed_percent)(struct smu_context *smu, uint32_t *speed);
 	int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed);
 	int (*set_watermarks_table)(struct smu_context *smu,
 				    struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
@@ -567,7 +573,6 @@ struct pptable_funcs {
 	int (*conv_power_profile_to_pplib_workload)(int power_profile);
 	uint32_t (*get_fan_control_mode)(struct smu_context *smu);
 	int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
-	int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed);
 	int (*set_fan_speed_rpm)(struct smu_context *smu, uint32_t speed);
 	int (*set_xgmi_pstate)(struct smu_context *smu, uint32_t pstate);
 	int (*gfx_off_control)(struct smu_context *smu, bool enable);
@@ -590,6 +595,11 @@ struct pptable_funcs {
 	void (*log_thermal_throttling_event)(struct smu_context *smu);
 	size_t (*get_pp_feature_mask)(struct smu_context *smu, char *buf);
 	int (*set_pp_feature_mask)(struct smu_context *smu, uint64_t new_mask);
+	ssize_t (*get_gpu_metrics)(struct smu_context *smu, void **table);
+	int (*enable_mgpu_fan_boost)(struct smu_context *smu);
+	int (*gfx_ulv_control)(struct smu_context *smu, bool enablement);
+	int (*deep_sleep_control)(struct smu_context *smu, bool enablement);
+	int (*get_fan_parameters)(struct smu_context *smu);
 };
 
 typedef enum {
@@ -792,5 +802,9 @@ int smu_get_dpm_clock_table(struct smu_context *smu,
 
 int smu_get_status_gfxoff(struct amdgpu_device *adev, uint32_t *value);
 
+ssize_t smu_sys_get_gpu_metrics(struct smu_context *smu, void **table);
+
+int smu_enable_mgpu_fan_boost(struct smu_context *smu);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/arcturus_ppsmc.h
index 79afb132164e..79afb132164e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/arcturus_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/cz_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/cz_ppsmc.h
index 9b698780aed8..9b698780aed8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/cz_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/cz_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/fiji_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/fiji_ppsmc.h
index 7ae494569a60..7ae494569a60 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/fiji_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/fiji_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/pm/inc/hardwaremanager.h
index 6e0be6027705..6e0be6027705 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/pm/inc/hardwaremanager.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
index 15ed6cbdf366..1b3529efc91e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -359,6 +359,7 @@ struct pp_hwmgr_func {
 	int (*set_xgmi_pstate)(struct pp_hwmgr *hwmgr, uint32_t pstate);
 	int (*disable_power_features_for_compute_performance)(struct pp_hwmgr *hwmgr,
 					bool disable);
+	ssize_t (*get_gpu_metrics)(struct pp_hwmgr *hwmgr, void **table);
 };
 
 struct pp_table_func {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_pwrvirus.h b/drivers/gpu/drm/amd/pm/inc/polaris10_pwrvirus.h
index 6a53b7e74ccd..6a53b7e74ccd 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_pwrvirus.h
+++ b/drivers/gpu/drm/amd/pm/inc/polaris10_pwrvirus.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/inc/power_state.h
index a5f2227a3971..a5f2227a3971 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/power_state.h
+++ b/drivers/gpu/drm/amd/pm/inc/power_state.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h b/drivers/gpu/drm/amd/pm/inc/pp_debug.h
index cea65093b6ad..cea65093b6ad 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h
+++ b/drivers/gpu/drm/amd/pm/inc/pp_debug.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_endian.h b/drivers/gpu/drm/amd/pm/inc/pp_endian.h
index f49d1963fe85..f49d1963fe85 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_endian.h
+++ b/drivers/gpu/drm/amd/pm/inc/pp_endian.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_thermal.h b/drivers/gpu/drm/amd/pm/inc/pp_thermal.h
index 3e30768f9e1c..3e30768f9e1c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_thermal.h
+++ b/drivers/gpu/drm/amd/pm/inc/pp_thermal.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/ppinterrupt.h b/drivers/gpu/drm/amd/pm/inc/ppinterrupt.h
index c067e0925b6b..c067e0925b6b 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/ppinterrupt.h
+++ b/drivers/gpu/drm/amd/pm/inc/ppinterrupt.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/rv_ppsmc.h
index df4677da736c..df4677da736c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/rv_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu10.h b/drivers/gpu/drm/amd/pm/inc/smu10.h
index b96520528240..b96520528240 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu10.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu10.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu10_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h
index dea8fe93da63..dea8fe93da63 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu10_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if.h
index fdc6b7a57bc9..fdc6b7a57bc9 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_arcturus.h
index 43d43d6addc0..43d43d6addc0 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_arcturus.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_navi10.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_navi10.h
index 4b2da98afcd2..246d3951a78a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_navi10.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_navi10.h
@@ -885,6 +885,45 @@ typedef struct {
 } SmuMetrics_t;
 
 typedef struct {
+  uint16_t CurrClock[PPCLK_COUNT];
+  uint16_t AverageGfxclkFrequency;
+  uint16_t AverageSocclkFrequency;
+  uint16_t AverageUclkFrequency  ;
+  uint16_t AverageGfxActivity    ;
+  uint16_t AverageUclkActivity   ;
+  uint8_t  CurrSocVoltageOffset  ;
+  uint8_t  CurrGfxVoltageOffset  ;
+  uint8_t  CurrMemVidOffset      ;
+  uint8_t  Padding8              ;
+  uint16_t AverageSocketPower    ;
+  uint16_t TemperatureEdge       ;
+  uint16_t TemperatureHotspot    ;
+  uint16_t TemperatureMem        ;
+  uint16_t TemperatureVrGfx      ;
+  uint16_t TemperatureVrMem0     ;
+  uint16_t TemperatureVrMem1     ;
+  uint16_t TemperatureVrSoc      ;
+  uint16_t TemperatureLiquid0    ;
+  uint16_t TemperatureLiquid1    ;
+  uint16_t TemperaturePlx        ;
+  uint16_t Padding16             ;
+  uint32_t ThrottlerStatus       ;
+
+  uint8_t  LinkDpmLevel;
+  uint8_t  Padding8_2;
+  uint16_t CurrFanSpeed;
+
+  uint32_t EnergyAccumulator;
+  uint16_t AverageVclkFrequency  ;
+  uint16_t AverageDclkFrequency  ;
+  uint16_t VcnActivityPercentage ;
+  uint16_t padding16_2;
+
+  // Padding - ignore
+  uint32_t     MmHubPadding[8]; // SMU internal use
+} SmuMetrics_NV12_t;
+
+typedef struct {
   uint16_t MinClock; // This is either DCEFCLK or SOCCLK (in MHz)
   uint16_t MaxClock; // This is either DCEFCLK or SOCCLK (in MHz)
   uint16_t MinUclk;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
index aa2708fccb6d..5ef9c92f57c4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if 
 // any structure is changed in this file
-#define SMU11_DRIVER_IF_VERSION 0x34
+#define SMU11_DRIVER_IF_VERSION 0x35
 
 #define PPTABLE_Sienna_Cichlid_SMU_VERSION 5
 
@@ -127,7 +127,7 @@
 #define FEATURE_DF_CSTATE_BIT           45
 #define FEATURE_2_STEP_PSTATE_BIT       46
 #define FEATURE_SMNCLK_DPM_BIT          47
-#define FEATURE_SPARE_48_BIT            48
+#define FEATURE_PERLINK_GMIDOWN_BIT     48
 #define FEATURE_GFX_EDC_BIT             49
 #define FEATURE_SPARE_50_BIT            50
 #define FEATURE_SPARE_51_BIT            51
@@ -169,7 +169,7 @@ typedef enum {
 #define DPM_OVERRIDE_DISABLE_DFLL_PLL_SHUTDOWN       0x00000200
 #define DPM_OVERRIDE_DISABLE_MEMORY_TEMPERATURE_READ 0x00000400
 #define DPM_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCEFCLK   0x00000800
-#define DPM_OVERRIDE_DISABLE_FAST_FCLK_TIMER         0x00001000
+#define DPM_OVERRIDE_ENABLE_FAST_FCLK_TIMER          0x00001000
 #define DPM_OVERRIDE_DISABLE_VCN_PG                  0x00002000
 #define DPM_OVERRIDE_DISABLE_FMAX_VMAX               0x00004000
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu12_driver_if.h
index e9315eb5b48e..e9315eb5b48e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu12_driver_if.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7.h b/drivers/gpu/drm/amd/pm/inc/smu7.h
index e14072d45918..e14072d45918 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu7.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu7.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu71.h b/drivers/gpu/drm/amd/pm/inc/smu71.h
index 71c9b2d28640..71c9b2d28640 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu71.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu71.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu71_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu71_discrete.h
index c0e3936d5c2e..c0e3936d5c2e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu71_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu71_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu72.h b/drivers/gpu/drm/amd/pm/inc/smu72.h
index 9ad1cefff79f..9ad1cefff79f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu72.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu72.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu72_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu72_discrete.h
index 2aefbb85f620..2aefbb85f620 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu72_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu72_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu73.h b/drivers/gpu/drm/amd/pm/inc/smu73.h
index c6b12a4c00db..c6b12a4c00db 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu73.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu73.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu73_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu73_discrete.h
index 5916be08a7fe..5916be08a7fe 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu73_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu73_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/pm/inc/smu74.h
index fd10a9fa843d..fd10a9fa843d 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu74.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu74_discrete.h
index 899d6d8108c2..899d6d8108c2 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu74_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu75.h b/drivers/gpu/drm/amd/pm/inc/smu75.h
index 771523001533..771523001533 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu75.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu75.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu75_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu75_discrete.h
index b64e58a22ddf..b64e58a22ddf 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu75_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu75_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_common.h b/drivers/gpu/drm/amd/pm/inc/smu7_common.h
index 94bf7b649c20..94bf7b649c20 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu7_common.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu7_common.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_discrete.h b/drivers/gpu/drm/amd/pm/inc/smu7_discrete.h
index ee876745dd12..ee876745dd12 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu7_discrete.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu7_discrete.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_fusion.h b/drivers/gpu/drm/amd/pm/inc/smu7_fusion.h
index 78ada9ffd508..78ada9ffd508 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu7_fusion.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu7_fusion.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu7_ppsmc.h
index 6e19f4c7cf8f..6e19f4c7cf8f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu7_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu8.h b/drivers/gpu/drm/amd/pm/inc/smu8.h
index d758d07b6a31..d758d07b6a31 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu8.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu8.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu8_fusion.h b/drivers/gpu/drm/amd/pm/inc/smu8_fusion.h
index 0c37c94e9414..0c37c94e9414 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu8_fusion.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu8_fusion.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu9.h b/drivers/gpu/drm/amd/pm/inc/smu9.h
index 70ac4d477be2..70ac4d477be2 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu9.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu9.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu9_driver_if.h
index 2818c98ff5ca..2818c98ff5ca 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu9_driver_if.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 7b585e205a5a..7b585e205a5a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h b/drivers/gpu/drm/amd/pm/inc/smu_ucode_xfer_cz.h
index eb0f79f9c876..eb0f79f9c876 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_ucode_xfer_cz.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_vi.h b/drivers/gpu/drm/amd/pm/inc/smu_ucode_xfer_vi.h
index 880152c0f775..880152c0f775 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_vi.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_ucode_xfer_vi.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index 6a42331aba8a..1f9575a4dfe7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -28,10 +28,10 @@
 #define SMU11_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU11_DRIVER_IF_VERSION_ARCT 0x17
 #define SMU11_DRIVER_IF_VERSION_NV10 0x36
-#define SMU11_DRIVER_IF_VERSION_NV12 0x33
+#define SMU11_DRIVER_IF_VERSION_NV12 0x36
 #define SMU11_DRIVER_IF_VERSION_NV14 0x36
-#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x34
-#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x3
+#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x35
+#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x4
 
 /* MP Apertures */
 #define MP0_Public			0x03800000
@@ -200,12 +200,12 @@ int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode);
 
-int
-smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
-
 int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 				       uint32_t speed);
 
+int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu,
+				uint32_t *speed);
+
 int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
 				     uint32_t pstate);
 
@@ -264,5 +264,21 @@ int smu_v11_0_get_dpm_level_range(struct smu_context *smu,
 				  uint32_t *min_value,
 				  uint32_t *max_value);
 
+int smu_v11_0_get_current_pcie_link_width_level(struct smu_context *smu);
+
+int smu_v11_0_get_current_pcie_link_width(struct smu_context *smu);
+
+int smu_v11_0_get_current_pcie_link_speed_level(struct smu_context *smu);
+
+int smu_v11_0_get_current_pcie_link_speed(struct smu_context *smu);
+
+void smu_v11_0_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics);
+
+int smu_v11_0_gfx_ulv_control(struct smu_context *smu,
+			      bool enablement);
+
+int smu_v11_0_deep_sleep_control(struct smu_context *smu,
+				 bool enablement);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_7_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_7_ppsmc.h
index 35dd6072cc45..35dd6072cc45 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_7_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_7_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_7_pptable.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_7_pptable.h
index 247c6e9632ba..247c6e9632ba 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_7_pptable.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_7_pptable.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h
index 406bfd187ce8..fa0174dc7e0e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h
@@ -123,7 +123,9 @@
 #define PPSMC_MSG_DALDisableDummyPstateChange    0x49
 #define PPSMC_MSG_DALEnableDummyPstateChange     0x4A
 
-#define PPSMC_Message_Count                      0x4B
+#define PPSMC_MSG_SetMGpuFanBoostLimitRpm        0x4C
+
+#define PPSMC_Message_Count                      0x4D
 
 typedef uint32_t PPSMC_Result;
 typedef uint32_t PPSMC_Msg;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_pptable.h
index 7a63cf8e85ed..7a63cf8e85ed 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_pptable.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h
index 02de3b6199e5..fa2e8cb07967 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h
@@ -60,5 +60,7 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_
 
 int smu_v12_0_set_driver_table_location(struct smu_context *smu);
 
+void smu_v12_0_init_gpu_metrics_v2_0(struct gpu_metrics_v2_0 *gpu_metrics);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v12_0_ppsmc.h
index 9ac9f3bd3664..9ac9f3bd3664 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v12_0_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/pm/inc/smumgr.h
index ad100b533d04..ad100b533d04 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/tonga_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/tonga_ppsmc.h
index 63631296d751..63631296d751 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/tonga_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/tonga_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/vega10_ppsmc.h
index 715b5a168831..715b5a168831 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/vega10_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/pm/inc/vega12/smu9_driver_if.h
index b6ffd08784e7..b6ffd08784e7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/vega12/smu9_driver_if.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/vega12_ppsmc.h
index f985c78d746a..f985c78d746a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/vega12_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/vega20_ppsmc.h
index 0c66f0fe1aaf..0c66f0fe1aaf 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/vega20_ppsmc.h
diff --git a/drivers/gpu/drm/amd/powerplay/Makefile b/drivers/gpu/drm/amd/pm/powerplay/Makefile
index e9c48f99f71b..0fb114adc79f 100644
--- a/drivers/gpu/drm/amd/powerplay/Makefile
+++ b/drivers/gpu/drm/amd/pm/powerplay/Makefile
@@ -1,5 +1,5 @@
 #
-# Copyright 2017 Advanced Micro Devices, Inc.
+# Copyright 2020 Advanced Micro Devices, Inc.
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the "Software"),
@@ -20,25 +20,20 @@
 # OTHER DEALINGS IN THE SOFTWARE.
 #
 
-subdir-ccflags-y += \
-		-I$(FULL_AMD_PATH)/powerplay/inc/  \
-		-I$(FULL_AMD_PATH)/include/asic_reg  \
-		-I$(FULL_AMD_PATH)/include  \
-		-I$(FULL_AMD_PATH)/powerplay/smumgr\
-		-I$(FULL_AMD_PATH)/powerplay/hwmgr
-
-AMD_PP_PATH = ../powerplay
+AMD_PP_PATH = ../pm/powerplay
 
 PP_LIBS = smumgr hwmgr
 
-AMD_POWERPLAY = $(addsuffix /Makefile,$(addprefix $(FULL_AMD_PATH)/powerplay/,$(PP_LIBS)))
+AMD_POWERPLAY = $(addsuffix /Makefile,$(addprefix $(FULL_AMD_PATH)/pm/powerplay/,$(PP_LIBS)))
 
 include $(AMD_POWERPLAY)
 
-POWER_MGR = amd_powerplay.o amdgpu_smu.o smu_v11_0.o \
-	    smu_v12_0.o arcturus_ppt.o navi10_ppt.o \
-	    renoir_ppt.o sienna_cichlid_ppt.o smu_cmn.o
+POWER_MGR-y = amd_powerplay.o
+
+POWER_MGR-$(CONFIG_DRM_AMDGPU_CIK)+= kv_dpm.o kv_smc.o
+
+POWER_MGR-$(CONFIG_DRM_AMDGPU_SI)+= si_dpm.o si_smc.o
 
-AMD_PP_POWER = $(addprefix $(AMD_PP_PATH)/,$(POWER_MGR))
+AMD_PP_POWER = $(addprefix $(AMD_PP_PATH)/,$(POWER_MGR-y))
 
 AMD_POWERPLAY_FILES += $(AMD_PP_POWER)
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 7e6dcdf7df73..a6321f2063c1 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -1598,6 +1598,24 @@ static int pp_set_xgmi_pstate(void *handle, uint32_t pstate)
 	return 0;
 }
 
+static ssize_t pp_get_gpu_metrics(void *handle, void **table)
+{
+	struct pp_hwmgr *hwmgr = handle;
+	ssize_t size;
+
+	if (!hwmgr)
+		return -EINVAL;
+
+	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_gpu_metrics)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&hwmgr->smu_lock);
+	size = hwmgr->hwmgr_func->get_gpu_metrics(hwmgr, table);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return size;
+}
+
 static const struct amd_pm_funcs pp_dpm_funcs = {
 	.load_firmware = pp_dpm_load_fw,
 	.wait_for_fw_loading_complete = pp_dpm_fw_loading_complete,
@@ -1658,4 +1676,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.smu_i2c_bus_access = pp_smu_i2c_bus_access,
 	.set_df_cstate = pp_set_df_cstate,
 	.set_xgmi_pstate = pp_set_xgmi_pstate,
+	.get_gpu_metrics = pp_get_gpu_metrics,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_dpm.h b/drivers/gpu/drm/amd/pm/powerplay/cik_dpm.h
index 2fcc4b60153c..2fcc4b60153c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_dpm.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/cik_dpm.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/Makefile
index 2773966ae434..2773966ae434 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/Makefile
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
index 3be40114e63d..3be40114e63d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.h
index 17041f187020..17041f187020 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/common_baco.c
index 1c73776bd606..1c73776bd606 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/common_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/common_baco.h
index 8393eb62706d..8393eb62706d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/common_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/fiji_baco.c
index c0368f2dfb21..c0368f2dfb21 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/fiji_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/fiji_baco.h
index 47f402900bdb..47f402900bdb 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/fiji_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
index 9454ab50f9a1..1f9b9facdf1f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
@@ -271,7 +271,10 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 
 bool phm_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmgr)
 {
-	PHM_FUNC_CHECK(hwmgr);
+	if (hwmgr == NULL ||
+	    hwmgr->hwmgr_func == NULL)
+		return false;
+
 	if (hwmgr->pp_one_vf)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c
index f48fdc7f0382..f48fdc7f0382 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr_ppt.h
index c0193e09d58a..c0193e09d58a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr_ppt.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/polaris_baco.c
index 8f8e296f2fe9..8f8e296f2fe9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/polaris_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/polaris_baco.h
index 87a5fa0a157a..87a5fa0a157a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/polaris_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_overdriver.c
index 8de384bf9a8f..8de384bf9a8f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_overdriver.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_overdriver.h
index 4112a9398163..4112a9398163 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_overdriver.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_overdriver.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
index 31a32a79cfc2..31a32a79cfc2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.h
index b62d55f1f289..b62d55f1f289 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
index 01dc46dc9c8a..01dc46dc9c8a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.h
index 3ee54f182943..76ed2e413594 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.h
@@ -26,15 +26,6 @@
 
 #include "hwmgr.h"
 
-#define MEM_TYPE_GDDR5  0x50
-#define MEM_TYPE_GDDR4  0x40
-#define MEM_TYPE_GDDR3  0x30
-#define MEM_TYPE_DDR2   0x20
-#define MEM_TYPE_GDDR1  0x10
-#define MEM_TYPE_DDR3   0xb0
-#define MEM_TYPE_MASK   0xF0
-
-
 /* As returned from PowerConnectorDetectionTable. */
 #define PP_ATOM_POWER_BUDGET_DISABLE_OVERDRIVE  0x80
 #define PP_ATOM_POWER_BUDGET_SHOW_WARNING       0x40
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c
index 615cf2c09e54..615cf2c09e54 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h
index b7e2651b570b..b7e2651b570b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h
index 8f50a038396c..8f50a038396c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pppcielanes.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pppcielanes.c
index 186496a34cbe..186496a34cbe 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pppcielanes.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pppcielanes.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pppcielanes.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pppcielanes.h
index 70b163b35570..70b163b35570 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pppcielanes.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pppcielanes.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pptable_v1_0.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h
index 1e870f58dd12..1e870f58dd12 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pptable_v1_0.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
index b760f95e7fa7..b760f95e7fa7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.h
index b9710abdff01..b9710abdff01 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c
index 719597c5d27d..719597c5d27d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.h
index baddaa75693b..baddaa75693b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index c9cfe90a2947..9ee8cf8267c8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -204,8 +204,7 @@ static int smu10_set_min_deep_sleep_dcefclk(struct pp_hwmgr *hwmgr, uint32_t clo
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->need_min_deep_sleep_dcefclk &&
-		smu10_data->deep_sleep_dcefclk != clock) {
+	if (clock && smu10_data->deep_sleep_dcefclk != clock) {
 		smu10_data->deep_sleep_dcefclk = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetMinDeepSleepDcefclk,
@@ -219,8 +218,7 @@ static int smu10_set_hard_min_dcefclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t c
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->dcf_actual_hard_min_freq &&
-		smu10_data->dcf_actual_hard_min_freq != clock) {
+	if (clock && smu10_data->dcf_actual_hard_min_freq != clock) {
 		smu10_data->dcf_actual_hard_min_freq = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetHardMinDcefclkByFreq,
@@ -234,8 +232,7 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->f_actual_hard_min_freq &&
-		smu10_data->f_actual_hard_min_freq != clock) {
+	if (clock && smu10_data->f_actual_hard_min_freq != clock) {
 		smu10_data->f_actual_hard_min_freq = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetHardMinFclkByFreq,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
index 0f969de10fab..0f969de10fab 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_inc.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_inc.h
index edb68e302f6f..edb68e302f6f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_inc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_inc.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_baco.c
index 044cda005aed..044cda005aed 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_baco.h
index be0d98abb536..be0d98abb536 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c
index f2bda3bcbbde..f2bda3bcbbde 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h
index fc8f8a6acc72..fc8f8a6acc72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_dyn_defaults.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_dyn_defaults.h
index 3477d4dfff70..3477d4dfff70 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_dyn_defaults.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_dyn_defaults.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index ffe05b7cc1f0..4a3b64aa21ce 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3581,7 +3581,8 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	case AMDGPU_PP_SENSOR_GPU_POWER:
 		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
-		if ((data->vr_config & 0xff) == 0x2)
+		if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
+		    (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))
 			val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device,
 					CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID);
 		else
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h
index 69d361f8dfca..69d361f8dfca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_powertune.c
index 5d4971576111..5d4971576111 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_powertune.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_powertune.h
index 22f86b6bf1be..22f86b6bf1be 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_powertune.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
index 0b30f73649a8..0b30f73649a8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h
index 42c1ba0fad78..42c1ba0fad78 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
index 35ed47ebaf09..35ed47ebaf09 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.h
index 05a06083e1b8..05a06083e1b8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu9_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu9_baco.c
index de0a37f7c632..de0a37f7c632 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu9_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu9_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu9_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu9_baco.h
index 84e90f801ac3..84e90f801ac3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu9_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu9_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index 60b5ca974356..60b5ca974356 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
index ad33983a8064..ad33983a8064 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/tonga_baco.c
index ea743bea8e29..ea743bea8e29 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/tonga_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/tonga_baco.h
index 5dc16cc8a295..5dc16cc8a295 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/tonga_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_baco.c
index 46bb16c29cf6..46bb16c29cf6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_baco.h
index 96d793f026a5..96d793f026a5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index c378a000c934..c378a000c934 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.h
index f752b4ad0c8a..f752b4ad0c8a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_inc.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_inc.h
index faf7ac044348..faf7ac044348 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_inc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_inc.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c
index 9757d47dd6b8..9757d47dd6b8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.h
index b95771ab89cd..b95771ab89cd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_pptable.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h
index c934e9612c1b..c934e9612c1b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_pptable.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_processpptables.c
index f29af5ca0aa0..f29af5ca0aa0 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_processpptables.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_processpptables.h
index da5fbec9b0cd..da5fbec9b0cd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_processpptables.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
index 468bdd6f6697..952cd3d7240e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
@@ -363,17 +363,29 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v2_information *pp_table_info =
+		(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
+	/*
+	 * As a common sense, usSoftwareShutdownTemp should be bigger
+	 * than ThotspotLimit. For any invalid usSoftwareShutdownTemp,
+	 * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP
+	 * to avoid false alarms.
+	 */
+	if ((tdp_table->usSoftwareShutdownTemp >
+	     range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) {
+		if (high > tdp_table->usSoftwareShutdownTemp)
+			high = tdp_table->usSoftwareShutdownTemp;
+	}
 
 	if (low > high)
 		return -EINVAL;
@@ -382,8 +394,8 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h
index 4a0ede7c1f07..4a0ede7c1f07 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_baco.c
index bc53cce4f32d..bc53cce4f32d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_baco.h
index 57b72e5a95ae..57b72e5a95ae 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index a678a67f1c0d..f0680dd58508 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -47,6 +47,13 @@
 #include "pp_thermal.h"
 #include "vega12_baco.h"
 
+#define smnPCIE_LC_SPEED_CNTL			0x11140290
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
+#define LINK_WIDTH_MAX				6
+#define LINK_SPEED_MAX				3
+static int link_width[] = {0, 1, 2, 4, 8, 12, 16};
+static int link_speed[] = {25, 50, 80, 160};
 
 static int vega12_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask);
@@ -1255,22 +1262,29 @@ static uint32_t vega12_dpm_get_mclk(struct pp_hwmgr *hwmgr, bool low)
 	return (mem_clk * 100);
 }
 
-static int vega12_get_metrics_table(struct pp_hwmgr *hwmgr, SmuMetrics_t *metrics_table)
+static int vega12_get_metrics_table(struct pp_hwmgr *hwmgr,
+				    SmuMetrics_t *metrics_table,
+				    bool bypass_cache)
 {
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	int ret = 0;
 
-	if (!data->metrics_time || time_after(jiffies, data->metrics_time + HZ / 2)) {
-		ret = smum_smc_table_manager(hwmgr, (uint8_t *)metrics_table,
-				TABLE_SMU_METRICS, true);
+	if (bypass_cache ||
+	    !data->metrics_time ||
+	    time_after(jiffies, data->metrics_time + msecs_to_jiffies(1))) {
+		ret = smum_smc_table_manager(hwmgr,
+					     (uint8_t *)(&data->metrics_table),
+					     TABLE_SMU_METRICS,
+					     true);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
 			return ret;
 		}
-		memcpy(&data->metrics_table, metrics_table, sizeof(SmuMetrics_t));
 		data->metrics_time = jiffies;
-	} else
+	}
+
+	if (metrics_table)
 		memcpy(metrics_table, &data->metrics_table, sizeof(SmuMetrics_t));
 
 	return ret;
@@ -1281,7 +1295,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query)
 	SmuMetrics_t metrics_table;
 	int ret = 0;
 
-	ret = vega12_get_metrics_table(hwmgr, &metrics_table);
+	ret = vega12_get_metrics_table(hwmgr, &metrics_table, false);
 	if (ret)
 		return ret;
 
@@ -1332,7 +1346,7 @@ static int vega12_get_current_activity_percent(
 	SmuMetrics_t metrics_table;
 	int ret = 0;
 
-	ret = vega12_get_metrics_table(hwmgr, &metrics_table);
+	ret = vega12_get_metrics_table(hwmgr, &metrics_table, false);
 	if (ret)
 		return ret;
 
@@ -1380,7 +1394,7 @@ static int vega12_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_HOTSPOT_TEMP:
-		ret = vega12_get_metrics_table(hwmgr, &metrics_table);
+		ret = vega12_get_metrics_table(hwmgr, &metrics_table, false);
 		if (ret)
 			return ret;
 
@@ -1389,7 +1403,7 @@ static int vega12_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_MEM_TEMP:
-		ret = vega12_get_metrics_table(hwmgr, &metrics_table);
+		ret = vega12_get_metrics_table(hwmgr, &metrics_table, false);
 		if (ret)
 			return ret;
 
@@ -2095,6 +2109,46 @@ static int vega12_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe
 	return 0;
 }
 
+static int vega12_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+		PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+}
+
+static int vega12_get_current_pcie_link_width(struct pp_hwmgr *hwmgr)
+{
+	uint32_t width_level;
+
+	width_level = vega12_get_current_pcie_link_width_level(hwmgr);
+	if (width_level > LINK_WIDTH_MAX)
+		width_level = 0;
+
+	return link_width[width_level];
+}
+
+static int vega12_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+		PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+		>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+}
+
+static int vega12_get_current_pcie_link_speed(struct pp_hwmgr *hwmgr)
+{
+	uint32_t speed_level;
+
+	speed_level = vega12_get_current_pcie_link_speed_level(hwmgr);
+	if (speed_level > LINK_SPEED_MAX)
+		speed_level = 0;
+
+	return link_speed[speed_level];
+}
+
 static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, char *buf)
 {
@@ -2682,6 +2736,69 @@ static int vega12_set_mp1_state(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static void vega12_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics)
+{
+	memset(gpu_metrics, 0xFF, sizeof(struct gpu_metrics_v1_0));
+
+	gpu_metrics->common_header.structure_size =
+				sizeof(struct gpu_metrics_v1_0);
+	gpu_metrics->common_header.format_revision = 1;
+	gpu_metrics->common_header.content_revision = 0;
+
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+}
+
+static ssize_t vega12_get_gpu_metrics(struct pp_hwmgr *hwmgr,
+				      void **table)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	struct gpu_metrics_v1_0 *gpu_metrics =
+			&data->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	uint32_t fan_speed_rpm;
+	int ret;
+
+	ret = vega12_get_metrics_table(hwmgr, &metrics, true);
+	if (ret)
+		return ret;
+
+	vega12_init_gpu_metrics_v1_0(gpu_metrics);
+
+	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
+	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
+	gpu_metrics->temperature_mem = metrics.TemperatureHBM;
+	gpu_metrics->temperature_vrgfx = metrics.TemperatureVrGfx;
+	gpu_metrics->temperature_vrmem = metrics.TemperatureVrMem;
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+
+	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 = metrics.CurrClock[PPCLK_VCLK];
+	gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	vega12_fan_ctrl_get_fan_speed_rpm(hwmgr, &fan_speed_rpm);
+	gpu_metrics->current_fan_speed = (uint16_t)fan_speed_rpm;
+
+	gpu_metrics->pcie_link_width =
+			vega12_get_current_pcie_link_width(hwmgr);
+	gpu_metrics->pcie_link_speed =
+			vega12_get_current_pcie_link_speed(hwmgr);
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v1_0);
+}
+
 static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.backend_init = vega12_hwmgr_backend_init,
 	.backend_fini = vega12_hwmgr_backend_fini,
@@ -2739,6 +2856,7 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.get_ppfeature_status = vega12_get_ppfeature_status,
 	.set_ppfeature_status = vega12_set_ppfeature_status,
 	.set_mp1_state = vega12_set_mp1_state,
+	.get_gpu_metrics = vega12_get_gpu_metrics,
 };
 
 int vega12_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.h
index 73875399666a..aa63ae41942d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.h
@@ -399,6 +399,7 @@ struct vega12_hwmgr {
 
 	unsigned long                  metrics_time;
 	SmuMetrics_t                   metrics_table;
+	struct gpu_metrics_v1_0        gpu_metrics_table;
 };
 
 #define VEGA12_DPM2_NEAR_TDP_DEC                      10
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_inc.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_inc.h
index e6d9e84059e1..0d08c57d3bca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_inc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_inc.h
@@ -35,7 +35,6 @@
 #include "asic_reg/gc/gc_9_2_1_sh_mask.h"
 
 #include "asic_reg/nbio/nbio_6_1_offset.h"
-#include "asic_reg/nbio/nbio_6_1_offset.h"
 #include "asic_reg/nbio/nbio_6_1_sh_mask.h"
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_pptable.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_pptable.h
index bf4f5095b80d..bf4f5095b80d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_pptable.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_pptable.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c
index 195d8539fbb4..740e2fc7a034 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c
@@ -252,7 +252,7 @@ static int init_powerplay_table_information(
 	phm_copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_max, powerplay_table->PowerSavingClockMax, ATOM_VEGA12_PPCLOCK_COUNT);
 	phm_copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_min, powerplay_table->PowerSavingClockMin, ATOM_VEGA12_PPCLOCK_COUNT);
 
-	pptable_information->smc_pptable = (PPTable_t *)kmalloc(sizeof(PPTable_t), GFP_KERNEL);
+	pptable_information->smc_pptable = kmalloc(sizeof(PPTable_t), GFP_KERNEL);
 	if (pptable_information->smc_pptable == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.h
index 65652ae65929..65652ae65929 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
index c15b9756025d..7ace439dcde7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
@@ -170,17 +170,18 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	if (high > pptable_information->us_software_shutdown_temp)
+		high = pptable_information->us_software_shutdown_temp;
 
 	if (low > high)
 		return -EINVAL;
@@ -189,8 +190,8 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.h
index 0d8ed039ab12..0d8ed039ab12 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_baco.c
index 2a28c9df15a0..2a28c9df15a0 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_baco.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_baco.h
index f06471e712dc..f06471e712dc 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_baco.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 3b8839641770..da84012b7fd5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -55,6 +55,11 @@
 #define smnPCIE_LC_SPEED_CNTL			0x11140290
 #define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
 
+#define LINK_WIDTH_MAX				6
+#define LINK_SPEED_MAX				3
+static int link_width[] = {0, 1, 2, 4, 8, 12, 16};
+static int link_speed[] = {25, 50, 80, 160};
+
 static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 {
 	struct vega20_hwmgr *data =
@@ -484,7 +489,7 @@ static int vega20_setup_asic_task(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
 	int ret = 0;
-	bool use_baco = (adev->in_gpu_reset &&
+	bool use_baco = (amdgpu_in_reset(adev) &&
 			 (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
 		(adev->in_runpm && amdgpu_asic_supports_baco(adev));
 
@@ -979,10 +984,7 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr)
 {
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
-	uint64_t features_enabled;
-	int i;
-	bool enabled;
-	int ret = 0;
+	int i, ret = 0;
 
 	PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_DisableAllSmuFeatures,
@@ -990,17 +992,8 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr)
 			"[DisableAllSMUFeatures] Failed to disable all smu features!",
 			return ret);
 
-	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
-	PP_ASSERT_WITH_CODE(!ret,
-			"[DisableAllSMUFeatures] Failed to get enabled smc features!",
-			return ret);
-
-	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
-		enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ?
-			true : false;
-		data->smu_features[i].enabled = enabled;
-		data->smu_features[i].supported = enabled;
-	}
+	for (i = 0; i < GNLD_FEATURES_MAX; i++)
+		data->smu_features[i].enabled = 0;
 
 	return 0;
 }
@@ -1652,12 +1645,6 @@ static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr)
 
 	data->uvd_power_gated = true;
 	data->vce_power_gated = true;
-
-	if (data->smu_features[GNLD_DPM_UVD].enabled)
-		data->uvd_power_gated = false;
-
-	if (data->smu_features[GNLD_DPM_VCE].enabled)
-		data->vce_power_gated = false;
 }
 
 static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
@@ -2085,22 +2072,29 @@ static uint32_t vega20_dpm_get_mclk(struct pp_hwmgr *hwmgr, bool low)
 	return (mem_clk * 100);
 }
 
-static int vega20_get_metrics_table(struct pp_hwmgr *hwmgr, SmuMetrics_t *metrics_table)
+static int vega20_get_metrics_table(struct pp_hwmgr *hwmgr,
+				    SmuMetrics_t *metrics_table,
+				    bool bypass_cache)
 {
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
 	int ret = 0;
 
-	if (!data->metrics_time || time_after(jiffies, data->metrics_time + HZ / 2)) {
-		ret = smum_smc_table_manager(hwmgr, (uint8_t *)metrics_table,
-				TABLE_SMU_METRICS, true);
+	if (bypass_cache ||
+	    !data->metrics_time ||
+	    time_after(jiffies, data->metrics_time + msecs_to_jiffies(1))) {
+		ret = smum_smc_table_manager(hwmgr,
+					     (uint8_t *)(&data->metrics_table),
+					     TABLE_SMU_METRICS,
+					     true);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
 			return ret;
 		}
-		memcpy(&data->metrics_table, metrics_table, sizeof(SmuMetrics_t));
 		data->metrics_time = jiffies;
-	} else
+	}
+
+	if (metrics_table)
 		memcpy(metrics_table, &data->metrics_table, sizeof(SmuMetrics_t));
 
 	return ret;
@@ -2112,7 +2106,7 @@ static int vega20_get_gpu_power(struct pp_hwmgr *hwmgr,
 	int ret = 0;
 	SmuMetrics_t metrics_table;
 
-	ret = vega20_get_metrics_table(hwmgr, &metrics_table);
+	ret = vega20_get_metrics_table(hwmgr, &metrics_table, false);
 	if (ret)
 		return ret;
 
@@ -2150,7 +2144,7 @@ static int vega20_get_current_activity_percent(struct pp_hwmgr *hwmgr,
 	int ret = 0;
 	SmuMetrics_t metrics_table;
 
-	ret = vega20_get_metrics_table(hwmgr, &metrics_table);
+	ret = vega20_get_metrics_table(hwmgr, &metrics_table, false);
 	if (ret)
 		return ret;
 
@@ -2180,7 +2174,7 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 
 	switch (idx) {
 	case AMDGPU_PP_SENSOR_GFX_SCLK:
-		ret = vega20_get_metrics_table(hwmgr, &metrics_table);
+		ret = vega20_get_metrics_table(hwmgr, &metrics_table, false);
 		if (ret)
 			return ret;
 
@@ -2205,7 +2199,7 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_EDGE_TEMP:
-		ret = vega20_get_metrics_table(hwmgr, &metrics_table);
+		ret = vega20_get_metrics_table(hwmgr, &metrics_table, false);
 		if (ret)
 			return ret;
 
@@ -2214,7 +2208,7 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_MEM_TEMP:
-		ret = vega20_get_metrics_table(hwmgr, &metrics_table);
+		ret = vega20_get_metrics_table(hwmgr, &metrics_table, false);
 		if (ret)
 			return ret;
 
@@ -3230,10 +3224,11 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 
 static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks)
 {
-	uint64_t features_enabled;
-	uint64_t features_to_enable;
-	uint64_t features_to_disable;
-	int ret = 0;
+	struct vega20_hwmgr *data =
+			(struct vega20_hwmgr *)(hwmgr->backend);
+	uint64_t features_enabled, features_to_enable, features_to_disable;
+	int i, ret = 0;
+	bool enabled;
 
 	if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX))
 		return -EINVAL;
@@ -3262,9 +3257,60 @@ static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe
 			return ret;
 	}
 
+	/* Update the cached feature enablement state */
+	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
+		enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ?
+			true : false;
+		data->smu_features[i].enabled = enabled;
+	}
+
 	return 0;
 }
 
+static int vega20_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+		PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+}
+
+static int vega20_get_current_pcie_link_width(struct pp_hwmgr *hwmgr)
+{
+	uint32_t width_level;
+
+	width_level = vega20_get_current_pcie_link_width_level(hwmgr);
+	if (width_level > LINK_WIDTH_MAX)
+		width_level = 0;
+
+	return link_width[width_level];
+}
+
+static int vega20_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+		PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+		>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+}
+
+static int vega20_get_current_pcie_link_speed(struct pp_hwmgr *hwmgr)
+{
+	uint32_t speed_level;
+
+	speed_level = vega20_get_current_pcie_link_speed_level(hwmgr);
+	if (speed_level > LINK_SPEED_MAX)
+		speed_level = 0;
+
+	return link_speed[speed_level];
+}
+
 static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, char *buf)
 {
@@ -3277,7 +3323,6 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v3_information *pptable_information =
 		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable;
-	struct amdgpu_device *adev = hwmgr->adev;
 	struct pp_clock_levels_with_latency clocks;
 	struct vega20_single_dpm_table *fclk_dpm_table =
 			&(data->dpm_table.fclk_table);
@@ -3371,12 +3416,10 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 
 	case PP_PCIE:
-		current_gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
-			     PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
-			    >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
-		current_lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
-			      PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
-			    >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+		current_gen_speed =
+			vega20_get_current_pcie_link_speed_level(hwmgr);
+		current_lane_width =
+			vega20_get_current_pcie_link_width_level(hwmgr);
 		for (i = 0; i < NUM_LINK_LEVELS; i++) {
 			if (i == 1 && data->pcie_parameters_override) {
 				gen_speed = data->pcie_gen_level1;
@@ -4218,6 +4261,72 @@ static int vega20_set_xgmi_pstate(struct pp_hwmgr *hwmgr,
 	return ret;
 }
 
+static void vega20_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics)
+{
+	memset(gpu_metrics, 0xFF, sizeof(struct gpu_metrics_v1_0));
+
+	gpu_metrics->common_header.structure_size =
+				sizeof(struct gpu_metrics_v1_0);
+	gpu_metrics->common_header.format_revision = 1;
+	gpu_metrics->common_header.content_revision = 0;
+
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+}
+
+static ssize_t vega20_get_gpu_metrics(struct pp_hwmgr *hwmgr,
+				      void **table)
+{
+	struct vega20_hwmgr *data =
+			(struct vega20_hwmgr *)(hwmgr->backend);
+	struct gpu_metrics_v1_0 *gpu_metrics =
+			&data->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	uint32_t fan_speed_rpm;
+	int ret;
+
+	ret = vega20_get_metrics_table(hwmgr, &metrics, true);
+	if (ret)
+		return ret;
+
+	vega20_init_gpu_metrics_v1_0(gpu_metrics);
+
+	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
+	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
+	gpu_metrics->temperature_mem = metrics.TemperatureHBM;
+	gpu_metrics->temperature_vrgfx = metrics.TemperatureVrGfx;
+	gpu_metrics->temperature_vrsoc = metrics.TemperatureVrSoc;
+	gpu_metrics->temperature_vrmem = metrics.TemperatureVrMem0;
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+
+	gpu_metrics->average_socket_power = metrics.AverageSocketPower;
+
+	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 = metrics.CurrClock[PPCLK_VCLK];
+	gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	vega20_fan_ctrl_get_fan_speed_rpm(hwmgr, &fan_speed_rpm);
+	gpu_metrics->current_fan_speed = (uint16_t)fan_speed_rpm;
+
+	gpu_metrics->pcie_link_width =
+			vega20_get_current_pcie_link_width(hwmgr);
+	gpu_metrics->pcie_link_speed =
+			vega20_get_current_pcie_link_speed(hwmgr);
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v1_0);
+}
+
 static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	/* init/fini related */
 	.backend_init = vega20_hwmgr_backend_init,
@@ -4288,6 +4397,7 @@ static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	.smu_i2c_bus_access = vega20_smu_i2c_bus_access,
 	.set_df_cstate = vega20_set_df_cstate,
 	.set_xgmi_pstate = vega20_set_xgmi_pstate,
+	.get_gpu_metrics = vega20_get_gpu_metrics,
 };
 
 int vega20_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.h
index 2c3125f82b24..075c0094da9c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.h
@@ -527,6 +527,7 @@ struct vega20_hwmgr {
 
 	unsigned long                  metrics_time;
 	SmuMetrics_t                   metrics_table;
+	struct gpu_metrics_v1_0        gpu_metrics_table;
 
 	bool                           pcie_parameters_override;
 	uint32_t                       pcie_gen_level1;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_inc.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_inc.h
index 613cb1989b3d..613cb1989b3d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_inc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_inc.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_powertune.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_powertune.c
index d7cc3d2d9e17..d7cc3d2d9e17 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_powertune.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_powertune.c
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_powertune.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_powertune.h
index d68c734c0f4e..d68c734c0f4e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_powertune.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_powertune.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_pptable.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_pptable.h
index 2222e29405c6..2222e29405c6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_pptable.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_pptable.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_processpptables.c
index 7a7f15d0c53a..1f9082539457 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_processpptables.c
@@ -890,14 +890,12 @@ static int init_powerplay_table_information(
 				power_saving_clock_count);
 	}
 
-	pptable_information->smc_pptable = (PPTable_t *)kmalloc(sizeof(PPTable_t), GFP_KERNEL);
+	pptable_information->smc_pptable = kmemdup(&(powerplay_table->smcPPTable),
+						   sizeof(PPTable_t),
+						   GFP_KERNEL);
 	if (pptable_information->smc_pptable == NULL)
 		return -ENOMEM;
 
-	memcpy(pptable_information->smc_pptable,
-			&(powerplay_table->smcPPTable),
-			sizeof(PPTable_t));
-
 
 	result = append_vbios_pptable(hwmgr, (pptable_information->smc_pptable));
 	if (result)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_processpptables.h
index 846c2cb40b35..846c2cb40b35 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_processpptables.h
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
index 7add2f60f49c..364162ddaa9c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
@@ -240,17 +240,18 @@ int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	if (high > pptable_information->us_software_shutdown_temp)
+		high = pptable_information->us_software_shutdown_temp;
 
 	if (low > high)
 		return -EINVAL;
@@ -259,8 +260,8 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h
index 2d1769bbd24e..2d1769bbd24e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.h
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/kv_dpm.c
index 4b3faaccecb9..4b3faaccecb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/kv_dpm.c
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.h b/drivers/gpu/drm/amd/pm/powerplay/kv_dpm.h
index 6df0ed41317c..6df0ed41317c 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/kv_dpm.h
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_smc.c b/drivers/gpu/drm/amd/pm/powerplay/kv_smc.c
index 2d9ab6b8be66..2d9ab6b8be66 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_smc.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/kv_smc.c
diff --git a/drivers/gpu/drm/amd/amdgpu/ppsmc.h b/drivers/gpu/drm/amd/pm/powerplay/ppsmc.h
index 8463245f424f..8463245f424f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/ppsmc.h
diff --git a/drivers/gpu/drm/amd/amdgpu/r600_dpm.h b/drivers/gpu/drm/amd/pm/powerplay/r600_dpm.h
index 055321f61ca7..055321f61ca7 100644
--- a/drivers/gpu/drm/amd/amdgpu/r600_dpm.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/r600_dpm.h
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
index ea914b256ebd..b5986d19dc08 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
@@ -6196,7 +6196,7 @@ static void si_request_link_speed_change_before_state_change(struct amdgpu_devic
 			si_pi->force_pcie_gen = AMDGPU_PCIE_GEN2;
 			if (current_link_speed == AMDGPU_PCIE_GEN2)
 				break;
-			/* fall through */
+			fallthrough;
 		case AMDGPU_PCIE_GEN2:
 			if (amdgpu_acpi_pcie_performance_request(adev, PCIE_PERF_REQ_PECI_GEN2, false) == 0)
 				break;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.h b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.h
index bc0be6818e21..bc0be6818e21 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.h
diff --git a/drivers/gpu/drm/amd/amdgpu/si_smc.c b/drivers/gpu/drm/amd/pm/powerplay/si_smc.c
index 8f994ffa9cd1..8f994ffa9cd1 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_smc.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/si_smc.c
diff --git a/drivers/gpu/drm/amd/amdgpu/sislands_smc.h b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h
index d2930eceaf3c..d2930eceaf3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sislands_smc.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile b/drivers/gpu/drm/amd/pm/powerplay/smumgr/Makefile
index 6c59c61a0d81..6c59c61a0d81 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/Makefile
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
index c18169aa59ce..e4d1f3d66ef4 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
@@ -37,6 +37,7 @@
 #include "cgs_common.h"
 #include "atombios.h"
 #include "pppcielanes.h"
+#include "smu7_smumgr.h"
 
 #include "smu/smu_7_0_1_d.h"
 #include "smu/smu_7_0_1_sh_mask.h"
@@ -2948,6 +2949,7 @@ const struct pp_smumgr_func ci_smu_funcs = {
 	.request_smu_load_specific_fw = NULL,
 	.send_msg_to_smc = ci_send_msg_to_smc,
 	.send_msg_to_smc_with_parameter = ci_send_msg_to_smc_with_parameter,
+	.get_argument = smu7_get_argument,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.get_offsetof = ci_get_offsetof,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.h
index a8282705c569..a8282705c569 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c
index ecb9ee46d6b3..ecb9ee46d6b3 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.h
index 6d3746268ccf..6d3746268ccf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c
index 431ad2fd38df..431ad2fd38df 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.h
index f32c506779c9..f32c506779c9 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c
index c3d2e6dcf62a..c3d2e6dcf62a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.h
index 1ec425df9eda..1ec425df9eda 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu10_smumgr.c
index ea2279bb8cbf..ea2279bb8cbf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu10_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu10_smumgr.h
index 9c2be74a2b2f..9c2be74a2b2f 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu10_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c
index aae25243eb10..aae25243eb10 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.h
index e7303dc8c260..e7303dc8c260 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu8_smumgr.c
index 76d4f12ceedf..76d4f12ceedf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu8_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu8_smumgr.h
index c7b61222d258..c7b61222d258 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu8_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c
index adfbcbe5d113..adfbcbe5d113 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.h
index 1462279ca128..1462279ca128 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
index b6fb48066841..b6fb48066841 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c
index 4bfadb49521b..4bfadb49521b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.h
index d664fedd3d85..d664fedd3d85 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
index 1e222c5d91a4..1e222c5d91a4 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.h
index bad760f22624..bad760f22624 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c
index f54df76537e4..f54df76537e4 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.h
index aeec965ce81f..aeec965ce81f 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega20_smumgr.c
index cf43629d29d2..cf43629d29d2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega20_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega20_smumgr.h
index 62ebbfd6068f..62ebbfd6068f 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega20_smumgr.h
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vegam_smumgr.c
index 0ecc18b55ffb..0ecc18b55ffb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vegam_smumgr.c
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.h b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vegam_smumgr.h
index 2b6558238500..2b6558238500 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vegam_smumgr.h
diff --git a/drivers/gpu/drm/amd/pm/swsmu/Makefile b/drivers/gpu/drm/amd/pm/swsmu/Makefile
new file mode 100644
index 000000000000..6f281990b7b4
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/swsmu/Makefile
@@ -0,0 +1,36 @@
+#
+# Copyright 2020 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+
+AMD_SWSMU_PATH = ../pm/swsmu
+
+SWSMU_LIBS = smu11 smu12
+
+AMD_SWSMU = $(addsuffix /Makefile,$(addprefix $(FULL_AMD_PATH)/pm/swsmu/,$(SWSMU_LIBS)))
+
+include $(AMD_SWSMU)
+
+SWSMU_MGR = amdgpu_smu.o \
+	    smu_cmn.o \
+
+AMD_SWSMU_POWER = $(addprefix $(AMD_SWSMU_PATH)/,$(SWSMU_MGR))
+
+AMD_POWERPLAY_FILES += $(AMD_SWSMU_POWER)
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 0826625573dc..7a55ece1f124 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -504,6 +504,8 @@ static int smu_late_init(void *handle)
 
 	smu_get_unique_id(smu);
 
+	smu_get_fan_parameters(smu);
+
 	smu_handle_task(&adev->smu,
 			smu->smu_dpm.dpm_level,
 			AMD_PP_TASK_COMPLETE_INIT,
@@ -756,6 +758,7 @@ static int smu_sw_init(void *handle)
 	mutex_init(&smu->message_lock);
 
 	INIT_WORK(&smu->throttling_logging_work, smu_throttling_logging_work_fn);
+	atomic64_set(&smu->throttle_int_counter, 0);
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
@@ -1109,7 +1112,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	bool use_baco = !smu->is_apu &&
-		((adev->in_gpu_reset &&
+		((amdgpu_in_reset(adev) &&
 		  (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
 		 ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
 
@@ -1439,6 +1442,8 @@ static int smu_enable_umd_pstate(void *handle,
 			amdgpu_device_ip_set_clockgating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_CG_STATE_UNGATE);
+			smu_gfx_ulv_control(smu, false);
+			smu_deep_sleep_control(smu, false);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
@@ -1446,6 +1451,8 @@ static int smu_enable_umd_pstate(void *handle,
 			if (*level == AMD_DPM_FORCED_LEVEL_PROFILE_EXIT)
 				*level = smu_dpm_ctx->saved_dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = false;
+			smu_deep_sleep_control(smu, true);
+			smu_gfx_ulv_control(smu, true);
 			amdgpu_device_ip_set_clockgating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_CG_STATE_GATE);
@@ -2185,31 +2192,44 @@ int smu_set_fan_control_mode(struct smu_context *smu, int value)
 int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed)
 {
 	int ret = 0;
+	uint32_t percent;
+	uint32_t current_rpm;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->get_fan_speed_percent)
-		ret = smu->ppt_funcs->get_fan_speed_percent(smu, speed);
+	if (smu->ppt_funcs->get_fan_speed_rpm) {
+		ret = smu->ppt_funcs->get_fan_speed_rpm(smu, &current_rpm);
+		if (!ret) {
+			percent = current_rpm * 100 / smu->fan_max_rpm;
+			*speed = percent > 100 ? 100 : percent;
+		}
+	}
 
 	mutex_unlock(&smu->mutex);
 
+
 	return ret;
 }
 
 int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 {
 	int ret = 0;
+	uint32_t rpm;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->set_fan_speed_percent)
-		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
+	if (smu->ppt_funcs->set_fan_speed_rpm) {
+		if (speed > 100)
+			speed = 100;
+		rpm = speed * smu->fan_max_rpm / 100;
+		ret = smu->ppt_funcs->set_fan_speed_rpm(smu, rpm);
+	}
 
 	mutex_unlock(&smu->mutex);
 
@@ -2631,3 +2651,40 @@ int smu_get_dpm_clock_table(struct smu_context *smu,
 
 	return ret;
 }
+
+ssize_t smu_sys_get_gpu_metrics(struct smu_context *smu,
+				void **table)
+{
+	ssize_t size;
+
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+		return -EOPNOTSUPP;
+
+	if (!smu->ppt_funcs->get_gpu_metrics)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&smu->mutex);
+
+	size = smu->ppt_funcs->get_gpu_metrics(smu, table);
+
+	mutex_unlock(&smu->mutex);
+
+	return size;
+}
+
+int smu_enable_mgpu_fan_boost(struct smu_context *smu)
+{
+	int ret = 0;
+
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->enable_mgpu_fan_boost)
+		ret = smu->ppt_funcs->enable_mgpu_fan_boost(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile
new file mode 100644
index 000000000000..f98d97192635
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/Makefile
@@ -0,0 +1,33 @@
+#
+# Copyright 2020 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
+# Makefile for the 'smu manager' sub-component of powerplay.
+# It provides the smu management services for the driver.
+
+SMU11_MGR = arcturus_ppt.o \
+	    navi10_ppt.o \
+	    sienna_cichlid_ppt.o \
+	    smu_v11_0.o
+
+AMD_SWSMU_SMU11MGR = $(addprefix $(AMD_SWSMU_PATH)/smu11/,$(SMU11_MGR))
+
+AMD_POWERPLAY_FILES += $(AMD_SWSMU_SMU11MGR)
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 6c991de8f371..2ce6ad9c6609 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -79,6 +79,8 @@
 /* possible frequency drift (1Mhz) */
 #define EPSILON				1
 
+#define smnPCIE_ESM_CTRL			0x111003D0
+
 static const struct cmn2asic_msg_mapping arcturus_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,			     PPSMC_MSG_GetSmuVersion,			1),
@@ -234,6 +236,13 @@ static int arcturus_tables_init(struct smu_context *smu)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_0);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table) {
+		kfree(smu_table->metrics_table);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -542,19 +551,12 @@ static int arcturus_get_smu_metrics_data(struct smu_context *smu,
 
 	mutex_lock(&smu->metrics_lock);
 
-	if (!smu_table->metrics_time ||
-	     time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(1))) {
-		ret = smu_cmn_update_table(smu,
-				       SMU_TABLE_SMU_METRICS,
-				       0,
-				       smu_table->metrics_table,
-				       false);
-		if (ret) {
-			dev_info(smu->adev->dev, "Failed to export SMU metrics table!\n");
-			mutex_unlock(&smu->metrics_lock);
-			return ret;
-		}
-		smu_table->metrics_time = jiffies;
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       NULL,
+					       false);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
 	}
 
 	switch (member) {
@@ -897,9 +899,10 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
 		return ret;
 	}
 
-	if (smu_version >= 0x361200) {
+	if ((smu_version >= 0x361200) &&
+	    (smu_version <= 0x361a00)) {
 		dev_err(smu->adev->dev, "Forcing clock level is not supported with "
-		       "54.18 and onwards SMU firmwares\n");
+		       "54.18 - 54.26(included) SMU firmwares\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -1120,29 +1123,23 @@ static int arcturus_get_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	return arcturus_get_smu_metrics_data(smu,
-					     METRICS_CURR_FANSPEED,
-					     speed);
+	switch (smu_v11_0_get_fan_control_mode(smu)) {
+	case AMD_FAN_CTRL_AUTO:
+		return arcturus_get_smu_metrics_data(smu,
+						     METRICS_CURR_FANSPEED,
+						     speed);
+	default:
+		return smu_v11_0_get_fan_speed_rpm(smu, speed);
+	}
 }
 
-static int arcturus_get_fan_speed_percent(struct smu_context *smu,
-					  uint32_t *speed)
+static int arcturus_get_fan_parameters(struct smu_context *smu)
 {
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
-	uint32_t percent, current_rpm;
-	int ret = 0;
 
-	if (!speed)
-		return -EINVAL;
+	smu->fan_max_rpm = pptable->FanMaximumRpm;
 
-	ret = arcturus_get_fan_speed_rpm(smu, &current_rpm);
-	if (ret)
-		return ret;
-
-	percent = current_rpm * 100 / pptable->FanMaximumRpm;
-	*speed = percent > 100 ? 100 : percent;
-
-	return ret;
+	return 0;
 }
 
 static int arcturus_get_power_limit(struct smu_context *smu)
@@ -1392,9 +1389,10 @@ static int arcturus_set_performance_level(struct smu_context *smu,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-		if (smu_version >= 0x361200) {
+		if ((smu_version >= 0x361200) &&
+		    (smu_version <= 0x361a00)) {
 			dev_err(smu->adev->dev, "Forcing clock level is not supported with "
-			       "54.18 and onwards SMU firmwares\n");
+			       "54.18 - 54.26(included) SMU firmwares\n");
 			return -EOPNOTSUPP;
 		}
 		break;
@@ -1840,10 +1838,14 @@ static bool arcturus_is_dpm_running(struct smu_context *smu)
 {
 	int ret = 0;
 	uint32_t feature_mask[2];
-	unsigned long feature_enabled;
+	uint64_t feature_enabled;
+
 	ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2);
-	feature_enabled = (unsigned long)((uint64_t)feature_mask[0] |
-			   ((uint64_t)feature_mask[1] << 32));
+	if (ret)
+		return false;
+
+	feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0];
+
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
@@ -2204,14 +2206,17 @@ static const struct throttling_logging_label {
 };
 static void arcturus_log_thermal_throttling_event(struct smu_context *smu)
 {
+	int ret;
 	int throttler_idx, throtting_events = 0, buf_idx = 0;
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t throttler_status;
 	char log_buf[256];
 
-	arcturus_get_smu_metrics_data(smu,
-				      METRICS_THROTTLER_STATUS,
-				      &throttler_status);
+	ret = arcturus_get_smu_metrics_data(smu,
+					    METRICS_THROTTLER_STATUS,
+					    &throttler_status);
+	if (ret)
+		return;
 
 	memset(log_buf, 0, sizeof(log_buf));
 	for (throttler_idx = 0; throttler_idx < ARRAY_SIZE(logging_label);
@@ -2233,6 +2238,77 @@ static void arcturus_log_thermal_throttling_event(struct smu_context *smu)
 
 	dev_warn(adev->dev, "WARN: GPU thermal throttling temperature reached, expect performance decrease. %s.\n",
 			log_buf);
+	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev, throttler_status);
+}
+
+static int arcturus_get_current_pcie_link_speed(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t esm_ctrl;
+
+	/* TODO: confirm this on real target */
+	esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL);
+	if ((esm_ctrl >> 15) & 0x1FFFF)
+		return (((esm_ctrl >> 8) & 0x3F) + 128);
+
+	return smu_v11_0_get_current_pcie_link_speed(smu);
+}
+
+static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu,
+					void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v1_0 *gpu_metrics =
+		(struct gpu_metrics_v1_0 *)smu_table->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	int ret = 0;
+
+	ret = smu_cmn_get_metrics_table(smu,
+					&metrics,
+					true);
+	if (ret)
+		return ret;
+
+	smu_v11_0_init_gpu_metrics_v1_0(gpu_metrics);
+
+	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
+	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
+	gpu_metrics->temperature_mem = metrics.TemperatureHBM;
+	gpu_metrics->temperature_vrgfx = metrics.TemperatureVrGfx;
+	gpu_metrics->temperature_vrsoc = metrics.TemperatureVrSoc;
+	gpu_metrics->temperature_vrmem = metrics.TemperatureVrMem;
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+	gpu_metrics->average_mm_activity = metrics.VcnActivityPercentage;
+
+	gpu_metrics->average_socket_power = metrics.AverageSocketPower;
+	gpu_metrics->energy_accumulator = metrics.EnergyAccumulator;
+
+	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequency;
+	gpu_metrics->average_vclk0_frequency = metrics.AverageVclkFrequency;
+	gpu_metrics->average_dclk0_frequency = metrics.AverageDclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 = metrics.CurrClock[PPCLK_VCLK];
+	gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	gpu_metrics->current_fan_speed = metrics.CurrFanSpeed;
+
+	gpu_metrics->pcie_link_width =
+			smu_v11_0_get_current_pcie_link_width(smu);
+	gpu_metrics->pcie_link_speed =
+			arcturus_get_current_pcie_link_speed(smu);
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v1_0);
 }
 
 static const struct pptable_funcs arcturus_ppt_funcs = {
@@ -2247,7 +2323,6 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.print_clk_levels = arcturus_print_clk_levels,
 	.force_clk_levels = arcturus_force_clk_levels,
 	.read_sensor = arcturus_read_sensor,
-	.get_fan_speed_percent = arcturus_get_fan_speed_percent,
 	.get_fan_speed_rpm = arcturus_get_fan_speed_rpm,
 	.get_power_profile_mode = arcturus_get_power_profile_mode,
 	.set_power_profile_mode = arcturus_set_power_profile_mode,
@@ -2293,7 +2368,6 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
@@ -2312,6 +2386,10 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.log_thermal_throttling_event = arcturus_log_thermal_throttling_event,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
+	.get_gpu_metrics = arcturus_get_gpu_metrics,
+	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
+	.deep_sleep_control = smu_v11_0_deep_sleep_control,
+	.get_fan_parameters = arcturus_get_fan_parameters,
 };
 
 void arcturus_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.h
index d756b16924b8..d756b16924b8 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.h
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 9f62af9abd23..42d53cca7360 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -138,6 +138,7 @@ static struct cmn2asic_msg_mapping navi10_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(DAL_ENABLE_DUMMY_PSTATE_CHANGE,	PPSMC_MSG_DALEnableDummyPstateChange,	0),
 	MSG_MAP(GetVoltageByDpm,		PPSMC_MSG_GetVoltageByDpm,		0),
 	MSG_MAP(GetVoltageByDpmOverdrive,	PPSMC_MSG_GetVoltageByDpmOverdrive,	0),
+	MSG_MAP(SetMGpuFanBoostLimitRpm,	PPSMC_MSG_SetMGpuFanBoostLimitRpm,	0),
 };
 
 static struct cmn2asic_mapping navi10_clk_map[SMU_CLK_COUNT] = {
@@ -456,13 +457,18 @@ static int navi10_tables_init(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
+	struct amdgpu_device *adev = smu->adev;
 
 	SMU_TABLE_INIT(tables, SMU_TABLE_PPTABLE, sizeof(PPTable_t),
 		       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 	SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t),
 		       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
-	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t),
-		       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
+	if (adev->asic_type == CHIP_NAVI12)
+		SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_NV12_t),
+			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
+	else
+		SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t),
+			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 	SMU_TABLE_INIT(tables, SMU_TABLE_I2C_COMMANDS, sizeof(SwI2cRequest_t),
 		       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 	SMU_TABLE_INIT(tables, SMU_TABLE_OVERDRIVE, sizeof(OverDriveTable_t),
@@ -473,16 +479,30 @@ static int navi10_tables_init(struct smu_context *smu)
 		       sizeof(DpmActivityMonitorCoeffInt_t), PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM);
 
-	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+	smu_table->metrics_table = kzalloc(adev->asic_type == CHIP_NAVI12 ?
+					   sizeof(SmuMetrics_NV12_t) :
+					   sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
-		return -ENOMEM;
+		goto err0_out;
 	smu_table->metrics_time = 0;
 
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_0);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table)
+		goto err1_out;
+
 	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
 	if (!smu_table->watermarks_table)
-		return -ENOMEM;
+		goto err2_out;
 
 	return 0;
+
+err2_out:
+	kfree(smu_table->gpu_metrics_table);
+err1_out:
+	kfree(smu_table->metrics_table);
+err0_out:
+	return -ENOMEM;
 }
 
 static int navi10_get_smu_metrics_data(struct smu_context *smu,
@@ -490,23 +510,22 @@ static int navi10_get_smu_metrics_data(struct smu_context *smu,
 				       uint32_t *value)
 {
 	struct smu_table_context *smu_table= &smu->smu_table;
+	/*
+	 * This works for NV12 also. As although NV12 uses a different
+	 * SmuMetrics structure from other NV1X ASICs, they share the
+	 * same offsets for the heading parts(those members used here).
+	 */
 	SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table;
 	int ret = 0;
 
 	mutex_lock(&smu->metrics_lock);
-	if (!smu_table->metrics_time ||
-	     time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(1))) {
-		ret = smu_cmn_update_table(smu,
-				       SMU_TABLE_SMU_METRICS,
-				       0,
-				       smu_table->metrics_table,
-				       false);
-		if (ret) {
-			dev_info(smu->adev->dev, "Failed to export SMU metrics table!\n");
-			mutex_unlock(&smu->metrics_lock);
-			return ret;
-		}
-		smu_table->metrics_time = jiffies;
+
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       NULL,
+					       false);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
 	}
 
 	switch (member) {
@@ -909,7 +928,6 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	uint32_t gen_speed, lane_width;
 	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
 	struct smu_11_0_dpm_context *dpm_context = smu_dpm->dpm_context;
-	struct amdgpu_device *adev = smu->adev;
 	PPTable_t *pptable = (PPTable_t *)table_context->driver_pptable;
 	OverDriveTable_t *od_table =
 		(OverDriveTable_t *)table_context->overdrive_table;
@@ -963,12 +981,8 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 		}
 		break;
 	case SMU_PCIE:
-		gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
-			     PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
-			>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
-		lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
-			      PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
-			>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+		gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu);
+		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
 		for (i = 0; i < NUM_LINK_LEVELS; i++)
 			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
@@ -1331,10 +1345,14 @@ static bool navi10_is_dpm_running(struct smu_context *smu)
 {
 	int ret = 0;
 	uint32_t feature_mask[2];
-	unsigned long feature_enabled;
+	uint64_t feature_enabled;
+
 	ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2);
-	feature_enabled = (unsigned long)((uint64_t)feature_mask[0] |
-			   ((uint64_t)feature_mask[1] << 32));
+	if (ret)
+		return false;
+
+	feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0];
+
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
@@ -1344,27 +1362,23 @@ static int navi10_get_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	return navi10_get_smu_metrics_data(smu,
-					   METRICS_CURR_FANSPEED,
-					   speed);
+	switch (smu_v11_0_get_fan_control_mode(smu)) {
+	case AMD_FAN_CTRL_AUTO:
+		return navi10_get_smu_metrics_data(smu,
+						   METRICS_CURR_FANSPEED,
+						   speed);
+	default:
+		return smu_v11_0_get_fan_speed_rpm(smu, speed);
+	}
 }
 
-static int navi10_get_fan_speed_percent(struct smu_context *smu,
-					uint32_t *speed)
+static int navi10_get_fan_parameters(struct smu_context *smu)
 {
-	int ret = 0;
-	uint32_t percent = 0;
-	uint32_t current_rpm;
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 
-	ret = navi10_get_fan_speed_rpm(smu, &current_rpm);
-	if (ret)
-		return ret;
-
-	percent = current_rpm * 100 / pptable->FanMaximumRpm;
-	*speed = percent > 100 ? 100 : percent;
+	smu->fan_max_rpm = pptable->FanMaximumRpm;
 
-	return ret;
+	return 0;
 }
 
 static int navi10_get_power_profile_mode(struct smu_context *smu, char *buf)
@@ -2472,6 +2486,97 @@ static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter
 	i2c_del_adapter(control);
 }
 
+static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
+				      void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v1_0 *gpu_metrics =
+		(struct gpu_metrics_v1_0 *)smu_table->gpu_metrics_table;
+	struct amdgpu_device *adev = smu->adev;
+	SmuMetrics_NV12_t nv12_metrics = { 0 };
+	SmuMetrics_t metrics;
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       NULL,
+					       true);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
+	}
+
+	memcpy(&metrics, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	if (adev->asic_type == CHIP_NAVI12)
+		memcpy(&nv12_metrics, smu_table->metrics_table, sizeof(SmuMetrics_NV12_t));
+
+	mutex_unlock(&smu->metrics_lock);
+
+	smu_v11_0_init_gpu_metrics_v1_0(gpu_metrics);
+
+	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
+	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
+	gpu_metrics->temperature_mem = metrics.TemperatureMem;
+	gpu_metrics->temperature_vrgfx = metrics.TemperatureVrGfx;
+	gpu_metrics->temperature_vrsoc = metrics.TemperatureVrSoc;
+	gpu_metrics->temperature_vrmem = metrics.TemperatureVrMem0;
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+
+	gpu_metrics->average_socket_power = metrics.AverageSocketPower;
+
+	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequency;
+
+	if (adev->asic_type == CHIP_NAVI12) {
+		gpu_metrics->energy_accumulator = nv12_metrics.EnergyAccumulator;
+		gpu_metrics->average_vclk0_frequency = nv12_metrics.AverageVclkFrequency;
+		gpu_metrics->average_dclk0_frequency = nv12_metrics.AverageDclkFrequency;
+		gpu_metrics->average_mm_activity = nv12_metrics.VcnActivityPercentage;
+	}
+
+	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 = metrics.CurrClock[PPCLK_VCLK];
+	gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	gpu_metrics->current_fan_speed = metrics.CurrFanSpeed;
+
+	gpu_metrics->pcie_link_width =
+			smu_v11_0_get_current_pcie_link_width(smu);
+	gpu_metrics->pcie_link_speed =
+			smu_v11_0_get_current_pcie_link_speed(smu);
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v1_0);
+}
+
+static int navi10_enable_mgpu_fan_boost(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t param = 0;
+
+	/* Navi12 does not support this */
+	if (adev->asic_type == CHIP_NAVI12)
+		return 0;
+
+	/* Workaround for WS SKU */
+	if (adev->pdev->device == 0x7312 &&
+	    adev->pdev->revision == 0)
+		param = 0xD188;
+
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_SetMGpuFanBoostLimitRpm,
+					       param,
+					       NULL);
+}
 
 static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_allowed_feature_mask = navi10_get_allowed_feature_mask,
@@ -2488,7 +2593,6 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_config_changed = navi10_display_config_changed,
 	.notify_smc_display_config = navi10_notify_smc_display_config,
 	.is_dpm_running = navi10_is_dpm_running,
-	.get_fan_speed_percent = navi10_get_fan_speed_percent,
 	.get_fan_speed_rpm = navi10_get_fan_speed_rpm,
 	.get_power_profile_mode = navi10_get_power_profile_mode,
 	.set_power_profile_mode = navi10_set_power_profile_mode,
@@ -2532,7 +2636,6 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
@@ -2553,6 +2656,11 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.set_power_source = smu_v11_0_set_power_source,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
+	.get_gpu_metrics = navi10_get_gpu_metrics,
+	.enable_mgpu_fan_boost = navi10_enable_mgpu_fan_boost,
+	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
+	.deep_sleep_control = smu_v11_0_deep_sleep_control,
+	.get_fan_parameters = navi10_get_fan_parameters,
 };
 
 void navi10_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.h
index 2abb4ba01db1..84dc5a1b6830 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.h
@@ -49,9 +49,6 @@
 
 #define NAVI10_VOLTAGE_SCALE (4)
 
-#define smnPCIE_LC_SPEED_CNTL			0x11140290
-#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
-
 extern void navi10_set_ppt_funcs(struct smu_context *smu);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 3865dbed5f93..5c22611d5878 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -68,7 +68,8 @@
 	FEATURE_MASK(FEATURE_DPM_LINK_BIT)       | \
 	FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT)     | \
 	FEATURE_MASK(FEATURE_DPM_FCLK_BIT)	 | \
-	FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT))
+	FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT)	 | \
+	FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT))
 
 #define SMU_11_0_7_GFX_BUSY_THRESHOLD 15
 
@@ -95,6 +96,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(TransferTableSmu2Dram,		PPSMC_MSG_TransferTableSmu2Dram,       0),
 	MSG_MAP(TransferTableDram2Smu,		PPSMC_MSG_TransferTableDram2Smu,       0),
 	MSG_MAP(UseDefaultPPTable,		PPSMC_MSG_UseDefaultPPTable,           0),
+	MSG_MAP(RunDcBtc,			PPSMC_MSG_RunDcBtc,                    0),
 	MSG_MAP(EnterBaco,			PPSMC_MSG_EnterBaco,                   0),
 	MSG_MAP(SetSoftMinByFreq,		PPSMC_MSG_SetSoftMinByFreq,            0),
 	MSG_MAP(SetSoftMaxByFreq,		PPSMC_MSG_SetSoftMaxByFreq,            0),
@@ -124,6 +126,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(BacoAudioD3PME,			PPSMC_MSG_BacoAudioD3PME,              0),
 	MSG_MAP(ArmD3,				PPSMC_MSG_ArmD3,                       0),
 	MSG_MAP(Mode1Reset,                     PPSMC_MSG_Mode1Reset,		       0),
+	MSG_MAP(SetMGpuFanBoostLimitRpm,	PPSMC_MSG_SetMGpuFanBoostLimitRpm,     0),
 };
 
 static struct cmn2asic_mapping sienna_cichlid_clk_map[SMU_CLK_COUNT] = {
@@ -228,6 +231,7 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu,
 
 	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_PREFETCHER_BIT)
 				| FEATURE_MASK(FEATURE_DPM_FCLK_BIT)
+				| FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT)
 				| FEATURE_MASK(FEATURE_DS_SOCCLK_BIT)
 				| FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT)
 				| FEATURE_MASK(FEATURE_DS_FCLK_BIT)
@@ -385,14 +389,26 @@ static int sienna_cichlid_tables_init(struct smu_context *smu)
 
 	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
-		return -ENOMEM;
+		goto err0_out;
 	smu_table->metrics_time = 0;
 
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_0);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table)
+		goto err1_out;
+
 	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
 	if (!smu_table->watermarks_table)
-		return -ENOMEM;
+		goto err2_out;
 
 	return 0;
+
+err2_out:
+	kfree(smu_table->gpu_metrics_table);
+err1_out:
+	kfree(smu_table->metrics_table);
+err0_out:
+	return -ENOMEM;
 }
 
 static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
@@ -404,19 +420,13 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 	int ret = 0;
 
 	mutex_lock(&smu->metrics_lock);
-	if (!smu_table->metrics_time ||
-	     time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(1))) {
-		ret = smu_cmn_update_table(smu,
-				       SMU_TABLE_SMU_METRICS,
-				       0,
-				       smu_table->metrics_table,
-				       false);
-		if (ret) {
-			dev_info(smu->adev->dev, "Failed to export SMU metrics table!\n");
-			mutex_unlock(&smu->metrics_lock);
-			return ret;
-		}
-		smu_table->metrics_time = jiffies;
+
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       NULL,
+					       false);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
 	}
 
 	switch (member) {
@@ -775,7 +785,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl
 			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0, NULL);
 			if (ret)
 				return ret;
-			if (adev->asic_type == CHIP_SIENNA_CICHLID) {
+			if (adev->vcn.num_vcn_inst > 1) {
 				ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn,
 								  0x10000, NULL);
 				if (ret)
@@ -787,7 +797,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl
 			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL);
 			if (ret)
 				return ret;
-			if (adev->asic_type == CHIP_SIENNA_CICHLID) {
+			if (adev->vcn.num_vcn_inst > 1) {
 				ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn,
 								  0x10000, NULL);
 				if (ret)
@@ -951,12 +961,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		}
 		break;
 	case SMU_PCIE:
-		gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
-			     PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
-			>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
-		lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
-			      PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
-			>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+		gen_speed = smu_v11_0_get_current_pcie_link_speed(smu);
+		lane_width = smu_v11_0_get_current_pcie_link_width(smu);
 		for (i = 0; i < NUM_LINK_LEVELS; i++)
 			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
@@ -1146,10 +1152,14 @@ static bool sienna_cichlid_is_dpm_running(struct smu_context *smu)
 {
 	int ret = 0;
 	uint32_t feature_mask[2];
-	unsigned long feature_enabled;
+	uint64_t feature_enabled;
+
 	ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2);
-	feature_enabled = (unsigned long)((uint64_t)feature_mask[0] |
-			   ((uint64_t)feature_mask[1] << 32));
+	if (ret)
+		return false;
+
+	feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0];
+
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
@@ -1159,27 +1169,23 @@ static int sienna_cichlid_get_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	return sienna_cichlid_get_smu_metrics_data(smu,
-						   METRICS_CURR_FANSPEED,
-						   speed);
+	switch (smu_v11_0_get_fan_control_mode(smu)) {
+	case AMD_FAN_CTRL_AUTO:
+		return sienna_cichlid_get_smu_metrics_data(smu,
+							   METRICS_CURR_FANSPEED,
+							   speed);
+	default:
+		return smu_v11_0_get_fan_speed_rpm(smu, speed);
+	}
 }
 
-static int sienna_cichlid_get_fan_speed_percent(struct smu_context *smu,
-					uint32_t *speed)
+static int sienna_cichlid_get_fan_parameters(struct smu_context *smu)
 {
-	int ret = 0;
-	uint32_t percent = 0;
-	uint32_t current_rpm;
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 
-	ret = sienna_cichlid_get_fan_speed_rpm(smu, &current_rpm);
-	if (ret)
-		return ret;
-
-	percent = current_rpm * 100 / pptable->FanMaximumRpm;
-	*speed = percent > 100 ? 100 : percent;
+	smu->fan_max_rpm = pptable->FanMaximumRpm;
 
-	return ret;
+	return 0;
 }
 
 static int sienna_cichlid_get_power_profile_mode(struct smu_context *smu, char *buf)
@@ -1732,6 +1738,11 @@ static int sienna_cichlid_get_dpm_ultimate_freq(struct smu_context *smu,
 	return ret;
 }
 
+static int sienna_cichlid_run_btc(struct smu_context *smu)
+{
+	return smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL);
+}
+
 static bool sienna_cichlid_is_baco_supported(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -2644,6 +2655,76 @@ static void sienna_cichlid_i2c_control_fini(struct smu_context *smu, struct i2c_
 	i2c_del_adapter(control);
 }
 
+static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu,
+					      void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v1_0 *gpu_metrics =
+		(struct gpu_metrics_v1_0 *)smu_table->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	int ret = 0;
+
+	ret = smu_cmn_get_metrics_table(smu,
+					&metrics,
+					true);
+	if (ret)
+		return ret;
+
+	smu_v11_0_init_gpu_metrics_v1_0(gpu_metrics);
+
+	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
+	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
+	gpu_metrics->temperature_mem = metrics.TemperatureMem;
+	gpu_metrics->temperature_vrgfx = metrics.TemperatureVrGfx;
+	gpu_metrics->temperature_vrsoc = metrics.TemperatureVrSoc;
+	gpu_metrics->temperature_vrmem = metrics.TemperatureVrMem0;
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+	gpu_metrics->average_mm_activity = metrics.VcnActivityPercentage;
+
+	gpu_metrics->average_socket_power = metrics.AverageSocketPower;
+	gpu_metrics->energy_accumulator = metrics.EnergyAccumulator;
+
+	if (metrics.AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
+		gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequencyPostDs;
+	else
+		gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequencyPreDs;
+	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequencyPostDs;
+	gpu_metrics->average_vclk0_frequency = metrics.AverageVclk0Frequency;
+	gpu_metrics->average_dclk0_frequency = metrics.AverageDclk0Frequency;
+	gpu_metrics->average_vclk1_frequency = metrics.AverageVclk1Frequency;
+	gpu_metrics->average_dclk1_frequency = metrics.AverageDclk1Frequency;
+
+	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.CurrClock[PPCLK_UCLK];
+	gpu_metrics->current_vclk0 = metrics.CurrClock[PPCLK_VCLK_0];
+	gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK_0];
+	gpu_metrics->current_vclk1 = metrics.CurrClock[PPCLK_VCLK_1];
+	gpu_metrics->current_dclk1 = metrics.CurrClock[PPCLK_DCLK_1];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	gpu_metrics->current_fan_speed = metrics.CurrFanSpeed;
+
+	gpu_metrics->pcie_link_width =
+			smu_v11_0_get_current_pcie_link_width(smu);
+	gpu_metrics->pcie_link_speed =
+			smu_v11_0_get_current_pcie_link_speed(smu);
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v1_0);
+}
+
+static int sienna_cichlid_enable_mgpu_fan_boost(struct smu_context *smu)
+{
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_SetMGpuFanBoostLimitRpm,
+					       0,
+					       NULL);
+}
 
 static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.get_allowed_feature_mask = sienna_cichlid_get_allowed_feature_mask,
@@ -2659,7 +2740,6 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_config_changed = sienna_cichlid_display_config_changed,
 	.notify_smc_display_config = sienna_cichlid_notify_smc_display_config,
 	.is_dpm_running = sienna_cichlid_is_dpm_running,
-	.get_fan_speed_percent = sienna_cichlid_get_fan_speed_percent,
 	.get_fan_speed_rpm = sienna_cichlid_get_fan_speed_rpm,
 	.get_power_profile_mode = sienna_cichlid_get_power_profile_mode,
 	.set_power_profile_mode = sienna_cichlid_set_power_profile_mode,
@@ -2703,7 +2783,6 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
@@ -2719,8 +2798,14 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.mode1_reset = smu_v11_0_mode1_reset,
 	.get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
+	.run_btc = sienna_cichlid_run_btc,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
+	.get_gpu_metrics = sienna_cichlid_get_gpu_metrics,
+	.enable_mgpu_fan_boost = sienna_cichlid_enable_mgpu_fan_boost,
+	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
+	.deep_sleep_control = smu_v11_0_deep_sleep_control,
+	.get_fan_parameters = sienna_cichlid_get_fan_parameters,
 };
 
 void sienna_cichlid_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.h
index 8078886e4cbc..57e120c440ea 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.h
@@ -31,7 +31,4 @@ typedef enum {
 
 extern void sienna_cichlid_set_ppt_funcs(struct smu_context *smu);
 
-#define smnPCIE_LC_SPEED_CNTL                   0x11140290
-#define smnPCIE_LC_LINK_WIDTH_CNTL              0x11140288
-
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 7b950a582a28..f5aeb0b5cf97 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -67,6 +67,19 @@ MODULE_FIRMWARE("amdgpu/navy_flounder_smc.bin");
 
 #define SMU11_MODE1_RESET_WAIT_TIME_IN_MS 500  //500ms
 
+#define LINK_WIDTH_MAX				6
+#define LINK_SPEED_MAX				3
+
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+#define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L
+#define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4
+#define smnPCIE_LC_SPEED_CNTL			0x11140290
+#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xC000
+#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0xE
+
+static int link_width[] = {0, 1, 2, 4, 8, 12, 16};
+static int link_speed[] = {25, 50, 80, 160};
+
 int smu_v11_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -404,10 +417,12 @@ int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
 
+	kfree(smu_table->gpu_metrics_table);
 	kfree(smu_table->boot_overdrive_table);
 	kfree(smu_table->overdrive_table);
 	kfree(smu_table->max_sustainable_clocks);
 	kfree(smu_table->driver_pptable);
+	smu_table->gpu_metrics_table = NULL;
 	smu_table->boot_overdrive_table = NULL;
 	smu_table->overdrive_table = NULL;
 	smu_table->max_sustainable_clocks = NULL;
@@ -1085,35 +1100,6 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode)
 }
 
 int
-smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
-{
-	struct amdgpu_device *adev = smu->adev;
-	uint32_t duty100, duty;
-	uint64_t tmp64;
-
-	if (speed > 100)
-		speed = 100;
-
-	if (smu_v11_0_auto_fan_control(smu, 0))
-		return -EINVAL;
-
-	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
-				CG_FDO_CTRL1, FMAX_DUTY100);
-	if (!duty100)
-		return -EINVAL;
-
-	tmp64 = (uint64_t)speed * duty100;
-	do_div(tmp64, 100);
-	duty = (uint32_t)tmp64;
-
-	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
-		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0),
-				   CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
-
-	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
-}
-
-int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode)
 {
@@ -1121,7 +1107,7 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		ret = smu_v11_0_set_fan_speed_percent(smu, 100);
+		ret = smu_v11_0_set_fan_speed_rpm(smu, smu->fan_max_rpm);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		ret = smu_v11_0_auto_fan_control(smu, 0);
@@ -1167,6 +1153,27 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	return ret;
 }
 
+int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu,
+				uint32_t *speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t tach_period, crystal_clock_freq;
+	uint64_t tmp64;
+
+	tach_period = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
+				    CG_TACH_CTRL, TARGET_PERIOD);
+	if (!tach_period)
+		return -EINVAL;
+
+	crystal_clock_freq = amdgpu_asic_get_xclk(adev);
+
+	tmp64 = (uint64_t)crystal_clock_freq * 60 * 10000;
+	do_div(tmp64, (tach_period * 8));
+	*speed = (uint32_t)tmp64;
+
+	return 0;
+}
+
 int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
 				     uint32_t pstate)
 {
@@ -1312,6 +1319,11 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 				smu_v11_0_ack_ac_dc_interrupt(&adev->smu);
 				break;
 			case 0x7:
+				/*
+				 * Increment the throttle interrupt counter
+				 */
+				atomic64_inc(&smu->throttle_int_counter);
+
 				if (!atomic_read(&adev->throttling_logging_enabled))
 					return 0;
 
@@ -1913,3 +1925,99 @@ int smu_v11_0_get_dpm_level_range(struct smu_context *smu,
 
 	return ret;
 }
+
+int smu_v11_0_get_current_pcie_link_width_level(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+		PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+}
+
+int smu_v11_0_get_current_pcie_link_width(struct smu_context *smu)
+{
+	uint32_t width_level;
+
+	width_level = smu_v11_0_get_current_pcie_link_width_level(smu);
+	if (width_level > LINK_WIDTH_MAX)
+		width_level = 0;
+
+	return link_width[width_level];
+}
+
+int smu_v11_0_get_current_pcie_link_speed_level(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+		PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+		>> PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+}
+
+int smu_v11_0_get_current_pcie_link_speed(struct smu_context *smu)
+{
+	uint32_t speed_level;
+
+	speed_level = smu_v11_0_get_current_pcie_link_speed_level(smu);
+	if (speed_level > LINK_SPEED_MAX)
+		speed_level = 0;
+
+	return link_speed[speed_level];
+}
+
+void smu_v11_0_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics)
+{
+	memset(gpu_metrics, 0xFF, sizeof(struct gpu_metrics_v1_0));
+
+	gpu_metrics->common_header.structure_size =
+				sizeof(struct gpu_metrics_v1_0);
+	gpu_metrics->common_header.format_revision = 1;
+	gpu_metrics->common_header.content_revision = 0;
+
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+}
+
+int smu_v11_0_gfx_ulv_control(struct smu_context *smu,
+			      bool enablement)
+{
+	int ret = 0;
+
+	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_GFX_ULV_BIT))
+		ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_GFX_ULV_BIT, enablement);
+
+	return ret;
+}
+
+int smu_v11_0_deep_sleep_control(struct smu_context *smu,
+				 bool enablement)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_DS_GFXCLK_BIT)) {
+		ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_DS_GFXCLK_BIT, enablement);
+		if (ret) {
+			dev_err(adev->dev, "Failed to %s GFXCLK DS!\n", enablement ? "enable" : "disable");
+			return ret;
+		}
+	}
+
+	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_DS_SOCCLK_BIT)) {
+		ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_DS_SOCCLK_BIT, enablement);
+		if (ret) {
+			dev_err(adev->dev, "Failed to %s SOCCLK DS!\n", enablement ? "enable" : "disable");
+			return ret;
+		}
+	}
+
+	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_DS_LCLK_BIT)) {
+		ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_DS_LCLK_BIT, enablement);
+		if (ret) {
+			dev_err(adev->dev, "Failed to %s LCLK DS!\n", enablement ? "enable" : "disable");
+			return ret;
+		}
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu12/Makefile
new file mode 100644
index 000000000000..67e53f7da3ce
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/Makefile
@@ -0,0 +1,31 @@
+#
+# Copyright 2020 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
+# Makefile for the 'smu manager' sub-component of powerplay.
+# It provides the smu management services for the driver.
+
+SMU12_MGR = renoir_ppt.o \
+	    smu_v12_0.o
+
+AMD_SWSMU_SMU12MGR = $(addprefix $(AMD_SWSMU_PATH)/smu12/,$(SMU12_MGR))
+
+AMD_POWERPLAY_FILES += $(AMD_SWSMU_SMU12MGR)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index dbb676c482fd..3b9ac72c7571 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -128,30 +128,6 @@ static struct cmn2asic_mapping renoir_workload_map[PP_SMC_POWER_PROFILE_COUNT] =
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
 };
 
-static int renoir_get_metrics_table(struct smu_context *smu,
-				    SmuMetrics_t *metrics_table)
-{
-	struct smu_table_context *smu_table= &smu->smu_table;
-	int ret = 0;
-
-	mutex_lock(&smu->metrics_lock);
-	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
-		ret = smu_cmn_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
-				(void *)smu_table->metrics_table, false);
-		if (ret) {
-			dev_info(smu->adev->dev, "Failed to export SMU metrics table!\n");
-			mutex_unlock(&smu->metrics_lock);
-			return ret;
-		}
-		smu_table->metrics_time = jiffies;
-	}
-
-	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
-	mutex_unlock(&smu->metrics_lock);
-
-	return ret;
-}
-
 static int renoir_init_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
@@ -166,18 +142,32 @@ static int renoir_init_smc_tables(struct smu_context *smu)
 
 	smu_table->clocks_table = kzalloc(sizeof(DpmClocks_t), GFP_KERNEL);
 	if (!smu_table->clocks_table)
-		return -ENOMEM;
+		goto err0_out;
 
 	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
-		return -ENOMEM;
+		goto err1_out;
 	smu_table->metrics_time = 0;
 
 	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
 	if (!smu_table->watermarks_table)
-		return -ENOMEM;
+		goto err2_out;
+
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_0);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table)
+		goto err3_out;
 
 	return 0;
+
+err3_out:
+	kfree(smu_table->watermarks_table);
+err2_out:
+	kfree(smu_table->metrics_table);
+err1_out:
+	kfree(smu_table->clocks_table);
+err0_out:
+	return -ENOMEM;
 }
 
 /**
@@ -361,7 +351,7 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 
 	memset(&metrics, 0, sizeof(metrics));
 
-	ret = renoir_get_metrics_table(smu, &metrics);
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
 	if (ret)
 		return ret;
 
@@ -507,7 +497,7 @@ static int renoir_get_current_clk_freq_by_table(struct smu_context *smu,
 	int ret = 0, clk_id = 0;
 	SmuMetrics_t metrics;
 
-	ret = renoir_get_metrics_table(smu, &metrics);
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
 	if (ret)
 		return ret;
 
@@ -590,7 +580,7 @@ static int renoir_get_gpu_temperature(struct smu_context *smu, uint32_t *value)
 	if (!value)
 		return -EINVAL;
 
-	ret = renoir_get_metrics_table(smu, &metrics);
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
 	if (ret)
 		return ret;
 
@@ -610,7 +600,7 @@ static int renoir_get_current_activity_percent(struct smu_context *smu,
 	if (!value)
 		return -EINVAL;
 
-	ret = renoir_get_metrics_table(smu, &metrics);
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
 	if (ret)
 		return ret;
 
@@ -626,6 +616,44 @@ static int renoir_get_current_activity_percent(struct smu_context *smu,
 	return 0;
 }
 
+static int renoir_get_vddc(struct smu_context *smu, uint32_t *value,
+			   unsigned int index)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (index >= 2)
+		return -EINVAL;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
+	if (ret)
+		return ret;
+
+	*value = metrics.Voltage[index];
+
+	return 0;
+}
+
+static int renoir_get_power(struct smu_context *smu, uint32_t *value)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = smu_cmn_get_metrics_table(smu, &metrics, false);
+	if (ret)
+		return ret;
+
+	*value = metrics.CurrentSocketPower << 8;
+
+	return 0;
+}
+
 /**
  * This interface get dpm clock table for dc
  */
@@ -962,6 +990,18 @@ static int renoir_read_sensor(struct smu_context *smu,
 		*(uint32_t *)data *= 100;
 		*size = 4;
 		break;
+	case AMDGPU_PP_SENSOR_VDDGFX:
+		ret = renoir_get_vddc(smu, (uint32_t *)data, 0);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_VDDNB:
+		ret = renoir_get_vddc(smu, (uint32_t *)data, 1);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GPU_POWER:
+		ret = renoir_get_power(smu, (uint32_t *)data);
+		*size = 4;
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -987,6 +1027,65 @@ static bool renoir_is_dpm_running(struct smu_context *smu)
 
 }
 
+static ssize_t renoir_get_gpu_metrics(struct smu_context *smu,
+				      void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v2_0 *gpu_metrics =
+		(struct gpu_metrics_v2_0 *)smu_table->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	int ret = 0;
+
+	ret = smu_cmn_get_metrics_table(smu, &metrics, true);
+	if (ret)
+		return ret;
+
+	smu_v12_0_init_gpu_metrics_v2_0(gpu_metrics);
+
+	gpu_metrics->temperature_gfx = metrics.GfxTemperature;
+	gpu_metrics->temperature_soc = metrics.SocTemperature;
+	memcpy(&gpu_metrics->temperature_core[0],
+		&metrics.CoreTemperature[0],
+		sizeof(uint16_t) * 8);
+	gpu_metrics->temperature_l3[0] = metrics.L3Temperature[0];
+	gpu_metrics->temperature_l3[1] = metrics.L3Temperature[1];
+
+	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
+	gpu_metrics->average_mm_activity = metrics.AverageUvdActivity;
+
+	gpu_metrics->average_socket_power = metrics.CurrentSocketPower;
+	gpu_metrics->average_cpu_power = metrics.Power[0];
+	gpu_metrics->average_soc_power = metrics.Power[1];
+	memcpy(&gpu_metrics->average_core_power[0],
+		&metrics.CorePower[0],
+		sizeof(uint16_t) * 8);
+
+	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
+	gpu_metrics->average_fclk_frequency = metrics.AverageFclkFrequency;
+	gpu_metrics->average_vclk_frequency = metrics.AverageVclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.ClockFrequency[CLOCK_GFXCLK];
+	gpu_metrics->current_socclk = metrics.ClockFrequency[CLOCK_SOCCLK];
+	gpu_metrics->current_uclk = metrics.ClockFrequency[CLOCK_UMCCLK];
+	gpu_metrics->current_fclk = metrics.ClockFrequency[CLOCK_FCLK];
+	gpu_metrics->current_vclk = metrics.ClockFrequency[CLOCK_VCLK];
+	gpu_metrics->current_dclk = metrics.ClockFrequency[CLOCK_DCLK];
+	memcpy(&gpu_metrics->current_coreclk[0],
+		&metrics.CoreFrequency[0],
+		sizeof(uint16_t) * 8);
+	gpu_metrics->current_l3clk[0] = metrics.L3Frequency[0];
+	gpu_metrics->current_l3clk[1] = metrics.L3Frequency[1];
+
+	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
+
+	gpu_metrics->fan_pwm = metrics.FanPwm;
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v2_0);
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.set_power_state = NULL,
 	.print_clk_levels = renoir_print_clk_levels,
@@ -1021,6 +1120,7 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.is_dpm_running = renoir_is_dpm_running,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
+	.get_gpu_metrics = renoir_get_gpu_metrics,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h
index 8c3f004cdf8d..8c3f004cdf8d 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
index 31456437bb18..660f403d5770 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -274,3 +274,15 @@ int smu_v12_0_set_driver_table_location(struct smu_context *smu)
 
 	return ret;
 }
+
+void smu_v12_0_init_gpu_metrics_v2_0(struct gpu_metrics_v2_0 *gpu_metrics)
+{
+	memset(gpu_metrics, 0xFF, sizeof(struct gpu_metrics_v2_0));
+
+	gpu_metrics->common_header.structure_size =
+				sizeof(struct gpu_metrics_v2_0);
+	gpu_metrics->common_header.format_revision = 2;
+	gpu_metrics->common_header.content_revision = 0;
+
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 5c23c44c33bd..a58ea08cd115 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -604,7 +604,7 @@ int smu_cmn_update_table(struct smu_context *smu,
 		memcpy(table_data, table->cpu_addr, table_size);
 	}
 
-	return ret;
+	return 0;
 }
 
 int smu_cmn_write_watermarks_table(struct smu_context *smu)
@@ -631,3 +631,48 @@ int smu_cmn_write_pptable(struct smu_context *smu)
 				    pptable,
 				    true);
 }
+
+int smu_cmn_get_metrics_table_locked(struct smu_context *smu,
+				     void *metrics_table,
+				     bool bypass_cache)
+{
+	struct smu_table_context *smu_table= &smu->smu_table;
+	uint32_t table_size =
+		smu_table->tables[SMU_TABLE_SMU_METRICS].size;
+	int ret = 0;
+
+	if (bypass_cache ||
+	    !smu_table->metrics_time ||
+	    time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(1))) {
+		ret = smu_cmn_update_table(smu,
+				       SMU_TABLE_SMU_METRICS,
+				       0,
+				       smu_table->metrics_table,
+				       false);
+		if (ret) {
+			dev_info(smu->adev->dev, "Failed to export SMU metrics table!\n");
+			return ret;
+		}
+		smu_table->metrics_time = jiffies;
+	}
+
+	if (metrics_table)
+		memcpy(metrics_table, smu_table->metrics_table, table_size);
+
+	return 0;
+}
+
+int smu_cmn_get_metrics_table(struct smu_context *smu,
+			      void *metrics_table,
+			      bool bypass_cache)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+	ret = smu_cmn_get_metrics_table_locked(smu,
+					       metrics_table,
+					       bypass_cache);
+	mutex_unlock(&smu->metrics_lock);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 98face8c5fd6..6d00ad740c27 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -79,5 +79,13 @@ int smu_cmn_write_watermarks_table(struct smu_context *smu);
 
 int smu_cmn_write_pptable(struct smu_context *smu);
 
+int smu_cmn_get_metrics_table_locked(struct smu_context *smu,
+				     void *metrics_table,
+				     bool bypass_cache);
+
+int smu_cmn_get_metrics_table(struct smu_context *smu,
+			      void *metrics_table,
+			      bool bypass_cache);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 264073d4e263..38c10177ed21 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -92,6 +92,9 @@
 #define smu_get_asic_power_limits(smu)					smu_ppt_funcs(get_power_limit, 0, smu)
 #define smu_get_pp_feature_mask(smu, buf)				smu_ppt_funcs(get_pp_feature_mask, 0, smu, buf)
 #define smu_set_pp_feature_mask(smu, new_mask)				smu_ppt_funcs(set_pp_feature_mask, 0, smu, new_mask)
+#define smu_gfx_ulv_control(smu, enablement)				smu_ppt_funcs(gfx_ulv_control, 0, smu, enablement)
+#define smu_deep_sleep_control(smu, enablement)				smu_ppt_funcs(deep_sleep_control, 0, smu, enablement)
+#define smu_get_fan_parameters(smu)					smu_ppt_funcs(get_fan_parameters, 0, smu)
 
 #endif
 #endif
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index ca570b135478..e9de542f9b7c 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -532,7 +532,7 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
 		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
 		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
 		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
-		/* fall through */
+		fallthrough;
 	case 1:
 		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
 		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
@@ -869,7 +869,7 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
 		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
 		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
 		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
-		/* fall through */
+		fallthrough;
 	case 1:
 		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
 		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
@@ -1324,7 +1324,7 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 			break;
 		case MW_RESTART:
 			drm_writeback_signal_completion(&malidp->mw_connector, 0);
-			/* fall through - to a new start */
+			fallthrough;	/* to a new start */
 		case MW_START:
 			/* writeback started, need to emulate one-shot mode */
 			hw->disable_memwrite(hwdev);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index d62749a10cdd..77066bca8793 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -240,7 +240,7 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 					ast->dp501_fw_addr = NULL;
 				}
 			}
-			/* fallthrough */
+			fallthrough;
 		case 0x0c:
 			ast->tx_chip_type = AST_TX_DP501;
 		}
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index ce94f797d090..66b67402f1ac 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -409,7 +409,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status)
 
 		switch (data_type) {
 		case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_2BYTE:
-			fallthrough;
 		case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_2BYTE:
 			if (xfer->msg->rx_len > 1) {
 				/* read second byte */
@@ -418,7 +417,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status)
 			}
 			fallthrough;
 		case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE:
-			fallthrough;
 		case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE:
 			if (xfer->msg->rx_len > 0) {
 				/* read first byte */
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
index d7e65c869415..9fef6413741d 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
@@ -61,10 +61,10 @@ static int dw_hdmi_i2s_hw_params(struct device *dev, void *data,
 	switch (hparms->channels) {
 	case 7 ... 8:
 		conf0 |= HDMI_AUD_CONF0_I2S_EN3;
-		/* Fall-thru */
+		fallthrough;
 	case 5 ... 6:
 		conf0 |= HDMI_AUD_CONF0_I2S_EN2;
-		/* Fall-thru */
+		fallthrough;
 	case 3 ... 4:
 		conf0 |= HDMI_AUD_CONF0_I2S_EN1;
 		/* Fall-thru */
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 454544e0da7d..ecdf9b01340f 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -601,13 +601,13 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn_bridge *pdata,
 		DRM_DEV_ERROR(pdata->dev,
 			      "Unexpected max rate (%#x); assuming 5.4 GHz\n",
 			      (int)dpcd_val);
-		/* fall through */
+		fallthrough;
 	case DP_LINK_BW_5_4:
 		rate_valid[7] = 1;
-		/* fall through */
+		fallthrough;
 	case DP_LINK_BW_2_7:
 		rate_valid[4] = 1;
-		/* fall through */
+		fallthrough;
 	case DP_LINK_BW_1_62:
 		rate_valid[1] = 1;
 		break;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index f68c69a45752..9e1ad493e689 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -34,6 +34,7 @@
 #include <drm/drm_bridge.h>
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_print.h>
 #include <drm/drm_self_refresh_helper.h>
@@ -3106,7 +3107,7 @@ void drm_atomic_helper_shutdown(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("Disabling all crtc's during unload failed with %i\n", ret);
 
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 }
 EXPORT_SYMBOL(drm_atomic_helper_shutdown);
 
@@ -3246,7 +3247,7 @@ struct drm_atomic_state *drm_atomic_helper_suspend(struct drm_device *dev)
 	}
 
 unlock:
-	DRM_MODESET_LOCK_ALL_END(ctx, err);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, err);
 	if (err)
 		return ERR_PTR(err);
 
@@ -3327,7 +3328,7 @@ int drm_atomic_helper_resume(struct drm_device *dev,
 
 	err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
 
-	DRM_MODESET_LOCK_ALL_END(ctx, err);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, err);
 	drm_atomic_state_put(state);
 
 	return err;
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index a0735fbc144b..7a01d0918861 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -537,7 +537,7 @@ int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 	switch (map->type) {
 	case _DRM_REGISTERS:
 		iounmap(map->handle);
-		/* FALLTHROUGH */
+		fallthrough;
 	case _DRM_FRAME_BUFFER:
 		arch_phys_wc_del(map->mtrr);
 		break;
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c
index c93123ff7c21..138ff34b31db 100644
--- a/drivers/gpu/drm/drm_color_mgmt.c
+++ b/drivers/gpu/drm/drm_color_mgmt.c
@@ -294,7 +294,7 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 				     crtc->gamma_size, &ctx);
 
 out:
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 	return ret;
 
 }
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 283bcc4362ca..aecdd7ea26dc 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -588,7 +588,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	if (crtc_req->mode_valid && !drm_lease_held(file_priv, plane->base.id))
 		return -EACCES;
 
-	mutex_lock(&crtc->dev->mode_config.mutex);
 	DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx,
 				   DRM_MODESET_ACQUIRE_INTERRUPTIBLE, ret);
 
@@ -756,8 +755,7 @@ out:
 	fb = NULL;
 	mode = NULL;
 
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
-	mutex_unlock(&crtc->dev->mode_config.mutex);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 4c21cf69dad5..1e7c638873c8 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -423,6 +423,133 @@ bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux,
 }
 EXPORT_SYMBOL(drm_dp_send_real_edid_checksum);
 
+static u8 drm_dp_downstream_port_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 port_count = dpcd[DP_DOWN_STREAM_PORT_COUNT] & DP_PORT_COUNT_MASK;
+
+	if (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE && port_count > 4)
+		port_count = 4;
+
+	return port_count;
+}
+
+static int drm_dp_read_extended_dpcd_caps(struct drm_dp_aux *aux,
+					  u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 dpcd_ext[6];
+	int ret;
+
+	/*
+	 * Prior to DP1.3 the bit represented by
+	 * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
+	 * If it is set DP_DPCD_REV at 0000h could be at a value less than
+	 * the true capability of the panel. The only way to check is to
+	 * then compare 0000h and 2200h.
+	 */
+	if (!(dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+	      DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
+		return 0;
+
+	ret = drm_dp_dpcd_read(aux, DP_DP13_DPCD_REV, &dpcd_ext,
+			       sizeof(dpcd_ext));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(dpcd_ext))
+		return -EIO;
+
+	if (dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
+		DRM_DEBUG_KMS("%s: Extended DPCD rev less than base DPCD rev (%d > %d)\n",
+			      aux->name, dpcd[DP_DPCD_REV],
+			      dpcd_ext[DP_DPCD_REV]);
+		return 0;
+	}
+
+	if (!memcmp(dpcd, dpcd_ext, sizeof(dpcd_ext)))
+		return 0;
+
+	DRM_DEBUG_KMS("%s: Base DPCD: %*ph\n",
+		      aux->name, DP_RECEIVER_CAP_SIZE, dpcd);
+
+	memcpy(dpcd, dpcd_ext, sizeof(dpcd_ext));
+
+	return 0;
+}
+
+/**
+ * drm_dp_read_dpcd_caps() - read DPCD caps and extended DPCD caps if
+ * available
+ * @aux: DisplayPort AUX channel
+ * @dpcd: Buffer to store the resulting DPCD in
+ *
+ * Attempts to read the base DPCD caps for @aux. Additionally, this function
+ * checks for and reads the extended DPRX caps (%DP_DP13_DPCD_REV) if
+ * present.
+ *
+ * Returns: %0 if the DPCD was read successfully, negative error code
+ * otherwise.
+ */
+int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux,
+			  u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	int ret;
+
+	ret = drm_dp_dpcd_read(aux, DP_DPCD_REV, dpcd, DP_RECEIVER_CAP_SIZE);
+	if (ret < 0)
+		return ret;
+	if (ret != DP_RECEIVER_CAP_SIZE || dpcd[DP_DPCD_REV] == 0)
+		return -EIO;
+
+	ret = drm_dp_read_extended_dpcd_caps(aux, dpcd);
+	if (ret < 0)
+		return ret;
+
+	DRM_DEBUG_KMS("%s: DPCD: %*ph\n",
+		      aux->name, DP_RECEIVER_CAP_SIZE, dpcd);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_dp_read_dpcd_caps);
+
+/**
+ * drm_dp_read_downstream_info() - read DPCD downstream port info if available
+ * @aux: DisplayPort AUX channel
+ * @dpcd: A cached copy of the port's DPCD
+ * @downstream_ports: buffer to store the downstream port info in
+ *
+ * See also:
+ * drm_dp_downstream_max_clock()
+ * drm_dp_downstream_max_bpc()
+ *
+ * Returns: 0 if either the downstream port info was read successfully or
+ * there was no downstream info to read, or a negative error code otherwise.
+ */
+int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS])
+{
+	int ret;
+	u8 len;
+
+	memset(downstream_ports, 0, DP_MAX_DOWNSTREAM_PORTS);
+
+	/* No downstream info to read */
+	if (!drm_dp_is_branch(dpcd) ||
+	    dpcd[DP_DPCD_REV] < DP_DPCD_REV_10 ||
+	    !(dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT))
+		return 0;
+
+	len = drm_dp_downstream_port_count(dpcd);
+	if (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE)
+		len *= 4;
+
+	ret = drm_dp_dpcd_read(aux, DP_DOWNSTREAM_PORT_0, downstream_ports, len);
+	if (ret < 0)
+		return ret;
+
+	return ret == len ? 0 : -EIO;
+}
+EXPORT_SYMBOL(drm_dp_read_downstream_info);
+
 /**
  * drm_dp_downstream_max_clock() - extract branch device max
  *                                 pixel rate for legacy VGA
@@ -431,7 +558,11 @@ EXPORT_SYMBOL(drm_dp_send_real_edid_checksum);
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
  *
- * Returns max clock in kHz on success or 0 if max clock not defined
+ * See also:
+ * drm_dp_read_downstream_info()
+ * drm_dp_downstream_max_bpc()
+ *
+ * Returns: Max clock in kHz on success or 0 if max clock not defined
  */
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4])
@@ -462,7 +593,11 @@ EXPORT_SYMBOL(drm_dp_downstream_max_clock);
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
  *
- * Returns max bpc on success or 0 if max bpc not defined
+ * See also:
+ * drm_dp_read_downstream_info()
+ * drm_dp_downstream_max_clock()
+ *
+ * Returns: Max bpc on success or 0 if max bpc not defined
  */
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4])
@@ -492,7 +627,7 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 		case DP_DS_16BPC:
 			return 16;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -668,6 +803,54 @@ void drm_dp_set_subconnector_property(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_dp_set_subconnector_property);
 
+/**
+ * drm_dp_read_sink_count_cap() - Check whether a given connector has a valid sink
+ * count
+ * @connector: The DRM connector to check
+ * @dpcd: A cached copy of the connector's DPCD RX capabilities
+ * @desc: A cached copy of the connector's DP descriptor
+ *
+ * See also: drm_dp_read_sink_count()
+ *
+ * Returns: %True if the (e)DP connector has a valid sink count that should
+ * be probed, %false otherwise.
+ */
+bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				const struct drm_dp_desc *desc)
+{
+	/* Some eDP panels don't set a valid value for the sink count */
+	return connector->connector_type != DRM_MODE_CONNECTOR_eDP &&
+		dpcd[DP_DPCD_REV] >= DP_DPCD_REV_11 &&
+		dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT &&
+		!drm_dp_has_quirk(desc, 0, DP_DPCD_QUIRK_NO_SINK_COUNT);
+}
+EXPORT_SYMBOL(drm_dp_read_sink_count_cap);
+
+/**
+ * drm_dp_read_sink_count() - Retrieve the sink count for a given sink
+ * @aux: The DP AUX channel to use
+ *
+ * See also: drm_dp_read_sink_count_cap()
+ *
+ * Returns: The current sink count reported by @aux, or a negative error code
+ * otherwise.
+ */
+int drm_dp_read_sink_count(struct drm_dp_aux *aux)
+{
+	u8 count;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_SINK_COUNT, &count);
+	if (ret < 0)
+		return ret;
+	if (ret != 1)
+		return -EIO;
+
+	return DP_GET_SINK_COUNT(count);
+}
+EXPORT_SYMBOL(drm_dp_read_sink_count);
+
 /*
  * I2C-over-AUX implementation
  */
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 166405d4c536..b9c5a98c5c9c 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3489,6 +3489,28 @@ static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8  dp_link_count)
 }
 
 /**
+ * drm_dp_read_mst_cap() - check whether or not a sink supports MST
+ * @aux: The DP AUX channel to use
+ * @dpcd: A cached copy of the DPCD capabilities for this sink
+ *
+ * Returns: %True if the sink supports MST, %false otherwise
+ */
+bool drm_dp_read_mst_cap(struct drm_dp_aux *aux,
+			 const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 mstm_cap;
+
+	if (dpcd[DP_DPCD_REV] < DP_DPCD_REV_12)
+		return false;
+
+	if (drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &mstm_cap) != 1)
+		return false;
+
+	return mstm_cap & DP_MST_CAP;
+}
+EXPORT_SYMBOL(drm_dp_read_mst_cap);
+
+/**
  * drm_dp_mst_topology_mgr_set_mst() - Set the MST state for a topology manager
  * @mgr: manager to set state for
  * @mst_state: true to enable MST on this connector - false to disable.
@@ -5042,8 +5064,8 @@ int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm
 
 		crtc = conn_state->crtc;
 
-		if (WARN_ON(!crtc))
-			return -EINVAL;
+		if (!crtc)
+			continue;
 
 		if (!drm_dp_mst_dsc_aux_for_port(pos->port))
 			continue;
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index 901b078abf40..db05f386a709 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -428,7 +428,7 @@ int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
 out_unref:
 	drm_mode_object_put(obj);
 out:
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 	return ret;
 }
 
@@ -470,7 +470,7 @@ static int set_property_legacy(struct drm_mode_object *obj,
 		break;
 	}
 	drm_property_change_valid_put(prop, ref);
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 14b6f7638728..501b4fe55a3d 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1930,7 +1930,7 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
 	default:
 		WARN(1, "Invalid aspect ratio (0%x) on mode\n",
 		     in->picture_aspect_ratio);
-		/* fall through */
+		fallthrough;
 	case HDMI_PICTURE_ASPECT_NONE:
 		out->flags |= DRM_MODE_FLAG_PIC_AR_NONE;
 		break;
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index b7b90b3a2e38..affe1cfed009 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -792,7 +792,7 @@ static int setplane_internal(struct drm_plane *plane,
 					  crtc_x, crtc_y, crtc_w, crtc_h,
 					  src_x, src_y, src_w, src_h, &ctx);
 
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(plane->dev, ctx, ret);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index d5a4cd85a0f6..c6404b8d067f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -337,9 +337,16 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu)
 
 		gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL);
 		gpu->identity.revision = gpu_read(gpu, VIVS_HI_CHIP_REV);
-		gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID);
 		gpu->identity.customer_id = gpu_read(gpu, VIVS_HI_CHIP_CUSTOMER_ID);
-		gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID);
+
+		/*
+		 * Reading these two registers on GC600 rev 0x19 result in a
+		 * unhandled fault: external abort on non-linefetch
+		 */
+		if (!etnaviv_is_model_rev(gpu, GC600, 0x19)) {
+			gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID);
+			gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID);
+		}
 
 		/*
 		 * !!!! HACK ALERT !!!!
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 4e3e95dce6d8..cd46c882269c 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -89,12 +89,15 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 	u32 dma_addr;
 	int change;
 
+	/* block scheduler */
+	drm_sched_stop(&gpu->sched, sched_job);
+
 	/*
 	 * If the GPU managed to complete this jobs fence, the timout is
 	 * spurious. Bail out.
 	 */
 	if (dma_fence_is_signaled(submit->out_fence))
-		return;
+		goto out_no_timeout;
 
 	/*
 	 * If the GPU is still making forward progress on the front-end (which
@@ -105,12 +108,9 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 	change = dma_addr - gpu->hangcheck_dma_addr;
 	if (change < 0 || change > 16) {
 		gpu->hangcheck_dma_addr = dma_addr;
-		return;
+		goto out_no_timeout;
 	}
 
-	/* block scheduler */
-	drm_sched_stop(&gpu->sched, sched_job);
-
 	if(sched_job)
 		drm_sched_increase_karma(sched_job);
 
@@ -120,6 +120,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 
 	drm_sched_resubmit_jobs(&gpu->sched);
 
+out_no_timeout:
 	/* restart scheduler after GPU is usable again */
 	drm_sched_start(&gpu->sched, true);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 843dfcefc46a..1a1a2853a842 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -987,10 +987,10 @@ static void exynos_dsi_send_to_fifo(struct exynos_dsi *dsi,
 	switch (length) {
 	case 3:
 		reg |= payload[2] << 16;
-		/* Fall through */
+		fallthrough;
 	case 2:
 		reg |= payload[1] << 8;
-		/* Fall through */
+		fallthrough;
 	case 1:
 		reg |= payload[0];
 		exynos_dsi_write(dsi, DSIM_PAYLOAD_REG, reg);
@@ -1038,7 +1038,7 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi,
 				payload[1] = reg >> 16;
 				++xfer->rx_done;
 			}
-			/* Fall through */
+			fallthrough;
 		case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE:
 		case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE:
 			payload[0] = reg >> 8;
@@ -1082,10 +1082,10 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi,
 		switch (length) {
 		case 3:
 			payload[2] = (reg >> 16) & 0xff;
-			/* Fall through */
+			fallthrough;
 		case 2:
 			payload[1] = (reg >> 8) & 0xff;
-			/* Fall through */
+			fallthrough;
 		case 1:
 			payload[0] = reg & 0xff;
 		}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 56a2b47e1af7..5147f5929be7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -92,7 +92,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 	offset = fbi->var.xoffset * fb->format->cpp[0];
 	offset += fbi->var.yoffset * fb->pitches[0];
 
-	fbi->screen_base = exynos_gem->kvaddr + offset;
+	fbi->screen_buffer = exynos_gem->kvaddr + offset;
 	fbi->screen_size = size;
 	fbi->fix.smem_len = size;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 7445748288da..74e926abeff0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -40,7 +40,7 @@ struct exynos_drm_gem {
 	unsigned int		flags;
 	unsigned long		size;
 	void			*cookie;
-	void __iomem		*kvaddr;
+	void			*kvaddr;
 	dma_addr_t		dma_addr;
 	unsigned long		dma_attrs;
 	struct sg_table		*sgt;
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index 86fac677fe69..3c6d9f3913d5 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -101,19 +101,19 @@ static void fsl_dcu_drm_plane_atomic_update(struct drm_plane *plane,
 		break;
 	case DRM_FORMAT_ARGB8888:
 		alpha = DCU_LAYER_AB_WHOLE_FRAME;
-		/* fall-through */
+		fallthrough;
 	case DRM_FORMAT_XRGB8888:
 		bpp = FSL_DCU_ARGB8888;
 		break;
 	case DRM_FORMAT_ARGB4444:
 		alpha = DCU_LAYER_AB_WHOLE_FRAME;
-		/* fall-through */
+		fallthrough;
 	case DRM_FORMAT_XRGB4444:
 		bpp = FSL_DCU_ARGB4444;
 		break;
 	case DRM_FORMAT_ARGB1555:
 		alpha = DCU_LAYER_AB_WHOLE_FRAME;
-		/* fall-through */
+		fallthrough;
 	case DRM_FORMAT_XRGB1555:
 		bpp = FSL_DCU_ARGB1555;
 		break;
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 8c55f5bee9ab..f4053dd6bde9 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -712,7 +712,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			switch (intel_dsi->pixel_format) {
 			default:
 				MISSING_CASE(intel_dsi->pixel_format);
-				/* fallthrough */
+				fallthrough;
 			case MIPI_DSI_FMT_RGB565:
 				tmp |= PIX_FMT_RGB565;
 				break;
@@ -739,7 +739,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			switch (intel_dsi->video_mode_format) {
 			default:
 				MISSING_CASE(intel_dsi->video_mode_format);
-				/* fallthrough */
+				fallthrough;
 			case VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS:
 				tmp |= VIDEO_MODE_SYNC_EVENT;
 				break;
@@ -792,7 +792,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		switch (pipe) {
 		default:
 			MISSING_CASE(pipe);
-			/* fallthrough */
+			fallthrough;
 		case PIPE_A:
 			tmp |= TRANS_DDI_EDP_INPUT_A_ON;
 			break;
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index c53c85d38fa5..a0a41ec5c341 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -905,7 +905,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 			drm_dbg_kms(&dev_priv->drm,
 				    "VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
 				    psr_table->tp1_wakeup_time);
-			/* fallthrough */
+			fallthrough;
 		case 2:
 			dev_priv->vbt.psr.tp1_wakeup_time_us = 2500;
 			break;
@@ -925,7 +925,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 			drm_dbg_kms(&dev_priv->drm,
 				    "VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
 				    psr_table->tp2_tp3_wakeup_time);
-			/* fallthrough */
+			fallthrough;
 		case 2:
 			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500;
 		break;
@@ -1775,7 +1775,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 		switch (child->hdmi_max_data_rate) {
 		default:
 			MISSING_CASE(child->hdmi_max_data_rate);
-			/* fall through */
+			fallthrough;
 		case HDMI_MAX_DATA_RATE_PLATFORM:
 			max_tmds_clock = 0;
 			break;
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index bb91dace304a..577c4441f32d 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -326,7 +326,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv,
 	default:
 		drm_err(&dev_priv->drm,
 			"Unknown pnv display core clock 0x%04x\n", gcfgc);
-		/* fall through */
+		fallthrough;
 	case GC_DISPLAY_CLOCK_133_MHZ_PNV:
 		cdclk_config->cdclk = 133333;
 		break;
@@ -766,7 +766,7 @@ static void bdw_set_cdclk(struct drm_i915_private *dev_priv,
 	switch (cdclk) {
 	default:
 		MISSING_CASE(cdclk);
-		/* fall through */
+		fallthrough;
 	case 337500:
 		val |= LCPLL_CLK_FREQ_337_5_BDW;
 		break;
@@ -1042,7 +1042,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 		drm_WARN_ON(&dev_priv->drm,
 			    cdclk != dev_priv->cdclk.hw.bypass);
 		drm_WARN_ON(&dev_priv->drm, vco != 0);
-		/* fall through */
+		fallthrough;
 	case 308571:
 	case 337500:
 		freq_select = CDCLK_FREQ_337_308;
@@ -1333,7 +1333,7 @@ static void icl_readout_refclk(struct drm_i915_private *dev_priv,
 	switch (dssm) {
 	default:
 		MISSING_CASE(dssm);
-		/* fall through */
+		fallthrough;
 	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
 		cdclk_config->ref = 24000;
 		break;
@@ -1561,7 +1561,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 		drm_WARN_ON(&dev_priv->drm,
 			    cdclk != dev_priv->cdclk.hw.bypass);
 		drm_WARN_ON(&dev_priv->drm, vco != 0);
-		/* fall through */
+		fallthrough;
 	case 2:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
 		break;
@@ -2677,7 +2677,7 @@ void intel_update_cdclk(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		intel_de_write(dev_priv, GMBUSFREQ_VLV,
-		               DIV_ROUND_UP(dev_priv->cdclk.hw.cdclk, 1000));
+			       DIV_ROUND_UP(dev_priv->cdclk.hw.cdclk, 1000));
 }
 
 static int cnp_rawclk(struct drm_i915_private *dev_priv)
@@ -2903,9 +2903,10 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.get_cdclk = i85x_get_cdclk;
 	else if (IS_I845G(dev_priv))
 		dev_priv->display.get_cdclk = fixed_200mhz_get_cdclk;
-	else { /* 830 */
-		drm_WARN(&dev_priv->drm, !IS_I830(dev_priv),
-			 "Unknown platform. Assuming 133 MHz CDCLK\n");
+	else if (IS_I830(dev_priv))
+		dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk;
+
+	if (drm_WARN(&dev_priv->drm, !dev_priv->display.get_cdclk,
+		     "Unknown platform. Assuming 133 MHz CDCLK\n"))
 		dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk;
-	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 5731806e4cee..6b31fde4be16 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -17,8 +17,8 @@ struct intel_atomic_state;
 struct intel_crtc_state;
 
 struct intel_cdclk_vals {
-	u16 refclk;
 	u32 cdclk;
+	u16 refclk;
 	u8 divider;	/* CD2X divider * 2 */
 	u8 ratio;
 };
diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c
index eccaa79cb4a9..157d8c8c605a 100644
--- a/drivers/gpu/drm/i915/display/intel_combo_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c
@@ -52,7 +52,7 @@ cnl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
 	switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) {
 	default:
 		MISSING_CASE(val);
-		/* fall through */
+		fallthrough;
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
 		procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0];
 		break;
@@ -258,7 +258,7 @@ static bool phy_is_master(struct drm_i915_private *dev_priv, enum phy phy)
 static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv,
 				       enum phy phy)
 {
-	bool ret;
+	bool ret = true;
 	u32 expected_val = 0;
 
 	if (!icl_combo_phy_enabled(dev_priv, phy))
@@ -276,7 +276,7 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv,
 				     DCC_MODE_SELECT_CONTINUOSLY);
 	}
 
-	ret = cnl_verify_procmon_ref_values(dev_priv, phy);
+	ret &= cnl_verify_procmon_ref_values(dev_priv, phy);
 
 	if (phy_is_master(dev_priv, phy)) {
 		ret &= check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW8(phy),
@@ -320,7 +320,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv,
 			break;
 		default:
 			MISSING_CASE(lane_count);
-			/* fall-through */
+			fallthrough;
 		case 4:
 			lane_mask = PWR_UP_ALL_LANES;
 			break;
@@ -337,7 +337,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv,
 			break;
 		default:
 			MISSING_CASE(lane_count);
-			/* fall-through */
+			fallthrough;
 		case 4:
 			lane_mask = PWR_UP_ALL_LANES;
 			break;
diff --git a/drivers/gpu/drm/i915/display/intel_csr.c b/drivers/gpu/drm/i915/display/intel_csr.c
index f22a7645c249..d5db16764619 100644
--- a/drivers/gpu/drm/i915/display/intel_csr.c
+++ b/drivers/gpu/drm/i915/display/intel_csr.c
@@ -40,12 +40,12 @@
 
 #define GEN12_CSR_MAX_FW_SIZE		ICL_CSR_MAX_FW_SIZE
 
-#define RKL_CSR_PATH			"i915/rkl_dmc_ver2_01.bin"
-#define RKL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 1)
+#define RKL_CSR_PATH			"i915/rkl_dmc_ver2_02.bin"
+#define RKL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 2)
 MODULE_FIRMWARE(RKL_CSR_PATH);
 
-#define TGL_CSR_PATH			"i915/tgl_dmc_ver2_06.bin"
-#define TGL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 6)
+#define TGL_CSR_PATH			"i915/tgl_dmc_ver2_08.bin"
+#define TGL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 8)
 #define TGL_CSR_MAX_FW_SIZE		0x6000
 MODULE_FIRMWARE(TGL_CSR_PATH);
 
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2c484b55bcdf..19ac6b2a664c 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -706,6 +706,42 @@ static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr2[] =
 	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
 };
 
+static const struct cnl_ddi_buf_trans tgl_uy_combo_phy_ddi_translations_dp_hbr2[] = {
+						/* NT mV Trans mV db    */
+	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
+	{ 0xA, 0x4F, 0x36, 0x00, 0x09 },	/* 350   500      3.1   */
+	{ 0xC, 0x60, 0x32, 0x00, 0x0D },	/* 350   700      6.0   */
+	{ 0xC, 0x7F, 0x2D, 0x00, 0x12 },	/* 350   900      8.2   */
+	{ 0xC, 0x47, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
+	{ 0xC, 0x6F, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
+	{ 0x6, 0x7D, 0x32, 0x00, 0x0D },	/* 500   900      5.1   */
+	{ 0x6, 0x60, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
+	{ 0x6, 0x7F, 0x34, 0x00, 0x0B },	/* 600   900      3.5   */
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
+};
+
+/*
+ * Cloned the HOBL entry to comply with the voltage and pre-emphasis entries
+ * that DisplayPort specification requires
+ */
+static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_edp_hbr2_hobl[] = {
+						/* VS	pre-emp	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	1	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	2	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	3	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	1	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	2	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	1	*/
+};
+
+static bool is_hobl_buf_trans(const struct cnl_ddi_buf_trans *table)
+{
+	return table == tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
+}
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
 {
@@ -1050,9 +1086,26 @@ static const struct cnl_ddi_buf_trans *
 tgl_get_combo_buf_trans(struct intel_encoder *encoder, int type, int rate,
 			int *n_entries)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.hobl) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+		if (!intel_dp->hobl_failed && rate <= 540000) {
+			/* Same table applies to TGL, RKL and DG1 */
+			*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_edp_hbr2_hobl);
+			return tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
+		}
+	}
+
 	if (type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_EDP) {
 		return icl_get_combo_buf_trans(encoder, type, rate, n_entries);
 	} else if (rate > 270000) {
+		if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) {
+			*n_entries = ARRAY_SIZE(tgl_uy_combo_phy_ddi_translations_dp_hbr2);
+			return tgl_uy_combo_phy_ddi_translations_dp_hbr2;
+		}
+
 		*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2);
 		return tgl_combo_phy_ddi_translations_dp_hbr2;
 	}
@@ -1888,7 +1941,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
 		default:
 			MISSING_CASE(tmp & TRANS_DDI_EDP_INPUT_MASK);
-			/* fallthrough */
+			fallthrough;
 		case TRANS_DDI_EDP_INPUT_A_ON:
 		case TRANS_DDI_EDP_INPUT_A_ONOFF:
 			*pipe_mask = BIT(PIPE_A);
@@ -2392,6 +2445,15 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder,
 		level = n_entries - 1;
 	}
 
+	if (type == INTEL_OUTPUT_EDP) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+		val = EDP4K2K_MODE_OVRD_EN | EDP4K2K_MODE_OVRD_OPTIMIZED;
+		intel_dp->hobl_active = is_hobl_buf_trans(ddi_translations);
+		intel_de_rmw(dev_priv, ICL_PORT_CL_DW10(phy), val,
+			     intel_dp->hobl_active ? val : 0);
+	}
+
 	/* Set PORT_TX_DW5 */
 	val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy));
 	val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK |
@@ -2802,7 +2864,9 @@ hsw_set_signal_levels(struct intel_dp *intel_dp)
 static u32 icl_dpclka_cfgcr0_clk_off(struct drm_i915_private *dev_priv,
 				     enum phy phy)
 {
-	if (intel_phy_is_combo(dev_priv, phy)) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		return RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
+	} else if (intel_phy_is_combo(dev_priv, phy)) {
 		return ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 	} else if (intel_phy_is_tc(dev_priv, phy)) {
 		enum tc_port tc_port = intel_port_to_tc(dev_priv,
@@ -2829,6 +2893,16 @@ static void icl_map_plls_to_ports(struct intel_encoder *encoder,
 		    (val & icl_dpclka_cfgcr0_clk_off(dev_priv, phy)) == 0);
 
 	if (intel_phy_is_combo(dev_priv, phy)) {
+		u32 mask, sel;
+
+		if (IS_ROCKETLAKE(dev_priv)) {
+			mask = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			sel = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		} else {
+			mask = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			sel = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		}
+
 		/*
 		 * Even though this register references DDIs, note that we
 		 * want to pass the PHY rather than the port (DDI).  For
@@ -2839,8 +2913,8 @@ static void icl_map_plls_to_ports(struct intel_encoder *encoder,
 		 *   Clock Select chooses the PLL for both DDIA and DDID and
 		 *   drives port A in all cases."
 		 */
-		val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
-		val |= ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		val &= ~mask;
+		val |= sel;
 		intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
 		intel_de_posting_read(dev_priv, ICL_DPCLKA_CFGCR0);
 	}
@@ -4037,8 +4111,7 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 			intel_wait_ddi_buf_idle(dev_priv, port);
 	}
 
-	dp_tp_ctl = DP_TP_CTL_ENABLE |
-		    DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
+	dp_tp_ctl = DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_PAT1;
 	if (intel_dp->link_mst)
 		dp_tp_ctl |= DP_TP_CTL_MODE_MST;
 	else {
@@ -4061,16 +4134,10 @@ static void intel_ddi_set_link_train(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	u8 train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
 	u32 temp;
 
 	temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
 
-	if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
-		temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
-	else
-		temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
-
 	temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
 	switch (dp_train_pat & train_pat_mask) {
 	case DP_TRAINING_PATTERN_DISABLE:
@@ -4091,9 +4158,6 @@ static void intel_ddi_set_link_train(struct intel_dp *intel_dp,
 	}
 
 	intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, temp);
-
-	intel_de_write(dev_priv, DDI_BUF_CTL(port), intel_dp->DP);
-	intel_de_posting_read(dev_priv, DDI_BUF_CTL(port));
 }
 
 static void intel_ddi_set_idle_link_train(struct intel_dp *intel_dp)
@@ -4268,7 +4332,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 			pipe_config->hdmi_scrambling = true;
 		if (temp & TRANS_DDI_HIGH_TMDS_CHAR_RATE)
 			pipe_config->hdmi_high_tmds_clock_ratio = true;
-		/* fall through */
+		fallthrough;
 	case TRANS_DDI_MODE_SELECT_DVI:
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_HDMI);
 		pipe_config->lane_count = 4;
@@ -4878,6 +4942,13 @@ intel_ddi_max_lanes(struct intel_digital_port *dig_port)
 	return max_lanes;
 }
 
+static bool hti_uses_phy(struct drm_i915_private *i915, enum phy phy)
+{
+	return i915->hti_state & HDPORT_ENABLED &&
+		(i915->hti_state & HDPORT_PHY_USED_DP(phy) ||
+		 i915->hti_state & HDPORT_PHY_USED_HDMI(phy));
+}
+
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 {
 	struct intel_digital_port *dig_port;
@@ -4885,6 +4956,18 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	bool init_hdmi, init_dp, init_lspcon = false;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
+	/*
+	 * On platforms with HTI (aka HDPORT), if it's enabled at boot it may
+	 * have taken over some of the PHYs and made them unavailable to the
+	 * driver.  In that case we should skip initializing the corresponding
+	 * outputs.
+	 */
+	if (hti_uses_phy(dev_priv, phy)) {
+		drm_dbg_kms(&dev_priv->drm, "PORT %c / PHY %c reserved by HTI\n",
+			    port_name(port), phy_name(phy));
+		return;
+	}
+
 	init_hdmi = intel_bios_port_supports_dvi(dev_priv, port) ||
 		intel_bios_port_supports_hdmi(dev_priv, port);
 	init_dp = intel_bios_port_supports_dp(dev_priv, port);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 729ec6e0d43a..ddb588f863f8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -47,6 +47,7 @@
 #include "display/intel_ddi.h"
 #include "display/intel_dp.h"
 #include "display/intel_dp_mst.h"
+#include "display/intel_dpll_mgr.h"
 #include "display/intel_dsi.h"
 #include "display/intel_dvo.h"
 #include "display/intel_gmbus.h"
@@ -2029,12 +2030,12 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 		if (is_ccs_plane(fb, color_plane))
 			return 128;
-		/* fall through */
+		fallthrough;
 	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		if (is_ccs_plane(fb, color_plane))
 			return 64;
-		/* fall through */
+		fallthrough;
 	case I915_FORMAT_MOD_Y_TILED:
 		if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv))
 			return 128;
@@ -2043,7 +2044,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 		if (is_ccs_plane(fb, color_plane))
 			return 128;
-		/* fall through */
+		fallthrough;
 	case I915_FORMAT_MOD_Yf_TILED:
 		switch (cpp) {
 		case 1:
@@ -2185,7 +2186,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		if (is_semiplanar_uv_plane(fb, color_plane))
 			return intel_tile_row_size(fb, color_plane);
-		/* Fall-through */
+		fallthrough;
 	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		return 16 * 1024;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
@@ -2194,7 +2195,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 		if (INTEL_GEN(dev_priv) >= 12 &&
 		    is_semiplanar_uv_plane(fb, color_plane))
 			return intel_tile_row_size(fb, color_plane);
-		/* Fall-through */
+		fallthrough;
 	case I915_FORMAT_MOD_Yf_TILED:
 		return 1 * 1024 * 1024;
 	default:
@@ -2310,7 +2311,7 @@ err:
 
 void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags)
 {
-	i915_gem_object_lock(vma->obj);
+	i915_gem_object_lock(vma->obj, NULL);
 	if (flags & PLANE_HAS_FENCE)
 		i915_vma_unpin_fence(vma);
 	i915_gem_object_unpin_from_display_plane(vma);
@@ -3450,7 +3451,7 @@ initial_plane_vma(struct drm_i915_private *i915,
 	if (IS_ERR(vma))
 		goto err_obj;
 
-	if (i915_ggtt_pin(vma, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base))
+	if (i915_ggtt_pin(vma, NULL, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base))
 		goto err_obj;
 
 	if (i915_gem_object_is_tiled(obj) &&
@@ -3761,6 +3762,44 @@ static int glk_max_plane_width(const struct drm_framebuffer *fb,
 	}
 }
 
+static int icl_min_plane_width(const struct drm_framebuffer *fb)
+{
+	/* Wa_14011264657, Wa_14011050563: gen11+ */
+	switch (fb->format->format) {
+	case DRM_FORMAT_C8:
+		return 18;
+	case DRM_FORMAT_RGB565:
+		return 10;
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_XVYU2101010:
+	case DRM_FORMAT_Y212:
+	case DRM_FORMAT_Y216:
+		return 6;
+	case DRM_FORMAT_NV12:
+		return 20;
+	case DRM_FORMAT_P010:
+	case DRM_FORMAT_P012:
+	case DRM_FORMAT_P016:
+		return 12;
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_XBGR16161616F:
+	case DRM_FORMAT_ARGB16161616F:
+	case DRM_FORMAT_ABGR16161616F:
+	case DRM_FORMAT_XVYU12_16161616:
+	case DRM_FORMAT_XVYU16161616:
+		return 4;
+	default:
+		return 1;
+	}
+}
+
 static int icl_max_plane_width(const struct drm_framebuffer *fb,
 			       int color_plane,
 			       unsigned int rotation)
@@ -3843,29 +3882,31 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	int y = plane_state->uapi.src.y1 >> 16;
 	int w = drm_rect_width(&plane_state->uapi.src) >> 16;
 	int h = drm_rect_height(&plane_state->uapi.src) >> 16;
-	int max_width;
-	int max_height;
-	u32 alignment;
-	u32 offset;
+	int max_width, min_width, max_height;
+	u32 alignment, offset;
 	int aux_plane = intel_main_to_aux_plane(fb, 0);
 	u32 aux_offset = plane_state->color_plane[aux_plane].offset;
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
 		max_width = icl_max_plane_width(fb, 0, rotation);
-	else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		min_width = icl_min_plane_width(fb);
+	} else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		max_width = glk_max_plane_width(fb, 0, rotation);
-	else
+		min_width = 1;
+	} else {
 		max_width = skl_max_plane_width(fb, 0, rotation);
+		min_width = 1;
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		max_height = icl_max_plane_height();
 	else
 		max_height = skl_max_plane_height();
 
-	if (w > max_width || h > max_height) {
+	if (w > max_width || w < min_width || h > max_height) {
 		drm_dbg_kms(&dev_priv->drm,
-			    "requested Y/RGB source size %dx%d too big (limit %dx%d)\n",
-			    w, h, max_width, max_height);
+			    "requested Y/RGB source size %dx%d outside limits (min: %dx1 max: %dx%d)\n",
+			    w, h, min_width, max_width, max_height);
 		return -EINVAL;
 	}
 
@@ -6211,7 +6252,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ARGB16161616F:
 		if (INTEL_GEN(dev_priv) >= 11)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		drm_dbg_kms(&dev_priv->drm,
 			    "[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n",
@@ -10802,9 +10843,18 @@ static void icl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
 	u32 temp;
 
 	if (intel_phy_is_combo(dev_priv, phy)) {
-		temp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0) &
-			ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
-		id = temp >> ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		u32 mask, shift;
+
+		if (IS_ROCKETLAKE(dev_priv)) {
+			mask = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			shift = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		} else {
+			mask = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			shift = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		}
+
+		temp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0) & mask;
+		id = temp >> shift;
 		port_dpll_id = ICL_PORT_DPLL_DEFAULT;
 	} else if (intel_phy_is_tc(dev_priv, phy)) {
 		u32 clk_sel = intel_de_read(dev_priv, DDI_CLK_SEL(port)) & DDI_CLK_SEL_MASK;
@@ -10896,7 +10946,7 @@ static void hsw_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
 		break;
 	default:
 		MISSING_CASE(ddi_pll_sel);
-		/* fall through */
+		fallthrough;
 	case PORT_CLK_SEL_NONE:
 		return;
 	}
@@ -10956,10 +11006,10 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 			drm_WARN(dev, 1,
 				 "unknown pipe linked to transcoder %s\n",
 				 transcoder_name(panel_transcoder));
-			/* fall through */
+			fallthrough;
 		case TRANS_DDI_EDP_INPUT_A_ONOFF:
 			force_thru = true;
-			/* fall through */
+			fallthrough;
 		case TRANS_DDI_EDP_INPUT_A_ON:
 			trans_pipe = PIPE_A;
 			break;
@@ -12760,6 +12810,9 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 
 	}
 
+	if (!mode_changed)
+		intel_psr2_sel_fetch_update(state, crtc);
+
 	return 0;
 }
 
@@ -13183,7 +13236,7 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state)
 		case INTEL_OUTPUT_DDI:
 			if (drm_WARN_ON(dev, !HAS_DDI(to_i915(dev))))
 				break;
-			/* else, fall through */
+			fallthrough;
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_HDMI:
 		case INTEL_OUTPUT_EDP:
@@ -14930,7 +14983,7 @@ static int intel_atomic_check(struct drm_device *dev,
 	if (any_ms && !check_digital_port_conflicts(state)) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "rejecting conflicting digital port configuration\n");
-		ret = EINVAL;
+		ret = -EINVAL;
 		goto fail;
 	}
 
@@ -14956,12 +15009,6 @@ static int intel_atomic_check(struct drm_device *dev,
 	if (dev_priv->wm.distrust_bios_wm)
 		any_ms = true;
 
-	if (any_ms) {
-		ret = intel_modeset_checks(state);
-		if (ret)
-			goto fail;
-	}
-
 	intel_fbc_choose_crtc(dev_priv, state);
 	ret = calc_watermark_data(state);
 	if (ret)
@@ -14976,6 +15023,10 @@ static int intel_atomic_check(struct drm_device *dev,
 		goto fail;
 
 	if (any_ms) {
+		ret = intel_modeset_checks(state);
+		if (ret)
+			goto fail;
+
 		ret = intel_modeset_calc_cdclk(state);
 		if (ret)
 			return ret;
@@ -15136,6 +15187,8 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 
 		if (new_crtc_state->update_pipe)
 			intel_pipe_fastset(old_crtc_state, new_crtc_state);
+
+		intel_psr2_program_trans_man_trk_ctl(new_crtc_state);
 	}
 
 	if (dev_priv->display.atomic_update_watermarks)
@@ -17139,7 +17192,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	if (!intel_fb->frontbuffer)
 		return -ENOMEM;
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	tiling = i915_gem_object_get_tiling(obj);
 	stride = i915_gem_object_get_stride(obj);
 	i915_gem_object_unlock(obj);
@@ -17894,6 +17947,13 @@ int intel_modeset_init(struct drm_i915_private *i915)
 	if (i915->max_cdclk_freq == 0)
 		intel_update_max_cdclk(i915);
 
+	/*
+	 * If the platform has HTI, we need to find out whether it has reserved
+	 * any display resources before we create our display outputs.
+	 */
+	if (INTEL_INFO(i915)->display.has_hti)
+		i915->hti_state = intel_de_read(i915, HDPORT_STATE);
+
 	/* Just disable it once at startup */
 	intel_vga_disable(i915);
 	intel_setup_outputs(i915);
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 3644752cc5ec..f549381048b3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -417,6 +417,9 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 			su_blocks = su_blocks >> PSR2_SU_STATUS_SHIFT(frame);
 			seq_printf(m, "%d\t%d\n", frame, su_blocks);
 		}
+
+		seq_printf(m, "PSR2 selective fetch: %s\n",
+			   enableddisabled(psr->psr2_sel_fetch_enabled));
 	}
 
 unlock:
@@ -2044,9 +2047,12 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability);
 static int i915_lpsp_capability_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
-	struct intel_encoder *encoder =
-			intel_attached_encoder(to_intel_connector(connector));
 	struct drm_i915_private *i915 = to_i915(connector->dev);
+	struct intel_encoder *encoder;
+
+	encoder = intel_attached_encoder(to_intel_connector(connector));
+	if (!encoder)
+		return -ENODEV;
 
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 0c713e83274d..7946c6af4b1e 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -3927,12 +3927,13 @@ tgl_tc_cold_request(struct drm_i915_private *i915, bool block)
 	int ret;
 
 	while (1) {
-		u32 low_val = 0, high_val;
+		u32 low_val;
+		u32 high_val = 0;
 
 		if (block)
-			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ;
+			low_val = TGL_PCODE_EXIT_TCCOLD_DATA_L_BLOCK_REQ;
 		else
-			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ;
+			low_val = TGL_PCODE_EXIT_TCCOLD_DATA_L_UNBLOCK_REQ;
 
 		/*
 		 * Spec states that we should timeout the request after 200us
@@ -3951,8 +3952,7 @@ tgl_tc_cold_request(struct drm_i915_private *i915, bool block)
 		if (++tries == 3)
 			break;
 
-		if (ret == -EAGAIN)
-			msleep(1);
+		msleep(1);
 	}
 
 	if (ret)
@@ -4147,6 +4147,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
+		.name = "TC cold off",
+		.domains = TGL_TC_COLD_OFF_POWER_DOMAINS,
+		.ops = &tgl_tc_cold_off_ops,
+		.id = DISP_PW_ID_NONE,
+	},
+	{
 		.name = "AUX A",
 		.domains = TGL_AUX_A_IO_POWER_DOMAINS,
 		.ops = &icl_aux_power_well_ops,
@@ -4332,12 +4338,6 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 			.hsw.irq_pipe_mask = BIT(PIPE_D),
 		},
 	},
-	{
-		.name = "TC cold off",
-		.domains = TGL_TC_COLD_OFF_POWER_DOMAINS,
-		.ops = &tgl_tc_cold_off_ops,
-		.id = DISP_PW_ID_NONE,
-	},
 };
 
 static const struct i915_power_well_desc rkl_power_wells[] = {
@@ -5240,10 +5240,10 @@ struct buddy_page_mask {
 };
 
 static const struct buddy_page_mask tgl_buddy_page_masks[] = {
-	{ .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE },
 	{ .num_channels = 1, .type = INTEL_DRAM_DDR4,   .page_mask = 0xF },
 	{ .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C },
 	{ .num_channels = 2, .type = INTEL_DRAM_DDR4,   .page_mask = 0x1F },
+	{ .num_channels = 4, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x38 },
 	{}
 };
 
@@ -5302,6 +5302,12 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
+	/* Wa_14011294188:ehl,jsl,tgl,rkl */
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_JSP &&
+	    INTEL_PCH_TYPE(dev_priv) < PCH_DG1)
+		intel_de_rmw(dev_priv, SOUTH_DSPCLK_GATE_D, 0,
+			     PCH_DPMGUNIT_CLOCK_GATE_DISABLE);
+
 	/* 1. Enable PCH reset handshake. */
 	intel_pch_reset_handshake(dev_priv, !HAS_PCH_NOP(dev_priv));
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index e8f809161c75..9349b15afff6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -931,6 +931,7 @@ struct intel_crtc_state {
 
 	bool has_psr;
 	bool has_psr2;
+	bool enable_psr2_sel_fetch;
 	u32 dc3co_exitline;
 
 	/*
@@ -1073,6 +1074,8 @@ struct intel_crtc_state {
 
 	/* For DSB related info */
 	struct intel_dsb *dsb;
+
+	u32 psr2_man_track_ctl;
 };
 
 enum intel_pipe_crc_source {
@@ -1375,6 +1378,9 @@ struct intel_dp {
 
 	/* Display stream compression testing */
 	bool force_dsc_en;
+
+	bool hobl_failed;
+	bool hobl_active;
 };
 
 enum lspcon_vendor {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 79c27f91f42c..284b15f84592 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4449,62 +4449,6 @@ intel_dp_link_down(struct intel_encoder *encoder,
 	}
 }
 
-static void
-intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp)
-{
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 dpcd_ext[6];
-
-	/*
-	 * Prior to DP1.3 the bit represented by
-	 * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
-	 * if it is set DP_DPCD_REV at 0000h could be at a value less than
-	 * the true capability of the panel. The only way to check is to
-	 * then compare 0000h and 2200h.
-	 */
-	if (!(intel_dp->dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
-	      DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
-		return;
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_DP13_DPCD_REV,
-			     &dpcd_ext, sizeof(dpcd_ext)) != sizeof(dpcd_ext)) {
-		drm_err(&i915->drm,
-			"DPCD failed read at extended capabilities\n");
-		return;
-	}
-
-	if (intel_dp->dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
-		drm_dbg_kms(&i915->drm,
-			    "DPCD extended DPCD rev less than base DPCD rev\n");
-		return;
-	}
-
-	if (!memcmp(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext)))
-		return;
-
-	drm_dbg_kms(&i915->drm, "Base DPCD: %*ph\n",
-		    (int)sizeof(intel_dp->dpcd), intel_dp->dpcd);
-
-	memcpy(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext));
-}
-
-bool
-intel_dp_read_dpcd(struct intel_dp *intel_dp)
-{
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, 0x000, intel_dp->dpcd,
-			     sizeof(intel_dp->dpcd)) < 0)
-		return false; /* aux transfer failed */
-
-	intel_dp_extended_receiver_capabilities(intel_dp);
-
-	drm_dbg_kms(&i915->drm, "DPCD: %*ph\n", (int)sizeof(intel_dp->dpcd),
-		    intel_dp->dpcd);
-
-	return intel_dp->dpcd[DP_DPCD_REV] != 0;
-}
-
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 {
 	u8 dprx = 0;
@@ -4563,7 +4507,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	/* this function is meant to be called only once */
 	drm_WARN_ON(&dev_priv->drm, intel_dp->dpcd[DP_DPCD_REV] != 0);
 
-	if (!intel_dp_read_dpcd(intel_dp))
+	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd) != 0)
 		return false;
 
 	drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
@@ -4634,11 +4578,23 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	return true;
 }
 
+static bool
+intel_dp_has_sink_count(struct intel_dp *intel_dp)
+{
+	if (!intel_dp->attached_connector)
+		return false;
+
+	return drm_dp_read_sink_count_cap(&intel_dp->attached_connector->base,
+					  intel_dp->dpcd,
+					  &intel_dp->desc);
+}
 
 static bool
 intel_dp_get_dpcd(struct intel_dp *intel_dp)
 {
-	if (!intel_dp_read_dpcd(intel_dp))
+	int ret;
+
+	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd))
 		return false;
 
 	/*
@@ -4653,18 +4609,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		intel_dp_set_common_rates(intel_dp);
 	}
 
-	/*
-	 * Some eDP panels do not set a valid value for sink count, that is why
-	 * it don't care about read it here and in intel_edp_init_dpcd().
-	 */
-	if (!intel_dp_is_edp(intel_dp) &&
-	    !drm_dp_has_quirk(&intel_dp->desc, 0,
-			      DP_DPCD_QUIRK_NO_SINK_COUNT)) {
-		u8 count;
-		ssize_t r;
-
-		r = drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_COUNT, &count);
-		if (r < 1)
+	if (intel_dp_has_sink_count(intel_dp)) {
+		ret = drm_dp_read_sink_count(&intel_dp->aux);
+		if (ret < 0)
 			return false;
 
 		/*
@@ -4672,7 +4619,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		 * a member variable in intel_dp will track any changes
 		 * between short pulse interrupts.
 		 */
-		intel_dp->sink_count = DP_GET_SINK_COUNT(count);
+		intel_dp->sink_count = ret;
 
 		/*
 		 * SINK_COUNT == 0 and DOWNSTREAM_PORT_PRESENT == 1 implies that
@@ -4685,32 +4632,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 			return false;
 	}
 
-	if (!drm_dp_is_branch(intel_dp->dpcd))
-		return true; /* native DP sink */
-
-	if (intel_dp->dpcd[DP_DPCD_REV] == 0x10)
-		return true; /* no per-port downstream info */
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_DOWNSTREAM_PORT_0,
-			     intel_dp->downstream_ports,
-			     DP_MAX_DOWNSTREAM_PORTS) < 0)
-		return false; /* downstream port status fetch failed */
-
-	return true;
-}
-
-static bool
-intel_dp_sink_can_mst(struct intel_dp *intel_dp)
-{
-	u8 mstm_cap;
-
-	if (intel_dp->dpcd[DP_DPCD_REV] < 0x12)
-		return false;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_MSTM_CAP, &mstm_cap) != 1)
-		return false;
-
-	return mstm_cap & DP_MST_CAP;
+	return drm_dp_read_downstream_info(&intel_dp->aux, intel_dp->dpcd,
+					   intel_dp->downstream_ports) == 0;
 }
 
 static bool
@@ -4720,7 +4643,7 @@ intel_dp_can_mst(struct intel_dp *intel_dp)
 
 	return i915->params.enable_dp_mst &&
 		intel_dp->can_mst &&
-		intel_dp_sink_can_mst(intel_dp);
+		drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd);
 }
 
 static void
@@ -4729,7 +4652,7 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_encoder *encoder =
 		&dp_to_dig_port(intel_dp)->base;
-	bool sink_can_mst = intel_dp_sink_can_mst(intel_dp);
+	bool sink_can_mst = drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd);
 
 	drm_dbg_kms(&i915->drm,
 		    "[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n",
@@ -5963,9 +5886,8 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 		return connector_status_connected;
 
 	/* If we're HPD-aware, SINK_COUNT changes dynamically */
-	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
+	if (intel_dp_has_sink_count(intel_dp) &&
 	    intel_dp->downstream_ports[0] & DP_DS_PORT_HPD) {
-
 		return intel_dp->sink_count ?
 		connector_status_connected : connector_status_disconnected;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index b901ab850cbd..0a3af3410d52 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -99,7 +99,6 @@ bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
 
-bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
 int intel_dp_link_required(int pixel_clock, int bpp);
 int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index a23ed7290843..f2c8b56be9ea 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -410,10 +410,17 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		    intel_connector->base.base.id,
 		    intel_connector->base.name,
 		    intel_dp->link_rate, intel_dp->lane_count);
-	if (!intel_dp_get_link_train_fallback_values(intel_dp,
-						     intel_dp->link_rate,
-						     intel_dp->lane_count))
-		/* Schedule a Hotplug Uevent to userspace to start modeset */
-		schedule_work(&intel_connector->modeset_retry_work);
-	return;
+
+	if (intel_dp->hobl_active) {
+		drm_dbg_kms(&dp_to_i915(intel_dp)->drm,
+			    "Link Training failed with HOBL active, not enabling it from now on");
+		intel_dp->hobl_failed = true;
+	} else if (intel_dp_get_link_train_fallback_values(intel_dp,
+							   intel_dp->link_rate,
+							   intel_dp->lane_count)) {
+		return;
+	}
+
+	/* Schedule a Hotplug Uevent to userspace to start modeset */
+	schedule_work(&intel_connector->modeset_retry_work);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index aeb6ee395cce..c9013f8f766f 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -892,7 +892,7 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv,
 			refclk = dev_priv->dpll.ref_clks.nssc;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case WRPLL_REF_PCH_SSC:
 		/*
 		 * We could calculate spread here, but our checking
@@ -2977,7 +2977,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state,
 		switch (dev_priv->dpll.ref_clks.nssc) {
 		default:
 			MISSING_CASE(dev_priv->dpll.ref_clks.nssc);
-			/* fall-through */
+			fallthrough;
 		case 19200:
 			*pll_params = tgl_tbt_pll_19_2MHz_values;
 			break;
@@ -2992,7 +2992,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state,
 		switch (dev_priv->dpll.ref_clks.nssc) {
 		default:
 			MISSING_CASE(dev_priv->dpll.ref_clks.nssc);
-			/* fall-through */
+			fallthrough;
 		case 19200:
 		case 38400:
 			*pll_params = icl_tbt_pll_19_2MHz_values;
@@ -3120,7 +3120,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 			switch (div1) {
 			default:
 				MISSING_CASE(div1);
-				/* fall through */
+				fallthrough;
 			case 2:
 				hsdiv = MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_2;
 				break;
@@ -3475,6 +3475,14 @@ static void icl_update_active_dpll(struct intel_atomic_state *state,
 	icl_set_active_port_dpll(crtc_state, port_dpll_id);
 }
 
+static u32 intel_get_hti_plls(struct drm_i915_private *i915)
+{
+	if (!(i915->hti_state & HDPORT_ENABLED))
+		return 0;
+
+	return REG_FIELD_GET(HDPORT_DPLL_USED_MASK, i915->hti_state);
+}
+
 static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc,
 				   struct intel_encoder *encoder)
@@ -3504,13 +3512,22 @@ static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 
 	icl_calc_dpll_state(dev_priv, &pll_params, &port_dpll->hw_state);
 
-	if (IS_ELKHARTLAKE(dev_priv) && port != PORT_A)
+	if (IS_ROCKETLAKE(dev_priv)) {
 		dpll_mask =
 			BIT(DPLL_ID_EHL_DPLL4) |
 			BIT(DPLL_ID_ICL_DPLL1) |
 			BIT(DPLL_ID_ICL_DPLL0);
-	else
+	} else if (IS_ELKHARTLAKE(dev_priv) && port != PORT_A) {
+		dpll_mask =
+			BIT(DPLL_ID_EHL_DPLL4) |
+			BIT(DPLL_ID_ICL_DPLL1) |
+			BIT(DPLL_ID_ICL_DPLL0);
+	} else {
 		dpll_mask = BIT(DPLL_ID_ICL_DPLL1) | BIT(DPLL_ID_ICL_DPLL0);
+	}
+
+	/* Eliminate DPLLs from consideration if reserved by HTI */
+	dpll_mask &= ~intel_get_hti_plls(dev_priv);
 
 	port_dpll->pll = intel_find_shared_dpll(state, crtc,
 						&port_dpll->hw_state,
@@ -3791,7 +3808,12 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	if (!(val & PLL_ENABLE))
 		goto out;
 
-	if (INTEL_GEN(dev_priv) >= 12) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		hw_state->cfgcr0 = intel_de_read(dev_priv,
+						 RKL_DPLL_CFGCR0(id));
+		hw_state->cfgcr1 = intel_de_read(dev_priv,
+						 RKL_DPLL_CFGCR1(id));
+	} else if (INTEL_GEN(dev_priv) >= 12) {
 		hw_state->cfgcr0 = intel_de_read(dev_priv,
 						 TGL_DPLL_CFGCR0(id));
 		hw_state->cfgcr1 = intel_de_read(dev_priv,
@@ -3844,7 +3866,10 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv,
 	const enum intel_dpll_id id = pll->info->id;
 	i915_reg_t cfgcr0_reg, cfgcr1_reg;
 
-	if (INTEL_GEN(dev_priv) >= 12) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		cfgcr0_reg = RKL_DPLL_CFGCR0(id);
+		cfgcr1_reg = RKL_DPLL_CFGCR1(id);
+	} else if (INTEL_GEN(dev_priv) >= 12) {
 		cfgcr0_reg = TGL_DPLL_CFGCR0(id);
 		cfgcr1_reg = TGL_DPLL_CFGCR1(id);
 	} else {
@@ -4276,6 +4301,21 @@ static const struct intel_dpll_mgr tgl_pll_mgr = {
 	.dump_hw_state = icl_dump_hw_state,
 };
 
+static const struct dpll_info rkl_plls[] = {
+	{ "DPLL 0", &combo_pll_funcs, DPLL_ID_ICL_DPLL0, 0 },
+	{ "DPLL 1", &combo_pll_funcs, DPLL_ID_ICL_DPLL1, 0 },
+	{ "DPLL 4", &combo_pll_funcs, DPLL_ID_EHL_DPLL4, 0 },
+	{ },
+};
+
+static const struct intel_dpll_mgr rkl_pll_mgr = {
+	.dpll_info = rkl_plls,
+	.get_dplls = icl_get_dplls,
+	.put_dplls = icl_put_dplls,
+	.update_ref_clks = icl_update_dpll_ref_clks,
+	.dump_hw_state = icl_dump_hw_state,
+};
+
 /**
  * intel_shared_dpll_init - Initialize shared DPLLs
  * @dev: drm device
@@ -4289,7 +4329,9 @@ void intel_shared_dpll_init(struct drm_device *dev)
 	const struct dpll_info *dpll_info;
 	int i;
 
-	if (INTEL_GEN(dev_priv) >= 12)
+	if (IS_ROCKETLAKE(dev_priv))
+		dpll_mgr = &rkl_pll_mgr;
+	else if (INTEL_GEN(dev_priv) >= 12)
 		dpll_mgr = &tgl_pll_mgr;
 	else if (IS_ELKHARTLAKE(dev_priv))
 		dpll_mgr = &ehl_pll_mgr;
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 24c3a0f212c6..135f5e8a4d70 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -424,6 +424,14 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 	fbc->no_fbc_reason = reason;
 }
 
+static u64 intel_fbc_cfb_base_max(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) >= 5 || IS_G4X(i915))
+		return BIT_ULL(28);
+	else
+		return BIT_ULL(32);
+}
+
 static int find_compression_threshold(struct drm_i915_private *dev_priv,
 				      struct drm_mm_node *node,
 				      unsigned int size,
@@ -442,6 +450,8 @@ static int find_compression_threshold(struct drm_i915_private *dev_priv,
 	else
 		end = U64_MAX;
 
+	end = min(end, intel_fbc_cfb_base_max(dev_priv));
+
 	/* HACK: This code depends on what we will do in *_enable_fbc. If that
 	 * code changes, this code needs to change as well.
 	 *
@@ -1416,6 +1426,13 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
+	/*
+	 * Fbc is causing random underruns in CI execution on TGL platforms.
+	 * Disabling the same while the problem is being debugged and analyzed.
+	 */
+	if (IS_TIGERLAKE(dev_priv))
+		return 0;
+
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 2979ed2588eb..d898b370d7a4 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -232,6 +232,8 @@ static void frontbuffer_release(struct kref *ref)
 	RCU_INIT_POINTER(obj->frontbuffer, NULL);
 	spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock);
 
+	i915_active_fini(&front->write);
+
 	i915_gem_object_put(obj);
 	kfree_rcu(front, rcu);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 89a4d294822d..1a0d49af2a08 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -336,8 +336,10 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 
 		/* Fill up the empty slots in sha_text and write it out */
 		sha_empty = sizeof(sha_text) - sha_leftovers;
-		for (j = 0; j < sha_empty; j++)
-			sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8);
+		for (j = 0; j < sha_empty; j++) {
+			u8 off = ((sizeof(sha_text) - j - 1 - sha_leftovers) * 8);
+			sha_text |= ksv[j] << off;
+		}
 
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
@@ -435,7 +437,7 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 		/* Write 32 bits of text */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_32);
-		sha_text |= bstatus[0] << 24 | bstatus[1] << 16;
+		sha_text |= bstatus[0] << 8 | bstatus[1];
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
 			return ret;
@@ -450,17 +452,29 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 				return ret;
 			sha_idx += sizeof(sha_text);
 		}
+
+		/*
+		 * Terminate the SHA-1 stream by hand. For the other leftover
+		 * cases this is appended by the hardware.
+		 */
+		intel_de_write(dev_priv, HDCP_REP_CTL,
+			       rep_ctl | HDCP_SHA1_TEXT_32);
+		sha_text = DRM_HDCP_SHA1_TERMINATOR << 24;
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
 	} else if (sha_leftovers == 3) {
-		/* Write 32 bits of text */
+		/* Write 32 bits of text (filled from LSB) */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_32);
-		sha_text |= bstatus[0] << 24;
+		sha_text |= bstatus[0];
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
 			return ret;
 		sha_idx += sizeof(sha_text);
 
-		/* Write 8 bits of text, 24 bits of M0 */
+		/* Write 8 bits of text (filled from LSB), 24 bits of M0 */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_8);
 		ret = intel_write_sha_text(dev_priv, bstatus[1]);
@@ -781,6 +795,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector)
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	enum port port = dig_port->base.port;
 	enum transcoder cpu_transcoder = hdcp->cpu_transcoder;
+	u32 repeater_ctl;
 	int ret;
 
 	drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP is being disabled...\n",
@@ -796,6 +811,11 @@ static int _intel_hdcp_disable(struct intel_connector *connector)
 		return -ETIMEDOUT;
 	}
 
+	repeater_ctl = intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder,
+						   port);
+	intel_de_write(dev_priv, HDCP_REP_CTL,
+		       intel_de_read(dev_priv, HDCP_REP_CTL) & ~repeater_ctl);
+
 	ret = hdcp->shim->toggle_signalling(dig_port, false);
 	if (ret) {
 		drm_err(&dev_priv->drm, "Failed to disable HDCP signalling\n");
diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index b781bf469644..dc1b35559afd 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -571,7 +571,7 @@ bool lspcon_init(struct intel_digital_port *dig_port)
 		return false;
 	}
 
-	if (!intel_dp_read_dpcd(dp)) {
+	if (drm_dp_read_dpcd_caps(&dp->aux, dp->dpcd) != 0) {
 		DRM_ERROR("LSPCON DPCD read failed\n");
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index bbde3b12c311..4072d7062efd 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -229,7 +229,7 @@ int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state,
 	case DRM_MODE_SCALE_NONE:
 		WARN_ON(adjusted_mode->crtc_hdisplay != crtc_state->pipe_src_w);
 		WARN_ON(adjusted_mode->crtc_vdisplay != crtc_state->pipe_src_h);
-		/* fall through */
+		fallthrough;
 	case DRM_MODE_SCALE_FULLSCREEN:
 		x = y = 0;
 		width = adjusted_mode->crtc_hdisplay;
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index bf9e320c547d..2b004ee9619c 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -553,6 +553,22 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 		val |= EDP_PSR2_FAST_WAKE(7);
 	}
 
+	if (dev_priv->psr.psr2_sel_fetch_enabled) {
+		/* WA 1408330847 */
+		if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) ||
+		    IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0))
+			intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+				     DIS_RAM_BYPASS_PSR2_MAN_TRACK,
+				     DIS_RAM_BYPASS_PSR2_MAN_TRACK);
+
+		intel_de_write(dev_priv,
+			       PSR2_MAN_TRK_CTL(dev_priv->psr.transcoder),
+			       PSR2_MAN_TRK_CTL_ENABLE);
+	} else if (HAS_PSR2_SEL_FETCH(dev_priv)) {
+		intel_de_write(dev_priv,
+			       PSR2_MAN_TRK_CTL(dev_priv->psr.transcoder), 0);
+	}
+
 	/*
 	 * PSR2 HW is incorrectly using EDP_PSR_TP1_TP3_SEL and BSpec is
 	 * recommending keep this bit unset while PSR2 is enabled.
@@ -663,6 +679,38 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp,
 	crtc_state->dc3co_exitline = crtc_vdisplay - exit_scanlines;
 }
 
+static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp,
+					      struct intel_crtc_state *crtc_state)
+{
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
+	int i;
+
+	if (!dev_priv->params.enable_psr2_sel_fetch) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 sel fetch not enabled, disabled by parameter\n");
+		return false;
+	}
+
+	if (crtc_state->uapi.async_flip) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 sel fetch not enabled, async flip enabled\n");
+		return false;
+	}
+
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		if (plane_state->uapi.rotation != DRM_MODE_ROTATE_0) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "PSR2 sel fetch not enabled, plane rotated\n");
+			return false;
+		}
+	}
+
+	return crtc_state->enable_psr2_sel_fetch = true;
+}
+
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -732,22 +780,17 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	/*
-	 * Some platforms lack PSR2 HW tracking and instead require manual
-	 * tracking by software.  In this case, the driver is required to track
-	 * the areas that need updates and program hardware to send selective
-	 * updates.
-	 *
-	 * So until the software tracking is implemented, PSR2 needs to be
-	 * disabled for platforms without PSR2 HW tracking.
-	 */
-	if (!HAS_PSR_HW_TRACKING(dev_priv)) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "No PSR2 HW tracking in the platform\n");
-		return false;
+	if (HAS_PSR2_SEL_FETCH(dev_priv)) {
+		if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) &&
+		    !HAS_PSR_HW_TRACKING(dev_priv)) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "PSR2 not enabled, selective fetch not valid and no HW tracking available\n");
+			return false;
+		}
 	}
 
-	if (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v) {
+	if (!crtc_state->enable_psr2_sel_fetch &&
+	    (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v)) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "PSR2 not enabled, resolution %dx%d > max supported %dx%d\n",
 			    crtc_hdisplay, crtc_vdisplay,
@@ -898,6 +941,11 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 		val |= EXITLINE_ENABLE;
 		intel_de_write(dev_priv, EXITLINE(cpu_transcoder), val);
 	}
+
+	if (HAS_PSR_HW_TRACKING(dev_priv))
+		intel_de_rmw(dev_priv, CHICKEN_PAR1_1, IGNORE_PSR2_HW_TRACKING,
+			     dev_priv->psr.psr2_sel_fetch_enabled ?
+			     IGNORE_PSR2_HW_TRACKING : 0);
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
@@ -919,6 +967,7 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 	/* DC5/DC6 requires at least 6 idle frames */
 	val = usecs_to_jiffies(intel_get_frame_time_us(crtc_state) * 6);
 	dev_priv->psr.dc3co_exit_delay = val;
+	dev_priv->psr.psr2_sel_fetch_enabled = crtc_state->enable_psr2_sel_fetch;
 
 	/*
 	 * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR
@@ -1058,6 +1107,13 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 				    psr_status_mask, 2000))
 		drm_err(&dev_priv->drm, "Timed out waiting PSR idle state\n");
 
+	/* WA 1408330847 */
+	if (dev_priv->psr.psr2_sel_fetch_enabled &&
+	    (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) ||
+	     IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0)))
+		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+			     DIS_RAM_BYPASS_PSR2_MAN_TRACK, 0);
+
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
 
@@ -1115,6 +1171,32 @@ static void psr_force_hw_tracking_exit(struct drm_i915_private *dev_priv)
 		intel_psr_exit(dev_priv);
 }
 
+void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct i915_psr *psr = &dev_priv->psr;
+
+	if (!HAS_PSR2_SEL_FETCH(dev_priv) ||
+	    !crtc_state->enable_psr2_sel_fetch)
+		return;
+
+	intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(psr->transcoder),
+		       crtc_state->psr2_man_track_ctl);
+}
+
+void intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+
+	if (!crtc_state->enable_psr2_sel_fetch)
+		return;
+
+	crtc_state->psr2_man_track_ctl = PSR2_MAN_TRK_CTL_ENABLE |
+					 PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
+}
+
 /**
  * intel_psr_update - Update PSR state
  * @intel_dp: Intel DP
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index b4515186d5f4..6a83c8e682e6 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -13,6 +13,8 @@ struct drm_connector_state;
 struct drm_i915_private;
 struct intel_crtc_state;
 struct intel_dp;
+struct intel_crtc;
+struct intel_atomic_state;
 
 #define CAN_PSR(dev_priv) (HAS_PSR(dev_priv) && dev_priv->psr.sink_support)
 void intel_psr_init_dpcd(struct intel_dp *intel_dp);
@@ -43,5 +45,8 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 			    struct drm_connector_state *old_state,
 			    struct drm_connector_state *new_state);
 void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp);
+void intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc);
+void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 2da4388e1540..5e9fb349c829 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1531,7 +1531,7 @@ static void intel_sdvo_pre_enable(struct intel_atomic_state *state,
 	default:
 		drm_WARN(&dev_priv->drm, 1,
 			 "unknown pixel multiplier specified\n");
-		/* fall through */
+		fallthrough;
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
 	case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break;
 	case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break;
@@ -2549,19 +2549,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo)
 	switch (sdvo->controlled_output) {
 	case SDVO_OUTPUT_LVDS1:
 		mask |= SDVO_OUTPUT_LVDS1;
-		/* fall through */
+		fallthrough;
 	case SDVO_OUTPUT_LVDS0:
 		mask |= SDVO_OUTPUT_LVDS0;
-		/* fall through */
+		fallthrough;
 	case SDVO_OUTPUT_TMDS1:
 		mask |= SDVO_OUTPUT_TMDS1;
-		/* fall through */
+		fallthrough;
 	case SDVO_OUTPUT_TMDS0:
 		mask |= SDVO_OUTPUT_TMDS0;
-		/* fall through */
+		fallthrough;
 	case SDVO_OUTPUT_RGB1:
 		mask |= SDVO_OUTPUT_RGB1;
-		/* fall through */
+		fallthrough;
 	case SDVO_OUTPUT_RGB0:
 		mask |= SDVO_OUTPUT_RGB0;
 		break;
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index d03860fef2d7..6b72223981be 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2147,7 +2147,7 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 		case DRM_FORMAT_RGB565:
 			if (INTEL_GEN(dev_priv) >= 11)
 				break;
-			/* fall through */
+			fallthrough;
 		case DRM_FORMAT_C8:
 		case DRM_FORMAT_XRGB16161616F:
 		case DRM_FORMAT_XBGR16161616F:
@@ -2702,7 +2702,7 @@ static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane,
 		if (modifier == DRM_FORMAT_MOD_LINEAR ||
 		    modifier == I915_FORMAT_MOD_X_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
@@ -2733,7 +2733,7 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
 		if (modifier == DRM_FORMAT_MOD_LINEAR ||
 		    modifier == I915_FORMAT_MOD_X_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
@@ -2768,7 +2768,7 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
 		if (modifier == DRM_FORMAT_MOD_LINEAR ||
 		    modifier == I915_FORMAT_MOD_X_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
@@ -2801,7 +2801,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_ABGR8888:
 		if (is_ccs_modifier(modifier))
 			return true;
-		/* fall through */
+		fallthrough;
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
@@ -2819,7 +2819,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XVYU2101010:
 		if (modifier == I915_FORMAT_MOD_Yf_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_ABGR16161616F:
@@ -2834,7 +2834,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 		    modifier == I915_FORMAT_MOD_X_TILED ||
 		    modifier == I915_FORMAT_MOD_Y_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
@@ -2843,8 +2843,9 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv,
 					enum plane_id plane_id)
 {
-	/* Wa_14010477008:tgl[a0..c0] */
-	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0))
+	/* Wa_14010477008:tgl[a0..c0],rkl[all] */
+	if (IS_ROCKETLAKE(dev_priv) ||
+	    IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0))
 		return false;
 
 	return plane_id < PLANE_SPRITE4;
@@ -2860,7 +2861,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id))
 			return false;
-		/* fall through */
+		fallthrough;
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
 	case I915_FORMAT_MOD_Y_TILED:
@@ -2877,7 +2878,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_ABGR8888:
 		if (is_ccs_modifier(modifier))
 			return true;
-		/* fall through */
+		fallthrough;
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2889,7 +2890,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_P016:
 		if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS)
 			return true;
-		/* fall through */
+		fallthrough;
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
@@ -2910,7 +2911,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 		    modifier == I915_FORMAT_MOD_X_TILED ||
 		    modifier == I915_FORMAT_MOD_Y_TILED)
 			return true;
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 5b5dc86a5737..8f67aef18b2d 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -159,7 +159,7 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port)
 	switch (lane_mask) {
 	default:
 		MISSING_CASE(lane_mask);
-		/* fall-through */
+		fallthrough;
 	case 0x1:
 	case 0x2:
 	case 0x4:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
index 278664f831e7..272cf3ea68d5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -32,12 +32,13 @@ static void vma_clear_pages(struct i915_vma *vma)
 	vma->pages = NULL;
 }
 
-static int vma_bind(struct i915_address_space *vm,
-		    struct i915_vma *vma,
-		    enum i915_cache_level cache_level,
-		    u32 flags)
+static void vma_bind(struct i915_address_space *vm,
+		     struct i915_vm_pt_stash *stash,
+		     struct i915_vma *vma,
+		     enum i915_cache_level cache_level,
+		     u32 flags)
 {
-	return vm->vma_ops.bind_vma(vm, vma, cache_level, flags);
+	vm->vma_ops.bind_vma(vm, stash, vma, cache_level, flags);
 }
 
 static void vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
@@ -157,6 +158,7 @@ static void clear_pages_worker(struct work_struct *work)
 	struct clear_pages_work *w = container_of(work, typeof(*w), work);
 	struct drm_i915_gem_object *obj = w->sleeve->vma->obj;
 	struct i915_vma *vma = w->sleeve->vma;
+	struct i915_gem_ww_ctx ww;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	int err = w->dma.error;
@@ -172,17 +174,20 @@ static void clear_pages_worker(struct work_struct *work)
 	obj->read_domains = I915_GEM_GPU_DOMAINS;
 	obj->write_domain = 0;
 
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (unlikely(err))
+	i915_gem_ww_ctx_init(&ww, false);
+	intel_engine_pm_get(w->ce->engine);
+retry:
+	err = intel_context_pin_ww(w->ce, &ww);
+	if (err)
 		goto out_signal;
 
-	batch = intel_emit_vma_fill_blt(w->ce, vma, w->value);
+	batch = intel_emit_vma_fill_blt(w->ce, vma, &ww, w->value);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
-		goto out_unpin;
+		goto out_ctx;
 	}
 
-	rq = intel_context_create_request(w->ce);
+	rq = i915_request_create(w->ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out_batch;
@@ -224,9 +229,19 @@ out_request:
 	i915_request_add(rq);
 out_batch:
 	intel_emit_vma_release(w->ce, batch);
-out_unpin:
-	i915_vma_unpin(vma);
+out_ctx:
+	intel_context_unpin(w->ce);
 out_signal:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+
+	i915_vma_unpin(w->sleeve->vma);
+	intel_engine_pm_put(w->ce->engine);
+
 	if (unlikely(err)) {
 		dma_fence_set_error(&w->dma, err);
 		dma_fence_signal(&w->dma);
@@ -234,6 +249,44 @@ out_signal:
 	}
 }
 
+static int pin_wait_clear_pages_work(struct clear_pages_work *w,
+				     struct intel_context *ce)
+{
+	struct i915_vma *vma = w->sleeve->vma;
+	struct i915_gem_ww_ctx ww;
+	int err;
+
+	i915_gem_ww_ctx_init(&ww, false);
+retry:
+	err = i915_gem_object_lock(vma->obj, &ww);
+	if (err)
+		goto out;
+
+	err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
+	if (unlikely(err))
+		goto out;
+
+	err = i915_sw_fence_await_reservation(&w->wait,
+					      vma->obj->base.resv, NULL,
+					      true, 0, I915_FENCE_GFP);
+	if (err)
+		goto err_unpin_vma;
+
+	dma_resv_add_excl_fence(vma->obj->base.resv, &w->dma);
+
+err_unpin_vma:
+	if (err)
+		i915_vma_unpin(vma);
+out:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	return err;
+}
+
 static int __i915_sw_fence_call
 clear_pages_work_notify(struct i915_sw_fence *fence,
 			enum i915_sw_fence_notify state)
@@ -287,17 +340,9 @@ int i915_gem_schedule_fill_pages_blt(struct drm_i915_gem_object *obj,
 	dma_fence_init(&work->dma, &clear_pages_work_ops, &fence_lock, 0, 0);
 	i915_sw_fence_init(&work->wait, clear_pages_work_notify);
 
-	i915_gem_object_lock(obj);
-	err = i915_sw_fence_await_reservation(&work->wait,
-					      obj->base.resv, NULL, true, 0,
-					      I915_FENCE_GFP);
-	if (err < 0) {
+	err = pin_wait_clear_pages_work(work, ce);
+	if (err < 0)
 		dma_fence_set_error(&work->dma, err);
-	} else {
-		dma_resv_add_excl_fence(obj->base.resv, &work->dma);
-		err = 0;
-	}
-	i915_gem_object_unlock(obj);
 
 	dma_fence_get(&work->dma);
 	i915_sw_fence_commit(&work->wait);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index d0bdb6d447ed..cf5ecbde9e06 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
 	return __reset_engine(engine);
 }
 
-static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+static bool
+__active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 {
 	struct intel_engine_cs *engine, *locked;
+	bool ret = false;
 
 	/*
 	 * Serialise with __i915_request_submit() so that it sees
 	 * is-banned?, or we know the request is already inflight.
+	 *
+	 * Note that rq->engine is unstable, and so we double
+	 * check that we have acquired the lock on the final engine.
 	 */
 	locked = READ_ONCE(rq->engine);
 	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
-		spin_lock(&engine->active.lock);
 		locked = engine;
+		spin_lock(&locked->active.lock);
 	}
 
-	engine = NULL;
-	if (i915_request_is_active(rq) && rq->fence.error != -EIO)
-		engine = rq->engine;
+	if (!i915_request_completed(rq)) {
+		if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+			*active = locked;
+		ret = true;
+	}
 
 	spin_unlock_irq(&locked->active.lock);
 
-	return engine;
+	return ret;
 }
 
 static struct intel_engine_cs *active_engine(struct intel_context *ce)
@@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
-	mutex_lock(&ce->timeline->mutex);
-	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
-		if (i915_request_completed(rq))
-			break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
+		if (i915_request_is_active(rq) && i915_request_completed(rq))
+			continue;
 
 		/* Check with the backend if the request is inflight */
-		engine = __active_engine(rq);
-		if (engine)
+		if (__active_engine(rq, &engine))
 			break;
 	}
-	mutex_unlock(&ce->timeline->mutex);
+	rcu_read_unlock();
 
 	return engine;
 }
@@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915)
 	ctx->i915 = i915;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->link);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
@@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	spin_lock(&i915->gem.contexts.lock);
-	list_add_tail(&ctx->link, &i915->gem.contexts.list);
-	spin_unlock(&i915->gem.contexts.lock);
-
 	return ctx;
 
 err_free:
@@ -889,7 +892,7 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
 		struct intel_timeline *timeline;
 
-		timeline = intel_timeline_create(&i915->gt, NULL);
+		timeline = intel_timeline_create(&i915->gt);
 		if (IS_ERR(timeline)) {
 			context_close(ctx);
 			return ERR_CAST(timeline);
@@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx,
 				struct drm_i915_file_private *fpriv,
 				u32 *id)
 {
+	struct drm_i915_private *i915 = ctx->i915;
 	struct i915_address_space *vm;
 	int ret;
 
@@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	/* And finally expose ourselves to userspace via the idr */
 	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
 	if (ret)
-		put_pid(fetch_and_zero(&ctx->pid));
+		goto err_pid;
+
+	spin_lock(&i915->gem.contexts.lock);
+	list_add_tail(&ctx->link, &i915->gem.contexts.list);
+	spin_unlock(&i915->gem.contexts.lock);
 
+	return 0;
+
+err_pid:
+	put_pid(fetch_and_zero(&ctx->pid));
 	return ret;
 }
 
@@ -1094,6 +1106,7 @@ I915_SELFTEST_DECLARE(static intel_engine_mask_t context_barrier_inject_fault);
 static int context_barrier_task(struct i915_gem_context *ctx,
 				intel_engine_mask_t engines,
 				bool (*skip)(struct intel_context *ce, void *data),
+				int (*pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void *data),
 				int (*emit)(struct i915_request *rq, void *data),
 				void (*task)(void *data),
 				void *data)
@@ -1101,6 +1114,7 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 	struct context_barrier_task *cb;
 	struct i915_gem_engines_iter it;
 	struct i915_gem_engines *e;
+	struct i915_gem_ww_ctx ww;
 	struct intel_context *ce;
 	int err = 0;
 
@@ -1138,10 +1152,21 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 		if (skip && skip(ce, data))
 			continue;
 
-		rq = intel_context_create_request(ce);
+		i915_gem_ww_ctx_init(&ww, true);
+retry:
+		err = intel_context_pin_ww(ce, &ww);
+		if (err)
+			goto err;
+
+		if (pin)
+			err = pin(ce, &ww, data);
+		if (err)
+			goto err_unpin;
+
+		rq = i915_request_create(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			break;
+			goto err_unpin;
 		}
 
 		err = 0;
@@ -1151,6 +1176,16 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 			err = i915_active_add_request(&cb->base, rq);
 
 		i915_request_add(rq);
+err_unpin:
+		intel_context_unpin(ce);
+err:
+		if (err == -EDEADLK) {
+			err = i915_gem_ww_ctx_backoff(&ww);
+			if (!err)
+				goto retry;
+		}
+		i915_gem_ww_ctx_fini(&ww);
+
 		if (err)
 			break;
 	}
@@ -1206,6 +1241,17 @@ static void set_ppgtt_barrier(void *data)
 	i915_vm_close(old);
 }
 
+static int pin_ppgtt_update(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void *data)
+{
+	struct i915_address_space *vm = ce->vm;
+
+	if (!HAS_LOGICAL_RING_CONTEXTS(vm->i915))
+		/* ppGTT is not part of the legacy context image */
+		return gen6_ppgtt_pin(i915_vm_to_ppgtt(vm), ww);
+
+	return 0;
+}
+
 static int emit_ppgtt_update(struct i915_request *rq, void *data)
 {
 	struct i915_address_space *vm = rq->context->vm;
@@ -1262,20 +1308,10 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 
 static bool skip_ppgtt_update(struct intel_context *ce, void *data)
 {
-	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
-		return true;
-
 	if (HAS_LOGICAL_RING_CONTEXTS(ce->engine->i915))
-		return false;
-
-	if (!atomic_read(&ce->pin_count))
-		return true;
-
-	/* ppGTT is not part of the legacy context image */
-	if (gen6_ppgtt_pin(i915_vm_to_ppgtt(ce->vm)))
-		return true;
-
-	return false;
+		return !ce->state;
+	else
+		return !atomic_read(&ce->pin_count);
 }
 
 static int set_ppgtt(struct drm_i915_file_private *file_priv,
@@ -1326,6 +1362,7 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	 */
 	err = context_barrier_task(ctx, ALL_ENGINES,
 				   skip_ppgtt_update,
+				   pin_ppgtt_update,
 				   emit_ppgtt_update,
 				   set_ppgtt_barrier,
 				   old);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 2679380159fc..27fddc22a7c6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -128,7 +128,7 @@ static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_dire
 	if (err)
 		return err;
 
-	err = i915_gem_object_lock_interruptible(obj);
+	err = i915_gem_object_lock_interruptible(obj, NULL);
 	if (err)
 		goto out;
 
@@ -149,7 +149,7 @@ static int i915_gem_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direct
 	if (err)
 		return err;
 
-	err = i915_gem_object_lock_interruptible(obj);
+	err = i915_gem_object_lock_interruptible(obj, NULL);
 	if (err)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 7f76fc68f498..7c90a63c273d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -32,11 +32,17 @@ void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj)
 	if (!i915_gem_object_is_framebuffer(obj))
 		return;
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	__i915_gem_object_flush_for_display(obj);
 	i915_gem_object_unlock(obj);
 }
 
+void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj)
+{
+	if (i915_gem_object_is_framebuffer(obj))
+		__i915_gem_object_flush_for_display(obj);
+}
+
 /**
  * Moves a single object to the WC read, and possibly write domain.
  * @obj: object to act on
@@ -197,18 +203,12 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 	if (ret)
 		return ret;
 
-	ret = i915_gem_object_lock_interruptible(obj);
-	if (ret)
-		return ret;
-
 	/* Always invalidate stale cachelines */
 	if (obj->cache_level != cache_level) {
 		i915_gem_object_set_cache_coherency(obj, cache_level);
 		obj->cache_dirty = true;
 	}
 
-	i915_gem_object_unlock(obj);
-
 	/* The cache-level will be applied when each vma is rebound. */
 	return i915_gem_object_unbind(obj,
 				      I915_GEM_OBJECT_UNBIND_ACTIVE |
@@ -293,7 +293,12 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
+	if (ret)
+		goto out;
+
 	ret = i915_gem_object_set_cache_level(obj, level);
+	i915_gem_object_unlock(obj);
 
 out:
 	i915_gem_object_put(obj);
@@ -313,6 +318,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     unsigned int flags)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_gem_ww_ctx ww;
 	struct i915_vma *vma;
 	int ret;
 
@@ -320,6 +326,11 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj))
 		return ERR_PTR(-EINVAL);
 
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	ret = i915_gem_object_lock(obj, &ww);
+	if (ret)
+		goto err;
 	/*
 	 * The display engine is not coherent with the LLC cache on gen6.  As
 	 * a result, we make sure that the pinning that is about to occur is
@@ -334,7 +345,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 					      HAS_WT(i915) ?
 					      I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
-		return ERR_PTR(ret);
+		goto err;
 
 	/*
 	 * As the user may map the buffer once pinned in the display plane
@@ -347,18 +358,31 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	vma = ERR_PTR(-ENOSPC);
 	if ((flags & PIN_MAPPABLE) == 0 &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL))
-		vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment,
-					       flags |
-					       PIN_MAPPABLE |
-					       PIN_NONBLOCK);
-	if (IS_ERR(vma))
-		vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment, flags);
-	if (IS_ERR(vma))
-		return vma;
+		vma = i915_gem_object_ggtt_pin_ww(obj, &ww, view, 0, alignment,
+						  flags | PIN_MAPPABLE |
+						  PIN_NONBLOCK);
+	if (IS_ERR(vma) && vma != ERR_PTR(-EDEADLK))
+		vma = i915_gem_object_ggtt_pin_ww(obj, &ww, view, 0,
+						  alignment, flags);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err;
+	}
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
-	i915_gem_object_flush_if_display(obj);
+	i915_gem_object_flush_if_display_locked(obj);
+
+err:
+	if (ret == -EDEADLK) {
+		ret = i915_gem_ww_ctx_backoff(&ww);
+		if (!ret)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+
+	if (ret)
+		return ERR_PTR(ret);
 
 	return vma;
 }
@@ -536,7 +560,7 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	if (err)
 		goto out;
 
-	err = i915_gem_object_lock_interruptible(obj);
+	err = i915_gem_object_lock_interruptible(obj, NULL);
 	if (err)
 		goto out_unpin;
 
@@ -576,19 +600,17 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_has_struct_page(obj))
 		return -ENODEV;
 
-	ret = i915_gem_object_lock_interruptible(obj);
-	if (ret)
-		return ret;
+	assert_object_held(obj);
 
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE,
 				   MAX_SCHEDULE_TIMEOUT);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	ret = i915_gem_object_pin_pages(obj);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ ||
 	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -616,8 +638,6 @@ out:
 
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
-err_unlock:
-	i915_gem_object_unlock(obj);
 	return ret;
 }
 
@@ -630,20 +650,18 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_has_struct_page(obj))
 		return -ENODEV;
 
-	ret = i915_gem_object_lock_interruptible(obj);
-	if (ret)
-		return ret;
+	assert_object_held(obj);
 
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE |
 				   I915_WAIT_ALL,
 				   MAX_SCHEDULE_TIMEOUT);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	ret = i915_gem_object_pin_pages(obj);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE ||
 	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -680,7 +698,5 @@ out:
 
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
-err_unlock:
-	i915_gem_object_unlock(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..5509946f1a1d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
 #include "i915_gem_ioctls.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -40,9 +41,11 @@ struct eb_vma {
 	u32 handle;
 };
 
-struct eb_vma_array {
-	struct kref kref;
-	struct eb_vma vma[];
+enum {
+	FORCE_CPU_RELOC = 1,
+	FORCE_GTT_RELOC,
+	FORCE_GPU_RELOC,
+#define DBG_FORCE_RELOC 0 /* choose one of the above! */
 };
 
 #define __EXEC_OBJECT_HAS_PIN		BIT(31)
@@ -50,9 +53,11 @@ struct eb_vma_array {
 #define __EXEC_OBJECT_NEEDS_MAP		BIT(29)
 #define __EXEC_OBJECT_NEEDS_BIAS	BIT(28)
 #define __EXEC_OBJECT_INTERNAL_FLAGS	(~0u << 28) /* all of the above */
+#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE)
 
 #define __EXEC_HAS_RELOC	BIT(31)
-#define __EXEC_INTERNAL_FLAGS	(~0u << 31)
+#define __EXEC_ENGINE_PINNED	BIT(30)
+#define __EXEC_INTERNAL_FLAGS	(~0u << 30)
 #define UPDATE			PIN_OFFSET_FIXED
 
 #define BATCH_OFFSET_BIAS (256*1024)
@@ -222,6 +227,13 @@ struct eb_vma_array {
  * the batchbuffer in trusted mode, otherwise the ioctl is rejected.
  */
 
+struct eb_fence {
+	struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	struct dma_fence *dma_fence;
+	u64 value;
+	struct dma_fence_chain *chain_fence;
+};
+
 struct i915_execbuffer {
 	struct drm_i915_private *i915; /** i915 backpointer */
 	struct drm_file *file; /** per-file lookup tables and limits */
@@ -246,6 +258,8 @@ struct i915_execbuffer {
 	/** list of vma that have execobj.relocation_count */
 	struct list_head relocs;
 
+	struct i915_gem_ww_ctx ww;
+
 	/**
 	 * Track the most recently used object for relocations, as we
 	 * frequently have to perform multiple relocations within the same
@@ -253,25 +267,30 @@ struct i915_execbuffer {
 	 */
 	struct reloc_cache {
 		struct drm_mm_node node; /** temporary GTT binding */
+		unsigned long vaddr; /** Current kmap address */
+		unsigned long page; /** Currently mapped page index */
 		unsigned int gen; /** Cached value of INTEL_GEN */
 		bool use_64bit_reloc : 1;
 		bool has_llc : 1;
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
 
-		struct i915_vma *target;
 		struct i915_request *rq;
-		struct i915_vma *rq_vma;
 		u32 *rq_cmd;
 		unsigned int rq_size;
+		struct intel_gt_buffer_pool_node *pool;
 	} reloc_cache;
 
+	struct intel_gt_buffer_pool_node *reloc_pool; /** relocation pool for -EDEADLK handling */
+	struct intel_context *reloc_context;
+
 	u64 invalid_flags; /** Set of execobj.flags that are invalid */
 	u32 context_flags; /** Set of execobj.flags to insert from the ctx */
 
 	u32 batch_start_offset; /** Location within object of batch */
 	u32 batch_len; /** Length of batch within object */
 	u32 batch_flags; /** Flags composed for emit_bb_start() */
+	struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */
 
 	/**
 	 * Indicate either the size of the hastable used to resolve
@@ -280,9 +299,16 @@ struct i915_execbuffer {
 	 */
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
-	struct eb_vma_array *array;
+
+	struct eb_fence *fences;
+	unsigned long num_fences;
 };
 
+static int eb_parse(struct i915_execbuffer *eb);
+static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb,
+					  bool throttle);
+static void eb_unpin_engine(struct i915_execbuffer *eb);
+
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
 	return intel_engine_requires_cmd_parser(eb->engine) ||
@@ -290,62 +316,8 @@ static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 		 eb->args->batch_len);
 }
 
-static struct eb_vma_array *eb_vma_array_create(unsigned int count)
-{
-	struct eb_vma_array *arr;
-
-	arr = kvmalloc(struct_size(arr, vma, count), GFP_KERNEL | __GFP_NOWARN);
-	if (!arr)
-		return NULL;
-
-	kref_init(&arr->kref);
-	arr->vma[0].vma = NULL;
-
-	return arr;
-}
-
-static inline void eb_unreserve_vma(struct eb_vma *ev)
-{
-	struct i915_vma *vma = ev->vma;
-
-	if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE))
-		__i915_vma_unpin_fence(vma);
-
-	if (ev->flags & __EXEC_OBJECT_HAS_PIN)
-		__i915_vma_unpin(vma);
-
-	ev->flags &= ~(__EXEC_OBJECT_HAS_PIN |
-		       __EXEC_OBJECT_HAS_FENCE);
-}
-
-static void eb_vma_array_destroy(struct kref *kref)
-{
-	struct eb_vma_array *arr = container_of(kref, typeof(*arr), kref);
-	struct eb_vma *ev = arr->vma;
-
-	while (ev->vma) {
-		eb_unreserve_vma(ev);
-		i915_vma_put(ev->vma);
-		ev++;
-	}
-
-	kvfree(arr);
-}
-
-static void eb_vma_array_put(struct eb_vma_array *arr)
-{
-	kref_put(&arr->kref, eb_vma_array_destroy);
-}
-
 static int eb_create(struct i915_execbuffer *eb)
 {
-	/* Allocate an extra slot for use by the command parser + sentinel */
-	eb->array = eb_vma_array_create(eb->buffer_count + 2);
-	if (!eb->array)
-		return -ENOMEM;
-
-	eb->vma = eb->array->vma;
-
 	if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) {
 		unsigned int size = 1 + ilog2(eb->buffer_count);
 
@@ -379,10 +351,8 @@ static int eb_create(struct i915_execbuffer *eb)
 				break;
 		} while (--size);
 
-		if (unlikely(!size)) {
-			eb_vma_array_put(eb->array);
+		if (unlikely(!size))
 			return -ENOMEM;
-		}
 
 		eb->lut_size = size;
 	} else {
@@ -466,16 +436,17 @@ eb_pin_vma(struct i915_execbuffer *eb,
 		pin_flags |= PIN_GLOBAL;
 
 	/* Attempt to reuse the current location if available */
-	if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags))) {
+	/* TODO: Add -EDEADLK handling here */
+	if (unlikely(i915_vma_pin_ww(vma, &eb->ww, 0, 0, pin_flags))) {
 		if (entry->flags & EXEC_OBJECT_PINNED)
 			return false;
 
 		/* Failing that pick any _free_ space if suitable */
-		if (unlikely(i915_vma_pin(vma,
-					  entry->pad_to_size,
-					  entry->alignment,
-					  eb_pin_flags(entry, ev->flags) |
-					  PIN_USER | PIN_NOEVICT)))
+		if (unlikely(i915_vma_pin_ww(vma, &eb->ww,
+					     entry->pad_to_size,
+					     entry->alignment,
+					     eb_pin_flags(entry, ev->flags) |
+					     PIN_USER | PIN_NOEVICT)))
 			return false;
 	}
 
@@ -493,6 +464,19 @@ eb_pin_vma(struct i915_execbuffer *eb,
 	return !eb_vma_misplaced(entry, vma, ev->flags);
 }
 
+static inline void
+eb_unreserve_vma(struct eb_vma *ev)
+{
+	if (!(ev->flags & __EXEC_OBJECT_HAS_PIN))
+		return;
+
+	if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE))
+		__i915_vma_unpin_fence(ev->vma);
+
+	__i915_vma_unpin(ev->vma);
+	ev->flags &= ~__EXEC_OBJECT_RESERVED;
+}
+
 static int
 eb_validate_vma(struct i915_execbuffer *eb,
 		struct drm_i915_gem_exec_object2 *entry,
@@ -584,19 +568,26 @@ eb_add_vma(struct i915_execbuffer *eb,
 
 		eb->batch = ev;
 	}
+}
 
-	if (eb_pin_vma(eb, entry, ev)) {
-		if (entry->offset != vma->node.start) {
-			entry->offset = vma->node.start | UPDATE;
-			eb->args->flags |= __EXEC_HAS_RELOC;
-		}
-	} else {
-		eb_unreserve_vma(ev);
-		list_add_tail(&ev->bind_link, &eb->unbound);
-	}
+static inline int use_cpu_reloc(const struct reloc_cache *cache,
+				const struct drm_i915_gem_object *obj)
+{
+	if (!i915_gem_object_has_struct_page(obj))
+		return false;
+
+	if (DBG_FORCE_RELOC == FORCE_CPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
+		return false;
+
+	return (cache->has_llc ||
+		obj->cache_dirty ||
+		obj->cache_level != I915_CACHE_NONE);
 }
 
-static int eb_reserve_vma(const struct i915_execbuffer *eb,
+static int eb_reserve_vma(struct i915_execbuffer *eb,
 			  struct eb_vma *ev,
 			  u64 pin_flags)
 {
@@ -611,7 +602,7 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 			return err;
 	}
 
-	err = i915_vma_pin(vma,
+	err = i915_vma_pin_ww(vma, &eb->ww,
 			   entry->pad_to_size, entry->alignment,
 			   eb_pin_flags(entry, ev->flags) | pin_flags);
 	if (err)
@@ -661,10 +652,6 @@ static int eb_reserve(struct i915_execbuffer *eb)
 	 * This avoid unnecessary unbinding of later objects in order to make
 	 * room for the earlier objects *unless* we need to defragment.
 	 */
-
-	if (mutex_lock_interruptible(&eb->i915->drm.struct_mutex))
-		return -EINTR;
-
 	pass = 0;
 	do {
 		list_for_each_entry(ev, &eb->unbound, bind_link) {
@@ -672,8 +659,8 @@ static int eb_reserve(struct i915_execbuffer *eb)
 			if (err)
 				break;
 		}
-		if (!(err == -ENOSPC || err == -EAGAIN))
-			break;
+		if (err != -ENOSPC)
+			return err;
 
 		/* Resort *all* the objects into priority order */
 		INIT_LIST_HEAD(&eb->unbound);
@@ -703,13 +690,6 @@ static int eb_reserve(struct i915_execbuffer *eb)
 		}
 		list_splice_tail(&last, &eb->unbound);
 
-		if (err == -EAGAIN) {
-			mutex_unlock(&eb->i915->drm.struct_mutex);
-			flush_workqueue(eb->i915->mm.userptr_wq);
-			mutex_lock(&eb->i915->drm.struct_mutex);
-			continue;
-		}
-
 		switch (pass++) {
 		case 0:
 			break;
@@ -720,20 +700,15 @@ static int eb_reserve(struct i915_execbuffer *eb)
 			err = i915_gem_evict_vm(eb->context->vm);
 			mutex_unlock(&eb->context->vm->mutex);
 			if (err)
-				goto unlock;
+				return err;
 			break;
 
 		default:
-			err = -ENOSPC;
-			goto unlock;
+			return -ENOSPC;
 		}
 
 		pin_flags = PIN_USER;
 	} while (1);
-
-unlock:
-	mutex_unlock(&eb->i915->drm.struct_mutex);
-	return err;
 }
 
 static unsigned int eb_batch_index(const struct i915_execbuffer *eb)
@@ -856,12 +831,12 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
 
 static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
+	struct drm_i915_private *i915 = eb->i915;
 	unsigned int batch = eb_batch_index(eb);
 	unsigned int i;
 	int err = 0;
 
 	INIT_LIST_HEAD(&eb->relocs);
-	INIT_LIST_HEAD(&eb->unbound);
 
 	for (i = 0; i < eb->buffer_count; i++) {
 		struct i915_vma *vma;
@@ -869,22 +844,83 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 		vma = eb_lookup_vma(eb, eb->exec[i].handle);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			break;
+			goto err;
 		}
 
 		err = eb_validate_vma(eb, &eb->exec[i], vma);
 		if (unlikely(err)) {
 			i915_vma_put(vma);
-			break;
+			goto err;
 		}
 
 		eb_add_vma(eb, i, batch, vma);
 	}
 
+	if (unlikely(eb->batch->flags & EXEC_OBJECT_WRITE)) {
+		drm_dbg(&i915->drm,
+			"Attempting to use self-modifying batch buffer\n");
+		return -EINVAL;
+	}
+
+	if (range_overflows_t(u64,
+			      eb->batch_start_offset, eb->batch_len,
+			      eb->batch->vma->size)) {
+		drm_dbg(&i915->drm, "Attempting to use out-of-bounds batch\n");
+		return -EINVAL;
+	}
+
+	if (eb->batch_len == 0)
+		eb->batch_len = eb->batch->vma->size - eb->batch_start_offset;
+
+	return 0;
+
+err:
 	eb->vma[i].vma = NULL;
 	return err;
 }
 
+static int eb_validate_vmas(struct i915_execbuffer *eb)
+{
+	unsigned int i;
+	int err;
+
+	INIT_LIST_HEAD(&eb->unbound);
+
+	for (i = 0; i < eb->buffer_count; i++) {
+		struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
+		struct eb_vma *ev = &eb->vma[i];
+		struct i915_vma *vma = ev->vma;
+
+		err = i915_gem_object_lock(vma->obj, &eb->ww);
+		if (err)
+			return err;
+
+		if (eb_pin_vma(eb, entry, ev)) {
+			if (entry->offset != vma->node.start) {
+				entry->offset = vma->node.start | UPDATE;
+				eb->args->flags |= __EXEC_HAS_RELOC;
+			}
+		} else {
+			eb_unreserve_vma(ev);
+
+			list_add_tail(&ev->bind_link, &eb->unbound);
+			if (drm_mm_node_allocated(&vma->node)) {
+				err = i915_vma_unbind(vma);
+				if (err)
+					return err;
+			}
+		}
+
+		GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
+			   eb_vma_misplaced(&eb->exec[i], vma, ev->flags));
+	}
+
+	if (!list_empty(&eb->unbound))
+		return eb_reserve(eb);
+
+	return 0;
+}
+
 static struct eb_vma *
 eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
 {
@@ -905,13 +941,31 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
 	}
 }
 
+static void eb_release_vmas(struct i915_execbuffer *eb, bool final)
+{
+	const unsigned int count = eb->buffer_count;
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		struct eb_vma *ev = &eb->vma[i];
+		struct i915_vma *vma = ev->vma;
+
+		if (!vma)
+			break;
+
+		eb_unreserve_vma(ev);
+
+		if (final)
+			i915_vma_put(vma);
+	}
+
+	eb_unpin_engine(eb);
+}
+
 static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
-	if (eb->array)
-		eb_vma_array_put(eb->array);
-
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -923,9 +977,19 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
 	return gen8_canonical_addr((int)reloc->delta + target->node.start);
 }
 
+static void reloc_cache_clear(struct reloc_cache *cache)
+{
+	cache->rq = NULL;
+	cache->rq_cmd = NULL;
+	cache->pool = NULL;
+	cache->rq_size = 0;
+}
+
 static void reloc_cache_init(struct reloc_cache *cache,
 			     struct drm_i915_private *i915)
 {
+	cache->page = -1;
+	cache->vaddr = 0;
 	/* Must be a variable in the struct to allow GCC to unroll. */
 	cache->gen = INTEL_GEN(i915);
 	cache->has_llc = HAS_LLC(i915);
@@ -933,120 +997,249 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->gen < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
-	cache->rq = NULL;
-	cache->target = NULL;
+	reloc_cache_clear(cache);
 }
 
-#define RELOC_TAIL 4
+static inline void *unmask_page(unsigned long p)
+{
+	return (void *)(uintptr_t)(p & PAGE_MASK);
+}
 
-static int reloc_gpu_chain(struct reloc_cache *cache)
+static inline unsigned int unmask_flags(unsigned long p)
 {
-	struct intel_gt_buffer_pool_node *pool;
-	struct i915_request *rq = cache->rq;
-	struct i915_vma *batch;
-	u32 *cmd;
-	int err;
+	return p & ~PAGE_MASK;
+}
 
-	pool = intel_gt_get_buffer_pool(rq->engine->gt, PAGE_SIZE);
-	if (IS_ERR(pool))
-		return PTR_ERR(pool);
+#define KMAP 0x4 /* after CLFLUSH_FLAGS */
 
-	batch = i915_vma_instance(pool->obj, rq->context->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_pool;
-	}
+static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
+{
+	struct drm_i915_private *i915 =
+		container_of(cache, struct i915_execbuffer, reloc_cache)->i915;
+	return &i915->ggtt;
+}
 
-	err = i915_vma_pin(batch, 0, 0, PIN_USER | PIN_NONBLOCK);
-	if (err)
-		goto out_pool;
+static void reloc_cache_put_pool(struct i915_execbuffer *eb, struct reloc_cache *cache)
+{
+	if (!cache->pool)
+		return;
 
-	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
-	cmd = cache->rq_cmd + cache->rq_size;
-	*cmd++ = MI_ARB_CHECK;
-	if (cache->gen >= 8)
-		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
-	else if (cache->gen >= 6)
-		*cmd++ = MI_BATCH_BUFFER_START;
-	else
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-	*cmd++ = lower_32_bits(batch->node.start);
-	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
-	i915_gem_object_flush_map(cache->rq_vma->obj);
-	i915_gem_object_unpin_map(cache->rq_vma->obj);
-	cache->rq_vma = NULL;
+	/*
+	 * This is a bit nasty, normally we keep objects locked until the end
+	 * of execbuffer, but we already submit this, and have to unlock before
+	 * dropping the reference. Fortunately we can only hold 1 pool node at
+	 * a time, so this should be harmless.
+	 */
+	i915_gem_ww_unlock_single(cache->pool->obj);
+	intel_gt_buffer_pool_put(cache->pool);
+	cache->pool = NULL;
+}
 
-	err = intel_gt_buffer_pool_mark_active(pool, rq);
-	if (err == 0) {
-		i915_vma_lock(batch);
-		err = i915_request_await_object(rq, batch->obj, false);
-		if (err == 0)
-			err = i915_vma_move_to_active(batch, rq, 0);
-		i915_vma_unlock(batch);
-	}
-	i915_vma_unpin(batch);
-	if (err)
-		goto out_pool;
+static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cache)
+{
+	struct drm_i915_gem_object *obj = cache->rq->batch->obj;
 
-	cmd = i915_gem_object_pin_map(batch->obj,
-				      cache->has_llc ?
-				      I915_MAP_FORCE_WB :
-				      I915_MAP_FORCE_WC);
-	if (IS_ERR(cmd)) {
-		err = PTR_ERR(cmd);
-		goto out_pool;
-	}
+	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
+	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	/* Return with batch mapping (cmd) still pinned */
-	cache->rq_cmd = cmd;
-	cache->rq_size = 0;
-	cache->rq_vma = batch;
+	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+	i915_gem_object_unpin_map(obj);
 
-out_pool:
-	intel_gt_buffer_pool_put(pool);
-	return err;
+	intel_gt_chipset_flush(cache->rq->engine->gt);
+
+	i915_request_add(cache->rq);
+	reloc_cache_put_pool(eb, cache);
+	reloc_cache_clear(cache);
+
+	eb->reloc_pool = NULL;
 }
 
-static unsigned int reloc_bb_flags(const struct reloc_cache *cache)
+static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb)
 {
-	return cache->gen > 5 ? 0 : I915_DISPATCH_SECURE;
+	void *vaddr;
+
+	if (cache->rq)
+		reloc_gpu_flush(eb, cache);
+
+	if (!cache->vaddr)
+		return;
+
+	vaddr = unmask_page(cache->vaddr);
+	if (cache->vaddr & KMAP) {
+		struct drm_i915_gem_object *obj =
+			(struct drm_i915_gem_object *)cache->node.mm;
+		if (cache->vaddr & CLFLUSH_AFTER)
+			mb();
+
+		kunmap_atomic(vaddr);
+		i915_gem_object_finish_access(obj);
+	} else {
+		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __iomem *)vaddr);
+
+		if (drm_mm_node_allocated(&cache->node)) {
+			ggtt->vm.clear_range(&ggtt->vm,
+					     cache->node.start,
+					     cache->node.size);
+			mutex_lock(&ggtt->vm.mutex);
+			drm_mm_remove_node(&cache->node);
+			mutex_unlock(&ggtt->vm.mutex);
+		} else {
+			i915_vma_unpin((struct i915_vma *)cache->node.mm);
+		}
+	}
+
+	cache->vaddr = 0;
+	cache->page = -1;
 }
 
-static int reloc_gpu_flush(struct reloc_cache *cache)
+static void *reloc_kmap(struct drm_i915_gem_object *obj,
+			struct reloc_cache *cache,
+			unsigned long pageno)
 {
-	struct i915_request *rq;
-	int err;
+	void *vaddr;
+	struct page *page;
 
-	rq = fetch_and_zero(&cache->rq);
-	if (!rq)
-		return 0;
+	if (cache->vaddr) {
+		kunmap_atomic(unmask_page(cache->vaddr));
+	} else {
+		unsigned int flushes;
+		int err;
 
-	if (cache->rq_vma) {
-		struct drm_i915_gem_object *obj = cache->rq_vma->obj;
+		err = i915_gem_object_prepare_write(obj, &flushes);
+		if (err)
+			return ERR_PTR(err);
 
-		GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
-		cache->rq_cmd[cache->rq_size++] = MI_BATCH_BUFFER_END;
+		BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
+		BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);
 
-		__i915_gem_object_flush_map(obj,
-					    0, sizeof(u32) * cache->rq_size);
-		i915_gem_object_unpin_map(obj);
+		cache->vaddr = flushes | KMAP;
+		cache->node.mm = (void *)obj;
+		if (flushes)
+			mb();
 	}
 
-	err = 0;
-	if (rq->engine->emit_init_breadcrumb)
-		err = rq->engine->emit_init_breadcrumb(rq);
-	if (!err)
-		err = rq->engine->emit_bb_start(rq,
-						rq->batch->node.start,
-						PAGE_SIZE,
-						reloc_bb_flags(cache));
-	if (err)
-		i915_request_set_error_once(rq, err);
+	page = i915_gem_object_get_page(obj, pageno);
+	if (!obj->mm.dirty)
+		set_page_dirty(page);
 
-	intel_gt_chipset_flush(rq->engine->gt);
-	i915_request_add(rq);
+	vaddr = kmap_atomic(page);
+	cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr;
+	cache->page = pageno;
 
-	return err;
+	return vaddr;
+}
+
+static void *reloc_iomap(struct drm_i915_gem_object *obj,
+			 struct i915_execbuffer *eb,
+			 unsigned long page)
+{
+	struct reloc_cache *cache = &eb->reloc_cache;
+	struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+	unsigned long offset;
+	void *vaddr;
+
+	if (cache->vaddr) {
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr));
+	} else {
+		struct i915_vma *vma;
+		int err;
+
+		if (i915_gem_object_is_tiled(obj))
+			return ERR_PTR(-EINVAL);
+
+		if (use_cpu_reloc(cache, obj))
+			return NULL;
+
+		err = i915_gem_object_set_to_gtt_domain(obj, true);
+		if (err)
+			return ERR_PTR(err);
+
+		vma = i915_gem_object_ggtt_pin_ww(obj, &eb->ww, NULL, 0, 0,
+						  PIN_MAPPABLE |
+						  PIN_NONBLOCK /* NOWARN */ |
+						  PIN_NOEVICT);
+		if (vma == ERR_PTR(-EDEADLK))
+			return vma;
+
+		if (IS_ERR(vma)) {
+			memset(&cache->node, 0, sizeof(cache->node));
+			mutex_lock(&ggtt->vm.mutex);
+			err = drm_mm_insert_node_in_range
+				(&ggtt->vm.mm, &cache->node,
+				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
+				 0, ggtt->mappable_end,
+				 DRM_MM_INSERT_LOW);
+			mutex_unlock(&ggtt->vm.mutex);
+			if (err) /* no inactive aperture space, use cpu reloc */
+				return NULL;
+		} else {
+			cache->node.start = vma->node.start;
+			cache->node.mm = (void *)vma;
+		}
+	}
+
+	offset = cache->node.start;
+	if (drm_mm_node_allocated(&cache->node)) {
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, page),
+				     offset, I915_CACHE_NONE, 0);
+	} else {
+		offset += page << PAGE_SHIFT;
+	}
+
+	vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap,
+							 offset);
+	cache->page = page;
+	cache->vaddr = (unsigned long)vaddr;
+
+	return vaddr;
+}
+
+static void *reloc_vaddr(struct drm_i915_gem_object *obj,
+			 struct i915_execbuffer *eb,
+			 unsigned long page)
+{
+	struct reloc_cache *cache = &eb->reloc_cache;
+	void *vaddr;
+
+	if (cache->page == page) {
+		vaddr = unmask_page(cache->vaddr);
+	} else {
+		vaddr = NULL;
+		if ((cache->vaddr & KMAP) == 0)
+			vaddr = reloc_iomap(obj, eb, page);
+		if (!vaddr)
+			vaddr = reloc_kmap(obj, cache, page);
+	}
+
+	return vaddr;
+}
+
+static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
+{
+	if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
+		if (flushes & CLFLUSH_BEFORE) {
+			clflushopt(addr);
+			mb();
+		}
+
+		*addr = value;
+
+		/*
+		 * Writes to the same cacheline are serialised by the CPU
+		 * (including clflush). On the write path, we only require
+		 * that it hits memory in an orderly fashion and place
+		 * mb barriers at the start and end of the relocation phase
+		 * to ensure ordering of clflush wrt to the system.
+		 */
+		if (flushes & CLFLUSH_AFTER)
+			clflushopt(addr);
+	} else
+		*addr = value;
 }
 
 static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
@@ -1054,7 +1247,7 @@ static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 	struct drm_i915_gem_object *obj = vma->obj;
 	int err;
 
-	i915_vma_lock(vma);
+	assert_vma_held(vma);
 
 	if (obj->cache_dirty & ~obj->cache_coherent)
 		i915_gem_clflush_object(obj, 0);
@@ -1064,25 +1257,31 @@ static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 
-	i915_vma_unlock(vma);
-
 	return err;
 }
 
 static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 			     struct intel_engine_cs *engine,
+			     struct i915_vma *vma,
 			     unsigned int len)
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
-	struct intel_gt_buffer_pool_node *pool;
+	struct intel_gt_buffer_pool_node *pool = eb->reloc_pool;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	u32 *cmd;
 	int err;
 
-	pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE);
-	if (IS_ERR(pool))
-		return PTR_ERR(pool);
+	if (!pool) {
+		pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE);
+		if (IS_ERR(pool))
+			return PTR_ERR(pool);
+	}
+	eb->reloc_pool = NULL;
+
+	err = i915_gem_object_lock(pool->obj, &eb->ww);
+	if (err)
+		goto err_pool;
 
 	cmd = i915_gem_object_pin_map(pool->obj,
 				      cache->has_llc ?
@@ -1090,35 +1289,42 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 				      I915_MAP_FORCE_WC);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto out_pool;
+		goto err_pool;
 	}
 
-	batch = i915_vma_instance(pool->obj, eb->context->vm, NULL);
+	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		goto err_unmap;
 	}
 
-	err = i915_vma_pin(batch, 0, 0, PIN_USER | PIN_NONBLOCK);
+	err = i915_vma_pin_ww(batch, &eb->ww, 0, 0, PIN_USER | PIN_NONBLOCK);
 	if (err)
 		goto err_unmap;
 
 	if (engine == eb->context->engine) {
 		rq = i915_request_create(eb->context);
 	} else {
-		struct intel_context *ce;
+		struct intel_context *ce = eb->reloc_context;
 
-		ce = intel_context_create(engine);
-		if (IS_ERR(ce)) {
-			err = PTR_ERR(ce);
-			goto err_unpin;
+		if (!ce) {
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
+				goto err_unpin;
+			}
+
+			i915_vm_put(ce->vm);
+			ce->vm = i915_vm_get(eb->context->vm);
+			eb->reloc_context = ce;
 		}
 
-		i915_vm_put(ce->vm);
-		ce->vm = i915_vm_get(eb->context->vm);
+		err = intel_context_pin_ww(ce, &eb->ww);
+		if (err)
+			goto err_unpin;
 
-		rq = intel_context_create_request(ce);
-		intel_context_put(ce);
+		rq = i915_request_create(ce);
+		intel_context_unpin(ce);
 	}
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
@@ -1129,11 +1335,20 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_request;
 
-	i915_vma_lock(batch);
+	err = reloc_move_to_gpu(rq, vma);
+	if (err)
+		goto err_request;
+
+	err = eb->engine->emit_bb_start(rq,
+					batch->node.start, PAGE_SIZE,
+					cache->gen > 5 ? 0 : I915_DISPATCH_SECURE);
+	if (err)
+		goto skip_request;
+
+	assert_vma_held(batch);
 	err = i915_request_await_object(rq, batch->obj, false);
 	if (err == 0)
 		err = i915_vma_move_to_active(batch, rq, 0);
-	i915_vma_unlock(batch);
 	if (err)
 		goto skip_request;
 
@@ -1143,10 +1358,10 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	cache->rq = rq;
 	cache->rq_cmd = cmd;
 	cache->rq_size = 0;
-	cache->rq_vma = batch;
+	cache->pool = pool;
 
 	/* Return with batch mapping (cmd) still pinned */
-	goto out_pool;
+	return 0;
 
 skip_request:
 	i915_request_set_error_once(rq, err);
@@ -1156,8 +1371,8 @@ err_unpin:
 	i915_vma_unpin(batch);
 err_unmap:
 	i915_gem_object_unpin_map(pool->obj);
-out_pool:
-	intel_gt_buffer_pool_put(pool);
+err_pool:
+	eb->reloc_pool = pool;
 	return err;
 }
 
@@ -1172,9 +1387,12 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
 	u32 *cmd;
-	int err;
+
+	if (cache->rq_size > PAGE_SIZE/sizeof(u32) - (len + 1))
+		reloc_gpu_flush(eb, cache);
 
 	if (unlikely(!cache->rq)) {
+		int err;
 		struct intel_engine_cs *engine = eb->engine;
 
 		if (!reloc_can_use_engine(engine)) {
@@ -1183,37 +1401,28 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 				return ERR_PTR(-ENODEV);
 		}
 
-		err = __reloc_gpu_alloc(eb, engine, len);
+		err = __reloc_gpu_alloc(eb, engine, vma, len);
 		if (unlikely(err))
 			return ERR_PTR(err);
 	}
 
-	if (vma != cache->target) {
-		err = reloc_move_to_gpu(cache->rq, vma);
-		if (unlikely(err)) {
-			i915_request_set_error_once(cache->rq, err);
-			return ERR_PTR(err);
-		}
-
-		cache->target = vma;
-	}
-
-	if (unlikely(cache->rq_size + len >
-		     PAGE_SIZE / sizeof(u32) - RELOC_TAIL)) {
-		err = reloc_gpu_chain(cache);
-		if (unlikely(err)) {
-			i915_request_set_error_once(cache->rq, err);
-			return ERR_PTR(err);
-		}
-	}
-
-	GEM_BUG_ON(cache->rq_size + len >= PAGE_SIZE  / sizeof(u32));
 	cmd = cache->rq_cmd + cache->rq_size;
 	cache->rq_size += len;
 
 	return cmd;
 }
 
+static inline bool use_reloc_gpu(struct i915_vma *vma)
+{
+	if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC)
+		return false;
+
+	return !dma_resv_test_signaled_rcu(vma->resv, true);
+}
+
 static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 {
 	struct page *page;
@@ -1229,9 +1438,9 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 }
 
 static int __reloc_entry_gpu(struct i915_execbuffer *eb,
-			     struct i915_vma *vma,
-			     u64 offset,
-			     u64 target_addr)
+			      struct i915_vma *vma,
+			      u64 offset,
+			      u64 target_addr)
 {
 	const unsigned int gen = eb->reloc_cache.gen;
 	unsigned int len;
@@ -1246,8 +1455,10 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 		len = 3;
 
 	batch = reloc_gpu(eb, vma, len);
-	if (IS_ERR(batch))
-		return PTR_ERR(batch);
+	if (batch == ERR_PTR(-EDEADLK))
+		return -EDEADLK;
+	else if (IS_ERR(batch))
+		return false;
 
 	addr = gen8_canonical_addr(vma->node.start + offset);
 	if (gen >= 8) {
@@ -1296,21 +1507,58 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 		*batch++ = target_addr;
 	}
 
-	return 0;
+	return true;
+}
+
+static int reloc_entry_gpu(struct i915_execbuffer *eb,
+			    struct i915_vma *vma,
+			    u64 offset,
+			    u64 target_addr)
+{
+	if (eb->reloc_cache.vaddr)
+		return false;
+
+	if (!use_reloc_gpu(vma))
+		return false;
+
+	return __reloc_entry_gpu(eb, vma, offset, target_addr);
 }
 
 static u64
-relocate_entry(struct i915_execbuffer *eb,
-	       struct i915_vma *vma,
+relocate_entry(struct i915_vma *vma,
 	       const struct drm_i915_gem_relocation_entry *reloc,
+	       struct i915_execbuffer *eb,
 	       const struct i915_vma *target)
 {
 	u64 target_addr = relocation_target(reloc, target);
-	int err;
-
-	err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr);
-	if (err)
-		return err;
+	u64 offset = reloc->offset;
+	int reloc_gpu = reloc_entry_gpu(eb, vma, offset, target_addr);
+
+	if (reloc_gpu < 0)
+		return reloc_gpu;
+
+	if (!reloc_gpu) {
+		bool wide = eb->reloc_cache.use_64bit_reloc;
+		void *vaddr;
+
+repeat:
+		vaddr = reloc_vaddr(vma->obj, eb,
+				    offset >> PAGE_SHIFT);
+		if (IS_ERR(vaddr))
+			return PTR_ERR(vaddr);
+
+		GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
+		clflush_write32(vaddr + offset_in_page(offset),
+				lower_32_bits(target_addr),
+				eb->reloc_cache.vaddr);
+
+		if (wide) {
+			offset += sizeof(u32);
+			target_addr >>= 32;
+			wide = false;
+			goto repeat;
+		}
+	}
 
 	return target->node.start | UPDATE;
 }
@@ -1375,7 +1623,8 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	 * If the relocation already has the right value in it, no
 	 * more work needs to be done.
 	 */
-	if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
+	if (!DBG_FORCE_RELOC &&
+	    gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
 		return 0;
 
 	/* Check that the relocation address is valid... */
@@ -1407,7 +1656,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	ev->flags &= ~EXEC_OBJECT_ASYNC;
 
 	/* and update the user's relocation entry */
-	return relocate_entry(eb, ev->vma, reloc, target->vma);
+	return relocate_entry(ev->vma, reloc, eb, target->vma);
 }
 
 static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
@@ -1444,9 +1693,13 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		 * we would try to acquire the struct mutex again. Obviously
 		 * this is bad and so lockdep complains vehemently.
 		 */
-		copied = __copy_from_user(r, urelocs, count * sizeof(r[0]));
-		if (unlikely(copied))
-			return -EFAULT;
+		pagefault_disable();
+		copied = __copy_from_user_inatomic(r, urelocs, count * sizeof(r[0]));
+		pagefault_enable();
+		if (unlikely(copied)) {
+			remain = -EFAULT;
+			goto out;
+		}
 
 		remain -= count;
 		do {
@@ -1454,7 +1707,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 
 			if (likely(offset == 0)) {
 			} else if ((s64)offset < 0) {
-				return (int)offset;
+				remain = (int)offset;
+				goto out;
 			} else {
 				/*
 				 * Note that reporting an error now
@@ -1484,74 +1738,401 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		} while (r++, --count);
 		urelocs += ARRAY_SIZE(stack);
 	} while (remain);
+out:
+	reloc_cache_reset(&eb->reloc_cache, eb);
+	return remain;
+}
 
-	return 0;
+static int
+eb_relocate_vma_slow(struct i915_execbuffer *eb, struct eb_vma *ev)
+{
+	const struct drm_i915_gem_exec_object2 *entry = ev->exec;
+	struct drm_i915_gem_relocation_entry *relocs =
+		u64_to_ptr(typeof(*relocs), entry->relocs_ptr);
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < entry->relocation_count; i++) {
+		u64 offset = eb_relocate_entry(eb, ev, &relocs[i]);
+
+		if ((s64)offset < 0) {
+			err = (int)offset;
+			goto err;
+		}
+	}
+	err = 0;
+err:
+	reloc_cache_reset(&eb->reloc_cache, eb);
+	return err;
+}
+
+static int check_relocations(const struct drm_i915_gem_exec_object2 *entry)
+{
+	const char __user *addr, *end;
+	unsigned long size;
+	char __maybe_unused c;
+
+	size = entry->relocation_count;
+	if (size == 0)
+		return 0;
+
+	if (size > N_RELOC(ULONG_MAX))
+		return -EINVAL;
+
+	addr = u64_to_user_ptr(entry->relocs_ptr);
+	size *= sizeof(struct drm_i915_gem_relocation_entry);
+	if (!access_ok(addr, size))
+		return -EFAULT;
+
+	end = addr + size;
+	for (; addr < end; addr += PAGE_SIZE) {
+		int err = __get_user(c, addr);
+		if (err)
+			return err;
+	}
+	return __get_user(c, end - 1);
 }
 
-static int eb_relocate(struct i915_execbuffer *eb)
+static int eb_copy_relocations(const struct i915_execbuffer *eb)
 {
+	struct drm_i915_gem_relocation_entry *relocs;
+	const unsigned int count = eb->buffer_count;
+	unsigned int i;
 	int err;
 
-	err = eb_lookup_vmas(eb);
-	if (err)
-		return err;
+	for (i = 0; i < count; i++) {
+		const unsigned int nreloc = eb->exec[i].relocation_count;
+		struct drm_i915_gem_relocation_entry __user *urelocs;
+		unsigned long size;
+		unsigned long copied;
+
+		if (nreloc == 0)
+			continue;
+
+		err = check_relocations(&eb->exec[i]);
+		if (err)
+			goto err;
+
+		urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
+		size = nreloc * sizeof(*relocs);
+
+		relocs = kvmalloc_array(size, 1, GFP_KERNEL);
+		if (!relocs) {
+			err = -ENOMEM;
+			goto err;
+		}
+
+		/* copy_from_user is limited to < 4GiB */
+		copied = 0;
+		do {
+			unsigned int len =
+				min_t(u64, BIT_ULL(31), size - copied);
+
+			if (__copy_from_user((char *)relocs + copied,
+					     (char __user *)urelocs + copied,
+					     len))
+				goto end;
+
+			copied += len;
+		} while (copied < size);
+
+		/*
+		 * As we do not update the known relocation offsets after
+		 * relocating (due to the complexities in lock handling),
+		 * we need to mark them as invalid now so that we force the
+		 * relocation processing next time. Just in case the target
+		 * object is evicted and then rebound into its old
+		 * presumed_offset before the next execbuffer - if that
+		 * happened we would make the mistake of assuming that the
+		 * relocations were valid.
+		 */
+		if (!user_access_begin(urelocs, size))
+			goto end;
+
+		for (copied = 0; copied < nreloc; copied++)
+			unsafe_put_user(-1,
+					&urelocs[copied].presumed_offset,
+					end_user);
+		user_access_end();
+
+		eb->exec[i].relocs_ptr = (uintptr_t)relocs;
+	}
+
+	return 0;
+
+end_user:
+	user_access_end();
+end:
+	kvfree(relocs);
+	err = -EFAULT;
+err:
+	while (i--) {
+		relocs = u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr);
+		if (eb->exec[i].relocation_count)
+			kvfree(relocs);
+	}
+	return err;
+}
+
+static int eb_prefault_relocations(const struct i915_execbuffer *eb)
+{
+	const unsigned int count = eb->buffer_count;
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		int err;
 
-	if (!list_empty(&eb->unbound)) {
-		err = eb_reserve(eb);
+		err = check_relocations(&eb->exec[i]);
 		if (err)
 			return err;
 	}
 
-	/* The objects are in their final locations, apply the relocations. */
-	if (eb->args->flags & __EXEC_HAS_RELOC) {
-		struct eb_vma *ev;
-		int flush;
+	return 0;
+}
 
-		list_for_each_entry(ev, &eb->relocs, reloc_link) {
+static noinline int eb_relocate_parse_slow(struct i915_execbuffer *eb,
+					   struct i915_request *rq)
+{
+	bool have_copy = false;
+	struct eb_vma *ev;
+	int err = 0;
+
+repeat:
+	if (signal_pending(current)) {
+		err = -ERESTARTSYS;
+		goto out;
+	}
+
+	/* We may process another execbuffer during the unlock... */
+	eb_release_vmas(eb, false);
+	i915_gem_ww_ctx_fini(&eb->ww);
+
+	if (rq) {
+		/* nonblocking is always false */
+		if (i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE,
+				      MAX_SCHEDULE_TIMEOUT) < 0) {
+			i915_request_put(rq);
+			rq = NULL;
+
+			err = -EINTR;
+			goto err_relock;
+		}
+
+		i915_request_put(rq);
+		rq = NULL;
+	}
+
+	/*
+	 * We take 3 passes through the slowpatch.
+	 *
+	 * 1 - we try to just prefault all the user relocation entries and
+	 * then attempt to reuse the atomic pagefault disabled fast path again.
+	 *
+	 * 2 - we copy the user entries to a local buffer here outside of the
+	 * local and allow ourselves to wait upon any rendering before
+	 * relocations
+	 *
+	 * 3 - we already have a local copy of the relocation entries, but
+	 * were interrupted (EAGAIN) whilst waiting for the objects, try again.
+	 */
+	if (!err) {
+		err = eb_prefault_relocations(eb);
+	} else if (!have_copy) {
+		err = eb_copy_relocations(eb);
+		have_copy = err == 0;
+	} else {
+		cond_resched();
+		err = 0;
+	}
+
+	if (!err)
+		flush_workqueue(eb->i915->mm.userptr_wq);
+
+err_relock:
+	i915_gem_ww_ctx_init(&eb->ww, true);
+	if (err)
+		goto out;
+
+	/* reacquire the objects */
+repeat_validate:
+	rq = eb_pin_engine(eb, false);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		rq = NULL;
+		goto err;
+	}
+
+	/* We didn't throttle, should be NULL */
+	GEM_WARN_ON(rq);
+
+	err = eb_validate_vmas(eb);
+	if (err)
+		goto err;
+
+	GEM_BUG_ON(!eb->batch);
+
+	list_for_each_entry(ev, &eb->relocs, reloc_link) {
+		if (!have_copy) {
+			pagefault_disable();
 			err = eb_relocate_vma(eb, ev);
+			pagefault_enable();
+			if (err)
+				break;
+		} else {
+			err = eb_relocate_vma_slow(eb, ev);
 			if (err)
 				break;
 		}
+	}
+
+	if (err == -EDEADLK)
+		goto err;
+
+	if (err && !have_copy)
+		goto repeat;
+
+	if (err)
+		goto err;
 
-		flush = reloc_gpu_flush(&eb->reloc_cache);
+	/* as last step, parse the command buffer */
+	err = eb_parse(eb);
+	if (err)
+		goto err;
+
+	/*
+	 * Leave the user relocations as are, this is the painfully slow path,
+	 * and we want to avoid the complication of dropping the lock whilst
+	 * having buffers reserved in the aperture and so causing spurious
+	 * ENOSPC for random operations.
+	 */
+
+err:
+	if (err == -EDEADLK) {
+		eb_release_vmas(eb, false);
+		err = i915_gem_ww_ctx_backoff(&eb->ww);
 		if (!err)
-			err = flush;
+			goto repeat_validate;
 	}
 
+	if (err == -EAGAIN)
+		goto repeat;
+
+out:
+	if (have_copy) {
+		const unsigned int count = eb->buffer_count;
+		unsigned int i;
+
+		for (i = 0; i < count; i++) {
+			const struct drm_i915_gem_exec_object2 *entry =
+				&eb->exec[i];
+			struct drm_i915_gem_relocation_entry *relocs;
+
+			if (!entry->relocation_count)
+				continue;
+
+			relocs = u64_to_ptr(typeof(*relocs), entry->relocs_ptr);
+			kvfree(relocs);
+		}
+	}
+
+	if (rq)
+		i915_request_put(rq);
+
 	return err;
 }
 
-static int eb_move_to_gpu(struct i915_execbuffer *eb)
+static int eb_relocate_parse(struct i915_execbuffer *eb)
 {
-	const unsigned int count = eb->buffer_count;
-	struct ww_acquire_ctx acquire;
-	unsigned int i;
-	int err = 0;
+	int err;
+	struct i915_request *rq = NULL;
+	bool throttle = true;
 
-	ww_acquire_init(&acquire, &reservation_ww_class);
+retry:
+	rq = eb_pin_engine(eb, throttle);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		rq = NULL;
+		if (err != -EDEADLK)
+			return err;
 
-	for (i = 0; i < count; i++) {
-		struct eb_vma *ev = &eb->vma[i];
-		struct i915_vma *vma = ev->vma;
+		goto err;
+	}
+
+	if (rq) {
+		bool nonblock = eb->file->filp->f_flags & O_NONBLOCK;
+
+		/* Need to drop all locks now for throttling, take slowpath */
+		err = i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE, 0);
+		if (err == -ETIME) {
+			if (nonblock) {
+				err = -EWOULDBLOCK;
+				i915_request_put(rq);
+				goto err;
+			}
+			goto slow;
+		}
+		i915_request_put(rq);
+		rq = NULL;
+	}
 
-		err = ww_mutex_lock_interruptible(&vma->resv->lock, &acquire);
-		if (err == -EDEADLK) {
-			GEM_BUG_ON(i == 0);
-			do {
-				int j = i - 1;
+	/* only throttle once, even if we didn't need to throttle */
+	throttle = false;
 
-				ww_mutex_unlock(&eb->vma[j].vma->resv->lock);
+	err = eb_validate_vmas(eb);
+	if (err == -EAGAIN)
+		goto slow;
+	else if (err)
+		goto err;
 
-				swap(eb->vma[i],  eb->vma[j]);
-			} while (--i);
+	/* The objects are in their final locations, apply the relocations. */
+	if (eb->args->flags & __EXEC_HAS_RELOC) {
+		struct eb_vma *ev;
 
-			err = ww_mutex_lock_slow_interruptible(&vma->resv->lock,
-							       &acquire);
+		list_for_each_entry(ev, &eb->relocs, reloc_link) {
+			err = eb_relocate_vma(eb, ev);
+			if (err)
+				break;
 		}
-		if (err)
-			break;
+
+		if (err == -EDEADLK)
+			goto err;
+		else if (err)
+			goto slow;
 	}
-	ww_acquire_done(&acquire);
+
+	if (!err)
+		err = eb_parse(eb);
+
+err:
+	if (err == -EDEADLK) {
+		eb_release_vmas(eb, false);
+		err = i915_gem_ww_ctx_backoff(&eb->ww);
+		if (!err)
+			goto retry;
+	}
+
+	return err;
+
+slow:
+	err = eb_relocate_parse_slow(eb, rq);
+	if (err)
+		/*
+		 * If the user expects the execobject.offset and
+		 * reloc.presumed_offset to be an exact match,
+		 * as for using NO_RELOC, then we cannot update
+		 * the execobject.offset until we have completed
+		 * relocation.
+		 */
+		eb->args->flags &= ~__EXEC_HAS_RELOC;
+
+	return err;
+}
+
+static int eb_move_to_gpu(struct i915_execbuffer *eb)
+{
+	const unsigned int count = eb->buffer_count;
+	unsigned int i = count;
+	int err = 0;
 
 	while (i--) {
 		struct eb_vma *ev = &eb->vma[i];
@@ -1596,13 +2177,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 
 		if (err == 0)
 			err = i915_vma_move_to_active(vma, eb->request, flags);
-
-		i915_vma_unlock(vma);
-		eb_unreserve_vma(ev);
 	}
-	ww_acquire_fini(&acquire);
-
-	eb_vma_array_put(fetch_and_zero(&eb->array));
 
 	if (unlikely(err))
 		goto err_skip;
@@ -1622,7 +2197,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
-	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
+	if (!(exec->flags & (I915_EXEC_FENCE_ARRAY |
+			     I915_EXEC_USE_EXTENSIONS))) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
 			return -EINVAL;
 	}
@@ -1666,7 +2242,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 }
 
 static struct i915_vma *
-shadow_batch_pin(struct drm_i915_gem_object *obj,
+shadow_batch_pin(struct i915_execbuffer *eb,
+		 struct drm_i915_gem_object *obj,
 		 struct i915_address_space *vm,
 		 unsigned int flags)
 {
@@ -1677,7 +2254,7 @@ shadow_batch_pin(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		return vma;
 
-	err = i915_vma_pin(vma, 0, 0, flags);
+	err = i915_vma_pin_ww(vma, &eb->ww, 0, 0, flags);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1729,7 +2306,7 @@ __parser_mark_active(struct i915_vma *vma,
 {
 	struct intel_gt_buffer_pool_node *node = vma->private;
 
-	return i915_active_ref(&node->active, tl, fence);
+	return i915_active_ref(&node->active, tl->fence_context, fence);
 }
 
 static int
@@ -1793,36 +2370,26 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb,
 	if (err)
 		goto err_commit;
 
-	err = dma_resv_lock_interruptible(pw->batch->resv, NULL);
-	if (err)
-		goto err_commit;
-
 	err = dma_resv_reserve_shared(pw->batch->resv, 1);
 	if (err)
-		goto err_commit_unlock;
+		goto err_commit;
 
 	/* Wait for all writes (and relocs) into the batch to complete */
 	err = i915_sw_fence_await_reservation(&pw->base.chain,
 					      pw->batch->resv, NULL, false,
 					      0, I915_FENCE_GFP);
 	if (err < 0)
-		goto err_commit_unlock;
+		goto err_commit;
 
 	/* Keep the batch alive and unwritten as we parse */
 	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
 
-	dma_resv_unlock(pw->batch->resv);
-
 	/* Force execution to wait for completion of the parser */
-	dma_resv_lock(shadow->resv, NULL);
 	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-	dma_resv_unlock(shadow->resv);
 
 	dma_fence_work_commit_imm(&pw->base);
 	return 0;
 
-err_commit_unlock:
-	dma_resv_unlock(pw->batch->resv);
 err_commit:
 	i915_sw_fence_set_error_once(&pw->base.chain, err);
 	dma_fence_work_commit_imm(&pw->base);
@@ -1837,16 +2404,33 @@ err_free:
 	return err;
 }
 
+static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
+{
+	/*
+	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
+	 * batch" bit. Hence we need to pin secure batches into the global gtt.
+	 * hsw should have this fixed, but bdw mucks it up again. */
+	if (eb->batch_flags & I915_DISPATCH_SECURE)
+		return i915_gem_object_ggtt_pin_ww(vma->obj, &eb->ww, NULL, 0, 0, 0);
+
+	return NULL;
+}
+
 static int eb_parse(struct i915_execbuffer *eb)
 {
 	struct drm_i915_private *i915 = eb->i915;
-	struct intel_gt_buffer_pool_node *pool;
-	struct i915_vma *shadow, *trampoline;
+	struct intel_gt_buffer_pool_node *pool = eb->batch_pool;
+	struct i915_vma *shadow, *trampoline, *batch;
 	unsigned int len;
 	int err;
 
-	if (!eb_use_cmdparser(eb))
-		return 0;
+	if (!eb_use_cmdparser(eb)) {
+		batch = eb_dispatch_secure(eb, eb->batch->vma);
+		if (IS_ERR(batch))
+			return PTR_ERR(batch);
+
+		goto secure_batch;
+	}
 
 	len = eb->batch_len;
 	if (!CMDPARSER_USES_GGTT(eb->i915)) {
@@ -1863,11 +2447,18 @@ static int eb_parse(struct i915_execbuffer *eb)
 		len += I915_CMD_PARSER_TRAMPOLINE_SIZE;
 	}
 
-	pool = intel_gt_get_buffer_pool(eb->engine->gt, len);
-	if (IS_ERR(pool))
-		return PTR_ERR(pool);
+	if (!pool) {
+		pool = intel_gt_get_buffer_pool(eb->engine->gt, len);
+		if (IS_ERR(pool))
+			return PTR_ERR(pool);
+		eb->batch_pool = pool;
+	}
 
-	shadow = shadow_batch_pin(pool->obj, eb->context->vm, PIN_USER);
+	err = i915_gem_object_lock(pool->obj, &eb->ww);
+	if (err)
+		goto err;
+
+	shadow = shadow_batch_pin(eb, pool->obj, eb->context->vm, PIN_USER);
 	if (IS_ERR(shadow)) {
 		err = PTR_ERR(shadow);
 		goto err;
@@ -1879,7 +2470,7 @@ static int eb_parse(struct i915_execbuffer *eb)
 	if (CMDPARSER_USES_GGTT(eb->i915)) {
 		trampoline = shadow;
 
-		shadow = shadow_batch_pin(pool->obj,
+		shadow = shadow_batch_pin(eb, pool->obj,
 					  &eb->engine->gt->ggtt->vm,
 					  PIN_GLOBAL);
 		if (IS_ERR(shadow)) {
@@ -1892,42 +2483,43 @@ static int eb_parse(struct i915_execbuffer *eb)
 		eb->batch_flags |= I915_DISPATCH_SECURE;
 	}
 
+	batch = eb_dispatch_secure(eb, shadow);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto err_trampoline;
+	}
+
 	err = eb_parse_pipeline(eb, shadow, trampoline);
 	if (err)
-		goto err_trampoline;
+		goto err_unpin_batch;
 
-	eb->vma[eb->buffer_count].vma = i915_vma_get(shadow);
-	eb->vma[eb->buffer_count].flags = __EXEC_OBJECT_HAS_PIN;
 	eb->batch = &eb->vma[eb->buffer_count++];
-	eb->vma[eb->buffer_count].vma = NULL;
+	eb->batch->vma = i915_vma_get(shadow);
+	eb->batch->flags = __EXEC_OBJECT_HAS_PIN;
 
 	eb->trampoline = trampoline;
 	eb->batch_start_offset = 0;
 
+secure_batch:
+	if (batch) {
+		eb->batch = &eb->vma[eb->buffer_count++];
+		eb->batch->flags = __EXEC_OBJECT_HAS_PIN;
+		eb->batch->vma = i915_vma_get(batch);
+	}
 	return 0;
 
+err_unpin_batch:
+	if (batch)
+		i915_vma_unpin(batch);
 err_trampoline:
 	if (trampoline)
 		i915_vma_unpin(trampoline);
 err_shadow:
 	i915_vma_unpin(shadow);
 err:
-	intel_gt_buffer_pool_put(pool);
 	return err;
 }
 
-static void
-add_to_client(struct i915_request *rq, struct drm_file *file)
-{
-	struct drm_i915_file_private *file_priv = file->driver_priv;
-
-	rq->file_priv = file_priv;
-
-	spin_lock(&file_priv->mm.lock);
-	list_add_tail(&rq->client_link, &file_priv->mm.request_list);
-	spin_unlock(&file_priv->mm.lock);
-}
-
 static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch)
 {
 	int err;
@@ -2009,7 +2601,7 @@ static const enum intel_engine_id user_ring_map[] = {
 	[I915_EXEC_VEBOX]	= VECS0
 };
 
-static struct i915_request *eb_throttle(struct intel_context *ce)
+static struct i915_request *eb_throttle(struct i915_execbuffer *eb, struct intel_context *ce)
 {
 	struct intel_ring *ring = ce->ring;
 	struct intel_timeline *tl = ce->timeline;
@@ -2043,31 +2635,26 @@ static struct i915_request *eb_throttle(struct intel_context *ce)
 	return i915_request_get(rq);
 }
 
-static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
+static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb, bool throttle)
 {
+	struct intel_context *ce = eb->context;
 	struct intel_timeline *tl;
-	struct i915_request *rq;
+	struct i915_request *rq = NULL;
 	int err;
 
-	/*
-	 * ABI: Before userspace accesses the GPU (e.g. execbuffer), report
-	 * EIO if the GPU is already wedged.
-	 */
-	err = intel_gt_terminally_wedged(ce->engine->gt);
-	if (err)
-		return err;
+	GEM_BUG_ON(eb->args->flags & __EXEC_ENGINE_PINNED);
 
 	if (unlikely(intel_context_is_banned(ce)))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	/*
 	 * Pinning the contexts may generate requests in order to acquire
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	err = intel_context_pin(ce);
+	err = intel_context_pin_ww(ce, &eb->ww);
 	if (err)
-		return err;
+		return ERR_PTR(err);
 
 	/*
 	 * Take a local wakeref for preparing to dispatch the execbuf as
@@ -2079,45 +2666,17 @@ static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 	 */
 	tl = intel_context_timeline_lock(ce);
 	if (IS_ERR(tl)) {
-		err = PTR_ERR(tl);
-		goto err_unpin;
+		intel_context_unpin(ce);
+		return ERR_CAST(tl);
 	}
 
 	intel_context_enter(ce);
-	rq = eb_throttle(ce);
-
+	if (throttle)
+		rq = eb_throttle(eb, ce);
 	intel_context_timeline_unlock(tl);
 
-	if (rq) {
-		bool nonblock = eb->file->filp->f_flags & O_NONBLOCK;
-		long timeout;
-
-		timeout = MAX_SCHEDULE_TIMEOUT;
-		if (nonblock)
-			timeout = 0;
-
-		timeout = i915_request_wait(rq,
-					    I915_WAIT_INTERRUPTIBLE,
-					    timeout);
-		i915_request_put(rq);
-
-		if (timeout < 0) {
-			err = nonblock ? -EWOULDBLOCK : timeout;
-			goto err_exit;
-		}
-	}
-
-	eb->engine = ce->engine;
-	eb->context = ce;
-	return 0;
-
-err_exit:
-	mutex_lock(&tl->mutex);
-	intel_context_exit(ce);
-	intel_context_timeline_unlock(tl);
-err_unpin:
-	intel_context_unpin(ce);
-	return err;
+	eb->args->flags |= __EXEC_ENGINE_PINNED;
+	return rq;
 }
 
 static void eb_unpin_engine(struct i915_execbuffer *eb)
@@ -2125,6 +2684,11 @@ static void eb_unpin_engine(struct i915_execbuffer *eb)
 	struct intel_context *ce = eb->context;
 	struct intel_timeline *tl = ce->timeline;
 
+	if (!(eb->args->flags & __EXEC_ENGINE_PINNED))
+		return;
+
+	eb->args->flags &= ~__EXEC_ENGINE_PINNED;
+
 	mutex_lock(&tl->mutex);
 	intel_context_exit(ce);
 	mutex_unlock(&tl->mutex);
@@ -2133,11 +2697,10 @@ static void eb_unpin_engine(struct i915_execbuffer *eb)
 }
 
 static unsigned int
-eb_select_legacy_ring(struct i915_execbuffer *eb,
-		      struct drm_file *file,
-		      struct drm_i915_gem_execbuffer2 *args)
+eb_select_legacy_ring(struct i915_execbuffer *eb)
 {
 	struct drm_i915_private *i915 = eb->i915;
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
 	unsigned int user_ring_id = args->flags & I915_EXEC_RING_MASK;
 
 	if (user_ring_id != I915_EXEC_BSD &&
@@ -2152,7 +2715,7 @@ eb_select_legacy_ring(struct i915_execbuffer *eb,
 		unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK;
 
 		if (bsd_idx == I915_EXEC_BSD_DEFAULT) {
-			bsd_idx = gen8_dispatch_bsd_engine(i915, file);
+			bsd_idx = gen8_dispatch_bsd_engine(i915, eb->file);
 		} else if (bsd_idx >= I915_EXEC_BSD_RING1 &&
 			   bsd_idx <= I915_EXEC_BSD_RING2) {
 			bsd_idx >>= I915_EXEC_BSD_SHIFT;
@@ -2177,131 +2740,297 @@ eb_select_legacy_ring(struct i915_execbuffer *eb,
 }
 
 static int
-eb_pin_engine(struct i915_execbuffer *eb,
-	      struct drm_file *file,
-	      struct drm_i915_gem_execbuffer2 *args)
+eb_select_engine(struct i915_execbuffer *eb)
 {
 	struct intel_context *ce;
 	unsigned int idx;
 	int err;
 
 	if (i915_gem_context_user_engines(eb->gem_context))
-		idx = args->flags & I915_EXEC_RING_MASK;
+		idx = eb->args->flags & I915_EXEC_RING_MASK;
 	else
-		idx = eb_select_legacy_ring(eb, file, args);
+		idx = eb_select_legacy_ring(eb);
 
 	ce = i915_gem_context_get_engine(eb->gem_context, idx);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	err = __eb_pin_engine(eb, ce);
-	intel_context_put(ce);
+	intel_gt_pm_get(ce->engine->gt);
+
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
+		err = intel_context_alloc_state(ce);
+		if (err)
+			goto err;
+	}
+
+	/*
+	 * ABI: Before userspace accesses the GPU (e.g. execbuffer), report
+	 * EIO if the GPU is already wedged.
+	 */
+	err = intel_gt_terminally_wedged(ce->engine->gt);
+	if (err)
+		goto err;
+
+	eb->context = ce;
+	eb->engine = ce->engine;
+
+	/*
+	 * Make sure engine pool stays alive even if we call intel_context_put
+	 * during ww handling. The pool is destroyed when last pm reference
+	 * is dropped, which breaks our -EDEADLK handling.
+	 */
+	return err;
 
+err:
+	intel_gt_pm_put(ce->engine->gt);
+	intel_context_put(ce);
 	return err;
 }
 
 static void
-__free_fence_array(struct drm_syncobj **fences, unsigned int n)
+eb_put_engine(struct i915_execbuffer *eb)
 {
-	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+	intel_gt_pm_put(eb->engine->gt);
+	intel_context_put(eb->context);
+}
+
+static void
+__free_fence_array(struct eb_fence *fences, unsigned int n)
+{
+	while (n--) {
+		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
+		dma_fence_put(fences[n].dma_fence);
+		kfree(fences[n].chain_fence);
+	}
 	kvfree(fences);
 }
 
-static struct drm_syncobj **
-get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_file *file)
+static int
+add_timeline_fence_array(struct i915_execbuffer *eb,
+			 const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences)
 {
-	const unsigned long nfences = args->num_cliprects;
-	struct drm_i915_gem_exec_fence __user *user;
-	struct drm_syncobj **fences;
-	unsigned long n;
-	int err;
+	struct drm_i915_gem_exec_fence __user *user_fences;
+	u64 __user *user_values;
+	struct eb_fence *f;
+	u64 nfences;
+	int err = 0;
 
-	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
-		return NULL;
+	nfences = timeline_fences->fence_count;
+	if (!nfences)
+		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
-			    ULONG_MAX / sizeof(*user),
-			    SIZE_MAX / sizeof(*fences)))
-		return ERR_PTR(-EINVAL);
+			    ULONG_MAX / sizeof(*user_fences),
+			    SIZE_MAX / sizeof(*f)) - eb->num_fences)
+		return -EINVAL;
 
-	user = u64_to_user_ptr(args->cliprects_ptr);
-	if (!access_ok(user, nfences * sizeof(*user)))
-		return ERR_PTR(-EFAULT);
+	user_fences = u64_to_user_ptr(timeline_fences->handles_ptr);
+	if (!access_ok(user_fences, nfences * sizeof(*user_fences)))
+		return -EFAULT;
+
+	user_values = u64_to_user_ptr(timeline_fences->values_ptr);
+	if (!access_ok(user_values, nfences * sizeof(*user_values)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + nfences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
 
-	fences = kvmalloc_array(nfences, sizeof(*fences),
-				__GFP_NOWARN | GFP_KERNEL);
-	if (!fences)
-		return ERR_PTR(-ENOMEM);
+	eb->fences = f;
+	f += eb->num_fences;
 
-	for (n = 0; n < nfences; n++) {
-		struct drm_i915_gem_exec_fence fence;
+	BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
+		     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
+
+	while (nfences--) {
+		struct drm_i915_gem_exec_fence user_fence;
 		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+		u64 point;
 
-		if (__copy_from_user(&fence, user++, sizeof(fence))) {
-			err = -EFAULT;
-			goto err;
+		if (__copy_from_user(&user_fence,
+				     user_fences++,
+				     sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		if (__get_user(point, user_values++))
+			return -EFAULT;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
+		if (!syncobj) {
+			DRM_DEBUG("Invalid syncobj handle provided\n");
+			return -ENOENT;
 		}
 
-		if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
-			err = -EINVAL;
-			goto err;
+		fence = drm_syncobj_fence_get(syncobj);
+
+		if (!fence && user_fence.flags &&
+		    !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle has no fence\n");
+			drm_syncobj_put(syncobj);
+			return -EINVAL;
+		}
+
+		if (fence)
+			err = dma_fence_chain_find_seqno(&fence, point);
+
+		if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle missing requested point %llu\n", point);
+			dma_fence_put(fence);
+			drm_syncobj_put(syncobj);
+			return err;
+		}
+
+		/*
+		 * A point might have been signaled already and
+		 * garbage collected from the timeline. In this case
+		 * just ignore the point and carry on.
+		 */
+		if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			drm_syncobj_put(syncobj);
+			continue;
+		}
+
+		/*
+		 * For timeline syncobjs we need to preallocate chains for
+		 * later signaling.
+		 */
+		if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) {
+			/*
+			 * Waiting and signaling the same point (when point !=
+			 * 0) would break the timeline.
+			 */
+			if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+				DRM_DEBUG("Trying to wait & signal the same timeline point.\n");
+				dma_fence_put(fence);
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
+
+			f->chain_fence =
+				kmalloc(sizeof(*f->chain_fence),
+					GFP_KERNEL);
+			if (!f->chain_fence) {
+				drm_syncobj_put(syncobj);
+				dma_fence_put(fence);
+				return -ENOMEM;
+			}
+		} else {
+			f->chain_fence = NULL;
 		}
 
-		syncobj = drm_syncobj_find(file, fence.handle);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = point;
+		f++;
+		eb->num_fences++;
+	}
+
+	return 0;
+}
+
+static int add_fence_array(struct i915_execbuffer *eb)
+{
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
+	struct drm_i915_gem_exec_fence __user *user;
+	unsigned long num_fences = args->num_cliprects;
+	struct eb_fence *f;
+
+	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+		return 0;
+
+	if (!num_fences)
+		return 0;
+
+	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
+	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
+	if (num_fences > min_t(unsigned long,
+			       ULONG_MAX / sizeof(*user),
+			       SIZE_MAX / sizeof(*f) - eb->num_fences))
+		return -EINVAL;
+
+	user = u64_to_user_ptr(args->cliprects_ptr);
+	if (!access_ok(user, num_fences * sizeof(*user)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + num_fences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
+	while (num_fences--) {
+		struct drm_i915_gem_exec_fence user_fence;
+		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+
+		if (__copy_from_user(&user_fence, user++, sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
-			err = -ENOENT;
-			goto err;
+			return -ENOENT;
+		}
+
+		if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+			fence = drm_syncobj_fence_get(syncobj);
+			if (!fence) {
+				DRM_DEBUG("Syncobj handle has no fence\n");
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
 		}
 
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = 0;
+		f->chain_fence = NULL;
+		f++;
+		eb->num_fences++;
 	}
 
-	return fences;
-
-err:
-	__free_fence_array(fences, n);
-	return ERR_PTR(err);
+	return 0;
 }
 
-static void
-put_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_syncobj **fences)
+static void put_fence_array(struct eb_fence *fences, int num_fences)
 {
 	if (fences)
-		__free_fence_array(fences, args->num_cliprects);
+		__free_fence_array(fences, num_fences);
 }
 
 static int
-await_fence_array(struct i915_execbuffer *eb,
-		  struct drm_syncobj **fences)
+await_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
-		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
-		if (!(flags & I915_EXEC_FENCE_WAIT))
-			continue;
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 
-		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!eb->fences[n].dma_fence)
+			continue;
 
-		err = i915_request_await_dma_fence(eb->request, fence);
-		dma_fence_put(fence);
+		err = i915_request_await_dma_fence(eb->request,
+						   eb->fences[n].dma_fence);
 		if (err < 0)
 			return err;
 	}
@@ -2309,26 +3038,47 @@ await_fence_array(struct i915_execbuffer *eb,
 	return 0;
 }
 
-static void
-signal_fence_array(struct i915_execbuffer *eb,
-		   struct drm_syncobj **fences)
+static void signal_fence_array(const struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		if (eb->fences[n].chain_fence) {
+			drm_syncobj_add_point(syncobj,
+					      eb->fences[n].chain_fence,
+					      fence,
+					      eb->fences[n].value);
+			/*
+			 * The chain's ownership is transferred to the
+			 * timeline.
+			 */
+			eb->fences[n].chain_fence = NULL;
+		} else {
+			drm_syncobj_replace_fence(syncobj, fence);
+		}
 	}
 }
 
+static int
+parse_timeline_fences(struct i915_user_extension __user *ext, void *data)
+{
+	struct i915_execbuffer *eb = data;
+	struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences;
+
+	if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences)))
+		return -EFAULT;
+
+	return add_timeline_fence_array(eb, &timeline_fences);
+}
+
 static void retire_requests(struct intel_timeline *tl, struct i915_request *end)
 {
 	struct i915_request *rq, *rn;
@@ -2370,12 +3120,37 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	mutex_unlock(&tl->mutex);
 }
 
+static const i915_user_extension_fn execbuf_extensions[] = {
+	[DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences,
+};
+
+static int
+parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
+			  struct i915_execbuffer *eb)
+{
+	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
+		return 0;
+
+	/* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot
+	 * have another flag also using it at the same time.
+	 */
+	if (eb->args->flags & I915_EXEC_FENCE_ARRAY)
+		return -EINVAL;
+
+	if (args->num_cliprects != 0)
+		return -EINVAL;
+
+	return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr),
+				    execbuf_extensions,
+				    ARRAY_SIZE(execbuf_extensions),
+				    eb);
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct drm_syncobj **fences)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
@@ -2392,10 +3167,14 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
-	if (!(args->flags & I915_EXEC_NO_RELOC))
+	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
 		args->flags |= __EXEC_HAS_RELOC;
 
 	eb.exec = exec;
+	eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1);
+	eb.vma[0].vma = NULL;
+	eb.reloc_pool = eb.batch_pool = NULL;
+	eb.reloc_context = NULL;
 
 	eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
 	reloc_cache_init(&eb.reloc_cache, eb.i915);
@@ -2405,6 +3184,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.batch_len = args->batch_len;
 	eb.trampoline = NULL;
 
+	eb.fences = NULL;
+	eb.num_fences = 0;
+
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
 		if (INTEL_GEN(i915) >= 11)
@@ -2422,14 +3204,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
+	err = parse_execbuf2_extensions(args, &eb);
+	if (err)
+		goto err_ext;
+
+	err = add_fence_array(&eb);
+	if (err)
+		goto err_ext;
+
 #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
 	if (args->flags & IN_FENCES) {
 		if ((args->flags & IN_FENCES) == IN_FENCES)
 			return -EINVAL;
 
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!in_fence)
-			return -EINVAL;
+		if (!in_fence) {
+			err = -EINVAL;
+			goto err_ext;
+		}
 	}
 #undef IN_FENCES
 
@@ -2451,11 +3243,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (unlikely(err))
 		goto err_destroy;
 
-	err = eb_pin_engine(&eb, file, args);
+	err = eb_select_engine(&eb);
 	if (unlikely(err))
 		goto err_context;
 
-	err = eb_relocate(&eb);
+	err = eb_lookup_vmas(&eb);
+	if (err) {
+		eb_release_vmas(&eb, true);
+		goto err_engine;
+	}
+
+	i915_gem_ww_ctx_init(&eb.ww, true);
+
+	err = eb_relocate_parse(&eb);
 	if (err) {
 		/*
 		 * If the user expects the execobject.offset and
@@ -2468,54 +3268,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_vma;
 	}
 
-	if (unlikely(eb.batch->flags & EXEC_OBJECT_WRITE)) {
-		drm_dbg(&i915->drm,
-			"Attempting to use self-modifying batch buffer\n");
-		err = -EINVAL;
-		goto err_vma;
-	}
-
-	if (range_overflows_t(u64,
-			      eb.batch_start_offset, eb.batch_len,
-			      eb.batch->vma->size)) {
-		drm_dbg(&i915->drm, "Attempting to use out-of-bounds batch\n");
-		err = -EINVAL;
-		goto err_vma;
-	}
-
-	if (eb.batch_len == 0)
-		eb.batch_len = eb.batch->vma->size - eb.batch_start_offset;
+	ww_acquire_done(&eb.ww.ctx);
 
-	err = eb_parse(&eb);
-	if (err)
-		goto err_vma;
-
-	/*
-	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
-	 * batch" bit. Hence we need to pin secure batches into the global gtt.
-	 * hsw should have this fixed, but bdw mucks it up again. */
 	batch = eb.batch->vma;
-	if (eb.batch_flags & I915_DISPATCH_SECURE) {
-		struct i915_vma *vma;
-
-		/*
-		 * So on first glance it looks freaky that we pin the batch here
-		 * outside of the reservation loop. But:
-		 * - The batch is already pinned into the relevant ppgtt, so we
-		 *   already have the backing storage fully allocated.
-		 * - No other BO uses the global gtt (well contexts, but meh),
-		 *   so we don't really have issues with multiple objects not
-		 *   fitting due to fragmentation.
-		 * So this is actually safe.
-		 */
-		vma = i915_gem_object_ggtt_pin(batch->obj, NULL, 0, 0, 0);
-		if (IS_ERR(vma)) {
-			err = PTR_ERR(vma);
-			goto err_parse;
-		}
-
-		batch = vma;
-	}
 
 	/* All GPU relocation batches must be submitted prior to the user rq */
 	GEM_BUG_ON(eb.reloc_cache.rq);
@@ -2524,7 +3279,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.request = i915_request_create(eb.context);
 	if (IS_ERR(eb.request)) {
 		err = PTR_ERR(eb.request);
-		goto err_batch_unpin;
+		goto err_vma;
 	}
 
 	if (in_fence) {
@@ -2539,8 +3294,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (fences) {
-		err = await_fence_array(&eb, fences);
+	if (eb.fences) {
+		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
 	}
@@ -2561,18 +3316,17 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	 * to explicitly hold another reference here.
 	 */
 	eb.request->batch = batch;
-	if (batch->private)
-		intel_gt_buffer_pool_mark_active(batch->private, eb.request);
+	if (eb.batch_pool)
+		intel_gt_buffer_pool_mark_active(eb.batch_pool, eb.request);
 
 	trace_i915_request_queue(eb.request, eb.batch_flags);
 	err = eb_submit(&eb, batch);
 err_request:
-	add_to_client(eb.request, file);
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (fences)
-		signal_fence_array(&eb, fences);
+	if (eb.fences)
+		signal_fence_array(&eb);
 
 	if (out_fence) {
 		if (err == 0) {
@@ -2586,16 +3340,21 @@ err_request:
 	}
 	i915_request_put(eb.request);
 
-err_batch_unpin:
-	if (eb.batch_flags & I915_DISPATCH_SECURE)
-		i915_vma_unpin(batch);
-err_parse:
-	if (batch->private)
-		intel_gt_buffer_pool_put(batch->private);
 err_vma:
+	eb_release_vmas(&eb, true);
 	if (eb.trampoline)
 		i915_vma_unpin(eb.trampoline);
-	eb_unpin_engine(&eb);
+	WARN_ON(err == -EDEADLK);
+	i915_gem_ww_ctx_fini(&eb.ww);
+
+	if (eb.batch_pool)
+		intel_gt_buffer_pool_put(eb.batch_pool);
+	if (eb.reloc_pool)
+		intel_gt_buffer_pool_put(eb.reloc_pool);
+	if (eb.reloc_context)
+		intel_context_put(eb.reloc_context);
+err_engine:
+	eb_put_engine(&eb);
 err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
@@ -2605,12 +3364,14 @@ err_out_fence:
 		put_unused_fd(out_fence_fd);
 err_in_fence:
 	dma_fence_put(in_fence);
+err_ext:
+	put_fence_array(eb.fences, eb.num_fences);
 	return err;
 }
 
 static size_t eb_element_size(void)
 {
-	return sizeof(struct drm_i915_gem_exec_object2);
+	return sizeof(struct drm_i915_gem_exec_object2) + sizeof(struct eb_vma);
 }
 
 static bool check_buffer_count(size_t count)
@@ -2666,7 +3427,9 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 	/* Copy in the exec list from userland */
 	exec_list = kvmalloc_array(count, sizeof(*exec_list),
 				   __GFP_NOWARN | GFP_KERNEL);
-	exec2_list = kvmalloc_array(count, eb_element_size(),
+
+	/* Allocate extra slots for use by the command parser */
+	exec2_list = kvmalloc_array(count + 2, eb_element_size(),
 				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec_list == NULL || exec2_list == NULL) {
 		drm_dbg(&i915->drm,
@@ -2699,7 +3462,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 			exec2_list[i].flags = 0;
 	}
 
-	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
+	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list);
 	if (exec2.flags & __EXEC_HAS_RELOC) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
 			u64_to_user_ptr(args->buffers_ptr);
@@ -2731,7 +3494,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
-	struct drm_syncobj **fences = NULL;
 	const size_t count = args->buffer_count;
 	int err;
 
@@ -2744,7 +3506,8 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	if (err)
 		return err;
 
-	exec2_list = kvmalloc_array(count, eb_element_size(),
+	/* Allocate extra slots for use by the command parser */
+	exec2_list = kvmalloc_array(count + 2, eb_element_size(),
 				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec2_list == NULL) {
 		drm_dbg(&i915->drm, "Failed to allocate exec list for %zd buffers\n",
@@ -2759,15 +3522,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	if (args->flags & I915_EXEC_FENCE_ARRAY) {
-		fences = get_fence_array(args, file);
-		if (IS_ERR(fences)) {
-			kvfree(exec2_list);
-			return PTR_ERR(fences);
-		}
-	}
-
-	err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
+	err = i915_gem_do_execbuffer(dev, file, args, exec2_list);
 
 	/*
 	 * Now that we have begun execution of the batchbuffer, we ignore
@@ -2808,7 +3563,6 @@ end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
-	put_fence_array(args, fences);
 	kvfree(exec2_list);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index b23368529a40..3d69e51f3e4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -209,7 +209,7 @@ static vm_fault_t i915_error_to_vmf_fault(int err)
 	switch (err) {
 	default:
 		WARN_ONCE(err, "unhandled error in %s: %i\n", __func__, err);
-		/* fallthrough */
+		fallthrough;
 	case -EIO: /* shmemfs failure from swap device */
 	case -EFAULT: /* purged object */
 	case -ENODEV: /* bad object, how did you get here! */
@@ -283,37 +283,46 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 	struct intel_runtime_pm *rpm = &i915->runtime_pm;
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	bool write = area->vm_flags & VM_WRITE;
+	struct i915_gem_ww_ctx ww;
 	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	pgoff_t page_offset;
 	int srcu;
 	int ret;
 
-	/* Sanity check that we allow writing into this object */
-	if (i915_gem_object_is_readonly(obj) && write)
-		return VM_FAULT_SIGBUS;
-
 	/* We don't use vmf->pgoff since that has the fake offset */
 	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
 
 	trace_i915_gem_object_fault(obj, page_offset, true, write);
 
-	ret = i915_gem_object_pin_pages(obj);
+	wakeref = intel_runtime_pm_get(rpm);
+
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	ret = i915_gem_object_lock(obj, &ww);
 	if (ret)
-		goto err;
+		goto err_rpm;
 
-	wakeref = intel_runtime_pm_get(rpm);
+	/* Sanity check that we allow writing into this object */
+	if (i915_gem_object_is_readonly(obj) && write) {
+		ret = -EFAULT;
+		goto err_rpm;
+	}
 
-	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	ret = i915_gem_object_pin_pages(obj);
 	if (ret)
 		goto err_rpm;
 
+	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	if (ret)
+		goto err_pages;
+
 	/* Now pin it into the GTT as needed */
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
-				       PIN_MAPPABLE |
-				       PIN_NONBLOCK /* NOWARN */ |
-				       PIN_NOEVICT);
-	if (IS_ERR(vma)) {
+	vma = i915_gem_object_ggtt_pin_ww(obj, &ww, NULL, 0, 0,
+					  PIN_MAPPABLE |
+					  PIN_NONBLOCK /* NOWARN */ |
+					  PIN_NOEVICT);
+	if (IS_ERR(vma) && vma != ERR_PTR(-EDEADLK)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
 			compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
@@ -328,11 +337,11 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 		 * all hope that the hardware is able to track future writes.
 		 */
 
-		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
-		if (IS_ERR(vma)) {
+		vma = i915_gem_object_ggtt_pin_ww(obj, &ww, &view, 0, 0, flags);
+		if (IS_ERR(vma) && vma != ERR_PTR(-EDEADLK)) {
 			flags = PIN_MAPPABLE;
 			view.type = I915_GGTT_VIEW_PARTIAL;
-			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+			vma = i915_gem_object_ggtt_pin_ww(obj, &ww, &view, 0, 0, flags);
 		}
 
 		/* The entire mappable GGTT is pinned? Unexpected! */
@@ -389,10 +398,16 @@ err_unpin:
 	__i915_vma_unpin(vma);
 err_reset:
 	intel_gt_reset_unlock(ggtt->vm.gt, srcu);
+err_pages:
+	i915_gem_object_unpin_pages(obj);
 err_rpm:
+	if (ret == -EDEADLK) {
+		ret = i915_gem_ww_ctx_backoff(&ww);
+		if (!ret)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
 	intel_runtime_pm_put(rpm, wakeref);
-	i915_gem_object_unpin_pages(obj);
-err:
 	return i915_error_to_vmf_fault(ret);
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index e5b9276d254c..d46db8d8f38e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -110,20 +110,44 @@ i915_gem_object_put(struct drm_i915_gem_object *obj)
 
 #define assert_object_held(obj) dma_resv_assert_held((obj)->base.resv)
 
-static inline void i915_gem_object_lock(struct drm_i915_gem_object *obj)
+static inline int __i915_gem_object_lock(struct drm_i915_gem_object *obj,
+					 struct i915_gem_ww_ctx *ww,
+					 bool intr)
 {
-	dma_resv_lock(obj->base.resv, NULL);
+	int ret;
+
+	if (intr)
+		ret = dma_resv_lock_interruptible(obj->base.resv, ww ? &ww->ctx : NULL);
+	else
+		ret = dma_resv_lock(obj->base.resv, ww ? &ww->ctx : NULL);
+
+	if (!ret && ww)
+		list_add_tail(&obj->obj_link, &ww->obj_list);
+	if (ret == -EALREADY)
+		ret = 0;
+
+	if (ret == -EDEADLK)
+		ww->contended = obj;
+
+	return ret;
 }
 
-static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj)
+static inline int i915_gem_object_lock(struct drm_i915_gem_object *obj,
+				       struct i915_gem_ww_ctx *ww)
 {
-	return dma_resv_trylock(obj->base.resv);
+	return __i915_gem_object_lock(obj, ww, ww && ww->intr);
 }
 
-static inline int
-i915_gem_object_lock_interruptible(struct drm_i915_gem_object *obj)
+static inline int i915_gem_object_lock_interruptible(struct drm_i915_gem_object *obj,
+						     struct i915_gem_ww_ctx *ww)
 {
-	return dma_resv_lock_interruptible(obj->base.resv, NULL);
+	WARN_ON(ww && !ww->intr);
+	return __i915_gem_object_lock(obj, ww, true);
+}
+
+static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj)
+{
+	return dma_resv_trylock(obj->base.resv);
 }
 
 static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj)
@@ -258,6 +282,10 @@ struct page *
 i915_gem_object_get_page(struct drm_i915_gem_object *obj,
 			 unsigned int n);
 
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n);
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,
@@ -408,7 +436,6 @@ static inline void
 i915_gem_object_finish_access(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_pages(obj);
-	i915_gem_object_unlock(obj);
 }
 
 static inline struct intel_engine_cs *
@@ -431,6 +458,7 @@ i915_gem_object_last_write_engine(struct drm_i915_gem_object *obj)
 void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 					 unsigned int cache_level);
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj);
+void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj);
 
 int __must_check
 i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
index bfdb32d46877..d93eb36160c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
@@ -14,6 +14,7 @@
 
 struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 					 struct i915_vma *vma,
+					 struct i915_gem_ww_ctx *ww,
 					 u32 value)
 {
 	struct drm_i915_private *i915 = ce->vm->i915;
@@ -39,10 +40,24 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 		goto out_pm;
 	}
 
+	err = i915_gem_object_lock(pool->obj, ww);
+	if (err)
+		goto out_put;
+
+	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_put;
+	}
+
+	err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
+	if (unlikely(err))
+		goto out_put;
+
 	cmd = i915_gem_object_pin_map(pool->obj, I915_MAP_WC);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto out_put;
+		goto out_unpin;
 	}
 
 	rem = vma->size;
@@ -84,19 +99,11 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 
 	intel_gt_chipset_flush(ce->vm->gt);
 
-	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put;
-	}
-
-	err = i915_vma_pin(batch, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out_put;
-
 	batch->private = pool;
 	return batch;
 
+out_unpin:
+	i915_vma_unpin(batch);
 out_put:
 	intel_gt_buffer_pool_put(pool);
 out_pm:
@@ -108,11 +115,9 @@ int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq)
 {
 	int err;
 
-	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, false);
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, 0);
-	i915_vma_unlock(vma);
 	if (unlikely(err))
 		return err;
 
@@ -141,6 +146,7 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
 			     struct intel_context *ce,
 			     u32 value)
 {
+	struct i915_gem_ww_ctx ww;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	struct i915_vma *vma;
@@ -150,17 +156,28 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (unlikely(err))
-		return err;
+	i915_gem_ww_ctx_init(&ww, true);
+	intel_engine_pm_get(ce->engine);
+retry:
+	err = i915_gem_object_lock(obj, &ww);
+	if (err)
+		goto out;
 
-	batch = intel_emit_vma_fill_blt(ce, vma, value);
+	err = intel_context_pin_ww(ce, &ww);
+	if (err)
+		goto out;
+
+	err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
+	if (err)
+		goto out_ctx;
+
+	batch = intel_emit_vma_fill_blt(ce, vma, &ww, value);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
-		goto out_unpin;
+		goto out_vma;
 	}
 
-	rq = intel_context_create_request(ce);
+	rq = i915_request_create(ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out_batch;
@@ -170,11 +187,9 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
 	if (unlikely(err))
 		goto out_request;
 
-	i915_vma_lock(vma);
 	err = move_obj_to_gpu(vma->obj, rq, true);
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	i915_vma_unlock(vma);
 	if (unlikely(err))
 		goto out_request;
 
@@ -193,8 +208,18 @@ out_request:
 	i915_request_add(rq);
 out_batch:
 	intel_emit_vma_release(ce, batch);
-out_unpin:
+out_vma:
 	i915_vma_unpin(vma);
+out_ctx:
+	intel_context_unpin(ce);
+out:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	intel_engine_pm_put(ce->engine);
 	return err;
 }
 
@@ -210,6 +235,7 @@ static bool wa_1209644611_applies(struct drm_i915_private *i915, u32 size)
 }
 
 struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
+					 struct i915_gem_ww_ctx *ww,
 					 struct i915_vma *src,
 					 struct i915_vma *dst)
 {
@@ -236,10 +262,24 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 		goto out_pm;
 	}
 
+	err = i915_gem_object_lock(pool->obj, ww);
+	if (err)
+		goto out_put;
+
+	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_put;
+	}
+
+	err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
+	if (unlikely(err))
+		goto out_put;
+
 	cmd = i915_gem_object_pin_map(pool->obj, I915_MAP_WC);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto out_put;
+		goto out_unpin;
 	}
 
 	rem = src->size;
@@ -296,20 +336,11 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	i915_gem_object_unpin_map(pool->obj);
 
 	intel_gt_chipset_flush(ce->vm->gt);
-
-	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put;
-	}
-
-	err = i915_vma_pin(batch, 0, 0, PIN_USER);
-	if (unlikely(err))
-		goto out_put;
-
 	batch->private = pool;
 	return batch;
 
+out_unpin:
+	i915_vma_unpin(batch);
 out_put:
 	intel_gt_buffer_pool_put(pool);
 out_pm:
@@ -321,10 +352,9 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
 			     struct drm_i915_gem_object *dst,
 			     struct intel_context *ce)
 {
-	struct drm_gem_object *objs[] = { &src->base, &dst->base };
 	struct i915_address_space *vm = ce->vm;
 	struct i915_vma *vma[2], *batch;
-	struct ww_acquire_ctx acquire;
+	struct i915_gem_ww_ctx ww;
 	struct i915_request *rq;
 	int err, i;
 
@@ -332,25 +362,36 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
 	if (IS_ERR(vma[0]))
 		return PTR_ERR(vma[0]);
 
-	err = i915_vma_pin(vma[0], 0, 0, PIN_USER);
-	if (unlikely(err))
-		return err;
-
 	vma[1] = i915_vma_instance(dst, vm, NULL);
 	if (IS_ERR(vma[1]))
-		goto out_unpin_src;
+		return PTR_ERR(vma);
 
-	err = i915_vma_pin(vma[1], 0, 0, PIN_USER);
+	i915_gem_ww_ctx_init(&ww, true);
+	intel_engine_pm_get(ce->engine);
+retry:
+	err = i915_gem_object_lock(src, &ww);
+	if (!err)
+		err = i915_gem_object_lock(dst, &ww);
+	if (!err)
+		err = intel_context_pin_ww(ce, &ww);
+	if (err)
+		goto out;
+
+	err = i915_vma_pin_ww(vma[0], &ww, 0, 0, PIN_USER);
+	if (err)
+		goto out_ctx;
+
+	err = i915_vma_pin_ww(vma[1], &ww, 0, 0, PIN_USER);
 	if (unlikely(err))
 		goto out_unpin_src;
 
-	batch = intel_emit_vma_copy_blt(ce, vma[0], vma[1]);
+	batch = intel_emit_vma_copy_blt(ce, &ww, vma[0], vma[1]);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		goto out_unpin_dst;
 	}
 
-	rq = intel_context_create_request(ce);
+	rq = i915_request_create(ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out_batch;
@@ -360,14 +401,10 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
 	if (unlikely(err))
 		goto out_request;
 
-	err = drm_gem_lock_reservations(objs, ARRAY_SIZE(objs), &acquire);
-	if (unlikely(err))
-		goto out_request;
-
 	for (i = 0; i < ARRAY_SIZE(vma); i++) {
 		err = move_obj_to_gpu(vma[i]->obj, rq, i);
 		if (unlikely(err))
-			goto out_unlock;
+			goto out_request;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(vma); i++) {
@@ -375,20 +412,19 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
 
 		err = i915_vma_move_to_active(vma[i], rq, flags);
 		if (unlikely(err))
-			goto out_unlock;
+			goto out_request;
 	}
 
 	if (rq->engine->emit_init_breadcrumb) {
 		err = rq->engine->emit_init_breadcrumb(rq);
 		if (unlikely(err))
-			goto out_unlock;
+			goto out_request;
 	}
 
 	err = rq->engine->emit_bb_start(rq,
 					batch->node.start, batch->node.size,
 					0);
-out_unlock:
-	drm_gem_unlock_reservations(objs, ARRAY_SIZE(objs), &acquire);
+
 out_request:
 	if (unlikely(err))
 		i915_request_set_error_once(rq, err);
@@ -400,6 +436,16 @@ out_unpin_dst:
 	i915_vma_unpin(vma[1]);
 out_unpin_src:
 	i915_vma_unpin(vma[0]);
+out_ctx:
+	intel_context_unpin(ce);
+out:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	intel_engine_pm_put(ce->engine);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
index 8bcd336a90dc..2409fdcccf0e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
@@ -13,12 +13,15 @@
 #include "i915_vma.h"
 
 struct drm_i915_gem_object;
+struct i915_gem_ww_ctx;
 
 struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 					 struct i915_vma *vma,
+					 struct i915_gem_ww_ctx *ww,
 					 u32 value);
 
 struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
+					 struct i915_gem_ww_ctx *ww,
 					 struct i915_vma *src,
 					 struct i915_vma *dst);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 5335f799b548..b5c15557cc87 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -123,6 +123,15 @@ struct drm_i915_gem_object {
 	struct list_head lut_list;
 	spinlock_t lut_lock; /* guards lut_list */
 
+	/**
+	 * @obj_link: Link into @i915_gem_ww_ctx.obj_list
+	 *
+	 * When we lock this object through i915_gem_object_lock() with a
+	 * context, we add it to the list to ensure we can unlock everything
+	 * when i915_gem_ww_ctx_backoff() or i915_gem_ww_ctx_fini() are called.
+	 */
+	struct list_head obj_link;
+
 	/** Stolen memory for this object, instead of being backed by shmem. */
 	struct drm_mm_node *stolen;
 	union {
@@ -282,6 +291,7 @@ struct drm_i915_gem_object {
 		} userptr;
 
 		unsigned long scratch;
+		u64 encode;
 
 		void *gvt_info;
 	};
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 7050519c87a4..e8a083743e09 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -276,7 +276,7 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 	switch (type) {
 	default:
 		MISSING_CASE(type);
-		/* fallthrough - to use PAGE_KERNEL anyway */
+		fallthrough;	/* to use PAGE_KERNEL anyway */
 	case I915_MAP_WB:
 		pgprot = PAGE_KERNEL;
 		break;
@@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n)
 	return nth_page(sg_page(sg), offset);
 }
 
+/* Like i915_gem_object_get_page(), but mark the returned page dirty */
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n)
+{
+	struct page *page;
+
+	page = i915_gem_object_get_page(obj, n);
+	if (!obj->mm.dirty)
+		set_page_dirty(page);
+
+	return page;
+}
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 3d215164dd5a..40d3e40500fa 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -84,7 +84,7 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 
 			spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 
-			i915_gem_object_lock(obj);
+			i915_gem_object_lock(obj, NULL);
 			drm_WARN_ON(&i915->drm,
 			    i915_gem_object_set_to_gtt_domain(obj, false));
 			i915_gem_object_unlock(obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index e0f21f12d3ce..0be5e8683337 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -249,7 +249,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *i915,
 	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
 	default:
 		MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK);
-		/* fall through */
+		fallthrough;
 	case GEN7_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
 		break;
@@ -416,7 +416,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915)
 	case 4:
 		if (!IS_G4X(i915))
 			break;
-		/* fall through */
+		fallthrough;
 	case 5:
 		g4x_get_stolen_reserved(i915, uncore,
 					&reserved_base, &reserved_size);
@@ -445,7 +445,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915)
 		break;
 	default:
 		MISSING_CASE(INTEL_GEN(i915));
-		/* fall-through */
+		fallthrough;
 	case 11:
 	case 12:
 		icl_get_stolen_reserved(i915, uncore,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
index 540ef0551789..1929d6cf4150 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
@@ -9,6 +9,7 @@
 #include <drm/drm_file.h>
 
 #include "i915_drv.h"
+#include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
 
@@ -35,9 +36,10 @@ int
 i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file)
 {
+	const unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES;
-	struct i915_request *request, *target = NULL;
+	struct i915_gem_context *ctx;
+	unsigned long idx;
 	long ret;
 
 	/* ABI: return -EIO if already wedged */
@@ -45,27 +47,54 @@ i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		return ret;
 
-	spin_lock(&file_priv->mm.lock);
-	list_for_each_entry(request, &file_priv->mm.request_list, client_link) {
-		if (time_after_eq(request->emitted_jiffies, recent_enough))
-			break;
+	rcu_read_lock();
+	xa_for_each(&file_priv->context_xa, idx, ctx) {
+		struct i915_gem_engines_iter it;
+		struct intel_context *ce;
 
-		if (target && xchg(&target->file_priv, NULL))
-			list_del(&target->client_link);
+		if (!kref_get_unless_zero(&ctx->ref))
+			continue;
+		rcu_read_unlock();
 
-		target = request;
-	}
-	if (target)
-		i915_request_get(target);
-	spin_unlock(&file_priv->mm.lock);
+		for_each_gem_engine(ce,
+				    i915_gem_context_lock_engines(ctx),
+				    it) {
+			struct i915_request *rq, *target = NULL;
+
+			if (!ce->timeline)
+				continue;
+
+			mutex_lock(&ce->timeline->mutex);
+			list_for_each_entry_reverse(rq,
+						    &ce->timeline->requests,
+						    link) {
+				if (i915_request_completed(rq))
+					break;
 
-	if (!target)
-		return 0;
+				if (time_after(rq->emitted_jiffies,
+					       recent_enough))
+					continue;
 
-	ret = i915_request_wait(target,
-				I915_WAIT_INTERRUPTIBLE,
-				MAX_SCHEDULE_TIMEOUT);
-	i915_request_put(target);
+				target = i915_request_get(rq);
+				break;
+			}
+			mutex_unlock(&ce->timeline->mutex);
+			if (!target)
+				continue;
+
+			ret = i915_request_wait(target,
+						I915_WAIT_INTERRUPTIBLE,
+						MAX_SCHEDULE_TIMEOUT);
+			i915_request_put(target);
+			if (ret < 0)
+				break;
+		}
+		i915_gem_context_unlock_engines(ctx);
+		i915_gem_context_put(ctx);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
 
 	return ret < 0 ? ret : 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index ff72ee2fd9cd..ffcaee74a249 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -249,7 +249,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 	 * whilst executing a fenced command for an untiled object.
 	 */
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	if (i915_gem_object_is_framebuffer(obj)) {
 		i915_gem_object_unlock(obj);
 		return -EBUSY;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 2c2bf24140c9..12b30075134a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -596,14 +596,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 				      GFP_KERNEL |
 				      __GFP_NORETRY |
 				      __GFP_NOWARN);
-		/*
-		 * Using __get_user_pages_fast() with a read-only
-		 * access is questionable. A read-only page may be
-		 * COW-broken, and then this might end up giving
-		 * the wrong side of the COW..
-		 *
-		 * We may or may not care.
-		 */
 		if (pvec) {
 			/* defer to worker if malloc fails */
 			if (!i915_gem_object_is_readonly(obj))
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 8291ede6902c..5daf4a2be422 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -393,7 +393,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 	 */
 
 	for (i = 1; i < BIT(ARRAY_SIZE(page_sizes)); i++) {
-		unsigned int combination = 0;
+		unsigned int combination = SZ_4K; /* Required for ppGTT */
 
 		for (j = 0; j < ARRAY_SIZE(page_sizes); j++) {
 			if (i & BIT(j))
@@ -947,7 +947,7 @@ static int gpu_write(struct intel_context *ce,
 {
 	int err;
 
-	i915_gem_object_lock(vma->obj);
+	i915_gem_object_lock(vma->obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(vma->obj, true);
 	i915_gem_object_unlock(vma->obj);
 	if (err)
@@ -964,9 +964,10 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	unsigned long n;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_read(obj, &needs_flush);
 	if (err)
-		return err;
+		goto err_unlock;
 
 	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
 		u32 *ptr = kmap_atomic(i915_gem_object_get_page(obj, n));
@@ -986,6 +987,8 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	}
 
 	i915_gem_object_finish_access(obj);
+err_unlock:
+	i915_gem_object_unlock(obj);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index 299c29e9ad86..4e36d4897ea6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -75,7 +75,7 @@ static int __igt_client_fill(struct intel_engine_cs *engine)
 		if (err)
 			goto err_unpin;
 
-		i915_gem_object_lock(obj);
+		i915_gem_object_lock(obj, NULL);
 		err = i915_gem_object_set_to_cpu_domain(obj, false);
 		i915_gem_object_unlock(obj);
 		if (err)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 87d7d8aa080f..7049a6bbc03d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -27,9 +27,10 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
 	u32 *cpu;
 	int err;
 
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_prepare_write(ctx->obj, &needs_clflush);
 	if (err)
-		return err;
+		goto out;
 
 	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
@@ -46,7 +47,9 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
 	kunmap_atomic(map);
 	i915_gem_object_finish_access(ctx->obj);
 
-	return 0;
+out:
+	i915_gem_object_unlock(ctx->obj);
+	return err;
 }
 
 static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
@@ -57,9 +60,10 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 	u32 *cpu;
 	int err;
 
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_prepare_read(ctx->obj, &needs_clflush);
 	if (err)
-		return err;
+		goto out;
 
 	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
@@ -73,7 +77,9 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 	kunmap_atomic(map);
 	i915_gem_object_finish_access(ctx->obj);
 
-	return 0;
+out:
+	i915_gem_object_unlock(ctx->obj);
+	return err;
 }
 
 static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
@@ -82,7 +88,7 @@ static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 	u32 __iomem *map;
 	int err = 0;
 
-	i915_gem_object_lock(ctx->obj);
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(ctx->obj, true);
 	i915_gem_object_unlock(ctx->obj);
 	if (err)
@@ -115,7 +121,7 @@ static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 	u32 __iomem *map;
 	int err = 0;
 
-	i915_gem_object_lock(ctx->obj);
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(ctx->obj, false);
 	i915_gem_object_unlock(ctx->obj);
 	if (err)
@@ -147,7 +153,7 @@ static int wc_set(struct context *ctx, unsigned long offset, u32 v)
 	u32 *map;
 	int err;
 
-	i915_gem_object_lock(ctx->obj);
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_set_to_wc_domain(ctx->obj, true);
 	i915_gem_object_unlock(ctx->obj);
 	if (err)
@@ -170,7 +176,7 @@ static int wc_get(struct context *ctx, unsigned long offset, u32 *v)
 	u32 *map;
 	int err;
 
-	i915_gem_object_lock(ctx->obj);
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_set_to_wc_domain(ctx->obj, false);
 	i915_gem_object_unlock(ctx->obj);
 	if (err)
@@ -193,27 +199,27 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v)
 	u32 *cs;
 	int err;
 
-	i915_gem_object_lock(ctx->obj);
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(ctx->obj, true);
-	i915_gem_object_unlock(ctx->obj);
 	if (err)
-		return err;
+		goto out_unlock;
 
 	vma = i915_gem_object_ggtt_pin(ctx->obj, NULL, 0, 0, 0);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_unlock;
+	}
 
 	rq = intel_engine_create_kernel_request(ctx->engine);
 	if (IS_ERR(rq)) {
-		i915_vma_unpin(vma);
-		return PTR_ERR(rq);
+		err = PTR_ERR(rq);
+		goto out_unpin;
 	}
 
 	cs = intel_ring_begin(rq, 4);
 	if (IS_ERR(cs)) {
-		i915_request_add(rq);
-		i915_vma_unpin(vma);
-		return PTR_ERR(cs);
+		err = PTR_ERR(cs);
+		goto out_rq;
 	}
 
 	if (INTEL_GEN(ctx->engine->i915) >= 8) {
@@ -234,14 +240,16 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v)
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, true);
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	i915_vma_unlock(vma);
-	i915_vma_unpin(vma);
 
+out_rq:
 	i915_request_add(rq);
+out_unpin:
+	i915_vma_unpin(vma);
+out_unlock:
+	i915_gem_object_unlock(ctx->obj);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 7ffc3c751432..99becb86abd3 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -461,9 +461,10 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
 	unsigned int n, m, need_flush;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_write(obj, &need_flush);
 	if (err)
-		return err;
+		goto out;
 
 	for (n = 0; n < real_page_count(obj); n++) {
 		u32 *map;
@@ -479,7 +480,9 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
 	i915_gem_object_finish_access(obj);
 	obj->read_domains = I915_GEM_DOMAIN_GTT | I915_GEM_DOMAIN_CPU;
 	obj->write_domain = 0;
-	return 0;
+out:
+	i915_gem_object_unlock(obj);
+	return err;
 }
 
 static noinline int cpu_check(struct drm_i915_gem_object *obj,
@@ -488,9 +491,10 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj,
 	unsigned int n, m, needs_flush;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_read(obj, &needs_flush);
 	if (err)
-		return err;
+		goto out_unlock;
 
 	for (n = 0; n < real_page_count(obj); n++) {
 		u32 *map;
@@ -527,6 +531,8 @@ out_unmap:
 	}
 
 	i915_gem_object_finish_access(obj);
+out_unlock:
+	i915_gem_object_unlock(obj);
 	return err;
 }
 
@@ -887,24 +893,15 @@ out_file:
 	return err;
 }
 
-static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj;
 	u32 *cmd;
-	int err;
 
-	if (INTEL_GEN(vma->vm->i915) < 8)
-		return ERR_PTR(-EINVAL);
+	GEM_BUG_ON(INTEL_GEN(vma->vm->i915) < 8);
 
-	obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
-	if (IS_ERR(obj))
-		return ERR_CAST(obj);
-
-	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
-	if (IS_ERR(cmd)) {
-		err = PTR_ERR(cmd);
-		goto err;
-	}
+	cmd = i915_gem_object_pin_map(rpcs, I915_MAP_WB);
+	if (IS_ERR(cmd))
+		return PTR_ERR(cmd);
 
 	*cmd++ = MI_STORE_REGISTER_MEM_GEN8;
 	*cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
@@ -912,26 +909,12 @@ static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
 	*cmd++ = upper_32_bits(vma->node.start);
 	*cmd = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(obj, 0, 64);
-	i915_gem_object_unpin_map(obj);
+	__i915_gem_object_flush_map(rpcs, 0, 64);
+	i915_gem_object_unpin_map(rpcs);
 
 	intel_gt_chipset_flush(vma->vm->gt);
 
-	vma = i915_vma_instance(obj, vma->vm, NULL);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err;
-	}
-
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
-		goto err;
-
-	return vma;
-
-err:
-	i915_gem_object_put(obj);
-	return ERR_PTR(err);
+	return 0;
 }
 
 static int
@@ -939,52 +922,68 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 		struct intel_context *ce,
 		struct i915_request **rq_out)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_request *rq;
+	struct i915_gem_ww_ctx ww;
 	struct i915_vma *batch;
 	struct i915_vma *vma;
+	struct drm_i915_gem_object *rpcs;
 	int err;
 
 	GEM_BUG_ON(!intel_engine_can_store_dword(ce->engine));
 
+	if (INTEL_GEN(i915) < 8)
+		return -EINVAL;
+
 	vma = i915_vma_instance(obj, ce->vm, NULL);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_gtt_domain(obj, false);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
-
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
-		return err;
+	rpcs = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(rpcs))
+		return PTR_ERR(rpcs);
 
-	batch = rpcs_query_batch(vma);
+	batch = i915_vma_instance(rpcs, ce->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
-		goto err_vma;
+		goto err_put;
 	}
 
+	i915_gem_ww_ctx_init(&ww, false);
+retry:
+	err = i915_gem_object_lock(obj, &ww);
+	if (!err)
+		err = i915_gem_object_lock(rpcs, &ww);
+	if (!err)
+		err = i915_gem_object_set_to_gtt_domain(obj, false);
+	if (!err)
+		err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
+	if (err)
+		goto err_put;
+
+	err = i915_vma_pin_ww(batch, &ww, 0, 0, PIN_USER);
+	if (err)
+		goto err_vma;
+
+	err = rpcs_query_batch(rpcs, vma);
+	if (err)
+		goto err_batch;
+
 	rq = i915_request_create(ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_batch;
 	}
 
-	i915_vma_lock(batch);
 	err = i915_request_await_object(rq, batch->obj, false);
 	if (err == 0)
 		err = i915_vma_move_to_active(batch, rq, 0);
-	i915_vma_unlock(batch);
 	if (err)
 		goto skip_request;
 
-	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, true);
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	i915_vma_unlock(vma);
 	if (err)
 		goto skip_request;
 
@@ -1000,23 +999,24 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 	if (err)
 		goto skip_request;
 
-	i915_vma_unpin_and_release(&batch, 0);
-	i915_vma_unpin(vma);
-
 	*rq_out = i915_request_get(rq);
 
-	i915_request_add(rq);
-
-	return 0;
-
 skip_request:
-	i915_request_set_error_once(rq, err);
+	if (err)
+		i915_request_set_error_once(rq, err);
 	i915_request_add(rq);
 err_batch:
-	i915_vma_unpin_and_release(&batch, 0);
+	i915_vma_unpin(batch);
 err_vma:
 	i915_vma_unpin(vma);
-
+err_put:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	i915_gem_object_put(rpcs);
 	return err;
 }
 
@@ -1709,7 +1709,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 
 	i915_request_add(rq);
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_set_to_cpu_domain(obj, false);
 	i915_gem_object_unlock(obj);
 	if (err)
@@ -1748,7 +1748,7 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
 	if (!vm)
 		return -ENODEV;
 
-	page = vm->scratch[0].base.page;
+	page = __px_page(vm->scratch[0]);
 	if (!page) {
 		pr_err("No scratch page!\n");
 		return -EINVAL;
@@ -1914,8 +1914,8 @@ static int mock_context_barrier(void *arg)
 		return -ENOMEM;
 
 	counter = 0;
-	err = context_barrier_task(ctx, 0,
-				   NULL, NULL, mock_barrier_task, &counter);
+	err = context_barrier_task(ctx, 0, NULL, NULL, NULL,
+				   mock_barrier_task, &counter);
 	if (err) {
 		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
 		goto out;
@@ -1927,11 +1927,8 @@ static int mock_context_barrier(void *arg)
 	}
 
 	counter = 0;
-	err = context_barrier_task(ctx, ALL_ENGINES,
-				   skip_unused_engines,
-				   NULL,
-				   mock_barrier_task,
-				   &counter);
+	err = context_barrier_task(ctx, ALL_ENGINES, skip_unused_engines,
+				   NULL, NULL, mock_barrier_task, &counter);
 	if (err) {
 		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
 		goto out;
@@ -1951,8 +1948,8 @@ static int mock_context_barrier(void *arg)
 
 	counter = 0;
 	context_barrier_inject_fault = BIT(RCS0);
-	err = context_barrier_task(ctx, ALL_ENGINES,
-				   NULL, NULL, mock_barrier_task, &counter);
+	err = context_barrier_task(ctx, ALL_ENGINES, NULL, NULL, NULL,
+				   mock_barrier_task, &counter);
 	context_barrier_inject_fault = 0;
 	if (err == -ENXIO)
 		err = 0;
@@ -1966,11 +1963,8 @@ static int mock_context_barrier(void *arg)
 		goto out;
 
 	counter = 0;
-	err = context_barrier_task(ctx, ALL_ENGINES,
-				   skip_unused_engines,
-				   NULL,
-				   mock_barrier_task,
-				   &counter);
+	err = context_barrier_task(ctx, ALL_ENGINES, skip_unused_engines,
+				   NULL, NULL, mock_barrier_task, &counter);
 	if (err) {
 		pr_err("Failed at line %d, err=%d\n", __LINE__, err);
 		goto out;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 57c14d3340cd..e1d50a5a1477 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -32,37 +32,39 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+	err = i915_gem_object_lock(obj, &eb->ww);
+	if (err)
+		return err;
+
+	err = i915_vma_pin_ww(vma, &eb->ww, 0, 0, PIN_USER | PIN_HIGH);
 	if (err)
 		return err;
 
 	/* 8-Byte aligned */
 	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
-	if (err)
-		goto unpin_vma;
+	if (err <= 0)
+		goto reloc_err;
 
 	/* !8-Byte aligned */
 	err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1);
-	if (err)
-		goto unpin_vma;
+	if (err <= 0)
+		goto reloc_err;
 
 	/* Skip to the end of the cmd page */
-	i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1;
+	i = PAGE_SIZE / sizeof(u32) - 1;
 	i -= eb->reloc_cache.rq_size;
 	memset32(eb->reloc_cache.rq_cmd + eb->reloc_cache.rq_size,
 		 MI_NOOP, i);
 	eb->reloc_cache.rq_size += i;
 
-	/* Force batch chaining */
+	/* Force next batch */
 	err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2);
-	if (err)
-		goto unpin_vma;
+	if (err <= 0)
+		goto reloc_err;
 
 	GEM_BUG_ON(!eb->reloc_cache.rq);
 	rq = i915_request_get(eb->reloc_cache.rq);
-	err = reloc_gpu_flush(&eb->reloc_cache);
-	if (err)
-		goto put_rq;
+	reloc_gpu_flush(eb, &eb->reloc_cache);
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
 	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
@@ -94,6 +96,11 @@ put_rq:
 unpin_vma:
 	i915_vma_unpin(vma);
 	return err;
+
+reloc_err:
+	if (!err)
+		err = -EIO;
+	goto unpin_vma;
 }
 
 static int igt_gpu_reloc(void *arg)
@@ -115,6 +122,8 @@ static int igt_gpu_reloc(void *arg)
 		goto err_scratch;
 	}
 
+	intel_gt_pm_get(&eb.i915->gt);
+
 	for_each_uabi_engine(eb.engine, eb.i915) {
 		reloc_cache_init(&eb.reloc_cache, eb.i915);
 		memset(map, POISON_INUSE, 4096);
@@ -125,15 +134,29 @@ static int igt_gpu_reloc(void *arg)
 			err = PTR_ERR(eb.context);
 			goto err_pm;
 		}
+		eb.reloc_pool = NULL;
+		eb.reloc_context = NULL;
 
-		err = intel_context_pin(eb.context);
-		if (err)
-			goto err_put;
+		i915_gem_ww_ctx_init(&eb.ww, false);
+retry:
+		err = intel_context_pin_ww(eb.context, &eb.ww);
+		if (!err) {
+			err = __igt_gpu_reloc(&eb, scratch);
+
+			intel_context_unpin(eb.context);
+		}
+		if (err == -EDEADLK) {
+			err = i915_gem_ww_ctx_backoff(&eb.ww);
+			if (!err)
+				goto retry;
+		}
+		i915_gem_ww_ctx_fini(&eb.ww);
 
-		err = __igt_gpu_reloc(&eb, scratch);
+		if (eb.reloc_pool)
+			intel_gt_buffer_pool_put(eb.reloc_pool);
+		if (eb.reloc_context)
+			intel_context_put(eb.reloc_context);
 
-		intel_context_unpin(eb.context);
-err_put:
 		intel_context_put(eb.context);
 err_pm:
 		intel_engine_pm_put(eb.engine);
@@ -144,6 +167,7 @@ err_pm:
 	if (igt_flush_test(eb.i915))
 		err = -EIO;
 
+	intel_gt_pm_put(&eb.i915->gt);
 err_scratch:
 	i915_gem_object_put(scratch);
 	return err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 9c7402ce5bf9..d27d87a678c8 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -103,7 +103,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(i915_gem_object_get_tiling(obj) != tile->tiling);
 	GEM_BUG_ON(i915_gem_object_get_stride(obj) != tile->stride);
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(obj, true);
 	i915_gem_object_unlock(obj);
 	if (err) {
@@ -188,7 +188,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(i915_gem_object_get_tiling(obj) != tile->tiling);
 	GEM_BUG_ON(i915_gem_object_get_stride(obj) != tile->stride);
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(obj, true);
 	i915_gem_object_unlock(obj);
 	if (err) {
@@ -528,31 +528,42 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 		struct i915_vma *vma;
+		struct i915_gem_ww_ctx ww;
 		int err;
 
 		vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
 		if (IS_ERR(vma))
 			return PTR_ERR(vma);
 
-		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		i915_gem_ww_ctx_init(&ww, false);
+retry:
+		err = i915_gem_object_lock(obj, &ww);
+		if (!err)
+			err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
 		if (err)
-			return err;
+			goto err;
 
 		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
-			i915_vma_unpin(vma);
-			return PTR_ERR(rq);
+			err = PTR_ERR(rq);
+			goto err_unpin;
 		}
 
-		i915_vma_lock(vma);
 		err = i915_request_await_object(rq, vma->obj, true);
 		if (err == 0)
 			err = i915_vma_move_to_active(vma, rq,
 						      EXEC_OBJECT_WRITE);
-		i915_vma_unlock(vma);
 
 		i915_request_add(rq);
+err_unpin:
 		i915_vma_unpin(vma);
+err:
+		if (err == -EDEADLK) {
+			err = i915_gem_ww_ctx_backoff(&ww);
+			if (!err)
+				goto retry;
+		}
+		i915_gem_ww_ctx_fini(&ww);
 		if (err)
 			return err;
 	}
@@ -1123,6 +1134,7 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 		struct i915_vma *vma;
+		struct i915_gem_ww_ctx ww;
 
 		vma = i915_vma_instance(obj, engine->kernel_context->vm, NULL);
 		if (IS_ERR(vma)) {
@@ -1130,9 +1142,13 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 			goto out_unmap;
 		}
 
-		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		i915_gem_ww_ctx_init(&ww, false);
+retry:
+		err = i915_gem_object_lock(obj, &ww);
+		if (!err)
+			err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
 		if (err)
-			goto out_unmap;
+			goto out_ww;
 
 		rq = i915_request_create(engine->kernel_context);
 		if (IS_ERR(rq)) {
@@ -1140,11 +1156,9 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 			goto out_unpin;
 		}
 
-		i915_vma_lock(vma);
 		err = i915_request_await_object(rq, vma->obj, false);
 		if (err == 0)
 			err = i915_vma_move_to_active(vma, rq, 0);
-		i915_vma_unlock(vma);
 
 		err = engine->emit_bb_start(rq, vma->node.start, 0, 0);
 		i915_request_get(rq);
@@ -1166,6 +1180,13 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915,
 
 out_unpin:
 		i915_vma_unpin(vma);
+out_ww:
+		if (err == -EDEADLK) {
+			err = i915_gem_ww_ctx_backoff(&ww);
+			if (!err)
+				goto retry;
+		}
+		i915_gem_ww_ctx_fini(&ww);
 		if (err)
 			goto out_unmap;
 	}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
index 34932871b3a5..a94243dc4c5c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
@@ -44,7 +44,7 @@ static int mock_phys_object(void *arg)
 	}
 
 	/* Make the object dirty so that put_pages must do copy back the data */
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_set_to_gtt_domain(obj, true);
 	i915_gem_object_unlock(obj);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index cdc0b9c54305..fd0d24d28763 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -16,8 +16,10 @@ static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
 				  const unsigned int pde,
 				  const struct i915_page_table *pt)
 {
+	dma_addr_t addr = pt ? px_dma(pt) : px_dma(ppgtt->base.vm.scratch[1]);
+
 	/* Caller needs to make sure the write completes if necessary */
-	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+	iowrite32(GEN6_PDE_ADDR_ENCODE(addr) | GEN6_PDE_VALID,
 		  ppgtt->pd_addr + pde);
 }
 
@@ -79,7 +81,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 {
 	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
-	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
+	const gen6_pte_t scratch_pte = vm->scratch[0]->encode;
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
@@ -90,8 +92,6 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 		const unsigned int count = min(num_entries, GEN6_PTES - pte);
 		gen6_pte_t *vaddr;
 
-		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
-
 		num_entries -= count;
 
 		GEM_BUG_ON(count > atomic_read(&pt->used));
@@ -127,7 +127,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	struct sgt_dma iter = sgt_dma(vma);
 	gen6_pte_t *vaddr;
 
-	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
+	GEM_BUG_ON(!pd->entry[act_pt]);
 
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
 	do {
@@ -177,39 +177,36 @@ static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end)
 	mutex_unlock(&ppgtt->flush);
 }
 
-static int gen6_alloc_va_range(struct i915_address_space *vm,
-			       u64 start, u64 length)
+static void gen6_alloc_va_range(struct i915_address_space *vm,
+				struct i915_vm_pt_stash *stash,
+				u64 start, u64 length)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_table *pt, *alloc = NULL;
+	struct i915_page_table *pt;
 	bool flush = false;
 	u64 from = start;
 	unsigned int pde;
-	int ret = 0;
 
 	spin_lock(&pd->lock);
 	gen6_for_each_pde(pt, pd, start, length, pde) {
 		const unsigned int count = gen6_pte_count(start, length);
 
-		if (px_base(pt) == px_base(&vm->scratch[1])) {
+		if (!pt) {
 			spin_unlock(&pd->lock);
 
-			pt = fetch_and_zero(&alloc);
-			if (!pt)
-				pt = alloc_pt(vm);
-			if (IS_ERR(pt)) {
-				ret = PTR_ERR(pt);
-				goto unwind_out;
-			}
+			pt = stash->pt[0];
+			__i915_gem_object_pin_pages(pt->base);
+			i915_gem_object_make_unshrinkable(pt->base);
 
-			fill32_px(pt, vm->scratch[0].encode);
+			fill32_px(pt, vm->scratch[0]->encode);
 
 			spin_lock(&pd->lock);
-			if (pd->entry[pde] == &vm->scratch[1]) {
+			if (!pd->entry[pde]) {
+				stash->pt[0] = pt->stash;
+				atomic_set(&pt->used, 0);
 				pd->entry[pde] = pt;
 			} else {
-				alloc = pt;
 				pt = pd->entry[pde];
 			}
 
@@ -226,38 +223,32 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 		with_intel_runtime_pm(&vm->i915->runtime_pm, wakeref)
 			gen6_flush_pd(ppgtt, from, start);
 	}
-
-	goto out;
-
-unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start - from);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	return ret;
 }
 
 static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 {
 	struct i915_address_space * const vm = &ppgtt->base.vm;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
 	int ret;
 
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	ret = setup_scratch_page(vm);
 	if (ret)
 		return ret;
 
-	vm->scratch[0].encode =
-		vm->pte_encode(px_dma(&vm->scratch[0]),
+	vm->scratch[0]->encode =
+		vm->pte_encode(px_dma(vm->scratch[0]),
 			       I915_CACHE_NONE, PTE_READ_ONLY);
 
-	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
-		cleanup_scratch_page(vm);
-		return -ENOMEM;
+	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	if (IS_ERR(vm->scratch[1]))
+		return PTR_ERR(vm->scratch[1]);
+
+	ret = pin_pt_dma(vm, vm->scratch[1]);
+	if (ret) {
+		i915_gem_object_put(vm->scratch[1]);
+		return ret;
 	}
 
-	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
-	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
+	fill32_px(vm->scratch[1], vm->scratch[0]->encode);
 
 	return 0;
 }
@@ -265,14 +256,12 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
 {
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
 	struct i915_page_table *pt;
 	u32 pde;
 
 	gen6_for_all_pdes(pt, pd, pde)
-		if (px_base(pt) != scratch)
-			free_px(&ppgtt->base.vm, pt);
+		if (pt)
+			free_pt(&ppgtt->base.vm, pt);
 }
 
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
@@ -286,7 +275,8 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 	mutex_destroy(&ppgtt->flush);
 	mutex_destroy(&ppgtt->pin_mutex);
-	kfree(ppgtt->base.pd);
+
+	free_pd(&ppgtt->base.vm, ppgtt->base.pd);
 }
 
 static int pd_vma_set_pages(struct i915_vma *vma)
@@ -302,28 +292,26 @@ static void pd_vma_clear_pages(struct i915_vma *vma)
 	vma->pages = NULL;
 }
 
-static int pd_vma_bind(struct i915_address_space *vm,
-		       struct i915_vma *vma,
-		       enum i915_cache_level cache_level,
-		       u32 unused)
+static void pd_vma_bind(struct i915_address_space *vm,
+			struct i915_vm_pt_stash *stash,
+			struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 unused)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	struct gen6_ppgtt *ppgtt = vma->private;
 	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
 
-	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pp_dir = ggtt_offset * sizeof(gen6_pte_t) << 10;
 	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
 
 	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
-	return 0;
 }
 
 static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
 {
 	struct gen6_ppgtt *ppgtt = vma->private;
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
 	struct i915_page_table *pt;
 	unsigned int pde;
 
@@ -332,11 +320,11 @@ static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
 
 	/* Free all no longer used page tables */
 	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
-		if (px_base(pt) == scratch || atomic_read(&pt->used))
+		if (!pt || atomic_read(&pt->used))
 			continue;
 
-		free_px(&ppgtt->base.vm, pt);
-		pd->entry[pde] = scratch;
+		free_pt(&ppgtt->base.vm, pt);
+		pd->entry[pde] = NULL;
 	}
 
 	ppgtt->scan_for_unused_pt = false;
@@ -380,7 +368,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 	return vma;
 }
 
-int gen6_ppgtt_pin(struct i915_ppgtt *base)
+int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
 	int err;
@@ -406,7 +394,7 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base)
 	 */
 	err = 0;
 	if (!atomic_read(&ppgtt->pin_count))
-		err = i915_ggtt_pin(ppgtt->vma, GEN6_PD_ALIGN, PIN_HIGH);
+		err = i915_ggtt_pin(ppgtt->vma, ww, GEN6_PD_ALIGN, PIN_HIGH);
 	if (!err)
 		atomic_inc(&ppgtt->pin_count);
 	mutex_unlock(&ppgtt->pin_mutex);
@@ -448,6 +436,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 	mutex_init(&ppgtt->pin_mutex);
 
 	ppgtt_init(&ppgtt->base, gt);
+	ppgtt->base.vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen6_pte_t));
 	ppgtt->base.vm.top = 1;
 
 	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
@@ -456,9 +445,10 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
 
+	ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma;
 	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
 
-	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
+	ppgtt->base.pd = __alloc_pd(I915_PDES);
 	if (!ppgtt->base.pd) {
 		err = -ENOMEM;
 		goto err_free;
@@ -479,7 +469,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 err_scratch:
 	free_scratch(&ppgtt->base.vm);
 err_pd:
-	kfree(ppgtt->base.pd);
+	free_pd(&ppgtt->base.vm, ppgtt->base.pd);
 err_free:
 	mutex_destroy(&ppgtt->pin_mutex);
 	kfree(ppgtt);
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
index 72e481806c96..3357228f3304 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
@@ -8,12 +8,15 @@
 
 #include "intel_gtt.h"
 
+struct i915_gem_ww_ctx;
+
 struct gen6_ppgtt {
 	struct i915_ppgtt base;
 
 	struct mutex flush;
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
+	u32 pp_dir;
 
 	atomic_t pin_count;
 	struct mutex pin_mutex;
@@ -66,7 +69,7 @@ static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
 		     (pt = i915_pt_entry(pd, iter), true);		\
 	     ++iter)
 
-int gen6_ppgtt_pin(struct i915_ppgtt *base);
+int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww);
 void gen6_ppgtt_unpin(struct i915_ppgtt *base);
 void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
 void gen6_ppgtt_enable(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 699125928272..eb64f474a78c 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -181,7 +181,7 @@ static void __gen8_ppgtt_cleanup(struct i915_address_space *vm,
 		} while (pde++, --count);
 	}
 
-	free_px(vm, pd);
+	free_px(vm, &pd->pt, lvl);
 }
 
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
@@ -199,7 +199,7 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
 			      struct i915_page_directory * const pd,
 			      u64 start, const u64 end, int lvl)
 {
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
+	const struct drm_i915_gem_object * const scratch = vm->scratch[lvl];
 	unsigned int idx, len;
 
 	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
@@ -239,7 +239,7 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
 
 			vaddr = kmap_atomic_px(pt);
 			memset64(vaddr + gen8_pd_index(start, 0),
-				 vm->scratch[0].encode,
+				 vm->scratch[0]->encode,
 				 count);
 			kunmap_atomic(vaddr);
 
@@ -248,7 +248,7 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
 		}
 
 		if (release_pd_entry(pd, idx, pt, scratch))
-			free_px(vm, pt);
+			free_px(vm, pt, lvl);
 	} while (idx++, --len);
 
 	return start;
@@ -269,14 +269,12 @@ static void gen8_ppgtt_clear(struct i915_address_space *vm,
 			   start, start + length, vm->top);
 }
 
-static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
-			      struct i915_page_directory * const pd,
-			      u64 * const start, const u64 end, int lvl)
+static void __gen8_ppgtt_alloc(struct i915_address_space * const vm,
+			       struct i915_vm_pt_stash *stash,
+			       struct i915_page_directory * const pd,
+			       u64 * const start, const u64 end, int lvl)
 {
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
-	struct i915_page_table *alloc = NULL;
 	unsigned int idx, len;
-	int ret = 0;
 
 	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
 
@@ -297,49 +295,31 @@ static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
 			DBG("%s(%p):{ lvl:%d, idx:%d } allocating new tree\n",
 			    __func__, vm, lvl + 1, idx);
 
-			pt = fetch_and_zero(&alloc);
-			if (lvl) {
-				if (!pt) {
-					pt = &alloc_pd(vm)->pt;
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				fill_px(pt, vm->scratch[lvl].encode);
-			} else {
-				if (!pt) {
-					pt = alloc_pt(vm);
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				if (intel_vgpu_active(vm->i915) ||
-				    gen8_pt_count(*start, end) < I915_PDES)
-					fill_px(pt, vm->scratch[lvl].encode);
-			}
+			pt = stash->pt[!!lvl];
+			__i915_gem_object_pin_pages(pt->base);
+			i915_gem_object_make_unshrinkable(pt->base);
+
+			if (lvl ||
+			    gen8_pt_count(*start, end) < I915_PDES ||
+			    intel_vgpu_active(vm->i915))
+				fill_px(pt, vm->scratch[lvl]->encode);
 
 			spin_lock(&pd->lock);
-			if (likely(!pd->entry[idx]))
+			if (likely(!pd->entry[idx])) {
+				stash->pt[!!lvl] = pt->stash;
+				atomic_set(&pt->used, 0);
 				set_pd_entry(pd, idx, pt);
-			else
-				alloc = pt, pt = pd->entry[idx];
+			} else {
+				pt = pd->entry[idx];
+			}
 		}
 
 		if (lvl) {
 			atomic_inc(&pt->used);
 			spin_unlock(&pd->lock);
 
-			ret = __gen8_ppgtt_alloc(vm, as_pd(pt),
-						 start, end, lvl);
-			if (unlikely(ret)) {
-				if (release_pd_entry(pd, idx, pt, scratch))
-					free_px(vm, pt);
-				goto out;
-			}
+			__gen8_ppgtt_alloc(vm, stash,
+					   as_pd(pt), start, end, lvl);
 
 			spin_lock(&pd->lock);
 			atomic_dec(&pt->used);
@@ -359,18 +339,12 @@ static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
 		}
 	} while (idx++, --len);
 	spin_unlock(&pd->lock);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	return ret;
 }
 
-static int gen8_ppgtt_alloc(struct i915_address_space *vm,
-			    u64 start, u64 length)
+static void gen8_ppgtt_alloc(struct i915_address_space *vm,
+			     struct i915_vm_pt_stash *stash,
+			     u64 start, u64 length)
 {
-	u64 from;
-	int err;
-
 	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
 	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
 	GEM_BUG_ON(range_overflows(start, length, vm->total));
@@ -378,25 +352,9 @@ static int gen8_ppgtt_alloc(struct i915_address_space *vm,
 	start >>= GEN8_PTE_SHIFT;
 	length >>= GEN8_PTE_SHIFT;
 	GEM_BUG_ON(length == 0);
-	from = start;
 
-	err = __gen8_ppgtt_alloc(vm, i915_vm_to_ppgtt(vm)->pd,
-				 &start, start + length, vm->top);
-	if (unlikely(err && from != start))
-		__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
-				   from, start, vm->top);
-
-	return err;
-}
-
-static __always_inline void
-write_pte(gen8_pte_t *pte, const gen8_pte_t val)
-{
-	/* Magic delays? Or can we refine these to flush all in one pass? */
-	*pte = val;
-	wmb(); /* cpu to cache */
-	clflush(pte); /* cache to memory */
-	wmb(); /* visible to all */
+	__gen8_ppgtt_alloc(vm, stash, i915_vm_to_ppgtt(vm)->pd,
+			   &start, start + length, vm->top);
 }
 
 static __always_inline u64
@@ -415,8 +373,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
 		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
-		write_pte(&vaddr[gen8_pd_index(idx, 0)],
-			  pte_encode | iter->dma);
+		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
 
 		iter->dma += I915_GTT_PAGE_SIZE;
 		if (iter->dma >= iter->max) {
@@ -439,10 +396,12 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 				pd = pdp->entry[gen8_pd_index(idx, 2)];
 			}
 
+			clflush_cache_range(vaddr, PAGE_SIZE);
 			kunmap_atomic(vaddr);
 			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 		}
 	} while (1);
+	clflush_cache_range(vaddr, PAGE_SIZE);
 	kunmap_atomic(vaddr);
 
 	return idx;
@@ -498,7 +457,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 
 		do {
 			GEM_BUG_ON(iter->sg->length < page_size);
-			write_pte(&vaddr[index++], encode | iter->dma);
+			vaddr[index++] = encode | iter->dma;
 
 			start += page_size;
 			iter->dma += page_size;
@@ -523,6 +482,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			}
 		} while (rem >= page_size && index < I915_PDES);
 
+		clflush_cache_range(vaddr, PAGE_SIZE);
 		kunmap_atomic(vaddr);
 
 		/*
@@ -554,7 +514,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
 				u16 i;
 
-				encode = vma->vm->scratch[0].encode;
+				encode = vma->vm->scratch[0]->encode;
 				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
 
 				for (i = 1; i < index; i += 16)
@@ -608,27 +568,37 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 		GEM_BUG_ON(!clone->has_read_only);
 
 		vm->scratch_order = clone->scratch_order;
-		memcpy(vm->scratch, clone->scratch, sizeof(vm->scratch));
-		px_dma(&vm->scratch[0]) = 0; /* no xfer of ownership */
+		for (i = 0; i <= vm->top; i++)
+			vm->scratch[i] = i915_gem_object_get(clone->scratch[i]);
+
 		return 0;
 	}
 
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	ret = setup_scratch_page(vm);
 	if (ret)
 		return ret;
 
-	vm->scratch[0].encode =
-		gen8_pte_encode(px_dma(&vm->scratch[0]),
+	vm->scratch[0]->encode =
+		gen8_pte_encode(px_dma(vm->scratch[0]),
 				I915_CACHE_LLC, vm->has_read_only);
 
 	for (i = 1; i <= vm->top; i++) {
-		if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[i]))))
+		struct drm_i915_gem_object *obj;
+
+		obj = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+		if (IS_ERR(obj))
+			goto free_scratch;
+
+		ret = pin_pt_dma(vm, obj);
+		if (ret) {
+			i915_gem_object_put(obj);
 			goto free_scratch;
+		}
 
-		fill_px(&vm->scratch[i], vm->scratch[i - 1].encode);
-		vm->scratch[i].encode =
-			gen8_pde_encode(px_dma(&vm->scratch[i]),
-					I915_CACHE_LLC);
+		fill_px(obj, vm->scratch[i - 1]->encode);
+		obj->encode = gen8_pde_encode(px_dma(obj), I915_CACHE_LLC);
+
+		vm->scratch[i] = obj;
 	}
 
 	return 0;
@@ -649,12 +619,20 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 
 	for (idx = 0; idx < GEN8_3LVL_PDPES; idx++) {
 		struct i915_page_directory *pde;
+		int err;
 
 		pde = alloc_pd(vm);
 		if (IS_ERR(pde))
 			return PTR_ERR(pde);
 
-		fill_px(pde, vm->scratch[1].encode);
+		err = pin_pt_dma(vm, pde->pt.base);
+		if (err) {
+			i915_gem_object_put(pde->pt.base);
+			free_pd(vm, pde);
+			return err;
+		}
+
+		fill_px(pde, vm->scratch[1]->encode);
 		set_pd_entry(pd, idx, pde);
 		atomic_inc(px_used(pde)); /* keep pinned */
 	}
@@ -668,21 +646,32 @@ gen8_alloc_top_pd(struct i915_address_space *vm)
 {
 	const unsigned int count = gen8_pd_top_count(vm);
 	struct i915_page_directory *pd;
+	int err;
 
-	GEM_BUG_ON(count > ARRAY_SIZE(pd->entry));
+	GEM_BUG_ON(count > I915_PDES);
 
-	pd = __alloc_pd(offsetof(typeof(*pd), entry[count]));
+	pd = __alloc_pd(count);
 	if (unlikely(!pd))
 		return ERR_PTR(-ENOMEM);
 
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
-		kfree(pd);
-		return ERR_PTR(-ENOMEM);
+	pd->pt.base = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	if (IS_ERR(pd->pt.base)) {
+		err = PTR_ERR(pd->pt.base);
+		pd->pt.base = NULL;
+		goto err_pd;
 	}
 
-	fill_page_dma(px_base(pd), vm->scratch[vm->top].encode, count);
+	err = pin_pt_dma(vm, pd->pt.base);
+	if (err)
+		goto err_pd;
+
+	fill_page_dma(px_base(pd), vm->scratch[vm->top]->encode, count);
 	atomic_inc(px_used(pd)); /* mark as pinned */
 	return pd;
+
+err_pd:
+	free_pd(vm, pd);
+	return ERR_PTR(err);
 }
 
 /*
@@ -703,6 +692,7 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
 
 	ppgtt_init(ppgtt, gt);
 	ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2;
+	ppgtt->vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen8_pte_t));
 
 	/*
 	 * From bdw, there is hw support for read-only pages in the PPGTT.
@@ -714,12 +704,7 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
 	 */
 	ppgtt->vm.has_read_only = !IS_GEN_RANGE(gt->i915, 11, 12);
 
-	/*
-	 * There are only few exceptions for gen >=6. chv and bxt.
-	 * And we are not sure about the latter so play safe for now.
-	 */
-	if (IS_CHERRYVIEW(gt->i915) || IS_BROXTON(gt->i915))
-		ppgtt->vm.pt_kmap_wc = true;
+	ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
 
 	err = gen8_init_scratch(&ppgtt->vm);
 	if (err)
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 91786310c114..d8b206e53660 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -28,6 +28,8 @@
 
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_breadcrumbs.h"
+#include "intel_context.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 
@@ -53,33 +55,65 @@ static void irq_disable(struct intel_engine_cs *engine)
 	spin_unlock(&engine->gt->irq_lock);
 }
 
-static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
+static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 {
-	struct intel_engine_cs *engine =
-		container_of(b, struct intel_engine_cs, breadcrumbs);
+	lockdep_assert_held(&b->irq_lock);
+
+	if (!b->irq_engine || b->irq_armed)
+		return;
+
+	if (!intel_gt_pm_get_if_awake(b->irq_engine->gt))
+		return;
+
+	/*
+	 * The breadcrumb irq will be disarmed on the interrupt after the
+	 * waiters are signaled. This gives us a single interrupt window in
+	 * which we can add a new waiter and avoid the cost of re-enabling
+	 * the irq.
+	 */
+	WRITE_ONCE(b->irq_armed, true);
+
+	/*
+	 * Since we are waiting on a request, the GPU should be busy
+	 * and should have its own rpm reference. This is tracked
+	 * by i915->gt.awake, we can forgo holding our own wakref
+	 * for the interrupt as before i915->gt.awake is released (when
+	 * the driver is idle) we disarm the breadcrumbs.
+	 */
 
+	if (!b->irq_enabled++)
+		irq_enable(b->irq_engine);
+}
+
+static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
+{
 	lockdep_assert_held(&b->irq_lock);
 
+	if (!b->irq_engine || !b->irq_armed)
+		return;
+
 	GEM_BUG_ON(!b->irq_enabled);
 	if (!--b->irq_enabled)
-		irq_disable(engine);
+		irq_disable(b->irq_engine);
 
 	WRITE_ONCE(b->irq_armed, false);
-	intel_gt_pm_put_async(engine->gt);
+	intel_gt_pm_put_async(b->irq_engine->gt);
 }
 
-void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
+static void add_signaling_context(struct intel_breadcrumbs *b,
+				  struct intel_context *ce)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
-	unsigned long flags;
-
-	if (!READ_ONCE(b->irq_armed))
-		return;
+	intel_context_get(ce);
+	list_add_tail(&ce->signal_link, &b->signalers);
+	if (list_is_first(&ce->signal_link, &b->signalers))
+		__intel_breadcrumbs_arm_irq(b);
+}
 
-	spin_lock_irqsave(&b->irq_lock, flags);
-	if (b->irq_armed)
-		__intel_breadcrumbs_disarm_irq(b);
-	spin_unlock_irqrestore(&b->irq_lock, flags);
+static void remove_signaling_context(struct intel_breadcrumbs *b,
+				     struct intel_context *ce)
+{
+	list_del(&ce->signal_link);
+	intel_context_put(ce);
 }
 
 static inline bool __request_completed(const struct i915_request *rq)
@@ -90,6 +124,9 @@ static inline bool __request_completed(const struct i915_request *rq)
 __maybe_unused static bool
 check_signal_order(struct intel_context *ce, struct i915_request *rq)
 {
+	if (rq->context != ce)
+		return false;
+
 	if (!list_is_last(&rq->signal_link, &ce->signals) &&
 	    i915_seqno_passed(rq->fence.seqno,
 			      list_next_entry(rq, signal_link)->fence.seqno))
@@ -133,25 +170,21 @@ __dma_fence_signal__notify(struct dma_fence *fence,
 
 static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 {
-	struct intel_engine_cs *engine =
-		container_of(b, struct intel_engine_cs, breadcrumbs);
-
-	if (unlikely(intel_engine_is_virtual(engine)))
-		engine = intel_virtual_engine_get_sibling(engine, 0);
-
-	intel_engine_add_retire(engine, tl);
+	if (b->irq_engine)
+		intel_engine_add_retire(b->irq_engine, tl);
 }
 
-static void __signal_request(struct i915_request *rq, struct list_head *signals)
+static bool __signal_request(struct i915_request *rq, struct list_head *signals)
 {
-	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
 	clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
 
-	if (!__dma_fence_signal(&rq->fence))
-		return;
+	if (!__dma_fence_signal(&rq->fence)) {
+		i915_request_put(rq);
+		return false;
+	}
 
-	i915_request_get(rq);
 	list_add_tail(&rq->signal_link, signals);
+	return true;
 }
 
 static void signal_irq_work(struct irq_work *work)
@@ -164,7 +197,7 @@ static void signal_irq_work(struct irq_work *work)
 
 	spin_lock(&b->irq_lock);
 
-	if (b->irq_armed && list_empty(&b->signalers))
+	if (list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
 
 	list_splice_init(&b->signaled_requests, &signal);
@@ -197,8 +230,8 @@ static void signal_irq_work(struct irq_work *work)
 			/* Advance the list to the first incomplete request */
 			__list_del_many(&ce->signals, pos);
 			if (&ce->signals == pos) { /* now empty */
-				list_del_init(&ce->signal_link);
 				add_retire(b, ce->timeline);
+				remove_signaling_context(b, ce);
 			}
 		}
 	}
@@ -220,116 +253,89 @@ static void signal_irq_work(struct irq_work *work)
 	}
 }
 
-static bool __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
+struct intel_breadcrumbs *
+intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
 {
-	struct intel_engine_cs *engine =
-		container_of(b, struct intel_engine_cs, breadcrumbs);
-
-	lockdep_assert_held(&b->irq_lock);
-	if (b->irq_armed)
-		return true;
-
-	if (!intel_gt_pm_get_if_awake(engine->gt))
-		return false;
-
-	/*
-	 * The breadcrumb irq will be disarmed on the interrupt after the
-	 * waiters are signaled. This gives us a single interrupt window in
-	 * which we can add a new waiter and avoid the cost of re-enabling
-	 * the irq.
-	 */
-	WRITE_ONCE(b->irq_armed, true);
-
-	/*
-	 * Since we are waiting on a request, the GPU should be busy
-	 * and should have its own rpm reference. This is tracked
-	 * by i915->gt.awake, we can forgo holding our own wakref
-	 * for the interrupt as before i915->gt.awake is released (when
-	 * the driver is idle) we disarm the breadcrumbs.
-	 */
-
-	if (!b->irq_enabled++)
-		irq_enable(engine);
+	struct intel_breadcrumbs *b;
 
-	return true;
-}
-
-void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
-{
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	b = kzalloc(sizeof(*b), GFP_KERNEL);
+	if (!b)
+		return NULL;
 
 	spin_lock_init(&b->irq_lock);
 	INIT_LIST_HEAD(&b->signalers);
 	INIT_LIST_HEAD(&b->signaled_requests);
 
 	init_irq_work(&b->irq_work, signal_irq_work);
+
+	b->irq_engine = irq_engine;
+
+	return b;
 }
 
-void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
+void intel_breadcrumbs_reset(struct intel_breadcrumbs *b)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 	unsigned long flags;
 
+	if (!b->irq_engine)
+		return;
+
 	spin_lock_irqsave(&b->irq_lock, flags);
 
 	if (b->irq_enabled)
-		irq_enable(engine);
+		irq_enable(b->irq_engine);
 	else
-		irq_disable(engine);
+		irq_disable(b->irq_engine);
 
 	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
-void intel_engine_transfer_stale_breadcrumbs(struct intel_engine_cs *engine,
-					     struct intel_context *ce)
+void intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 	unsigned long flags;
 
-	spin_lock_irqsave(&b->irq_lock, flags);
-	if (!list_empty(&ce->signals)) {
-		struct i915_request *rq, *next;
-
-		/* Queue for executing the signal callbacks in the irq_work */
-		list_for_each_entry_safe(rq, next, &ce->signals, signal_link) {
-			GEM_BUG_ON(rq->engine != engine);
-			GEM_BUG_ON(!__request_completed(rq));
-
-			__signal_request(rq, &b->signaled_requests);
-		}
+	if (!READ_ONCE(b->irq_armed))
+		return;
 
-		INIT_LIST_HEAD(&ce->signals);
-		list_del_init(&ce->signal_link);
+	spin_lock_irqsave(&b->irq_lock, flags);
+	__intel_breadcrumbs_disarm_irq(b);
+	spin_unlock_irqrestore(&b->irq_lock, flags);
 
+	if (!list_empty(&b->signalers))
 		irq_work_queue(&b->irq_work);
-	}
-	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
-void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
+void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
 {
+	kfree(b);
 }
 
-bool i915_request_enable_breadcrumb(struct i915_request *rq)
+static void insert_breadcrumb(struct i915_request *rq,
+			      struct intel_breadcrumbs *b)
 {
-	lockdep_assert_held(&rq->lock);
-
-	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
-		return true;
+	struct intel_context *ce = rq->context;
+	struct list_head *pos;
 
-	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
-		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-		struct intel_context *ce = rq->context;
-		struct list_head *pos;
-
-		spin_lock(&b->irq_lock);
+	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
+		return;
 
-		if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
-			goto unlock;
+	i915_request_get(rq);
 
-		if (!__intel_breadcrumbs_arm_irq(b))
-			goto unlock;
+	/*
+	 * If the request is already completed, we can transfer it
+	 * straight onto a signaled list, and queue the irq worker for
+	 * its signal completion.
+	 */
+	if (__request_completed(rq)) {
+		if (__signal_request(rq, &b->signaled_requests))
+			irq_work_queue(&b->irq_work);
+		return;
+	}
 
+	if (list_empty(&ce->signals)) {
+		add_signaling_context(b, ce);
+		pos = &ce->signals;
+	} else {
 		/*
 		 * We keep the seqno in retirement order, so we can break
 		 * inside intel_engine_signal_breadcrumbs as soon as we've
@@ -351,24 +357,75 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 			if (i915_seqno_passed(rq->fence.seqno, it->fence.seqno))
 				break;
 		}
-		list_add(&rq->signal_link, pos);
-		if (pos == &ce->signals) /* catch transitions from empty list */
-			list_move_tail(&ce->signal_link, &b->signalers);
-		GEM_BUG_ON(!check_signal_order(ce, rq));
+	}
+	list_add(&rq->signal_link, pos);
+	GEM_BUG_ON(!check_signal_order(ce, rq));
+	set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+
+	/* Check after attaching to irq, interrupt may have already fired. */
+	if (__request_completed(rq))
+		irq_work_queue(&b->irq_work);
+}
 
-		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
-unlock:
+bool i915_request_enable_breadcrumb(struct i915_request *rq)
+{
+	struct intel_breadcrumbs *b;
+
+	/* Serialises with i915_request_retire() using rq->lock */
+	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
+		return true;
+
+	/*
+	 * Peek at i915_request_submit()/i915_request_unsubmit() status.
+	 *
+	 * If the request is not yet active (and not signaled), we will
+	 * attach the breadcrumb later.
+	 */
+	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
+		return true;
+
+	/*
+	 * rq->engine is locked by rq->engine->active.lock. That however
+	 * is not known until after rq->engine has been dereferenced and
+	 * the lock acquired. Hence we acquire the lock and then validate
+	 * that rq->engine still matches the lock we hold for it.
+	 *
+	 * Here, we are using the breadcrumb lock as a proxy for the
+	 * rq->engine->active.lock, and we know that since the breadcrumb
+	 * will be serialised within i915_request_submit/i915_request_unsubmit,
+	 * the engine cannot change while active as long as we hold the
+	 * breadcrumb lock on that engine.
+	 *
+	 * From the dma_fence_enable_signaling() path, we are outside of the
+	 * request submit/unsubmit path, and so we must be more careful to
+	 * acquire the right lock.
+	 */
+	b = READ_ONCE(rq->engine)->breadcrumbs;
+	spin_lock(&b->irq_lock);
+	while (unlikely(b != READ_ONCE(rq->engine)->breadcrumbs)) {
 		spin_unlock(&b->irq_lock);
+		b = READ_ONCE(rq->engine)->breadcrumbs;
+		spin_lock(&b->irq_lock);
 	}
 
-	return !__request_completed(rq);
+	/*
+	 * Now that we are finally serialised with request submit/unsubmit,
+	 * [with b->irq_lock] and with i915_request_retire() [via checking
+	 * SIGNALED with rq->lock] confirm the request is indeed active. If
+	 * it is no longer active, the breadcrumb will be attached upon
+	 * i915_request_submit().
+	 */
+	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
+		insert_breadcrumb(rq, b);
+
+	spin_unlock(&b->irq_lock);
+
+	return true;
 }
 
 void i915_request_cancel_breadcrumb(struct i915_request *rq)
 {
-	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-
-	lockdep_assert_held(&rq->lock);
+	struct intel_breadcrumbs *b = rq->engine->breadcrumbs;
 
 	/*
 	 * We must wait for b->irq_lock so that we know the interrupt handler
@@ -382,23 +439,19 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 
 		list_del(&rq->signal_link);
 		if (list_empty(&ce->signals))
-			list_del_init(&ce->signal_link);
+			remove_signaling_context(b, ce);
 
 		clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+		i915_request_put(rq);
 	}
 	spin_unlock(&b->irq_lock);
 }
 
-void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
-				    struct drm_printer *p)
+static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 	struct intel_context *ce;
 	struct i915_request *rq;
 
-	if (list_empty(&b->signalers))
-		return;
-
 	drm_printf(p, "Signals:\n");
 
 	spin_lock_irq(&b->irq_lock);
@@ -414,3 +467,17 @@ void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
 	}
 	spin_unlock_irq(&b->irq_lock);
 }
+
+void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
+				    struct drm_printer *p)
+{
+	struct intel_breadcrumbs *b;
+
+	b = engine->breadcrumbs;
+	if (!b)
+		return;
+
+	drm_printf(p, "IRQ: %s\n", enableddisabled(b->irq_armed));
+	if (!list_empty(&b->signalers))
+		print_signals(b, p);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
new file mode 100644
index 000000000000..ed3d1deabfbd
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_BREADCRUMBS__
+#define __INTEL_BREADCRUMBS__
+
+#include <linux/irq_work.h>
+
+#include "intel_engine_types.h"
+
+struct drm_printer;
+struct i915_request;
+struct intel_breadcrumbs;
+
+struct intel_breadcrumbs *
+intel_breadcrumbs_create(struct intel_engine_cs *irq_engine);
+void intel_breadcrumbs_free(struct intel_breadcrumbs *b);
+
+void intel_breadcrumbs_reset(struct intel_breadcrumbs *b);
+void intel_breadcrumbs_park(struct intel_breadcrumbs *b);
+
+static inline void
+intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
+{
+	irq_work_queue(&engine->breadcrumbs->irq_work);
+}
+
+void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
+				    struct drm_printer *p);
+
+bool i915_request_enable_breadcrumb(struct i915_request *request);
+void i915_request_cancel_breadcrumb(struct i915_request *request);
+
+#endif /* __INTEL_BREADCRUMBS__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
new file mode 100644
index 000000000000..8e53b9942695
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_BREADCRUMBS_TYPES__
+#define __INTEL_BREADCRUMBS_TYPES__
+
+#include <linux/irq_work.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/*
+ * Rather than have every client wait upon all user interrupts,
+ * with the herd waking after every interrupt and each doing the
+ * heavyweight seqno dance, we delegate the task (of being the
+ * bottom-half of the user interrupt) to the first client. After
+ * every interrupt, we wake up one client, who does the heavyweight
+ * coherent seqno read and either goes back to sleep (if incomplete),
+ * or wakes up all the completed clients in parallel, before then
+ * transferring the bottom-half status to the next client in the queue.
+ *
+ * Compared to walking the entire list of waiters in a single dedicated
+ * bottom-half, we reduce the latency of the first waiter by avoiding
+ * a context switch, but incur additional coherent seqno reads when
+ * following the chain of request breadcrumbs. Since it is most likely
+ * that we have a single client waiting on each seqno, then reducing
+ * the overhead of waking that client is much preferred.
+ */
+struct intel_breadcrumbs {
+	spinlock_t irq_lock; /* protects the lists used in hardirq context */
+
+	/* Not all breadcrumbs are attached to physical HW */
+	struct intel_engine_cs *irq_engine;
+
+	struct list_head signalers;
+	struct list_head signaled_requests;
+
+	struct irq_work irq_work; /* for use from inside irq_lock */
+
+	unsigned int irq_enabled;
+
+	bool irq_armed;
+};
+
+#endif /* __INTEL_BREADCRUMBS_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 52db2bde44a3..d301dda1b261 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -93,57 +93,210 @@ static void intel_context_active_release(struct intel_context *ce)
 	i915_active_release(&ce->active);
 }
 
-int __intel_context_do_pin(struct intel_context *ce)
+static int __context_pin_state(struct i915_vma *vma, struct i915_gem_ww_ctx *ww)
+{
+	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
+	int err;
+
+	err = i915_ggtt_pin(vma, ww, 0, bias | PIN_HIGH);
+	if (err)
+		return err;
+
+	err = i915_active_acquire(&vma->active);
+	if (err)
+		goto err_unpin;
+
+	/*
+	 * And mark it as a globally pinned object to let the shrinker know
+	 * it cannot reclaim the object until we release it.
+	 */
+	i915_vma_make_unshrinkable(vma);
+	vma->obj->mm.dirty = true;
+
+	return 0;
+
+err_unpin:
+	i915_vma_unpin(vma);
+	return err;
+}
+
+static void __context_unpin_state(struct i915_vma *vma)
+{
+	i915_vma_make_shrinkable(vma);
+	i915_active_release(&vma->active);
+	__i915_vma_unpin(vma);
+}
+
+static int __ring_active(struct intel_ring *ring,
+			 struct i915_gem_ww_ctx *ww)
+{
+	int err;
+
+	err = intel_ring_pin(ring, ww);
+	if (err)
+		return err;
+
+	err = i915_active_acquire(&ring->vma->active);
+	if (err)
+		goto err_pin;
+
+	return 0;
+
+err_pin:
+	intel_ring_unpin(ring);
+	return err;
+}
+
+static void __ring_retire(struct intel_ring *ring)
+{
+	i915_active_release(&ring->vma->active);
+	intel_ring_unpin(ring);
+}
+
+static int intel_context_pre_pin(struct intel_context *ce,
+				 struct i915_gem_ww_ctx *ww)
 {
 	int err;
 
+	CE_TRACE(ce, "active\n");
+
+	err = __ring_active(ce->ring, ww);
+	if (err)
+		return err;
+
+	err = intel_timeline_pin(ce->timeline, ww);
+	if (err)
+		goto err_ring;
+
+	if (!ce->state)
+		return 0;
+
+	err = __context_pin_state(ce->state, ww);
+	if (err)
+		goto err_timeline;
+
+
+	return 0;
+
+err_timeline:
+	intel_timeline_unpin(ce->timeline);
+err_ring:
+	__ring_retire(ce->ring);
+	return err;
+}
+
+static void intel_context_post_unpin(struct intel_context *ce)
+{
+	if (ce->state)
+		__context_unpin_state(ce->state);
+
+	intel_timeline_unpin(ce->timeline);
+	__ring_retire(ce->ring);
+}
+
+int __intel_context_do_pin_ww(struct intel_context *ce,
+			      struct i915_gem_ww_ctx *ww)
+{
+	bool handoff = false;
+	void *vaddr;
+	int err = 0;
+
 	if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
 		err = intel_context_alloc_state(ce);
 		if (err)
 			return err;
 	}
 
-	err = i915_active_acquire(&ce->active);
+	/*
+	 * We always pin the context/ring/timeline here, to ensure a pin
+	 * refcount for __intel_context_active(), which prevent a lock
+	 * inversion of ce->pin_mutex vs dma_resv_lock().
+	 */
+
+	err = i915_gem_object_lock(ce->timeline->hwsp_ggtt->obj, ww);
+	if (!err && ce->ring->vma->obj)
+		err = i915_gem_object_lock(ce->ring->vma->obj, ww);
+	if (!err && ce->state)
+		err = i915_gem_object_lock(ce->state->obj, ww);
+	if (!err)
+		err = intel_context_pre_pin(ce, ww);
 	if (err)
 		return err;
 
-	if (mutex_lock_interruptible(&ce->pin_mutex)) {
-		err = -EINTR;
-		goto out_release;
-	}
+	err = i915_active_acquire(&ce->active);
+	if (err)
+		goto err_ctx_unpin;
+
+	err = ce->ops->pre_pin(ce, ww, &vaddr);
+	if (err)
+		goto err_release;
+
+	err = mutex_lock_interruptible(&ce->pin_mutex);
+	if (err)
+		goto err_post_unpin;
 
 	if (unlikely(intel_context_is_closed(ce))) {
 		err = -ENOENT;
-		goto out_unlock;
+		goto err_unlock;
 	}
 
 	if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) {
 		err = intel_context_active_acquire(ce);
 		if (unlikely(err))
-			goto out_unlock;
+			goto err_unlock;
 
-		err = ce->ops->pin(ce);
-		if (unlikely(err))
-			goto err_active;
+		err = ce->ops->pin(ce, vaddr);
+		if (err) {
+			intel_context_active_release(ce);
+			goto err_unlock;
+		}
 
 		CE_TRACE(ce, "pin ring:{start:%08x, head:%04x, tail:%04x}\n",
 			 i915_ggtt_offset(ce->ring->vma),
 			 ce->ring->head, ce->ring->tail);
 
+		handoff = true;
 		smp_mb__before_atomic(); /* flush pin before it is visible */
 		atomic_inc(&ce->pin_count);
 	}
 
 	GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
-	GEM_BUG_ON(i915_active_is_idle(&ce->active));
-	goto out_unlock;
 
-err_active:
-	intel_context_active_release(ce);
-out_unlock:
+err_unlock:
 	mutex_unlock(&ce->pin_mutex);
-out_release:
+err_post_unpin:
+	if (!handoff)
+		ce->ops->post_unpin(ce);
+err_release:
 	i915_active_release(&ce->active);
+err_ctx_unpin:
+	intel_context_post_unpin(ce);
+
+	/*
+	 * Unlock the hwsp_ggtt object since it's shared.
+	 * In principle we can unlock all the global state locked above
+	 * since it's pinned and doesn't need fencing, and will
+	 * thus remain resident until it is explicitly unpinned.
+	 */
+	i915_gem_ww_unlock_single(ce->timeline->hwsp_ggtt->obj);
+
+	return err;
+}
+
+int __intel_context_do_pin(struct intel_context *ce)
+{
+	struct i915_gem_ww_ctx ww;
+	int err;
+
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	err = __intel_context_do_pin_ww(ce, &ww);
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
 	return err;
 }
 
@@ -154,6 +307,7 @@ void intel_context_unpin(struct intel_context *ce)
 
 	CE_TRACE(ce, "unpin\n");
 	ce->ops->unpin(ce);
+	ce->ops->post_unpin(ce);
 
 	/*
 	 * Once released, we may asynchronously drop the active reference.
@@ -166,65 +320,6 @@ void intel_context_unpin(struct intel_context *ce)
 	intel_context_put(ce);
 }
 
-static int __context_pin_state(struct i915_vma *vma)
-{
-	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
-	int err;
-
-	err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
-	if (err)
-		return err;
-
-	err = i915_active_acquire(&vma->active);
-	if (err)
-		goto err_unpin;
-
-	/*
-	 * And mark it as a globally pinned object to let the shrinker know
-	 * it cannot reclaim the object until we release it.
-	 */
-	i915_vma_make_unshrinkable(vma);
-	vma->obj->mm.dirty = true;
-
-	return 0;
-
-err_unpin:
-	i915_vma_unpin(vma);
-	return err;
-}
-
-static void __context_unpin_state(struct i915_vma *vma)
-{
-	i915_vma_make_shrinkable(vma);
-	i915_active_release(&vma->active);
-	__i915_vma_unpin(vma);
-}
-
-static int __ring_active(struct intel_ring *ring)
-{
-	int err;
-
-	err = intel_ring_pin(ring);
-	if (err)
-		return err;
-
-	err = i915_active_acquire(&ring->vma->active);
-	if (err)
-		goto err_pin;
-
-	return 0;
-
-err_pin:
-	intel_ring_unpin(ring);
-	return err;
-}
-
-static void __ring_retire(struct intel_ring *ring)
-{
-	i915_active_release(&ring->vma->active);
-	intel_ring_unpin(ring);
-}
-
 __i915_active_call
 static void __intel_context_retire(struct i915_active *active)
 {
@@ -235,48 +330,29 @@ static void __intel_context_retire(struct i915_active *active)
 		 intel_context_get_avg_runtime_ns(ce));
 
 	set_bit(CONTEXT_VALID_BIT, &ce->flags);
-	if (ce->state)
-		__context_unpin_state(ce->state);
-
-	intel_timeline_unpin(ce->timeline);
-	__ring_retire(ce->ring);
-
+	intel_context_post_unpin(ce);
 	intel_context_put(ce);
 }
 
 static int __intel_context_active(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
-	int err;
-
-	CE_TRACE(ce, "active\n");
 
 	intel_context_get(ce);
 
-	err = __ring_active(ce->ring);
-	if (err)
-		goto err_put;
+	/* everything should already be activated by intel_context_pre_pin() */
+	GEM_WARN_ON(!i915_active_acquire_if_busy(&ce->ring->vma->active));
+	__intel_ring_pin(ce->ring);
 
-	err = intel_timeline_pin(ce->timeline);
-	if (err)
-		goto err_ring;
+	__intel_timeline_pin(ce->timeline);
 
-	if (!ce->state)
-		return 0;
-
-	err = __context_pin_state(ce->state);
-	if (err)
-		goto err_timeline;
+	if (ce->state) {
+		GEM_WARN_ON(!i915_active_acquire_if_busy(&ce->state->active));
+		__i915_vma_pin(ce->state);
+		i915_vma_make_unshrinkable(ce->state);
+	}
 
 	return 0;
-
-err_timeline:
-	intel_timeline_unpin(ce->timeline);
-err_ring:
-	__ring_retire(ce->ring);
-err_put:
-	intel_context_put(ce);
-	return err;
 }
 
 void
@@ -382,15 +458,37 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce)
 {
+	struct i915_gem_ww_ctx ww;
 	struct i915_request *rq;
 	int err;
 
-	err = intel_context_pin(ce);
-	if (unlikely(err))
-		return ERR_PTR(err);
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	err = intel_context_pin_ww(ce, &ww);
+	if (!err) {
+		rq = i915_request_create(ce);
+		intel_context_unpin(ce);
+	} else if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	} else {
+		rq = ERR_PTR(err);
+	}
+
+	i915_gem_ww_ctx_fini(&ww);
 
-	rq = i915_request_create(ce);
-	intel_context_unpin(ce);
+	if (IS_ERR(rq))
+		return rq;
+
+	/*
+	 * timeline->mutex should be the inner lock, but is used as outer lock.
+	 * Hack around this to shut up lockdep in selftests..
+	 */
+	lockdep_unpin_lock(&ce->timeline->mutex, rq->cookie);
+	mutex_release(&ce->timeline->mutex.dep_map, _RET_IP_);
+	mutex_acquire(&ce->timeline->mutex.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+	rq->cookie = lockdep_pin_lock(&ce->timeline->mutex);
 
 	return rq;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 07be021882cc..fda2eba81e22 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -25,6 +25,8 @@
 		     ##__VA_ARGS__);					\
 } while (0)
 
+struct i915_gem_ww_ctx;
+
 void intel_context_init(struct intel_context *ce,
 			struct intel_engine_cs *engine);
 void intel_context_fini(struct intel_context *ce);
@@ -81,6 +83,8 @@ static inline void intel_context_unlock_pinned(struct intel_context *ce)
 }
 
 int __intel_context_do_pin(struct intel_context *ce);
+int __intel_context_do_pin_ww(struct intel_context *ce,
+			      struct i915_gem_ww_ctx *ww);
 
 static inline bool intel_context_pin_if_active(struct intel_context *ce)
 {
@@ -95,6 +99,15 @@ static inline int intel_context_pin(struct intel_context *ce)
 	return __intel_context_do_pin(ce);
 }
 
+static inline int intel_context_pin_ww(struct intel_context *ce,
+				       struct i915_gem_ww_ctx *ww)
+{
+	if (likely(intel_context_pin_if_active(ce)))
+		return 0;
+
+	return __intel_context_do_pin_ww(ce, ww);
+}
+
 static inline void __intel_context_pin(struct intel_context *ce)
 {
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 4954b0df4864..552cb57a2e8c 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -23,6 +23,7 @@
 DECLARE_EWMA(runtime, 3, 8);
 
 struct i915_gem_context;
+struct i915_gem_ww_ctx;
 struct i915_vma;
 struct intel_context;
 struct intel_ring;
@@ -30,8 +31,10 @@ struct intel_ring;
 struct intel_context_ops {
 	int (*alloc)(struct intel_context *ce);
 
-	int (*pin)(struct intel_context *ce);
+	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
+	int (*pin)(struct intel_context *ce, void *vaddr);
 	void (*unpin)(struct intel_context *ce);
+	void (*post_unpin)(struct intel_context *ce);
 
 	void (*enter)(struct intel_context *ce);
 	void (*exit)(struct intel_context *ce);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index a9249a23903a..08e2c000dcc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -223,26 +223,6 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 
 void intel_engine_init_execlists(struct intel_engine_cs *engine);
 
-void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
-void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
-
-void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine);
-
-static inline void
-intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
-{
-	irq_work_queue(&engine->breadcrumbs.irq_work);
-}
-
-void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine);
-void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
-
-void intel_engine_transfer_stale_breadcrumbs(struct intel_engine_cs *engine,
-					     struct intel_context *ce);
-
-void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
-				    struct drm_printer *p);
-
 static inline u32 *__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
 {
 	memset(batch, 0, 6 * sizeof(u32));
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index dd1a42c4d344..5bfb5f7ed02c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -28,6 +28,7 @@
 
 #include "i915_drv.h"
 
+#include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
@@ -213,7 +214,7 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
 		break;
 	default:
 		MISSING_CASE(class);
-		/* fall through */
+		fallthrough;
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
@@ -634,7 +635,7 @@ static int pin_ggtt_status_page(struct intel_engine_cs *engine,
 	else
 		flags = PIN_HIGH;
 
-	return i915_ggtt_pin(vma, 0, flags);
+	return i915_ggtt_pin(vma, NULL, 0, flags);
 }
 
 static int init_status_page(struct intel_engine_cs *engine)
@@ -700,8 +701,13 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 	if (err)
 		return err;
 
+	engine->breadcrumbs = intel_breadcrumbs_create(engine);
+	if (!engine->breadcrumbs) {
+		err = -ENOMEM;
+		goto err_status;
+	}
+
 	intel_engine_init_active(engine, ENGINE_PHYSICAL);
-	intel_engine_init_breadcrumbs(engine);
 	intel_engine_init_execlists(engine);
 	intel_engine_init_cmd_parser(engine);
 	intel_engine_init__pm(engine);
@@ -716,6 +722,10 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_ctx_wa(engine);
 
 	return 0;
+
+err_status:
+	cleanup_status_page(engine);
+	return err;
 }
 
 struct measure_breadcrumb {
@@ -785,9 +795,11 @@ intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
 }
 
 static struct intel_context *
-create_kernel_context(struct intel_engine_cs *engine)
+create_pinned_context(struct intel_engine_cs *engine,
+		      unsigned int hwsp,
+		      struct lock_class_key *key,
+		      const char *name)
 {
-	static struct lock_class_key kernel;
 	struct intel_context *ce;
 	int err;
 
@@ -796,6 +808,7 @@ create_kernel_context(struct intel_engine_cs *engine)
 		return ce;
 
 	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);
+	ce->timeline = page_pack_bits(NULL, hwsp);
 
 	err = intel_context_pin(ce); /* perma-pin so it is always available */
 	if (err) {
@@ -809,11 +822,20 @@ create_kernel_context(struct intel_engine_cs *engine)
 	 * should we need to inject GPU operations during their request
 	 * construction.
 	 */
-	lockdep_set_class(&ce->timeline->mutex, &kernel);
+	lockdep_set_class_and_name(&ce->timeline->mutex, key, name);
 
 	return ce;
 }
 
+static struct intel_context *
+create_kernel_context(struct intel_engine_cs *engine)
+{
+	static struct lock_class_key kernel;
+
+	return create_pinned_context(engine, I915_GEM_HWS_SEQNO_ADDR,
+				     &kernel, "kernel_context");
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -902,9 +924,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
 	cleanup_status_page(engine);
+	intel_breadcrumbs_free(engine->breadcrumbs);
 
 	intel_engine_fini_retire(engine);
-	intel_engine_fini_breadcrumbs(engine);
 	intel_engine_cleanup_cmd_parser(engine);
 
 	if (engine->default_state)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 8ec3eecf3e39..f7b2e07e2229 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 
+#include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_heartbeat.h"
@@ -247,7 +248,7 @@ static int __engine_park(struct intel_wakeref *wf)
 	call_idle_barriers(engine); /* cleanup after wedging */
 
 	intel_engine_park_heartbeat(engine);
-	intel_engine_disarm_breadcrumbs(engine);
+	intel_breadcrumbs_park(engine->breadcrumbs);
 
 	/* Must be reset upon idling, or we may miss the busy wakeup. */
 	GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 8de92fd7d392..c400aaa2287b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -22,6 +22,7 @@
 #include "i915_pmu.h"
 #include "i915_priolist_types.h"
 #include "i915_selftest.h"
+#include "intel_breadcrumbs_types.h"
 #include "intel_sseu.h"
 #include "intel_timeline_types.h"
 #include "intel_uncore.h"
@@ -373,34 +374,8 @@ struct intel_engine_cs {
 	 */
 	struct ewma__engine_latency latency;
 
-	/* Rather than have every client wait upon all user interrupts,
-	 * with the herd waking after every interrupt and each doing the
-	 * heavyweight seqno dance, we delegate the task (of being the
-	 * bottom-half of the user interrupt) to the first client. After
-	 * every interrupt, we wake up one client, who does the heavyweight
-	 * coherent seqno read and either goes back to sleep (if incomplete),
-	 * or wakes up all the completed clients in parallel, before then
-	 * transferring the bottom-half status to the next client in the queue.
-	 *
-	 * Compared to walking the entire list of waiters in a single dedicated
-	 * bottom-half, we reduce the latency of the first waiter by avoiding
-	 * a context switch, but incur additional coherent seqno reads when
-	 * following the chain of request breadcrumbs. Since it is most likely
-	 * that we have a single client waiting on each seqno, then reducing
-	 * the overhead of waking that client is much preferred.
-	 */
-	struct intel_breadcrumbs {
-		spinlock_t irq_lock;
-		struct list_head signalers;
-
-		struct list_head signaled_requests;
-
-		struct irq_work irq_work; /* for use from inside irq_lock */
-
-		unsigned int irq_enabled;
-
-		bool irq_armed;
-	} breadcrumbs;
+	/* Keep track of all the seqno used, a trail of breadcrumbs */
+	struct intel_breadcrumbs *breadcrumbs;
 
 	struct intel_engine_pmu {
 		/**
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 62979ea591f0..81c05f551b9c 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -78,8 +78,6 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915)
 {
 	int ret;
 
-	stash_init(&i915->mm.wc_stash);
-
 	/*
 	 * Note that we use page colouring to enforce a guard page at the
 	 * end of the address space. This is required as the CS may prefetch
@@ -232,7 +230,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 
 	/* Fill the allocated but "unused" space beyond the end of the buffer */
 	while (gte < end)
-		gen8_set_pte(gte++, vm->scratch[0].encode);
+		gen8_set_pte(gte++, vm->scratch[0]->encode);
 
 	/*
 	 * We want to flush the TLBs only after we're certain all the PTE
@@ -283,7 +281,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 	/* Fill the allocated but "unused" space beyond the end of the buffer */
 	while (gte < end)
-		iowrite32(vm->scratch[0].encode, gte++);
+		iowrite32(vm->scratch[0]->encode, gte++);
 
 	/*
 	 * We want to flush the TLBs only after we're certain all the PTE
@@ -303,7 +301,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
 	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
-	const gen8_pte_t scratch_pte = vm->scratch[0].encode;
+	const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
 	gen8_pte_t __iomem *gtt_base =
 		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
 	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
@@ -401,7 +399,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = vm->scratch[0].encode;
+	scratch_pte = vm->scratch[0]->encode;
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
 }
@@ -436,16 +434,17 @@ static void i915_ggtt_clear_range(struct i915_address_space *vm,
 	intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
 }
 
-static int ggtt_bind_vma(struct i915_address_space *vm,
-			 struct i915_vma *vma,
-			 enum i915_cache_level cache_level,
-			 u32 flags)
+static void ggtt_bind_vma(struct i915_address_space *vm,
+			  struct i915_vm_pt_stash *stash,
+			  struct i915_vma *vma,
+			  enum i915_cache_level cache_level,
+			  u32 flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
 	u32 pte_flags;
 
 	if (i915_vma_is_bound(vma, ~flags & I915_VMA_BIND_MASK))
-		return 0;
+		return;
 
 	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
@@ -454,8 +453,6 @@ static int ggtt_bind_vma(struct i915_address_space *vm,
 
 	vm->insert_entries(vm, vma, cache_level, pte_flags);
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-
-	return 0;
 }
 
 static void ggtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
@@ -568,31 +565,25 @@ err:
 	return ret;
 }
 
-static int aliasing_gtt_bind_vma(struct i915_address_space *vm,
-				 struct i915_vma *vma,
-				 enum i915_cache_level cache_level,
-				 u32 flags)
+static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
+				  struct i915_vm_pt_stash *stash,
+				  struct i915_vma *vma,
+				  enum i915_cache_level cache_level,
+				  u32 flags)
 {
 	u32 pte_flags;
-	int ret;
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
 	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
-	if (flags & I915_VMA_LOCAL_BIND) {
-		struct i915_ppgtt *alias = i915_vm_to_ggtt(vm)->alias;
-
-		ret = ppgtt_bind_vma(&alias->vm, vma, cache_level, flags);
-		if (ret)
-			return ret;
-	}
+	if (flags & I915_VMA_LOCAL_BIND)
+		ppgtt_bind_vma(&i915_vm_to_ggtt(vm)->alias->vm,
+			       stash, vma, cache_level, flags);
 
 	if (flags & I915_VMA_GLOBAL_BIND)
 		vm->insert_entries(vm, vma, cache_level, pte_flags);
-
-	return 0;
 }
 
 static void aliasing_gtt_unbind_vma(struct i915_address_space *vm,
@@ -607,6 +598,7 @@ static void aliasing_gtt_unbind_vma(struct i915_address_space *vm,
 
 static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 {
+	struct i915_vm_pt_stash stash = {};
 	struct i915_ppgtt *ppgtt;
 	int err;
 
@@ -619,15 +611,21 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 		goto err_ppgtt;
 	}
 
+	err = i915_vm_alloc_pt_stash(&ppgtt->vm, &stash, ggtt->vm.total);
+	if (err)
+		goto err_ppgtt;
+
+	err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
+	if (err)
+		goto err_stash;
+
 	/*
 	 * Note we only pre-allocate as far as the end of the global
 	 * GTT. On 48b / 4-level page-tables, the difference is very,
 	 * very significant! We have to preallocate as GVT/vgpu does
 	 * not like the page directory disappearing.
 	 */
-	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
-	if (err)
-		goto err_ppgtt;
+	ppgtt->vm.allocate_va_range(&ppgtt->vm, &stash, 0, ggtt->vm.total);
 
 	ggtt->alias = ppgtt;
 	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
@@ -638,8 +636,11 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
 	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
 
+	i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 	return 0;
 
+err_stash:
+	i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 err_ppgtt:
 	i915_vm_put(&ppgtt->vm);
 	return err;
@@ -715,18 +716,11 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 void i915_ggtt_driver_release(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
-	struct pagevec *pvec;
 
 	fini_aliasing_ppgtt(ggtt);
 
 	intel_ggtt_fini_fences(ggtt);
 	ggtt_cleanup_hw(ggtt);
-
-	pvec = &i915->mm.wc_stash.pvec;
-	if (pvec->nr) {
-		set_pages_array_wb(pvec->pages, pvec->nr);
-		__pagevec_release(pvec);
-	}
 }
 
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
@@ -789,7 +783,7 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 		return -ENOMEM;
 	}
 
-	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
+	ret = setup_scratch_page(&ggtt->vm);
 	if (ret) {
 		drm_err(&i915->drm, "Scratch setup failed\n");
 		/* iounmap will also get called at remove, but meh */
@@ -797,8 +791,8 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 		return ret;
 	}
 
-	ggtt->vm.scratch[0].encode =
-		ggtt->vm.pte_encode(px_dma(&ggtt->vm.scratch[0]),
+	ggtt->vm.scratch[0]->encode =
+		ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
 				    I915_CACHE_NONE, 0);
 
 	return 0;
@@ -824,7 +818,7 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 
 	iounmap(ggtt->gsm);
-	cleanup_scratch_page(vm);
+	free_scratch(vm);
 }
 
 static struct resource pci_resource(struct pci_dev *pdev, int bar)
@@ -852,6 +846,8 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	else
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
 
+	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+
 	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
 	ggtt->vm.cleanup = gen6_gmch_remove;
 	ggtt->vm.insert_page = gen8_ggtt_insert_page;
@@ -1000,6 +996,8 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	size = gen6_get_total_gtt_size(snb_gmch_ctl);
 	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
 
+	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+
 	ggtt->vm.clear_range = nop_clear_range;
 	if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
 		ggtt->vm.clear_range = gen6_ggtt_clear_range;
@@ -1050,6 +1048,8 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->gmadr =
 		(struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
 
+	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+
 	ggtt->do_idle_maps = needs_idle_maps(i915);
 	ggtt->vm.insert_page = i915_ggtt_insert_page;
 	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
@@ -1165,11 +1165,6 @@ void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
 	ggtt->invalidate(ggtt);
 }
 
-static unsigned int clear_bind(struct i915_vma *vma)
-{
-	return atomic_fetch_and(~I915_VMA_BIND_MASK, &vma->flags);
-}
-
 void i915_ggtt_resume(struct i915_ggtt *ggtt)
 {
 	struct i915_vma *vma;
@@ -1187,11 +1182,13 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
 	/* clflush objects bound into the GGTT and rebind them. */
 	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
 		struct drm_i915_gem_object *obj = vma->obj;
-		unsigned int was_bound = clear_bind(vma);
+		unsigned int was_bound =
+			atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
 
-		WARN_ON(i915_vma_bind(vma,
-				      obj ? obj->cache_level : 0,
-				      was_bound, NULL));
+		GEM_BUG_ON(!was_bound);
+		vma->ops->bind_vma(&ggtt->vm, NULL, vma,
+				   obj ? obj->cache_level : 0,
+				   was_bound);
 		if (obj) { /* only used during resume => exclusive access */
 			flush |= fetch_and_zero(&obj->write_domain);
 			obj->read_domains |= I915_GEM_DOMAIN_GTT;
@@ -1437,7 +1434,7 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma)
 	switch (vma->ggtt_view.type) {
 	default:
 		GEM_BUG_ON(vma->ggtt_view.type);
-		/* fall through */
+		fallthrough;
 	case I915_GGTT_VIEW_NORMAL:
 		vma->pages = vma->obj->mm.pages;
 		return 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index e0755f1a904b..39b428c5049c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -356,7 +356,7 @@ static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
 		goto err_unref;
 	}
 
-	ret = i915_ggtt_pin(vma, 0, PIN_HIGH);
+	ret = i915_ggtt_pin(vma, NULL, 0, PIN_HIGH);
 	if (ret)
 		goto err_unref;
 
@@ -406,21 +406,20 @@ static int __engines_record_defaults(struct intel_gt *gt)
 		/* We must be able to switch to something! */
 		GEM_BUG_ON(!engine->kernel_context);
 
-		err = intel_renderstate_init(&so, engine);
-		if (err)
-			goto out;
-
 		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			goto out;
 		}
 
-		rq = intel_context_create_request(ce);
+		err = intel_renderstate_init(&so, ce);
+		if (err)
+			goto err;
+
+		rq = i915_request_create(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			intel_context_put(ce);
-			goto out;
+			goto err_fini;
 		}
 
 		err = intel_engine_emit_ctx_wa(rq);
@@ -434,9 +433,13 @@ static int __engines_record_defaults(struct intel_gt *gt)
 err_rq:
 		requests[id] = i915_request_get(rq);
 		i915_request_add(rq);
-		intel_renderstate_fini(&so);
-		if (err)
+err_fini:
+		intel_renderstate_fini(&so, ce);
+err:
+		if (err) {
+			intel_context_put(ce);
 			goto out;
+		}
 	}
 
 	/* Flush the default context image to memory, and enable powersaving. */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
index 418ae184cecf..4b7671ac5dca 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
@@ -35,39 +35,65 @@ static void node_free(struct intel_gt_buffer_pool_node *node)
 {
 	i915_gem_object_put(node->obj);
 	i915_active_fini(&node->active);
-	kfree(node);
+	kfree_rcu(node, rcu);
 }
 
-static void pool_free_work(struct work_struct *wrk)
+static bool pool_free_older_than(struct intel_gt_buffer_pool *pool, long keep)
 {
-	struct intel_gt_buffer_pool *pool =
-		container_of(wrk, typeof(*pool), work.work);
-	struct intel_gt_buffer_pool_node *node, *next;
-	unsigned long old = jiffies - HZ;
+	struct intel_gt_buffer_pool_node *node, *stale = NULL;
 	bool active = false;
-	LIST_HEAD(stale);
 	int n;
 
 	/* Free buffers that have not been used in the past second */
-	spin_lock_irq(&pool->lock);
 	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) {
 		struct list_head *list = &pool->cache_list[n];
 
-		/* Most recent at head; oldest at tail */
-		list_for_each_entry_safe_reverse(node, next, list, link) {
-			if (time_before(node->age, old))
-				break;
+		if (list_empty(list))
+			continue;
+
+		if (spin_trylock_irq(&pool->lock)) {
+			struct list_head *pos;
+
+			/* Most recent at head; oldest at tail */
+			list_for_each_prev(pos, list) {
+				unsigned long age;
+
+				node = list_entry(pos, typeof(*node), link);
+
+				age = READ_ONCE(node->age);
+				if (!age || jiffies - age < keep)
+					break;
+
+				/* Check we are the first to claim this node */
+				if (!xchg(&node->age, 0))
+					break;
 
-			list_move(&node->link, &stale);
+				node->free = stale;
+				stale = node;
+			}
+			if (!list_is_last(pos, list))
+				__list_del_many(pos, list);
+
+			spin_unlock_irq(&pool->lock);
 		}
+
 		active |= !list_empty(list);
 	}
-	spin_unlock_irq(&pool->lock);
 
-	list_for_each_entry_safe(node, next, &stale, link)
+	while ((node = stale)) {
+		stale = stale->free;
 		node_free(node);
+	}
+
+	return active;
+}
+
+static void pool_free_work(struct work_struct *wrk)
+{
+	struct intel_gt_buffer_pool *pool =
+		container_of(wrk, typeof(*pool), work.work);
 
-	if (active)
+	if (pool_free_older_than(pool, HZ))
 		schedule_delayed_work(&pool->work,
 				      round_jiffies_up_relative(HZ));
 }
@@ -109,8 +135,8 @@ static void pool_retire(struct i915_active *ref)
 	i915_gem_object_make_purgeable(node->obj);
 
 	spin_lock_irqsave(&pool->lock, flags);
-	node->age = jiffies;
-	list_add(&node->link, list);
+	list_add_rcu(&node->link, list);
+	WRITE_ONCE(node->age, jiffies ?: 1); /* 0 reserved for active nodes */
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	schedule_delayed_work(&pool->work,
@@ -151,20 +177,30 @@ intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size)
 	struct intel_gt_buffer_pool *pool = &gt->buffer_pool;
 	struct intel_gt_buffer_pool_node *node;
 	struct list_head *list;
-	unsigned long flags;
 	int ret;
 
 	size = PAGE_ALIGN(size);
 	list = bucket_for_size(pool, size);
 
-	spin_lock_irqsave(&pool->lock, flags);
-	list_for_each_entry(node, list, link) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(node, list, link) {
+		unsigned long age;
+
 		if (node->obj->base.size < size)
 			continue;
-		list_del(&node->link);
-		break;
+
+		age = READ_ONCE(node->age);
+		if (!age)
+			continue;
+
+		if (cmpxchg(&node->age, age, 0) == age) {
+			spin_lock_irq(&pool->lock);
+			list_del_rcu(&node->link);
+			spin_unlock_irq(&pool->lock);
+			break;
+		}
 	}
-	spin_unlock_irqrestore(&pool->lock, flags);
+	rcu_read_unlock();
 
 	if (&node->link == list) {
 		node = node_create(pool, size);
@@ -192,28 +228,13 @@ void intel_gt_init_buffer_pool(struct intel_gt *gt)
 	INIT_DELAYED_WORK(&pool->work, pool_free_work);
 }
 
-static void pool_free_imm(struct intel_gt_buffer_pool *pool)
-{
-	int n;
-
-	spin_lock_irq(&pool->lock);
-	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) {
-		struct intel_gt_buffer_pool_node *node, *next;
-		struct list_head *list = &pool->cache_list[n];
-
-		list_for_each_entry_safe(node, next, list, link)
-			node_free(node);
-		INIT_LIST_HEAD(list);
-	}
-	spin_unlock_irq(&pool->lock);
-}
-
 void intel_gt_flush_buffer_pool(struct intel_gt *gt)
 {
 	struct intel_gt_buffer_pool *pool = &gt->buffer_pool;
 
 	do {
-		pool_free_imm(pool);
+		while (pool_free_older_than(pool, 0))
+			;
 	} while (cancel_delayed_work_sync(&pool->work));
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h
index e28bdda771ed..bcf1658c9633 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h
@@ -25,7 +25,11 @@ struct intel_gt_buffer_pool_node {
 	struct i915_active active;
 	struct drm_i915_gem_object *obj;
 	struct list_head link;
-	struct intel_gt_buffer_pool *pool;
+	union {
+		struct intel_gt_buffer_pool *pool;
+		struct intel_gt_buffer_pool_node *free;
+		struct rcu_head rcu;
+	};
 	unsigned long age;
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index b05da68e52f4..257063a57101 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -8,6 +8,7 @@
 
 #include "i915_drv.h"
 #include "i915_irq.h"
+#include "intel_breadcrumbs.h"
 #include "intel_gt.h"
 #include "intel_gt_irq.h"
 #include "intel_uncore.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 2a72cce63fd9..3f1114b58b01 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -11,160 +11,24 @@
 #include "intel_gt.h"
 #include "intel_gtt.h"
 
-void stash_init(struct pagestash *stash)
+struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 {
-	pagevec_init(&stash->pvec);
-	spin_lock_init(&stash->lock);
-}
-
-static struct page *stash_pop_page(struct pagestash *stash)
-{
-	struct page *page = NULL;
-
-	spin_lock(&stash->lock);
-	if (likely(stash->pvec.nr))
-		page = stash->pvec.pages[--stash->pvec.nr];
-	spin_unlock(&stash->lock);
-
-	return page;
-}
-
-static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
-{
-	unsigned int nr;
-
-	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
-
-	nr = min_t(typeof(nr), pvec->nr, pagevec_space(&stash->pvec));
-	memcpy(stash->pvec.pages + stash->pvec.nr,
-	       pvec->pages + pvec->nr - nr,
-	       sizeof(pvec->pages[0]) * nr);
-	stash->pvec.nr += nr;
-
-	spin_unlock(&stash->lock);
-
-	pvec->nr -= nr;
-}
-
-static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
-{
-	struct pagevec stack;
-	struct page *page;
-
 	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
 		i915_gem_shrink_all(vm->i915);
 
-	page = stash_pop_page(&vm->free_pages);
-	if (page)
-		return page;
-
-	if (!vm->pt_kmap_wc)
-		return alloc_page(gfp);
-
-	/* Look in our global stash of WC pages... */
-	page = stash_pop_page(&vm->i915->mm.wc_stash);
-	if (page)
-		return page;
-
-	/*
-	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
-	 *
-	 * We have to be careful as page allocation may trigger the shrinker
-	 * (via direct reclaim) which will fill up the WC stash underneath us.
-	 * So we add our WB pages into a temporary pvec on the stack and merge
-	 * them into the WC stash after all the allocations are complete.
-	 */
-	pagevec_init(&stack);
-	do {
-		struct page *page;
-
-		page = alloc_page(gfp);
-		if (unlikely(!page))
-			break;
-
-		stack.pages[stack.nr++] = page;
-	} while (pagevec_space(&stack));
-
-	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
-		page = stack.pages[--stack.nr];
-
-		/* Merge spare WC pages to the global stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
-
-		/* Push any surplus WC pages onto the local VM stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->free_pages, &stack);
-	}
-
-	/* Return unwanted leftovers */
-	if (unlikely(stack.nr)) {
-		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
-		__pagevec_release(&stack);
-	}
-
-	return page;
+	return i915_gem_object_create_internal(vm->i915, sz);
 }
 
-static void vm_free_pages_release(struct i915_address_space *vm,
-				  bool immediate)
+int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 {
-	struct pagevec *pvec = &vm->free_pages.pvec;
-	struct pagevec stack;
-
-	lockdep_assert_held(&vm->free_pages.lock);
-	GEM_BUG_ON(!pagevec_count(pvec));
-
-	if (vm->pt_kmap_wc) {
-		/*
-		 * When we use WC, first fill up the global stash and then
-		 * only if full immediately free the overflow.
-		 */
-		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
-
-		/*
-		 * As we have made some room in the VM's free_pages,
-		 * we can wait for it to fill again. Unless we are
-		 * inside i915_address_space_fini() and must
-		 * immediately release the pages!
-		 */
-		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
-			return;
+	int err;
 
-		/*
-		 * We have to drop the lock to allow ourselves to sleep,
-		 * so take a copy of the pvec and clear the stash for
-		 * others to use it as we sleep.
-		 */
-		stack = *pvec;
-		pagevec_reinit(pvec);
-		spin_unlock(&vm->free_pages.lock);
-
-		pvec = &stack;
-		set_pages_array_wb(pvec->pages, pvec->nr);
-
-		spin_lock(&vm->free_pages.lock);
-	}
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		return err;
 
-	__pagevec_release(pvec);
-}
-
-static void vm_free_page(struct i915_address_space *vm, struct page *page)
-{
-	/*
-	 * On !llc, we need to change the pages back to WB. We only do so
-	 * in bulk, so we rarely need to change the page attributes here,
-	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
-	 * To make detection of the possible sleep more likely, use an
-	 * unconditional might_sleep() for everybody.
-	 */
-	might_sleep();
-	spin_lock(&vm->free_pages.lock);
-	while (!pagevec_space(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, false);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec) >= PAGEVEC_SIZE);
-	pagevec_add(&vm->free_pages.pvec, page);
-	spin_unlock(&vm->free_pages.lock);
+	i915_gem_object_make_unshrinkable(obj);
+	return 0;
 }
 
 void __i915_vm_close(struct i915_address_space *vm)
@@ -194,14 +58,7 @@ void __i915_vm_close(struct i915_address_space *vm)
 
 void i915_address_space_fini(struct i915_address_space *vm)
 {
-	spin_lock(&vm->free_pages.lock);
-	if (pagevec_count(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, true);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
-	spin_unlock(&vm->free_pages.lock);
-
 	drm_mm_takedown(&vm->mm);
-
 	mutex_destroy(&vm->mutex);
 }
 
@@ -246,8 +103,6 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 	drm_mm_init(&vm->mm, 0, vm->total);
 	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
 
-	stash_init(&vm->free_pages);
-
 	INIT_LIST_HEAD(&vm->bound_list);
 }
 
@@ -264,64 +119,50 @@ void clear_pages(struct i915_vma *vma)
 	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
 }
 
-static int __setup_page_dma(struct i915_address_space *vm,
-			    struct i915_page_dma *p,
-			    gfp_t gfp)
-{
-	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
-	if (unlikely(!p->page))
-		return -ENOMEM;
-
-	p->daddr = dma_map_page_attrs(vm->dma,
-				      p->page, 0, PAGE_SIZE,
-				      PCI_DMA_BIDIRECTIONAL,
-				      DMA_ATTR_SKIP_CPU_SYNC |
-				      DMA_ATTR_NO_WARN);
-	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
-		vm_free_page(vm, p->page);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+dma_addr_t __px_dma(struct drm_i915_gem_object *p)
 {
-	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
+	GEM_BUG_ON(!i915_gem_object_has_pages(p));
+	return sg_dma_address(p->mm.pages->sgl);
 }
 
-void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+struct page *__px_page(struct drm_i915_gem_object *p)
 {
-	dma_unmap_page(vm->dma, p->daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	vm_free_page(vm, p->page);
+	GEM_BUG_ON(!i915_gem_object_has_pages(p));
+	return sg_page(p->mm.pages->sgl);
 }
 
 void
-fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count)
+fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count)
 {
-	kunmap_atomic(memset64(kmap_atomic(p->page), val, count));
+	struct page *page = __px_page(p);
+	void *vaddr;
+
+	vaddr = kmap(page);
+	memset64(vaddr, val, count);
+	clflush_cache_range(vaddr, PAGE_SIZE);
+	kunmap(page);
 }
 
-static void poison_scratch_page(struct page *page, unsigned long size)
+static void poison_scratch_page(struct drm_i915_gem_object *scratch)
 {
-	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-		return;
+	struct sgt_iter sgt;
+	struct page *page;
+	u8 val;
 
-	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
+	val = 0;
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		val = POISON_FREE;
 
-	do {
+	for_each_sgt_page(page, sgt, scratch->mm.pages) {
 		void *vaddr;
 
 		vaddr = kmap(page);
-		memset(vaddr, POISON_FREE, PAGE_SIZE);
+		memset(vaddr, val, PAGE_SIZE);
 		kunmap(page);
-
-		page = pfn_to_page(page_to_pfn(page) + 1);
-		size -= PAGE_SIZE;
-	} while (size);
+	}
 }
 
-int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
+int setup_scratch_page(struct i915_address_space *vm)
 {
 	unsigned long size;
 
@@ -338,21 +179,27 @@ int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 	 */
 	size = I915_GTT_PAGE_SIZE_4K;
 	if (i915_vm_is_4lvl(vm) &&
-	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
+	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K))
 		size = I915_GTT_PAGE_SIZE_64K;
-		gfp |= __GFP_NOWARN;
-	}
-	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
 
 	do {
-		unsigned int order = get_order(size);
-		struct page *page;
-		dma_addr_t addr;
+		struct drm_i915_gem_object *obj;
 
-		page = alloc_pages(gfp, order);
-		if (unlikely(!page))
+		obj = vm->alloc_pt_dma(vm, size);
+		if (IS_ERR(obj))
 			goto skip;
 
+		if (pin_pt_dma(vm, obj))
+			goto skip_obj;
+
+		/* We need a single contiguous page for our scratch */
+		if (obj->mm.page_sizes.sg < size)
+			goto skip_obj;
+
+		/* And it needs to be correspondingly aligned */
+		if (__px_dma(obj) & (size - 1))
+			goto skip_obj;
+
 		/*
 		 * Use a non-zero scratch page for debugging.
 		 *
@@ -362,61 +209,28 @@ int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 		 * should it ever be accidentally used, the effect should be
 		 * fairly benign.
 		 */
-		poison_scratch_page(page, size);
-
-		addr = dma_map_page_attrs(vm->dma,
-					  page, 0, size,
-					  PCI_DMA_BIDIRECTIONAL,
-					  DMA_ATTR_SKIP_CPU_SYNC |
-					  DMA_ATTR_NO_WARN);
-		if (unlikely(dma_mapping_error(vm->dma, addr)))
-			goto free_page;
-
-		if (unlikely(!IS_ALIGNED(addr, size)))
-			goto unmap_page;
-
-		vm->scratch[0].base.page = page;
-		vm->scratch[0].base.daddr = addr;
-		vm->scratch_order = order;
+		poison_scratch_page(obj);
+
+		vm->scratch[0] = obj;
+		vm->scratch_order = get_order(size);
 		return 0;
 
-unmap_page:
-		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
-free_page:
-		__free_pages(page, order);
+skip_obj:
+		i915_gem_object_put(obj);
 skip:
 		if (size == I915_GTT_PAGE_SIZE_4K)
 			return -ENOMEM;
 
 		size = I915_GTT_PAGE_SIZE_4K;
-		gfp &= ~__GFP_NOWARN;
 	} while (1);
 }
 
-void cleanup_scratch_page(struct i915_address_space *vm)
-{
-	struct i915_page_dma *p = px_base(&vm->scratch[0]);
-	unsigned int order = vm->scratch_order;
-
-	dma_unmap_page(vm->dma, p->daddr, BIT(order) << PAGE_SHIFT,
-		       PCI_DMA_BIDIRECTIONAL);
-	__free_pages(p->page, order);
-}
-
 void free_scratch(struct i915_address_space *vm)
 {
 	int i;
 
-	if (!px_dma(&vm->scratch[0])) /* set to 0 on clones */
-		return;
-
-	for (i = 1; i <= vm->top; i++) {
-		if (!px_dma(&vm->scratch[i]))
-			break;
-		cleanup_page_dma(vm, px_base(&vm->scratch[i]));
-	}
-
-	cleanup_scratch_page(vm);
+	for (i = 0; i <= vm->top; i++)
+		i915_gem_object_put(vm->scratch[i]);
 }
 
 void gtt_write_workarounds(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index f2b75078e05f..c13c650ced22 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -134,38 +134,29 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
+enum i915_cache_level;
+
+struct drm_i915_file_private;
+struct drm_i915_gem_object;
 struct i915_fence_reg;
+struct i915_vma;
+struct intel_gt;
 
 #define for_each_sgt_daddr(__dp, __iter, __sgt) \
 	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
 
-struct i915_page_dma {
-	struct page *page;
+struct i915_page_table {
+	struct drm_i915_gem_object *base;
 	union {
-		dma_addr_t daddr;
-
-		/*
-		 * For gen6/gen7 only. This is the offset in the GGTT
-		 * where the page directory entries for PPGTT begin
-		 */
-		u32 ggtt_offset;
+		atomic_t used;
+		struct i915_page_table *stash;
 	};
 };
 
-struct i915_page_scratch {
-	struct i915_page_dma base;
-	u64 encode;
-};
-
-struct i915_page_table {
-	struct i915_page_dma base;
-	atomic_t used;
-};
-
 struct i915_page_directory {
 	struct i915_page_table pt;
 	spinlock_t lock;
-	void *entry[512];
+	void **entry;
 };
 
 #define __px_choose_expr(x, type, expr, other) \
@@ -176,12 +167,14 @@ struct i915_page_directory {
 	other)
 
 #define px_base(px) \
-	__px_choose_expr(px, struct i915_page_dma *, __x, \
-	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
-	(void)0))))
-#define px_dma(px) (px_base(px)->daddr)
+	__px_choose_expr(px, struct drm_i915_gem_object *, __x, \
+	__px_choose_expr(px, struct i915_page_table *, __x->base, \
+	__px_choose_expr(px, struct i915_page_directory *, __x->pt.base, \
+	(void)0)))
+
+struct page *__px_page(struct drm_i915_gem_object *p);
+dma_addr_t __px_dma(struct drm_i915_gem_object *p);
+#define px_dma(px) (__px_dma(px_base(px)))
 
 #define px_pt(px) \
 	__px_choose_expr(px, struct i915_page_table *, __x, \
@@ -189,19 +182,18 @@ struct i915_page_directory {
 	(void)0))
 #define px_used(px) (&px_pt(px)->used)
 
-enum i915_cache_level;
-
-struct drm_i915_file_private;
-struct drm_i915_gem_object;
-struct i915_vma;
-struct intel_gt;
+struct i915_vm_pt_stash {
+	/* preallocated chains of page tables/directories */
+	struct i915_page_table *pt[2];
+};
 
 struct i915_vma_ops {
 	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_address_space *vm,
-			struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
+	void (*bind_vma)(struct i915_address_space *vm,
+			 struct i915_vm_pt_stash *stash,
+			 struct i915_vma *vma,
+			 enum i915_cache_level cache_level,
+			 u32 flags);
 	/*
 	 * Unmap an object from an address space. This usually consists of
 	 * setting the valid PTE entries to a reserved scratch page.
@@ -213,13 +205,6 @@ struct i915_vma_ops {
 	void (*clear_pages)(struct i915_vma *vma);
 };
 
-struct pagestash {
-	spinlock_t lock;
-	struct pagevec pvec;
-};
-
-void stash_init(struct pagestash *stash);
-
 struct i915_address_space {
 	struct kref ref;
 	struct rcu_work rcu;
@@ -256,33 +241,33 @@ struct i915_address_space {
 #define VM_CLASS_GGTT 0
 #define VM_CLASS_PPGTT 1
 
-	struct i915_page_scratch scratch[4];
-	unsigned int scratch_order;
-	unsigned int top;
-
+	struct drm_i915_gem_object *scratch[4];
 	/**
 	 * List of vma currently bound.
 	 */
 	struct list_head bound_list;
 
-	struct pagestash free_pages;
-
 	/* Global GTT */
 	bool is_ggtt:1;
 
-	/* Some systems require uncached updates of the page directories */
-	bool pt_kmap_wc:1;
-
 	/* Some systems support read-only mappings for GGTT and/or PPGTT */
 	bool has_read_only:1;
 
+	u8 top;
+	u8 pd_shift;
+	u8 scratch_order;
+
+	struct drm_i915_gem_object *
+		(*alloc_pt_dma)(struct i915_address_space *vm, int sz);
+
 	u64 (*pte_encode)(dma_addr_t addr,
 			  enum i915_cache_level level,
 			  u32 flags); /* Create a valid PTE */
 #define PTE_READ_ONLY	BIT(0)
 
-	int (*allocate_va_range)(struct i915_address_space *vm,
-				 u64 start, u64 length);
+	void (*allocate_va_range)(struct i915_address_space *vm,
+				  struct i915_vm_pt_stash *stash,
+				  u64 start, u64 length);
 	void (*clear_range)(struct i915_address_space *vm,
 			    u64 start, u64 length);
 	void (*insert_page)(struct i915_address_space *vm,
@@ -490,9 +475,9 @@ i915_pd_entry(const struct i915_page_directory * const pdp,
 static inline dma_addr_t
 i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
 {
-	struct i915_page_dma *pt = ppgtt->pd->entry[n];
+	struct i915_page_table *pt = ppgtt->pd->entry[n];
 
-	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
+	return __px_dma(pt ? px_base(pt) : ppgtt->vm.scratch[ppgtt->vm.top]);
 }
 
 void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt);
@@ -517,13 +502,10 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt);
 void i915_ggtt_suspend(struct i915_ggtt *gtt);
 void i915_ggtt_resume(struct i915_ggtt *ggtt);
 
-int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
-void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
-
-#define kmap_atomic_px(px) kmap_atomic(px_base(px)->page)
+#define kmap_atomic_px(px) kmap_atomic(__px_page(px_base(px)))
 
 void
-fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count);
+fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count);
 
 #define fill_px(px, v) fill_page_dma(px_base(px), (v), PAGE_SIZE / sizeof(u64))
 #define fill32_px(px, v) do {						\
@@ -531,47 +513,51 @@ fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count);
 	fill_px((px), v__ << 32 | v__);					\
 } while (0)
 
-int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp);
-void cleanup_scratch_page(struct i915_address_space *vm);
+int setup_scratch_page(struct i915_address_space *vm);
 void free_scratch(struct i915_address_space *vm);
 
+struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz);
 struct i915_page_table *alloc_pt(struct i915_address_space *vm);
 struct i915_page_directory *alloc_pd(struct i915_address_space *vm);
-struct i915_page_directory *__alloc_pd(size_t sz);
+struct i915_page_directory *__alloc_pd(int npde);
 
-void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd);
+int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj);
 
-#define free_px(vm, px) free_pd(vm, px_base(px))
+void free_px(struct i915_address_space *vm,
+	     struct i915_page_table *pt, int lvl);
+#define free_pt(vm, px) free_px(vm, px, 0)
+#define free_pd(vm, px) free_px(vm, px_pt(px), 1)
 
 void
 __set_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
-	       struct i915_page_dma * const to,
+	       struct i915_page_table *pt,
 	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level));
 
 #define set_pd_entry(pd, idx, to) \
-	__set_pd_entry((pd), (idx), px_base(to), gen8_pde_encode)
+	__set_pd_entry((pd), (idx), px_pt(to), gen8_pde_encode)
 
 void
 clear_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
-	       const struct i915_page_scratch * const scratch);
+	       const struct drm_i915_gem_object * const scratch);
 
 bool
 release_pd_entry(struct i915_page_directory * const pd,
 		 const unsigned short idx,
 		 struct i915_page_table * const pt,
-		 const struct i915_page_scratch * const scratch);
+		 const struct drm_i915_gem_object * const scratch);
 void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
 
 int ggtt_set_pages(struct i915_vma *vma);
 int ppgtt_set_pages(struct i915_vma *vma);
 void clear_pages(struct i915_vma *vma);
 
-int ppgtt_bind_vma(struct i915_address_space *vm,
-		   struct i915_vma *vma,
-		   enum i915_cache_level cache_level,
-		   u32 flags);
+void ppgtt_bind_vma(struct i915_address_space *vm,
+		    struct i915_vm_pt_stash *stash,
+		    struct i915_vma *vma,
+		    enum i915_cache_level cache_level,
+		    u32 flags);
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma *vma);
 
@@ -579,6 +565,14 @@ void gtt_write_workarounds(struct intel_gt *gt);
 
 void setup_private_pat(struct intel_uncore *uncore);
 
+int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash,
+			   u64 size);
+int i915_vm_pin_pt_stash(struct i915_address_space *vm,
+			 struct i915_vm_pt_stash *stash);
+void i915_vm_free_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash);
+
 static inline struct sgt_dma {
 	struct scatterlist *sg;
 	dma_addr_t dma, max;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..0412a44f25f2 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -137,6 +137,7 @@
 #include "i915_perf.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
+#include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
@@ -1148,20 +1149,6 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 		} else {
 			struct intel_engine_cs *owner = rq->context->engine;
 
-			/*
-			 * Decouple the virtual breadcrumb before moving it
-			 * back to the virtual engine -- we don't want the
-			 * request to complete in the background and try
-			 * and cancel the breadcrumb on the virtual engine
-			 * (instead of the old engine where it is linked)!
-			 */
-			if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
-				     &rq->fence.flags)) {
-				spin_lock_nested(&rq->lock,
-						 SINGLE_DEPTH_NESTING);
-				i915_request_cancel_breadcrumb(rq);
-				spin_unlock(&rq->lock);
-			}
 			WRITE_ONCE(rq->engine, owner);
 			owner->submit_request(rq);
 			active = NULL;
@@ -1819,16 +1806,31 @@ static bool virtual_matches(const struct virtual_engine *ve,
 	return true;
 }
 
-static void virtual_xfer_breadcrumbs(struct virtual_engine *ve)
+static void virtual_xfer_context(struct virtual_engine *ve,
+				 struct intel_engine_cs *engine)
 {
+	unsigned int n;
+
+	if (likely(engine == ve->siblings[0]))
+		return;
+
+	GEM_BUG_ON(READ_ONCE(ve->context.inflight));
+	if (!intel_engine_has_relative_mmio(engine))
+		virtual_update_register_offsets(ve->context.lrc_reg_state,
+						engine);
+
 	/*
-	 * All the outstanding signals on ve->siblings[0] must have
-	 * been completed, just pending the interrupt handler. As those
-	 * signals still refer to the old sibling (via rq->engine), we must
-	 * transfer those to the old irq_worker to keep our locking
-	 * consistent.
+	 * Move the bound engine to the top of the list for
+	 * future execution. We then kick this tasklet first
+	 * before checking others, so that we preferentially
+	 * reuse this set of bound registers.
 	 */
-	intel_engine_transfer_stale_breadcrumbs(ve->siblings[0], &ve->context);
+	for (n = 1; n < ve->num_siblings; n++) {
+		if (ve->siblings[n] == engine) {
+			swap(ve->siblings[n], ve->siblings[0]);
+			break;
+		}
+	}
 }
 
 #define for_each_waiter(p__, rq__) \
@@ -2060,6 +2062,14 @@ static inline void clear_ports(struct i915_request **ports, int count)
 	memset_p((void **)ports, NULL, count);
 }
 
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -2271,38 +2281,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			GEM_BUG_ON(!(rq->execution_mask & engine->mask));
 			WRITE_ONCE(rq->engine, engine);
 
-			if (engine != ve->siblings[0]) {
-				u32 *regs = ve->context.lrc_reg_state;
-				unsigned int n;
-
-				GEM_BUG_ON(READ_ONCE(ve->context.inflight));
-
-				if (!intel_engine_has_relative_mmio(engine))
-					virtual_update_register_offsets(regs,
-									engine);
-
-				if (!list_empty(&ve->context.signals))
-					virtual_xfer_breadcrumbs(ve);
-
+			if (__i915_request_submit(rq)) {
 				/*
-				 * Move the bound engine to the top of the list
-				 * for future execution. We then kick this
-				 * tasklet first before checking others, so that
-				 * we preferentially reuse this set of bound
-				 * registers.
+				 * Only after we confirm that we will submit
+				 * this request (i.e. it has not already
+				 * completed), do we want to update the context.
+				 *
+				 * This serves two purposes. It avoids
+				 * unnecessary work if we are resubmitting an
+				 * already completed request after timeslicing.
+				 * But more importantly, it prevents us altering
+				 * ve->siblings[] on an idle context, where
+				 * we may be using ve->siblings[] in
+				 * virtual_context_enter / virtual_context_exit.
 				 */
-				for (n = 1; n < ve->num_siblings; n++) {
-					if (ve->siblings[n] == engine) {
-						swap(ve->siblings[n],
-						     ve->siblings[0]);
-						break;
-					}
-				}
-
+				virtual_xfer_context(ve, engine);
 				GEM_BUG_ON(ve->siblings[0] != engine);
-			}
 
-			if (__i915_request_submit(rq)) {
 				submit = true;
 				last = rq;
 			}
@@ -2648,10 +2643,9 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			memcpy(execlists->inflight,
-			       execlists->pending,
-			       execlists_num_ports(execlists) *
-			       sizeof(*execlists->pending));
+			copy_ports(execlists->inflight,
+				   execlists->pending,
+				   execlists_num_ports(execlists));
 			smp_wmb(); /* complete the seqlock */
 			WRITE_ONCE(execlists->active, execlists->inflight);
 
@@ -3309,7 +3303,10 @@ static void execlists_context_unpin(struct intel_context *ce)
 {
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
 		      ce->engine);
+}
 
+static void execlists_context_post_unpin(struct intel_context *ce)
+{
 	i915_gem_object_unpin_map(ce->state->obj);
 }
 
@@ -3471,20 +3468,24 @@ __execlists_update_reg_state(const struct intel_context *ce,
 }
 
 static int
-__execlists_context_pin(struct intel_context *ce,
-			struct intel_engine_cs *engine)
+execlists_context_pre_pin(struct intel_context *ce,
+			  struct i915_gem_ww_ctx *ww, void **vaddr)
 {
-	void *vaddr;
-
 	GEM_BUG_ON(!ce->state);
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
-	vaddr = i915_gem_object_pin_map(ce->state->obj,
-					i915_coherent_map_type(engine->i915) |
+	*vaddr = i915_gem_object_pin_map(ce->state->obj,
+					i915_coherent_map_type(ce->engine->i915) |
 					I915_MAP_OVERRIDE);
-	if (IS_ERR(vaddr))
-		return PTR_ERR(vaddr);
 
+	return PTR_ERR_OR_ZERO(*vaddr);
+}
+
+static int
+__execlists_context_pin(struct intel_context *ce,
+			struct intel_engine_cs *engine,
+			void *vaddr)
+{
 	ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_OFFSET;
 	__execlists_update_reg_state(ce, engine, ce->ring->tail);
@@ -3492,9 +3493,9 @@ __execlists_context_pin(struct intel_context *ce,
 	return 0;
 }
 
-static int execlists_context_pin(struct intel_context *ce)
+static int execlists_context_pin(struct intel_context *ce, void *vaddr)
 {
-	return __execlists_context_pin(ce, ce->engine);
+	return __execlists_context_pin(ce, ce->engine, vaddr);
 }
 
 static int execlists_context_alloc(struct intel_context *ce)
@@ -3520,8 +3521,10 @@ static void execlists_context_reset(struct intel_context *ce)
 static const struct intel_context_ops execlists_context_ops = {
 	.alloc = execlists_context_alloc,
 
+	.pre_pin = execlists_context_pre_pin,
 	.pin = execlists_context_pin,
 	.unpin = execlists_context_unpin,
+	.post_unpin = execlists_context_post_unpin,
 
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
@@ -3885,7 +3888,7 @@ static int lrc_setup_wa_ctx(struct intel_engine_cs *engine)
 		goto err;
 	}
 
-	err = i915_ggtt_pin(vma, 0, PIN_HIGH);
+	err = i915_ggtt_pin(vma, NULL, 0, PIN_HIGH);
 	if (err)
 		goto err;
 
@@ -4126,7 +4129,7 @@ static int execlists_resume(struct intel_engine_cs *engine)
 {
 	intel_mocs_init_engine(engine);
 
-	intel_engine_reset_breadcrumbs(engine);
+	intel_breadcrumbs_reset(engine->breadcrumbs);
 
 	if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) {
 		struct drm_printer p = drm_debug_printer(__func__);
@@ -4555,7 +4558,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_REVID(request->engine->i915, 0, KBL_REVID_B0))
+		if (IS_KBL_GT_REVID(request->engine->i915, 0, KBL_REVID_B0))
 			dc_flush_wa = true;
 	}
 
@@ -4757,14 +4760,21 @@ static int gen12_emit_flush(struct i915_request *request, u32 mode)
 	intel_engine_mask_t aux_inv = 0;
 	u32 cmd, *cs;
 
+	cmd = 4;
+	if (mode & EMIT_INVALIDATE)
+		cmd += 2;
 	if (mode & EMIT_INVALIDATE)
 		aux_inv = request->engine->mask & ~BIT(BCS0);
+	if (aux_inv)
+		cmd += 2 * hweight8(aux_inv) + 2;
 
-	cs = intel_ring_begin(request,
-			      4 + (aux_inv ? 2 * hweight8(aux_inv) + 2 : 0));
+	cs = intel_ring_begin(request, cmd);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
+	if (mode & EMIT_INVALIDATE)
+		*cs++ = preparser_disable(true);
+
 	cmd = MI_FLUSH_DW + 1;
 
 	/* We always require a command barrier so that subsequent
@@ -4797,6 +4807,10 @@ static int gen12_emit_flush(struct i915_request *request, u32 mode)
 		}
 		*cs++ = MI_NOOP;
 	}
+
+	if (mode & EMIT_INVALIDATE)
+		*cs++ = preparser_disable(false);
+
 	intel_ring_advance(request, cs);
 
 	return 0;
@@ -5295,6 +5309,14 @@ populate_lr_context(struct intel_context *ce,
 	return 0;
 }
 
+static struct intel_timeline *pinned_timeline(struct intel_context *ce)
+{
+	struct intel_timeline *tl = fetch_and_zero(&ce->timeline);
+
+	return intel_timeline_create_from_engine(ce->engine,
+						 page_unmask_bits(tl));
+}
+
 static int __execlists_context_alloc(struct intel_context *ce,
 				     struct intel_engine_cs *engine)
 {
@@ -5325,19 +5347,17 @@ static int __execlists_context_alloc(struct intel_context *ce,
 		goto error_deref_obj;
 	}
 
-	if (!ce->timeline) {
+	if (!page_mask_bits(ce->timeline)) {
 		struct intel_timeline *tl;
-		struct i915_vma *hwsp;
 
 		/*
 		 * Use the static global HWSP for the kernel context, and
 		 * a dynamically allocated cacheline for everyone else.
 		 */
-		hwsp = NULL;
-		if (unlikely(intel_context_is_barrier(ce)))
-			hwsp = engine->status_page.vma;
-
-		tl = intel_timeline_create(engine->gt, hwsp);
+		if (unlikely(ce->timeline))
+			tl = pinned_timeline(ce);
+		else
+			tl = intel_timeline_create(engine->gt);
 		if (IS_ERR(tl)) {
 			ret = PTR_ERR(tl);
 			goto error_deref_obj;
@@ -5443,12 +5463,12 @@ static int virtual_context_alloc(struct intel_context *ce)
 	return __execlists_context_alloc(ce, ve->siblings[0]);
 }
 
-static int virtual_context_pin(struct intel_context *ce)
+static int virtual_context_pin(struct intel_context *ce, void *vaddr)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
 
 	/* Note: we must use a real engine class for setting up reg state */
-	return __execlists_context_pin(ce, ve->siblings[0]);
+	return __execlists_context_pin(ce, ve->siblings[0], vaddr);
 }
 
 static void virtual_context_enter(struct intel_context *ce)
@@ -5476,8 +5496,10 @@ static void virtual_context_exit(struct intel_context *ce)
 static const struct intel_context_ops virtual_context_ops = {
 	.alloc = virtual_context_alloc,
 
+	.pre_pin = execlists_context_pre_pin,
 	.pin = virtual_context_pin,
 	.unpin = execlists_context_unpin,
+	.post_unpin = execlists_context_post_unpin,
 
 	.enter = virtual_context_enter,
 	.exit = virtual_context_exit,
@@ -5711,9 +5733,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
-	intel_engine_init_breadcrumbs(&ve->base);
 	intel_engine_init_execlists(&ve->base);
-	ve->base.breadcrumbs.irq_armed = true; /* fake HW, used for irq_work */
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
@@ -5730,6 +5750,12 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	intel_context_init(&ve->context, &ve->base);
 
+	ve->base.breadcrumbs = intel_breadcrumbs_create(NULL);
+	if (!ve->base.breadcrumbs) {
+		err = -ENOMEM;
+		goto err_put;
+	}
+
 	for (n = 0; n < count; n++) {
 		struct intel_engine_cs *sibling = siblings[n];
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index f0862e924d11..46d9aceda64c 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -18,7 +18,8 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm)
 	if (unlikely(!pt))
 		return ERR_PTR(-ENOMEM);
 
-	if (unlikely(setup_page_dma(vm, &pt->base))) {
+	pt->base = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	if (IS_ERR(pt->base)) {
 		kfree(pt);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -27,14 +28,20 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm)
 	return pt;
 }
 
-struct i915_page_directory *__alloc_pd(size_t sz)
+struct i915_page_directory *__alloc_pd(int count)
 {
 	struct i915_page_directory *pd;
 
-	pd = kzalloc(sz, I915_GFP_ALLOW_FAIL);
+	pd = kzalloc(sizeof(*pd), I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pd))
 		return NULL;
 
+	pd->entry = kcalloc(count, sizeof(*pd->entry), I915_GFP_ALLOW_FAIL);
+	if (unlikely(!pd->entry)) {
+		kfree(pd);
+		return NULL;
+	}
+
 	spin_lock_init(&pd->lock);
 	return pd;
 }
@@ -43,11 +50,13 @@ struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
 {
 	struct i915_page_directory *pd;
 
-	pd = __alloc_pd(sizeof(*pd));
+	pd = __alloc_pd(I915_PDES);
 	if (unlikely(!pd))
 		return ERR_PTR(-ENOMEM);
 
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
+	pd->pt.base = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	if (IS_ERR(pd->pt.base)) {
+		kfree(pd->entry);
 		kfree(pd);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -55,41 +64,52 @@ struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
 	return pd;
 }
 
-void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd)
+void free_px(struct i915_address_space *vm, struct i915_page_table *pt, int lvl)
 {
-	cleanup_page_dma(vm, pd);
-	kfree(pd);
+	BUILD_BUG_ON(offsetof(struct i915_page_directory, pt));
+
+	if (lvl) {
+		struct i915_page_directory *pd =
+			container_of(pt, typeof(*pd), pt);
+		kfree(pd->entry);
+	}
+
+	if (pt->base)
+		i915_gem_object_put(pt->base);
+
+	kfree(pt);
 }
 
 static inline void
-write_dma_entry(struct i915_page_dma * const pdma,
+write_dma_entry(struct drm_i915_gem_object * const pdma,
 		const unsigned short idx,
 		const u64 encoded_entry)
 {
-	u64 * const vaddr = kmap_atomic(pdma->page);
+	u64 * const vaddr = kmap_atomic(__px_page(pdma));
 
 	vaddr[idx] = encoded_entry;
+	clflush_cache_range(&vaddr[idx], sizeof(u64));
 	kunmap_atomic(vaddr);
 }
 
 void
 __set_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
-	       struct i915_page_dma * const to,
+	       struct i915_page_table * const to,
 	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
 {
 	/* Each thread pre-pins the pd, and we may have a thread per pde. */
-	GEM_BUG_ON(atomic_read(px_used(pd)) > NALLOC * ARRAY_SIZE(pd->entry));
+	GEM_BUG_ON(atomic_read(px_used(pd)) > NALLOC * I915_PDES);
 
 	atomic_inc(px_used(pd));
 	pd->entry[idx] = to;
-	write_dma_entry(px_base(pd), idx, encode(to->daddr, I915_CACHE_LLC));
+	write_dma_entry(px_base(pd), idx, encode(px_dma(to), I915_CACHE_LLC));
 }
 
 void
 clear_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
-	       const struct i915_page_scratch * const scratch)
+	       const struct drm_i915_gem_object * const scratch)
 {
 	GEM_BUG_ON(atomic_read(px_used(pd)) == 0);
 
@@ -102,7 +122,7 @@ bool
 release_pd_entry(struct i915_page_directory * const pd,
 		 const unsigned short idx,
 		 struct i915_page_table * const pt,
-		 const struct i915_page_scratch * const scratch)
+		 const struct drm_i915_gem_object * const scratch)
 {
 	bool free = false;
 
@@ -155,19 +175,16 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt)
 	return ppgtt;
 }
 
-int ppgtt_bind_vma(struct i915_address_space *vm,
-		   struct i915_vma *vma,
-		   enum i915_cache_level cache_level,
-		   u32 flags)
+void ppgtt_bind_vma(struct i915_address_space *vm,
+		    struct i915_vm_pt_stash *stash,
+		    struct i915_vma *vma,
+		    enum i915_cache_level cache_level,
+		    u32 flags)
 {
 	u32 pte_flags;
-	int err;
 
 	if (!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
-		err = vm->allocate_va_range(vm, vma->node.start, vma->size);
-		if (err)
-			return err;
-
+		vm->allocate_va_range(vm, stash, vma->node.start, vma->size);
 		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
 	}
 
@@ -178,8 +195,6 @@ int ppgtt_bind_vma(struct i915_address_space *vm,
 
 	vm->insert_entries(vm, vma, cache_level, pte_flags);
 	wmb();
-
-	return 0;
 }
 
 void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
@@ -188,12 +203,93 @@ void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
 		vm->clear_range(vm, vma->node.start, vma->size);
 }
 
+static unsigned long pd_count(u64 size, int shift)
+{
+	/* Beware later misalignment */
+	return (size + 2 * (BIT_ULL(shift) - 1)) >> shift;
+}
+
+int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash,
+			   u64 size)
+{
+	unsigned long count;
+	int shift, n;
+
+	shift = vm->pd_shift;
+	if (!shift)
+		return 0;
+
+	count = pd_count(size, shift);
+	while (count--) {
+		struct i915_page_table *pt;
+
+		pt = alloc_pt(vm);
+		if (IS_ERR(pt)) {
+			i915_vm_free_pt_stash(vm, stash);
+			return PTR_ERR(pt);
+		}
+
+		pt->stash = stash->pt[0];
+		stash->pt[0] = pt;
+	}
+
+	for (n = 1; n < vm->top; n++) {
+		shift += ilog2(I915_PDES); /* Each PD holds 512 entries */
+		count = pd_count(size, shift);
+		while (count--) {
+			struct i915_page_directory *pd;
+
+			pd = alloc_pd(vm);
+			if (IS_ERR(pd)) {
+				i915_vm_free_pt_stash(vm, stash);
+				return PTR_ERR(pd);
+			}
+
+			pd->pt.stash = stash->pt[1];
+			stash->pt[1] = &pd->pt;
+		}
+	}
+
+	return 0;
+}
+
+int i915_vm_pin_pt_stash(struct i915_address_space *vm,
+			 struct i915_vm_pt_stash *stash)
+{
+	struct i915_page_table *pt;
+	int n, err;
+
+	for (n = 0; n < ARRAY_SIZE(stash->pt); n++) {
+		for (pt = stash->pt[n]; pt; pt = pt->stash) {
+			err = pin_pt_dma(vm, pt->base);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+void i915_vm_free_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash)
+{
+	struct i915_page_table *pt;
+	int n;
+
+	for (n = 0; n < ARRAY_SIZE(stash->pt); n++) {
+		while ((pt = stash->pt[n])) {
+			stash->pt[n] = pt->stash;
+			free_px(vm, pt, n);
+		}
+	}
+}
+
 int ppgtt_set_pages(struct i915_vma *vma)
 {
 	GEM_BUG_ON(vma->pages);
 
 	vma->pages = vma->obj->mm.pages;
-
 	vma->page_sizes = vma->obj->mm.page_sizes;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index 1bfad589c63b..ea2a77c7b469 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -27,6 +27,7 @@
 
 #include "i915_drv.h"
 #include "intel_renderstate.h"
+#include "gt/intel_context.h"
 #include "intel_ring.h"
 
 static const struct intel_renderstate_rodata *
@@ -157,33 +158,47 @@ out:
 #undef OUT_BATCH
 
 int intel_renderstate_init(struct intel_renderstate *so,
-			   struct intel_engine_cs *engine)
+			   struct intel_context *ce)
 {
-	struct drm_i915_gem_object *obj;
+	struct intel_engine_cs *engine = ce->engine;
+	struct drm_i915_gem_object *obj = NULL;
 	int err;
 
 	memset(so, 0, sizeof(*so));
 
 	so->rodata = render_state_get_rodata(engine);
-	if (!so->rodata)
-		return 0;
+	if (so->rodata) {
+		if (so->rodata->batch_items * 4 > PAGE_SIZE)
+			return -EINVAL;
+
+		obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		so->vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
+		if (IS_ERR(so->vma)) {
+			err = PTR_ERR(so->vma);
+			goto err_obj;
+		}
+	}
 
-	if (so->rodata->batch_items * 4 > PAGE_SIZE)
-		return -EINVAL;
+	i915_gem_ww_ctx_init(&so->ww, true);
+retry:
+	err = intel_context_pin_ww(ce, &so->ww);
+	if (err)
+		goto err_fini;
 
-	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+	/* return early if there's nothing to setup */
+	if (!err && !so->rodata)
+		return 0;
 
-	so->vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
-	if (IS_ERR(so->vma)) {
-		err = PTR_ERR(so->vma);
-		goto err_obj;
-	}
+	err = i915_gem_object_lock(so->vma->obj, &so->ww);
+	if (err)
+		goto err_context;
 
 	err = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
-		goto err_obj;
+		goto err_context;
 
 	err = render_state_setup(so, engine->i915);
 	if (err)
@@ -193,8 +208,18 @@ int intel_renderstate_init(struct intel_renderstate *so,
 
 err_unpin:
 	i915_vma_unpin(so->vma);
+err_context:
+	intel_context_unpin(ce);
+err_fini:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&so->ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&so->ww);
 err_obj:
-	i915_gem_object_put(obj);
+	if (obj)
+		i915_gem_object_put(obj);
 	so->vma = NULL;
 	return err;
 }
@@ -208,11 +233,9 @@ int intel_renderstate_emit(struct intel_renderstate *so,
 	if (!so->vma)
 		return 0;
 
-	i915_vma_lock(so->vma);
 	err = i915_request_await_object(rq, so->vma->obj, false);
 	if (err == 0)
 		err = i915_vma_move_to_active(so->vma, rq, 0);
-	i915_vma_unlock(so->vma);
 	if (err)
 		return err;
 
@@ -233,7 +256,17 @@ int intel_renderstate_emit(struct intel_renderstate *so,
 	return 0;
 }
 
-void intel_renderstate_fini(struct intel_renderstate *so)
+void intel_renderstate_fini(struct intel_renderstate *so,
+			    struct intel_context *ce)
 {
-	i915_vma_unpin_and_release(&so->vma, 0);
+	if (so->vma) {
+		i915_vma_unpin(so->vma);
+		i915_vma_close(so->vma);
+	}
+
+	intel_context_unpin(ce);
+	i915_gem_ww_ctx_fini(&so->ww);
+
+	if (so->vma)
+		i915_gem_object_put(so->vma->obj);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.h b/drivers/gpu/drm/i915/gt/intel_renderstate.h
index 5700be69a05a..713aa1e86c80 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.h
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.h
@@ -25,9 +25,10 @@
 #define _INTEL_RENDERSTATE_H_
 
 #include <linux/types.h>
+#include "i915_gem.h"
 
 struct i915_request;
-struct intel_engine_cs;
+struct intel_context;
 struct i915_vma;
 
 struct intel_renderstate_rodata {
@@ -49,6 +50,7 @@ extern const struct intel_renderstate_rodata gen8_null_state;
 extern const struct intel_renderstate_rodata gen9_null_state;
 
 struct intel_renderstate {
+	struct i915_gem_ww_ctx ww;
 	const struct intel_renderstate_rodata *rodata;
 	struct i915_vma *vma;
 	u32 batch_offset;
@@ -58,9 +60,10 @@ struct intel_renderstate {
 };
 
 int intel_renderstate_init(struct intel_renderstate *so,
-			   struct intel_engine_cs *engine);
+			   struct intel_context *ce);
 int intel_renderstate_emit(struct intel_renderstate *so,
 			   struct i915_request *rq);
-void intel_renderstate_fini(struct intel_renderstate *so);
+void intel_renderstate_fini(struct intel_renderstate *so,
+			    struct intel_context *ce);
 
 #endif /* _INTEL_RENDERSTATE_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 46a5ceffc22f..ac36b67fb46b 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -15,6 +15,7 @@
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
 #include "i915_irq.h"
+#include "intel_breadcrumbs.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index bdb324167ef3..4034a4bac7f0 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -21,7 +21,13 @@ unsigned int intel_ring_update_space(struct intel_ring *ring)
 	return space;
 }
 
-int intel_ring_pin(struct intel_ring *ring)
+void __intel_ring_pin(struct intel_ring *ring)
+{
+	GEM_BUG_ON(!atomic_read(&ring->pin_count));
+	atomic_inc(&ring->pin_count);
+}
+
+int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww)
 {
 	struct i915_vma *vma = ring->vma;
 	unsigned int flags;
@@ -39,7 +45,7 @@ int intel_ring_pin(struct intel_ring *ring)
 	else
 		flags |= PIN_HIGH;
 
-	ret = i915_ggtt_pin(vma, 0, flags);
+	ret = i915_ggtt_pin(vma, ww, 0, flags);
 	if (unlikely(ret))
 		goto err_unpin;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index cc0ebca65167..1700579bdc93 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -21,7 +21,8 @@ int intel_ring_cacheline_align(struct i915_request *rq);
 
 unsigned int intel_ring_update_space(struct intel_ring *ring);
 
-int intel_ring_pin(struct intel_ring *ring);
+void __intel_ring_pin(struct intel_ring *ring);
+int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww);
 void intel_ring_unpin(struct intel_ring *ring);
 void intel_ring_reset(struct intel_ring *ring, u32 tail);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 94915f668715..16b48e72c369 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -32,6 +32,7 @@
 #include "gen6_ppgtt.h"
 #include "gen7_renderclear.h"
 #include "i915_drv.h"
+#include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_gt.h"
 #include "intel_reset.h"
@@ -100,7 +101,7 @@ static void set_hwsp(struct intel_engine_cs *engine, u32 offset)
 		 */
 		default:
 			GEM_BUG_ON(engine->id);
-			/* fallthrough */
+			fallthrough;
 		case RCS0:
 			hwsp = RENDER_HWS_PGA_GEN7;
 			break;
@@ -201,16 +202,18 @@ static struct i915_address_space *vm_alias(struct i915_address_space *vm)
 	return vm;
 }
 
+static u32 pp_dir(struct i915_address_space *vm)
+{
+	return to_gen6_ppgtt(i915_vm_to_ppgtt(vm))->pp_dir;
+}
+
 static void set_pp_dir(struct intel_engine_cs *engine)
 {
 	struct i915_address_space *vm = vm_alias(engine->gt->vm);
 
 	if (vm) {
-		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-
 		ENGINE_WRITE(engine, RING_PP_DIR_DCLV, PP_DIR_DCLV_2G);
-		ENGINE_WRITE(engine, RING_PP_DIR_BASE,
-			     px_base(ppgtt->pd)->ggtt_offset << 10);
+		ENGINE_WRITE(engine, RING_PP_DIR_BASE, pp_dir(vm));
 	}
 }
 
@@ -255,7 +258,7 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	else
 		ring_setup_status_page(engine);
 
-	intel_engine_reset_breadcrumbs(engine);
+	intel_breadcrumbs_reset(engine->breadcrumbs);
 
 	/* Enforce ordering by reading HEAD register back */
 	ENGINE_POSTING_READ(engine, RING_HEAD);
@@ -474,14 +477,16 @@ static void ring_context_destroy(struct kref *ref)
 	intel_context_free(ce);
 }
 
-static int __context_pin_ppgtt(struct intel_context *ce)
+static int ring_context_pre_pin(struct intel_context *ce,
+				struct i915_gem_ww_ctx *ww,
+				void **unused)
 {
 	struct i915_address_space *vm;
 	int err = 0;
 
 	vm = vm_alias(ce->vm);
 	if (vm)
-		err = gen6_ppgtt_pin(i915_vm_to_ppgtt((vm)));
+		err = gen6_ppgtt_pin(i915_vm_to_ppgtt((vm)), ww);
 
 	return err;
 }
@@ -497,6 +502,10 @@ static void __context_unpin_ppgtt(struct intel_context *ce)
 
 static void ring_context_unpin(struct intel_context *ce)
 {
+}
+
+static void ring_context_post_unpin(struct intel_context *ce)
+{
 	__context_unpin_ppgtt(ce);
 }
 
@@ -584,9 +593,9 @@ static int ring_context_alloc(struct intel_context *ce)
 	return 0;
 }
 
-static int ring_context_pin(struct intel_context *ce)
+static int ring_context_pin(struct intel_context *ce, void *unused)
 {
-	return __context_pin_ppgtt(ce);
+	return 0;
 }
 
 static void ring_context_reset(struct intel_context *ce)
@@ -597,8 +606,10 @@ static void ring_context_reset(struct intel_context *ce)
 static const struct intel_context_ops ring_context_ops = {
 	.alloc = ring_context_alloc,
 
+	.pre_pin = ring_context_pre_pin,
 	.pin = ring_context_pin,
 	.unpin = ring_context_unpin,
+	.post_unpin = ring_context_post_unpin,
 
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
@@ -608,7 +619,7 @@ static const struct intel_context_ops ring_context_ops = {
 };
 
 static int load_pd_dir(struct i915_request *rq,
-		       const struct i915_ppgtt *ppgtt,
+		       struct i915_address_space *vm,
 		       u32 valid)
 {
 	const struct intel_engine_cs * const engine = rq->engine;
@@ -624,7 +635,7 @@ static int load_pd_dir(struct i915_request *rq,
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
-	*cs++ = px_base(ppgtt->pd)->ggtt_offset << 10;
+	*cs++ = pp_dir(vm);
 
 	/* Stall until the page table load is complete? */
 	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
@@ -826,7 +837,7 @@ static int switch_mm(struct i915_request *rq, struct i915_address_space *vm)
 	 * post-sync op, this extra pass appears vital before a
 	 * mm switch!
 	 */
-	ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm), PP_DIR_DCLV_2G);
+	ret = load_pd_dir(rq, vm, PP_DIR_DCLV_2G);
 	if (ret)
 		return ret;
 
@@ -1250,14 +1261,15 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 		return -ENODEV;
 	}
 
-	timeline = intel_timeline_create(engine->gt, engine->status_page.vma);
+	timeline = intel_timeline_create_from_engine(engine,
+						     I915_GEM_HWS_SEQNO_ADDR);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
 		goto err;
 	}
 	GEM_BUG_ON(timeline->has_initial_breadcrumb);
 
-	err = intel_timeline_pin(timeline);
+	err = intel_timeline_pin(timeline, NULL);
 	if (err)
 		goto err_timeline;
 
@@ -1267,7 +1279,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 		goto err_timeline_unpin;
 	}
 
-	err = intel_ring_pin(ring);
+	err = intel_ring_pin(ring, NULL);
 	if (err)
 		goto err_ring;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 97ba14ad52e4..e6a00eea0631 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -7,6 +7,7 @@
 #include <drm/i915_drm.h>
 
 #include "i915_drv.h"
+#include "intel_breadcrumbs.h"
 #include "intel_gt.h"
 #include "intel_gt_clock_utils.h"
 #include "intel_gt_irq.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 46d20f5f3ddc..a2f74cefe4c3 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -215,7 +215,8 @@ static void cacheline_free(struct intel_timeline_cacheline *cl)
 
 static int intel_timeline_init(struct intel_timeline *timeline,
 			       struct intel_gt *gt,
-			       struct i915_vma *hwsp)
+			       struct i915_vma *hwsp,
+			       unsigned int offset)
 {
 	void *vaddr;
 
@@ -246,8 +247,7 @@ static int intel_timeline_init(struct intel_timeline *timeline,
 
 		vaddr = page_mask_bits(cl->vaddr);
 	} else {
-		timeline->hwsp_offset = I915_GEM_HWS_SEQNO_ADDR;
-
+		timeline->hwsp_offset = offset;
 		vaddr = i915_gem_object_pin_map(hwsp->obj, I915_MAP_WB);
 		if (IS_ERR(vaddr))
 			return PTR_ERR(vaddr);
@@ -297,7 +297,9 @@ static void intel_timeline_fini(struct intel_timeline *timeline)
 }
 
 struct intel_timeline *
-intel_timeline_create(struct intel_gt *gt, struct i915_vma *global_hwsp)
+__intel_timeline_create(struct intel_gt *gt,
+			struct i915_vma *global_hwsp,
+			unsigned int offset)
 {
 	struct intel_timeline *timeline;
 	int err;
@@ -306,7 +308,7 @@ intel_timeline_create(struct intel_gt *gt, struct i915_vma *global_hwsp)
 	if (!timeline)
 		return ERR_PTR(-ENOMEM);
 
-	err = intel_timeline_init(timeline, gt, global_hwsp);
+	err = intel_timeline_init(timeline, gt, global_hwsp, offset);
 	if (err) {
 		kfree(timeline);
 		return ERR_PTR(err);
@@ -315,14 +317,20 @@ intel_timeline_create(struct intel_gt *gt, struct i915_vma *global_hwsp)
 	return timeline;
 }
 
-int intel_timeline_pin(struct intel_timeline *tl)
+void __intel_timeline_pin(struct intel_timeline *tl)
+{
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
+	atomic_inc(&tl->pin_count);
+}
+
+int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww)
 {
 	int err;
 
 	if (atomic_add_unless(&tl->pin_count, 1, 0))
 		return 0;
 
-	err = i915_ggtt_pin(tl->hwsp_ggtt, 0, PIN_HIGH);
+	err = i915_ggtt_pin(tl->hwsp_ggtt, ww, 0, PIN_HIGH);
 	if (err)
 		return err;
 
@@ -465,7 +473,7 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 		goto err_rollback;
 	}
 
-	err = i915_ggtt_pin(vma, 0, PIN_HIGH);
+	err = i915_ggtt_pin(vma, NULL, 0, PIN_HIGH);
 	if (err) {
 		__idle_hwsp_free(vma->private, cacheline);
 		goto err_rollback;
@@ -484,7 +492,9 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 	 * free it after the current request is retired, which ensures that
 	 * all writes into the cacheline from previous requests are complete.
 	 */
-	err = i915_active_ref(&tl->hwsp_cacheline->active, tl, &rq->fence);
+	err = i915_active_ref(&tl->hwsp_cacheline->active,
+			      tl->fence_context,
+			      &rq->fence);
 	if (err)
 		goto err_cacheline;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index 4298b9ac7327..9882cd911d8e 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -29,10 +29,27 @@
 
 #include "i915_active.h"
 #include "i915_syncmap.h"
-#include "gt/intel_timeline_types.h"
+#include "intel_timeline_types.h"
 
 struct intel_timeline *
-intel_timeline_create(struct intel_gt *gt, struct i915_vma *global_hwsp);
+__intel_timeline_create(struct intel_gt *gt,
+			struct i915_vma *global_hwsp,
+			unsigned int offset);
+
+static inline struct intel_timeline *
+intel_timeline_create(struct intel_gt *gt)
+{
+	return __intel_timeline_create(gt, NULL, 0);
+}
+
+static inline struct intel_timeline *
+intel_timeline_create_from_engine(struct intel_engine_cs *engine,
+				  unsigned int offset)
+{
+	return __intel_timeline_create(engine->gt,
+				       engine->status_page.vma,
+				       offset);
+}
 
 static inline struct intel_timeline *
 intel_timeline_get(struct intel_timeline *timeline)
@@ -71,7 +88,8 @@ static inline bool intel_timeline_sync_is_later(struct intel_timeline *tl,
 	return __intel_timeline_sync_is_later(tl, fence->context, fence->seqno);
 }
 
-int intel_timeline_pin(struct intel_timeline *tl);
+void __intel_timeline_pin(struct intel_timeline *tl);
+int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww);
 void intel_timeline_enter(struct intel_timeline *tl);
 int intel_timeline_get_seqno(struct intel_timeline *tl,
 			     struct i915_request *rq,
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5726cd0a37e0..a3f72b75c61e 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -52,6 +52,24 @@
  * - Public functions to init or apply the given workaround type.
  */
 
+/*
+ * KBL revision ID ordering is bizarre; higher revision ID's map to lower
+ * steppings in some cases.  So rather than test against the revision ID
+ * directly, let's map that into our own range of increasing ID's that we
+ * can test against in a regular manner.
+ */
+
+const struct i915_rev_steppings kbl_revids[] = {
+	[0] = { .gt_stepping = KBL_REVID_A0, .disp_stepping = KBL_REVID_A0 },
+	[1] = { .gt_stepping = KBL_REVID_B0, .disp_stepping = KBL_REVID_B0 },
+	[2] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B0 },
+	[3] = { .gt_stepping = KBL_REVID_D0, .disp_stepping = KBL_REVID_B0 },
+	[4] = { .gt_stepping = KBL_REVID_F0, .disp_stepping = KBL_REVID_C0 },
+	[5] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B1 },
+	[6] = { .gt_stepping = KBL_REVID_D1, .disp_stepping = KBL_REVID_B1 },
+	[7] = { .gt_stepping = KBL_REVID_G0, .disp_stepping = KBL_REVID_C0 },
+};
+
 static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name)
 {
 	wal->name = name;
@@ -470,7 +488,7 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen9_ctx_workarounds_init(engine, wal);
 
 	/* WaToEnableHwFixForPushConstHWBug:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
@@ -596,8 +614,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
-static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
-				     struct i915_wa_list *wal)
+static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
+				       struct i915_wa_list *wal)
 {
 	/*
 	 * Wa_1409142259:tgl
@@ -607,12 +625,28 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 * Wa_1409207793:tgl
 	 * Wa_1409178076:tgl
 	 * Wa_1408979724:tgl
+	 * Wa_14010443199:rkl
+	 * Wa_14010698770:rkl
 	 */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
+	/* WaDisableGPGPUMidThreadPreemption:gen12 */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
+}
+
+static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	gen12_ctx_workarounds_init(engine, wal);
+
 	/*
-	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * Wa_1604555607:tgl,rkl
+	 *
+	 * Note that the implementation of this workaround is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
 	 * FF_MODE2 register will return the wrong value when read. The default
 	 * value for this register is zero for all fields and there are no bit
 	 * masks. So instead of doing a RMW we should just write the GS Timer
@@ -623,11 +657,6 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
 	       0);
-
-	/* WaDisableGPGPUMidThreadPreemption:tgl */
-	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
-			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 }
 
 static void
@@ -642,8 +671,10 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 
 	wa_init_start(wal, name, engine->name);
 
-	if (IS_GEN(i915, 12))
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915))
 		tgl_ctx_workarounds_init(engine, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_ctx_workarounds_init(engine, wal);
 	else if (IS_GEN(i915, 11))
 		icl_ctx_workarounds_init(engine, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -995,7 +1026,7 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen9_gt_workarounds_init(i915, wal);
 
 	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_REVID(i915, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(i915, 0, KBL_REVID_B0))
 		wa_write_or(wal,
 			    GAMT_CHKN_BIT_REG,
 			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
@@ -1176,9 +1207,16 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 }
 
 static void
-tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+gen12_gt_workarounds_init(struct drm_i915_private *i915,
+			  struct i915_wa_list *wal)
 {
 	wa_init_mcr(i915, wal);
+}
+
+static void
+tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1409420604:tgl */
 	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
@@ -1196,8 +1234,10 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 static void
 gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
-	if (IS_GEN(i915, 12))
+	if (IS_TIGERLAKE(i915))
 		tgl_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_gt_workarounds_init(i915, wal);
 	else if (IS_GEN(i915, 11))
 		icl_gt_workarounds_init(i915, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -1630,18 +1670,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 
 		/*
-		 * Wa_1607030317:tgl
-		 * Wa_1607186500:tgl
-		 * Wa_1607297627:tgl there is 3 entries for this WA on BSpec, 2
-		 * of then says it is fixed on B0 the other one says it is
-		 * permanent
-		 */
-		wa_masked_en(wal,
-			     GEN6_RC_SLEEP_PSMI_CONTROL,
-			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
-			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
-
-		/*
 		 * Wa_1606679103:tgl
 		 * (see also Wa_1606682166:icl)
 		 */
@@ -1654,22 +1682,17 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    VSUNIT_CLKGATE_DIS_TGL);
 	}
 
-	if (IS_TIGERLAKE(i915)) {
-		/* Wa_1606931601:tgl */
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+		/* Wa_1606931601:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
 
-		/* Wa_1409804808:tgl */
+		/* Wa_1409804808:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
 			     GEN12_PUSH_CONST_DEREF_HOLD_DIS);
 
-		/* Wa_1606700617:tgl */
-		wa_masked_en(wal,
-			     GEN9_CS_DEBUG_MODE1,
-			     FF_DOP_CLOCK_GATE_DISABLE);
-
 		/*
 		 * Wa_1409085225:tgl
-		 * Wa_14010229206:tgl
+		 * Wa_14010229206:tgl,rkl
 		 */
 		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 
@@ -1677,9 +1700,29 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1407928979:tgl A*
 		 * Wa_18011464164:tgl B0+
 		 * Wa_22010931296:tgl B0+
+		 * Wa_14010919138:rkl
 		 */
 		wa_write_or(wal, GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
+
+		/*
+		 * Wa_1607030317:tgl
+		 * Wa_1607186500:tgl
+		 * Wa_1607297627:tgl,rkl there are multiple entries for this
+		 * WA in the BSpec; some indicate this is an A0-only WA,
+		 * others indicate it applies to all steppings.
+		 */
+		wa_masked_en(wal,
+			     GEN6_RC_SLEEP_PSMI_CONTROL,
+			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
+			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
+	}
+
+	if (IS_TIGERLAKE(i915)) {
+		/* Wa_1606700617:tgl */
+		wa_masked_en(wal,
+			     GEN9_CS_DEBUG_MODE1,
+			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
 	if (IS_GEN(i915, 11)) {
@@ -1898,7 +1941,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	struct drm_i915_private *i915 = engine->i915;
 
 	/* WaKBLVECSSemaphoreWaitPoll:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
 		wa_write(wal,
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);
@@ -2045,6 +2088,7 @@ static int engine_wa_list_verify(struct intel_context *ce,
 	const struct i915_wa *wa;
 	struct i915_request *rq;
 	struct i915_vma *vma;
+	struct i915_gem_ww_ctx ww;
 	unsigned int i;
 	u32 *results;
 	int err;
@@ -2057,29 +2101,34 @@ static int engine_wa_list_verify(struct intel_context *ce,
 		return PTR_ERR(vma);
 
 	intel_engine_pm_get(ce->engine);
-	rq = intel_context_create_request(ce);
-	intel_engine_pm_put(ce->engine);
+	i915_gem_ww_ctx_init(&ww, false);
+retry:
+	err = i915_gem_object_lock(vma->obj, &ww);
+	if (err == 0)
+		err = intel_context_pin_ww(ce, &ww);
+	if (err)
+		goto err_pm;
+
+	rq = i915_request_create(ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
-		goto err_vma;
+		goto err_unpin;
 	}
 
-	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, true);
 	if (err == 0)
 		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	i915_vma_unlock(vma);
-	if (err) {
-		i915_request_add(rq);
-		goto err_vma;
-	}
-
-	err = wa_list_srm(rq, wal, vma);
-	if (err)
-		goto err_vma;
+	if (err == 0)
+		err = wa_list_srm(rq, wal, vma);
 
 	i915_request_get(rq);
+	if (err)
+		i915_request_set_error_once(rq, err);
 	i915_request_add(rq);
+
+	if (err)
+		goto err_rq;
+
 	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 		err = -ETIME;
 		goto err_rq;
@@ -2104,7 +2153,16 @@ static int engine_wa_list_verify(struct intel_context *ce,
 
 err_rq:
 	i915_request_put(rq);
-err_vma:
+err_unpin:
+	intel_context_unpin(ce);
+err_pm:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	intel_engine_pm_put(ce->engine);
 	i915_vma_unpin(vma);
 	i915_vma_put(vma);
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index b8dd3cbc8696..dfd1cfb8a7ec 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -131,6 +131,10 @@ static void mock_context_unpin(struct intel_context *ce)
 {
 }
 
+static void mock_context_post_unpin(struct intel_context *ce)
+{
+}
+
 static void mock_context_destroy(struct kref *ref)
 {
 	struct intel_context *ce = container_of(ref, typeof(*ce), ref);
@@ -152,8 +156,7 @@ static int mock_context_alloc(struct intel_context *ce)
 	if (!ce->ring)
 		return -ENOMEM;
 
-	GEM_BUG_ON(ce->timeline);
-	ce->timeline = intel_timeline_create(ce->engine->gt, NULL);
+	ce->timeline = intel_timeline_create(ce->engine->gt);
 	if (IS_ERR(ce->timeline)) {
 		kfree(ce->engine);
 		return PTR_ERR(ce->timeline);
@@ -164,7 +167,13 @@ static int mock_context_alloc(struct intel_context *ce)
 	return 0;
 }
 
-static int mock_context_pin(struct intel_context *ce)
+static int mock_context_pre_pin(struct intel_context *ce,
+				struct i915_gem_ww_ctx *ww, void **unused)
+{
+	return 0;
+}
+
+static int mock_context_pin(struct intel_context *ce, void *unused)
 {
 	return 0;
 }
@@ -176,8 +185,10 @@ static void mock_context_reset(struct intel_context *ce)
 static const struct intel_context_ops mock_context_ops = {
 	.alloc = mock_context_alloc,
 
+	.pre_pin = mock_context_pre_pin,
 	.pin = mock_context_pin,
 	.unpin = mock_context_unpin,
+	.post_unpin = mock_context_post_unpin,
 
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
@@ -261,11 +272,12 @@ static void mock_engine_release(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
+	intel_breadcrumbs_free(engine->breadcrumbs);
+
 	intel_context_unpin(engine->kernel_context);
 	intel_context_put(engine->kernel_context);
 
 	intel_engine_fini_retire(engine);
-	intel_engine_fini_breadcrumbs(engine);
 }
 
 struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
@@ -323,20 +335,26 @@ int mock_engine_init(struct intel_engine_cs *engine)
 	struct intel_context *ce;
 
 	intel_engine_init_active(engine, ENGINE_MOCK);
-	intel_engine_init_breadcrumbs(engine);
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
 
+	engine->breadcrumbs = intel_breadcrumbs_create(NULL);
+	if (!engine->breadcrumbs)
+		return -ENOMEM;
+
 	ce = create_kernel_context(engine);
 	if (IS_ERR(ce))
 		goto err_breadcrumbs;
 
+	/* We insist the kernel context is using the status_page */
+	engine->status_page.vma = ce->timeline->hwsp_ggtt;
+
 	engine->kernel_context = ce;
 	return 0;
 
 err_breadcrumbs:
-	intel_engine_fini_breadcrumbs(engine);
+	intel_breadcrumbs_free(engine->breadcrumbs);
 	return -ENOMEM;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 52af1cee9a94..1f4020e906a8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -68,6 +68,8 @@ static int context_sync(struct intel_context *ce)
 	} while (!err);
 	mutex_unlock(&tl->mutex);
 
+	/* Wait for all barriers to complete (remote CPU) before we check */
+	i915_active_unlock_wait(&ce->active);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index 73243ba59c7d..e73854dd2fe0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -47,7 +47,10 @@ static int pulse_active(struct i915_active *active)
 
 static void pulse_free(struct kref *kref)
 {
-	kfree(container_of(kref, struct pulse, kref));
+	struct pulse *p = container_of(kref, typeof(*p), kref);
+
+	i915_active_fini(&p->active);
+	kfree(p);
 }
 
 static void pulse_put(struct pulse *p)
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 3fc5de961280..95d41c01d0e0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -2729,7 +2729,7 @@ static int create_gang(struct intel_engine_cs *engine,
 	i915_gem_object_put(obj);
 	intel_context_put(ce);
 
-	rq->client_link.next = &(*prev)->client_link;
+	rq->mock.link.next = &(*prev)->mock.link;
 	*prev = rq;
 	return 0;
 
@@ -2970,8 +2970,7 @@ static int live_preempt_gang(void *arg)
 		}
 
 		while (rq) { /* wait for each rq from highest to lowest prio */
-			struct i915_request *n =
-				list_next_entry(rq, client_link);
+			struct i915_request *n = list_next_entry(rq, mock.link);
 
 			if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
@@ -3090,7 +3089,7 @@ static struct i915_vma *create_global(struct intel_gt *gt, size_t sz)
 		return vma;
 	}
 
-	err = i915_ggtt_pin(vma, 0, 0);
+	err = i915_ggtt_pin(vma, NULL, 0, 0);
 	if (err) {
 		i915_vma_put(vma);
 		return ERR_PTR(err);
@@ -4997,6 +4996,7 @@ static int __live_lrc_state(struct intel_engine_cs *engine,
 {
 	struct intel_context *ce;
 	struct i915_request *rq;
+	struct i915_gem_ww_ctx ww;
 	enum {
 		RING_START_IDX = 0,
 		RING_TAIL_IDX,
@@ -5011,7 +5011,11 @@ static int __live_lrc_state(struct intel_engine_cs *engine,
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	err = intel_context_pin(ce);
+	i915_gem_ww_ctx_init(&ww, false);
+retry:
+	err = i915_gem_object_lock(scratch->obj, &ww);
+	if (!err)
+		err = intel_context_pin_ww(ce, &ww);
 	if (err)
 		goto err_put;
 
@@ -5040,11 +5044,9 @@ static int __live_lrc_state(struct intel_engine_cs *engine,
 	*cs++ = i915_ggtt_offset(scratch) + RING_TAIL_IDX * sizeof(u32);
 	*cs++ = 0;
 
-	i915_vma_lock(scratch);
 	err = i915_request_await_object(rq, scratch->obj, true);
 	if (!err)
 		err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE);
-	i915_vma_unlock(scratch);
 
 	i915_request_get(rq);
 	i915_request_add(rq);
@@ -5081,6 +5083,12 @@ err_rq:
 err_unpin:
 	intel_context_unpin(ce);
 err_put:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
 	intel_context_put(ce);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 8624f5d2a1f3..3540ba9bd459 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -77,20 +77,20 @@ create_spin_counter(struct intel_engine_cs *engine,
 
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
-		i915_gem_object_put(obj);
-		return vma;
+		err = PTR_ERR(vma);
+		goto err_put;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err) {
-		i915_vma_put(vma);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err_unlock;
+
+	i915_vma_lock(vma);
 
 	base = i915_gem_object_pin_map(obj, I915_MAP_WC);
 	if (IS_ERR(base)) {
-		i915_gem_object_put(obj);
-		return ERR_CAST(base);
+		err = PTR_ERR(base);
+		goto err_unpin;
 	}
 	cs = base;
 
@@ -134,6 +134,14 @@ create_spin_counter(struct intel_engine_cs *engine,
 	*cancel = base + loop;
 	*counter = srm ? memset32(base + end, 0, 1) : NULL;
 	return vma;
+
+err_unpin:
+	i915_vma_unpin(vma);
+err_unlock:
+	i915_vma_unlock(vma);
+err_put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
 }
 
 static u8 wait_for_freq(struct intel_rps *rps, u8 freq, int timeout_ms)
@@ -639,7 +647,6 @@ int live_rps_frequency_cs(void *arg)
 			goto err_vma;
 		}
 
-		i915_vma_lock(vma);
 		err = i915_request_await_object(rq, vma->obj, false);
 		if (!err)
 			err = i915_vma_move_to_active(vma, rq, 0);
@@ -647,7 +654,6 @@ int live_rps_frequency_cs(void *arg)
 			err = rq->engine->emit_bb_start(rq,
 							vma->node.start,
 							PAGE_SIZE, 0);
-		i915_vma_unlock(vma);
 		i915_request_add(rq);
 		if (err)
 			goto err_vma;
@@ -700,7 +706,7 @@ int live_rps_frequency_cs(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
@@ -708,6 +714,7 @@ err_vma:
 		i915_gem_object_flush_map(vma->obj);
 		i915_gem_object_unpin_map(vma->obj);
 		i915_vma_unpin(vma);
+		i915_vma_unlock(vma);
 		i915_vma_put(vma);
 
 		st_engine_heartbeat_enable(engine);
@@ -781,7 +788,6 @@ int live_rps_frequency_srm(void *arg)
 			goto err_vma;
 		}
 
-		i915_vma_lock(vma);
 		err = i915_request_await_object(rq, vma->obj, false);
 		if (!err)
 			err = i915_vma_move_to_active(vma, rq, 0);
@@ -789,7 +795,6 @@ int live_rps_frequency_srm(void *arg)
 			err = rq->engine->emit_bb_start(rq,
 							vma->node.start,
 							PAGE_SIZE, 0);
-		i915_vma_unlock(vma);
 		i915_request_add(rq);
 		if (err)
 			goto err_vma;
@@ -841,7 +846,7 @@ int live_rps_frequency_srm(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
@@ -849,6 +854,7 @@ err_vma:
 		i915_gem_object_flush_map(vma->obj);
 		i915_gem_object_unpin_map(vma->obj);
 		i915_vma_unpin(vma);
+		i915_vma_unlock(vma);
 		i915_vma_put(vma);
 
 		st_engine_heartbeat_enable(engine);
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index fb5b7d3498a6..96d164a3841d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -72,7 +72,7 @@ static int __mock_hwsp_timeline(struct mock_hwsp_freelist *state,
 		unsigned long cacheline;
 		int err;
 
-		tl = intel_timeline_create(state->gt, NULL);
+		tl = intel_timeline_create(state->gt);
 		if (IS_ERR(tl))
 			return PTR_ERR(tl);
 
@@ -455,7 +455,7 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 	struct i915_request *rq;
 	int err;
 
-	err = intel_timeline_pin(tl);
+	err = intel_timeline_pin(tl, NULL);
 	if (err) {
 		rq = ERR_PTR(err);
 		goto out;
@@ -487,11 +487,11 @@ checked_intel_timeline_create(struct intel_gt *gt)
 {
 	struct intel_timeline *tl;
 
-	tl = intel_timeline_create(gt, NULL);
+	tl = intel_timeline_create(gt);
 	if (IS_ERR(tl))
 		return tl;
 
-	if (*tl->hwsp_seqno != tl->seqno) {
+	if (READ_ONCE(*tl->hwsp_seqno) != tl->seqno) {
 		pr_err("Timeline created with incorrect breadcrumb, found %x, expected %x\n",
 		       *tl->hwsp_seqno, tl->seqno);
 		intel_timeline_put(tl);
@@ -561,9 +561,9 @@ static int live_hwsp_engine(void *arg)
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -633,9 +633,9 @@ out:
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -660,14 +660,14 @@ static int live_hwsp_wrap(void *arg)
 	 * foreign GPU references.
 	 */
 
-	tl = intel_timeline_create(gt, NULL);
+	tl = intel_timeline_create(gt);
 	if (IS_ERR(tl))
 		return PTR_ERR(tl);
 
 	if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline)
 		goto out_free;
 
-	err = intel_timeline_pin(tl);
+	err = intel_timeline_pin(tl, NULL);
 	if (err)
 		goto out_free;
 
@@ -733,7 +733,8 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 
-		if (*hwsp_seqno[0] != seqno[0] || *hwsp_seqno[1] != seqno[1]) {
+		if (READ_ONCE(*hwsp_seqno[0]) != seqno[0] ||
+		    READ_ONCE(*hwsp_seqno[1]) != seqno[1]) {
 			pr_err("Bad timeline values: found (%x, %x), expected (%x, %x)\n",
 			       *hwsp_seqno[0], *hwsp_seqno[1],
 			       seqno[0], seqno[1]);
@@ -966,9 +967,10 @@ static int live_hwsp_recycle(void *arg)
 				break;
 			}
 
-			if (*tl->hwsp_seqno != count) {
-				pr_err("Invalid seqno stored in timeline %lu @ tl->hwsp_offset, found 0x%x\n",
-				       count, *tl->hwsp_seqno);
+			if (READ_ONCE(*tl->hwsp_seqno) != count) {
+				GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x found 0x%x\n",
+					      count, tl->fence_context,
+					      tl->hwsp_offset, *tl->hwsp_seqno);
 				GEM_TRACE_DUMP();
 				err = -EINVAL;
 			}
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index febc9e6692ba..61a0532d0f3d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -214,7 +214,7 @@ static int check_whitelist(struct i915_gem_context *ctx,
 		return PTR_ERR(results);
 
 	err = 0;
-	i915_gem_object_lock(results);
+	i915_gem_object_lock(results, NULL);
 	intel_wedge_on_timeout(&wedge, engine->gt, HZ / 5) /* safety net! */
 		err = i915_gem_object_set_to_cpu_domain(results, false);
 	i915_gem_object_unlock(results);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 861657897c0f..942c7c187adb 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -677,7 +677,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 		goto err;
 
 	flags = PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
-	ret = i915_ggtt_pin(vma, 0, flags);
+	ret = i915_ggtt_pin(vma, NULL, 0, flags);
 	if (ret) {
 		vma = ERR_PTR(ret);
 		goto err;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 59b27aba15c6..80e8b6c3bc8c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -51,8 +51,8 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * Note that RKL uses the same firmware as TGL.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
-	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
+	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
+	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  9, 0, 0)) \
 	fw_def(COMETLAKE,   5, guc_def(cml, 33, 0, 0), huc_def(cml,  4, 0, 0)) \
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 072725a448db..ad86c5eb5bba 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -70,6 +70,7 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off,
 {
 	u8 *cfg_base = vgpu_cfg_space(vgpu);
 	u8 mask, new, old;
+	pci_power_t pwr;
 	int i = 0;
 
 	for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) {
@@ -91,6 +92,15 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off,
 	/* For other configuration space directly copy as it is. */
 	if (i < bytes)
 		memcpy(cfg_base + off + i, src + i, bytes - i);
+
+	if (off == vgpu->cfg_space.pmcsr_off && vgpu->cfg_space.pmcsr_off) {
+		pwr = (pci_power_t __force)(*(u16*)(&vgpu_cfg_space(vgpu)[off])
+			& PCI_PM_CTRL_STATE_MASK);
+		if (pwr == PCI_D3hot)
+			vgpu->d3_entered = true;
+		gvt_dbg_core("vgpu-%d power status changed to %d\n",
+			     vgpu->id, pwr);
+	}
 }
 
 /**
@@ -366,6 +376,7 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
 	struct intel_gvt *gvt = vgpu->gvt;
 	const struct intel_gvt_device_info *info = &gvt->device_info;
 	u16 *gmch_ctl;
+	u8 next;
 
 	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
 	       info->cfg_space_size);
@@ -401,6 +412,19 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
 		pci_resource_len(gvt->gt->i915->drm.pdev, 2);
 
 	memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4);
+
+	/* PM Support */
+	vgpu->cfg_space.pmcsr_off = 0;
+	if (vgpu_cfg_space(vgpu)[PCI_STATUS] & PCI_STATUS_CAP_LIST) {
+		next = vgpu_cfg_space(vgpu)[PCI_CAPABILITY_LIST];
+		do {
+			if (vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_ID] == PCI_CAP_ID_PM) {
+				vgpu->cfg_space.pmcsr_off = next + PCI_PM_CTRL;
+				break;
+			}
+			next = vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_NEXT];
+		} while (next);
+	}
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index f1940939260a..d0a599b51bfe 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1923,6 +1923,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	if (ret)
 		goto err_unmap;
 
+	i915_gem_object_unlock(bb->obj);
 	INIT_LIST_HEAD(&bb->list);
 	list_add(&bb->list, &s->workload->shadow_bb);
 
@@ -2982,7 +2983,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 		goto put_obj;
 	}
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	ret = i915_gem_object_set_to_cpu_domain(obj, false);
 	i915_gem_object_unlock(obj);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 210016192ce7..a3a4305eda01 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2501,7 +2501,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 	return create_scratch_page_tree(vgpu);
 }
 
-static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu)
+void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu)
 {
 	struct list_head *pos, *n;
 	struct intel_vgpu_mm *mm;
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 320b8d6ad92f..52d0d88abd86 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -279,4 +279,6 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu,
 int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu,
 	unsigned int off, void *p_data, unsigned int bytes);
 
+void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu);
+
 #endif /* _GVT_GTT_H_ */
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index a4a6db6b7f90..ff7f2515a6fe 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -106,6 +106,7 @@ struct intel_vgpu_pci_bar {
 struct intel_vgpu_cfg_space {
 	unsigned char virtual_cfg_space[PCI_CFG_SPACE_EXP_SIZE];
 	struct intel_vgpu_pci_bar bar[INTEL_GVT_MAX_BAR_NUM];
+	u32 pmcsr_off;
 };
 
 #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space)
@@ -198,6 +199,8 @@ struct intel_vgpu {
 	struct intel_vgpu_submission submission;
 	struct radix_tree_root page_track_tree;
 	u32 hws_pga[I915_NUM_ENGINES];
+	/* Set on PCI_D3, reset on DMLR, not reflecting the actual PM state */
+	bool d3_entered;
 
 	struct dentry *debugfs;
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 63bba7b4bb2f..05f3bc98d242 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1226,7 +1226,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
 	switch (notification) {
 	case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE:
 		root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY;
-		/* fall through */
+		fallthrough;
 	case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE:
 		mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps);
 		return PTR_ERR_OR_ZERO(mm);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 3c3b9842bbbd..1570eb8aa978 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -403,6 +403,14 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	wa_ctx->indirect_ctx.shadow_va = NULL;
 }
 
+static void set_dma_address(struct i915_page_directory *pd, dma_addr_t addr)
+{
+	struct scatterlist *sg = pd->pt.base->mm.pages->sgl;
+
+	/* This is not a good idea */
+	sg->dma_address = addr;
+}
+
 static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 					  struct intel_context *ce)
 {
@@ -411,7 +419,7 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 	int i = 0;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
-		px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0];
+		set_dma_address(ppgtt->pd, mm->ppgtt_mm.shadow_pdps[0]);
 	} else {
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
 			struct i915_page_directory * const pd =
@@ -421,7 +429,8 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 			   shadow ppgtt. */
 			if (!pd)
 				break;
-			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
+
+			set_dma_address(pd, mm->ppgtt_mm.shadow_pdps[i]);
 		}
 	}
 }
@@ -1240,13 +1249,13 @@ i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s,
 	int i;
 
 	if (i915_vm_is_4lvl(&ppgtt->vm)) {
-		px_dma(ppgtt->pd) = s->i915_context_pml4;
+		set_dma_address(ppgtt->pd, s->i915_context_pml4);
 	} else {
 		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
 			struct i915_page_directory * const pd =
 				i915_pd_entry(ppgtt->pd, i);
 
-			px_dma(pd) = s->i915_context_pdps[i];
+			set_dma_address(pd, s->i915_context_pdps[i]);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 7d361623ff67..8fa9b31a2484 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -257,6 +257,7 @@ void intel_gvt_release_vgpu(struct intel_vgpu *vgpu)
 	intel_gvt_deactivate_vgpu(vgpu);
 
 	mutex_lock(&vgpu->vgpu_lock);
+	vgpu->d3_entered = false;
 	intel_vgpu_clean_workloads(vgpu, ALL_ENGINES);
 	intel_vgpu_dmabuf_cleanup(vgpu);
 	mutex_unlock(&vgpu->vgpu_lock);
@@ -393,6 +394,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL);
 	idr_init(&vgpu->object_idr);
 	intel_vgpu_init_cfg_space(vgpu, param->primary);
+	vgpu->d3_entered = false;
 
 	ret = intel_vgpu_init_mmio(vgpu);
 	if (ret)
@@ -557,10 +559,15 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 	/* full GPU reset or device model level reset */
 	if (engine_mask == ALL_ENGINES || dmlr) {
 		intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
-		intel_vgpu_invalidate_ppgtt(vgpu);
+		if (engine_mask == ALL_ENGINES)
+			intel_vgpu_invalidate_ppgtt(vgpu);
 		/*fence will not be reset during virtual reset */
 		if (dmlr) {
-			intel_vgpu_reset_gtt(vgpu);
+			if(!vgpu->d3_entered) {
+				intel_vgpu_invalidate_ppgtt(vgpu);
+				intel_vgpu_destroy_all_ppgtt_mm(vgpu);
+			}
+			intel_vgpu_reset_ggtt(vgpu, true);
 			intel_vgpu_reset_resource(vgpu);
 		}
 
@@ -572,7 +579,14 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
-			vgpu->pv_notified = false;
+			/*
+			 * PCI_D0 is set before dmlr, so reset d3_entered here
+			 * after done using.
+			 */
+			if(vgpu->d3_entered)
+				vgpu->d3_entered = false;
+			else
+				vgpu->pv_notified = false;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index d960d0be5bd2..b0a6522be3d1 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -28,12 +28,14 @@ static struct i915_global_active {
 } global;
 
 struct active_node {
+	struct rb_node node;
 	struct i915_active_fence base;
 	struct i915_active *ref;
-	struct rb_node node;
 	u64 timeline;
 };
 
+#define fetch_node(x) rb_entry(READ_ONCE(x), typeof(struct active_node), node)
+
 static inline struct active_node *
 node_from_active(struct i915_active_fence *active)
 {
@@ -128,8 +130,8 @@ static inline void debug_active_assert(struct i915_active *ref) { }
 static void
 __active_retire(struct i915_active *ref)
 {
+	struct rb_root root = RB_ROOT;
 	struct active_node *it, *n;
-	struct rb_root root;
 	unsigned long flags;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
@@ -141,9 +143,25 @@ __active_retire(struct i915_active *ref)
 	GEM_BUG_ON(rcu_access_pointer(ref->excl.fence));
 	debug_active_deactivate(ref);
 
-	root = ref->tree;
-	ref->tree = RB_ROOT;
-	ref->cache = NULL;
+	/* Even if we have not used the cache, we may still have a barrier */
+	if (!ref->cache)
+		ref->cache = fetch_node(ref->tree.rb_node);
+
+	/* Keep the MRU cached node for reuse */
+	if (ref->cache) {
+		/* Discard all other nodes in the tree */
+		rb_erase(&ref->cache->node, &ref->tree);
+		root = ref->tree;
+
+		/* Rebuild the tree with only the cached node */
+		rb_link_node(&ref->cache->node, NULL, &ref->tree.rb_node);
+		rb_insert_color(&ref->cache->node, &ref->tree);
+		GEM_BUG_ON(ref->tree.rb_node != &ref->cache->node);
+
+		/* Make the cached node available for reuse with any timeline */
+		if (IS_ENABLED(CONFIG_64BIT))
+			ref->cache->timeline = 0; /* needs cmpxchg(u64) */
+	}
 
 	spin_unlock_irqrestore(&ref->tree_lock, flags);
 
@@ -154,6 +172,7 @@ __active_retire(struct i915_active *ref)
 	/* ... except if you wait on it, you must manage your own references! */
 	wake_up_var(ref);
 
+	/* Finally free the discarded timeline tree  */
 	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
 		GEM_BUG_ON(i915_active_fence_isset(&it->base));
 		kmem_cache_free(global.slab_cache, it);
@@ -216,12 +235,11 @@ excl_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 		active_retire(container_of(cb, struct i915_active, excl.cb));
 }
 
-static struct i915_active_fence *
-active_instance(struct i915_active *ref, struct intel_timeline *tl)
+static struct active_node *__active_lookup(struct i915_active *ref, u64 idx)
 {
-	struct active_node *node, *prealloc;
-	struct rb_node **p, *parent;
-	u64 idx = tl->fence_context;
+	struct active_node *it;
+
+	GEM_BUG_ON(idx == 0); /* 0 is the unordered timeline, rsvd for cache */
 
 	/*
 	 * We track the most recently used timeline to skip a rbtree search
@@ -230,8 +248,59 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	 * after the previous activity has been retired, or if it matches the
 	 * current timeline.
 	 */
-	node = READ_ONCE(ref->cache);
-	if (node && node->timeline == idx)
+	it = READ_ONCE(ref->cache);
+	if (it) {
+		u64 cached = READ_ONCE(it->timeline);
+
+		/* Once claimed, this slot will only belong to this idx */
+		if (cached == idx)
+			return it;
+
+#ifdef CONFIG_64BIT /* for cmpxchg(u64) */
+		/*
+		 * An unclaimed cache [.timeline=0] can only be claimed once.
+		 *
+		 * If the value is already non-zero, some other thread has
+		 * claimed the cache and we know that is does not match our
+		 * idx. If, and only if, the timeline is currently zero is it
+		 * worth competing to claim it atomically for ourselves (for
+		 * only the winner of that race will cmpxchg return the old
+		 * value of 0).
+		 */
+		if (!cached && !cmpxchg(&it->timeline, 0, idx))
+			return it;
+#endif
+	}
+
+	BUILD_BUG_ON(offsetof(typeof(*it), node));
+
+	/* While active, the tree can only be built; not destroyed */
+	GEM_BUG_ON(i915_active_is_idle(ref));
+
+	it = fetch_node(ref->tree.rb_node);
+	while (it) {
+		if (it->timeline < idx) {
+			it = fetch_node(it->node.rb_right);
+		} else if (it->timeline > idx) {
+			it = fetch_node(it->node.rb_left);
+		} else {
+			WRITE_ONCE(ref->cache, it);
+			break;
+		}
+	}
+
+	/* NB: If the tree rotated beneath us, we may miss our target. */
+	return it;
+}
+
+static struct i915_active_fence *
+active_instance(struct i915_active *ref, u64 idx)
+{
+	struct active_node *node, *prealloc;
+	struct rb_node **p, *parent;
+
+	node = __active_lookup(ref, idx);
+	if (likely(node))
 		return &node->base;
 
 	/* Preallocate a replacement, just in case */
@@ -268,10 +337,9 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	rb_insert_color(&node->node, &ref->tree);
 
 out:
-	ref->cache = node;
+	WRITE_ONCE(ref->cache, node);
 	spin_unlock_irq(&ref->tree_lock);
 
-	BUILD_BUG_ON(offsetof(typeof(*node), base));
 	return &node->base;
 }
 
@@ -353,69 +421,116 @@ __active_del_barrier(struct i915_active *ref, struct active_node *node)
 	return ____active_del_barrier(ref, node, barrier_to_engine(node));
 }
 
-int i915_active_ref(struct i915_active *ref,
-		    struct intel_timeline *tl,
-		    struct dma_fence *fence)
+static bool
+replace_barrier(struct i915_active *ref, struct i915_active_fence *active)
+{
+	if (!is_barrier(active)) /* proto-node used by our idle barrier? */
+		return false;
+
+	/*
+	 * This request is on the kernel_context timeline, and so
+	 * we can use it to substitute for the pending idle-barrer
+	 * request that we want to emit on the kernel_context.
+	 */
+	__active_del_barrier(ref, node_from_active(active));
+	return true;
+}
+
+int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
 {
 	struct i915_active_fence *active;
 	int err;
 
-	lockdep_assert_held(&tl->mutex);
-
 	/* Prevent reaping in case we malloc/wait while building the tree */
 	err = i915_active_acquire(ref);
 	if (err)
 		return err;
 
-	active = active_instance(ref, tl);
+	active = active_instance(ref, idx);
 	if (!active) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	if (is_barrier(active)) { /* proto-node used by our idle barrier */
-		/*
-		 * This request is on the kernel_context timeline, and so
-		 * we can use it to substitute for the pending idle-barrer
-		 * request that we want to emit on the kernel_context.
-		 */
-		__active_del_barrier(ref, node_from_active(active));
+	if (replace_barrier(ref, active)) {
 		RCU_INIT_POINTER(active->fence, NULL);
 		atomic_dec(&ref->count);
 	}
 	if (!__i915_active_fence_set(active, fence))
-		atomic_inc(&ref->count);
+		__i915_active_acquire(ref);
 
 out:
 	i915_active_release(ref);
 	return err;
 }
 
-struct dma_fence *
-i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
+static struct dma_fence *
+__i915_active_set_fence(struct i915_active *ref,
+			struct i915_active_fence *active,
+			struct dma_fence *fence)
 {
 	struct dma_fence *prev;
 
-	/* We expect the caller to manage the exclusive timeline ordering */
-	GEM_BUG_ON(i915_active_is_idle(ref));
+	if (replace_barrier(ref, active)) {
+		RCU_INIT_POINTER(active->fence, fence);
+		return NULL;
+	}
 
 	rcu_read_lock();
-	prev = __i915_active_fence_set(&ref->excl, f);
+	prev = __i915_active_fence_set(active, fence);
 	if (prev)
 		prev = dma_fence_get_rcu(prev);
 	else
-		atomic_inc(&ref->count);
+		__i915_active_acquire(ref);
 	rcu_read_unlock();
 
 	return prev;
 }
 
+static struct i915_active_fence *
+__active_fence(struct i915_active *ref, u64 idx)
+{
+	struct active_node *it;
+
+	it = __active_lookup(ref, idx);
+	if (unlikely(!it)) { /* Contention with parallel tree builders! */
+		spin_lock_irq(&ref->tree_lock);
+		it = __active_lookup(ref, idx);
+		spin_unlock_irq(&ref->tree_lock);
+	}
+	GEM_BUG_ON(!it); /* slot must be preallocated */
+
+	return &it->base;
+}
+
+struct dma_fence *
+__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
+{
+	/* Only valid while active, see i915_active_acquire_for_context() */
+	return __i915_active_set_fence(ref, __active_fence(ref, idx), fence);
+}
+
+struct dma_fence *
+i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
+{
+	/* We expect the caller to manage the exclusive timeline ordering */
+	return __i915_active_set_fence(ref, &ref->excl, f);
+}
+
 bool i915_active_acquire_if_busy(struct i915_active *ref)
 {
 	debug_active_assert(ref);
 	return atomic_add_unless(&ref->count, 1, 0);
 }
 
+static void __i915_active_activate(struct i915_active *ref)
+{
+	spin_lock_irq(&ref->tree_lock); /* __active_retire() */
+	if (!atomic_fetch_inc(&ref->count))
+		debug_active_activate(ref);
+	spin_unlock_irq(&ref->tree_lock);
+}
+
 int i915_active_acquire(struct i915_active *ref)
 {
 	int err;
@@ -423,19 +538,19 @@ int i915_active_acquire(struct i915_active *ref)
 	if (i915_active_acquire_if_busy(ref))
 		return 0;
 
+	if (!ref->active) {
+		__i915_active_activate(ref);
+		return 0;
+	}
+
 	err = mutex_lock_interruptible(&ref->mutex);
 	if (err)
 		return err;
 
 	if (likely(!i915_active_acquire_if_busy(ref))) {
-		if (ref->active)
-			err = ref->active(ref);
-		if (!err) {
-			spin_lock_irq(&ref->tree_lock); /* __active_retire() */
-			debug_active_activate(ref);
-			atomic_inc(&ref->count);
-			spin_unlock_irq(&ref->tree_lock);
-		}
+		err = ref->active(ref);
+		if (!err)
+			__i915_active_activate(ref);
 	}
 
 	mutex_unlock(&ref->mutex);
@@ -443,6 +558,24 @@ int i915_active_acquire(struct i915_active *ref)
 	return err;
 }
 
+int i915_active_acquire_for_context(struct i915_active *ref, u64 idx)
+{
+	struct i915_active_fence *active;
+	int err;
+
+	err = i915_active_acquire(ref);
+	if (err)
+		return err;
+
+	active = active_instance(ref, idx);
+	if (!active) {
+		i915_active_release(ref);
+		return -ENOMEM;
+	}
+
+	return 0; /* return with active ref */
+}
+
 void i915_active_release(struct i915_active *ref)
 {
 	debug_active_assert(ref);
@@ -651,16 +784,16 @@ int i915_sw_fence_await_active(struct i915_sw_fence *fence,
 	return await_active(ref, flags, sw_await_fence, fence, fence);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 void i915_active_fini(struct i915_active *ref)
 {
 	debug_active_fini(ref);
 	GEM_BUG_ON(atomic_read(&ref->count));
 	GEM_BUG_ON(work_pending(&ref->work));
-	GEM_BUG_ON(!RB_EMPTY_ROOT(&ref->tree));
 	mutex_destroy(&ref->mutex);
+
+	if (ref->cache)
+		kmem_cache_free(global.slab_cache, ref->cache);
 }
-#endif
 
 static inline bool is_idle_barrier(struct active_node *node, u64 idx)
 {
@@ -674,7 +807,6 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 	if (RB_EMPTY_ROOT(&ref->tree))
 		return NULL;
 
-	spin_lock_irq(&ref->tree_lock);
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	/*
@@ -700,9 +832,9 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 
 		prev = p;
 		if (node->timeline < idx)
-			p = p->rb_right;
+			p = READ_ONCE(p->rb_right);
 		else
-			p = p->rb_left;
+			p = READ_ONCE(p->rb_left);
 	}
 
 	/*
@@ -739,14 +871,13 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 			goto match;
 	}
 
-	spin_unlock_irq(&ref->tree_lock);
-
 	return NULL;
 
 match:
+	spin_lock_irq(&ref->tree_lock);
 	rb_erase(p, &ref->tree); /* Hide from waits and sibling allocations */
 	if (p == &ref->cache->node)
-		ref->cache = NULL;
+		WRITE_ONCE(ref->cache, NULL);
 	spin_unlock_irq(&ref->tree_lock);
 
 	return rb_entry(p, struct active_node, node);
@@ -758,7 +889,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 	intel_engine_mask_t tmp, mask = engine->mask;
 	struct llist_node *first = NULL, *last = NULL;
 	struct intel_gt *gt = engine->gt;
-	int err;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
@@ -778,13 +908,13 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 		struct llist_node *prev = first;
 		struct active_node *node;
 
+		rcu_read_lock();
 		node = reuse_idle_barrier(ref, idx);
+		rcu_read_unlock();
 		if (!node) {
 			node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
-			if (!node) {
-				err = ENOMEM;
+			if (!node)
 				goto unwind;
-			}
 
 			RCU_INIT_POINTER(node->base.fence, NULL);
 			node->base.cb.func = node_retire;
@@ -804,7 +934,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			 */
 			RCU_INIT_POINTER(node->base.fence, ERR_PTR(-EAGAIN));
 			node->base.cb.node.prev = (void *)engine;
-			atomic_inc(&ref->count);
+			__i915_active_acquire(ref);
 		}
 		GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN));
 
@@ -832,7 +962,7 @@ unwind:
 
 		kmem_cache_free(global.slab_cache, node);
 	}
-	return err;
+	return -ENOMEM;
 }
 
 void i915_active_acquire_barrier(struct i915_active *ref)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index cf4058150966..fb165d3f01cf 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -163,14 +163,16 @@ void __i915_active_init(struct i915_active *ref,
 	__i915_active_init(ref, active, retire, &__mkey, &__wkey);	\
 } while (0)
 
-int i915_active_ref(struct i915_active *ref,
-		    struct intel_timeline *tl,
-		    struct dma_fence *fence);
+struct dma_fence *
+__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence);
+int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence);
 
 static inline int
 i915_active_add_request(struct i915_active *ref, struct i915_request *rq)
 {
-	return i915_active_ref(ref, i915_request_timeline(rq), &rq->fence);
+	return i915_active_ref(ref,
+			       i915_request_timeline(rq)->fence_context,
+			       &rq->fence);
 }
 
 struct dma_fence *
@@ -198,7 +200,9 @@ int i915_request_await_active(struct i915_request *rq,
 #define I915_ACTIVE_AWAIT_BARRIER BIT(2)
 
 int i915_active_acquire(struct i915_active *ref);
+int i915_active_acquire_for_context(struct i915_active *ref, u64 idx);
 bool i915_active_acquire_if_busy(struct i915_active *ref);
+
 void i915_active_release(struct i915_active *ref);
 
 static inline void __i915_active_acquire(struct i915_active *ref)
@@ -213,11 +217,7 @@ i915_active_is_idle(const struct i915_active *ref)
 	return !atomic_read(&ref->count);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 void i915_active_fini(struct i915_active *ref);
-#else
-static inline void i915_active_fini(struct i915_active *ref) { }
-#endif
 
 int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine);
@@ -231,4 +231,19 @@ struct i915_active *i915_active_create(void);
 struct i915_active *i915_active_get(struct i915_active *ref);
 void i915_active_put(struct i915_active *ref);
 
+static inline int __i915_request_await_exclusive(struct i915_request *rq,
+						 struct i915_active *active)
+{
+	struct dma_fence *fence;
+	int err = 0;
+
+	fence = i915_active_fence_get(&active->excl);
+	if (fence) {
+		err = i915_request_await_dma_fence(rq, fence);
+		dma_fence_put(fence);
+	}
+
+	return err;
+}
+
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 372354d33f55..5ac4a999f05a 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1204,6 +1204,12 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 	return dst;
 }
 
+static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc,
+			       const u32 cmd)
+{
+	return desc->cmd.value == (cmd & desc->cmd.mask);
+}
+
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
 		      const u32 *cmd, u32 length)
@@ -1242,19 +1248,19 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			 * allowed mask/value pair given in the whitelist entry.
 			 */
 			if (reg->mask) {
-				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) {
 					DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n",
 						  reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) {
 					DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n",
 						  reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
 					DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n",
@@ -1478,7 +1484,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			break;
 		}
 
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+		if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
 			ret = check_bbstart(cmd, offset, length, batch_length,
 					    batch_addr, shadow_addr,
 					    jump_whitelist);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5fd5af4bc855..00292a849c34 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -392,7 +392,7 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv)
 	pre |= IS_HSW_EARLY_SDV(dev_priv);
 	pre |= IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0);
 	pre |= IS_BXT_REVID(dev_priv, 0, BXT_REVID_B_LAST);
-	pre |= IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0);
+	pre |= IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_A0);
 	pre |= IS_GLK_REVID(dev_priv, 0, GLK_REVID_A2);
 
 	if (pre) {
@@ -1075,6 +1075,7 @@ static void i915_driver_release(struct drm_device *dev)
 
 	intel_memory_regions_driver_release(dev_priv);
 	i915_ggtt_driver_release(dev_priv);
+	i915_gem_drain_freed_objects(dev_priv);
 
 	i915_driver_mmio_release(dev_priv);
 
@@ -1119,7 +1120,6 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
 	i915_gem_context_close(file);
-	i915_gem_release(dev, file);
 
 	kfree_rcu(file_priv, rcu);
 
@@ -1846,7 +1846,8 @@ static struct drm_driver driver = {
 	 */
 	.driver_features =
 	    DRIVER_GEM |
-	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ,
+	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ |
+	    DRIVER_SYNCOBJ_TIMELINE,
 	.release = i915_driver_release,
 	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e4f7f6518945..ab17084af0ff 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -108,8 +108,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20200715"
-#define DRIVER_TIMESTAMP	1594811881
+#define DRIVER_DATE		"20200824"
+#define DRIVER_TIMESTAMP	1598293597
 
 struct drm_i915_gem_object;
 
@@ -203,11 +203,6 @@ struct drm_i915_file_private {
 		struct rcu_head rcu;
 	};
 
-	struct {
-		spinlock_t lock;
-		struct list_head request_list;
-	} mm;
-
 	struct xarray context_xa;
 	struct xarray vm_xa;
 
@@ -506,6 +501,7 @@ struct i915_psr {
 	bool link_standby;
 	bool colorimetry_support;
 	bool psr2_enabled;
+	bool psr2_sel_fetch_enabled;
 	u8 sink_sync_latency;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
@@ -592,11 +588,6 @@ struct i915_gem_mm {
 	atomic_t free_count;
 
 	/**
-	 * Small stash of WC pages
-	 */
-	struct pagestash wc_stash;
-
-	/**
 	 * tmpfs instance used for shmem backed objects
 	 */
 	struct vfsmount *gemfs;
@@ -1045,6 +1036,14 @@ struct drm_i915_private {
 	struct intel_l3_parity l3_parity;
 
 	/*
+	 * HTI (aka HDPORT) state read during initial hw readout.  Most
+	 * platforms don't have HTI, so this will just stay 0.  Those that do
+	 * will use this later to figure out which PLLs and PHYs are unavailable
+	 * for driver usage.
+	 */
+	u32 hti_state;
+
+	/*
 	 * edram size in MB.
 	 * Cannot be determined by PCIID. You must always read a register.
 	 */
@@ -1489,6 +1488,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_ICL_WITH_PORT_F(dev_priv) \
 	IS_SUBPLATFORM(dev_priv, INTEL_ICELAKE, INTEL_SUBPLATFORM_PORTF)
 
+#define IS_TGL_U(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULT)
+
+#define IS_TGL_Y(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULX)
+
 #define SKL_REVID_A0		0x0
 #define SKL_REVID_B0		0x1
 #define SKL_REVID_C0		0x2
@@ -1509,14 +1514,34 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_BXT_REVID(dev_priv, since, until) \
 	(IS_BROXTON(dev_priv) && IS_REVID(dev_priv, since, until))
 
-#define KBL_REVID_A0		0x0
-#define KBL_REVID_B0		0x1
-#define KBL_REVID_C0		0x2
-#define KBL_REVID_D0		0x3
-#define KBL_REVID_E0		0x4
+enum {
+	KBL_REVID_A0,
+	KBL_REVID_B0,
+	KBL_REVID_B1,
+	KBL_REVID_C0,
+	KBL_REVID_D0,
+	KBL_REVID_D1,
+	KBL_REVID_E0,
+	KBL_REVID_F0,
+	KBL_REVID_G0,
+};
+
+struct i915_rev_steppings {
+	u8 gt_stepping;
+	u8 disp_stepping;
+};
+
+/* Defined in intel_workarounds.c */
+extern const struct i915_rev_steppings kbl_revids[];
 
-#define IS_KBL_REVID(dev_priv, since, until) \
-	(IS_KABYLAKE(dev_priv) && IS_REVID(dev_priv, since, until))
+#define IS_KBL_GT_REVID(dev_priv, since, until) \
+	(IS_KABYLAKE(dev_priv) && \
+	 kbl_revids[INTEL_REVID(dev_priv)].gt_stepping >= since && \
+	 kbl_revids[INTEL_REVID(dev_priv)].gt_stepping <= until)
+#define IS_KBL_DISP_REVID(dev_priv, since, until) \
+	(IS_KABYLAKE(dev_priv) && \
+	 kbl_revids[INTEL_REVID(dev_priv)].disp_stepping >= since && \
+	 kbl_revids[INTEL_REVID(dev_priv)].disp_stepping <= until)
 
 #define GLK_REVID_A0		0x0
 #define GLK_REVID_A1		0x1
@@ -1665,6 +1690,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_PSR(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_psr)
 #define HAS_PSR_HW_TRACKING(dev_priv) \
 	(INTEL_INFO(dev_priv)->display.has_psr_hw_tracking)
+#define HAS_PSR2_SEL_FETCH(dev_priv)	 (INTEL_GEN(dev_priv) >= 12)
 #define HAS_TRANSCODER(dev_priv, trans)	 ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0)
 
 #define HAS_RC6(dev_priv)		 (INTEL_INFO(dev_priv)->has_rc6)
@@ -1790,11 +1816,18 @@ static inline void i915_gem_drain_workqueue(struct drm_i915_private *i915)
 }
 
 struct i915_vma * __must_check
+i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
+			    struct i915_gem_ww_ctx *ww,
+			    const struct i915_ggtt_view *view,
+			    u64 size, u64 alignment, u64 flags);
+
+static inline struct i915_vma * __must_check
 i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 const struct i915_ggtt_view *view,
-			 u64 size,
-			 u64 alignment,
-			 u64 flags);
+			 u64 size, u64 alignment, u64 flags)
+{
+	return i915_gem_object_ggtt_pin_ww(obj, NULL, view, size, alignment, flags);
+}
 
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
@@ -1831,7 +1864,6 @@ void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
 
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file);
-void i915_gem_release(struct drm_device *dev, struct drm_file *file);
 
 int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9aa3066cb75d..bb0c12975f38 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -335,12 +335,20 @@ i915_gem_shmem_pread(struct drm_i915_gem_object *obj,
 	u64 remain;
 	int ret;
 
-	ret = i915_gem_object_prepare_read(obj, &needs_clflush);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		return ret;
 
+	ret = i915_gem_object_prepare_read(obj, &needs_clflush);
+	if (ret) {
+		i915_gem_object_unlock(obj);
+		return ret;
+	}
+
 	fence = i915_gem_object_lock_fence(obj);
 	i915_gem_object_finish_access(obj);
+	i915_gem_object_unlock(obj);
+
 	if (!fence)
 		return -ENOMEM;
 
@@ -420,7 +428,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
-	ret = i915_gem_object_lock_interruptible(obj);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		goto out_unpin;
 
@@ -619,7 +627,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
-	ret = i915_gem_object_lock_interruptible(obj);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		goto out_unpin;
 
@@ -734,12 +742,20 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj,
 	u64 remain;
 	int ret;
 
-	ret = i915_gem_object_prepare_write(obj, &needs_clflush);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		return ret;
 
+	ret = i915_gem_object_prepare_write(obj, &needs_clflush);
+	if (ret) {
+		i915_gem_object_unlock(obj);
+		return ret;
+	}
+
 	fence = i915_gem_object_lock_fence(obj);
 	i915_gem_object_finish_access(obj);
+	i915_gem_object_unlock(obj);
+
 	if (!fence)
 		return -ENOMEM;
 
@@ -946,11 +962,10 @@ static void discard_ggtt_vma(struct i915_vma *vma)
 }
 
 struct i915_vma *
-i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
-			 const struct i915_ggtt_view *view,
-			 u64 size,
-			 u64 alignment,
-			 u64 flags)
+i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
+			    struct i915_gem_ww_ctx *ww,
+			    const struct i915_ggtt_view *view,
+			    u64 size, u64 alignment, u64 flags)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_ggtt *ggtt = &i915->ggtt;
@@ -1016,7 +1031,7 @@ new_vma:
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	ret = i915_vma_pin_ww(vma, ww, size, alignment, flags | PIN_GLOBAL);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1290,7 +1305,7 @@ int i915_gem_freeze_late(struct drm_i915_private *i915)
 	i915_gem_drain_freed_objects(i915);
 
 	list_for_each_entry(obj, &i915->mm.shrink_list, mm.link) {
-		i915_gem_object_lock(obj);
+		i915_gem_object_lock(obj, NULL);
 		drm_WARN_ON(&i915->drm,
 			    i915_gem_object_set_to_cpu_domain(obj, true));
 		i915_gem_object_unlock(obj);
@@ -1301,21 +1316,6 @@ int i915_gem_freeze_late(struct drm_i915_private *i915)
 	return 0;
 }
 
-void i915_gem_release(struct drm_device *dev, struct drm_file *file)
-{
-	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct i915_request *request;
-
-	/* Clean up our request list when the client is going away, so that
-	 * later retire_requests won't dereference our soon-to-be-gone
-	 * file_priv.
-	 */
-	spin_lock(&file_priv->mm.lock);
-	list_for_each_entry(request, &file_priv->mm.request_list, client_link)
-		request->file_priv = NULL;
-	spin_unlock(&file_priv->mm.lock);
-}
-
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv;
@@ -1331,9 +1331,6 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	file_priv->dev_priv = i915;
 	file_priv->file = file;
 
-	spin_lock_init(&file_priv->mm.lock);
-	INIT_LIST_HEAD(&file_priv->mm.request_list);
-
 	file_priv->bsd_engine = -1;
 	file_priv->hang_timestamp = jiffies;
 
@@ -1344,6 +1341,58 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	return ret;
 }
 
+void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ww, bool intr)
+{
+	ww_acquire_init(&ww->ctx, &reservation_ww_class);
+	INIT_LIST_HEAD(&ww->obj_list);
+	ww->intr = intr;
+	ww->contended = NULL;
+}
+
+static void i915_gem_ww_ctx_unlock_all(struct i915_gem_ww_ctx *ww)
+{
+	struct drm_i915_gem_object *obj;
+
+	while ((obj = list_first_entry_or_null(&ww->obj_list, struct drm_i915_gem_object, obj_link))) {
+		list_del(&obj->obj_link);
+		i915_gem_object_unlock(obj);
+	}
+}
+
+void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj)
+{
+	list_del(&obj->obj_link);
+	i915_gem_object_unlock(obj);
+}
+
+void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ww)
+{
+	i915_gem_ww_ctx_unlock_all(ww);
+	WARN_ON(ww->contended);
+	ww_acquire_fini(&ww->ctx);
+}
+
+int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ww)
+{
+	int ret = 0;
+
+	if (WARN_ON(!ww->contended))
+		return -EINVAL;
+
+	i915_gem_ww_ctx_unlock_all(ww);
+	if (ww->intr)
+		ret = dma_resv_lock_slow_interruptible(ww->contended->base.resv, &ww->ctx);
+	else
+		dma_resv_lock_slow(ww->contended->base.resv, &ww->ctx);
+
+	if (!ret)
+		list_add_tail(&ww->contended->obj_link, &ww->obj_list);
+
+	ww->contended = NULL;
+
+	return ret;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_gem_device.c"
 #include "selftests/i915_gem.c"
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index f333e88a2b6e..a4cad3f154ca 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -116,4 +116,16 @@ static inline bool __tasklet_is_scheduled(struct tasklet_struct *t)
 	return test_bit(TASKLET_STATE_SCHED, &t->state);
 }
 
+struct i915_gem_ww_ctx {
+	struct ww_acquire_ctx ctx;
+	struct list_head obj_list;
+	bool intr;
+	struct drm_i915_gem_object *contended;
+};
+
+void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ctx, bool intr);
+void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ctx);
+int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ctx);
+void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj);
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 421613219ae9..f96032c60a12 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -132,6 +132,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_BATCH_FIRST:
 	case I915_PARAM_HAS_EXEC_FENCE_ARRAY:
 	case I915_PARAM_HAS_EXEC_SUBMIT_FENCE:
+	case I915_PARAM_HAS_EXEC_TIMELINE_FENCES:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6a3a2ce0b394..3e6cbb0d1150 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1159,7 +1159,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
 			switch (engine->id) {
 			default:
 				MISSING_CASE(engine->id);
-				/* fall through */
+				fallthrough;
 			case RCS0:
 				mmio = RENDER_HWS_PGA_GEN7;
 				break;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 1fa67700d8f4..f113fe44572b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -41,6 +41,7 @@
 #include "display/intel_lpe_audio.h"
 #include "display/intel_psr.h"
 
+#include "gt/intel_breadcrumbs.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_irq.h"
 #include "gt/intel_gt_pm_irq.h"
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 8d8db9ff0a48..7f139ea4a90b 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -102,6 +102,11 @@ i915_param_named(psr_safest_params, bool, 0400,
 	"is helpful to detect if PSR issues are related to bad values set in "
 	" VBT. (0=use VBT parameters, 1=use safest parameters)");
 
+i915_param_named_unsafe(enable_psr2_sel_fetch, bool, 0400,
+	"Enable PSR2 selective fetch "
+	"(0=disabled, 1=enabled) "
+	"Default: 0");
+
 i915_param_named_unsafe(force_probe, charp, 0400,
 	"Force probe the driver for specified devices. "
 	"See CONFIG_DRM_I915_FORCE_PROBE for details.");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 53fb5ba8fbed..330c03e2b4f7 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -54,6 +54,7 @@ struct drm_printer;
 	param(int, enable_fbc, -1, 0600) \
 	param(int, enable_psr, -1, 0600) \
 	param(bool, psr_safest_params, false, 0600) \
+	param(bool, enable_psr2_sel_fetch, false, 0600) \
 	param(int, disable_power_well, -1, 0400) \
 	param(int, enable_ips, 1, 0600) \
 	param(int, invert_brightness, 0, 0600) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 2338f92ce490..366ddfc8df6b 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -890,6 +890,7 @@ static const struct intel_device_info rkl_info = {
 	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |
 		BIT(TRANSCODER_C),
 	.require_force_probe = 1,
+	.display.has_hti = 1,
 	.display.has_psr_hw_tracking = 0,
 	.platform_engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0),
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index c6f6370283cf..e94976976571 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1195,24 +1195,39 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
 	struct i915_gem_engines_iter it;
 	struct i915_gem_context *ctx = stream->ctx;
 	struct intel_context *ce;
-	int err;
+	struct i915_gem_ww_ctx ww;
+	int err = -ENODEV;
 
 	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
 		if (ce->engine != stream->engine) /* first match! */
 			continue;
 
-		/*
-		 * As the ID is the gtt offset of the context's vma we
-		 * pin the vma to ensure the ID remains fixed.
-		 */
-		err = intel_context_pin(ce);
-		if (err == 0) {
-			stream->pinned_ctx = ce;
-			break;
-		}
+		err = 0;
+		break;
 	}
 	i915_gem_context_unlock_engines(ctx);
 
+	if (err)
+		return ERR_PTR(err);
+
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	/*
+	 * As the ID is the gtt offset of the context's vma we
+	 * pin the vma to ensure the ID remains fixed.
+	 */
+	err = intel_context_pin_ww(ce, &ww);
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+
+	if (err)
+		return ERR_PTR(err);
+
+	stream->pinned_ctx = ce;
 	return stream->pinned_ctx;
 }
 
@@ -1923,15 +1938,22 @@ emit_oa_config(struct i915_perf_stream *stream,
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
+	struct i915_gem_ww_ctx ww;
 	int err;
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	err = i915_gem_object_lock(vma->obj, &ww);
+	if (err)
+		goto err;
+
+	err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
-		goto err_vma_put;
+		goto err;
 
 	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
@@ -1953,11 +1975,9 @@ emit_oa_config(struct i915_perf_stream *stream,
 			goto err_add_request;
 	}
 
-	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, 0);
 	if (!err)
 		err = i915_vma_move_to_active(vma, rq, 0);
-	i915_vma_unlock(vma);
 	if (err)
 		goto err_add_request;
 
@@ -1971,7 +1991,14 @@ err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
-err_vma_put:
+err:
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+
+	i915_gem_ww_ctx_fini(&ww);
 	i915_vma_put(vma);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 28bc5f13ae52..69c0fa20eba1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -445,8 +445,6 @@ static void i915_pmu_event_destroy(struct perf_event *event)
 		container_of(event->pmu, typeof(*i915), pmu.base);
 
 	drm_WARN_ON(&i915->drm, event->parent);
-
-	module_put(THIS_MODULE);
 }
 
 static int
@@ -476,7 +474,7 @@ config_status(struct drm_i915_private *i915, u64 config)
 		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
 			/* Requires a mutex for sampling! */
 			return -ENODEV;
-		/* Fall-through. */
+		fallthrough;
 	case I915_PMU_REQUESTED_FREQUENCY:
 		if (INTEL_GEN(i915) < 6)
 			return -ENODEV;
@@ -538,10 +536,8 @@ static int i915_pmu_event_init(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (!event->parent) {
-		__module_get(THIS_MODULE);
+	if (!event->parent)
 		event->destroy = i915_pmu_event_destroy;
-	}
 
 	return 0;
 }
@@ -1130,6 +1126,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	if (!pmu->base.attr_groups)
 		goto err_attr;
 
+	pmu->base.module	= THIS_MODULE;
 	pmu->base.task_ctx_nr	= perf_invalid_context;
 	pmu->base.event_init	= i915_pmu_event_init;
 	pmu->base.add		= i915_pmu_event_add;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4e796ff4d7d0..ac691927e29d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1898,6 +1898,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  PWR_DOWN_LN_3_1_0		(0xb << 4)
 #define  PWR_DOWN_LN_MASK		(0xf << 4)
 #define  PWR_DOWN_LN_SHIFT		4
+#define  EDP4K2K_MODE_OVRD_EN		(1 << 3)
+#define  EDP4K2K_MODE_OVRD_OPTIMIZED	(1 << 2)
 
 #define ICL_PORT_CL_DW12(phy)		_MMIO(_ICL_PORT_CL_DW(12, phy))
 #define   ICL_LANE_ENABLE_AUX		(1 << 0)
@@ -2919,6 +2921,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MBUS_BBOX_CTL_S1		_MMIO(0x45040)
 #define MBUS_BBOX_CTL_S2		_MMIO(0x45044)
 
+#define HDPORT_STATE			_MMIO(0x45050)
+#define   HDPORT_DPLL_USED_MASK		REG_GENMASK(14, 12)
+#define   HDPORT_PHY_USED_DP(phy)	REG_BIT(2 * (phy) + 2)
+#define   HDPORT_PHY_USED_HDMI(phy)	REG_BIT(2 * (phy) + 1)
+#define   HDPORT_ENABLED		REG_BIT(0)
+
 /* Make render/texture TLB fetches lower priorty than associated data
  *   fetches. This is not turned on by default
  */
@@ -7870,6 +7878,7 @@ enum {
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
 #define CHICKEN_PAR1_1			_MMIO(0x42080)
+#define  DIS_RAM_BYPASS_PSR2_MAN_TRACK	(1 << 16)
 #define  SKL_DE_COMPRESSED_HASH_MODE	(1 << 15)
 #define  DPA_MASK_VBLANK_SRD		(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES		(1 << 14)
@@ -8711,6 +8720,7 @@ enum {
 #define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1 << 31)
 #define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1 << 30)
 #define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1 << 29)
+#define  PCH_DPMGUNIT_CLOCK_GATE_DISABLE (1 << 15)
 #define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1 << 14)
 #define  CNP_PWM_CGE_GATING_DISABLE (1 << 13)
 #define  PCH_LP_PARTITION_LEVEL_DISABLE  (1 << 12)
@@ -9217,8 +9227,8 @@ enum {
 #define   DISPLAY_IPS_CONTROL			0x19
 #define   TGL_PCODE_TCCOLD			0x26
 #define     TGL_PCODE_EXIT_TCCOLD_DATA_L_EXIT_FAILED	REG_BIT(0)
-#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ	0
-#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ	REG_BIT(0)
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_L_BLOCK_REQ	0
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_L_UNBLOCK_REQ	REG_BIT(0)
             /* See also IPS_CTL */
 #define     IPS_PCODE_CONTROL			(1 << 30)
 #define   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL	0x1A
@@ -10277,12 +10287,18 @@ enum skl_power_gate {
 
 #define ICL_DPCLKA_CFGCR0			_MMIO(0x164280)
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)	(1 << _PICK(phy, 10, 11, 24))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)	REG_BIT((phy) + 10)
 #define  ICL_DPCLKA_CFGCR0_TC_CLK_OFF(tc_port)	(1 << ((tc_port) < PORT_TC4 ? \
 						       (tc_port) + 12 : \
 						       (tc_port) - PORT_TC4 + 21))
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy)	((phy) * 2)
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy)	(3 << ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll, phy)	((pll) << ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy)	_PICK(phy, 0, 2, 4, 27)
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy) \
+	(3 << RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll, phy) \
+	((pll) << RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
 
 /* CNL PLL */
 #define DPLL0_ENABLE		0x46010
@@ -10503,19 +10519,21 @@ enum skl_power_gate {
 
 #define _TGL_DPLL0_CFGCR0		0x164284
 #define _TGL_DPLL1_CFGCR0		0x16428C
-/* TODO: add DPLL4 */
 #define _TGL_TBTPLL_CFGCR0		0x16429C
 #define TGL_DPLL_CFGCR0(pll)		_MMIO_PLL3(pll, _TGL_DPLL0_CFGCR0, \
 						  _TGL_DPLL1_CFGCR0, \
 						  _TGL_TBTPLL_CFGCR0)
+#define RKL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _TGL_DPLL0_CFGCR0, \
+						  _TGL_DPLL1_CFGCR0)
 
 #define _TGL_DPLL0_CFGCR1		0x164288
 #define _TGL_DPLL1_CFGCR1		0x164290
-/* TODO: add DPLL4 */
 #define _TGL_TBTPLL_CFGCR1		0x1642A0
 #define TGL_DPLL_CFGCR1(pll)		_MMIO_PLL3(pll, _TGL_DPLL0_CFGCR1, \
 						   _TGL_DPLL1_CFGCR1, \
 						   _TGL_TBTPLL_CFGCR1)
+#define RKL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _TGL_DPLL0_CFGCR1, \
+						  _TGL_DPLL1_CFGCR1)
 
 #define _DKL_PHY1_BASE			0x168000
 #define _DKL_PHY2_BASE			0x169000
@@ -12336,4 +12354,10 @@ enum skl_power_gate {
 #define   DSB_ENABLE			(1 << 31)
 #define   DSB_STATUS			(1 << 0)
 
+#define TGL_ROOT_DEVICE_ID		0x9A00
+#define TGL_ROOT_DEVICE_MASK		0xFF00
+#define TGL_ROOT_DEVICE_SKU_MASK	0xF
+#define TGL_ROOT_DEVICE_SKU_ULX		0x2
+#define TGL_ROOT_DEVICE_SKU_ULT		0x4
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..11e272422fb7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -31,6 +31,7 @@
 #include <linux/sched/signal.h>
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
 #include "gt/intel_ring.h"
 #include "gt/intel_rps.h"
@@ -186,48 +187,34 @@ static void irq_execute_cb_hook(struct irq_work *wrk)
 	irq_execute_cb(wrk);
 }
 
-static void __notify_execute_cb(struct i915_request *rq)
+static __always_inline void
+__notify_execute_cb(struct i915_request *rq, bool (*fn)(struct irq_work *wrk))
 {
 	struct execute_cb *cb, *cn;
 
-	lockdep_assert_held(&rq->lock);
-
-	GEM_BUG_ON(!i915_request_is_active(rq));
 	if (llist_empty(&rq->execute_cb))
 		return;
 
-	llist_for_each_entry_safe(cb, cn, rq->execute_cb.first, work.llnode)
-		irq_work_queue(&cb->work);
-
-	/*
-	 * XXX Rollback on __i915_request_unsubmit()
-	 *
-	 * In the future, perhaps when we have an active time-slicing scheduler,
-	 * it will be interesting to unsubmit parallel execution and remove
-	 * busywaits from the GPU until their master is restarted. This is
-	 * quite hairy, we have to carefully rollback the fence and do a
-	 * preempt-to-idle cycle on the target engine, all the while the
-	 * master execute_cb may refire.
-	 */
-	init_llist_head(&rq->execute_cb);
+	llist_for_each_entry_safe(cb, cn,
+				  llist_del_all(&rq->execute_cb),
+				  work.llnode)
+		fn(&cb->work);
 }
 
-static inline void
-remove_from_client(struct i915_request *request)
+static void __notify_execute_cb_irq(struct i915_request *rq)
 {
-	struct drm_i915_file_private *file_priv;
+	__notify_execute_cb(rq, irq_work_queue);
+}
 
-	if (!READ_ONCE(request->file_priv))
-		return;
+static bool irq_work_imm(struct irq_work *wrk)
+{
+	wrk->func(wrk);
+	return false;
+}
 
-	rcu_read_lock();
-	file_priv = xchg(&request->file_priv, NULL);
-	if (file_priv) {
-		spin_lock(&file_priv->mm.lock);
-		list_del(&request->client_link);
-		spin_unlock(&file_priv->mm.lock);
-	}
-	rcu_read_unlock();
+static void __notify_execute_cb_imm(struct i915_request *rq)
+{
+	__notify_execute_cb(rq, irq_work_imm);
 }
 
 static void free_capture_list(struct i915_request *request)
@@ -274,9 +261,16 @@ static void remove_from_engine(struct i915_request *rq)
 		locked = engine;
 	}
 	list_del_init(&rq->sched.link);
+
 	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
+
+	/* Prevent further __await_execution() registering a cb, then flush */
+	set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
+
 	spin_unlock_irq(&locked->active.lock);
+
+	__notify_execute_cb_imm(rq);
 }
 
 bool i915_request_retire(struct i915_request *rq)
@@ -288,6 +282,7 @@ bool i915_request_retire(struct i915_request *rq)
 
 	GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
 	trace_i915_request_retire(rq);
+	i915_request_mark_complete(rq);
 
 	/*
 	 * We know the GPU must have read the request to have
@@ -305,32 +300,30 @@ bool i915_request_retire(struct i915_request *rq)
 		__i915_request_fill(rq, POISON_FREE);
 	rq->ring->head = rq->postfix;
 
+	if (!i915_request_signaled(rq)) {
+		spin_lock_irq(&rq->lock);
+		dma_fence_signal_locked(&rq->fence);
+		spin_unlock_irq(&rq->lock);
+	}
+
+	if (i915_request_has_waitboost(rq)) {
+		GEM_BUG_ON(!atomic_read(&rq->engine->gt->rps.num_waiters));
+		atomic_dec(&rq->engine->gt->rps.num_waiters);
+	}
+
 	/*
 	 * We only loosely track inflight requests across preemption,
 	 * and so we may find ourselves attempting to retire a _completed_
 	 * request that we have removed from the HW and put back on a run
 	 * queue.
+	 *
+	 * As we set I915_FENCE_FLAG_ACTIVE on the request, this should be
+	 * after removing the breadcrumb and signaling it, so that we do not
+	 * inadvertently attach the breadcrumb to a completed request.
 	 */
 	remove_from_engine(rq);
-
-	spin_lock_irq(&rq->lock);
-	i915_request_mark_complete(rq);
-	if (!i915_request_signaled(rq))
-		dma_fence_signal_locked(&rq->fence);
-	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
-		i915_request_cancel_breadcrumb(rq);
-	if (i915_request_has_waitboost(rq)) {
-		GEM_BUG_ON(!atomic_read(&rq->engine->gt->rps.num_waiters));
-		atomic_dec(&rq->engine->gt->rps.num_waiters);
-	}
-	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
-		set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
-		__notify_execute_cb(rq);
-	}
 	GEM_BUG_ON(!llist_empty(&rq->execute_cb));
-	spin_unlock_irq(&rq->lock);
 
-	remove_from_client(rq);
 	__list_del_entry(&rq->link); /* poison neither prev/next (RCU walks) */
 
 	intel_context_exit(rq->context);
@@ -357,12 +350,6 @@ void i915_request_retire_upto(struct i915_request *rq)
 	} while (i915_request_retire(tmp) && tmp != rq);
 }
 
-static void __llist_add(struct llist_node *node, struct llist_head *head)
-{
-	node->next = head->first;
-	head->first = node;
-}
-
 static struct i915_request * const *
 __engine_active(struct intel_engine_cs *engine)
 {
@@ -388,17 +375,38 @@ static bool __request_in_flight(const struct i915_request *signal)
 	 * As we know that there are always preemption points between
 	 * requests, we know that only the currently executing request
 	 * may be still active even though we have cleared the flag.
-	 * However, we can't rely on our tracking of ELSP[0] to known
+	 * However, we can't rely on our tracking of ELSP[0] to know
 	 * which request is currently active and so maybe stuck, as
 	 * the tracking maybe an event behind. Instead assume that
 	 * if the context is still inflight, then it is still active
 	 * even if the active flag has been cleared.
+	 *
+	 * To further complicate matters, if there a pending promotion, the HW
+	 * may either perform a context switch to the second inflight execlists,
+	 * or it may switch to the pending set of execlists. In the case of the
+	 * latter, it may send the ACK and we process the event copying the
+	 * pending[] over top of inflight[], _overwriting_ our *active. Since
+	 * this implies the HW is arbitrating and not struck in *active, we do
+	 * not worry about complete accuracy, but we do require no read/write
+	 * tearing of the pointer [the read of the pointer must be valid, even
+	 * as the array is being overwritten, for which we require the writes
+	 * to avoid tearing.]
+	 *
+	 * Note that the read of *execlists->active may race with the promotion
+	 * of execlists->pending[] to execlists->inflight[], overwritting
+	 * the value at *execlists->active. This is fine. The promotion implies
+	 * that we received an ACK from the HW, and so the context is not
+	 * stuck -- if we do not see ourselves in *active, the inflight status
+	 * is valid. If instead we see ourselves being copied into *active,
+	 * we are inflight and may signal the callback.
 	 */
 	if (!intel_context_inflight(signal->context))
 		return false;
 
 	rcu_read_lock();
-	for (port = __engine_active(signal->engine); (rq = *port); port++) {
+	for (port = __engine_active(signal->engine);
+	     (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */
+	     port++) {
 		if (rq->context == signal->context) {
 			inflight = i915_seqno_passed(rq->fence.seqno,
 						     signal->fence.seqno);
@@ -439,18 +447,24 @@ __await_execution(struct i915_request *rq,
 		cb->work.func = irq_execute_cb_hook;
 	}
 
-	spin_lock_irq(&signal->lock);
-	if (i915_request_is_active(signal) || __request_in_flight(signal)) {
-		if (hook) {
-			hook(rq, &signal->fence);
-			i915_request_put(signal);
-		}
-		i915_sw_fence_complete(cb->fence);
-		kmem_cache_free(global.slab_execute_cbs, cb);
-	} else {
-		__llist_add(&cb->work.llnode, &signal->execute_cb);
+	/*
+	 * Register the callback first, then see if the signaler is already
+	 * active. This ensures that if we race with the
+	 * __notify_execute_cb from i915_request_submit() and we are not
+	 * included in that list, we get a second bite of the cherry and
+	 * execute it ourselves. After this point, a future
+	 * i915_request_submit() will notify us.
+	 *
+	 * In i915_request_retire() we set the ACTIVE bit on a completed
+	 * request (then flush the execute_cb). So by registering the
+	 * callback first, then checking the ACTIVE bit, we serialise with
+	 * the completed/retired request.
+	 */
+	if (llist_add(&cb->work.llnode, &signal->execute_cb)) {
+		if (i915_request_is_active(signal) ||
+		    __request_in_flight(signal))
+			__notify_execute_cb_imm(signal);
 	}
-	spin_unlock_irq(&signal->lock);
 
 	return 0;
 }
@@ -566,18 +580,28 @@ xfer:
 		clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
 	}
 
+	/*
+	 * XXX Rollback bonded-execution on __i915_request_unsubmit()?
+	 *
+	 * In the future, perhaps when we have an active time-slicing scheduler,
+	 * it will be interesting to unsubmit parallel execution and remove
+	 * busywaits from the GPU until their master is restarted. This is
+	 * quite hairy, we have to carefully rollback the fence and do a
+	 * preempt-to-idle cycle on the target engine, all the while the
+	 * master execute_cb may refire.
+	 */
+	__notify_execute_cb_irq(request);
+
 	/* We may be recursing from the signal callback of another i915 fence */
 	if (!i915_request_signaled(request)) {
 		spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-		__notify_execute_cb(request);
 		if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			     &request->fence.flags) &&
 		    !i915_request_enable_breadcrumb(request))
 			intel_engine_signal_breadcrumbs(engine);
 
 		spin_unlock(&request->lock);
-		GEM_BUG_ON(!llist_empty(&request->execute_cb));
 	}
 
 	return result;
@@ -600,27 +624,27 @@ void __i915_request_unsubmit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 
+	/*
+	 * Only unwind in reverse order, required so that the per-context list
+	 * is kept in seqno/ring order.
+	 */
 	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
 
 	/*
-	 * Only unwind in reverse order, required so that the per-context list
-	 * is kept in seqno/ring order.
+	 * Before we remove this breadcrumb from the signal list, we have
+	 * to ensure that a concurrent dma_fence_enable_signaling() does not
+	 * attach itself. We first mark the request as no longer active and
+	 * make sure that is visible to other cores, and then remove the
+	 * breadcrumb if attached.
 	 */
-
-	/* We may be recursing from the signal callback of another i915 fence */
-	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
-
+	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
+	clear_bit_unlock(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
 		i915_request_cancel_breadcrumb(request);
 
-	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	clear_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
-
-	spin_unlock(&request->lock);
-
 	/* We've already spun, don't charge on resubmitting. */
 	if (request->sched.semaphores && i915_request_started(request))
 		request->sched.semaphores = 0;
@@ -757,7 +781,6 @@ static void __i915_request_ctor(void *arg)
 
 	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
 
-	rq->file_priv = NULL;
 	rq->capture_list = NULL;
 
 	init_llist_head(&rq->execute_cb);
@@ -847,7 +870,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 
 	/* No zalloc, everything must be cleared after use */
 	rq->batch = NULL;
-	GEM_BUG_ON(rq->file_priv);
 	GEM_BUG_ON(rq->capture_list);
 	GEM_BUG_ON(!llist_empty(&rq->execute_cb));
 
@@ -1640,7 +1662,7 @@ static bool busywait_stop(unsigned long timeout, unsigned int cpu)
 	return this_cpu != cpu;
 }
 
-static bool __i915_spin_request(const struct i915_request * const rq, int state)
+static bool __i915_spin_request(struct i915_request * const rq, int state)
 {
 	unsigned long timeout_ns;
 	unsigned int cpu;
@@ -1673,7 +1695,7 @@ static bool __i915_spin_request(const struct i915_request * const rq, int state)
 	timeout_ns = READ_ONCE(rq->engine->props.max_busywait_duration_ns);
 	timeout_ns += local_clock_ns(&cpu);
 	do {
-		if (i915_request_completed(rq))
+		if (dma_fence_is_signaled(&rq->fence))
 			return true;
 
 		if (signal_pending_state(state, current))
@@ -1697,7 +1719,7 @@ static void request_wait_wake(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
 	struct request_wait *wait = container_of(cb, typeof(*wait), cb);
 
-	wake_up_process(wait->tsk);
+	wake_up_process(fetch_and_zero(&wait->tsk));
 }
 
 /**
@@ -1766,10 +1788,8 @@ long i915_request_wait(struct i915_request *rq,
 	 * duration, which we currently lack.
 	 */
 	if (IS_ACTIVE(CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT) &&
-	    __i915_spin_request(rq, state)) {
-		dma_fence_signal(&rq->fence);
+	    __i915_spin_request(rq, state))
 		goto out;
-	}
 
 	/*
 	 * This client is about to stall waiting for the GPU. In many cases
@@ -1783,25 +1803,36 @@ long i915_request_wait(struct i915_request *rq,
 	 * but at a cost of spending more power processing the workload
 	 * (bad for battery).
 	 */
-	if (flags & I915_WAIT_PRIORITY) {
-		if (!i915_request_started(rq) &&
-		    INTEL_GEN(rq->engine->i915) >= 6)
-			intel_rps_boost(rq);
-	}
+	if (flags & I915_WAIT_PRIORITY && !i915_request_started(rq))
+		intel_rps_boost(rq);
 
 	wait.tsk = current;
 	if (dma_fence_add_callback(&rq->fence, &wait.cb, request_wait_wake))
 		goto out;
 
+	/*
+	 * Flush the submission tasklet, but only if it may help this request.
+	 *
+	 * We sometimes experience some latency between the HW interrupts and
+	 * tasklet execution (mostly due to ksoftirqd latency, but it can also
+	 * be due to lazy CS events), so lets run the tasklet manually if there
+	 * is a chance it may submit this request. If the request is not ready
+	 * to run, as it is waiting for other fences to be signaled, flushing
+	 * the tasklet is busy work without any advantage for this client.
+	 *
+	 * If the HW is being lazy, this is the last chance before we go to
+	 * sleep to catch any pending events. We will check periodically in
+	 * the heartbeat to flush the submission tasklets as a last resort
+	 * for unhappy HW.
+	 */
+	if (i915_request_is_ready(rq))
+		intel_engine_flush_submission(rq->engine);
+
 	for (;;) {
 		set_current_state(state);
 
-		if (i915_request_completed(rq)) {
-			dma_fence_signal(&rq->fence);
+		if (dma_fence_is_signaled(&rq->fence))
 			break;
-		}
-
-		intel_engine_flush_submission(rq->engine);
 
 		if (signal_pending_state(state, current)) {
 			timeout = -ERESTARTSYS;
@@ -1817,7 +1848,9 @@ long i915_request_wait(struct i915_request *rq,
 	}
 	__set_current_state(TASK_RUNNING);
 
-	dma_fence_remove_callback(&rq->fence, &wait.cb);
+	if (READ_ONCE(wait.tsk))
+		dma_fence_remove_callback(&rq->fence, &wait.cb);
+	GEM_BUG_ON(!list_empty(&wait.cb.node));
 
 out:
 	mutex_release(&rq->engine->gt->reset.mutex.dep_map, _THIS_IP_);
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 590762820761..16b721080195 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -284,10 +284,6 @@ struct i915_request {
 	/** timeline->request entry for this request */
 	struct list_head link;
 
-	struct drm_i915_file_private *file_priv;
-	/** file_priv list entry for this request */
-	struct list_head client_link;
-
 	I915_SELFTEST_DECLARE(struct {
 		struct list_head link;
 		unsigned long delay;
@@ -365,10 +361,6 @@ void i915_request_submit(struct i915_request *request);
 void __i915_request_unsubmit(struct i915_request *request);
 void i915_request_unsubmit(struct i915_request *request);
 
-/* Note: part of the intel_breadcrumbs family */
-bool i915_request_enable_breadcrumb(struct i915_request *request);
-void i915_request_cancel_breadcrumb(struct i915_request *request);
-
 long i915_request_wait(struct i915_request *rq,
 		       unsigned int flags,
 		       long timeout)
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 295b9829e2da..4cd2038cbe35 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence,
 
 		do {
 			list_for_each_entry_safe(pos, next, &x->head, entry) {
-				pos->func(pos,
-					  TASK_NORMAL, fence->error,
-					  &extra);
+				int wake_flags;
+
+				wake_flags = fence->error;
+				if (pos->func == autoremove_wake_function)
+					wake_flags = 0;
+
+				pos->func(pos, TASK_NORMAL, wake_flags, &extra);
 			}
 
 			if (list_empty(&extra))
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index bc64f773dcdb..495d28f6d160 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -291,6 +291,8 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 
 struct i915_vma_work {
 	struct dma_fence_work base;
+	struct i915_address_space *vm;
+	struct i915_vm_pt_stash stash;
 	struct i915_vma *vma;
 	struct drm_i915_gem_object *pinned;
 	struct i915_sw_dma_fence_cb cb;
@@ -302,13 +304,10 @@ static int __vma_bind(struct dma_fence_work *work)
 {
 	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
 	struct i915_vma *vma = vw->vma;
-	int err;
-
-	err = vma->ops->bind_vma(vma->vm, vma, vw->cache_level, vw->flags);
-	if (err)
-		atomic_or(I915_VMA_ERROR, &vma->flags);
 
-	return err;
+	vma->ops->bind_vma(vw->vm, &vw->stash,
+			   vma, vw->cache_level, vw->flags);
+	return 0;
 }
 
 static void __vma_release(struct dma_fence_work *work)
@@ -317,6 +316,9 @@ static void __vma_release(struct dma_fence_work *work)
 
 	if (vw->pinned)
 		__i915_gem_object_unpin_pages(vw->pinned);
+
+	i915_vm_free_pt_stash(vw->vm, &vw->stash);
+	i915_vm_put(vw->vm);
 }
 
 static const struct dma_fence_work_ops bind_ops = {
@@ -376,7 +378,6 @@ int i915_vma_bind(struct i915_vma *vma,
 {
 	u32 bind_flags;
 	u32 vma_flags;
-	int ret;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->size > vma->node.size);
@@ -433,9 +434,7 @@ int i915_vma_bind(struct i915_vma *vma,
 			work->pinned = vma->obj;
 		}
 	} else {
-		ret = vma->ops->bind_vma(vma->vm, vma, cache_level, bind_flags);
-		if (ret)
-			return ret;
+		vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
 	}
 
 	atomic_or(bind_flags, &vma->flags);
@@ -853,13 +852,19 @@ static void vma_unbind_pages(struct i915_vma *vma)
 	__vma_put_pages(vma, count | count << I915_VMA_PAGES_BIAS);
 }
 
-int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
+int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
+		    u64 size, u64 alignment, u64 flags)
 {
 	struct i915_vma_work *work = NULL;
 	intel_wakeref_t wakeref = 0;
 	unsigned int bound;
 	int err;
 
+#ifdef CONFIG_PROVE_LOCKING
+	if (debug_locks && lockdep_is_held(&vma->vm->i915->drm.struct_mutex))
+		WARN_ON(!ww);
+#endif
+
 	BUILD_BUG_ON(PIN_GLOBAL != I915_VMA_GLOBAL_BIND);
 	BUILD_BUG_ON(PIN_USER != I915_VMA_LOCAL_BIND);
 
@@ -873,16 +878,30 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	if (err)
 		return err;
 
+	if (flags & PIN_GLOBAL)
+		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+
 	if (flags & vma->vm->bind_async_flags) {
 		work = i915_vma_work();
 		if (!work) {
 			err = -ENOMEM;
-			goto err_pages;
+			goto err_rpm;
 		}
-	}
 
-	if (flags & PIN_GLOBAL)
-		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+		work->vm = i915_vm_get(vma->vm);
+
+		/* Allocate enough page directories to used PTE */
+		if (vma->vm->allocate_va_range) {
+			i915_vm_alloc_pt_stash(vma->vm,
+					       &work->stash,
+					       vma->size);
+
+			err = i915_vm_pin_pt_stash(vma->vm,
+						   &work->stash);
+			if (err)
+				goto err_fence;
+		}
+	}
 
 	/*
 	 * Differentiate between user/kernel vma inside the aliasing-ppgtt.
@@ -971,9 +990,9 @@ err_unlock:
 err_fence:
 	if (work)
 		dma_fence_work_commit_imm(&work->base);
+err_rpm:
 	if (wakeref)
 		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
-err_pages:
 	vma_put_pages(vma);
 	return err;
 }
@@ -989,7 +1008,8 @@ static void flush_idle_contexts(struct intel_gt *gt)
 	intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
 }
 
-int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags)
+int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
+		  u32 align, unsigned int flags)
 {
 	struct i915_address_space *vm = vma->vm;
 	int err;
@@ -997,7 +1017,7 @@ int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags)
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 
 	do {
-		err = i915_vma_pin(vma, 0, align, flags | PIN_GLOBAL);
+		err = i915_vma_pin_ww(vma, ww, 0, align, flags | PIN_GLOBAL);
 		if (err != -ENOSPC) {
 			if (!err) {
 				err = i915_vma_wait_for_bind(vma);
@@ -1167,6 +1187,12 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 		list_del(&vma->obj->userfault_link);
 }
 
+static int
+__i915_request_await_bind(struct i915_request *rq, struct i915_vma *vma)
+{
+	return __i915_request_await_exclusive(rq, &vma->active);
+}
+
 int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq)
 {
 	int err;
@@ -1174,8 +1200,7 @@ int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq)
 	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 
 	/* Wait for the vma to be bound before we start! */
-	err = i915_request_await_active(rq, &vma->active,
-					I915_ACTIVE_AWAIT_EXCL);
+	err = __i915_request_await_bind(rq, vma);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index d0d01f909548..5b3a3c653454 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -237,8 +237,17 @@ static inline void i915_vma_unlock(struct i915_vma *vma)
 }
 
 int __must_check
-i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags);
-int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags);
+i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
+		u64 size, u64 alignment, u64 flags);
+
+static inline int __must_check
+i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
+{
+	return i915_vma_pin_ww(vma, NULL, size, alignment, flags);
+}
+
+int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
+		  u32 align, unsigned int flags);
 
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 40c590db3c76..e2aa5bc3a6e0 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -346,6 +346,25 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 		mask = BIT(INTEL_SUBPLATFORM_PORTF);
 	}
 
+	if (IS_TIGERLAKE(i915)) {
+		struct pci_dev *root, *pdev = i915->drm.pdev;
+
+		root = list_first_entry(&pdev->bus->devices, typeof(*root), bus_list);
+
+		drm_WARN_ON(&i915->drm, mask);
+		drm_WARN_ON(&i915->drm, (root->device & TGL_ROOT_DEVICE_MASK) !=
+			    TGL_ROOT_DEVICE_ID);
+
+		switch (root->device & TGL_ROOT_DEVICE_SKU_MASK) {
+		case TGL_ROOT_DEVICE_SKU_ULX:
+			mask = BIT(INTEL_SUBPLATFORM_ULX);
+			break;
+		case TGL_ROOT_DEVICE_SKU_ULT:
+			mask = BIT(INTEL_SUBPLATFORM_ULT);
+			break;
+		}
+	}
+
 	GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_BITS);
 
 	RUNTIME_INFO(i915)->platform_mask[pi] |= mask;
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index fd2385457ab6..6a3d607218aa 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -146,6 +146,7 @@ enum intel_ppgtt_type {
 	func(has_gmch); \
 	func(has_hdcp); \
 	func(has_hotplug); \
+	func(has_hti); \
 	func(has_ipc); \
 	func(has_modular_fia); \
 	func(has_overlay); \
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cfabbe0481ab..b4bd19266b8c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -100,12 +100,6 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
 		   DISP_FBC_MEMORY_WAKE);
-
-	if (IS_SKYLAKE(dev_priv)) {
-		/* WaDisableDopClockGating */
-		I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL)
-			   & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	}
 }
 
 static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -7223,12 +7217,12 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WaDisableSDEUnitClockGating:kbl */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
 		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableGamClockGating:kbl */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
 		I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
 
@@ -7251,6 +7245,10 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	gen9_init_clock_gating(dev_priv);
 
+	/* WaDisableDopClockGating:skl */
+	I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL) &
+		   ~GEN7_DOP_CLOCK_GATE_ENABLE);
+
 	/* WAC6entrylatency:skl */
 	I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
 		   FBC_LLC_FULLY_OPEN);
diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c
index 939a6caebb03..632b912b0bc9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_buddy.c
+++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c
@@ -8,8 +8,6 @@
 #include "../i915_selftest.h"
 #include "i915_random.h"
 
-#define SZ_8G (1ULL << 33)
-
 static void __igt_dump_block(struct i915_buddy_mm *mm,
 			     struct i915_buddy_block *block,
 			     bool buddy)
@@ -281,18 +279,22 @@ static int igt_check_mm(struct i915_buddy_mm *mm)
 static void igt_mm_config(u64 *size, u64 *chunk_size)
 {
 	I915_RND_STATE(prng);
-	u64 s, ms;
+	u32 s, ms;
 
 	/* Nothing fancy, just try to get an interesting bit pattern */
 
 	prandom_seed_state(&prng, i915_selftest.random_seed);
 
-	s = i915_prandom_u64_state(&prng) & (SZ_8G - 1);
-	ms = BIT_ULL(12 + (prandom_u32_state(&prng) % ilog2(s >> 12)));
-	s = max(s & -ms, ms);
+	/* Let size be a random number of pages up to 8 GB (2M pages) */
+	s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng);
+	/* Let the chunk size be a random power of 2 less than size */
+	ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng));
+	/* Round size down to the chunk size */
+	s &= -ms;
 
-	*chunk_size = ms;
-	*size = s;
+	/* Convert from pages to bytes */
+	*chunk_size = (u64)ms << 12;
+	*size = (u64)s << 12;
 }
 
 static int igt_buddy_alloc_smoke(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 88d400b9df88..23a6132c5f4e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -199,11 +199,52 @@ out:
 	return err;
 }
 
+static int igt_gem_ww_ctx(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj, *obj2;
+	struct i915_gem_ww_ctx ww;
+	int err = 0;
+
+	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	obj2 = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto put1;
+	}
+
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	/* Lock the objects, twice for good measure (-EALREADY handling) */
+	err = i915_gem_object_lock(obj, &ww);
+	if (!err)
+		err = i915_gem_object_lock_interruptible(obj, &ww);
+	if (!err)
+		err = i915_gem_object_lock_interruptible(obj2, &ww);
+	if (!err)
+		err = i915_gem_object_lock(obj2, &ww);
+
+	if (err == -EDEADLK) {
+		err = i915_gem_ww_ctx_backoff(&ww);
+		if (!err)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	i915_gem_object_put(obj2);
+put1:
+	i915_gem_object_put(obj);
+	return err;
+}
+
 int i915_gem_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_gem_suspend),
 		SUBTEST(igt_gem_hibernate),
+		SUBTEST(igt_gem_ww_ctx),
 	};
 
 	if (intel_gt_is_wedged(&i915->gt))
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 0016ffc7d914..af8205a2bd8f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -172,35 +172,45 @@ static int igt_ppgtt_alloc(void *arg)
 
 	/* Check we can allocate the entire range */
 	for (size = 4096; size <= limit; size <<= 2) {
-		err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size);
+		struct i915_vm_pt_stash stash = {};
+
+		err = i915_vm_alloc_pt_stash(&ppgtt->vm, &stash, size);
+		if (err)
+			goto err_ppgtt_cleanup;
+
+		err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
 		if (err) {
-			if (err == -ENOMEM) {
-				pr_info("[1] Ran out of memory for va_range [0 + %llx] [bit %d]\n",
-					size, ilog2(size));
-				err = 0; /* virtual space too large! */
-			}
+			i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 			goto err_ppgtt_cleanup;
 		}
 
+		ppgtt->vm.allocate_va_range(&ppgtt->vm, &stash, 0, size);
 		cond_resched();
 
 		ppgtt->vm.clear_range(&ppgtt->vm, 0, size);
+
+		i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 	}
 
 	/* Check we can incrementally allocate the entire range */
 	for (last = 0, size = 4096; size <= limit; last = size, size <<= 2) {
-		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
-						  last, size - last);
+		struct i915_vm_pt_stash stash = {};
+
+		err = i915_vm_alloc_pt_stash(&ppgtt->vm, &stash, size - last);
+		if (err)
+			goto err_ppgtt_cleanup;
+
+		err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
 		if (err) {
-			if (err == -ENOMEM) {
-				pr_info("[2] Ran out of memory for va_range [%llx + %llx] [bit %d]\n",
-					last, size - last, ilog2(size));
-				err = 0; /* virtual space too large! */
-			}
+			i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 			goto err_ppgtt_cleanup;
 		}
 
+		ppgtt->vm.allocate_va_range(&ppgtt->vm, &stash,
+					    last, size - last);
 		cond_resched();
+
+		i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 	}
 
 err_ppgtt_cleanup:
@@ -284,9 +294,23 @@ static int lowlevel_hole(struct i915_address_space *vm,
 				break;
 			}
 
-			if (vm->allocate_va_range &&
-			    vm->allocate_va_range(vm, addr, BIT_ULL(size)))
-				break;
+			if (vm->allocate_va_range) {
+				struct i915_vm_pt_stash stash = {};
+
+				if (i915_vm_alloc_pt_stash(vm, &stash,
+							   BIT_ULL(size)))
+					break;
+
+				if (i915_vm_pin_pt_stash(vm, &stash)) {
+					i915_vm_free_pt_stash(vm, &stash);
+					break;
+				}
+
+				vm->allocate_va_range(vm, &stash,
+						      addr, BIT_ULL(size));
+
+				i915_vm_free_pt_stash(vm, &stash);
+			}
 
 			mock_vma->pages = obj->mm.pages;
 			mock_vma->node.size = BIT_ULL(size);
@@ -1881,6 +1905,7 @@ static int igt_cs_tlb(void *arg)
 			continue;
 
 		while (!__igt_timeout(end_time, NULL)) {
+			struct i915_vm_pt_stash stash = {};
 			struct i915_request *rq;
 			u64 offset;
 
@@ -1888,10 +1913,6 @@ static int igt_cs_tlb(void *arg)
 						   0, vm->total - PAGE_SIZE,
 						   chunk_size, PAGE_SIZE);
 
-			err = vm->allocate_va_range(vm, offset, chunk_size);
-			if (err)
-				goto end;
-
 			memset32(result, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
 
 			vma = i915_vma_instance(bbe, vm, NULL);
@@ -1904,6 +1925,20 @@ static int igt_cs_tlb(void *arg)
 			if (err)
 				goto end;
 
+			err = i915_vm_alloc_pt_stash(vm, &stash, chunk_size);
+			if (err)
+				goto end;
+
+			err = i915_vm_pin_pt_stash(vm, &stash);
+			if (err) {
+				i915_vm_free_pt_stash(vm, &stash);
+				goto end;
+			}
+
+			vm->allocate_va_range(vm, &stash, offset, chunk_size);
+
+			i915_vm_free_pt_stash(vm, &stash);
+
 			/* Prime the TLB with the dummy pages */
 			for (i = 0; i < count; i++) {
 				vma->node.start = offset + i * PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index c2d001d9c0ec..debbac660519 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -307,7 +307,7 @@ static int live_noa_gpr(void *arg)
 	}
 
 	/* Poison the ce->vm so we detect writes not to the GGTT gt->scratch */
-	scratch = kmap(ce->vm->scratch[0].base.page);
+	scratch = kmap(__px_page(ce->vm->scratch[0]));
 	memset(scratch, POISON_FREE, PAGE_SIZE);
 
 	rq = intel_context_create_request(ce);
@@ -405,7 +405,7 @@ static int live_noa_gpr(void *arg)
 out_rq:
 	i915_request_put(rq);
 out_ce:
-	kunmap(ce->vm->scratch[0].base.page);
+	kunmap(__px_page(ce->vm->scratch[0]));
 	intel_context_put(ce);
 out:
 	stream_destroy(stream);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 57dd6f5122ee..3092ca763789 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -331,7 +331,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 		if (!wait) {
 			i915_sw_fence_commit(submit);
 			heap_fence_put(submit);
-			err = ENOMEM;
+			err = -ENOMEM;
 			break;
 		}
 
@@ -862,6 +862,8 @@ static int live_all_engines(void *arg)
 		goto out_free;
 	}
 
+	i915_vma_lock(batch);
+
 	idx = 0;
 	for_each_uabi_engine(engine, i915) {
 		request[idx] = intel_engine_create_kernel_request(engine);
@@ -872,11 +874,9 @@ static int live_all_engines(void *arg)
 			goto out_request;
 		}
 
-		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx], batch->obj, 0);
 		if (err == 0)
 			err = i915_vma_move_to_active(batch, request[idx], 0);
-		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
 		err = engine->emit_bb_start(request[idx],
@@ -891,6 +891,8 @@ static int live_all_engines(void *arg)
 		idx++;
 	}
 
+	i915_vma_unlock(batch);
+
 	idx = 0;
 	for_each_uabi_engine(engine, i915) {
 		if (i915_request_completed(request[idx])) {
@@ -981,12 +983,13 @@ static int live_sequential_engines(void *arg)
 			goto out_free;
 		}
 
+		i915_vma_lock(batch);
 		request[idx] = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(request[idx])) {
 			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed for %s with err=%d\n",
 			       __func__, engine->name, err);
-			goto out_request;
+			goto out_unlock;
 		}
 
 		if (prev) {
@@ -996,16 +999,14 @@ static int live_sequential_engines(void *arg)
 				i915_request_add(request[idx]);
 				pr_err("%s: Request await failed for %s with err=%d\n",
 				       __func__, engine->name, err);
-				goto out_request;
+				goto out_unlock;
 			}
 		}
 
-		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx],
 						batch->obj, false);
 		if (err == 0)
 			err = i915_vma_move_to_active(batch, request[idx], 0);
-		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
 		err = engine->emit_bb_start(request[idx],
@@ -1020,6 +1021,11 @@ static int live_sequential_engines(void *arg)
 
 		prev = request[idx];
 		idx++;
+
+out_unlock:
+		i915_vma_unlock(batch);
+		if (err)
+			goto out_request;
 	}
 
 	idx = 0;
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index af89c7fc8f59..88c5e9acb84c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -892,7 +892,7 @@ static int igt_vma_remapped_gtt(void *arg)
 			unsigned int x, y;
 			int err;
 
-			i915_gem_object_lock(obj);
+			i915_gem_object_lock(obj, NULL);
 			err = i915_gem_object_set_to_gtt_domain(obj, true);
 			i915_gem_object_unlock(obj);
 			if (err)
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 6e80d99048e4..93a38a323584 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -509,7 +509,7 @@ static int igt_lmem_write_cpu(void *arg)
 	if (err)
 		goto out_unpin;
 
-	i915_gem_object_lock(obj);
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_set_to_wc_domain(obj, true);
 	i915_gem_object_unlock(obj);
 	if (err)
@@ -522,9 +522,9 @@ static int igt_lmem_write_cpu(void *arg)
 		goto out_unpin;
 	}
 
-	/* We want to throw in a random width/align */
-	bytes[0] = igt_random_offset(&prng, 0, PAGE_SIZE, sizeof(u32),
-				     sizeof(u32));
+	/* A random multiple of u32, picked between [64, PAGE_SIZE - 64] */
+	bytes[0] = igt_random_offset(&prng, 64, PAGE_SIZE - 64, 0, sizeof(u32));
+	GEM_BUG_ON(!IS_ALIGNED(bytes[0], sizeof(u32)));
 
 	i = 0;
 	do {
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index b9810bf156c3..f127e633f7ca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -78,6 +78,7 @@ static void mock_device_release(struct drm_device *dev)
 	drm_mode_config_cleanup(&i915->drm);
 
 out:
+	i915_params_free(&i915->params);
 	put_device(&i915->drm.pdev->dev);
 	i915->drm.pdev = NULL;
 }
@@ -165,6 +166,8 @@ struct drm_i915_private *mock_gem_device(void)
 	i915->drm.pdev = pdev;
 	drmm_add_final_kfree(&i915->drm, i915);
 
+	i915_params_copy(&i915->params, &i915_modparams);
+
 	intel_runtime_pm_init_early(&i915->runtime_pm);
 
 	/* Using the global GTT may ask questions about KMS users, so prepare */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index b173086411ef..7270fc8ca801 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -38,14 +38,14 @@ static void mock_insert_entries(struct i915_address_space *vm,
 {
 }
 
-static int mock_bind_ppgtt(struct i915_address_space *vm,
-			   struct i915_vma *vma,
-			   enum i915_cache_level cache_level,
-			   u32 flags)
+static void mock_bind_ppgtt(struct i915_address_space *vm,
+			    struct i915_vm_pt_stash *stash,
+			    struct i915_vma *vma,
+			    enum i915_cache_level cache_level,
+			    u32 flags)
 {
 	GEM_BUG_ON(flags & I915_VMA_GLOBAL_BIND);
 	set_bit(I915_VMA_LOCAL_BIND_BIT, __i915_vma_flags(vma));
-	return 0;
 }
 
 static void mock_unbind_ppgtt(struct i915_address_space *vm,
@@ -74,9 +74,12 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 	ppgtt->vm.i915 = i915;
 	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
 	ppgtt->vm.file = ERR_PTR(-ENODEV);
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
 	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
 
+	ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
+
 	ppgtt->vm.clear_range = mock_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
 	ppgtt->vm.insert_entries = mock_insert_entries;
@@ -90,13 +93,12 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 	return ppgtt;
 }
 
-static int mock_bind_ggtt(struct i915_address_space *vm,
-			  struct i915_vma *vma,
-			  enum i915_cache_level cache_level,
-			  u32 flags)
+static void mock_bind_ggtt(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash,
+			   struct i915_vma *vma,
+			   enum i915_cache_level cache_level,
+			   u32 flags)
 {
-	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
-	return 0;
 }
 
 static void mock_unbind_ggtt(struct i915_address_space *vm,
@@ -116,6 +118,8 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 	ggtt->vm.total = 4096 * PAGE_SIZE;
 
+	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+
 	ggtt->vm.clear_range = mock_clear_range;
 	ggtt->vm.insert_page = mock_insert_page;
 	ggtt->vm.insert_entries = mock_insert_entries;
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 6776ebb3246d..8a4235d9d9f1 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -447,7 +447,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 		if (fb->pitches[1] != fb->pitches[2])
 			return -EINVAL;
 
-		/* fall-through */
+		fallthrough;
 	case DRM_FORMAT_NV12:
 	case DRM_FORMAT_NV16:
 		ubo = drm_plane_state_to_ubo(state);
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
index 5dab9c3d0a52..a3d1617d7c67 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
@@ -686,7 +686,7 @@ static void ingenic_drm_unbind_all(void *d)
 	component_unbind_all(priv->dev, &priv->drm);
 }
 
-static int ingenic_drm_bind(struct device *dev)
+static int ingenic_drm_bind(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	const struct jz_soc_info *soc_info;
@@ -821,7 +821,7 @@ static int ingenic_drm_bind(struct device *dev)
 			return ret;
 		}
 
-		if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) {
+		if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && has_components) {
 			ret = component_bind_all(dev, drm);
 			if (ret) {
 				if (ret != -EPROBE_DEFER)
@@ -952,6 +952,11 @@ err_pixclk_disable:
 	return ret;
 }
 
+static int ingenic_drm_bind_with_components(struct device *dev)
+{
+	return ingenic_drm_bind(dev, true);
+}
+
 static int compare_of(struct device *dev, void *data)
 {
 	return dev->of_node == data;
@@ -970,7 +975,7 @@ static void ingenic_drm_unbind(struct device *dev)
 }
 
 static const struct component_master_ops ingenic_master_ops = {
-	.bind = ingenic_drm_bind,
+	.bind = ingenic_drm_bind_with_components,
 	.unbind = ingenic_drm_unbind,
 };
 
@@ -981,16 +986,15 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	struct device_node *np;
 
 	if (!IS_ENABLED(CONFIG_DRM_INGENIC_IPU))
-		return ingenic_drm_bind(dev);
+		return ingenic_drm_bind(dev, false);
 
 	/* IPU is at port address 8 */
 	np = of_graph_get_remote_node(dev->of_node, 8, 0);
-	if (!np) {
-		dev_err(dev, "Unable to get IPU node\n");
-		return -EINVAL;
-	}
+	if (!np)
+		return ingenic_drm_bind(dev, false);
 
 	drm_of_component_match_add(dev, &match, compare_of, np);
+	of_node_put(np);
 
 	return component_master_add_with_match(dev, &ingenic_master_ops, match);
 }
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c
index f12e0271f166..ffc6b584dbf8 100644
--- a/drivers/gpu/drm/meson/meson_osd_afbcd.c
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c
@@ -205,7 +205,7 @@ static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format)
 		/* YTR is forbidden for non XBGR formats */
 		if (modifier & AFBC_FORMAT_MOD_YTR)
 			return -EINVAL;
-	/* fall through */
+		fallthrough;
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ABGR8888:
 		return MAFBC_FMT_RGBA8888;
diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c
index a8bcc70644df..1ffbbecafa22 100644
--- a/drivers/gpu/drm/meson/meson_overlay.c
+++ b/drivers/gpu/drm/meson/meson_overlay.c
@@ -654,7 +654,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane,
 			 priv->viu.vd1_addr2,
 			 priv->viu.vd1_stride2,
 			 priv->viu.vd1_height2);
-	/* fallthrough */
+		fallthrough;
 	case 2:
 		gem = drm_fb_cma_get_gem_obj(fb, 1);
 		priv->viu.vd1_addr1 = gem->paddr + fb->offsets[1];
@@ -666,7 +666,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane,
 			 priv->viu.vd1_addr1,
 			 priv->viu.vd1_stride1,
 			 priv->viu.vd1_height1);
-	/* fallthrough */
+		fallthrough;
 	case 1:
 		gem = drm_fb_cma_get_gem_obj(fb, 0);
 		priv->viu.vd1_addr0 = gem->paddr + fb->offsets[0];
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 6021f8d9efd1..48fa49f69d6d 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* NOTE: PM4/micro-engine firmware registers look to be the same
 	 * for a2xx and a3xx.. we could possibly push that part down to
 	 * adreno_gpu base class.  Or push both PM4 and PFP but
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 0a5ea9f56cb8..f6471145a7a6 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* setup access protection: */
 	gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007);
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index b9b26b2bf9c5..954753600625 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_A4XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* Load PM4: */
 	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data);
 	len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 9e63a190642c..91726da82ed6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -59,7 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
-			/* fall-thru */
+			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
 			/* copy commands into RB: */
 			obj = submit->bos[submit->cmd[i].idx].obj;
@@ -150,7 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
-			/* fall-thru */
+			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
@@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	a5xx_preempt_hw_init(gpu);
-
 	if (!adreno_is_a510(adreno_gpu))
 		a5xx_gpmu_ucode_init(gpu);
 
@@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	a5xx_preempt_hw_init(gpu);
+
 	/* Disable the interrupts through the initial bringup stage */
 	gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK);
 
@@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 
 	check_speed_bin(&pdev->dev);
 
-	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4);
+	/* Restricting nr_rings to 1 to temporarily disable preemption */
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a5xx_destroy(&(a5xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
index 54868d4e3958..1e5b1a15a70f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
@@ -31,6 +31,7 @@ struct a5xx_gpu {
 	struct msm_ringbuffer *next_ring;
 
 	struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS];
+	struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
 	struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
 	uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index 9cf9353a7ff1..9f3fe177b00e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	struct adreno_gpu *adreno_gpu = &a5xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	struct a5xx_preempt_record *ptr;
-	struct drm_gem_object *bo = NULL;
-	u64 iova = 0;
+	void *counters;
+	struct drm_gem_object *bo = NULL, *counters_bo = NULL;
+	u64 iova = 0, counters_iova = 0;
 
 	ptr = msm_gem_kernel_new(gpu->dev,
 		A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE,
-		MSM_BO_UNCACHED, gpu->aspace, &bo, &iova);
+		MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova);
 
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	/* The buffer to store counters needs to be unprivileged */
+	counters = msm_gem_kernel_new(gpu->dev,
+		A5XX_PREEMPT_COUNTER_SIZE,
+		MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova);
+	if (IS_ERR(counters)) {
+		msm_gem_kernel_put(bo, gpu->aspace, true);
+		return PTR_ERR(counters);
+	}
+
 	msm_gem_object_set_name(bo, "preempt");
+	msm_gem_object_set_name(counters_bo, "preempt_counters");
 
 	a5xx_gpu->preempt_bo[ring->id] = bo;
+	a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo;
 	a5xx_gpu->preempt_iova[ring->id] = iova;
 	a5xx_gpu->preempt[ring->id] = ptr;
 
@@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	ptr->data = 0;
 	ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT;
 	ptr->rptr_addr = rbmemptr(ring, rptr);
-	ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE;
+	ptr->counter = counters_iova;
 
 	return 0;
 }
@@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	int i;
 
-	for (i = 0; i < gpu->nr_rings; i++)
+	for (i = 0; i < gpu->nr_rings; i++) {
 		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
+			gpu->aspace, true);
+	}
 }
 
 void a5xx_preempt_init(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index b67b38c8fadf..e1c7bcd1b1eb 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -133,7 +133,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 
 	if (!gmu->legacy) {
 		a6xx_hfi_set_freq(gmu, perf_index);
-		icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+		dev_pm_opp_set_bw(&gpu->pdev->dev, opp);
 		pm_runtime_put(gmu->dev);
 		return;
 	}
@@ -157,11 +157,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 	if (ret)
 		dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
 
-	/*
-	 * Eventually we will want to scale the path vote with the frequency but
-	 * for now leave it at max so that the performance is nominal.
-	 */
-	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+	dev_pm_opp_set_bw(&gpu->pdev->dev, opp);
 	pm_runtime_put(gmu->dev);
 }
 
@@ -204,6 +200,16 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 {
 	int ret;
 	u32 val;
+	u32 mask, reset_val;
+
+	val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8);
+	if (val <= 0x20010004) {
+		mask = 0xffffffff;
+		reset_val = 0xbabeface;
+	} else {
+		mask = 0x1ff;
+		reset_val = 0x100;
+	}
 
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
 
@@ -215,7 +221,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0);
 
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val,
-		val == 0xbabeface, 100, 10000);
+		(val & mask) == reset_val, 100, 10000);
 
 	if (ret)
 		DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n");
@@ -602,7 +608,7 @@ static void a6xx_gmu_power_config(struct a6xx_gmu *gmu)
 		gmu_rmw(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0,
 			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_IFPC_ENABLE |
 			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_HM_POWER_COLLAPSE_ENABLE);
-		/* Fall through */
+		fallthrough;
 	case GMU_IDLE_STATE_SPTP:
 		gmu_write(gmu, REG_A6XX_GMU_PWR_COL_SPTPRAC_HYST,
 			GMU_PWR_COL_HYST);
@@ -845,10 +851,24 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
 	if (IS_ERR_OR_NULL(gpu_opp))
 		return;
 
+	gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */
 	a6xx_gmu_set_freq(gpu, gpu_opp);
 	dev_pm_opp_put(gpu_opp);
 }
 
+static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
+{
+	struct dev_pm_opp *gpu_opp;
+	unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index];
+
+	gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true);
+	if (IS_ERR_OR_NULL(gpu_opp))
+		return;
+
+	dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp);
+	dev_pm_opp_put(gpu_opp);
+}
+
 int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
@@ -882,7 +902,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	}
 
 	/* Set the bus quota to a reasonable value for boot */
-	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072));
+	a6xx_gmu_set_initial_bw(gpu, gmu);
 
 	/* Enable the GMU interrupt */
 	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0);
@@ -1051,7 +1071,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 		a6xx_gmu_shutdown(gmu);
 
 	/* Remove the bus vote */
-	icc_set_bw(gpu->icc_path, 0, 0);
+	dev_pm_opp_set_bw(&gpu->pdev->dev, NULL);
 
 	/*
 	 * Make sure the GX domain is off before turning off the GMU (CX)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c5a3e4d4c007..66a95e22b7b3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -117,7 +117,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
-			/* fall-thru */
+			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
@@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 			A6XX_PROTECT_RDONLY(0x980, 0x4));
 	gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));
 
-	if (adreno_is_a650(adreno_gpu)) {
+	/* Enable expanded apriv for targets that support it */
+	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
 			(1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1));
 	}
@@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		goto out;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
@@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu->registers = NULL;
 	adreno_gpu->reg_offsets = a6xx_register_offsets;
 
+	if (adreno_is_a650(adreno_gpu))
+		adreno_gpu->base.hw_apriv = true;
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 959656ad6987..b12f5b4a1bea 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -938,7 +938,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
 	}
 
-	a6xx_get_debugbus(gpu, a6xx_state);
+	if (snapshot_debugbus)
+		a6xx_get_debugbus(gpu, a6xx_state);
 
 	return  &a6xx_state->base;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 846fd5b54c23..2fb58b7098e4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -372,7 +372,7 @@ static const struct a6xx_indexed_registers {
 	u32 data;
 	u32 count;
 } a6xx_indexed_reglist[] = {
-	{ "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
+	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33 },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100 },
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 4e84f3c76f4f..9eeb46bf2a5d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -14,6 +14,10 @@ bool hang_debug = false;
 MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
 module_param_named(hang_debug, hang_debug, bool, 0600);
 
+bool snapshot_debugbus = false;
+MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)");
+module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600);
+
 static const struct adreno_info gpulist[] = {
 	{
 		.rev   = ADRENO_REV(2, 0, 0, 0),
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index e23641a5ec84..862dd35b27d3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -396,30 +396,10 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		ring->next = ring->start;
 
 		/* reset completed fence seqno: */
-		ring->memptrs->fence = ring->seqno;
+		ring->memptrs->fence = ring->fctx->completed_fence;
 		ring->memptrs->rptr = 0;
 	}
 
-	/*
-	 * Setup REG_CP_RB_CNTL.  The same value is used across targets (with
-	 * the excpetion of A430 that disables the RPTR shadow) - the cacluation
-	 * for the ringbuffer size and block size is moved to msm_gpu.h for the
-	 * pre-processor to deal with and the A430 variant is ORed in here
-	 */
-	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
-		MSM_GPU_RB_CNTL_DEFAULT |
-		(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
-
-	/* Setup ringbuffer address - use ringbuffer[0] for GPU init */
-	adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
-		REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova);
-
-	if (!adreno_is_a430(adreno_gpu)) {
-		adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
-			REG_ADRENO_CP_RB_RPTR_ADDR_HI,
-			rbmemptr(gpu->rb[0], rptr));
-	}
-
 	return 0;
 }
 
@@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu)
 static uint32_t get_rptr(struct adreno_gpu *adreno_gpu,
 		struct msm_ringbuffer *ring)
 {
-	if (adreno_is_a430(adreno_gpu))
-		return ring->memptrs->rptr = adreno_gpu_read(
-			adreno_gpu, REG_ADRENO_CP_RB_RPTR);
-	else
-		return ring->memptrs->rptr;
+	return ring->memptrs->rptr = adreno_gpu_read(
+		adreno_gpu, REG_ADRENO_CP_RB_RPTR);
 }
 
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu)
@@ -474,7 +451,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 			/* ignore if there has not been a ctx switch: */
 			if (priv->lastctx == ctx)
 				break;
-			/* fall-thru */
+			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT3(ring, adreno_is_a4xx(adreno_gpu) ?
 				CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 99bb468f5f24..e55abae365b5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -21,6 +21,8 @@
 #define REG_SKIP ~0
 #define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP
 
+extern bool snapshot_debugbus;
+
 /**
  * adreno_regs: List of registers that are used in across all
  * 3D devices. Each device type has different offset value for the same
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index f272a8d0f95b..c2729f71e2fa 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -827,7 +827,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 {
 	struct dpu_crtc *dpu_crtc;
 	struct drm_encoder *encoder;
-	bool request_bandwidth;
+	bool request_bandwidth = false;
 
 	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index a97f6d2e5a08..bd6def436c65 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -599,7 +599,10 @@ static int dpu_encoder_virt_atomic_check(
 	dpu_kms = to_dpu_kms(priv->kms);
 	mode = &crtc_state->mode;
 	adj_mode = &crtc_state->adjusted_mode;
-	global_state = dpu_kms_get_existing_global_state(dpu_kms);
+	global_state = dpu_kms_get_global_state(crtc_state->state);
+	if (IS_ERR(global_state))
+		return PTR_ERR(global_state);
+
 	trace_dpu_enc_atomic_check(DRMID(drm_enc));
 
 	/* perform atomic check on the first physical encoder (master) */
@@ -625,12 +628,15 @@ static int dpu_encoder_virt_atomic_check(
 	/* Reserve dynamic resources now. */
 	if (!ret) {
 		/*
-		 * Avoid reserving resources when mode set is pending. Topology
-		 * info may not be available to complete reservation.
+		 * Release and Allocate resources on every modeset
+		 * Dont allocate when active is false.
 		 */
 		if (drm_atomic_crtc_needs_modeset(crtc_state)) {
-			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
-					drm_enc, crtc_state, topology);
+			dpu_rm_release(global_state, drm_enc);
+
+			if (!crtc_state->active_changed || crtc_state->active)
+				ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
+						drm_enc, crtc_state, topology);
 		}
 	}
 
@@ -1181,7 +1187,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct dpu_global_state *global_state;
 	int i = 0;
 
 	if (!drm_enc) {
@@ -1200,7 +1205,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
-	global_state = dpu_kms_get_existing_global_state(dpu_kms);
 
 	trace_dpu_enc_disable(DRMID(drm_enc));
 
@@ -1230,8 +1234,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
 
-	dpu_rm_release(global_state, drm_enc);
-
 	mutex_unlock(&dpu_enc->enc_lock);
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 33f6c56f01ed..29e373d2e7b5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -866,9 +866,9 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		crtc_state = drm_atomic_get_new_crtc_state(state->state,
 							   state->crtc);
 
-	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale);
+	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale);
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale,
-					  pdpu->pipe_sblk->maxupscale << 16,
+					  pdpu->pipe_sblk->maxdwnscale << 16,
 					  true, true);
 	if (ret) {
 		DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 5ccfad794c6a..561bfa48841c 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -27,6 +27,34 @@ int msm_atomic_prepare_fb(struct drm_plane *plane,
 	return msm_framebuffer_prepare(new_state->fb, kms->aspace);
 }
 
+/*
+ * Helpers to control vblanks while we flush.. basically just to ensure
+ * that vblank accounting is switched on, so we get valid seqn/timestamp
+ * on pageflip events (if requested)
+ */
+
+static void vblank_get(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_get(crtc);
+	}
+}
+
+static void vblank_put(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_put(crtc);
+	}
+}
+
 static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 {
 	unsigned crtc_mask = BIT(crtc_idx);
@@ -44,6 +72,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 
 	kms->funcs->enable_commit(kms);
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -58,6 +88,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);
@@ -221,6 +253,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 	 */
 	kms->pending_crtc_mask &= ~crtc_mask;
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -235,6 +269,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 7d641c7e3514..79333842f70a 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1320,6 +1320,13 @@ static int msm_pdev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void msm_pdev_shutdown(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(drm);
+}
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
@@ -1332,6 +1339,7 @@ MODULE_DEVICE_TABLE(of, dt_match);
 static struct platform_driver msm_platform_driver = {
 	.probe      = msm_pdev_probe,
 	.remove     = msm_pdev_remove,
+	.shutdown   = msm_pdev_shutdown,
 	.driver     = {
 		.name   = "msm",
 		.of_match_table = dt_match,
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index d5645472b25d..57ddc9438351 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	memptrs = msm_gem_kernel_new(drm,
 		sizeof(struct msm_rbmemptrs) * nr_rings,
-		MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo,
+		check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo,
 		&memptrs_iova);
 
 	if (IS_ERR(memptrs)) {
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 0db117a7339b..37cffac4cbe3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -15,6 +15,7 @@
 #include "msm_drv.h"
 #include "msm_fence.h"
 #include "msm_ringbuffer.h"
+#include "msm_gem.h"
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
@@ -139,6 +140,8 @@ struct msm_gpu {
 	} devfreq;
 
 	struct msm_gpu_state *crashstate;
+	/* True if the hardware supports expanded apriv (a650 and newer) */
+	bool hw_apriv;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->dev->struct_mutex);
 }
 
+/*
+ * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
+ * support expanded privileges
+ */
+#define check_apriv(gpu, flags) \
+	(((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags))
+
+
 #endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index e397c44cc011..935bf9b1d941 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -27,7 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->id = id;
 
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova);
+		check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY),
+		gpu->aspace, &ring->bo, &ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c
index ffdd447d8706..22d10f328559 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dac.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c
@@ -419,7 +419,7 @@ static void nv04_dac_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 nouveau_encoder_connector_get(nv_encoder)->base.name,
+		 nv04_encoder_get_connector(nv_encoder)->base.name,
 		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index f9f4482c79b5..42687ea2a4ca 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -184,7 +184,8 @@ static bool nv04_dfp_mode_fixup(struct drm_encoder *encoder,
 				struct drm_display_mode *adjusted_mode)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_connector *nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	struct nouveau_connector *nv_connector =
+		nv04_encoder_get_connector(nv_encoder);
 
 	if (!nv_connector->native_mode ||
 	    nv_connector->scaling_mode == DRM_MODE_SCALE_NONE ||
@@ -478,7 +479,7 @@ static void nv04_dfp_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 nouveau_encoder_connector_get(nv_encoder)->base.name,
+		 nv04_encoder_get_connector(nv_encoder)->base.name,
 		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
@@ -591,7 +592,7 @@ static void nv04_dfp_restore(struct drm_encoder *encoder)
 
 	if (nv_encoder->dcb->type == DCB_OUTPUT_LVDS) {
 		struct nouveau_connector *connector =
-			nouveau_encoder_connector_get(nv_encoder);
+			nv04_encoder_get_connector(nv_encoder);
 
 		if (connector && connector->native_mode)
 			call_lvds_script(dev, nv_encoder->dcb, head,
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index 41d990cca685..7739f46470d3 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -35,9 +35,28 @@
 
 #include <nvif/if0004.h>
 
+struct nouveau_connector *
+nv04_encoder_get_connector(struct nouveau_encoder *encoder)
+{
+	struct drm_device *dev = to_drm_encoder(encoder)->dev;
+	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	struct nouveau_connector *nv_connector = NULL;
+
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		if (connector->encoder == to_drm_encoder(encoder))
+			nv_connector = nouveau_connector(connector);
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	return nv_connector;
+}
+
 static void
-nv04_display_fini(struct drm_device *dev, bool suspend)
+nv04_display_fini(struct drm_device *dev, bool runtime, bool suspend)
 {
+	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nv04_display *disp = nv04_display(dev);
 	struct drm_crtc *crtc;
 
@@ -49,6 +68,9 @@ nv04_display_fini(struct drm_device *dev, bool suspend)
 	if (nv_two_heads(dev))
 		NVWriteCRTC(dev, 1, NV_PCRTC_INTR_EN_0, 0);
 
+	if (!runtime)
+		cancel_work_sync(&drm->hpd_work);
+
 	if (!suspend)
 		return;
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.h b/drivers/gpu/drm/nouveau/dispnv04/disp.h
index 495d3284e876..5ace5e906949 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.h
@@ -6,6 +6,8 @@
 
 #include "nouveau_display.h"
 
+struct nouveau_encoder;
+
 enum nv04_fp_display_regs {
 	FP_DISPLAY_END,
 	FP_TOTAL,
@@ -93,6 +95,8 @@ nv04_display(struct drm_device *dev)
 
 /* nv04_display.c */
 int nv04_display_create(struct drm_device *);
+struct nouveau_connector *
+nv04_encoder_get_connector(struct nouveau_encoder *nv_encoder);
 
 /* nv04_crtc.c */
 int nv04_crtc_create(struct drm_device *, int index);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index b701a4d8fe76..3ba7b59580d5 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -172,7 +172,7 @@ static void nv04_tv_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 nouveau_encoder_connector_get(nv_encoder)->base.name,
+		 nv04_encoder_get_connector(nv_encoder)->base.name,
 		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 3a9489ed6544..be28e7bd7490 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -599,7 +599,7 @@ static void nv17_tv_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_INFO(drm, "Output %s is running on CRTC %d using output %c\n",
-		nouveau_encoder_connector_get(nv_encoder)->base.name,
+		nv04_encoder_get_connector(nv_encoder)->base.name,
 		nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
index ad1f09a143aa..248edf69e168 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
@@ -50,7 +50,10 @@ core507d_update(struct nv50_core *core, u32 *interlock, bool ntfy)
 					interlock[NV50_DISP_INTERLOCK_OVLY] |
 		  NVDEF(NV507D, UPDATE, NOT_DRIVER_FRIENDLY, FALSE) |
 		  NVDEF(NV507D, UPDATE, NOT_DRIVER_UNFRIENDLY, FALSE) |
-		  NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE));
+		  NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE),
+
+				SET_NOTIFIER_CONTROL,
+		  NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE));
 
 	return PUSH_KICK(push);
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c
index 9afe9a87bde0..814e5bd97446 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c
@@ -6,7 +6,7 @@
 #include "disp.h"
 #include "head.h"
 
-#include <nvif/push507c.h>
+#include <nvif/pushc37b.h>
 
 #include <nvhw/class/clc37d.h>
 
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 9dfb577f148a..852e1b56f3a7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -257,6 +257,12 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 	dmac->push->end = dmac->push->bgn;
 	dmac->max = 0x1000/4 - 1;
 
+	/* EVO channels are affected by a HW bug where the last 12 DWORDs
+	 * of the push buffer aren't able to be used safely.
+	 */
+	if (disp->oclass < GV100_DISP)
+		dmac->max -= 12;
+
 	args->pushbuf = nvif_handle(&dmac->_push.mem.object);
 
 	ret = nv50_chan_create(device, disp, oclass, head, data, size,
@@ -411,6 +417,40 @@ nv50_outp_atomic_check(struct drm_encoder *encoder,
 	return 0;
 }
 
+struct nouveau_connector *
+nv50_outp_get_new_connector(struct nouveau_encoder *outp,
+			    struct drm_atomic_state *state)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *connector_state;
+	struct drm_encoder *encoder = to_drm_encoder(outp);
+	int i;
+
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->best_encoder == encoder)
+			return nouveau_connector(connector);
+	}
+
+	return NULL;
+}
+
+struct nouveau_connector *
+nv50_outp_get_old_connector(struct nouveau_encoder *outp,
+			    struct drm_atomic_state *state)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *connector_state;
+	struct drm_encoder *encoder = to_drm_encoder(outp);
+	int i;
+
+	for_each_old_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->best_encoder == encoder)
+			return nouveau_connector(connector);
+	}
+
+	return NULL;
+}
+
 /******************************************************************************
  * DAC
  *****************************************************************************/
@@ -552,16 +592,31 @@ nv50_audio_component_get_eld(struct device *kdev, int port, int dev_id,
 	struct nouveau_drm *drm = nouveau_drm(drm_dev);
 	struct drm_encoder *encoder;
 	struct nouveau_encoder *nv_encoder;
-	struct nouveau_connector *nv_connector;
+	struct drm_connector *connector;
 	struct nouveau_crtc *nv_crtc;
+	struct drm_connector_list_iter conn_iter;
 	int ret = 0;
 
 	*enabled = false;
+
 	drm_for_each_encoder(encoder, drm->dev) {
+		struct nouveau_connector *nv_connector = NULL;
+
 		nv_encoder = nouveau_encoder(encoder);
-		nv_connector = nouveau_encoder_connector_get(nv_encoder);
+
+		drm_connector_list_iter_begin(drm_dev, &conn_iter);
+		drm_for_each_connector_iter(connector, &conn_iter) {
+			if (connector->state->best_encoder == encoder) {
+				nv_connector = nouveau_connector(connector);
+				break;
+			}
+		}
+		drm_connector_list_iter_end(&conn_iter);
+		if (!nv_connector)
+			continue;
+
 		nv_crtc = nouveau_crtc(encoder->crtc);
-		if (!nv_connector || !nv_crtc || nv_encoder->or != port ||
+		if (!nv_crtc || nv_encoder->or != port ||
 		    nv_crtc->index != dev_id)
 			continue;
 		*enabled = nv_encoder->audio;
@@ -572,6 +627,7 @@ nv50_audio_component_get_eld(struct device *kdev, int port, int dev_id,
 		}
 		break;
 	}
+
 	return ret;
 }
 
@@ -665,7 +721,8 @@ nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 }
 
 static void
-nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
+nv50_audio_enable(struct drm_encoder *encoder, struct drm_atomic_state *state,
+		  struct drm_display_mode *mode)
 {
 	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
@@ -686,7 +743,7 @@ nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 				     (0x0100 << nv_crtc->index),
 	};
 
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	nv_connector = nv50_outp_get_new_connector(nv_encoder, state);
 	if (!drm_detect_monitor_audio(nv_connector->edid))
 		return;
 
@@ -723,7 +780,8 @@ nv50_hdmi_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 }
 
 static void
-nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
+nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_atomic_state *state,
+		 struct drm_display_mode *mode)
 {
 	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
@@ -752,7 +810,7 @@ nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 	int ret;
 	int size;
 
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	nv_connector = nv50_outp_get_new_connector(nv_encoder, state);
 	if (!drm_detect_hdmi_monitor(nv_connector->edid))
 		return;
 
@@ -798,7 +856,7 @@ nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 		+ args.pwr.vendor_infoframe_length;
 	nvif_mthd(&disp->disp->object, 0, &args, size);
 
-	nv50_audio_enable(encoder, mode);
+	nv50_audio_enable(encoder, state, mode);
 
 	/* If SCDC is supported by the downstream monitor, update
 	 * divider / scrambling settings to what we programmed above.
@@ -827,16 +885,6 @@ nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 #define nv50_mstc(p) container_of((p), struct nv50_mstc, connector)
 #define nv50_msto(p) container_of((p), struct nv50_msto, encoder)
 
-struct nv50_mstm {
-	struct nouveau_encoder *outp;
-
-	struct drm_dp_mst_topology_mgr mgr;
-
-	bool modified;
-	bool disabled;
-	int links;
-};
-
 struct nv50_mstc {
 	struct nv50_mstm *mstm;
 	struct drm_dp_mst_port *port;
@@ -1216,7 +1264,10 @@ nv50_mstc_detect(struct drm_connector *connector,
 
 	ret = drm_dp_mst_detect_port(connector, ctx, mstc->port->mgr,
 				     mstc->port);
+	if (ret != connector_status_connected)
+		goto out;
 
+out:
 	pm_runtime_mark_last_busy(connector->dev->dev);
 	pm_runtime_put_autosuspend(connector->dev->dev);
 	return ret;
@@ -1365,41 +1416,51 @@ nv50_mstm = {
 	.add_connector = nv50_mstm_add_connector,
 };
 
-void
-nv50_mstm_service(struct nv50_mstm *mstm)
+bool
+nv50_mstm_service(struct nouveau_drm *drm,
+		  struct nouveau_connector *nv_connector,
+		  struct nv50_mstm *mstm)
 {
-	struct drm_dp_aux *aux = mstm ? mstm->mgr.aux : NULL;
-	bool handled = true;
-	int ret;
+	struct drm_dp_aux *aux = &nv_connector->aux;
+	bool handled = true, ret = true;
+	int rc;
 	u8 esi[8] = {};
 
-	if (!aux)
-		return;
-
 	while (handled) {
-		ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8);
-		if (ret != 8) {
-			drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
-			return;
+		rc = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8);
+		if (rc != 8) {
+			ret = false;
+			break;
 		}
 
 		drm_dp_mst_hpd_irq(&mstm->mgr, esi, &handled);
 		if (!handled)
 			break;
 
-		drm_dp_dpcd_write(aux, DP_SINK_COUNT_ESI + 1, &esi[1], 3);
+		rc = drm_dp_dpcd_write(aux, DP_SINK_COUNT_ESI + 1, &esi[1],
+				       3);
+		if (rc != 3) {
+			ret = false;
+			break;
+		}
 	}
+
+	if (!ret)
+		NV_DEBUG(drm, "Failed to handle ESI on %s: %d\n",
+			 nv_connector->base.name, rc);
+
+	return ret;
 }
 
 void
 nv50_mstm_remove(struct nv50_mstm *mstm)
 {
-	if (mstm)
-		drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
+	mstm->is_mst = false;
+	drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
 }
 
 static int
-nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state)
+nv50_mstm_enable(struct nv50_mstm *mstm, int state)
 {
 	struct nouveau_encoder *outp = mstm->outp;
 	struct {
@@ -1414,106 +1475,85 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state)
 	};
 	struct nouveau_drm *drm = nouveau_drm(outp->base.base.dev);
 	struct nvif_object *disp = &drm->display->disp.object;
-	int ret;
-
-	if (dpcd >= 0x12) {
-		/* Even if we're enabling MST, start with disabling the
-		 * branching unit to clear any sink-side MST topology state
-		 * that wasn't set by us
-		 */
-		ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, 0);
-		if (ret < 0)
-			return ret;
-
-		if (state) {
-			/* Now, start initializing */
-			ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL,
-						 DP_MST_EN);
-			if (ret < 0)
-				return ret;
-		}
-	}
 
 	return nvif_mthd(disp, 0, &args, sizeof(args));
 }
 
 int
-nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow)
+nv50_mstm_detect(struct nouveau_encoder *outp)
 {
+	struct nv50_mstm *mstm = outp->dp.mstm;
 	struct drm_dp_aux *aux;
 	int ret;
-	bool old_state, new_state;
-	u8 mstm_ctrl;
 
-	if (!mstm)
+	if (!mstm || !mstm->can_mst)
 		return 0;
 
-	mutex_lock(&mstm->mgr.lock);
-
-	old_state = mstm->mgr.mst_state;
-	new_state = old_state;
 	aux = mstm->mgr.aux;
 
-	if (old_state) {
-		/* Just check that the MST hub is still as we expect it */
-		ret = drm_dp_dpcd_readb(aux, DP_MSTM_CTRL, &mstm_ctrl);
-		if (ret < 0 || !(mstm_ctrl & DP_MST_EN)) {
-			DRM_DEBUG_KMS("Hub gone, disabling MST topology\n");
-			new_state = false;
-		}
-	} else if (dpcd[0] >= 0x12) {
-		ret = drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &dpcd[1]);
-		if (ret < 0)
-			goto probe_error;
-
-		if (!(dpcd[1] & DP_MST_CAP))
-			dpcd[0] = 0x11;
-		else
-			new_state = allow;
-	}
-
-	if (new_state == old_state) {
-		mutex_unlock(&mstm->mgr.lock);
-		return new_state;
-	}
-
-	ret = nv50_mstm_enable(mstm, dpcd[0], new_state);
-	if (ret)
-		goto probe_error;
-
-	mutex_unlock(&mstm->mgr.lock);
+	/* Clear any leftover MST state we didn't set ourselves by first
+	 * disabling MST if it was already enabled
+	 */
+	ret = drm_dp_dpcd_writeb(aux, DP_MSTM_CTRL, 0);
+	if (ret < 0)
+		return ret;
 
-	ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, new_state);
+	/* And start enabling */
+	ret = nv50_mstm_enable(mstm, true);
 	if (ret)
-		return nv50_mstm_enable(mstm, dpcd[0], 0);
+		return ret;
 
-	return new_state;
+	ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, true);
+	if (ret) {
+		nv50_mstm_enable(mstm, false);
+		return ret;
+	}
 
-probe_error:
-	mutex_unlock(&mstm->mgr.lock);
-	return ret;
+	mstm->is_mst = true;
+	return 1;
 }
 
 static void
-nv50_mstm_fini(struct nv50_mstm *mstm)
+nv50_mstm_fini(struct nouveau_encoder *outp)
 {
-	if (mstm && mstm->mgr.mst_state)
+	struct nv50_mstm *mstm = outp->dp.mstm;
+
+	if (!mstm)
+		return;
+
+	/* Don't change the MST state of this connector until we've finished
+	 * resuming, since we can't safely grab hpd_irq_lock in our resume
+	 * path to protect mstm->is_mst without potentially deadlocking
+	 */
+	mutex_lock(&outp->dp.hpd_irq_lock);
+	mstm->suspended = true;
+	mutex_unlock(&outp->dp.hpd_irq_lock);
+
+	if (mstm->is_mst)
 		drm_dp_mst_topology_mgr_suspend(&mstm->mgr);
 }
 
 static void
-nv50_mstm_init(struct nv50_mstm *mstm, bool runtime)
+nv50_mstm_init(struct nouveau_encoder *outp, bool runtime)
 {
-	int ret;
+	struct nv50_mstm *mstm = outp->dp.mstm;
+	int ret = 0;
 
-	if (!mstm || !mstm->mgr.mst_state)
+	if (!mstm)
 		return;
 
-	ret = drm_dp_mst_topology_mgr_resume(&mstm->mgr, !runtime);
-	if (ret == -1) {
-		drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
-		drm_kms_helper_hotplug_event(mstm->mgr.dev);
+	if (mstm->is_mst) {
+		ret = drm_dp_mst_topology_mgr_resume(&mstm->mgr, !runtime);
+		if (ret == -1)
+			nv50_mstm_remove(mstm);
 	}
+
+	mutex_lock(&outp->dp.hpd_irq_lock);
+	mstm->suspended = false;
+	mutex_unlock(&outp->dp.hpd_irq_lock);
+
+	if (ret == -1)
+		drm_kms_helper_hotplug_event(mstm->mgr.dev);
 }
 
 static void
@@ -1535,17 +1575,6 @@ nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
 	struct drm_device *dev = outp->base.base.dev;
 	struct nv50_mstm *mstm;
 	int ret;
-	u8 dpcd;
-
-	/* This is a workaround for some monitors not functioning
-	 * correctly in MST mode on initial module load.  I think
-	 * some bad interaction with the VBIOS may be responsible.
-	 *
-	 * A good ol' off and on again seems to work here ;)
-	 */
-	ret = drm_dp_dpcd_readb(aux, DP_DPCD_REV, &dpcd);
-	if (ret >= 0 && dpcd >= 0x12)
-		drm_dp_dpcd_writeb(aux, DP_MSTM_CTRL, 0);
 
 	if (!(mstm = *pmstm = kzalloc(sizeof(*mstm), GFP_KERNEL)))
 		return -ENOMEM;
@@ -1584,23 +1613,27 @@ nv50_sor_update(struct nouveau_encoder *nv_encoder, u8 head,
 }
 
 static void
-nv50_sor_disable(struct drm_encoder *encoder)
+nv50_sor_disable(struct drm_encoder *encoder,
+		 struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
+	struct nouveau_connector *nv_connector =
+		nv50_outp_get_old_connector(nv_encoder, state);
 
 	nv_encoder->crtc = NULL;
 
 	if (nv_crtc) {
-		struct nvkm_i2c_aux *aux = nv_encoder->aux;
+		struct drm_dp_aux *aux = &nv_connector->aux;
 		u8 pwr;
 
-		if (aux) {
-			int ret = nvkm_rdaux(aux, DP_SET_POWER, &pwr, 1);
+		if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
+			int ret = drm_dp_dpcd_readb(aux, DP_SET_POWER, &pwr);
+
 			if (ret == 0) {
 				pwr &= ~DP_SET_POWER_MASK;
 				pwr |=  DP_SET_POWER_D3;
-				nvkm_wraux(aux, DP_SET_POWER, &pwr, 1);
+				drm_dp_dpcd_writeb(aux, DP_SET_POWER, pwr);
 			}
 		}
 
@@ -1612,7 +1645,8 @@ nv50_sor_disable(struct drm_encoder *encoder)
 }
 
 static void
-nv50_sor_enable(struct drm_encoder *encoder)
+nv50_sor_enable(struct drm_encoder *encoder,
+		struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -1636,7 +1670,7 @@ nv50_sor_enable(struct drm_encoder *encoder)
 	u8 proto = NV507D_SOR_SET_CONTROL_PROTOCOL_CUSTOM;
 	u8 depth = NV837D_SOR_SET_CONTROL_PIXEL_DEPTH_DEFAULT;
 
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	nv_connector = nv50_outp_get_new_connector(nv_encoder, state);
 	nv_encoder->crtc = encoder->crtc;
 
 	if ((disp->disp->object.oclass == GT214_DISP ||
@@ -1663,7 +1697,7 @@ nv50_sor_enable(struct drm_encoder *encoder)
 			proto = NV507D_SOR_SET_CONTROL_PROTOCOL_SINGLE_TMDS_B;
 		}
 
-		nv50_hdmi_enable(&nv_encoder->base.base, mode);
+		nv50_hdmi_enable(&nv_encoder->base.base, state, mode);
 		break;
 	case DCB_OUTPUT_LVDS:
 		proto = NV507D_SOR_SET_CONTROL_PROTOCOL_LVDS_CUSTOM;
@@ -1704,7 +1738,7 @@ nv50_sor_enable(struct drm_encoder *encoder)
 		else
 			proto = NV887D_SOR_SET_CONTROL_PROTOCOL_DP_B;
 
-		nv50_audio_enable(encoder, mode);
+		nv50_audio_enable(encoder, state, mode);
 		break;
 	default:
 		BUG();
@@ -1717,8 +1751,8 @@ nv50_sor_enable(struct drm_encoder *encoder)
 static const struct drm_encoder_helper_funcs
 nv50_sor_help = {
 	.atomic_check = nv50_outp_atomic_check,
-	.enable = nv50_sor_enable,
-	.disable = nv50_sor_disable,
+	.atomic_enable = nv50_sor_enable,
+	.atomic_disable = nv50_sor_disable,
 };
 
 static void
@@ -1727,6 +1761,10 @@ nv50_sor_destroy(struct drm_encoder *encoder)
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	nv50_mstm_del(&nv_encoder->dp.mstm);
 	drm_encoder_cleanup(encoder);
+
+	if (nv_encoder->dcb->type == DCB_OUTPUT_DP)
+		mutex_destroy(&nv_encoder->dp.hpd_irq_lock);
+
 	kfree(encoder);
 }
 
@@ -1786,6 +1824,8 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 		struct nvkm_i2c_aux *aux =
 			nvkm_i2c_aux_find(i2c, dcbe->i2c_index);
 
+		mutex_init(&nv_encoder->dp.hpd_irq_lock);
+
 		if (aux) {
 			if (disp->disp->object.oclass < GF110_DISP) {
 				/* HW has no support for address-only
@@ -2077,7 +2117,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 			  outp->clr.mask, outp->set.mask);
 
 		if (outp->clr.mask) {
-			help->disable(encoder);
+			help->atomic_disable(encoder, state);
 			interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
 			if (outp->flush_disable) {
 				nv50_disp_atomic_commit_wndw(state, interlock);
@@ -2116,7 +2156,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 			  outp->set.mask, outp->clr.mask);
 
 		if (outp->set.mask) {
-			help->enable(encoder);
+			help->atomic_enable(encoder, state);
 			interlock[NV50_DISP_INTERLOCK_CORE] = 1;
 		}
 
@@ -2484,9 +2524,9 @@ nv50_disp_func = {
  *****************************************************************************/
 
 static void
-nv50_display_fini(struct drm_device *dev, bool suspend)
+nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend)
 {
-	struct nouveau_encoder *nv_encoder;
+	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_encoder *encoder;
 	struct drm_plane *plane;
 
@@ -2498,11 +2538,12 @@ nv50_display_fini(struct drm_device *dev, bool suspend)
 	}
 
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
-			nv_encoder = nouveau_encoder(encoder);
-			nv50_mstm_fini(nv_encoder->dp.mstm);
-		}
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST)
+			nv50_mstm_fini(nouveau_encoder(encoder));
 	}
+
+	if (!runtime)
+		cancel_work_sync(&drm->hpd_work);
 }
 
 static int
@@ -2519,7 +2560,7 @@ nv50_display_init(struct drm_device *dev, bool resume, bool runtime)
 		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
 			struct nouveau_encoder *nv_encoder =
 				nouveau_encoder(encoder);
-			nv50_mstm_init(nv_encoder->dp.mstm, runtime);
+			nv50_mstm_init(nv_encoder, runtime);
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/include/nvif/push507c.h b/drivers/gpu/drm/nouveau/include/nvif/push507c.h
index 889467f13fd9..7917bead4845 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/push507c.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/push507c.h
@@ -20,6 +20,6 @@
         PUSH_ASSERT(!((o) & ~DRF_SMASK(NV507C_DMA_JUMP_OFFSET)), "offset"); \
 	PUSH_DATA__((p), NVDEF(NV507C, DMA, OPCODE, JUMP) |                 \
 			 NVVAL(NV507C, DMA, JUMP_OFFSET, (o) >> 2),         \
-		    "jump 0x%08x - %s", (u32)(o), __func__);                \
+		    " jump 0x%08x - %s", (u32)(o), __func__);               \
 } while(0)
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 7674025a4bfe..49dd0cbc332f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -391,20 +391,6 @@ find_encoder(struct drm_connector *connector, int type)
 	return NULL;
 }
 
-struct nouveau_connector *
-nouveau_encoder_connector_get(struct nouveau_encoder *encoder)
-{
-	struct drm_device *dev = to_drm_encoder(encoder)->dev;
-	struct drm_connector *drm_connector;
-
-	list_for_each_entry(drm_connector, &dev->mode_config.connector_list, head) {
-		if (drm_connector->encoder == to_drm_encoder(encoder))
-			return nouveau_connector(drm_connector);
-	}
-
-	return NULL;
-}
-
 static void
 nouveau_connector_destroy(struct drm_connector *connector)
 {
@@ -435,7 +421,8 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 
 		switch (nv_encoder->dcb->type) {
 		case DCB_OUTPUT_DP:
-			ret = nouveau_dp_detect(nv_encoder);
+			ret = nouveau_dp_detect(nouveau_connector(connector),
+						nv_encoder);
 			if (ret == NOUVEAU_DP_MST)
 				return NULL;
 			else if (ret == NOUVEAU_DP_SST)
@@ -541,6 +528,17 @@ nouveau_connector_set_encoder(struct drm_connector *connector,
 	}
 }
 
+static void
+nouveau_connector_set_edid(struct nouveau_connector *nv_connector,
+			   struct edid *edid)
+{
+	struct edid *old_edid = nv_connector->edid;
+
+	drm_connector_update_edid_property(&nv_connector->base, edid);
+	kfree(old_edid);
+	nv_connector->edid = edid;
+}
+
 static enum drm_connector_status
 nouveau_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -554,13 +552,6 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 	int ret;
 	enum drm_connector_status conn_status = connector_status_disconnected;
 
-	/* Cleanup the previous EDID block. */
-	if (nv_connector->edid) {
-		drm_connector_update_edid_property(connector, NULL);
-		kfree(nv_connector->edid);
-		nv_connector->edid = NULL;
-	}
-
 	/* Outputs are only polled while runtime active, so resuming the
 	 * device here is unnecessary (and would deadlock upon runtime suspend
 	 * because it waits for polling to finish). We do however, want to
@@ -573,22 +564,23 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		ret = pm_runtime_get_sync(dev->dev);
 		if (ret < 0 && ret != -EACCES) {
 			pm_runtime_put_autosuspend(dev->dev);
+			nouveau_connector_set_edid(nv_connector, NULL);
 			return conn_status;
 		}
 	}
 
 	nv_encoder = nouveau_connector_ddc_detect(connector);
 	if (nv_encoder && (i2c = nv_encoder->i2c) != NULL) {
+		struct edid *new_edid;
+
 		if ((vga_switcheroo_handler_flags() &
 		     VGA_SWITCHEROO_CAN_SWITCH_DDC) &&
 		    nv_connector->type == DCB_CONNECTOR_LVDS)
-			nv_connector->edid = drm_get_edid_switcheroo(connector,
-								     i2c);
+			new_edid = drm_get_edid_switcheroo(connector, i2c);
 		else
-			nv_connector->edid = drm_get_edid(connector, i2c);
+			new_edid = drm_get_edid(connector, i2c);
 
-		drm_connector_update_edid_property(connector,
-							nv_connector->edid);
+		nouveau_connector_set_edid(nv_connector, new_edid);
 		if (!nv_connector->edid) {
 			NV_ERROR(drm, "DDC responded, but no EDID for %s\n",
 				 connector->name);
@@ -622,6 +614,8 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		conn_status = connector_status_connected;
 		drm_dp_cec_set_edid(&nv_connector->aux, nv_connector->edid);
 		goto out;
+	} else {
+		nouveau_connector_set_edid(nv_connector, NULL);
 	}
 
 	nv_encoder = nouveau_connector_of_detect(connector);
@@ -646,10 +640,11 @@ detect_analog:
 			conn_status = connector_status_connected;
 			goto out;
 		}
-
 	}
 
  out:
+	if (!nv_connector->edid)
+		drm_dp_cec_unset_edid(&nv_connector->aux);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -664,18 +659,12 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_encoder *nv_encoder = NULL;
+	struct edid *edid = NULL;
 	enum drm_connector_status status = connector_status_disconnected;
 
-	/* Cleanup the previous EDID block. */
-	if (nv_connector->edid) {
-		drm_connector_update_edid_property(connector, NULL);
-		kfree(nv_connector->edid);
-		nv_connector->edid = NULL;
-	}
-
 	nv_encoder = find_encoder(connector, DCB_OUTPUT_LVDS);
 	if (!nv_encoder)
-		return connector_status_disconnected;
+		goto out;
 
 	/* Try retrieving EDID via DDC */
 	if (!drm->vbios.fp_no_ddc) {
@@ -694,7 +683,8 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 	 * valid - it's not (rh#613284)
 	 */
 	if (nv_encoder->dcb->lvdsconf.use_acpi_for_edid) {
-		if ((nv_connector->edid = nouveau_acpi_edid(dev, connector))) {
+		edid = nouveau_acpi_edid(dev, connector);
+		if (edid) {
 			status = connector_status_connected;
 			goto out;
 		}
@@ -714,12 +704,10 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 	 * stored for the panel stored in them.
 	 */
 	if (!drm->vbios.fp_no_ddc) {
-		struct edid *edid =
-			(struct edid *)nouveau_bios_embedded_edid(dev);
+		edid = (struct edid *)nouveau_bios_embedded_edid(dev);
 		if (edid) {
-			nv_connector->edid =
-					kmemdup(edid, EDID_LENGTH, GFP_KERNEL);
-			if (nv_connector->edid)
+			edid = kmemdup(edid, EDID_LENGTH, GFP_KERNEL);
+			if (edid)
 				status = connector_status_connected;
 		}
 	}
@@ -732,7 +720,7 @@ out:
 		status = connector_status_unknown;
 #endif
 
-	drm_connector_update_edid_property(connector, nv_connector->edid);
+	nouveau_connector_set_edid(nv_connector, edid);
 	nouveau_connector_set_encoder(connector, nv_encoder);
 	return status;
 }
@@ -1150,59 +1138,39 @@ nouveau_connector_funcs_lvds = {
 	.early_unregister = nouveau_connector_early_unregister,
 };
 
+void
+nouveau_connector_hpd(struct drm_connector *connector)
+{
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	u32 mask = drm_connector_mask(connector);
+
+	mutex_lock(&drm->hpd_lock);
+	if (!(drm->hpd_pending & mask)) {
+		drm->hpd_pending |= mask;
+		schedule_work(&drm->hpd_work);
+	}
+	mutex_unlock(&drm->hpd_lock);
+}
+
 static int
 nouveau_connector_hotplug(struct nvif_notify *notify)
 {
 	struct nouveau_connector *nv_connector =
 		container_of(notify, typeof(*nv_connector), hpd);
 	struct drm_connector *connector = &nv_connector->base;
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	struct drm_device *dev = connector->dev;
+	struct nouveau_drm *drm = nouveau_drm(dev);
 	const struct nvif_notify_conn_rep_v0 *rep = notify->data;
-	const char *name = connector->name;
-	struct nouveau_encoder *nv_encoder;
-	int ret;
 	bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG);
 
 	if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) {
-		NV_DEBUG(drm, "service %s\n", name);
-		drm_dp_cec_irq(&nv_connector->aux);
-		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP)))
-			nv50_mstm_service(nv_encoder->dp.mstm);
-
+		nouveau_dp_irq(drm, nv_connector);
 		return NVIF_NOTIFY_KEEP;
 	}
 
-	ret = pm_runtime_get(drm->dev->dev);
-	if (ret == 0) {
-		/* We can't block here if there's a pending PM request
-		 * running, as we'll deadlock nouveau_display_fini() when it
-		 * calls nvif_put() on our nvif_notify struct. So, simply
-		 * defer the hotplug event until the device finishes resuming
-		 */
-		NV_DEBUG(drm, "Deferring HPD on %s until runtime resume\n",
-			 name);
-		schedule_work(&drm->hpd_work);
-
-		pm_runtime_put_noidle(drm->dev->dev);
-		return NVIF_NOTIFY_KEEP;
-	} else if (ret != 1 && ret != -EACCES) {
-		NV_WARN(drm, "HPD on %s dropped due to RPM failure: %d\n",
-			name, ret);
-		return NVIF_NOTIFY_DROP;
-	}
-
-	if (!plugged)
-		drm_dp_cec_unset_edid(&nv_connector->aux);
-	NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
-	if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) {
-		if (!plugged)
-			nv50_mstm_remove(nv_encoder->dp.mstm);
-	}
-
-	drm_helper_hpd_irq_event(connector->dev);
+	NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", connector->name);
+	nouveau_connector_hpd(connector);
 
-	pm_runtime_mark_last_busy(drm->dev->dev);
-	pm_runtime_put_autosuspend(drm->dev->dev);
 	return NVIF_NOTIFY_KEEP;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index d6de5cb8e223..d0b859c4a80e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -187,6 +187,7 @@ nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc)
 
 struct drm_connector *
 nouveau_connector_create(struct drm_device *, const struct dcb_output *);
+void nouveau_connector_hpd(struct drm_connector *connector);
 
 extern int nouveau_tv_disable;
 extern int nouveau_ignorelid;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 5f31b11ac2e7..bceb48a2dfca 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -457,16 +457,70 @@ static struct nouveau_drm_prop_enum_list dither_depth[] = {
 	}                                                                      \
 } while(0)
 
+void
+nouveau_display_hpd_resume(struct drm_device *dev)
+{
+	struct nouveau_drm *drm = nouveau_drm(dev);
+
+	mutex_lock(&drm->hpd_lock);
+	drm->hpd_pending = ~0;
+	mutex_unlock(&drm->hpd_lock);
+
+	schedule_work(&drm->hpd_work);
+}
+
 static void
 nouveau_display_hpd_work(struct work_struct *work)
 {
 	struct nouveau_drm *drm = container_of(work, typeof(*drm), hpd_work);
+	struct drm_device *dev = drm->dev;
+	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	u32 pending;
+	bool changed = false;
+
+	pm_runtime_get_sync(dev->dev);
 
-	pm_runtime_get_sync(drm->dev->dev);
+	mutex_lock(&drm->hpd_lock);
+	pending = drm->hpd_pending;
+	drm->hpd_pending = 0;
+	mutex_unlock(&drm->hpd_lock);
 
-	drm_helper_hpd_irq_event(drm->dev);
+	/* Nothing to do, exit early without updating the last busy counter */
+	if (!pending)
+		goto noop;
+
+	mutex_lock(&dev->mode_config.mutex);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
+		enum drm_connector_status old_status = connector->status;
+		u64 old_epoch_counter = connector->epoch_counter;
+
+		if (!(pending & drm_connector_mask(connector)))
+			continue;
+
+		connector->status = drm_helper_probe_detect(connector, NULL,
+							    false);
+		if (old_epoch_counter == connector->epoch_counter)
+			continue;
+
+		changed = true;
+		drm_dbg_kms(dev, "[CONNECTOR:%d:%s] status updated from %s to %s (epoch counter %llu->%llu)\n",
+			    connector->base.id, connector->name,
+			    drm_get_connector_status_name(old_status),
+			    drm_get_connector_status_name(connector->status),
+			    old_epoch_counter, connector->epoch_counter);
+	}
+
+	drm_connector_list_iter_end(&conn_iter);
+	mutex_unlock(&dev->mode_config.mutex);
+
+	if (changed)
+		drm_kms_helper_hotplug_event(dev);
 
 	pm_runtime_mark_last_busy(drm->dev->dev);
+noop:
 	pm_runtime_put_sync(drm->dev->dev);
 }
 
@@ -490,12 +544,11 @@ nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val,
 				 */
 				pm_runtime_put_autosuspend(drm->dev->dev);
 			} else if (ret == 0) {
-				/* This may be the only indication we receive
-				 * of a connector hotplug on a runtime
-				 * suspended GPU, schedule hpd_work to check.
+				/* We've started resuming the GPU already, so
+				 * it will handle scheduling a full reprobe
+				 * itself
 				 */
 				NV_DEBUG(drm, "ACPI requested connector reprobe\n");
-				schedule_work(&drm->hpd_work);
 				pm_runtime_put_noidle(drm->dev->dev);
 			} else {
 				NV_WARN(drm, "Dropped ACPI reprobe event due to RPM error: %d\n",
@@ -569,7 +622,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime)
 		cancel_work_sync(&drm->hpd_work);
 
 	drm_kms_helper_poll_disable(dev);
-	disp->fini(dev, suspend);
+	disp->fini(dev, runtime, suspend);
 }
 
 static void
@@ -686,6 +739,7 @@ nouveau_display_create(struct drm_device *dev)
 	}
 
 	INIT_WORK(&drm->hpd_work, nouveau_display_hpd_work);
+	mutex_init(&drm->hpd_lock);
 #ifdef CONFIG_ACPI
 	drm->acpi_nb.notifier_call = nouveau_display_acpi_ntfy;
 	register_acpi_notifier(&drm->acpi_nb);
@@ -705,9 +759,10 @@ void
 nouveau_display_destroy(struct drm_device *dev)
 {
 	struct nouveau_display *disp = nouveau_display(dev);
+	struct nouveau_drm *drm = nouveau_drm(dev);
 
 #ifdef CONFIG_ACPI
-	unregister_acpi_notifier(&nouveau_drm(dev)->acpi_nb);
+	unregister_acpi_notifier(&drm->acpi_nb);
 #endif
 
 	drm_kms_helper_poll_fini(dev);
@@ -719,6 +774,7 @@ nouveau_display_destroy(struct drm_device *dev)
 	nvif_disp_dtor(&disp->disp);
 
 	nouveau_drm(dev)->display = NULL;
+	mutex_destroy(&drm->hpd_lock);
 	kfree(disp);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h
index 6e0d900441d6..616c43427059 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.h
+++ b/drivers/gpu/drm/nouveau/nouveau_display.h
@@ -18,7 +18,7 @@ struct nouveau_display {
 	void *priv;
 	void (*dtor)(struct drm_device *);
 	int  (*init)(struct drm_device *, bool resume, bool runtime);
-	void (*fini)(struct drm_device *, bool suspend);
+	void (*fini)(struct drm_device *, bool suspend, bool runtime);
 
 	struct nvif_disp disp;
 
@@ -45,6 +45,7 @@ nouveau_display(struct drm_device *dev)
 int  nouveau_display_create(struct drm_device *dev);
 void nouveau_display_destroy(struct drm_device *dev);
 int  nouveau_display_init(struct drm_device *dev, bool resume, bool runtime);
+void nouveau_display_hpd_resume(struct drm_device *dev);
 void nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime);
 int  nouveau_display_suspend(struct drm_device *dev, bool runtime);
 void nouveau_display_resume(struct drm_device *dev, bool runtime);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 8a0f7994e1ae..810bf6956568 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -36,50 +36,123 @@ MODULE_PARM_DESC(mst, "Enable DisplayPort multi-stream (default: enabled)");
 static int nouveau_mst = 1;
 module_param_named(mst, nouveau_mst, int, 0400);
 
-static void
-nouveau_dp_probe_oui(struct drm_device *dev, struct nvkm_i2c_aux *aux, u8 *dpcd)
+static bool
+nouveau_dp_has_sink_count(struct drm_connector *connector,
+			  struct nouveau_encoder *outp)
 {
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	u8 buf[3];
-
-	if (!(dpcd[DP_DOWN_STREAM_PORT_COUNT] & DP_OUI_SUPPORT))
-		return;
-
-	if (!nvkm_rdaux(aux, DP_SINK_OUI, buf, 3))
-		NV_DEBUG(drm, "Sink OUI: %02hx%02hx%02hx\n",
-			     buf[0], buf[1], buf[2]);
-
-	if (!nvkm_rdaux(aux, DP_BRANCH_OUI, buf, 3))
-		NV_DEBUG(drm, "Branch OUI: %02hx%02hx%02hx\n",
-			     buf[0], buf[1], buf[2]);
+	return drm_dp_read_sink_count_cap(connector, outp->dp.dpcd, &outp->dp.desc);
+}
 
+static enum drm_connector_status
+nouveau_dp_probe_dpcd(struct nouveau_connector *nv_connector,
+		      struct nouveau_encoder *outp)
+{
+	struct drm_connector *connector = &nv_connector->base;
+	struct drm_dp_aux *aux = &nv_connector->aux;
+	struct nv50_mstm *mstm = NULL;
+	enum drm_connector_status status = connector_status_disconnected;
+	int ret;
+	u8 *dpcd = outp->dp.dpcd;
+
+	ret = drm_dp_read_dpcd_caps(aux, dpcd);
+	if (ret < 0)
+		goto out;
+
+	ret = drm_dp_read_desc(aux, &outp->dp.desc, drm_dp_is_branch(dpcd));
+	if (ret < 0)
+		goto out;
+
+	if (nouveau_mst) {
+		mstm = outp->dp.mstm;
+		if (mstm)
+			mstm->can_mst = drm_dp_read_mst_cap(aux, dpcd);
+	}
+
+	if (nouveau_dp_has_sink_count(connector, outp)) {
+		ret = drm_dp_read_sink_count(aux);
+		if (ret < 0)
+			goto out;
+
+		outp->dp.sink_count = ret;
+
+		/*
+		 * Dongle connected, but no display. Don't bother reading
+		 * downstream port info
+		 */
+		if (!outp->dp.sink_count)
+			return connector_status_disconnected;
+	}
+
+	ret = drm_dp_read_downstream_info(aux, dpcd,
+					  outp->dp.downstream_ports);
+	if (ret < 0)
+		goto out;
+
+	status = connector_status_connected;
+out:
+	if (status != connector_status_connected) {
+		/* Clear any cached info */
+		outp->dp.sink_count = 0;
+	}
+	return status;
 }
 
 int
-nouveau_dp_detect(struct nouveau_encoder *nv_encoder)
+nouveau_dp_detect(struct nouveau_connector *nv_connector,
+		  struct nouveau_encoder *nv_encoder)
 {
 	struct drm_device *dev = nv_encoder->base.base.dev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nvkm_i2c_aux *aux;
-	u8 dpcd[8];
-	int ret;
-
-	aux = nv_encoder->aux;
-	if (!aux)
-		return -ENODEV;
-
-	ret = nvkm_rdaux(aux, DP_DPCD_REV, dpcd, sizeof(dpcd));
-	if (ret)
-		return ret;
+	struct drm_connector *connector = &nv_connector->base;
+	struct nv50_mstm *mstm = nv_encoder->dp.mstm;
+	enum drm_connector_status status;
+	u8 *dpcd = nv_encoder->dp.dpcd;
+	int ret = NOUVEAU_DP_NONE;
+
+	/* If we've already read the DPCD on an eDP device, we don't need to
+	 * reread it as it won't change
+	 */
+	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP &&
+	    dpcd[DP_DPCD_REV] != 0)
+		return NOUVEAU_DP_SST;
 
-	nv_encoder->dp.link_bw = 27000 * dpcd[1];
-	nv_encoder->dp.link_nr = dpcd[2] & DP_MAX_LANE_COUNT_MASK;
+	mutex_lock(&nv_encoder->dp.hpd_irq_lock);
+	if (mstm) {
+		/* If we're not ready to handle MST state changes yet, just
+		 * report the last status of the connector. We'll reprobe it
+		 * once we've resumed.
+		 */
+		if (mstm->suspended) {
+			if (mstm->is_mst)
+				ret = NOUVEAU_DP_MST;
+			else if (connector->status ==
+				 connector_status_connected)
+				ret = NOUVEAU_DP_SST;
+
+			goto out;
+		}
+	}
+
+	status = nouveau_dp_probe_dpcd(nv_connector, nv_encoder);
+	if (status == connector_status_disconnected)
+		goto out;
+
+	/* If we're in MST mode, we're done here */
+	if (mstm && mstm->can_mst && mstm->is_mst) {
+		ret = NOUVEAU_DP_MST;
+		goto out;
+	}
+
+	nv_encoder->dp.link_bw = 27000 * dpcd[DP_MAX_LINK_RATE];
+	nv_encoder->dp.link_nr =
+		dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
 
 	NV_DEBUG(drm, "display: %dx%d dpcd 0x%02x\n",
-		     nv_encoder->dp.link_nr, nv_encoder->dp.link_bw, dpcd[0]);
+		 nv_encoder->dp.link_nr, nv_encoder->dp.link_bw,
+		 dpcd[DP_DPCD_REV]);
 	NV_DEBUG(drm, "encoder: %dx%d\n",
-		     nv_encoder->dcb->dpconf.link_nr,
-		     nv_encoder->dcb->dpconf.link_bw);
+		 nv_encoder->dcb->dpconf.link_nr,
+		 nv_encoder->dcb->dpconf.link_bw);
 
 	if (nv_encoder->dcb->dpconf.link_nr < nv_encoder->dp.link_nr)
 		nv_encoder->dp.link_nr = nv_encoder->dcb->dpconf.link_nr;
@@ -87,23 +160,68 @@ nouveau_dp_detect(struct nouveau_encoder *nv_encoder)
 		nv_encoder->dp.link_bw = nv_encoder->dcb->dpconf.link_bw;
 
 	NV_DEBUG(drm, "maximum: %dx%d\n",
-		     nv_encoder->dp.link_nr, nv_encoder->dp.link_bw);
+		 nv_encoder->dp.link_nr, nv_encoder->dp.link_bw);
+
+	if (mstm && mstm->can_mst) {
+		ret = nv50_mstm_detect(nv_encoder);
+		if (ret == 1) {
+			ret = NOUVEAU_DP_MST;
+			goto out;
+		} else if (ret != 0) {
+			goto out;
+		}
+	}
+	ret = NOUVEAU_DP_SST;
+
+out:
+	if (mstm && !mstm->suspended && ret != NOUVEAU_DP_MST)
+		nv50_mstm_remove(mstm);
+
+	mutex_unlock(&nv_encoder->dp.hpd_irq_lock);
+	return ret;
+}
 
-	nouveau_dp_probe_oui(dev, aux, dpcd);
+void nouveau_dp_irq(struct nouveau_drm *drm,
+		    struct nouveau_connector *nv_connector)
+{
+	struct drm_connector *connector = &nv_connector->base;
+	struct nouveau_encoder *outp = find_encoder(connector, DCB_OUTPUT_DP);
+	struct nv50_mstm *mstm;
+	int ret;
+	bool send_hpd = false;
 
-	ret = nv50_mstm_detect(nv_encoder->dp.mstm, dpcd, nouveau_mst);
-	if (ret == 1)
-		return NOUVEAU_DP_MST;
-	if (ret == 0)
-		return NOUVEAU_DP_SST;
-	return ret;
+	if (!outp)
+		return;
+
+	mstm = outp->dp.mstm;
+	NV_DEBUG(drm, "service %s\n", connector->name);
+
+	mutex_lock(&outp->dp.hpd_irq_lock);
+
+	if (mstm && mstm->is_mst) {
+		if (!nv50_mstm_service(drm, nv_connector, mstm))
+			send_hpd = true;
+	} else {
+		drm_dp_cec_irq(&nv_connector->aux);
+
+		if (nouveau_dp_has_sink_count(connector, outp)) {
+			ret = drm_dp_read_sink_count(&nv_connector->aux);
+			if (ret != outp->dp.sink_count)
+				send_hpd = true;
+			if (ret >= 0)
+				outp->dp.sink_count = ret;
+		}
+	}
+
+	mutex_unlock(&outp->dp.hpd_irq_lock);
+
+	if (send_hpd)
+		nouveau_connector_hpd(connector);
 }
 
 /* TODO:
  * - Use the minimum possible BPC here, once we add support for the max bpc
  *   property.
- * - Validate the mode against downstream port caps (see
- *   drm_dp_downstream_max_clock())
  * - Validate against the DP caps advertised by the GPU (we don't check these
  *   yet)
  */
@@ -114,15 +232,19 @@ nv50_dp_mode_valid(struct drm_connector *connector,
 		   unsigned *out_clock)
 {
 	const unsigned min_clock = 25000;
-	unsigned max_clock, clock;
+	unsigned max_clock, ds_clock, clock;
 	enum drm_mode_status ret;
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace)
 		return MODE_NO_INTERLACE;
 
 	max_clock = outp->dp.link_nr * outp->dp.link_bw;
-	clock = mode->clock * (connector->display_info.bpc * 3) / 10;
+	ds_clock = drm_dp_downstream_max_clock(outp->dp.dpcd,
+					       outp->dp.downstream_ports);
+	if (ds_clock)
+		max_clock = min(max_clock, ds_clock);
 
+	clock = mode->clock * (connector->display_info.bpc * 3) / 10;
 	ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
 					    &clock);
 	if (out_clock)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 22d246acc5e5..42fc5c813a9b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -953,7 +953,7 @@ nouveau_pmops_resume(struct device *dev)
 	ret = nouveau_do_resume(drm_dev, false);
 
 	/* Monitors may have been connected / disconnected during suspend */
-	schedule_work(&nouveau_drm(drm_dev)->hpd_work);
+	nouveau_display_hpd_resume(drm_dev);
 
 	return ret;
 }
@@ -1036,7 +1036,7 @@ nouveau_pmops_runtime_resume(struct device *dev)
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 
 	/* Monitors may have been connected / disconnected during suspend */
-	schedule_work(&nouveau_drm(drm_dev)->hpd_work);
+	nouveau_display_hpd_resume(drm_dev);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 26a2c1090045..b8025507a9e4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -200,6 +200,8 @@ struct nouveau_drm {
 	struct nvbios vbios;
 	struct nouveau_display *display;
 	struct work_struct hpd_work;
+	struct mutex hpd_lock;
+	u32 hpd_pending;
 	struct work_struct fbcon_work;
 	int fbcon_new_state;
 #ifdef CONFIG_ACPI
diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h
index a72c412ac8b1..21937f1c7dd9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_encoder.h
+++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h
@@ -33,6 +33,7 @@
 #include <drm/drm_dp_mst_helper.h>
 #include "dispnv04/disp.h"
 struct nv50_head_atom;
+struct nouveau_connector;
 
 #define NV_DPMS_CLEARED 0x80
 
@@ -64,6 +65,17 @@ struct nouveau_encoder {
 			struct nv50_mstm *mstm;
 			int link_nr;
 			int link_bw;
+
+			/* Protects DP state that needs to be accessed outside
+			 * connector reprobing contexts
+			 */
+			struct mutex hpd_irq_lock;
+
+			u8 dpcd[DP_RECEIVER_CAP_SIZE];
+			u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
+			struct drm_dp_desc desc;
+
+			u8 sink_count;
 		} dp;
 	};
 
@@ -77,6 +89,21 @@ struct nouveau_encoder {
 		       struct nv50_head_atom *, u8 proto, u8 depth);
 };
 
+struct nv50_mstm {
+	struct nouveau_encoder *outp;
+
+	struct drm_dp_mst_topology_mgr mgr;
+
+	/* Protected under nouveau_encoder->dp.hpd_irq_lock */
+	bool can_mst;
+	bool is_mst;
+	bool suspended;
+
+	bool modified;
+	bool disabled;
+	int links;
+};
+
 struct nouveau_encoder *
 find_encoder(struct drm_connector *connector, int type);
 
@@ -100,20 +127,29 @@ get_slave_funcs(struct drm_encoder *enc)
 
 /* nouveau_dp.c */
 enum nouveau_dp_status {
+	NOUVEAU_DP_NONE,
 	NOUVEAU_DP_SST,
 	NOUVEAU_DP_MST,
 };
 
-int nouveau_dp_detect(struct nouveau_encoder *);
+int nouveau_dp_detect(struct nouveau_connector *, struct nouveau_encoder *);
+void nouveau_dp_irq(struct nouveau_drm *drm,
+		    struct nouveau_connector *nv_connector);
 enum drm_mode_status nv50_dp_mode_valid(struct drm_connector *,
 					struct nouveau_encoder *,
 					const struct drm_display_mode *,
 					unsigned *clock);
 
 struct nouveau_connector *
-nouveau_encoder_connector_get(struct nouveau_encoder *encoder);
-
-int nv50_mstm_detect(struct nv50_mstm *, u8 dpcd[8], int allow);
-void nv50_mstm_remove(struct nv50_mstm *);
-void nv50_mstm_service(struct nv50_mstm *);
+nv50_outp_get_new_connector(struct nouveau_encoder *outp,
+			    struct drm_atomic_state *state);
+struct nouveau_connector *
+nv50_outp_get_old_connector(struct nouveau_encoder *outp,
+			    struct drm_atomic_state *state);
+
+int nv50_mstm_detect(struct nouveau_encoder *encoder);
+void nv50_mstm_remove(struct nv50_mstm *mstm);
+bool nv50_mstm_service(struct nouveau_drm *drm,
+		       struct nouveau_connector *nv_connector,
+		       struct nv50_mstm *mstm);
 #endif /* __NOUVEAU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c
index 0fa8f677b647..5c027c81760f 100644
--- a/drivers/gpu/drm/omapdrm/dss/venc.c
+++ b/drivers/gpu/drm/omapdrm/dss/venc.c
@@ -597,7 +597,7 @@ static void venc_bridge_mode_set(struct drm_bridge *bridge,
 	switch (venc_mode) {
 	default:
 		WARN_ON_ONCE(1);
-		/* Fall-through */
+		fallthrough;
 	case VENC_MODE_PAL:
 		venc->config = &venc_config_pal_trm;
 		break;
diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c
index 6d40914675da..328a4a74f534 100644
--- a/drivers/gpu/drm/omapdrm/omap_crtc.c
+++ b/drivers/gpu/drm/omapdrm/omap_crtc.c
@@ -451,11 +451,12 @@ static void omap_crtc_atomic_enable(struct drm_crtc *crtc,
 	if (omap_state->manually_updated)
 		return;
 
-	spin_lock_irq(&crtc->dev->event_lock);
 	drm_crtc_vblank_on(crtc);
+
 	ret = drm_crtc_vblank_get(crtc);
 	WARN_ON(ret != 0);
 
+	spin_lock_irq(&crtc->dev->event_lock);
 	omap_crtc_arm_event(crtc);
 	spin_unlock_irq(&crtc->dev->event_lock);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index fa79688013b7..6063f3a15329 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -26,6 +26,7 @@
 #include <linux/crc32.h>
 #include <linux/delay.h>
 
+#include <drm/drm_drv.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
@@ -186,7 +187,7 @@ void qxl_display_read_client_monitors_config(struct qxl_device *qdev)
 
 	DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE, ret);
 	qxl_update_offset_props(qdev);
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 	if (!drm_helper_hpd_irq_event(dev)) {
 		/* notify that the monitor configuration changed, to
 		   adjust at the arbitrary resolution */
@@ -431,7 +432,7 @@ static int qxl_framebuffer_surface_dirty(struct drm_framebuffer *fb,
 			  clips, num_clips, inc, 0);
 
 out_lock_end:
-	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	DRM_MODESET_LOCK_ALL_END(fb->dev, ctx, ret);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index ba20c6f03719..886e9959496f 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4856,7 +4856,7 @@ static void ci_request_link_speed_change_before_state_change(struct radeon_devic
 			pi->force_pcie_gen = RADEON_PCIE_GEN2;
 			if (current_link_speed == RADEON_PCIE_GEN2)
 				break;
-			/* fall through */
+			fallthrough;
 		case RADEON_PCIE_GEN2:
 			if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0)
 				break;
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 3b7ead5be5bf..73f67bf222e1 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -820,7 +820,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 					  ((idx_value >> 21) & 0xF));
 				return -EINVAL;
 			}
-			/* Fall through. */
+			fallthrough;
 		case 6:
 			track->cb[i].cpp = 4;
 			break;
@@ -971,7 +971,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 				return -EINVAL;
 			}
 			/* The same rules apply as for DXT3/5. */
-			/* Fall through. */
+			fallthrough;
 		case R300_TX_FORMAT_DXT3:
 		case R300_TX_FORMAT_DXT5:
 			track->textures[i].cpp = 1;
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 1d4c04e0a449..50b89b6d9a6c 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -115,7 +115,7 @@ void r420_pipes_init(struct radeon_device *rdev)
 	default:
 		/* force to 1 pipe */
 		num_pipes = 1;
-		/* fall through */
+		fallthrough;
 	case 1:
 		tmp = (0 << 1);
 		break;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 49e8266461f8..390a9621604a 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -487,7 +487,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 				return -EINVAL;
 			}
 		}
-		/* fall through */
+		fallthrough;
 	case V_0280A0_CLEAR_ENABLE:
 	{
 		uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]);
@@ -1535,7 +1535,7 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		break;
 	case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA:
 		is_array = true;
-		/* fall through */
+		fallthrough;
 	case V_038000_SQ_TEX_DIM_2D_MSAA:
 		array_check.nsamples = 1 << llevel;
 		llevel = 0;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index e0ae911ef427..7b69d6dfe44a 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -933,7 +933,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
 
 	/* get matching reference and feedback divider */
 	*ref_div = min(max(den/post_div, 1u), ref_div_max);
-	*fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den);
+	*fb_div = max(nom * *ref_div * post_div / den, 1u);
 
 	/* limit fb divider to its maximum */
 	if (*fb_div > fb_div_max) {
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index f178ba321715..3808a753127b 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -72,8 +72,8 @@ int radeon_gart_table_ram_alloc(struct radeon_device *rdev)
 {
 	void *ptr;
 
-	ptr = pci_alloc_consistent(rdev->pdev, rdev->gart.table_size,
-				   &rdev->gart.table_addr);
+	ptr = dma_alloc_coherent(&rdev->pdev->dev, rdev->gart.table_size,
+				 &rdev->gart.table_addr, GFP_KERNEL);
 	if (ptr == NULL) {
 		return -ENOMEM;
 	}
@@ -85,7 +85,6 @@ int radeon_gart_table_ram_alloc(struct radeon_device *rdev)
 	}
 #endif
 	rdev->gart.ptr = ptr;
-	memset((void *)rdev->gart.ptr, 0, rdev->gart.table_size);
 	return 0;
 }
 
@@ -110,9 +109,8 @@ void radeon_gart_table_ram_free(struct radeon_device *rdev)
 			      rdev->gart.table_size >> PAGE_SHIFT);
 	}
 #endif
-	pci_free_consistent(rdev->pdev, rdev->gart.table_size,
-			    (void *)rdev->gart.ptr,
-			    rdev->gart.table_addr);
+	dma_free_coherent(&rdev->pdev->dev, rdev->gart.table_size,
+			  (void *)rdev->gart.ptr, rdev->gart.table_addr);
 	rdev->gart.ptr = NULL;
 	rdev->gart.table_addr = 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 1ad5c3b86b64..57fb3eb3a4b4 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -454,7 +454,7 @@ static int radeon_uvd_validate_codec(struct radeon_cs_parser *p,
 		if (p->rdev->family >= CHIP_PALM)
 			return 0;
 
-		/* fall through */
+		fallthrough;
 	default:
 		DRM_ERROR("UVD codec not supported by hardware %d!\n",
 			  stream_type);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index a167e1c36d24..d1c73e9db889 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -5744,7 +5744,7 @@ static void si_request_link_speed_change_before_state_change(struct radeon_devic
 			si_pi->force_pcie_gen = RADEON_PCIE_GEN2;
 			if (current_link_speed == RADEON_PCIE_GEN2)
 				break;
-			/* fall through */
+			fallthrough;
 		case RADEON_PCIE_GEN2:
 			if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0)
 				break;
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index f858d8d06347..800721153d51 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -219,7 +219,7 @@ done:
 			WREG32(RS_DQ_RD_RET_CONF, 0x3f);
 			WREG32(MC_CONFIG, 0x1f);
 
-			/* fall through */
+			fallthrough;
 		case CHIP_RV670:
 		case CHIP_RV635:
 
diff --git a/drivers/gpu/drm/savage/savage_state.c b/drivers/gpu/drm/savage/savage_state.c
index a2ac25c11c90..e0d40ae67d54 100644
--- a/drivers/gpu/drm/savage/savage_state.c
+++ b/drivers/gpu/drm/savage/savage_state.c
@@ -306,7 +306,7 @@ static int savage_dispatch_dma_prim(drm_savage_private_t * dev_priv,
 	case SAVAGE_PRIM_TRILIST_201:
 		reorder = 1;
 		prim = SAVAGE_PRIM_TRILIST;
-		/* fall through */
+		fallthrough;
 	case SAVAGE_PRIM_TRILIST:
 		if (n % 3 != 0) {
 			DRM_ERROR("wrong number of vertices %u in TRILIST\n",
@@ -444,7 +444,7 @@ static int savage_dispatch_vb_prim(drm_savage_private_t * dev_priv,
 	case SAVAGE_PRIM_TRILIST_201:
 		reorder = 1;
 		prim = SAVAGE_PRIM_TRILIST;
-		/* fall through */
+		fallthrough;
 	case SAVAGE_PRIM_TRILIST:
 		if (n % 3 != 0) {
 			DRM_ERROR("wrong number of vertices %u in TRILIST\n",
@@ -566,7 +566,7 @@ static int savage_dispatch_dma_idx(drm_savage_private_t * dev_priv,
 	case SAVAGE_PRIM_TRILIST_201:
 		reorder = 1;
 		prim = SAVAGE_PRIM_TRILIST;
-		/* fall through */
+		fallthrough;
 	case SAVAGE_PRIM_TRILIST:
 		if (n % 3 != 0) {
 			DRM_ERROR("wrong number of indices %u in TRILIST\n", n);
@@ -705,7 +705,7 @@ static int savage_dispatch_vb_idx(drm_savage_private_t * dev_priv,
 	case SAVAGE_PRIM_TRILIST_201:
 		reorder = 1;
 		prim = SAVAGE_PRIM_TRILIST;
-		/* fall through */
+		fallthrough;
 	case SAVAGE_PRIM_TRILIST:
 		if (n % 3 != 0) {
 			DRM_ERROR("wrong number of indices %u in TRILIST\n", n);
@@ -1066,7 +1066,7 @@ int savage_bci_cmdbuf(struct drm_device *dev, void *data, struct drm_file *file_
 				ret = -EINVAL;
 				goto done;
 			}
-			/* fall through */
+			fallthrough;
 		case SAVAGE_CMD_DMA_PRIM:
 		case SAVAGE_CMD_VB_PRIM:
 			if (!first_draw_cmd)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 96f763d888af..9a0d77a68018 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -625,7 +625,7 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		entity = drm_sched_rq_select_entity(&sched->sched_rq[i]);
 		if (entity)
 			break;
@@ -852,7 +852,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->name = name;
 	sched->timeout = timeout;
 	sched->hang_limit = hang_limit;
-	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
+	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
 		drm_sched_rq_init(sched, &sched->sched_rq[i]);
 
 	init_waitqueue_head(&sched->wake_up_worker);
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 008f07923bbc..38a558768e53 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -850,13 +850,13 @@ static int hdmi_audio_configure(struct sti_hdmi *hdmi)
 	switch (info->channels) {
 	case 8:
 		audio_cfg |= HDMI_AUD_CFG_CH78_VALID;
-		/* fall through */
+		fallthrough;
 	case 6:
 		audio_cfg |= HDMI_AUD_CFG_CH56_VALID;
-		/* fall through */
+		fallthrough;
 	case 4:
 		audio_cfg |= HDMI_AUD_CFG_CH34_VALID | HDMI_AUD_CFG_8CH;
-		/* fall through */
+		fallthrough;
 	case 2:
 		audio_cfg |= HDMI_AUD_CFG_CH12_VALID;
 		break;
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index f025534eb30c..2f26f85ef538 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -589,8 +589,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 
 	/* We can't have an alpha plane at the lowest position */
 	if (!backend->quirks->supports_lowest_plane_alpha &&
-	    (plane_states[0]->fb->format->has_alpha ||
-	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)))
+	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))
 		return -EINVAL;
 
 	for (i = 1; i < num_planes; i++) {
@@ -995,7 +994,6 @@ static const struct sun4i_backend_quirks sun6i_backend_quirks = {
 
 static const struct sun4i_backend_quirks sun7i_backend_quirks = {
 	.needs_output_muxing = true,
-	.supports_lowest_plane_alpha = true,
 };
 
 static const struct sun4i_backend_quirks sun8i_a33_backend_quirks = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 09ad8506a81b..eaaf5d70e352 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -195,7 +195,7 @@ void sun4i_tcon_set_status(struct sun4i_tcon *tcon,
 	switch (encoder->encoder_type) {
 	case DRM_MODE_ENCODER_LVDS:
 		is_lvds = true;
-		/* Fallthrough */
+		fallthrough;
 	case DRM_MODE_ENCODER_DSI:
 	case DRM_MODE_ENCODER_NONE:
 		channel = 0;
@@ -342,7 +342,7 @@ static void sun4i_tcon0_mode_set_dithering(struct sun4i_tcon *tcon,
 		/* R and B components are only 5 bits deep */
 		val |= SUN4I_TCON0_FRM_CTL_MODE_R;
 		val |= SUN4I_TCON0_FRM_CTL_MODE_B;
-		/* Fall through */
+		fallthrough;
 	case MEDIA_BUS_FMT_RGB666_1X18:
 	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
 		/* Fall through: enable dithering */
@@ -1431,14 +1431,18 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon,
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
 	    encoder->encoder_type == DRM_MODE_ENCODER_TMDS) {
 		ret = sun8i_tcon_top_set_hdmi_src(&pdev->dev, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP)) {
 		ret = sun8i_tcon_top_de_config(&pdev->dev, tcon->id, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 9abde2817e1b..4f5efcace68e 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -889,7 +889,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi,
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
 		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
 
-	bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL);
+	bounce = kzalloc(ALIGN(msg->tx_len + sizeof(crc), 4), GFP_KERNEL);
 	if (!bounce)
 		return -ENOMEM;
 
@@ -900,7 +900,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi,
 	memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc));
 	len += sizeof(crc);
 
-	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len);
+	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, DIV_ROUND_UP(len, 4));
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1);
 	kfree(bounce);
 
@@ -1024,7 +1024,7 @@ static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host,
 			ret = sun6i_dsi_dcs_read(dsi, msg);
 			break;
 		}
-		/* Else, fall through */
+		fallthrough;
 
 	default:
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index a360697a4a4a..76393fc976fe 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -211,7 +211,7 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 	return 0;
 }
 
-static bool sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format)
+static u32 sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format)
 {
 	if (!format->is_yuv)
 		return SUN8I_CSC_MODE_OFF;
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 9a0b3240bc58..424ad60b4f38 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -135,7 +135,7 @@ static inline u32 compute_dda_inc(unsigned int in, unsigned int out, bool v,
 
 		default:
 			WARN_ON_ONCE(1);
-			/* fallthrough */
+			fallthrough;
 		case 4:
 			max = 4;
 			break;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 1856962411c7..518220bd092a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -386,7 +386,7 @@ static void tilcdc_crtc_set_mode(struct drm_crtc *crtc)
 		case DRM_FORMAT_XBGR8888:
 		case DRM_FORMAT_XRGB8888:
 			reg |= LCDC_V2_TFT_24BPP_UNPACK;
-			/* fallthrough */
+			fallthrough;
 		case DRM_FORMAT_BGR888:
 		case DRM_FORMAT_RGB888:
 			reg |= LCDC_V2_TFT_24BPP_MODE;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0e5497d80686..98a006fc30a5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -505,7 +505,7 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 			if (unlikely(ret != 0))
 				return ret;
 		}
-		/* fall through */
+		fallthrough;
 	case TTM_PL_TT:
 		ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write);
 		break;
diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c
index d733bbc4ac0e..17ff24d999d1 100644
--- a/drivers/gpu/drm/tve200/tve200_display.c
+++ b/drivers/gpu/drm/tve200/tve200_display.c
@@ -14,6 +14,7 @@
 #include <linux/version.h>
 #include <linux/dma-buf.h>
 #include <linux/of_graph.h>
+#include <linux/delay.h>
 
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fourcc.h>
@@ -130,9 +131,25 @@ static void tve200_display_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_connector *connector = priv->connector;
 	u32 format = fb->format->format;
 	u32 ctrl1 = 0;
+	int retries;
 
 	clk_prepare_enable(priv->clk);
 
+	/* Reset the TVE200 and wait for it to come back online */
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
+	for (retries = 0; retries < 5; retries++) {
+		usleep_range(30000, 50000);
+		if (readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET)
+			continue;
+		else
+			break;
+	}
+	if (retries == 5 &&
+	    readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) {
+		dev_err(drm->dev, "can't get hardware out of reset\n");
+		return;
+	}
+
 	/* Function 1 */
 	ctrl1 |= TVE200_CTRL_CSMODE;
 	/* Interlace mode for CCIR656: parameterize? */
@@ -230,8 +247,9 @@ static void tve200_display_disable(struct drm_simple_display_pipe *pipe)
 
 	drm_crtc_vblank_off(crtc);
 
-	/* Disable and Power Down */
+	/* Disable put into reset and Power Down */
 	writel(0, priv->regs + TVE200_CTRL);
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
 
 	clk_disable_unprepare(priv->clk);
 }
@@ -279,6 +297,8 @@ static int tve200_display_enable_vblank(struct drm_simple_display_pipe *pipe)
 	struct drm_device *drm = crtc->dev;
 	struct tve200_drm_dev_private *priv = drm->dev_private;
 
+	/* Clear any IRQs and enable */
+	writel(0xFF, priv->regs + TVE200_INT_CLR);
 	writel(TVE200_INT_V_STATUS, priv->regs + TVE200_INT_EN);
 	return 0;
 }
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index 551fa31629af..5771bb53ce6a 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -179,21 +179,21 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 	switch (vsg->state) {
 	case dr_via_device_mapped:
 		via_unmap_blit_from_device(pdev, vsg);
-		/* fall through */
+		fallthrough;
 	case dr_via_desc_pages_alloc:
 		for (i = 0; i < vsg->num_desc_pages; ++i) {
 			if (vsg->desc_pages[i] != NULL)
 				free_page((unsigned long)vsg->desc_pages[i]);
 		}
 		kfree(vsg->desc_pages);
-		/* fall through */
+		fallthrough;
 	case dr_via_pages_locked:
 		unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
 					   (vsg->direction == DMA_FROM_DEVICE));
-		/* fall through */
+		fallthrough;
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);
-		/* fall through */
+		fallthrough;
 	default:
 		vsg->state = dr_via_sg_init;
 	}
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 7a2430e34e00..c8da7adc6b30 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -179,6 +179,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 
 	virtio_gpu_cmd_submit(vgdev, buf, exbuf->size,
 			      vfpriv->ctx_id, buflist, out_fence);
+	dma_fence_put(&out_fence->f);
 	virtio_gpu_notify(vgdev);
 	return 0;
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 729f98ad7c02..842f8b61aa89 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -79,6 +79,7 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo)
 			}
 
 			sg_free_table(shmem->pages);
+			kfree(shmem->pages);
 			shmem->pages = NULL;
 			drm_gem_shmem_unpin(&bo->base.base);
 		}
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 013c9e0e412c..cc93a8c9547b 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -649,9 +649,7 @@ static void displback_changed(struct xenbus_device *xb_dev,
 
 	switch (backend_state) {
 	case XenbusStateReconfiguring:
-		/* fall through */
 	case XenbusStateReconfigured:
-		/* fall through */
 	case XenbusStateInitialised:
 		break;
 
@@ -701,7 +699,6 @@ static void displback_changed(struct xenbus_device *xb_dev,
 		break;
 
 	case XenbusStateUnknown:
-		/* fall through */
 	case XenbusStateClosed:
 		if (xb_dev->state == XenbusStateClosed)
 			break;
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index aed7510e2710..a8aefaa38bd3 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -18,6 +18,7 @@
 #include <drm/drm_probe_helper.h>
 
 #include <xen/balloon.h>
+#include <xen/xen.h>
 
 #include "xen_drm_front.h"
 #include "xen_drm_front_gem.h"
@@ -99,8 +100,8 @@ static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size)
 		 * allocate ballooned pages which will be used to map
 		 * grant references provided by the backend
 		 */
-		ret = alloc_xenballooned_pages(xen_obj->num_pages,
-					       xen_obj->pages);
+		ret = xen_alloc_unpopulated_pages(xen_obj->num_pages,
+					          xen_obj->pages);
 		if (ret < 0) {
 			DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n",
 				  xen_obj->num_pages, ret);
@@ -152,8 +153,8 @@ void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj)
 	} else {
 		if (xen_obj->pages) {
 			if (xen_obj->be_alloc) {
-				free_xenballooned_pages(xen_obj->num_pages,
-							xen_obj->pages);
+				xen_free_unpopulated_pages(xen_obj->num_pages,
+							   xen_obj->pages);
 				gem_free_pages_array(xen_obj);
 			} else {
 				drm_gem_put_pages(&xen_obj->base,
diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig
index aa6cd889bd11..b52c6cdfc0b8 100644
--- a/drivers/gpu/drm/xlnx/Kconfig
+++ b/drivers/gpu/drm/xlnx/Kconfig
@@ -2,6 +2,7 @@ config DRM_ZYNQMP_DPSUB
 	tristate "ZynqMP DisplayPort Controller Driver"
 	depends on ARCH_ZYNQMP || COMPILE_TEST
 	depends on COMMON_CLK && DRM && OF
+	depends on DMADEVICES
 	select DMA_ENGINE
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/ipu-v3/ipu-dc.c b/drivers/gpu/ipu-v3/ipu-dc.c
index dbcc16721931..34b4075a6a8e 100644
--- a/drivers/gpu/ipu-v3/ipu-dc.c
+++ b/drivers/gpu/ipu-v3/ipu-dc.c
@@ -141,7 +141,7 @@ static int ipu_bus_format_to_map(u32 fmt)
 	switch (fmt) {
 	default:
 		WARN_ON(1);
-		/* fall-through */
+		fallthrough;
 	case MEDIA_BUS_FMT_RGB888_1X24:
 		return IPU_DC_MAP_RGB24;
 	case MEDIA_BUS_FMT_RGB565_1X16:
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 359616e3efbb..d2ecc9c45255 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1598,6 +1598,17 @@ static void hid_output_field(const struct hid_device *hid,
 }
 
 /*
+ * Compute the size of a report.
+ */
+static size_t hid_compute_report_size(struct hid_report *report)
+{
+	if (report->size)
+		return ((report->size - 1) >> 3) + 1;
+
+	return 0;
+}
+
+/*
  * Create a report. 'data' has to be allocated using
  * hid_alloc_report_buf() so that it has proper size.
  */
@@ -1609,7 +1620,7 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 	if (report->id > 0)
 		*data++ = report->id;
 
-	memset(data, 0, ((report->size - 1) >> 3) + 1);
+	memset(data, 0, hid_compute_report_size(report));
 	for (n = 0; n < report->maxfield; n++)
 		hid_output_field(report->device, report->field[n], data);
 }
@@ -1739,7 +1750,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
 		csize--;
 	}
 
-	rsize = ((report->size - 1) >> 3) + 1;
+	rsize = hid_compute_report_size(report);
 
 	if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE)
 		rsize = HID_MAX_BUFFER_SIZE - 1;
diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c
index 4ff3bc1d25e2..28d671c5e0ca 100644
--- a/drivers/hid/hid-cougar.c
+++ b/drivers/hid/hid-cougar.c
@@ -321,7 +321,7 @@ static const struct kernel_param_ops cougar_g6_is_space_ops = {
 };
 module_param_cb(g6_is_space, &cougar_g6_is_space_ops, &g6_is_space, 0644);
 
-static struct hid_device_id cougar_id_table[] = {
+static const struct hid_device_id cougar_id_table[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR,
 			 USB_DEVICE_ID_COUGAR_500K_GAMING_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR,
diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c
index 45c4f888b7c4..dae193749d44 100644
--- a/drivers/hid/hid-elan.c
+++ b/drivers/hid/hid-elan.c
@@ -188,6 +188,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	ret = input_mt_init_slots(input, ELAN_MAX_FINGERS, INPUT_MT_POINTER);
 	if (ret) {
 		hid_err(hdev, "Failed to init elan MT slots: %d\n", ret);
+		input_free_device(input);
 		return ret;
 	}
 
@@ -198,6 +199,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	if (ret) {
 		hid_err(hdev, "Failed to register elan input device: %d\n",
 			ret);
+		input_mt_destroy_slots(input);
 		input_free_device(input);
 		return ret;
 	}
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 6221888aae99..74fc1df6e3c2 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -728,6 +728,9 @@
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D	0x608d
+#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019	0x6019
+#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E	0x602e
+#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093	0x6093
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
@@ -847,6 +850,7 @@
 #define USB_DEVICE_ID_MS_POWER_COVER     0x07da
 #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER	0x02fd
 #define USB_DEVICE_ID_MS_PIXART_MOUSE    0x00cb
+#define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS      0x02e0
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -1012,6 +1016,8 @@
 #define USB_DEVICE_ID_SAITEK_RAT9	0x0cfa
 #define USB_DEVICE_ID_SAITEK_MMO7	0x0cd0
 #define USB_DEVICE_ID_SAITEK_X52	0x075c
+#define USB_DEVICE_ID_SAITEK_X52_2	0x0255
+#define USB_DEVICE_ID_SAITEK_X52_PRO	0x0762
 
 #define USB_VENDOR_ID_SAMSUNG		0x0419
 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE	0x0001
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index b8eabf206e74..88e19996427e 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1132,6 +1132,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 	}
 
 mapped:
+	/* Mapping failed, bail out */
+	if (!bit)
+		return;
+
 	if (device->driver->input_mapped &&
 	    device->driver->input_mapped(device, hidinput, field, usage,
 					 &bit, &max) < 0) {
diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c
index ef0cbcd7540d..fcaf8466e627 100644
--- a/drivers/hid/hid-lg-g15.c
+++ b/drivers/hid/hid-lg-g15.c
@@ -680,7 +680,7 @@ static int lg_g15_register_led(struct lg_g15_data *g15, int i)
 			 * but it does have a separate power-on (reset) value.
 			 */
 			g15->leds[i].cdev.name = "g15::power_on_backlight_val";
-			/* fall through */
+			fallthrough;
 		case LG_G15_KBD_BRIGHTNESS:
 			g15->leds[i].cdev.brightness_set_blocking =
 				lg_g510_kbd_led_set;
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index a78c13cc9f47..38ee25a813b9 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -844,7 +844,7 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev,
 			workitem.type = WORKITEM_TYPE_EMPTY;
 			break;
 		}
-		/* fall-through */
+		fallthrough;
 	case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
 		workitem.quad_id_msb =
 			dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_MSB];
diff --git a/drivers/hid/hid-macally.c b/drivers/hid/hid-macally.c
index 9a4fc7dffb14..aea46e522008 100644
--- a/drivers/hid/hid-macally.c
+++ b/drivers/hid/hid-macally.c
@@ -29,7 +29,7 @@ static __u8 *macally_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return rdesc;
 }
 
-static struct hid_device_id macally_id_table[] = {
+static const struct hid_device_id macally_id_table[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR,
 			 USB_DEVICE_ID_MACALLY_IKEY_KEYBOARD) },
 	{ }
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 2d8b589201a4..071fd093a5f4 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -163,16 +163,13 @@ static int ms_surface_dial_quirk(struct hid_input *hi, struct hid_field *field,
 {
 	switch (usage->hid & HID_USAGE_PAGE) {
 	case 0xff070000:
-		/* fall-through */
 	case HID_UP_DIGITIZER:
 		/* ignore those axis */
 		return -1;
 	case HID_UP_GENDESK:
 		switch (usage->hid) {
 		case HID_GD_X:
-			/* fall-through */
 		case HID_GD_Y:
-			/* fall-through */
 		case HID_GD_RFKILL_BTN:
 			/* ignore those axis */
 			return -1;
@@ -451,6 +448,8 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_SURFACE_DIAL },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER),
 		.driver_data = MS_QUIRK_FF },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS),
+		.driver_data = MS_QUIRK_FF },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, ms_devices);
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 3f94b4954225..e3152155c4b8 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -856,6 +856,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			code = BTN_0  + ((usage->hid - 1) & HID_USAGE);
 
 		hid_map_usage(hi, usage, bit, max, EV_KEY, code);
+		if (!*bit)
+			return -1;
 		input_set_capability(hi->input, EV_KEY, code);
 		return 1;
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index c242150d35a3..7a2be0205dfd 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -105,6 +105,9 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS), HID_QUIRK_NOGET },
@@ -147,6 +150,8 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_2), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_PRO), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET },
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 8cffa84c9650..7f41213d5ae3 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -428,7 +428,6 @@ static void rmi_report(struct hid_device *hid, struct hid_report *report)
 
 	switch (report->id) {
 	case RMI_READ_DATA_REPORT_ID:
-		/* fall-through */
 	case RMI_ATTN_REPORT_ID:
 		return;
 	}
diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c
index 1a6e600197d0..2ff4c8e366ff 100644
--- a/drivers/hid/hid-roccat-kone.c
+++ b/drivers/hid/hid-roccat-kone.c
@@ -780,7 +780,7 @@ static void kone_keep_values_up_to_date(struct kone_device *kone,
 	case kone_mouse_event_switch_profile:
 		kone->actual_dpi = kone->profiles[event->value - 1].
 				startup_dpi;
-		/* fall through */
+		fallthrough;
 	case kone_mouse_event_osd_profile:
 		kone->actual_profile = event->value;
 		break;
diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c
index 78a364ae2f68..7d20d1fcf8d2 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -974,7 +974,7 @@ int uclogic_params_init(struct uclogic_params *params,
 			}
 			break;
 		}
-		/* FALL THROUGH */
+		fallthrough;
 	case VID_PID(USB_VENDOR_ID_HUION,
 		     USB_DEVICE_ID_HUION_TABLET):
 	case VID_PID(USB_VENDOR_ID_HUION,
diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c
index 679e142fc850..e484c3618dec 100644
--- a/drivers/hid/hid-wiimote-core.c
+++ b/drivers/hid/hid-wiimote-core.c
@@ -1672,7 +1672,6 @@ static ssize_t wiimote_ext_show(struct device *dev,
 	case WIIMOTE_EXT_GUITAR:
 		return sprintf(buf, "guitar\n");
 	case WIIMOTE_EXT_UNKNOWN:
-		/* fallthrough */
 	default:
 		return sprintf(buf, "unknown\n");
 	}
@@ -1722,7 +1721,6 @@ static ssize_t wiimote_dev_show(struct device *dev,
 	case WIIMOTE_DEV_PENDING:
 		return sprintf(buf, "pending\n");
 	case WIIMOTE_DEV_UNKNOWN:
-		/* fallthrough */
 	default:
 		return sprintf(buf, "unknown\n");
 	}
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 294c84e136d7..dbd04492825d 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -420,6 +420,19 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 		dev_err(&client->dev, "failed to change power setting.\n");
 
 set_pwr_exit:
+
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests.
+	 * According to Goodix Windows even waits 60 ms after (other?)
+	 * PWR_ON requests. Testing has confirmed that several devices
+	 * will not work properly without a delay after a PWR_ON request.
+	 */
+	if (!ret && power_state == I2C_HID_PWR_ON)
+		msleep(60);
+
 	return ret;
 }
 
@@ -441,15 +454,6 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret)
 		goto out_unlock;
 
-	/*
-	 * The HID over I2C specification states that if a DEVICE needs time
-	 * after the PWR_ON request, it should utilise CLOCK stretching.
-	 * However, it has been observered that the Windows driver provides a
-	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
-	 * rely on this.
-	 */
-	usleep_range(1000, 5000);
-
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 492dd641a25d..17a29ee0ac6c 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -26,7 +26,6 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/string.h>
-#include <linux/timekeeping.h>
 
 #include <linux/usb.h>
 
@@ -96,18 +95,6 @@ static int hid_start_in(struct hid_device *hid)
 				set_bit(HID_NO_BANDWIDTH, &usbhid->iofl);
 		} else {
 			clear_bit(HID_NO_BANDWIDTH, &usbhid->iofl);
-
-			if (test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) {
-				/*
-				 * In case events are generated while nobody was
-				 * listening, some are released when the device
-				 * is re-opened. Wait 50 msec for the queue to
-				 * empty before allowing events to go through
-				 * hid.
-				 */
-				usbhid->input_start_time =
-					ktime_add_ms(ktime_get_coarse(), 50);
-			}
 		}
 	}
 	spin_unlock_irqrestore(&usbhid->lock, flags);
@@ -293,23 +280,20 @@ static void hid_irq_in(struct urb *urb)
 		if (!test_bit(HID_OPENED, &usbhid->iofl))
 			break;
 		usbhid_mark_busy(usbhid);
-		if (test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) {
-			if (ktime_before(ktime_get_coarse(),
-					 usbhid->input_start_time))
-				break;
-			clear_bit(HID_RESUME_RUNNING, &usbhid->iofl);
+		if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) {
+			hid_input_report(urb->context, HID_INPUT_REPORT,
+					 urb->transfer_buffer,
+					 urb->actual_length, 1);
+			/*
+			 * autosuspend refused while keys are pressed
+			 * because most keyboards don't wake up when
+			 * a key is released
+			 */
+			if (hid_check_keys_pressed(hid))
+				set_bit(HID_KEYS_PRESSED, &usbhid->iofl);
+			else
+				clear_bit(HID_KEYS_PRESSED, &usbhid->iofl);
 		}
-		hid_input_report(urb->context, HID_INPUT_REPORT,
-				 urb->transfer_buffer, urb->actual_length, 1);
-		/*
-		 * autosuspend refused while keys are pressed
-		 * because most keyboards don't wake up when
-		 * a key is released
-		 */
-		if (hid_check_keys_pressed(hid))
-			set_bit(HID_KEYS_PRESSED, &usbhid->iofl);
-		else
-			clear_bit(HID_KEYS_PRESSED, &usbhid->iofl);
 		break;
 	case -EPIPE:		/* stall */
 		usbhid_mark_busy(usbhid);
@@ -736,6 +720,17 @@ static int usbhid_open(struct hid_device *hid)
 
 	usb_autopm_put_interface(usbhid->intf);
 
+	/*
+	 * In case events are generated while nobody was listening,
+	 * some are released when the device is re-opened.
+	 * Wait 50 msec for the queue to empty before allowing events
+	 * to go through hid.
+	 */
+	if (res == 0)
+		msleep(50);
+
+	clear_bit(HID_RESUME_RUNNING, &usbhid->iofl);
+
  Done:
 	mutex_unlock(&usbhid->mutex);
 	return res;
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 4140dea693e9..45e0b1c75cb1 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -519,12 +519,16 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 		switch (cmd) {
 		case HIDIOCGUSAGE:
+			if (uref->usage_index >= field->report_count)
+				goto inval;
 			uref->value = field->value[uref->usage_index];
 			if (copy_to_user(user_arg, uref, sizeof(*uref)))
 				goto fault;
 			goto goodreturn;
 
 		case HIDIOCSUSAGE:
+			if (uref->usage_index >= field->report_count)
+				goto inval;
 			field->value[uref->usage_index] = uref->value;
 			goto goodreturn;
 
@@ -781,7 +785,6 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		break;
 
 	case HIDIOCGUCODE:
-		/* fall through */
 	case HIDIOCGUSAGE:
 	case HIDIOCSUSAGE:
 	case HIDIOCGUSAGES:
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index c6ad684d099a..75fe85d3d27a 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -13,7 +13,6 @@
 
 #include <linux/types.h>
 #include <linux/slab.h>
-#include <linux/ktime.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
@@ -84,7 +83,6 @@ struct usbhid_device {
 	struct mutex mutex;						/* start/stop/open/close */
 	spinlock_t lock;						/* fifo spinlock */
 	unsigned long iofl;                                             /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */
-	ktime_t input_start_time;					/* When to start handling input */
 	struct timer_list io_retry;                                     /* Retry timer */
 	unsigned long stop_retry;                                       /* Time to give up, in jiffies */
 	unsigned int retry_delay;                                       /* Delay length in ms */
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 1c96809b51c9..83dfec327c42 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -341,7 +341,7 @@ static int wacom_graphire_irq(struct wacom_wac *wacom)
 
 			case 2: /* Mouse with wheel */
 				input_report_key(input, BTN_MIDDLE, data[1] & 0x04);
-				/* fall through */
+				fallthrough;
 
 			case 3: /* Mouse without wheel */
 				wacom->tool[0] = BTN_TOOL_MOUSE;
@@ -1201,7 +1201,7 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 	case 0x04:
 		wacom_intuos_bt_process_data(wacom, data + i);
 		i += 10;
-		/* fall through */
+		fallthrough;
 	case 0x03:
 		wacom_intuos_bt_process_data(wacom, data + i);
 		i += 10;
@@ -2148,7 +2148,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 		for (i = 0; i < wacom->led.count; i++)
 			wacom_update_led(wacom, features->numbered_buttons,
 					 value, i);
-		 /* fall through*/
+		fallthrough;
 	default:
 		do_report = true;
 		break;
@@ -3602,14 +3602,14 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 	switch (features->type) {
 	case GRAPHIRE_BT:
 		__clear_bit(ABS_MISC, input_dev->absbit);
-		/* fall through */
+		fallthrough;
 
 	case WACOM_MO:
 	case WACOM_G4:
 		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
 					      features->distance_max,
 					      features->distance_fuzz, 0);
-		/* fall through */
+		fallthrough;
 
 	case GRAPHIRE:
 		input_set_capability(input_dev, EV_REL, REL_WHEEL);
@@ -3649,7 +3649,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 	case INTUOS4S:
 		input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0);
 		input_abs_set_res(input_dev, ABS_Z, 287);
-		/* fall through */
+		fallthrough;
 
 	case INTUOS:
 		wacom_setup_intuos(wacom_wac);
@@ -3682,7 +3682,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 	case TABLETPC:
 	case TABLETPCE:
 		__clear_bit(ABS_MISC, input_dev->absbit);
-		/* fall through */
+		fallthrough;
 
 	case DTUS:
 	case DTUSX:
@@ -3696,7 +3696,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 
 	case PTU:
 		__set_bit(BTN_STYLUS2, input_dev->keybit);
-		/* fall through */
+		fallthrough;
 
 	case PENPARTNER:
 		__set_bit(BTN_TOOL_PEN, input_dev->keybit);
@@ -3799,7 +3799,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 		input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40);
 		input_abs_set_res(input_dev, ABS_MT_POSITION_Y, 40);
 
-		/* fall through */
+		fallthrough;
 
 	case INTUOS5:
 	case INTUOS5L:
@@ -3817,7 +3817,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 		input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0);
 		input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0);
 		input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
-		/* fall through */
+		fallthrough;
 
 	case WACOM_27QHDT:
 		if (wacom_wac->shared->touch->product == 0x32C ||
@@ -3826,14 +3826,14 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 			__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
 			wacom_wac->shared->has_mute_touch_switch = true;
 		}
-		/* fall through */
+		fallthrough;
 
 	case MTSCREEN:
 	case MTTPC:
 	case MTTPC_B:
 	case TABLETPC2FG:
 		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
-		/*fall through */
+		fallthrough;
 
 	case TABLETPC:
 	case TABLETPCE:
@@ -3843,7 +3843,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 	case INTUOSHT2:
 		input_dev->evbit[0] |= BIT_MASK(EV_SW);
 		__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
-		/* fall through */
+		fallthrough;
 
 	case BAMBOO_PT:
 	case BAMBOO_TOUCH:
@@ -4099,7 +4099,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 
 		__set_bit(KEY_BUTTONCONFIG, input_dev->keybit);
 		__set_bit(KEY_INFO, input_dev->keybit);
-		/* fall through */
+		fallthrough;
 
 	case WACOM_21UX2:
 	case WACOM_BEE:
@@ -4115,7 +4115,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 	case INTUOS3:
 	case INTUOS3L:
 		input_set_abs_params(input_dev, ABS_RY, 0, 4096, 0, 0);
-		/* fall through */
+		fallthrough;
 
 	case INTUOS3S:
 		input_set_abs_params(input_dev, ABS_RX, 0, 4096, 0, 0);
@@ -4139,7 +4139,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 		 * ID_INPUT_TABLET to be set.
 		 */
 		__set_bit(BTN_STYLUS, input_dev->keybit);
-		/* fall through */
+		fallthrough;
 
 	case INTUOS4:
 	case INTUOS4L:
diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c
index 365b5d5967ac..96d0eccca3aa 100644
--- a/drivers/hsi/clients/ssi_protocol.c
+++ b/drivers/hsi/clients/ssi_protocol.c
@@ -291,7 +291,7 @@ static void ssip_set_rxstate(struct ssi_protocol *ssi, unsigned int state)
 		/* CMT speech workaround */
 		if (atomic_read(&ssi->tx_usecnt))
 			break;
-		/* Else, fall through */
+		fallthrough;
 	case RECEIVING:
 		mod_timer(&ssi->keep_alive, jiffies +
 						msecs_to_jiffies(SSIP_KATOUT));
@@ -466,7 +466,7 @@ static void ssip_keep_alive(struct timer_list *t)
 		case SEND_READY:
 			if (atomic_read(&ssi->tx_usecnt) == 0)
 				break;
-			/* Fall through */
+			fallthrough;
 			/*
 			 * Workaround for cmt-speech in that case
 			 * we relay on audio timers.
@@ -668,7 +668,7 @@ static void ssip_rx_bootinforeq(struct hsi_client *cl, u32 cmd)
 	case ACTIVE:
 		dev_err(&cl->device, "Boot info req on active state\n");
 		ssip_error(cl);
-		/* Fall through */
+		fallthrough;
 	case INIT:
 	case HANDSHAKE:
 		spin_lock_bh(&ssi->lock);
diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c
index 4bc4a201f0f6..fa69b94debd9 100644
--- a/drivers/hsi/controllers/omap_ssi_core.c
+++ b/drivers/hsi/controllers/omap_ssi_core.c
@@ -296,7 +296,7 @@ static int ssi_clk_event(struct notifier_block *nb, unsigned long event,
 		break;
 	case ABORT_RATE_CHANGE:
 		dev_dbg(&ssi->device, "abort rate change\n");
-		/* Fall through */
+		fallthrough;
 	case POST_RATE_CHANGE:
 		dev_dbg(&ssi->device, "post rate change (%lu -> %lu)\n",
 			clk_data->old_rate, clk_data->new_rate);
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index e74b144b8f3d..754d35a25a1c 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -354,7 +354,7 @@ static void process_ib_ipinfo(void *in_msg, void *out_msg, int op)
 
 		out->body.kvp_ip_val.dhcp_enabled = in->kvp_ip_val.dhcp_enabled;
 
-		/* fallthrough */
+		fallthrough;
 
 	case KVP_OP_GET_IP_INFO:
 		utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.adapter_id,
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 92ee0fe4c919..a4e8d96513c2 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -282,26 +282,52 @@ static struct {
 	spinlock_t			lock;
 } host_ts;
 
-static struct timespec64 hv_get_adj_host_time(void)
+static inline u64 reftime_to_ns(u64 reftime)
 {
-	struct timespec64 ts;
-	u64 newtime, reftime;
+	return (reftime - WLTIMEDELTA) * 100;
+}
+
+/*
+ * Hard coded threshold for host timesync delay: 600 seconds
+ */
+static const u64 HOST_TIMESYNC_DELAY_THRESH = 600 * (u64)NSEC_PER_SEC;
+
+static int hv_get_adj_host_time(struct timespec64 *ts)
+{
+	u64 newtime, reftime, timediff_adj;
 	unsigned long flags;
+	int ret = 0;
 
 	spin_lock_irqsave(&host_ts.lock, flags);
 	reftime = hv_read_reference_counter();
-	newtime = host_ts.host_time + (reftime - host_ts.ref_time);
-	ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
+
+	/*
+	 * We need to let the caller know that last update from host
+	 * is older than the max allowable threshold. clock_gettime()
+	 * and PTP ioctl do not have a documented error that we could
+	 * return for this specific case. Use ESTALE to report this.
+	 */
+	timediff_adj = reftime - host_ts.ref_time;
+	if (timediff_adj * 100 > HOST_TIMESYNC_DELAY_THRESH) {
+		pr_warn_once("TIMESYNC IC: Stale time stamp, %llu nsecs old\n",
+			     (timediff_adj * 100));
+		ret = -ESTALE;
+	}
+
+	newtime = host_ts.host_time + timediff_adj;
+	*ts = ns_to_timespec64(reftime_to_ns(newtime));
 	spin_unlock_irqrestore(&host_ts.lock, flags);
 
-	return ts;
+	return ret;
 }
 
 static void hv_set_host_time(struct work_struct *work)
 {
-	struct timespec64 ts = hv_get_adj_host_time();
 
-	do_settimeofday64(&ts);
+	struct timespec64 ts;
+
+	if (!hv_get_adj_host_time(&ts))
+		do_settimeofday64(&ts);
 }
 
 /*
@@ -361,10 +387,23 @@ static void timesync_onchannelcallback(void *context)
 	struct ictimesync_ref_data *refdata;
 	u8 *time_txf_buf = util_timesynch.recv_buffer;
 
-	vmbus_recvpacket(channel, time_txf_buf,
-			 HV_HYP_PAGE_SIZE, &recvlen, &requestid);
+	/*
+	 * Drain the ring buffer and use the last packet to update
+	 * host_ts
+	 */
+	while (1) {
+		int ret = vmbus_recvpacket(channel, time_txf_buf,
+					   HV_HYP_PAGE_SIZE, &recvlen,
+					   &requestid);
+		if (ret) {
+			pr_warn_once("TimeSync IC pkt recv failed (Err: %d)\n",
+				     ret);
+			break;
+		}
+
+		if (!recvlen)
+			break;
 
-	if (recvlen > 0) {
 		icmsghdrp = (struct icmsg_hdr *)&time_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];
 
@@ -622,9 +661,7 @@ static int hv_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 static int hv_ptp_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
 {
-	*ts = hv_get_adj_host_time();
-
-	return 0;
+	return hv_get_adj_host_time(ts);
 }
 
 static struct ptp_clock_info ptp_hyperv_info = {
diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c
index 319a0519ebdb..208813158bb4 100644
--- a/drivers/hwmon/adt7462.c
+++ b/drivers/hwmon/adt7462.c
@@ -435,7 +435,7 @@ static const char *voltage_label(struct adt7462_data *data, int which)
 		case 3:
 			return "+1.5V";
 		}
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (!(data->pin_cfg[1] & ADT7462_PIN22_INPUT))
 			return "+12V3";
@@ -493,7 +493,7 @@ static const char *voltage_label(struct adt7462_data *data, int which)
 		case 3:
 			return "+1.5";
 		}
-		/* fall through */
+		fallthrough;
 	case 11:
 		if (data->pin_cfg[3] >> ADT7462_PIN28_SHIFT ==
 					ADT7462_PIN28_VOLT &&
@@ -531,7 +531,7 @@ static int voltage_multiplier(struct adt7462_data *data, int which)
 		case 3:
 			return 7800;
 		}
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (!(data->pin_cfg[1] & ADT7462_PIN22_INPUT))
 			return 62500;
@@ -589,7 +589,7 @@ static int voltage_multiplier(struct adt7462_data *data, int which)
 		case 3:
 			return 7800;
 		}
-		/* fall through */
+		fallthrough;
 	case 11:
 	case 12:
 		if (data->pin_cfg[3] >> ADT7462_PIN28_SHIFT ==
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 316618409315..a18887990f4a 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -753,15 +753,18 @@ static ssize_t applesmc_light_show(struct device *dev,
 	}
 
 	ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length);
+	if (ret)
+		goto out;
 	/* newer macbooks report a single 10-bit bigendian value */
 	if (data_length == 10) {
 		left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2;
 		goto out;
 	}
 	left = buffer[2];
+
+	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	if (ret)
 		goto out;
-	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	right = buffer[2];
 
 out:
@@ -810,12 +813,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev,
 		  to_index(attr));
 
 	ret = applesmc_read_key(newkey, buffer, 2);
-	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
+
+	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
+	return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
 }
 
 static ssize_t applesmc_store_fan_speed(struct device *dev,
@@ -851,12 +853,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev,
 	u8 buffer[2];
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
+
+	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
 }
 
 static ssize_t applesmc_store_fan_manual(struct device *dev,
@@ -872,10 +873,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev,
 		return -EINVAL;
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	val = (buffer[0] << 8 | buffer[1]);
 	if (ret)
 		goto out;
 
+	val = (buffer[0] << 8 | buffer[1]);
+
 	if (input)
 		val = val | (0x01 << to_index(attr));
 	else
@@ -951,13 +953,12 @@ static ssize_t applesmc_key_count_show(struct device *dev,
 	u32 count;
 
 	ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4);
-	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
-						((u32)buffer[2]<<8) + buffer[3];
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
+
+	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
+						((u32)buffer[2]<<8) + buffer[3];
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
 }
 
 static ssize_t applesmc_key_at_index_read_show(struct device *dev,
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index cf0962f7a020..e9c0bbc2caa9 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -406,10 +406,10 @@ static int emc1403_probe(struct i2c_client *client,
 	switch (id->driver_data) {
 	case emc1404:
 		data->groups[2] = &emc1404_group;
-		/* fall through */
+		fallthrough;
 	case emc1403:
 		data->groups[1] = &emc1403_group;
-		/* fall through */
+		fallthrough;
 	case emc1402:
 		data->groups[0] = &emc1402_group;
 	}
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index d09deb409de7..4dec793fd07d 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -1285,7 +1285,7 @@ static struct f71882fg_data *f71882fg_update_device(struct device *dev)
 				data->pwm_auto_point_pwm[nr][0] =
 					f71882fg_read8(data,
 						F71882FG_REG_POINT_PWM(nr, 0));
-				/* Fall through */
+				fallthrough;
 			case f71862fg:
 				data->pwm_auto_point_pwm[nr][1] =
 					f71882fg_read8(data,
@@ -2442,7 +2442,7 @@ static int f71882fg_probe(struct platform_device *pdev)
 		case f71869a:
 			/* These always have signed auto point temps */
 			data->auto_point_temp_signed = 1;
-			/* Fall through - to select correct fan/pwm reg bank! */
+			fallthrough;	/* to select correct fan/pwm reg bank! */
 		case f71889fg:
 		case f71889ed:
 		case f71889a:
diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c
index 3dfe2ca2f8c8..c6d4567f3952 100644
--- a/drivers/hwmon/gsc-hwmon.c
+++ b/drivers/hwmon/gsc-hwmon.c
@@ -172,6 +172,7 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 	case mode_temperature:
 		if (tmp > 0x8000)
 			tmp -= 0xffff;
+		tmp *= 100; /* convert to millidegrees celsius */
 		break;
 	case mode_voltage_raw:
 		tmp = clamp_val(tmp, 0, BIT(GSC_HWMON_RESOLUTION));
diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c
index eb72e390844e..6d1175a51832 100644
--- a/drivers/hwmon/hwmon-vid.c
+++ b/drivers/hwmon/hwmon-vid.c
@@ -96,7 +96,7 @@ int vid_from_reg(int val, u8 vrm)
 		val &= 0x1f;
 		if (val == 0x1f)
 			return 0;
-				/* fall through */
+		fallthrough;
 	case 25:		/* AMD NPT 0Fh */
 		val &= 0x3f;
 		return (val < 32) ? 1550 - 25 * val
@@ -122,7 +122,7 @@ int vid_from_reg(int val, u8 vrm)
 
 	case 84:		/* VRM 8.4 */
 		val &= 0x0f;
-				/* fall through */
+		fallthrough;
 	case 82:		/* VRM 8.2 */
 		val &= 0x1f;
 		return val == 0x1f ? 0 :
diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c
index 7fc5b065ad8b..81e155692aba 100644
--- a/drivers/hwmon/ina3221.c
+++ b/drivers/hwmon/ina3221.c
@@ -352,7 +352,7 @@ static int ina3221_read_curr(struct device *dev, u32 attr,
 		if (ret)
 			return ret;
 
-		/* fall through */
+		fallthrough;
 	case hwmon_curr_crit:
 	case hwmon_curr_max:
 		if (!resistance_uo)
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 750b08713dee..5bd15622a85f 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -2669,7 +2669,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr)
 	case thermal_cruise:
 		nct6775_write_value(data, data->REG_TARGET[nr],
 				    data->target_temp[nr]);
-		/* fall through  */
+		fallthrough;
 	default:
 		reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
 		reg = (reg & ~data->tolerance_mask) |
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b0425694f702..242ff8bee78d 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -231,7 +231,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 		if (ret < 0)
 			return ret;
 		cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f);
-		if (cnt == 0x1fff)
+		if (cnt == 0 || cnt == 0x1fff)
 			rpm = 0;
 		else
 			rpm = 1350000 / cnt;
@@ -243,7 +243,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 		if (ret < 0)
 			return ret;
 		cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f);
-		if (cnt == 0x1fff)
+		if (cnt == 0 || cnt == 0x1fff)
 			rpm = 0;
 		else
 			rpm = 1350000 / cnt;
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 30e18eb60da7..a71777990d49 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -752,7 +752,7 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	switch (sensors->freq.version) {
 	case 2:
 		show_freq = occ_show_freq_2;
-		/* fall through */
+		fallthrough;
 	case 1:
 		num_attrs += (sensors->freq.num_sensors * 2);
 		break;
@@ -763,7 +763,7 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	switch (sensors->power.version) {
 	case 2:
 		show_power = occ_show_power_2;
-		/* fall through */
+		fallthrough;
 	case 1:
 		num_attrs += (sensors->power.num_sensors * 4);
 		break;
@@ -781,7 +781,7 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		break;
 	case 3:
 		show_caps = occ_show_caps_3;
-		/* fall through */
+		fallthrough;
 	case 2:
 		num_attrs += (sensors->caps.num_sensors * 8);
 		break;
diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c
index 0c622711ef7e..58aa95a3c010 100644
--- a/drivers/hwmon/pmbus/isl68137.c
+++ b/drivers/hwmon/pmbus/isl68137.c
@@ -67,6 +67,7 @@ enum variants {
 	raa_dmpvr1_2rail,
 	raa_dmpvr2_1rail,
 	raa_dmpvr2_2rail,
+	raa_dmpvr2_2rail_nontc,
 	raa_dmpvr2_3rail,
 	raa_dmpvr2_hv,
 };
@@ -241,6 +242,10 @@ static int isl68137_probe(struct i2c_client *client,
 		info->pages = 1;
 		info->read_word_data = raa_dmpvr2_read_word_data;
 		break;
+	case raa_dmpvr2_2rail_nontc:
+		info->func[0] &= ~PMBUS_HAVE_TEMP;
+		info->func[1] &= ~PMBUS_HAVE_TEMP;
+		fallthrough;
 	case raa_dmpvr2_2rail:
 		info->pages = 2;
 		info->read_word_data = raa_dmpvr2_read_word_data;
@@ -304,7 +309,7 @@ static const struct i2c_device_id raa_dmpvr_id[] = {
 	{"raa228000", raa_dmpvr2_hv},
 	{"raa228004", raa_dmpvr2_hv},
 	{"raa228006", raa_dmpvr2_hv},
-	{"raa228228", raa_dmpvr2_2rail},
+	{"raa228228", raa_dmpvr2_2rail_nontc},
 	{"raa229001", raa_dmpvr2_2rail},
 	{"raa229004", raa_dmpvr2_2rail},
 	{}
diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c
index e1d10a6b7f7c..a07b97400cba 100644
--- a/drivers/hwmon/w83627hf.c
+++ b/drivers/hwmon/w83627hf.c
@@ -1213,7 +1213,7 @@ temp_type_store(struct device *dev, struct device_attribute *devattr,
 	case W83781D_DEFAULT_BETA:
 		dev_warn(dev, "Sensor type %d is deprecated, please use 4 "
 			 "instead\n", W83781D_DEFAULT_BETA);
-		/* fall through */
+		fallthrough;
 	case 4:		/* thermistor */
 		tmp = w83627hf_read_value(data, W83781D_REG_SCFG1);
 		w83627hf_write_value(data, W83781D_REG_SCFG1,
diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c
index 015f1ea31966..d833a4f16c47 100644
--- a/drivers/hwmon/w83781d.c
+++ b/drivers/hwmon/w83781d.c
@@ -814,7 +814,7 @@ store_sensor(struct device *dev, struct device_attribute *da,
 		dev_warn(dev,
 			 "Sensor type %d is deprecated, please use 4 instead\n",
 			 W83781D_DEFAULT_BETA);
-		/* fall through */
+		fallthrough;
 	case 4:		/* thermistor */
 		tmp = w83781d_read_value(data, W83781D_REG_SCFG1);
 		w83781d_write_value(data, W83781D_REG_SCFG1,
diff --git a/drivers/hwmon/w83795.c b/drivers/hwmon/w83795.c
index 44f68b965aec..6d52b530b429 100644
--- a/drivers/hwmon/w83795.c
+++ b/drivers/hwmon/w83795.c
@@ -2127,7 +2127,7 @@ static void w83795_apply_temp_config(struct w83795_data *data, u8 config,
 		if (temp_chan >= 4)
 			break;
 		data->temp_mode |= 1 << temp_chan;
-		/* fall through */
+		fallthrough;
 	case 0x3: /* Thermistor */
 		data->has_temp |= 1 << temp_chan;
 		break;
diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c
index 96544b348c27..7e642fb3ed15 100644
--- a/drivers/hwtracing/coresight/coresight-cpu-debug.c
+++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c
@@ -346,10 +346,10 @@ static void debug_init_arch_data(void *info)
 	switch (mode) {
 	case EDDEVID_IMPL_FULL:
 		drvdata->edvidsr_present = true;
-		/* Fall through */
+		fallthrough;
 	case EDDEVID_IMPL_EDPCSR_EDCIDSR:
 		drvdata->edcidsr_present = true;
-		/* Fall through */
+		fallthrough;
 	case EDDEVID_IMPL_EDPCSR:
 		/*
 		 * In ARM DDI 0487A.k, the EDDEVID1.PCSROffset is used to
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 6d7d2169bfb2..96425e818fc2 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -1382,7 +1382,6 @@ static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd,
 				return NOTIFY_BAD;
 		break;
 	case CPU_PM_EXIT:
-		/* fallthrough */
 	case CPU_PM_ENTER_FAILED:
 		if (drvdata->state_needs_restore)
 			etm4_cpu_restore(drvdata);
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index 7040d583bed9..9ca3aaafcfbc 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -84,9 +84,7 @@ u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata)
 	 */
 	switch (drvdata->memwidth) {
 	case TMC_MEM_INTF_WIDTH_32BITS:
-	/* fallthrough */
 	case TMC_MEM_INTF_WIDTH_64BITS:
-	/* fallthrough */
 	case TMC_MEM_INTF_WIDTH_128BITS:
 		mask = GENMASK(31, 4);
 		break;
diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c
index a1529f571491..9ca8c4e045f8 100644
--- a/drivers/hwtracing/intel_th/sth.c
+++ b/drivers/hwtracing/intel_th/sth.c
@@ -84,11 +84,11 @@ static ssize_t notrace sth_stm_packet(struct stm_data *stm_data,
 	/* Global packets (GERR, XSYNC, TRIG) are sent with register writes */
 	case STP_PACKET_GERR:
 		reg += 4;
-		/* fall through */
+		fallthrough;
 
 	case STP_PACKET_XSYNC:
 		reg += 8;
-		/* fall through */
+		fallthrough;
 
 	case STP_PACKET_TRIG:
 		if (flags & STP_PACKET_TIMESTAMPED)
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 710fbef9a9c2..384af88e58ad 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -41,8 +41,22 @@ static void pca_reset(struct i2c_algo_pca_data *adap)
 		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IPRESET);
 		pca_outw(adap, I2C_PCA_IND, 0xA5);
 		pca_outw(adap, I2C_PCA_IND, 0x5A);
+
+		/*
+		 * After a reset we need to re-apply any configuration
+		 * (calculated in pca_init) to get the bus in a working state.
+		 */
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IMODE);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.mode);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.tlow);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.thi);
+
+		pca_set_con(adap, I2C_PCA_CON_ENSIO);
 	} else {
 		adap->reset_chip(adap->data);
+		pca_set_con(adap, I2C_PCA_CON_ENSIO | adap->bus_settings.clock_freq);
 	}
 }
 
@@ -423,13 +437,14 @@ static int pca_init(struct i2c_adapter *adap)
 				" Use the nominal frequency.\n", adap->name);
 		}
 
-		pca_reset(pca_data);
-
 		clock = pca_clock(pca_data);
 		printk(KERN_INFO "%s: Clock frequency is %dkHz\n",
 		     adap->name, freqs[clock]);
 
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO | clock);
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.clock_freq = clock;
+
+		pca_reset(pca_data);
 	} else {
 		int clock;
 		int mode;
@@ -496,19 +511,15 @@ static int pca_init(struct i2c_adapter *adap)
 			thi = tlow * min_thi / min_tlow;
 		}
 
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.mode = mode;
+		pca_data->bus_settings.tlow = tlow;
+		pca_data->bus_settings.thi = thi;
+
 		pca_reset(pca_data);
 
 		printk(KERN_INFO
 		     "%s: Clock frequency is %dHz\n", adap->name, clock * 100);
-
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_IMODE);
-		pca_outw(pca_data, I2C_PCA_IND, mode);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
-		pca_outw(pca_data, I2C_PCA_IND, tlow);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
-		pca_outw(pca_data, I2C_PCA_IND, thi);
-
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO);
 	}
 	udelay(500); /* 500 us for oscillator to stabilise */
 
diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c
index 688e92818821..d8295b1c379d 100644
--- a/drivers/i2c/busses/i2c-bcm-iproc.c
+++ b/drivers/i2c/busses/i2c-bcm-iproc.c
@@ -720,7 +720,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c,
 
 			/* mark the last byte */
 			if (!process_call && (i == msg->len - 1))
-				val |= 1 << M_TX_WR_STATUS_SHIFT;
+				val |= BIT(M_TX_WR_STATUS_SHIFT);
 
 			iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val);
 		}
@@ -738,7 +738,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c,
 		 */
 		addr = i2c_8bit_addr_from_msg(msg);
 		/* mark it the last byte out */
-		val = addr | (1 << M_TX_WR_STATUS_SHIFT);
+		val = addr | BIT(M_TX_WR_STATUS_SHIFT);
 		iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val);
 	}
 
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 75f07138a6fa..dfcf04e1967f 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2093,8 +2093,12 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 		}
 	}
 
-	/* Adaptive TimeOut: astimated time in usec + 100% margin */
-	timeout_usec = (2 * 10000 / bus->bus_freq) * (2 + nread + nwrite);
+	/*
+	 * Adaptive TimeOut: estimated time in usec + 100% margin:
+	 * 2: double the timeout for clock stretching case
+	 * 9: bits per transaction (including the ack/nack)
+	 */
+	timeout_usec = (2 * 9 * USEC_PER_SEC / bus->bus_freq) * (2 + nread + nwrite);
 	timeout = max(msecs_to_jiffies(35), usecs_to_jiffies(timeout_usec));
 	if (nwrite >= 32 * 1024 || nread >= 32 * 1024) {
 		dev_err(bus->dev, "i2c%d buffer too big\n", bus->num);
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 175c590b93b7..12ac4212aded 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1425,7 +1425,6 @@ omap_i2c_probe(struct platform_device *pdev)
 		major = OMAP_I2C_REV_SCHEME_0_MAJOR(omap->rev);
 		break;
 	case OMAP_I2C_SCHEME_1:
-		/* FALLTHROUGH */
 	default:
 		omap->regs = (u8 *)reg_map_ip_v2;
 		rev = (rev << 16) |
diff --git a/drivers/i2c/busses/i2c-opal.c b/drivers/i2c/busses/i2c-opal.c
index 1c4c9bb06a0b..6eb0f50c5d28 100644
--- a/drivers/i2c/busses/i2c-opal.c
+++ b/drivers/i2c/busses/i2c-opal.c
@@ -125,7 +125,7 @@ static int i2c_opal_smbus_xfer(struct i2c_adapter *adap, u16 addr,
 	case I2C_SMBUS_BYTE:
 		req.buffer_ra = cpu_to_be64(__pa(&data->byte));
 		req.size = cpu_to_be32(1);
-		/* Fall through */
+		fallthrough;
 	case I2C_SMBUS_QUICK:
 		req.type = (read_write == I2C_SMBUS_READ) ?
 			OPAL_I2C_RAW_READ : OPAL_I2C_RAW_WRITE;
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 9e883474db8c..c7c543483b08 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -590,6 +590,7 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv)
 	/* master sent stop */
 	if (ssr_filtered & SSR) {
 		i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value);
+		rcar_i2c_write(priv, ICSCR, SIE | SDBS); /* clear our NACK */
 		rcar_i2c_write(priv, ICSIER, SAR);
 		rcar_i2c_write(priv, ICSSR, ~SSR & 0xff);
 	}
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index 2ade99b105b9..e627d7b2790f 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -276,16 +276,6 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap)
 		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
 }
 
-const struct acpi_device_id *
-i2c_acpi_match_device(const struct acpi_device_id *matches,
-		      struct i2c_client *client)
-{
-	if (!(client && matches))
-		return NULL;
-
-	return acpi_match_device(matches, &client->dev);
-}
-
 static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = {
 	/*
 	 * These Silead touchscreen controllers only work at 400KHz, for
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 34a9609f256d..5ec082e2039d 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -480,7 +480,7 @@ static int i2c_device_probe(struct device *dev)
 	 * or ACPI ID table is supplied for the probing device.
 	 */
 	if (!driver->id_table &&
-	    !i2c_acpi_match_device(dev->driver->acpi_match_table, client) &&
+	    !acpi_driver_match_device(dev, dev->driver) &&
 	    !i2c_of_match_device(dev->driver->of_match_table, client)) {
 		status = -ENODEV;
 		goto put_sync_adapter;
diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h
index 94ff1693b391..8ce261167a2d 100644
--- a/drivers/i2c/i2c-core.h
+++ b/drivers/i2c/i2c-core.h
@@ -59,20 +59,11 @@ static inline int __i2c_check_suspended(struct i2c_adapter *adap)
 }
 
 #ifdef CONFIG_ACPI
-const struct acpi_device_id *
-i2c_acpi_match_device(const struct acpi_device_id *matches,
-		      struct i2c_client *client);
 void i2c_acpi_register_devices(struct i2c_adapter *adap);
 
 int i2c_acpi_get_irq(struct i2c_client *client);
 #else /* CONFIG_ACPI */
 static inline void i2c_acpi_register_devices(struct i2c_adapter *adap) { }
-static inline const struct acpi_device_id *
-i2c_acpi_match_device(const struct acpi_device_id *matches,
-		      struct i2c_client *client)
-{
-	return NULL;
-}
 
 static inline int i2c_acpi_get_irq(struct i2c_client *client)
 {
diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 5c5306cd50ec..8513bd353c05 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -603,7 +603,7 @@ static int dw_i3c_master_bus_init(struct i3c_master_controller *m)
 		ret = dw_i2c_clk_cfg(master);
 		if (ret)
 			return ret;
-		/* fall through */
+		fallthrough;
 	case I3C_BUS_MODE_PURE:
 		ret = dw_i3c_clk_cfg(master);
 		if (ret)
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index fd3b5da44619..50c9a41467c8 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -575,14 +575,14 @@ static u8 hpt3xx_udma_filter(ide_drive_t *drive)
 		if (!HPT370_ALLOW_ATA100_5 ||
 		    check_in_drive_list(drive, bad_ata100_5))
 			return ATA_UDMA4;
-		/* fall through */
+		fallthrough;
 	case HPT372 :
 	case HPT372A:
 	case HPT372N:
 	case HPT374 :
 		if (ata_id_is_sata(drive->id))
 			mask &= ~0x0e;
-		/* fall through */
+		fallthrough;
 	default:
 		return mask;
 	}
@@ -602,7 +602,7 @@ static u8 hpt3xx_mdma_filter(ide_drive_t *drive)
 	case HPT374 :
 		if (ata_id_is_sata(drive->id))
 			return 0x00;
-		/* fall through */
+		fallthrough;
 	default:
 		return 0x07;
 	}
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 7f17f8303988..212bb2d8bf34 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -350,7 +350,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		 */
 		if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT)
 			break;
-		/* fall-through */
+		fallthrough;
 	case DATA_PROTECT:
 		/*
 		 * No point in retrying after an illegal request or data
@@ -750,7 +750,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	case REQ_OP_DRV_IN:
 	case REQ_OP_DRV_OUT:
 		expiry = ide_cd_expiry;
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		timeout = ATAPI_WAIT_PC;
 		break;
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 1fe1f9d37a51..af7503b47dbe 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -428,7 +428,7 @@ static int ide_floppy_get_capacity(ide_drive_t *drive)
 				 * (maintains previous driver behaviour)
 				 */
 				break;
-			/* fall through */
+			fallthrough;
 		case CAPACITY_CURRENT:
 			/* Normal Zip/LS-120 disks */
 			if (memcmp(cap_desc, &floppy->cap_desc, 8))
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index e867129466b0..1ddc45a04418 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -143,7 +143,7 @@ static void ide_classify_atapi_dev(ide_drive_t *drive)
 		}
 		/* Early cdrom models used zero */
 		type = ide_cdrom;
-		/* fall through */
+		fallthrough;
 	case ide_cdrom:
 		drive->dev_flags |= IDE_DFLAG_REMOVABLE;
 #ifdef CONFIG_PPC
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index a26f85ab58a9..d016cbe68cba 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -129,7 +129,7 @@ ide_startstop_t do_rw_taskfile(ide_drive_t *drive, struct ide_cmd *orig_cmd)
 			return pre_task_out_intr(drive, cmd);
 		}
 		handler = task_pio_intr;
-		/* fall through */
+		fallthrough;
 	case ATA_PROT_NODATA:
 		if (handler == NULL)
 			handler = task_no_data_intr;
@@ -141,7 +141,7 @@ ide_startstop_t do_rw_taskfile(ide_drive_t *drive, struct ide_cmd *orig_cmd)
 		hwif->expiry = dma_ops->dma_timer_expiry;
 		ide_execute_command(drive, cmd, ide_dma_intr, 2 * WAIT_CMD);
 		dma_ops->dma_start(drive);
-		/* fall through */
+		fallthrough;
 	default:
 		return ide_started;
 	}
@@ -579,10 +579,10 @@ int ide_taskfile_ioctl(ide_drive_t *drive, unsigned long arg)
 			goto abort;
 		}
 		cmd.tf_flags |= IDE_TFLAG_MULTI_PIO;
-		/* fall through */
+		fallthrough;
 	case TASKFILE_OUT:
 		cmd.protocol = ATA_PROT_PIO;
-		/* fall through */
+		fallthrough;
 	case TASKFILE_OUT_DMAQ:
 	case TASKFILE_OUT_DMA:
 		cmd.tf_flags |= IDE_TFLAG_WRITE;
@@ -598,10 +598,10 @@ int ide_taskfile_ioctl(ide_drive_t *drive, unsigned long arg)
 			goto abort;
 		}
 		cmd.tf_flags |= IDE_TFLAG_MULTI_PIO;
-		/* fall through */
+		fallthrough;
 	case TASKFILE_IN:
 		cmd.protocol = ATA_PROT_PIO;
-		/* fall through */
+		fallthrough;
 	case TASKFILE_IN_DMAQ:
 	case TASKFILE_IN_DMA:
 		nsect = taskin / SECTOR_SIZE;
diff --git a/drivers/ide/sis5513.c b/drivers/ide/sis5513.c
index 024bc7ba49ee..1a700bef6c56 100644
--- a/drivers/ide/sis5513.c
+++ b/drivers/ide/sis5513.c
@@ -494,7 +494,7 @@ static int init_chipset_sis5513(struct pci_dev *dev)
 		pci_read_config_byte(dev, 0x09, &reg);
 		if ((reg & 0x0f) != 0x00)
 			pci_write_config_byte(dev, 0x09, reg&0xf0);
-		/* fall through */
+		fallthrough;
 	case ATA_16:
 		/* force per drive recovery and active timings
 		   needed on ATA_33 and below chips */
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 8e0fb1a5bdbd..9a810e4a7946 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -90,14 +90,6 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
- * Set this flag for states where the HW flushes the TLB for us
- * and so we don't need cross-calls to keep it consistent.
- * If this flag is set, SW flushes the TLB, so even if the
- * HW doesn't do the flushing, this flag is safe to use.
- */
-#define CPUIDLE_FLAG_TLB_FLUSHED	BIT(16)
-
-/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -131,14 +123,6 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	unsigned long eax = flg2MWAIT(state->flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
 	bool tick;
-	int cpu = smp_processor_id();
-
-	/*
-	 * leave_mm() to avoid costly and often unnecessary wakeups
-	 * for flushing the user TLB's associated with the active mm.
-	 */
-	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
-		leave_mm(cpu);
 
 	if (!static_cpu_has(X86_FEATURE_ARAT)) {
 		/*
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 24864d9dfab5..48435865fdaf 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -189,6 +189,14 @@ struct bmc150_accel_data {
 	struct mutex mutex;
 	u8 fifo_mode, watermark;
 	s16 buffer[8];
+	/*
+	 * Ensure there is sufficient space and correct alignment for
+	 * the timestamp if enabled
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	u8 bw_bits;
 	u32 slope_dur;
 	u32 slope_thres;
@@ -922,15 +930,16 @@ static int __bmc150_accel_fifo_flush(struct iio_dev *indio_dev,
 	 * now.
 	 */
 	for (i = 0; i < count; i++) {
-		u16 sample[8];
 		int j, bit;
 
 		j = 0;
 		for_each_set_bit(bit, indio_dev->active_scan_mask,
 				 indio_dev->masklength)
-			memcpy(&sample[j++], &buffer[i * 3 + bit], 2);
+			memcpy(&data->scan.channels[j++], &buffer[i * 3 + bit],
+			       sizeof(data->scan.channels[0]));
 
-		iio_push_to_buffers_with_timestamp(indio_dev, sample, tstamp);
+		iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
+						   tstamp);
 
 		tstamp += sample_period;
 	}
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 66b2e4cf24cf..0e18b92e2099 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -209,14 +209,20 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	const struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct kxsd9_state *st = iio_priv(indio_dev);
+	/*
+	 * Ensure correct positioning and alignment of timestamp.
+	 * No need to zero initialize as all elements written.
+	 */
+	struct {
+		__be16 chan[4];
+		s64 ts __aligned(8);
+	} hw_values;
 	int ret;
-	/* 4 * 16bit values AND timestamp */
-	__be16 hw_values[8];
 
 	ret = regmap_bulk_read(st->map,
 			       KXSD9_REG_X,
-			       &hw_values,
-			       8);
+			       hw_values.chan,
+			       sizeof(hw_values.chan));
 	if (ret) {
 		dev_err(st->dev,
 			"error reading data\n");
@@ -224,7 +230,7 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev,
-					   hw_values,
+					   &hw_values,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/accel/mma7455_core.c b/drivers/iio/accel/mma7455_core.c
index 7e99bcb3398d..922bd38ff6ea 100644
--- a/drivers/iio/accel/mma7455_core.c
+++ b/drivers/iio/accel/mma7455_core.c
@@ -52,6 +52,14 @@
 
 struct mma7455_data {
 	struct regmap *regmap;
+	/*
+	 * Used to reorganize data.  Will ensure correct alignment of
+	 * the timestamp if present
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static int mma7455_drdy(struct mma7455_data *mma7455)
@@ -82,19 +90,19 @@ static irqreturn_t mma7455_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma7455_data *mma7455 = iio_priv(indio_dev);
-	u8 buf[16]; /* 3 x 16-bit channels + padding + ts */
 	int ret;
 
 	ret = mma7455_drdy(mma7455);
 	if (ret)
 		goto done;
 
-	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL, buf,
-			       sizeof(__le16) * 3);
+	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL,
+			       mma7455->scan.channels,
+			       sizeof(mma7455->scan.channels));
 	if (ret)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &mma7455->scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index ba27f8673131..853febc29488 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -110,6 +110,12 @@ struct mma8452_data {
 	int sleep_val;
 	struct regulator *vdd_reg;
 	struct regulator *vddio_reg;
+
+	/* Ensure correct alignment of time stamp when present */
+	struct {
+		__be16 channels[3];
+		s64 ts __aligned(8);
+	} buffer;
 };
 
  /**
@@ -1091,14 +1097,13 @@ static irqreturn_t mma8452_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma8452_data *data = iio_priv(indio_dev);
-	u8 buffer[16]; /* 3 16-bit channels + padding + ts */
 	int ret;
 
-	ret = mma8452_read(data, (__be16 *)buffer);
+	ret = mma8452_read(data, data->buffer.channels);
 	if (ret < 0)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
 					   iio_get_time_ns(indio_dev));
 
 done:
@@ -1580,7 +1585,7 @@ static int mma8452_probe(struct i2c_client *client,
 	case FXLS8471_DEVICE_ID:
 		if (ret == data->chip_info->chip_id)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		ret = -ENODEV;
 		goto disable_regulators;
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 66d9cc073157..d94dc800b842 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -865,6 +865,8 @@ config ROCKCHIP_SARADC
 	tristate "Rockchip SARADC driver"
 	depends on ARCH_ROCKCHIP || (ARM && COMPILE_TEST)
 	depends on RESET_CONTROLLER
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	help
 	  Say yes here to build support for the SARADC found in SoCs from
 	  Rockchip.
diff --git a/drivers/iio/adc/ab8500-gpadc.c b/drivers/iio/adc/ab8500-gpadc.c
index 7fdc5d2d1d35..1bb987a4acba 100644
--- a/drivers/iio/adc/ab8500-gpadc.c
+++ b/drivers/iio/adc/ab8500-gpadc.c
@@ -484,7 +484,7 @@ static int ab8500_gpadc_read(struct ab8500_gpadc *gpadc,
 			delay_max = 10000; /* large range optimises sleepmode */
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		ctrl1 |= AB8500_GPADC_CTRL1_BUF_ENA;
 		break;
diff --git a/drivers/iio/adc/cpcap-adc.c b/drivers/iio/adc/cpcap-adc.c
index 84a1733e5913..64c3cc382311 100644
--- a/drivers/iio/adc/cpcap-adc.c
+++ b/drivers/iio/adc/cpcap-adc.c
@@ -690,7 +690,7 @@ static void cpcap_adc_phase(struct cpcap_adc_request *req)
 		break;
 	case CPCAP_ADC_BATTI_PI17:
 		index = req->bank_index;
-		/* fallthrough */
+		fallthrough;
 	default:
 		req->result += conv_tbl[index].cal_offset;
 		req->result += conv_tbl[index].align_offset;
diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c
index 5ed63e874292..b573ec60a8b8 100644
--- a/drivers/iio/adc/ina2xx-adc.c
+++ b/drivers/iio/adc/ina2xx-adc.c
@@ -146,6 +146,11 @@ struct ina2xx_chip_info {
 	int range_vbus; /* Bus voltage maximum in V */
 	int pga_gain_vshunt; /* Shunt voltage PGA gain */
 	bool allow_async_readout;
+	/* data buffer needs space for channel data and timestamp */
+	struct {
+		u16 chan[4];
+		u64 ts __aligned(8);
+	} scan;
 };
 
 static const struct ina2xx_config ina2xx_config[] = {
@@ -738,8 +743,6 @@ static int ina2xx_conversion_ready(struct iio_dev *indio_dev)
 static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 {
 	struct ina2xx_chip_info *chip = iio_priv(indio_dev);
-	/* data buffer needs space for channel data and timestap */
-	unsigned short data[4 + sizeof(s64)/sizeof(short)];
 	int bit, ret, i = 0;
 	s64 time;
 
@@ -758,10 +761,10 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 		if (ret < 0)
 			return ret;
 
-		data[i++] = val;
+		chip->scan.chan[i++] = val;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data, time);
+	iio_push_to_buffers_with_timestamp(indio_dev, &chip->scan, time);
 
 	return 0;
 };
diff --git a/drivers/iio/adc/max1118.c b/drivers/iio/adc/max1118.c
index 01b20e420ac4..6efb0b43d938 100644
--- a/drivers/iio/adc/max1118.c
+++ b/drivers/iio/adc/max1118.c
@@ -36,6 +36,11 @@ struct max1118 {
 	struct spi_device *spi;
 	struct mutex lock;
 	struct regulator *reg;
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u8 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 
 	u8 data ____cacheline_aligned;
 };
@@ -166,7 +171,6 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max1118 *adc = iio_priv(indio_dev);
-	u8 data[16] = { }; /* 2x 8-bit ADC data + padding + 8 bytes timestamp */
 	int scan_index;
 	int i = 0;
 
@@ -184,10 +188,10 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 			goto out;
 		}
 
-		data[i] = ret;
+		adc->scan.channels[i] = ret;
 		i++;
 	}
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	mutex_unlock(&adc->lock);
diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c
index 5f1706d1c3c0..da353dcb1e9d 100644
--- a/drivers/iio/adc/mcp3422.c
+++ b/drivers/iio/adc/mcp3422.c
@@ -96,16 +96,12 @@ static int mcp3422_update_config(struct mcp3422 *adc, u8 newconfig)
 {
 	int ret;
 
-	mutex_lock(&adc->lock);
-
 	ret = i2c_master_send(adc->i2c, &newconfig, 1);
 	if (ret > 0) {
 		adc->config = newconfig;
 		ret = 0;
 	}
 
-	mutex_unlock(&adc->lock);
-
 	return ret;
 }
 
@@ -138,6 +134,8 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 	u8 config;
 	u8 req_channel = channel->channel;
 
+	mutex_lock(&adc->lock);
+
 	if (req_channel != MCP3422_CHANNEL(adc->config)) {
 		config = adc->config;
 		config &= ~MCP3422_CHANNEL_MASK;
@@ -145,12 +143,18 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 		config &= ~MCP3422_PGA_MASK;
 		config |= MCP3422_PGA_VALUE(adc->pga[req_channel]);
 		ret = mcp3422_update_config(adc, config);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&adc->lock);
 			return ret;
+		}
 		msleep(mcp3422_read_times[MCP3422_SAMPLE_RATE(adc->config)]);
 	}
 
-	return mcp3422_read(adc, value, &config);
+	ret = mcp3422_read(adc, value, &config);
+
+	mutex_unlock(&adc->lock);
+
+	return ret;
 }
 
 static int mcp3422_read_raw(struct iio_dev *iio,
diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 93c2252c0b89..1a9189ba69ae 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -707,7 +707,7 @@ static int meson_sar_adc_temp_sensor_init(struct iio_dev *indio_dev)
 	size_t read_len;
 	int ret;
 
-	temperature_calib = devm_nvmem_cell_get(&indio_dev->dev,
+	temperature_calib = devm_nvmem_cell_get(indio_dev->dev.parent,
 						"temperature_calib");
 	if (IS_ERR(temperature_calib)) {
 		ret = PTR_ERR(temperature_calib);
diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c
index 9426f70a8005..cf63983a54d9 100644
--- a/drivers/iio/adc/ti-adc081c.c
+++ b/drivers/iio/adc/ti-adc081c.c
@@ -33,6 +33,12 @@ struct adc081c {
 
 	/* 8, 10 or 12 */
 	int bits;
+
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u16 channel;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 #define REG_CONV_RES 0x00
@@ -128,14 +134,13 @@ static irqreturn_t adc081c_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc081c *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2 bytes data + 6 bytes padding + 8 bytes timestamp */
 	int ret;
 
 	ret = i2c_smbus_read_word_swapped(data->i2c, REG_CONV_RES);
 	if (ret < 0)
 		goto out;
-	buf[0] = ret;
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	data->scan.channel = ret;
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c
index 9017e1e24273..dfba34834a57 100644
--- a/drivers/iio/adc/ti-adc084s021.c
+++ b/drivers/iio/adc/ti-adc084s021.c
@@ -26,6 +26,11 @@ struct adc084s021 {
 	struct spi_transfer spi_trans;
 	struct regulator *reg;
 	struct mutex lock;
+	/* Buffer used to align data */
+	struct {
+		__be16 channels[4];
+		s64 ts __aligned(8);
+	} scan;
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache line.
@@ -141,14 +146,13 @@ static irqreturn_t adc084s021_buffer_trigger_handler(int irq, void *pollfunc)
 	struct iio_poll_func *pf = pollfunc;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc084s021 *adc = iio_priv(indio_dev);
-	__be16 data[8] = {0}; /* 4 * 16-bit words of data + 8 bytes timestamp */
 
 	mutex_lock(&adc->lock);
 
-	if (adc084s021_adc_conversion(adc, &data) < 0)
+	if (adc084s021_adc_conversion(adc, adc->scan.channels) < 0)
 		dev_err(&adc->spi->dev, "Failed to read data\n");
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 	mutex_unlock(&adc->lock);
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index f42ab112986e..9fef39bcf997 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -316,6 +316,7 @@ static const struct iio_chan_spec ads1115_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(ADS1015_TIMESTAMP),
 };
 
+#ifdef CONFIG_PM
 static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 {
 	int ret;
@@ -333,6 +334,15 @@ static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 	return ret < 0 ? ret : 0;
 }
 
+#else /* !CONFIG_PM */
+
+static int ads1015_set_power_state(struct ads1015_data *data, bool on)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_PM */
+
 static
 int ads1015_get_adc_result(struct ads1015_data *data, int chan, int *val)
 {
diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c
index 2b007e7568b2..60dd87e96f5f 100644
--- a/drivers/iio/chemical/ccs811.c
+++ b/drivers/iio/chemical/ccs811.c
@@ -78,6 +78,11 @@ struct ccs811_data {
 	struct iio_trigger *drdy_trig;
 	struct gpio_desc *wakeup_gpio;
 	bool drdy_trig_on;
+	/* Ensures correct alignment of timestamp if present */
+	struct {
+		s16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static const struct iio_chan_spec ccs811_channels[] = {
@@ -327,17 +332,17 @@ static irqreturn_t ccs811_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ccs811_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	s16 buf[8]; /* s16 eCO2 + s16 TVOC + padding + 8 byte timestamp */
 	int ret;
 
-	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA, 4,
-					    (u8 *)&buf);
+	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA,
+					    sizeof(data->scan.channels),
+					    (u8 *)data->scan.channels);
 	if (ret != 4) {
 		dev_err(&client->dev, "cannot read sensor data\n");
 		goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 
 err:
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index 5a29e32c295f..2ea9a5c4d846 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -118,7 +118,7 @@ static int sps30_do_cmd(struct sps30_state *state, u16 cmd, u8 *data, int size)
 	case SPS30_READ_AUTO_CLEANING_PERIOD:
 		buf[0] = SPS30_AUTO_CLEANING_PERIOD >> 8;
 		buf[1] = (u8)(SPS30_AUTO_CLEANING_PERIOD & 0xff);
-		/* fall through */
+		fallthrough;
 	case SPS30_READ_DATA_READY_FLAG:
 	case SPS30_READ_DATA:
 	case SPS30_READ_SERIAL:
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index ea480c1d4349..1bc6efa47316 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -72,10 +72,13 @@ static void get_default_min_max_freq(enum motionsensor_type type,
 
 	switch (type) {
 	case MOTIONSENSE_TYPE_ACCEL:
-	case MOTIONSENSE_TYPE_GYRO:
 		*min_freq = 12500;
 		*max_freq = 100000;
 		break;
+	case MOTIONSENSE_TYPE_GYRO:
+		*min_freq = 25000;
+		*max_freq = 100000;
+		break;
 	case MOTIONSENSE_TYPE_MAG:
 		*min_freq = 5000;
 		*max_freq = 25000;
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index cc4875660a69..1fd75c02a7cd 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -220,7 +220,6 @@ static int ad5592r_set_channel_modes(struct ad5592r_state *st)
 			break;
 
 		case CH_MODE_UNUSED:
-			/* fall-through */
 		default:
 			switch (st->channel_offstate[i]) {
 			case CH_OFFSTATE_OUT_TRISTATE:
@@ -237,7 +236,6 @@ static int ad5592r_set_channel_modes(struct ad5592r_state *st)
 				break;
 
 			case CH_OFFSTATE_PULLDOWN:
-				/* fall-through */
 			default:
 				pulldown |= BIT(i);
 				break;
diff --git a/drivers/iio/dac/dpot-dac.c b/drivers/iio/dac/dpot-dac.c
index b3835fb6b862..1a9609eda5c5 100644
--- a/drivers/iio/dac/dpot-dac.c
+++ b/drivers/iio/dac/dpot-dac.c
@@ -74,11 +74,12 @@ static int dpot_dac_read_raw(struct iio_dev *indio_dev,
 		case IIO_VAL_INT:
 			/*
 			 * Convert integer scale to fractional scale by
-			 * setting the denominator (val2) to one, and...
+			 * setting the denominator (val2) to one...
 			 */
 			*val2 = 1;
 			ret = IIO_VAL_FRACTIONAL;
-			/* fall through */
+			/* ...and fall through. Say it again for GCC. */
+			fallthrough;
 		case IIO_VAL_FRACTIONAL:
 			*val *= regulator_get_voltage(dac->vref) / 1000;
 			*val2 *= dac->max_ohms;
diff --git a/drivers/iio/health/max30102.c b/drivers/iio/health/max30102.c
index 9b47d9472a4f..d9b2ed80882a 100644
--- a/drivers/iio/health/max30102.c
+++ b/drivers/iio/health/max30102.c
@@ -273,10 +273,10 @@ static int max30102_read_measurement(struct max30102_data *data,
 	switch (measurements) {
 	case 3:
 		MAX30102_COPY_DATA(2);
-		/* fall through */
+		fallthrough;
 	case 2:
 		MAX30102_COPY_DATA(1);
-		/* fall through */
+		fallthrough;
 	case 1:
 		MAX30102_COPY_DATA(0);
 		break;
diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index c539dfa3b8d3..319b64b2fd88 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -97,11 +97,11 @@ int __adis_write_reg(struct adis *adis, unsigned int reg,
 		adis->tx[9] = (value >> 24) & 0xff;
 		adis->tx[6] = ADIS_WRITE_REG(reg + 2);
 		adis->tx[7] = (value >> 16) & 0xff;
-		/* fall through */
+		fallthrough;
 	case 2:
 		adis->tx[4] = ADIS_WRITE_REG(reg + 1);
 		adis->tx[5] = (value >> 8) & 0xff;
-		/* fall through */
+		fallthrough;
 	case 1:
 		adis->tx[2] = ADIS_WRITE_REG(reg);
 		adis->tx[3] = value & 0xff;
@@ -191,7 +191,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg,
 		adis->tx[2] = ADIS_READ_REG(reg + 2);
 		adis->tx[3] = 0;
 		spi_message_add_tail(&xfers[1], &msg);
-		/* fall through */
+		fallthrough;
 	case 2:
 		adis->tx[4] = ADIS_READ_REG(reg);
 		adis->tx[5] = 0;
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 606d5e61c575..cdcd16f19500 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -599,7 +599,7 @@ static ssize_t __iio_format_value(char *buf, size_t len, unsigned int type,
 		return scnprintf(buf, len, "%d", vals[0]);
 	case IIO_VAL_INT_PLUS_MICRO_DB:
 		scale_db = true;
-		/* fall through */
+		fallthrough;
 	case IIO_VAL_INT_PLUS_MICRO:
 		if (vals[1] < 0)
 			return scnprintf(buf, len, "-%d.%06u%s", abs(vals[0]),
@@ -918,7 +918,7 @@ static ssize_t iio_write_channel_info(struct device *dev,
 			break;
 		case IIO_VAL_INT_PLUS_MICRO_DB:
 			scale_db = true;
-			/* fall through */
+			fallthrough;
 		case IIO_VAL_INT_PLUS_MICRO:
 			fract_mult = 100000;
 			break;
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 4bac0646398d..b4323d2db0b1 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1243,13 +1243,16 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ltr501_data *data = iio_priv(indio_dev);
-	u16 buf[8];
+	struct {
+		u16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	__le16 als_buf[2];
 	u8 mask = 0;
 	int j = 0;
 	int ret, psdata;
 
-	memset(buf, 0, sizeof(buf));
+	memset(&scan, 0, sizeof(scan));
 
 	/* figure out which data needs to be ready */
 	if (test_bit(0, indio_dev->active_scan_mask) ||
@@ -1268,9 +1271,9 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 		if (ret < 0)
 			return ret;
 		if (test_bit(0, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[1]);
+			scan.channels[j++] = le16_to_cpu(als_buf[1]);
 		if (test_bit(1, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[0]);
+			scan.channels[j++] = le16_to_cpu(als_buf[0]);
 	}
 
 	if (mask & LTR501_STATUS_PS_RDY) {
@@ -1278,10 +1281,10 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 				       &psdata, 2);
 		if (ret < 0)
 			goto done;
-		buf[j++] = psdata & LTR501_PS_DATA_MASK;
+		scan.channels[j++] = psdata & LTR501_PS_DATA_MASK;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index aa8ed1e3e89a..b8e721bced5b 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -75,6 +75,11 @@
 struct max44000_data {
 	struct mutex lock;
 	struct regmap *regmap;
+	/* Ensure naturally aligned timestamp */
+	struct {
+		u16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Default scale is set to the minimum of 0.03125 or 1 / (1 << 5) lux */
@@ -488,7 +493,6 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max44000_data *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2x u16 + padding + 8 bytes timestamp */
 	int index = 0;
 	unsigned int regval;
 	int ret;
@@ -498,17 +502,17 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 		ret = max44000_read_alsval(data);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index++] = ret;
+		data->scan.channels[index++] = ret;
 	}
 	if (test_bit(MAX44000_SCAN_INDEX_PRX, indio_dev->active_scan_mask)) {
 		ret = regmap_read(data->regmap, MAX44000_REG_PRX_DATA, &regval);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index] = regval;
+		data->scan.channels[index] = regval;
 	}
 	mutex_unlock(&data->lock);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 	return IRQ_HANDLED;
diff --git a/drivers/iio/light/si1145.c b/drivers/iio/light/si1145.c
index 155faaea8c72..8f5f857c2e7d 100644
--- a/drivers/iio/light/si1145.c
+++ b/drivers/iio/light/si1145.c
@@ -1042,7 +1042,7 @@ static int si1145_initialize(struct si1145_data *data)
 						SI1145_LED_CURRENT_45mA);
 		if (ret < 0)
 			return ret;
-		/* fallthrough */
+		fallthrough;
 	case 2:
 		ret = i2c_smbus_write_byte_data(client,
 						SI1145_REG_PS_LED21,
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 6a8ae145f0c0..cbb44e401c0a 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -499,7 +499,7 @@ static int ak8974_detect(struct ak8974 *ak8974)
 	switch (whoami) {
 	case AK8974_WHOAMI_VALUE_AMI306:
 		name = "ami306";
-		/* fall-through */
+		fallthrough;
 	case AK8974_WHOAMI_VALUE_AMI305:
 		ret = regmap_read(ak8974->map, AMI305_VER, &fw);
 		if (ret)
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 03d71f796177..623766ff800b 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -366,6 +366,12 @@ struct ak8975_data {
 	struct iio_mount_matrix orientation;
 	struct regulator	*vdd;
 	struct regulator	*vid;
+
+	/* Ensure natural alignment of timestamp */
+	struct {
+		s16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Enable attached power regulator if any. */
@@ -793,7 +799,6 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	const struct i2c_client *client = data->client;
 	const struct ak_def *def = data->def;
 	int ret;
-	s16 buff[8]; /* 3 x 16 bits axis values + 1 aligned 64 bits timestamp */
 	__le16 fval[3];
 
 	mutex_lock(&data->lock);
@@ -816,12 +821,13 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	mutex_unlock(&data->lock);
 
 	/* Clamp to valid range. */
-	buff[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
-	buff[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
-	buff[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
+	data->scan.channels[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
+	data->scan.channels[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
+	data->scan.channels[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buff,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
+
 	return;
 
 unlock:
diff --git a/drivers/iio/proximity/mb1232.c b/drivers/iio/proximity/mb1232.c
index 654564c45248..ad4b1fb2607a 100644
--- a/drivers/iio/proximity/mb1232.c
+++ b/drivers/iio/proximity/mb1232.c
@@ -40,6 +40,11 @@ struct mb1232_data {
 	 */
 	struct completion	ranging;
 	int			irqnr;
+	/* Ensure correct alignment of data to push to IIO buffer */
+	struct {
+		s16 distance;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static irqreturn_t mb1232_handle_irq(int irq, void *dev_id)
@@ -113,17 +118,13 @@ static irqreturn_t mb1232_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mb1232_data *data = iio_priv(indio_dev);
-	/*
-	 * triggered buffer
-	 * 16-bit channel + 48-bit padding + 64-bit timestamp
-	 */
-	s16 buffer[8] = { 0 };
 
-	buffer[0] = mb1232_read_distance(data);
-	if (buffer[0] < 0)
+	data->scan.distance = mb1232_read_distance(data);
+	if (data->scan.distance < 0)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
+					   pf->timestamp);
 
 err:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index dc0558b23158..fbc28f1a8b92 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3034,7 +3034,7 @@ static int cm_rej_handler(struct cm_work *work)
 	case IB_CM_REP_SENT:
 	case IB_CM_MRA_REP_RCVD:
 		ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
-		/* fall through */
+		fallthrough;
 	case IB_CM_REQ_RCVD:
 	case IB_CM_MRA_REQ_SENT:
 		if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_STALE_CONN)
@@ -3044,7 +3044,7 @@ static int cm_rej_handler(struct cm_work *work)
 		break;
 	case IB_CM_DREQ_SENT:
 		ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
-		/* fall through */
+		fallthrough;
 	case IB_CM_REP_RCVD:
 	case IB_CM_MRA_REP_SENT:
 		cm_enter_timewait(cm_id_priv);
@@ -3058,7 +3058,7 @@ static int cm_rej_handler(struct cm_work *work)
 			cm_enter_timewait(cm_id_priv);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
 			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
@@ -3116,7 +3116,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 			msg_response = CM_MSG_RESPONSE_OTHER;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
 			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
@@ -3227,7 +3227,7 @@ static int cm_mra_handler(struct cm_work *work)
 	case IB_CM_MRA_REP_RCVD:
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_MRA_COUNTER]);
-		/* fall through */
+		fallthrough;
 	default:
 		pr_debug("%s local_id %d, cm_id_priv->id.state: %d\n",
 			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
@@ -4214,7 +4214,7 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
 				qp_attr->retry_cnt = cm_id_priv->retry_count;
 				qp_attr->rnr_retry = cm_id_priv->rnr_retry_count;
 				qp_attr->max_rd_atomic = cm_id_priv->initiator_depth;
-				/* fall through */
+				fallthrough;
 			case IB_QPT_XRC_TGT:
 				*qp_attr_mask |= IB_QP_TIMEOUT;
 				qp_attr->timeout = cm_id_priv->av.timeout;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 26de0dab60bb..7f0e91e92968 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1985,7 +1985,8 @@ static int cma_ib_handler(struct ib_cm_id *cm_id,
 		event.event = RDMA_CM_EVENT_ESTABLISHED;
 		break;
 	case IB_CM_DREQ_ERROR:
-		event.status = -ETIMEDOUT; /* fall through */
+		event.status = -ETIMEDOUT;
+		fallthrough;
 	case IB_CM_DREQ_RECEIVED:
 	case IB_CM_DREP_RECEIVED:
 		if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT,
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 513825e424bf..a92fc3f90bb5 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -379,7 +379,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 {
 	LIST_HEAD(tmp_list);
 	unsigned int nr_cqs, i;
-	struct ib_cq *cq;
+	struct ib_cq *cq, *n;
 	int ret;
 
 	if (poll_ctx > IB_POLL_LAST_POOL_TYPE) {
@@ -412,7 +412,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 	return 0;
 
 out_free_cqs:
-	list_for_each_entry(cq, &tmp_list, pool_entry) {
+	list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) {
 		cq->shared = false;
 		ib_free_cq(cq);
 	}
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index ef0cd2998671..c36b4d2b61e0 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2751,7 +2751,7 @@ static int __init ib_core_init(void)
 
 	ret = addr_init();
 	if (ret) {
-		pr_warn("Could't init IB address resolution\n");
+		pr_warn("Couldn't init IB address resolution\n");
 		goto err_ibnl;
 	}
 
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 614cff89fc71..13f43ab7220b 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -510,7 +510,6 @@ struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	switch (ctx->type) {
 	case RDMA_RW_SIG_MR:
 	case RDMA_RW_MR:
-		/* fallthrough */
 		for (i = 0; i < ctx->nr_ops; i++) {
 			rdma_rw_update_lkey(&ctx->reg[i],
 				ctx->reg[i].wr.wr.opcode !=
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index d03dacaef788..1d184ea05eba 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -794,7 +794,7 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
 	case 2:
 		ib_copy_path_rec_to_user(&resp->ib_route[1],
 					 &route->path_rec[1]);
-		/* fall through */
+		fallthrough;
 	case 1:
 		ib_copy_path_rec_to_user(&resp->ib_route[0],
 					 &route->path_rec[0]);
@@ -820,7 +820,7 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
 	case 2:
 		ib_copy_path_rec_to_user(&resp->ib_route[1],
 					 &route->path_rec[1]);
-		/* fall through */
+		fallthrough;
 	case 1:
 		ib_copy_path_rec_to_user(&resp->ib_route[0],
 					 &route->path_rec[0]);
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index ef04a261097f..e47c5949013f 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -259,7 +259,7 @@ static int uverbs_process_attr(struct bundle_priv *pbundle,
 			return -EOPNOTSUPP;
 
 		e->ptr_attr.enum_id = uattr->attr_data.enum_data.elem_id;
-	/* fall through */
+		fallthrough;
 	case UVERBS_ATTR_TYPE_PTR_IN:
 		/* Ensure that any data provided by userspace beyond the known
 		 * struct is zero. Userspace that knows how to use some future
@@ -271,7 +271,7 @@ static int uverbs_process_attr(struct bundle_priv *pbundle,
 		    !uverbs_is_attr_cleared(uattr, val_spec->u.ptr.len))
 			return -EOPNOTSUPP;
 
-	/* fall through */
+		fallthrough;
 	case UVERBS_ATTR_TYPE_PTR_OUT:
 		if (uattr->len < val_spec->u.ptr.min_len ||
 		    (!val_spec->zero_trailing &&
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 3096e73797b7..307886737646 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1801,7 +1801,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
 
 	dev_put(netdev);
 
-	if (!rc) {
+	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
 		netdev_speed = lksettings.base.speed;
 	} else {
 		netdev_speed = SPEED_1000;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 3f18efc0c297..1d7a9ca5240c 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -752,12 +752,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	gsi_sqp = rdev->gsi_ctx.gsi_sqp;
 	gsi_sah = rdev->gsi_ctx.gsi_sah;
 
-	/* remove from active qp list */
-	mutex_lock(&rdev->qp_lock);
-	list_del(&gsi_sqp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	ibdev_dbg(&rdev->ibdev, "Destroy the shadow AH\n");
 	bnxt_qplib_destroy_ah(&rdev->qplib_res,
 			      &gsi_sah->qplib_ah,
@@ -772,6 +766,12 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	}
 	bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp);
 
+	/* remove from active qp list */
+	mutex_lock(&rdev->qp_lock);
+	list_del(&gsi_sqp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	kfree(rdev->gsi_ctx.sqp_tbl);
 	kfree(gsi_sah);
 	kfree(gsi_sqp);
@@ -792,11 +792,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	unsigned int flags;
 	int rc;
 
-	mutex_lock(&rdev->qp_lock);
-	list_del(&qp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	bnxt_qplib_flush_cqn_wq(&qp->qplib_qp);
 
 	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
@@ -819,6 +814,11 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 			goto sh_fail;
 	}
 
+	mutex_lock(&rdev->qp_lock);
+	list_del(&qp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 
@@ -2657,7 +2657,7 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 			default:
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case IB_WR_SEND_WITH_INV:
 			rc = bnxt_re_build_send_wqe(qp, wr, &wqe);
 			break;
@@ -3264,6 +3264,19 @@ static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc,
 	wc->wc_flags |= IB_WC_GRH;
 }
 
+static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev,
+					u16 vlan_id)
+{
+	/*
+	 * Check if the vlan is configured in the host.  If not configured, it
+	 * can be a transparent VLAN. So dont report the vlan id.
+	 */
+	if (!__vlan_find_dev_deep_rcu(rdev->netdev,
+				      htons(ETH_P_8021Q), vlan_id))
+		return false;
+	return true;
+}
+
 static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe,
 				u16 *vid, u8 *sl)
 {
@@ -3332,9 +3345,11 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
 	wc->src_qp = orig_cqe->src_qp;
 	memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
 	if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
-		wc->vlan_id = vlan_id;
-		wc->sl = sl;
-		wc->wc_flags |= IB_WC_WITH_VLAN;
+		if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) {
+			wc->vlan_id = vlan_id;
+			wc->sl = sl;
+			wc->wc_flags |= IB_WC_WITH_VLAN;
+		}
 	}
 	wc->port_num = 1;
 	wc->vendor_err = orig_cqe->status;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index dad0df8a2467..53aee5a42ab8 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -821,7 +821,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event,
 	struct ib_event event;
 	unsigned int flags;
 
-	if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+	if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR &&
+	    rdma_is_kernel_res(&qp->ib_qp.res)) {
 		flags = bnxt_re_lock_cqs(qp);
 		bnxt_qplib_add_flush_qp(&qp->qplib_qp);
 		bnxt_re_unlock_cqs(qp, flags);
@@ -1008,7 +1009,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
 static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 {
 	struct bnxt_re_ring_attr rattr = {};
-	struct bnxt_qplib_ctx *qplib_ctx;
 	int num_vec_created = 0;
 	int rc = 0, i;
 	u8 type;
@@ -1031,13 +1031,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 	if (rc)
 		goto dealloc_res;
 
-	qplib_ctx = &rdev->qplib_ctx;
 	for (i = 0; i < rdev->num_msix - 1; i++) {
 		struct bnxt_qplib_nq *nq;
 
 		nq = &rdev->nq[i];
-		nq->hwq.max_elements = (qplib_ctx->cq_count +
-					qplib_ctx->srqc_count + 2);
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
 		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x",
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 117b42349a28..f78da54a0bc5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -818,6 +818,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	int rc;
 
 	RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags);
@@ -907,8 +908,9 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 
@@ -935,10 +937,10 @@ static void bnxt_qplib_init_psn_ptr(struct bnxt_qplib_qp *qp, int size)
 
 	sq = &qp->sq;
 	hwq = &sq->hwq;
+	/* First psn entry */
 	fpsne = (u64)bnxt_qplib_get_qe(hwq, hwq->depth, &psn_pg);
 	if (!IS_ALIGNED(fpsne, PAGE_SIZE))
-		indx_pad = ALIGN(fpsne, PAGE_SIZE) / size;
-
+		indx_pad = (fpsne & ~PAGE_MASK) / size;
 	hwq->pad_pgofft = indx_pad;
 	hwq->pad_pg = (u64 *)psn_pg;
 	hwq->pad_stride = size;
@@ -959,6 +961,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	u16 nsge;
 
 	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);
@@ -1111,8 +1114,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 fail:
@@ -1457,10 +1461,12 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	struct cmdq_destroy_qp req;
 	struct creq_destroy_qp_resp resp;
 	u16 cmd_flags = 0;
+	u32 tbl_indx;
 	int rc;
 
-	rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID;
-	rcfw->qp_tbl[qp->id].qp_handle = NULL;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID;
+	rcfw->qp_tbl[tbl_indx].qp_handle = NULL;
 
 	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
 
@@ -1468,8 +1474,8 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
 					  (void *)&resp, NULL, 0);
 	if (rc) {
-		rcfw->qp_tbl[qp->id].qp_id = qp->id;
-		rcfw->qp_tbl[qp->id].qp_handle = qp;
+		rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+		rcfw->qp_tbl[tbl_indx].qp_handle = qp;
 		return rc;
 	}
 
@@ -1779,7 +1785,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 
 			break;
 		}
-		/* fall thru */
+		fallthrough;
 	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM:
 	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV:
 	{
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 4e211162acee..f7736e34ac64 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -307,14 +307,15 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 	__le16  mcookie;
 	u16 cookie;
 	int rc = 0;
-	u32 qp_id;
+	u32 qp_id, tbl_indx;
 
 	pdev = rcfw->pdev;
 	switch (qp_event->event) {
 	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
 		err_event = (struct creq_qp_error_notification *)qp_event;
 		qp_id = le32_to_cpu(err_event->xid);
-		qp = rcfw->qp_tbl[qp_id].qp_handle;
+		tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw);
+		qp = rcfw->qp_tbl[tbl_indx].qp_handle;
 		dev_dbg(&pdev->dev, "Received QP error notification\n");
 		dev_dbg(&pdev->dev,
 			"qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
@@ -615,8 +616,9 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 
 	cmdq->bmap_size = bmap_size;
 
-	rcfw->qp_tbl_size = qp_tbl_sz;
-	rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node),
+	/* Allocate one extra to hold the QP1 entries */
+	rcfw->qp_tbl_size = qp_tbl_sz + 1;
+	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
 			       GFP_KERNEL);
 	if (!rcfw->qp_tbl)
 		goto fail;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 157387636d00..5f2f0a5a3560 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -216,4 +216,9 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
 void bnxt_qplib_mark_qp_error(void *qp_handle);
+static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
+{
+	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+}
 #endif /* __BNXT_QPLIB_RCFW_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 4cd475ea97a2..64d44f51db4b 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -149,7 +149,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	attr->max_inline_data = le32_to_cpu(sb->max_inline_data);
 	attr->l2_db_size = (sb->l2_db_space_size + 1) *
 			    (0x01 << RCFW_DBR_BASE_PAGE_SHIFT);
-	attr->max_sgid = le32_to_cpu(sb->max_gid);
+	attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED;
 
 	bnxt_qplib_query_version(rcfw, attr->fw_ver);
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 6404f0da1051..967890cd81f2 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -47,6 +47,7 @@
 struct bnxt_qplib_dev_attr {
 #define FW_VER_ARR_LEN			4
 	u8				fw_ver[FW_VER_ARR_LEN];
+#define BNXT_QPLIB_NUM_GIDS_SUPPORTED	256
 	u16				max_sgid;
 	u16				max_mrw;
 	u32				max_qp;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 77bc02a9228e..1f288c73ccfc 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2885,7 +2885,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 	case MORIBUND:
 	case CLOSING:
 		stop_ep_timer(ep);
-		/*FALLTHROUGH*/
+		fallthrough;
 	case FPDU_MODE:
 		if (ep->com.qp && ep->com.qp->srq) {
 			srqidx = ABORT_RSS_SRQIDX_G(
@@ -3759,7 +3759,7 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
 			send_fw_act_open_req(ep, atid);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	case FW_EADDRINUSE:
 		set_bit(ACT_RETRY_INUSE, &ep->com.history);
 		if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index ac48012c992f..cbddb20c6121 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1165,7 +1165,7 @@ int c4iw_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 				break;
 			}
 			fw_flags |= FW_RI_RDMA_WRITE_WITH_IMMEDIATE;
-			/*FALLTHROUGH*/
+			fallthrough;
 		case IB_WR_RDMA_WRITE:
 			fw_opcode = FW_RI_RDMA_WRITE_WR;
 			swsqe->opcode = FW_RI_RDMA_WRITE;
diff --git a/drivers/infiniband/hw/hfi1/pio_copy.c b/drivers/infiniband/hw/hfi1/pio_copy.c
index b12e4665c9ab..4a4ec2397857 100644
--- a/drivers/infiniband/hw/hfi1/pio_copy.c
+++ b/drivers/infiniband/hw/hfi1/pio_copy.c
@@ -209,7 +209,6 @@ static inline void jcopy(u8 *dest, const u8 *src, u32 n)
 		fallthrough;
 	case 1:
 		*dest++ = *src++;
-		/* fall through */
 	}
 }
 
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index 9af82ff933d7..73d197e21730 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe)
 	case IB_WR_ATOMIC_CMP_AND_SWP:
 	case IB_WR_ATOMIC_FETCH_AND_ADD:
 	case IB_WR_RDMA_WRITE:
+	case IB_WR_RDMA_WRITE_WITH_IMM:
 		switch (prev->wr.opcode) {
 		case IB_WR_TID_RDMA_WRITE:
 			req = wqe_to_tid_req(prev);
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index da9888deff8c..6edcbdcd8f43 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -65,8 +65,6 @@
 #define HNS_ROCE_CQE_WCMD_EMPTY_BIT		0x2
 #define HNS_ROCE_MIN_CQE_CNT			16
 
-#define HNS_ROCE_RESERVED_SGE			1
-
 #define HNS_ROCE_MAX_IRQ_NUM			128
 
 #define HNS_ROCE_SGE_IN_WQE			2
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 07b4c85d341d..aeb3a6fa7d47 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -535,7 +535,7 @@ static void hns_roce_set_sdb_ext(struct hns_roce_dev *hr_dev, u32 ext_sdb_alept,
 	roce_write(hr_dev, ROCEE_EXT_DB_SQ_H_REG, val);
 
 	dev_dbg(dev, "ext SDB depth: 0x%x\n", db->ext_db->esdb_dep);
-	dev_dbg(dev, "ext SDB threshold: epmty: 0x%x, ful: 0x%x\n",
+	dev_dbg(dev, "ext SDB threshold: empty: 0x%x, ful: 0x%x\n",
 		ext_sdb_alept, ext_sdb_alful);
 }
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index d2968594664b..4cda95ed1fbe 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -633,7 +633,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 
 		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
 
-		if (unlikely(wr->num_sge >= hr_qp->rq.max_gs)) {
+		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			ibdev_err(ibdev, "rq:num_sge=%d >= qp->sq.max_gs=%d\n",
 				  wr->num_sge, hr_qp->rq.max_gs);
 			ret = -EINVAL;
@@ -653,7 +653,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 		if (wr->num_sge < hr_qp->rq.max_gs) {
 			dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
 			dseg->addr = 0;
-			dseg->len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH);
 		}
 
 		/* rq support inline data */
@@ -787,8 +786,8 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq,
 		}
 
 		if (wr->num_sge < srq->max_gs) {
-			dseg[i].len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH);
-			dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
+			dseg[i].len = 0;
+			dseg[i].lkey = cpu_to_le32(0x100);
 			dseg[i].addr = 0;
 		}
 
@@ -5070,7 +5069,7 @@ static int hns_roce_v2_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
 
 	attr->srq_limit = limit_wl;
 	attr->max_wr = srq->wqe_cnt - 1;
-	attr->max_sge = srq->max_gs - HNS_ROCE_RESERVED_SGE;
+	attr->max_sge = srq->max_gs;
 
 out:
 	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 1fb1c583d0f8..ac29be43b6bd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -92,9 +92,7 @@
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
-#define HNS_ROCE_INVALID_LKEY			0x0
-#define HNS_ROCE_INVALID_SGE_LENGTH		0x80000000
-
+#define HNS_ROCE_INVALID_LKEY			0x100
 #define HNS_ROCE_CMQ_TX_TIMEOUT			30000
 #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE	2
 #define HNS_ROCE_V2_RSV_QPS			8
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index e94ca130ff5e..c063c450c715 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -386,8 +386,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 		return -EINVAL;
 	}
 
-	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) +
-					      HNS_ROCE_RESERVED_SGE);
+	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge));
 
 	if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE)
 		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz);
@@ -402,7 +401,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 		hr_qp->rq_inl_buf.wqe_cnt = 0;
 
 	cap->max_recv_wr = cnt;
-	cap->max_recv_sge = hr_qp->rq.max_gs - HNS_ROCE_RESERVED_SGE;
+	cap->max_recv_sge = hr_qp->rq.max_gs;
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index f40a000e94ee..b9e2dbd372b6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -297,7 +297,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq,
 	spin_lock_init(&srq->lock);
 
 	srq->wqe_cnt = roundup_pow_of_two(init_attr->attr.max_wr + 1);
-	srq->max_gs = init_attr->attr.max_sge + HNS_ROCE_RESERVED_SGE;
+	srq->max_gs = init_attr->attr.max_sge;
 
 	if (udata) {
 		ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index fa7a5ff498c7..a3b95805c154 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -2443,7 +2443,7 @@ static void i40iw_handle_rst_pkt(struct i40iw_cm_node *cm_node,
 	case I40IW_CM_STATE_FIN_WAIT1:
 	case I40IW_CM_STATE_LAST_ACK:
 		cm_node->cm_id->rem_ref(cm_node->cm_id);
-		/* fall through */
+		fallthrough;
 	case I40IW_CM_STATE_TIME_WAIT:
 		cm_node->state = I40IW_CM_STATE_CLOSED;
 		i40iw_rem_ref_cm_node(cm_node);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index 688f19667221..86d3f8aff329 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -1964,7 +1964,6 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq,
 		info->out_rdrsp = true;
 		break;
 	case I40IW_AE_SOURCE_RSVD:
-		/* fallthrough */
 	default:
 		break;
 	}
@@ -3762,14 +3761,14 @@ static enum i40iw_status_code cqp_sds_wqe_fill(struct i40iw_sc_cqp *cqp,
 					LS_64(1, I40IW_CQPSQ_UPESD_ENTRY_VALID)));
 
 		set_64bit_val(wqe, 56, info->entry[2].data);
-		/* fallthrough */
+		fallthrough;
 	case 2:
 		set_64bit_val(wqe, 32,
 			      (LS_64(info->entry[1].cmd, I40IW_CQPSQ_UPESD_SDCMD) |
 					LS_64(1, I40IW_CQPSQ_UPESD_ENTRY_VALID)));
 
 		set_64bit_val(wqe, 40, info->entry[1].data);
-		/* fallthrough */
+		fallthrough;
 	case 1:
 		set_64bit_val(wqe, 0,
 			      LS_64(info->entry[0].cmd, I40IW_CQPSQ_UPESD_SDCMD));
diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c
index ae8b97c30665..e1085634b8d9 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_hw.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c
@@ -353,7 +353,6 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 				i40iw_cm_disconn(iwqp);
 			break;
 		case I40IW_AE_BAD_CLOSE:
-			/* fall through */
 		case I40IW_AE_RESET_SENT:
 			i40iw_next_iw_state(iwqp, I40IW_QP_STATE_ERROR, 1, 0, 0);
 			i40iw_cm_disconn(iwqp);
@@ -413,7 +412,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 		case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG:
 		case I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT:
 			ctx_info->err_rq_idx_valid = false;
-			/* fall through */
+			fallthrough;
 		default:
 			if (!info->sq && ctx_info->err_rq_idx_valid) {
 				ctx_info->err_rq_idx = info->wqe_idx;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index 9c96ece5e7f3..58a433135a03 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -1489,36 +1489,35 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev)
 		iwdev->iw_status = 0;
 		i40iw_port_ibevent(iwdev);
 		i40iw_destroy_rdma_device(iwdev->iwibdev);
-		/* fallthrough */
+		fallthrough;
 	case IP_ADDR_REGISTERED:
 		if (!iwdev->reset)
 			i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
-		/* fallthrough */
-		/* fallthrough */
+		fallthrough;
 	case PBLE_CHUNK_MEM:
 		i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc);
-		/* fallthrough */
+		fallthrough;
 	case CEQ_CREATED:
 		i40iw_dele_ceqs(iwdev);
-		/* fallthrough */
+		fallthrough;
 	case AEQ_CREATED:
 		i40iw_destroy_aeq(iwdev);
-		/* fallthrough */
+		fallthrough;
 	case IEQ_CREATED:
 		i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_IEQ, iwdev->reset);
-		/* fallthrough */
+		fallthrough;
 	case ILQ_CREATED:
 		i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_ILQ, iwdev->reset);
-		/* fallthrough */
+		fallthrough;
 	case CCQ_CREATED:
 		i40iw_destroy_ccq(iwdev);
-		/* fallthrough */
+		fallthrough;
 	case HMC_OBJS_CREATED:
 		i40iw_del_hmc_objects(dev, dev->hmc_info, true, iwdev->reset);
-		/* fallthrough */
+		fallthrough;
 	case CQP_CREATED:
 		i40iw_destroy_cqp(iwdev, true);
-		/* fallthrough */
+		fallthrough;
 	case INITIAL_STATE:
 		i40iw_cleanup_cm_core(&iwdev->cm_core);
 		if (iwdev->vsi.pestat) {
@@ -1528,7 +1527,6 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev)
 		i40iw_del_init_mem(iwdev);
 		break;
 	case INVALID_STATE:
-		/* fallthrough */
 	default:
 		i40iw_pr_err("bad init_state = %d\n", iwdev->init_state);
 		break;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index d9c7ae6a7030..924be4b03c9a 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -814,13 +814,13 @@ void i40iw_puda_dele_resources(struct i40iw_sc_vsi *vsi,
 	switch (rsrc->completion) {
 	case PUDA_HASH_CRC_COMPLETE:
 		i40iw_free_hash_desc(rsrc->hash_desc);
-		/* fall through */
+		fallthrough;
 	case PUDA_QP_CREATED:
 		if (!reset)
 			i40iw_puda_free_qp(rsrc);
 
 		i40iw_free_dma_mem(dev->hw, &rsrc->qpmem);
-		/* fallthrough */
+		fallthrough;
 	case PUDA_CQ_CREATED:
 		if (!reset)
 			i40iw_puda_free_cq(rsrc);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 016524683e17..e07fb37af086 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -190,9 +190,8 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 	switch (event) {
 	case NETDEV_DOWN:
 		action = I40IW_ARP_DELETE;
-		/* Fall through */
+		fallthrough;
 	case NETDEV_UP:
-		/* Fall through */
 	case NETDEV_CHANGEADDR:
 
 		/* Just skip if no need to handle ARP cache */
@@ -247,9 +246,8 @@ int i40iw_inet6addr_event(struct notifier_block *notifier,
 	switch (event) {
 	case NETDEV_DOWN:
 		action = I40IW_ARP_DELETE;
-		/* Fall through */
+		fallthrough;
 	case NETDEV_UP:
-		/* Fall through */
 	case NETDEV_CHANGEADDR:
 		i40iw_manage_arp_cache(iwdev,
 				       netdev->dev_addr,
@@ -344,7 +342,7 @@ int i40iw_netdevice_event(struct notifier_block *notifier,
 	switch (event) {
 	case NETDEV_DOWN:
 		iwdev->iw_status = 0;
-		/* Fall through */
+		fallthrough;
 	case NETDEV_UP:
 		i40iw_port_ibevent(iwdev);
 		break;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 6957e4f3404b..b51339328a51 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -810,7 +810,7 @@ void i40iw_hw_modify_qp(struct i40iw_device *iwdev, struct i40iw_qp *iwqp,
 	case I40IW_QP_STATE_RTS:
 		if (iwqp->iwarp_state == I40IW_QP_STATE_IDLE)
 			i40iw_send_reset(iwqp->cm_node);
-		/* fall through */
+		fallthrough;
 	case I40IW_QP_STATE_IDLE:
 	case I40IW_QP_STATE_TERMINATE:
 	case I40IW_QP_STATE_CLOSING:
@@ -2144,7 +2144,6 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 
 		switch (ib_wr->opcode) {
 		case IB_WR_SEND:
-			/* fall-through */
 		case IB_WR_SEND_WITH_INV:
 			if (ib_wr->opcode == IB_WR_SEND) {
 				if (ib_wr->send_flags & IB_SEND_SOLICITED)
@@ -2201,7 +2200,7 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 			break;
 		case IB_WR_RDMA_READ_WITH_INV:
 			inv_stag = true;
-			/* fall-through*/
+			fallthrough;
 		case IB_WR_RDMA_READ:
 			if (ib_wr->num_sge > I40IW_MAX_SGE_RD) {
 				err = -EINVAL;
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index f8b936b76dcd..8a3436994f80 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -765,13 +765,13 @@ repoll:
 		switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
 		case MLX4_OPCODE_RDMA_WRITE_IMM:
 			wc->wc_flags |= IB_WC_WITH_IMM;
-			/* fall through */
+			fallthrough;
 		case MLX4_OPCODE_RDMA_WRITE:
 			wc->opcode    = IB_WC_RDMA_WRITE;
 			break;
 		case MLX4_OPCODE_SEND_IMM:
 			wc->wc_flags |= IB_WC_WITH_IMM;
-			/* fall through */
+			fallthrough;
 		case MLX4_OPCODE_SEND:
 		case MLX4_OPCODE_SEND_INVAL:
 			wc->opcode    = IB_WC_SEND;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 5e7910a517da..bd4f975e7f9a 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -784,7 +784,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->ip_gids = true;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
-	props->pkey_tbl_len	= 1;
+	if (mdev->dev->caps.pkey_table_len[port])
+		props->pkey_tbl_len = 1;
 	props->max_mtu		= IB_MTU_4096;
 	props->max_vl_num	= 2;
 	props->state		= IB_PORT_DOWN;
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index d844831179cf..5e4ec9786081 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -944,7 +944,7 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port,
 	switch (sa_mad->mad_hdr.method) {
 	case IB_MGMT_METHOD_SET:
 		may_create = 1;
-		/* fall through */
+		fallthrough;
 	case IB_SA_METHOD_DELETE:
 		req = kzalloc(sizeof *req, GFP_KERNEL);
 		if (!req)
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index f9ca6e000a81..2975f350b9fd 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1578,12 +1578,12 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 		pd = to_mxrcd(init_attr->xrcd)->pd;
 		xrcdn = to_mxrcd(init_attr->xrcd)->xrcdn;
 		init_attr->send_cq = to_mxrcd(init_attr->xrcd)->cq;
-		/* fall through */
+		fallthrough;
 	case IB_QPT_XRC_INI:
 		if (!(to_mdev(pd->device)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
 			return ERR_PTR(-ENOSYS);
 		init_attr->recv_cq = init_attr->send_cq;
-		/* fall through */
+		fallthrough;
 	case IB_QPT_RC:
 	case IB_QPT_UC:
 	case IB_QPT_RAW_PACKET:
@@ -1592,7 +1592,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 			return ERR_PTR(-ENOMEM);
 		qp->pri.vid = 0xFFFF;
 		qp->alt.vid = 0xFFFF;
-		/* fall through */
+		fallthrough;
 	case IB_QPT_UD:
 	{
 		err = create_qp_common(pd, init_attr, udata, 0, &qp);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 0133ebb8d740..dceb0eb2bed1 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -121,13 +121,13 @@ static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) {
 	case MLX5_OPCODE_RDMA_WRITE_IMM:
 		wc->wc_flags |= IB_WC_WITH_IMM;
-		/* fall through */
+		fallthrough;
 	case MLX5_OPCODE_RDMA_WRITE:
 		wc->opcode    = IB_WC_RDMA_WRITE;
 		break;
 	case MLX5_OPCODE_SEND_IMM:
 		wc->wc_flags |= IB_WC_WITH_IMM;
-		/* fall through */
+		fallthrough;
 	case MLX5_OPCODE_SEND:
 	case MLX5_OPCODE_SEND_INVAL:
 		wc->opcode    = IB_WC_SEND;
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 454ce5de2de7..9bb9bb058932 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -250,9 +250,8 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		if (MLX5_CAP_GEN(dev->mdev, vport_counters) &&
 		    method == IB_MGMT_METHOD_GET)
 			return process_pma_cmd(dev, port_num, in, out);
-		/* fallthrough */
+		fallthrough;
 	case MLX5_IB_VENDOR_CLASS1:
-		/* fallthrough */
 	case MLX5_IB_VENDOR_CLASS2:
 	case IB_MGMT_CLASS_CONG_MGMT: {
 		if (method != IB_MGMT_METHOD_GET &&
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index fbc45a5e76c5..d60d63221b14 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2872,7 +2872,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 		break;
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		handle_general_event(ibdev, work->param, &ibev);
-		/* fall through */
+		fallthrough;
 	default:
 		goto out;
 	}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 59fce5fac7a3..5758dbe64045 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -416,7 +416,7 @@ static int sq_overhead(struct ib_qp_init_attr *attr)
 	switch (attr->qp_type) {
 	case IB_QPT_XRC_INI:
 		size += sizeof(struct mlx5_wqe_xrc_seg);
-		/* fall through */
+		fallthrough;
 	case IB_QPT_RC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
 			max(sizeof(struct mlx5_wqe_atomic_seg) +
@@ -441,7 +441,7 @@ static int sq_overhead(struct ib_qp_init_attr *attr)
 		if (attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO)
 			size += sizeof(struct mlx5_wqe_eth_pad) +
 				sizeof(struct mlx5_wqe_eth_seg);
-		/* fall through */
+		fallthrough;
 	case IB_QPT_SMI:
 	case MLX5_IB_QPT_HW_GSI:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c
index 0823c0bc7e73..f051f4e06b53 100644
--- a/drivers/infiniband/hw/mthca/mthca_av.c
+++ b/drivers/infiniband/hw/mthca/mthca_av.c
@@ -115,7 +115,7 @@ static u8 ib_rate_to_memfree(u8 req_rate, u8 cur_rate)
 	switch ((cur_rate - 1) / req_rate) {
 	case 0:	 return MTHCA_RATE_MEMFREE_FULL;
 	case 1:	 return MTHCA_RATE_MEMFREE_HALF;
-	case 2:	 /* fall through */
+	case 2:
 	case 3:	 return MTHCA_RATE_MEMFREE_QUARTER;
 	default: return MTHCA_RATE_MEMFREE_EIGHTH;
 	}
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 6cdbec13756a..c1751c9a0f62 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -2134,7 +2134,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		case IB_WR_SEND_WITH_IMM:
 			hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT);
 			hdr->immdt = ntohl(wr->ex.imm_data);
-			/* fall through */
+			fallthrough;
 		case IB_WR_SEND:
 			hdr->cw |= (OCRDMA_SEND << OCRDMA_WQE_OPCODE_SHIFT);
 			ocrdma_build_send(qp, hdr, wr);
@@ -2148,7 +2148,7 @@ int ocrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			hdr->cw |= (OCRDMA_FLAG_IMM << OCRDMA_WQE_FLAGS_SHIFT);
 			hdr->immdt = ntohl(wr->ex.imm_data);
-			/* fall through */
+			fallthrough;
 		case IB_WR_RDMA_WRITE:
 			hdr->cw |= (OCRDMA_WRITE << OCRDMA_WQE_OPCODE_SHIFT);
 			status = ocrdma_build_write(qp, hdr, wr);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 4ce4e2eef6cc..b49bef94637e 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -3528,7 +3528,7 @@ static int __qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		break;
 	case IB_WR_RDMA_READ_WITH_INV:
 		SET_FIELD2(wqe->flags, RDMA_SQ_RDMA_WQE_1ST_READ_INV_FLG, 1);
-		/* fallthrough -- same is identical to RDMA READ */
+		fallthrough;	/* same is identical to RDMA READ */
 
 	case IB_WR_RDMA_READ:
 		wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_RD;
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index ca5ea734e3d0..44150be215bf 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -2973,11 +2973,11 @@ static u32 qib_6120_iblink_state(u64 ibcs)
 		state = IB_PORT_ARMED;
 		break;
 	case IB_6120_L_STATE_ACTIVE:
-		/* fall through */
 	case IB_6120_L_STATE_ACT_DEFER:
 		state = IB_PORT_ACTIVE;
 		break;
-	default: /* fall through */
+	default:
+		fallthrough;
 	case IB_6120_L_STATE_DOWN:
 		state = IB_PORT_DOWN;
 		break;
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index ea3ddb05cbad..0a6f26d4cb31 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -3586,11 +3586,11 @@ static u32 qib_7220_iblink_state(u64 ibcs)
 		state = IB_PORT_ARMED;
 		break;
 	case IB_7220_L_STATE_ACTIVE:
-		/* fall through */
 	case IB_7220_L_STATE_ACT_DEFER:
 		state = IB_PORT_ACTIVE;
 		break;
-	default: /* fall through */
+	default:
+		fallthrough;
 	case IB_7220_L_STATE_DOWN:
 		state = IB_PORT_DOWN;
 		break;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 8bcbc884e5b6..a10eab89aee4 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -5508,11 +5508,11 @@ static u32 qib_7322_iblink_state(u64 ibcs)
 		state = IB_PORT_ARMED;
 		break;
 	case IB_7322_L_STATE_ACTIVE:
-		/* fall through */
 	case IB_7322_L_STATE_ACT_DEFER:
 		state = IB_PORT_ACTIVE;
 		break;
-	default: /* fall through */
+	default:
+		fallthrough;
 	case IB_7322_L_STATE_DOWN:
 		state = IB_PORT_DOWN;
 		break;
@@ -6533,7 +6533,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 				    "Invalid num_vls %u, using 4 VLs\n",
 				    qib_num_cfg_vls);
 			qib_num_cfg_vls = 4;
-			/* fall through */
+			fallthrough;
 		case 4:
 			ppd->vls_supported = IB_VL_VL0_3;
 			break;
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 79bb83222e8d..e7789e724f56 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -433,7 +433,7 @@ static int check_mkey(struct qib_ibport *ibp, struct ib_smp *smp, int mad_flags)
 			/* Bad mkey not a violation below level 2 */
 			if (ibp->rvp.mkeyprot < 2)
 				break;
-			/* fall through */
+			fallthrough;
 		case IB_MGMT_METHOD_SET:
 		case IB_MGMT_METHOD_TRAP_REPRESS:
 			if (ibp->rvp.mkey_violations != 0xFFFF)
@@ -828,7 +828,7 @@ static int subn_set_portinfo(struct ib_smp *smp, struct ib_device *ibdev,
 	case IB_PORT_NOP:
 		if (lstate == 0)
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case IB_PORT_DOWN:
 		if (lstate == 0)
 			lstate = QIB_IB_LINKDOWN_ONLY;
@@ -1928,7 +1928,7 @@ static int process_subn(struct ib_device *ibdev, int mad_flags,
 				ret = IB_MAD_RESULT_SUCCESS;
 				goto bail;
 			}
-			/* FALLTHROUGH */
+			fallthrough;
 		default:
 			smp->status |= IB_SMP_UNSUP_METH_ATTR;
 			ret = reply(smp);
@@ -1962,7 +1962,7 @@ static int process_subn(struct ib_device *ibdev, int mad_flags,
 				ret = IB_MAD_RESULT_SUCCESS;
 				goto bail;
 			}
-			/* FALLTHROUGH */
+			fallthrough;
 		default:
 			smp->status |= IB_SMP_UNSUP_METH_ATTR;
 			ret = reply(smp);
@@ -2322,7 +2322,7 @@ static int process_cc(struct ib_device *ibdev, int mad_flags,
 			ret = cc_get_congestion_control_table(ccp, ibdev, port);
 			goto bail;
 
-			/* FALLTHROUGH */
+			fallthrough;
 		default:
 			ccp->status |= IB_SMP_UNSUP_METH_ATTR;
 			ret = reply((struct ib_smp *) ccp);
@@ -2339,7 +2339,7 @@ static int process_cc(struct ib_device *ibdev, int mad_flags,
 			ret = cc_set_congestion_control_table(ccp, ibdev, port);
 			goto bail;
 
-			/* FALLTHROUGH */
+			fallthrough;
 		default:
 			ccp->status |= IB_SMP_UNSUP_METH_ATTR;
 			ret = reply((struct ib_smp *) ccp);
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index aaf7438258fa..3915e5b4a9bc 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -83,7 +83,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 			rvt_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(ATOMIC_ACKNOWLEDGE):
 		/*
 		 * We can increment the tail pointer now that the last
@@ -92,7 +92,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 		 */
 		if (++qp->s_tail_ack_queue > QIB_MAX_RDMA_ATOMIC)
 			qp->s_tail_ack_queue = 0;
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_ONLY):
 	case OP(ACKNOWLEDGE):
 		/* Check for no next entry in the queue. */
@@ -149,7 +149,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 
 	case OP(RDMA_READ_RESPONSE_FIRST):
 		qp->s_ack_state = OP(RDMA_READ_RESPONSE_MIDDLE);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(RDMA_READ_RESPONSE_MIDDLE):
 		qp->s_cur_sge = &qp->s_ack_rdma_sge;
 		qp->s_rdma_mr = qp->s_ack_rdma_sge.sge.mr;
@@ -471,10 +471,10 @@ no_flow_control:
 		 * See qib_restart_rc().
 		 */
 		qp->s_len = restart_sge(&qp->s_sge, wqe, qp->s_psn, pmtu);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_FIRST):
 		qp->s_state = OP(SEND_MIDDLE);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_MIDDLE):
 		bth2 = qp->s_psn++ & QIB_PSN_MASK;
 		ss = &qp->s_sge;
@@ -510,10 +510,10 @@ no_flow_control:
 		 * See qib_restart_rc().
 		 */
 		qp->s_len = restart_sge(&qp->s_sge, wqe, qp->s_psn, pmtu);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(RDMA_WRITE_FIRST):
 		qp->s_state = OP(RDMA_WRITE_MIDDLE);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(RDMA_WRITE_MIDDLE):
 		bth2 = qp->s_psn++ & QIB_PSN_MASK;
 		ss = &qp->s_sge;
@@ -1807,7 +1807,7 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr,
 		if (!ret)
 			goto rnr_nak;
 		qp->r_rcv_len = 0;
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_MIDDLE):
 	case OP(RDMA_WRITE_MIDDLE):
 send_middle:
@@ -1839,7 +1839,7 @@ send_middle:
 		qp->r_rcv_len = 0;
 		if (opcode == OP(SEND_ONLY))
 			goto no_immediate_data;
-		/* fall through -- for SEND_ONLY_WITH_IMMEDIATE */
+		fallthrough;	/* for SEND_ONLY_WITH_IMMEDIATE */
 	case OP(SEND_LAST_WITH_IMMEDIATE):
 send_last_imm:
 		wc.ex.imm_data = ohdr->u.imm_data;
diff --git a/drivers/infiniband/hw/qib/qib_sdma.c b/drivers/infiniband/hw/qib/qib_sdma.c
index 99e11c347130..8f8d61736656 100644
--- a/drivers/infiniband/hw/qib/qib_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_sdma.c
@@ -763,7 +763,7 @@ void __qib_sdma_process_event(struct qib_pportdata *ppd,
 			 * bringing the link up with traffic active on
 			 * 7220, e.g. */
 			ss->go_s99_running = 1;
-			/* fall through -- and start dma engine */
+			fallthrough;	/* and start dma engine */
 		case qib_sdma_event_e10_go_hw_start:
 			/* This reference means the state machine is started */
 			sdma_get(&ppd->sdma_state);
diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
index e17b91e2c22a..554af4273a13 100644
--- a/drivers/infiniband/hw/qib/qib_uc.c
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -161,7 +161,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags)
 
 	case OP(SEND_FIRST):
 		qp->s_state = OP(SEND_MIDDLE);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_MIDDLE):
 		len = qp->s_len;
 		if (len > pmtu) {
@@ -185,7 +185,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags)
 
 	case OP(RDMA_WRITE_FIRST):
 		qp->s_state = OP(RDMA_WRITE_MIDDLE);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(RDMA_WRITE_MIDDLE):
 		len = qp->s_len;
 		if (len > pmtu) {
@@ -351,7 +351,7 @@ send_first:
 			goto no_immediate_data;
 		else if (opcode == OP(SEND_ONLY_WITH_IMMEDIATE))
 			goto send_last_imm;
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(SEND_MIDDLE):
 		/* Check for invalid length PMTU or posted rwqe len. */
 		if (unlikely(tlen != (hdrsize + pmtu + 4)))
@@ -440,7 +440,7 @@ rdma_first:
 			wc.ex.imm_data = ohdr->u.rc.imm_data;
 			goto rdma_last_imm;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case OP(RDMA_WRITE_MIDDLE):
 		/* Check for invalid length PMTU or posted rwqe len. */
 		if (unlikely(tlen != (hdrsize + pmtu + 4)))
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 7acf9ba5358a..f6c01bad5a74 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -237,7 +237,7 @@ static void qib_qp_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr,
 	case IB_QPT_GSI:
 		if (ib_qib_disable_sma)
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case IB_QPT_UD:
 		qib_ud_rcv(ibp, hdr, has_grh, data, tlen, qp);
 		break;
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index c9abe1c01e4e..662e7fc7f628 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -120,7 +120,7 @@ static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev)
 								IB_QPS_ERR,
 								NULL);
 				if (status) {
-					usnic_err("Failed to transistion qp grp %u from %s to %s\n",
+					usnic_err("Failed to transition qp grp %u from %s to %s\n",
 						qp_grp->grp_id,
 						usnic_ib_qp_grp_state_to_string
 						(cur_state),
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index afcc2abcf55c..9a8f2a9507be 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -238,7 +238,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 			ret = -EINVAL;
 			goto err_qp;
 		}
-		/* fall through */
+		fallthrough;
 	case IB_QPT_RC:
 	case IB_QPT_UD:
 		qp = kzalloc(sizeof(*qp), GFP_KERNEL);
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 332a8ba94b81..ee48befc8978 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1111,7 +1111,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		if (init_attr->port_num == 0 ||
 		    init_attr->port_num > ibpd->device->phys_port_cnt)
 			return ERR_PTR(-EINVAL);
-		/* fall through */
+		fallthrough;
 	case IB_QPT_UC:
 	case IB_QPT_RC:
 	case IB_QPT_UD:
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 907203afbd99..77f2c7cd1216 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -40,6 +40,8 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib");
 MODULE_DESCRIPTION("Soft RDMA transport");
 MODULE_LICENSE("Dual BSD/GPL");
 
+bool rxe_initialized;
+
 /* free resources for a rxe device all objects created for this device must
  * have been destroyed
  */
@@ -315,6 +317,7 @@ static int __init rxe_module_init(void)
 		return err;
 
 	rdma_link_register(&rxe_link_ops);
+	rxe_initialized = true;
 	pr_info("loaded\n");
 	return 0;
 }
@@ -326,6 +329,7 @@ static void __exit rxe_module_exit(void)
 	rxe_net_exit();
 	rxe_cache_exit();
 
+	rxe_initialized = false;
 	pr_info("unloaded\n");
 }
 
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index fb07eed9e402..cae1b0a24c85 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -67,6 +67,8 @@
 
 #define RXE_ROCE_V2_SPORT		(0xc000)
 
+extern bool rxe_initialized;
+
 static inline u32 rxe_crc32(struct rxe_dev *rxe,
 			    u32 crc, void *next, size_t len)
 {
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 4bc88708b355..7b4df0028388 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -282,7 +282,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
 		if ((syn & AETH_TYPE_MASK) != AETH_ACK)
 			return COMPST_ERROR;
 
-		/* fall through */
+		fallthrough;
 		/* (IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE doesn't have an AETH)
 		 */
 	case IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE:
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index cdd811a45120..ce24144de16a 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -205,6 +205,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
 			vaddr = page_address(sg_page_iter_page(&sg_iter));
 			if (!vaddr) {
 				pr_warn("null vaddr\n");
+				ib_umem_release(umem);
 				err = -ENOMEM;
 				goto err1;
 			}
diff --git a/drivers/infiniband/sw/rxe/rxe_sysfs.c b/drivers/infiniband/sw/rxe/rxe_sysfs.c
index ccda5f5a3bc0..2af31d421bfc 100644
--- a/drivers/infiniband/sw/rxe/rxe_sysfs.c
+++ b/drivers/infiniband/sw/rxe/rxe_sysfs.c
@@ -61,6 +61,11 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp)
 	struct net_device *ndev;
 	struct rxe_dev *exists;
 
+	if (!rxe_initialized) {
+		pr_err("Module parameters are not supported, use rdma link add or rxe_cfg\n");
+		return -EAGAIN;
+	}
+
 	len = sanitize_arg(val, intf, sizeof(intf));
 	if (!len) {
 		pr_err("add: invalid interface name\n");
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index 08f05ac5f5d5..ecdac3f8fcc9 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -71,7 +71,7 @@ void rxe_do_task(unsigned long data)
 
 	case TASK_STATE_BUSY:
 		task->state = TASK_STATE_ARMED;
-		/* fall through */
+		fallthrough;
 	case TASK_STATE_ARMED:
 		spin_unlock_irqrestore(&task->state_lock, flags);
 		return;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index bb61e534e468..8522e9a3e914 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -540,7 +540,7 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr,
 		switch (wr->opcode) {
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			wr->ex.imm_data = ibwr->ex.imm_data;
-			/* fall through */
+			fallthrough;
 		case IB_WR_RDMA_READ:
 		case IB_WR_RDMA_WRITE:
 			wr->wr.rdma.remote_addr = rdma_wr(ibwr)->remote_addr;
@@ -1056,7 +1056,7 @@ static ssize_t parent_show(struct device *device,
 	struct rxe_dev *rxe =
 		rdma_device_to_drv_device(device, struct rxe_dev, ib_dev);
 
-	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1));
 }
 
 static DEVICE_ATTR_RO(parent);
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 1662216be66d..66764f7ef072 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -1224,12 +1224,10 @@ static void siw_cm_llp_data_ready(struct sock *sk)
 
 	switch (cep->state) {
 	case SIW_EPSTATE_RDMA_MODE:
-		/* fall through */
 	case SIW_EPSTATE_LISTENING:
 		break;
 
 	case SIW_EPSTATE_AWAIT_MPAREQ:
-		/* fall through */
 	case SIW_EPSTATE_AWAIT_MPAREP:
 		siw_cm_queue_work(cep, SIW_CM_WORK_READ_MPAHDR);
 		break;
diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index 857be5a7d0bd..4bd1f1f84057 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -1215,7 +1215,7 @@ static int siw_rdmap_complete(struct siw_qp *qp, int error)
 	case RDMAP_SEND_SE:
 	case RDMAP_SEND_SE_INVAL:
 		wqe->rqe.flags |= SIW_WQE_SOLICITED;
-		/* Fall through */
+		fallthrough;
 
 	case RDMAP_SEND:
 	case RDMAP_SEND_INVAL:
@@ -1386,7 +1386,7 @@ int siw_tcp_rx_data(read_descriptor_t *rd_desc, struct sk_buff *skb,
 			 * DDP segment.
 			 */
 			qp->rx_fpdu->first_ddp_seg = 0;
-			/* Fall through */
+			fallthrough;
 
 		case SIW_GET_DATA_START:
 			/*
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 9f53aa4feb87..d19d8325588b 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -1042,7 +1042,7 @@ next_wqe:
 		case SIW_OP_SEND_REMOTE_INV:
 		case SIW_OP_WRITE:
 			siw_wqe_put_mem(wqe, tx_type);
-			/* Fall through */
+			fallthrough;
 
 		case SIW_OP_INVAL_STAG:
 		case SIW_OP_REG_MR:
@@ -1128,7 +1128,7 @@ next_wqe:
 		case SIW_OP_READ:
 		case SIW_OP_READ_LOCAL_INV:
 			siw_wqe_put_mem(wqe, tx_type);
-			/* Fall through */
+			fallthrough;
 
 		case SIW_OP_INVAL_STAG:
 		case SIW_OP_REG_MR:
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 9bf0fa30df28..7c41fb040f7c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -512,13 +512,13 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id,
 		return ipoib_cm_req_handler(cm_id, event);
 	case IB_CM_DREQ_RECEIVED:
 		ib_send_cm_drep(cm_id, NULL, 0);
-		/* Fall through */
+		fallthrough;
 	case IB_CM_REJ_RECEIVED:
 		p = cm_id->context;
 		priv = ipoib_priv(p->dev);
 		if (ib_modify_qp(p->qp, &ipoib_cm_err_attr, IB_QP_STATE))
 			ipoib_warn(priv, "unable to move qp to error state\n");
-		/* Fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 752581a8627b..ab75b7f745d4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -502,7 +502,7 @@ static struct net_device *ipoib_get_net_dev_by_params(
 	default:
 		dev_warn_ratelimited(&dev->dev,
 				     "duplicate IP address detected\n");
-		/* Fall through */
+		fallthrough;
 	case 1:
 		return net_dev;
 	}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 699e075ae1b3..2f3ebc0a75d9 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -711,7 +711,7 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 	case RDMA_CM_EVENT_REJECTED:
 		iser_info("Connection rejected: %s\n",
 			 rdma_reject_msg(cma_id, event->status));
-		/* FALLTHROUGH */
+		fallthrough;
 	case RDMA_CM_EVENT_ADDR_ERROR:
 	case RDMA_CM_EVENT_ROUTE_ERROR:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 61e2f7fc513d..695f701dc43d 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -140,15 +140,15 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
-		dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc,
-					ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+		dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf,
+					ISER_RX_SIZE, DMA_FROM_DEVICE);
 		if (ib_dma_mapping_error(ib_dev, dma_addr))
 			goto dma_map_fail;
 
 		rx_desc->dma_addr = dma_addr;
 
 		rx_sg = &rx_desc->rx_sg;
-		rx_sg->addr = rx_desc->dma_addr;
+		rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc);
 		rx_sg->length = ISER_RX_PAYLOAD_SIZE;
 		rx_sg->lkey = device->pd->local_dma_lkey;
 		rx_desc->rx_cqe.done = isert_recv_done;
@@ -160,7 +160,7 @@ dma_map_fail:
 	rx_desc = isert_conn->rx_descs;
 	for (j = 0; j < i; j++, rx_desc++) {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 	kfree(isert_conn->rx_descs);
 	isert_conn->rx_descs = NULL;
@@ -181,7 +181,7 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 
 	kfree(isert_conn->rx_descs);
@@ -299,10 +299,9 @@ isert_free_login_buf(struct isert_conn *isert_conn)
 			    ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE);
 	kfree(isert_conn->login_rsp_buf);
 
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE,
-			    DMA_FROM_DEVICE);
-	kfree(isert_conn->login_req_buf);
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+	kfree(isert_conn->login_desc);
 }
 
 static int
@@ -311,25 +310,25 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 {
 	int ret;
 
-	isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf),
+	isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc),
 			GFP_KERNEL);
-	if (!isert_conn->login_req_buf)
+	if (!isert_conn->login_desc)
 		return -ENOMEM;
 
-	isert_conn->login_req_dma = ib_dma_map_single(ib_dev,
-				isert_conn->login_req_buf,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma);
+	isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev,
+				isert_conn->login_desc->buf,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
+	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr);
 	if (ret) {
-		isert_err("login_req_dma mapping error: %d\n", ret);
-		isert_conn->login_req_dma = 0;
-		goto out_free_login_req_buf;
+		isert_err("login_desc dma mapping error: %d\n", ret);
+		isert_conn->login_desc->dma_addr = 0;
+		goto out_free_login_desc;
 	}
 
 	isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL);
 	if (!isert_conn->login_rsp_buf) {
 		ret = -ENOMEM;
-		goto out_unmap_login_req_buf;
+		goto out_unmap_login_desc;
 	}
 
 	isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev,
@@ -346,11 +345,11 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 
 out_free_login_rsp_buf:
 	kfree(isert_conn->login_rsp_buf);
-out_unmap_login_req_buf:
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-out_free_login_req_buf:
-	kfree(isert_conn->login_req_buf);
+out_unmap_login_desc:
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+out_free_login_desc:
+	kfree(isert_conn->login_desc);
 	return ret;
 }
 
@@ -476,7 +475,7 @@ isert_connect_release(struct isert_conn *isert_conn)
 	if (isert_conn->qp)
 		isert_destroy_qp(isert_conn);
 
-	if (isert_conn->login_req_buf)
+	if (isert_conn->login_desc)
 		isert_free_login_buf(isert_conn);
 
 	isert_device_put(device);
@@ -664,8 +663,8 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_ESTABLISHED:
 		isert_connected_handler(cma_id);
 		break;
-	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
-	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_DISCONNECTED:
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
 		ret = isert_disconnected_handler(cma_id, event->event);
 		break;
@@ -684,7 +683,7 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_REJECTED:
 		isert_info("Connection rejected: %s\n",
 			   rdma_reject_msg(cma_id, event->status));
-		/* fall through */
+		fallthrough;
 	case RDMA_CM_EVENT_UNREACHABLE:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 		ret = isert_connect_error(cma_id);
@@ -862,17 +861,18 @@ isert_login_post_recv(struct isert_conn *isert_conn)
 	int ret;
 
 	memset(&sge, 0, sizeof(struct ib_sge));
-	sge.addr = isert_conn->login_req_dma;
+	sge.addr = isert_conn->login_desc->dma_addr +
+		isert_get_hdr_offset(isert_conn->login_desc);
 	sge.length = ISER_RX_PAYLOAD_SIZE;
 	sge.lkey = isert_conn->device->pd->local_dma_lkey;
 
 	isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n",
 		sge.addr, sge.length, sge.lkey);
 
-	isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done;
+	isert_conn->login_desc->rx_cqe.done = isert_login_recv_done;
 
 	memset(&rx_wr, 0, sizeof(struct ib_recv_wr));
-	rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe;
+	rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe;
 	rx_wr.sg_list = &sge;
 	rx_wr.num_sge = 1;
 
@@ -949,7 +949,7 @@ post_send:
 static void
 isert_rx_login_req(struct isert_conn *isert_conn)
 {
-	struct iser_rx_desc *rx_desc = isert_conn->login_req_buf;
+	struct iser_rx_desc *rx_desc = isert_conn->login_desc;
 	int rx_buflen = isert_conn->login_req_len;
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_login *login = conn->conn_login;
@@ -961,7 +961,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 
 	if (login->first_request) {
 		struct iscsi_login_req *login_req =
-			(struct iscsi_login_req *)&rx_desc->iscsi_header;
+			(struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc);
 		/*
 		 * Setup the initial iscsi_login values from the leading
 		 * login request PDU.
@@ -980,13 +980,13 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 		login->tsih		= be16_to_cpu(login_req->tsih);
 	}
 
-	memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN);
+	memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN);
 
 	size = min(rx_buflen, MAX_KEY_VALUE_PAIRS);
 	isert_dbg("Using login payload size: %d, rx_buflen: %d "
 		  "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen,
 		  MAX_KEY_VALUE_PAIRS);
-	memcpy(login->req_buf, &rx_desc->data[0], size);
+	memcpy(login->req_buf, isert_get_data(rx_desc), size);
 
 	if (login->first_request) {
 		complete(&isert_conn->login_comp);
@@ -1051,14 +1051,15 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (imm_data_len != data_len) {
 		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
 		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
-				    &rx_desc->data[0], imm_data_len);
+				    isert_get_data(rx_desc), imm_data_len);
 		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
 			  sg_nents, imm_data_len);
 	} else {
 		sg_init_table(&isert_cmd->sg, 1);
 		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
 		cmd->se_cmd.t_data_nents = 1;
-		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc),
+				imm_data_len);
 		isert_dbg("Transfer Immediate imm_data_len: %d\n",
 			  imm_data_len);
 	}
@@ -1127,9 +1128,9 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	}
 	isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u "
 		  "sg_nents: %u from %p %u\n", sg_start, sg_off,
-		  sg_nents, &rx_desc->data[0], unsol_data_len);
+		  sg_nents, isert_get_data(rx_desc), unsol_data_len);
 
-	sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0],
+	sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc),
 			    unsol_data_len);
 
 	rc = iscsit_check_dataout_payload(cmd, hdr, false);
@@ -1188,7 +1189,7 @@ isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd
 	}
 	cmd->text_in_ptr = text_in;
 
-	memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length);
+	memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length);
 
 	return iscsit_process_text_cmd(conn, cmd, hdr);
 }
@@ -1198,7 +1199,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 		uint32_t read_stag, uint64_t read_va,
 		uint32_t write_stag, uint64_t write_va)
 {
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_cmd *cmd;
 	struct isert_cmd *isert_cmd;
@@ -1296,8 +1297,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct isert_conn *isert_conn = wc->qp->qp_context;
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe);
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
-	struct iser_ctrl *iser_ctrl = &rx_desc->iser_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
+	struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc);
 	uint64_t read_va = 0, write_va = 0;
 	uint32_t read_stag = 0, write_stag = 0;
 
@@ -1311,7 +1312,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rx_desc->in_use = true;
 
 	ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n",
 		 rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags,
@@ -1346,7 +1347,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			read_stag, read_va, write_stag, write_va);
 
 	ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void
@@ -1360,8 +1361,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
-	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr,
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN;
 
@@ -1376,8 +1377,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	complete(&isert_conn->login_req_comp);
 	mutex_unlock(&isert_conn->mutex);
 
-	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void
@@ -1470,7 +1471,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err)
 			transport_generic_free_cmd(&cmd->se_cmd, 0);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		iscsit_release_cmd(cmd);
 		break;
@@ -1648,7 +1649,7 @@ isert_do_control_comp(struct work_struct *work)
 	switch (cmd->i_state) {
 	case ISTATE_SEND_TASKMGTRSP:
 		iscsit_tmr_post_handler(cmd, cmd->conn);
-		/* fall through */
+		fallthrough;
 	case ISTATE_SEND_REJECT:
 	case ISTATE_SEND_TEXTRSP:
 		cmd->i_state = ISTATE_SENT_STATUS;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index c55f7d9bfced..7fee4a65e181 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -59,9 +59,11 @@
 				ISERT_MAX_TX_MISC_PDUS	+ \
 				ISERT_MAX_RX_MISC_PDUS)
 
-#define ISER_RX_PAD_SIZE	(ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
-		(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
-		 sizeof(struct ib_cqe) + sizeof(bool)))
+/*
+ * RX size is default of 8k plus headers, but data needs to align to
+ * 512 boundary, so use 1024 to have the extra space for alignment.
+ */
+#define ISER_RX_SIZE		(ISCSI_DEF_MAX_RECV_SEG_LEN + 1024)
 
 /* Maximum support is 16MB I/O size */
 #define ISCSI_ISER_MAX_SG_TABLESIZE	4096
@@ -81,21 +83,41 @@ enum iser_conn_state {
 };
 
 struct iser_rx_desc {
-	struct iser_ctrl iser_header;
-	struct iscsi_hdr iscsi_header;
-	char		data[ISCSI_DEF_MAX_RECV_SEG_LEN];
+	char		buf[ISER_RX_SIZE];
 	u64		dma_addr;
 	struct ib_sge	rx_sg;
 	struct ib_cqe	rx_cqe;
 	bool		in_use;
-	char		pad[ISER_RX_PAD_SIZE];
-} __packed;
+};
 
 static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe)
 {
 	return container_of(cqe, struct iser_rx_desc, rx_cqe);
 }
 
+static void *isert_get_iser_hdr(struct iser_rx_desc *desc)
+{
+	return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN;
+}
+
+static size_t isert_get_hdr_offset(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) - (void *)desc->buf;
+}
+
+static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl);
+}
+
+static void *isert_get_data(struct iser_rx_desc *desc)
+{
+	void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN;
+
+	WARN_ON((uintptr_t)data & 511);
+	return data;
+}
+
 struct iser_tx_desc {
 	struct iser_ctrl iser_header;
 	struct iscsi_hdr iscsi_header;
@@ -142,9 +164,8 @@ struct isert_conn {
 	u32			responder_resources;
 	u32			initiator_depth;
 	bool			pi_support;
-	struct iser_rx_desc	*login_req_buf;
+	struct iser_rx_desc	*login_desc;
 	char			*login_rsp_buf;
-	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
 	struct iser_rx_desc	*rx_descs;
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
index 874a8eb7638c..4933085a864a 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
@@ -547,7 +547,6 @@ static void vema_get(struct opa_vnic_vema_port *port,
 		vema_get_mac_entries(port, recvd_mad, rsp_mad);
 		break;
 	case OPA_EM_ATTR_IFACE_UCAST_MACS:
-		/* fall through */
 	case OPA_EM_ATTR_IFACE_MCAST_MACS:
 		vema_get_mac_list(port, recvd_mad, rsp_mad, attr_id);
 		break;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
index 3d7877534bcc..cf6a2be61695 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
@@ -152,13 +152,6 @@ static struct attribute_group rtrs_srv_stats_attr_group = {
 	.attrs = rtrs_srv_stats_attrs,
 };
 
-static void rtrs_srv_dev_release(struct device *dev)
-{
-	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
-
-	kfree(srv);
-}
-
 static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 {
 	struct rtrs_srv *srv = sess->srv;
@@ -172,7 +165,6 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		goto unlock;
 	}
 	srv->dev.class = rtrs_dev_class;
-	srv->dev.release = rtrs_srv_dev_release;
 	err = dev_set_name(&srv->dev, "%s", sess->s.sessname);
 	if (err)
 		goto unlock;
@@ -182,16 +174,16 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 	 * sysfs files are created
 	 */
 	dev_set_uevent_suppress(&srv->dev, true);
-	err = device_register(&srv->dev);
+	err = device_add(&srv->dev);
 	if (err) {
-		pr_err("device_register(): %d\n", err);
+		pr_err("device_add(): %d\n", err);
 		goto put;
 	}
 	srv->kobj_paths = kobject_create_and_add("paths", &srv->dev.kobj);
 	if (!srv->kobj_paths) {
 		err = -ENOMEM;
 		pr_err("kobject_create_and_add(): %d\n", err);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 		goto unlock;
 	}
 	dev_set_uevent_suppress(&srv->dev, false);
@@ -216,7 +208,7 @@ rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		kobject_del(srv->kobj_paths);
 		kobject_put(srv->kobj_paths);
 		mutex_unlock(&srv->paths_mutex);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 	} else {
 		mutex_unlock(&srv->paths_mutex);
 	}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index a219bd1bdbc2..28f6414dfa3d 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1319,6 +1319,13 @@ static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_sess *sess)
 	return sess->cur_cq_vector;
 }
 
+static void rtrs_srv_dev_release(struct device *dev)
+{
+	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
+
+	kfree(srv);
+}
+
 static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 				     const uuid_t *paths_uuid)
 {
@@ -1336,6 +1343,8 @@ static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 	uuid_copy(&srv->paths_uuid, paths_uuid);
 	srv->queue_depth = sess_queue_depth;
 	srv->ctx = ctx;
+	device_initialize(&srv->dev);
+	srv->dev.release = rtrs_srv_dev_release;
 
 	srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks),
 			      GFP_KERNEL);
diff --git a/drivers/input/joystick/fsia6b.c b/drivers/input/joystick/fsia6b.c
index e78c4c768990..76ffdec5c183 100644
--- a/drivers/input/joystick/fsia6b.c
+++ b/drivers/input/joystick/fsia6b.c
@@ -102,12 +102,12 @@ static irqreturn_t fsia6b_serio_irq(struct serio *serio,
 					input_report_key(fsia6b->dev,
 							 sw_id++,
 							 sw_state == 0);
-					/* fall-through */
+					fallthrough;
 				case '2':
 					input_report_key(fsia6b->dev,
 							 sw_id++,
 							 sw_state == 1);
-					/* fall-through */
+					fallthrough;
 				case '1':
 					input_report_key(fsia6b->dev,
 							 sw_id++,
diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c
index 88df68cc4ac6..d37645e496ff 100644
--- a/drivers/input/joystick/gamecon.c
+++ b/drivers/input/joystick/gamecon.c
@@ -885,7 +885,6 @@ static int gc_setup_pad(struct gc *gc, int idx, int pad_type)
 
 	case GC_MULTI:
 		input_set_capability(input_dev, EV_KEY, BTN_TRIGGER);
-		/* fall through */
 		break;
 
 	case GC_PSX:
diff --git a/drivers/input/tablet/wacom_serial4.c b/drivers/input/tablet/wacom_serial4.c
index 959c1d82aa66..1cedb45ba497 100644
--- a/drivers/input/tablet/wacom_serial4.c
+++ b/drivers/input/tablet/wacom_serial4.c
@@ -213,7 +213,7 @@ static void wacom_handle_model_response(struct wacom *wacom)
 		case 0x3731: /* PL-710 */
 			wacom->res_x = 2540;
 			wacom->res_y = 2540;
-			/* fall through */
+			fallthrough;
 		case 0x3535: /* PL-550 */
 		case 0x3830: /* PL-800 */
 			wacom->extra_z_bits = 2;
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 6b71b0aff115..98f17fa3a892 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -477,7 +477,7 @@ static int mxt_lookup_bootloader_address(struct mxt_data *data, bool retry)
 			bootloader = appmode - 0x24;
 			break;
 		}
-		/* Fall through - for normal case */
+		fallthrough;	/* for normal case */
 	case 0x4c:
 	case 0x4d:
 	case 0x5a:
diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c
index 607d1aeb595d..bb1699e0d3c7 100644
--- a/drivers/input/touchscreen/wm831x-ts.c
+++ b/drivers/input/touchscreen/wm831x-ts.c
@@ -290,7 +290,7 @@ static int wm831x_ts_probe(struct platform_device *pdev)
 		default:
 			dev_err(&pdev->dev, "Unsupported ISEL setting: %d\n",
 				pdata->isel);
-			/* Fall through */
+			fallthrough;
 		case 200:
 		case 0:
 			wm831x_set_bits(wm831x, WM831X_TOUCH_CONTROL_2,
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index befd111049c0..cf07491b7415 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -55,12 +55,18 @@ static int icc_summary_show(struct seq_file *s, void *data)
 
 			icc_summary_show_one(s, n);
 			hlist_for_each_entry(r, &n->req_list, req_node) {
+				u32 avg_bw = 0, peak_bw = 0;
+
 				if (!r->dev)
 					continue;
 
+				if (r->enabled) {
+					avg_bw = r->avg_bw;
+					peak_bw = r->peak_bw;
+				}
+
 				seq_printf(s, "  %-27s %12u %12u %12u\n",
-					   dev_name(r->dev), r->tag, r->avg_bw,
-					   r->peak_bw);
+					   dev_name(r->dev), r->tag, avg_bw, peak_bw);
 			}
 		}
 	}
diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c
index a3d2ef1d9903..609db9c95fd7 100644
--- a/drivers/interconnect/qcom/bcm-voter.c
+++ b/drivers/interconnect/qcom/bcm-voter.c
@@ -52,8 +52,20 @@ static int cmp_vcd(void *priv, struct list_head *a, struct list_head *b)
 		return 1;
 }
 
+static u64 bcm_div(u64 num, u32 base)
+{
+	/* Ensure that small votes aren't lost. */
+	if (num && num < base)
+		return 1;
+
+	do_div(num, base);
+
+	return num;
+}
+
 static void bcm_aggregate(struct qcom_icc_bcm *bcm)
 {
+	struct qcom_icc_node *node;
 	size_t i, bucket;
 	u64 agg_avg[QCOM_ICC_NUM_BUCKETS] = {0};
 	u64 agg_peak[QCOM_ICC_NUM_BUCKETS] = {0};
@@ -61,22 +73,21 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm)
 
 	for (bucket = 0; bucket < QCOM_ICC_NUM_BUCKETS; bucket++) {
 		for (i = 0; i < bcm->num_nodes; i++) {
-			temp = bcm->nodes[i]->sum_avg[bucket] * bcm->aux_data.width;
-			do_div(temp, bcm->nodes[i]->buswidth * bcm->nodes[i]->channels);
+			node = bcm->nodes[i];
+			temp = bcm_div(node->sum_avg[bucket] * bcm->aux_data.width,
+				       node->buswidth * node->channels);
 			agg_avg[bucket] = max(agg_avg[bucket], temp);
 
-			temp = bcm->nodes[i]->max_peak[bucket] * bcm->aux_data.width;
-			do_div(temp, bcm->nodes[i]->buswidth);
+			temp = bcm_div(node->max_peak[bucket] * bcm->aux_data.width,
+				       node->buswidth);
 			agg_peak[bucket] = max(agg_peak[bucket], temp);
 		}
 
 		temp = agg_avg[bucket] * 1000ULL;
-		do_div(temp, bcm->aux_data.unit);
-		bcm->vote_x[bucket] = temp;
+		bcm->vote_x[bucket] = bcm_div(temp, bcm->aux_data.unit);
 
 		temp = agg_peak[bucket] * 1000ULL;
-		do_div(temp, bcm->aux_data.unit);
-		bcm->vote_y[bucket] = temp;
+		bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit);
 	}
 
 	if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 &&
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
index 1f061d91e0b8..626b97d0dd21 100644
--- a/drivers/iommu/amd/Kconfig
+++ b/drivers/iommu/amd/Kconfig
@@ -10,7 +10,7 @@ config AMD_IOMMU
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IOMMU_DMA
-	depends on X86_64 && PCI && ACPI
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
 	help
 	  With this option you can enable support for AMD IOMMU hardware in
 	  your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 958050c213f9..445a08d23fed 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1511,7 +1511,14 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling it.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		break;
 	case 0x11:
@@ -1520,8 +1527,18 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * XT, GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling them.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			break;
+		}
+
 		/*
 		 * Note: Since iommu_update_intcapxt() leverages
 		 * the IOMMU MMIO access to MSI capability block registers
@@ -2258,7 +2275,7 @@ static void iommu_enable_ga(struct amd_iommu *iommu)
 	switch (amd_iommu_guest_ir) {
 	case AMD_IOMMU_GUEST_IR_VAPIC:
 		iommu_feature_enable(iommu, CONTROL_GAM_EN);
-		/* Fall through */
+		fallthrough;
 	case AMD_IOMMU_GUEST_IR_LEGACY_GA:
 		iommu_feature_enable(iommu, CONTROL_GA_EN);
 		iommu->irte_ops = &irte_128_ops;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..07ae8b93887e 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	if (!dev_data)
 		return 0;
 
-	if (dev_data->iommu_v2)
+	/*
+	 * Do not identity map IOMMUv2 capable devices when memory encryption is
+	 * active, because some of those devices (AMD GPUs) don't have the
+	 * encryption bit in their DMA-mask and require remapping.
+	 */
+	if (!mem_encrypt_active() && dev_data->iommu_v2)
 		return IOMMU_DOMAIN_IDENTITY;
 
 	return 0;
@@ -3292,6 +3297,7 @@ out:
 static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 			  struct amd_ir_data *data)
 {
+	bool ret;
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
 	unsigned long flags;
@@ -3309,10 +3315,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
-	entry->lo.fields_remap.valid = 0;
-	entry->hi.val = irte->hi.val;
-	entry->lo.val = irte->lo.val;
-	entry->lo.fields_remap.valid = 1;
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			     entry->lo.val, entry->hi.val,
+			     irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
 	if (data)
 		data->ref = entry;
 
@@ -3850,6 +3864,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	struct irq_cfg *cfg = ir_data->cfg;
+	u64 valid = entry->lo.fields_remap.valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || !entry->lo.fields_vapic.guest_mode)
@@ -3858,6 +3873,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
 	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
 	entry->hi.fields.vector            = cfg->vector;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index c259108ab6dd..0d175aed1d92 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -737,6 +737,13 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 
 	might_sleep();
 
+	/*
+	 * When memory encryption is active the device is likely not in a
+	 * direct-mapped domain. Forbid using IOMMUv2 functionality for now.
+	 */
+	if (mem_encrypt_active())
+		return -ENODEV;
+
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7196207be7ea..c192544e874b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -903,7 +903,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		break;
 	case CMDQ_OP_CFGI_CD:
 		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid);
-		/* Fallthrough */
+		fallthrough;
 	case CMDQ_OP_CFGI_STE:
 		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf);
@@ -936,7 +936,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		break;
 	case CMDQ_OP_TLBI_NH_ASID:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
-		/* Fallthrough */
+		fallthrough;
 	case CMDQ_OP_TLBI_S12_VMALL:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		break;
@@ -1036,7 +1036,6 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
 		 */
 		return;
 	case CMDQ_ERR_CERROR_ILL_IDX:
-		/* Fallthrough */
 	default:
 		break;
 	}
@@ -3758,7 +3757,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	switch (FIELD_GET(IDR0_STALL_MODEL, reg)) {
 	case IDR0_STALL_MODEL_FORCE:
 		smmu->features |= ARM_SMMU_FEAT_STALL_FORCE;
-		/* Fallthrough */
+		fallthrough;
 	case IDR0_STALL_MODEL_STALL:
 		smmu->features |= ARM_SMMU_FEAT_STALLS;
 	}
@@ -3778,7 +3777,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	switch (FIELD_GET(IDR0_TTF, reg)) {
 	case IDR0_TTF_AARCH32_64:
 		smmu->ias = 40;
-		/* Fallthrough */
+		fallthrough;
 	case IDR0_TTF_AARCH64:
 		break;
 	default:
@@ -3875,7 +3874,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	default:
 		dev_info(smmu->dev,
 			"unknown output address size. Truncating to 48-bit\n");
-		/* Fallthrough */
+		fallthrough;
 	case IDR5_OAS_48_BIT:
 		smmu->oas = 48;
 	}
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 4959f5df21bd..5141d49a046b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    !gfpflags_allow_blocking(gfp) && !coherent)
-		cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page,
-					       gfp);
+		page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr,
+					       gfp, NULL);
 	else
 		cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs);
 	if (!cpu_addr)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index e9864e52b0e9..87b17bac04c2 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -123,29 +123,29 @@ static inline unsigned int level_to_offset_bits(int level)
 	return (level - 1) * LEVEL_STRIDE;
 }
 
-static inline int pfn_level_offset(unsigned long pfn, int level)
+static inline int pfn_level_offset(u64 pfn, int level)
 {
 	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
 }
 
-static inline unsigned long level_mask(int level)
+static inline u64 level_mask(int level)
 {
-	return -1UL << level_to_offset_bits(level);
+	return -1ULL << level_to_offset_bits(level);
 }
 
-static inline unsigned long level_size(int level)
+static inline u64 level_size(int level)
 {
-	return 1UL << level_to_offset_bits(level);
+	return 1ULL << level_to_offset_bits(level);
 }
 
-static inline unsigned long align_to_level(unsigned long pfn, int level)
+static inline u64 align_to_level(u64 pfn, int level)
 {
 	return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
 static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 {
-	return  1 << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
 }
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
@@ -364,7 +364,6 @@ static int iommu_skip_te_disable;
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
-#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 #define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
 struct device_domain_info *get_domain_info(struct device *dev)
 {
@@ -374,8 +373,7 @@ struct device_domain_info *get_domain_info(struct device *dev)
 		return NULL;
 
 	info = dev_iommu_priv_get(dev);
-	if (unlikely(info == DUMMY_DEVICE_DOMAIN_INFO ||
-		     info == DEFER_DEVICE_DOMAIN_INFO))
+	if (unlikely(info == DEFER_DEVICE_DOMAIN_INFO))
 		return NULL;
 
 	return info;
@@ -742,11 +740,6 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 	return &context[devfn];
 }
 
-static int iommu_dummy(struct device *dev)
-{
-	return dev_iommu_priv_get(dev) == DUMMY_DEVICE_DOMAIN_INFO;
-}
-
 static bool attach_deferred(struct device *dev)
 {
 	return dev_iommu_priv_get(dev) == DEFER_DEVICE_DOMAIN_INFO;
@@ -779,6 +772,53 @@ is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
 	return false;
 }
 
+static bool quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
+{
+	struct dmar_drhd_unit *drhd;
+	u32 vtbar;
+	int rc;
+
+	/* We know that this device on this chipset has its own IOMMU.
+	 * If we find it under a different IOMMU, then the BIOS is lying
+	 * to us. Hope that the IOMMU for this device is actually
+	 * disabled, and it needs no translation...
+	 */
+	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
+	if (rc) {
+		/* "can't" happen */
+		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
+		return false;
+	}
+	vtbar &= 0xffff0000;
+
+	/* we know that the this iommu should be at offset 0xa000 from vtbar */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return true;
+	}
+
+	return false;
+}
+
+static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
+{
+	if (!iommu || iommu->drhd->ignored)
+		return true;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		    pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SNB &&
+		    quirk_ioat_snb_local_iommu(pdev))
+			return true;
+	}
+
+	return false;
+}
+
 struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
@@ -788,7 +828,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 	u16 segment = 0;
 	int i;
 
-	if (!dev || iommu_dummy(dev))
+	if (!dev)
 		return NULL;
 
 	if (dev_is_pci(dev)) {
@@ -805,7 +845,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 		dev = &ACPI_COMPANION(dev)->dev;
 
 	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
 		if (pdev && segment != drhd->segment)
 			continue;
 
@@ -841,6 +881,9 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 	}
 	iommu = NULL;
  out:
+	if (iommu_is_dummy(iommu, dev))
+		iommu = NULL;
+
 	rcu_read_unlock();
 
 	return iommu;
@@ -2447,7 +2490,7 @@ struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
+	if (unlikely(attach_deferred(dev)))
 		return NULL;
 
 	/* No lock here, assumes no domain exit in normal case */
@@ -3989,35 +4032,6 @@ static void __init iommu_exit_mempool(void)
 	iova_cache_put();
 }
 
-static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
-{
-	struct dmar_drhd_unit *drhd;
-	u32 vtbar;
-	int rc;
-
-	/* We know that this device on this chipset has its own IOMMU.
-	 * If we find it under a different IOMMU, then the BIOS is lying
-	 * to us. Hope that the IOMMU for this device is actually
-	 * disabled, and it needs no translation...
-	 */
-	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
-	if (rc) {
-		/* "can't" happen */
-		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
-		return;
-	}
-	vtbar &= 0xffff0000;
-
-	/* we know that the this iommu should be at offset 0xa000 from vtbar */
-	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
-		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
-		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
-		dev_iommu_priv_set(&pdev->dev, DUMMY_DEVICE_DOMAIN_INFO);
-	}
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
-
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -4049,12 +4063,8 @@ static void __init init_no_remapping_devices(void)
 		/* This IOMMU has *only* gfx devices. Either bypass it or
 		   set the gfx_mapped flag, as appropriate */
 		drhd->gfx_dedicated = 1;
-		if (!dmar_map_gfx) {
+		if (!dmar_map_gfx)
 			drhd->ignored = 1;
-			for_each_active_dev_scope(drhd->devices,
-						  drhd->devices_cnt, i, dev)
-				dev_iommu_priv_set(dev, DUMMY_DEVICE_DOMAIN_INFO);
-		}
 	}
 }
 
@@ -5070,7 +5080,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 
 	switch (type) {
 	case IOMMU_DOMAIN_DMA:
-	/* fallthrough */
 	case IOMMU_DOMAIN_UNMANAGED:
 		dmar_domain = alloc_domain(0);
 		if (!dmar_domain) {
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 23583b0e66a5..8f4ce72570ce 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -508,12 +508,18 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
 
 	/* Enable interrupt-remapping */
 	iommu->gcmd |= DMA_GCMD_IRE;
-	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
-
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRES), sts);
 
+	/* Block compatibility-format MSIs */
+	if (sts & DMA_GSTS_CFIS) {
+		iommu->gcmd &= ~DMA_GCMD_CFI;
+		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, !(sts & DMA_GSTS_CFIS), sts);
+	}
+
 	/*
 	 * With CFI clear in the Global Command register, we should be
 	 * protected from dangerous (i.e. compatibility) interrupts
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index b4da396cce60..2bfdd5734844 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -440,7 +440,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
 	default:
 		dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n",
 			 mem->subtype);
-		/* Fall-through */
+		fallthrough;
 	case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
 		region = iommu_alloc_resv_region(start, size, 0,
 						 IOMMU_RESV_RESERVED);
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index bb70b7177f94..bfc9719dbcdc 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -425,7 +425,7 @@ config GOLDFISH_PIC
          for Goldfish based virtual platforms.
 
 config QCOM_PDC
-	tristate "QCOM PDC"
+	bool "QCOM PDC"
 	depends on ARCH_QCOM
 	select IRQ_DOMAIN_HIERARCHY
 	help
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 95f097448f97..548de7538632 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2737,7 +2737,7 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)
 	switch (gpsz) {
 	default:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	case GIC_PAGE_SIZE_4K:
 		psz = SZ_4K;
 		break;
@@ -2832,7 +2832,7 @@ static int allocate_vpe_l1_table(void)
 	switch (gpsz) {
 	default:
 		gpsz = GIC_PAGE_SIZE_4K;
-		/* fall through */
+		fallthrough;
 	case GIC_PAGE_SIZE_4K:
 		psz = SZ_4K;
 		break;
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 324f280ff606..850842f27bee 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -965,10 +965,10 @@ static void gic_cpu_sys_reg_init(void)
 		case 7:
 			write_gicreg(0, ICC_AP0R3_EL1);
 			write_gicreg(0, ICC_AP0R2_EL1);
-		/* Fall through */
+			fallthrough;
 		case 6:
 			write_gicreg(0, ICC_AP0R1_EL1);
-		/* Fall through */
+			fallthrough;
 		case 5:
 		case 4:
 			write_gicreg(0, ICC_AP0R0_EL1);
@@ -982,10 +982,10 @@ static void gic_cpu_sys_reg_init(void)
 	case 7:
 		write_gicreg(0, ICC_AP1R3_EL1);
 		write_gicreg(0, ICC_AP1R2_EL1);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		write_gicreg(0, ICC_AP1R1_EL1);
-		/* Fall through */
+		fallthrough;
 	case 5:
 	case 4:
 		write_gicreg(0, ICC_AP1R0_EL1);
diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c
index 4f74c15c4755..7031ef44de4f 100644
--- a/drivers/irqchip/irq-imx-gpcv2.c
+++ b/drivers/irqchip/irq-imx-gpcv2.c
@@ -259,7 +259,7 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node,
 		case 4:
 			writel_relaxed(~0, reg + GPC_IMR1_CORE2);
 			writel_relaxed(~0, reg + GPC_IMR1_CORE3);
-			/* fall through */
+			fallthrough;
 		case 2:
 			writel_relaxed(~0, reg + GPC_IMR1_CORE0);
 			writel_relaxed(~0, reg + GPC_IMR1_CORE1);
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index 9f3da4260ca6..b61a8901ef72 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -125,7 +125,7 @@ static int __init ingenic_intc_of_init(struct device_node *node,
 		irq_reg_writel(gc, IRQ_MSK(32), JZ_REG_INTC_SET_MASK);
 	}
 
-	if (request_irq(parent_irq, intc_cascade, 0,
+	if (request_irq(parent_irq, intc_cascade, IRQF_NO_SUSPEND,
 			"SoC intc cascade interrupt", NULL))
 		pr_err("Failed to register SoC intc cascade interrupt\n");
 	return 0;
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index aacfa012c082..215885962bb0 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -480,7 +480,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	case GIC_LOCAL_INT_TIMER:
 		/* CONFIG_MIPS_CMP workaround (see __gic_init) */
 		map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin;
-		/* fall-through */
+		fallthrough;
 	case GIC_LOCAL_INT_PERFCTR:
 	case GIC_LOCAL_INT_FDC:
 		/*
diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c
index 62a61275aaa3..69ba8ce3c178 100644
--- a/drivers/irqchip/irq-mtk-cirq.c
+++ b/drivers/irqchip/irq-mtk-cirq.c
@@ -295,6 +295,4 @@ out_free:
 	return ret;
 }
 
-IRQCHIP_PLATFORM_DRIVER_BEGIN(mtk_cirq)
-IRQCHIP_MATCH("mediatek,mtk-cirq", mtk_cirq_of_init)
-IRQCHIP_PLATFORM_DRIVER_END(mtk_cirq)
+IRQCHIP_DECLARE(mtk_cirq, "mediatek,mtk-cirq", mtk_cirq_of_init);
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index 7299c5ab4d10..6ff98b87e5c0 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -231,6 +231,4 @@ out_free_chip:
 	kfree(chip_data);
 	return ret;
 }
-IRQCHIP_PLATFORM_DRIVER_BEGIN(mtk_sysirq)
-IRQCHIP_MATCH("mediatek,mt6577-sysirq", mtk_sysirq_of_init)
-IRQCHIP_PLATFORM_DRIVER_END(mtk_sysirq)
+IRQCHIP_DECLARE(mtk_sysirq, "mediatek,mt6577-sysirq", mtk_sysirq_of_init);
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 03a36be757d8..0c2c61db26b4 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -416,6 +416,16 @@ static void stm32_irq_ack(struct irq_data *d)
 	irq_gc_unlock(gc);
 }
 
+/* directly set the target bit without reading first. */
+static inline void stm32_exti_write_bit(struct irq_data *d, u32 reg)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	void __iomem *base = chip_data->host_data->base;
+	u32 val = BIT(d->hwirq % IRQS_PER_BANK);
+
+	writel_relaxed(val, base + reg);
+}
+
 static inline u32 stm32_exti_set_bit(struct irq_data *d, u32 reg)
 {
 	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
@@ -449,9 +459,9 @@ static void stm32_exti_h_eoi(struct irq_data *d)
 
 	raw_spin_lock(&chip_data->rlock);
 
-	stm32_exti_set_bit(d, stm32_bank->rpr_ofst);
+	stm32_exti_write_bit(d, stm32_bank->rpr_ofst);
 	if (stm32_bank->fpr_ofst != UNDEF_REG)
-		stm32_exti_set_bit(d, stm32_bank->fpr_ofst);
+		stm32_exti_write_bit(d, stm32_bank->fpr_ofst);
 
 	raw_spin_unlock(&chip_data->rlock);
 
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index b7cc5d6580d8..d4e97605456b 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -8,6 +8,7 @@
 
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 #include <linux/interrupt.h>
@@ -83,6 +84,7 @@ struct ti_sci_inta_vint_desc {
  * @vint_mutex:		Mutex to protect vint_list
  * @base:		Base address of the memory mapped IO registers
  * @pdev:		Pointer to platform device.
+ * @ti_sci_id:		TI-SCI device identifier
  */
 struct ti_sci_inta_irq_domain {
 	const struct ti_sci_handle *sci;
@@ -93,6 +95,7 @@ struct ti_sci_inta_irq_domain {
 	struct mutex vint_mutex;
 	void __iomem *base;
 	struct platform_device *pdev;
+	u32 ti_sci_id;
 };
 
 #define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \
@@ -129,6 +132,37 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc)
 }
 
 /**
+ * ti_sci_inta_xlate_irq() - Translate hwirq to parent's hwirq.
+ * @inta:	IRQ domain corresponding to Interrupt Aggregator
+ * @irq:	Hardware irq corresponding to the above irq domain
+ *
+ * Return parent irq number if translation is available else -ENOENT.
+ */
+static int ti_sci_inta_xlate_irq(struct ti_sci_inta_irq_domain *inta,
+				 u16 vint_id)
+{
+	struct device_node *np = dev_of_node(&inta->pdev->dev);
+	u32 base, parent_base, size;
+	const __be32 *range;
+	int len;
+
+	range = of_get_property(np, "ti,interrupt-ranges", &len);
+	if (!range)
+		return vint_id;
+
+	for (len /= sizeof(*range); len >= 3; len -= 3) {
+		base = be32_to_cpu(*range++);
+		parent_base = be32_to_cpu(*range++);
+		size = be32_to_cpu(*range++);
+
+		if (base <= vint_id && vint_id < base + size)
+			return vint_id - base + parent_base;
+	}
+
+	return -ENOENT;
+}
+
+/**
  * ti_sci_inta_alloc_parent_irq() - Allocate parent irq to Interrupt aggregator
  * @domain:	IRQ domain corresponding to Interrupt Aggregator
  *
@@ -139,30 +173,52 @@ static struct ti_sci_inta_vint_desc *ti_sci_inta_alloc_parent_irq(struct irq_dom
 	struct ti_sci_inta_irq_domain *inta = domain->host_data;
 	struct ti_sci_inta_vint_desc *vint_desc;
 	struct irq_fwspec parent_fwspec;
+	struct device_node *parent_node;
 	unsigned int parent_virq;
-	u16 vint_id;
+	u16 vint_id, p_hwirq;
+	int ret;
 
 	vint_id = ti_sci_get_free_resource(inta->vint);
 	if (vint_id == TI_SCI_RESOURCE_NULL)
 		return ERR_PTR(-EINVAL);
 
+	p_hwirq = ti_sci_inta_xlate_irq(inta, vint_id);
+	if (p_hwirq < 0) {
+		ret = p_hwirq;
+		goto free_vint;
+	}
+
 	vint_desc = kzalloc(sizeof(*vint_desc), GFP_KERNEL);
-	if (!vint_desc)
-		return ERR_PTR(-ENOMEM);
+	if (!vint_desc) {
+		ret = -ENOMEM;
+		goto free_vint;
+	}
 
 	vint_desc->domain = domain;
 	vint_desc->vint_id = vint_id;
 	INIT_LIST_HEAD(&vint_desc->list);
 
-	parent_fwspec.fwnode = of_node_to_fwnode(of_irq_find_parent(dev_of_node(&inta->pdev->dev)));
-	parent_fwspec.param_count = 2;
-	parent_fwspec.param[0] = inta->pdev->id;
-	parent_fwspec.param[1] = vint_desc->vint_id;
+	parent_node = of_irq_find_parent(dev_of_node(&inta->pdev->dev));
+	parent_fwspec.fwnode = of_node_to_fwnode(parent_node);
+
+	if (of_device_is_compatible(parent_node, "arm,gic-v3")) {
+		/* Parent is GIC */
+		parent_fwspec.param_count = 3;
+		parent_fwspec.param[0] = 0;
+		parent_fwspec.param[1] = p_hwirq - 32;
+		parent_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
+	} else {
+		/* Parent is Interrupt Router */
+		parent_fwspec.param_count = 1;
+		parent_fwspec.param[0] = p_hwirq;
+	}
 
 	parent_virq = irq_create_fwspec_mapping(&parent_fwspec);
 	if (parent_virq == 0) {
-		kfree(vint_desc);
-		return ERR_PTR(-EINVAL);
+		dev_err(&inta->pdev->dev, "Parent IRQ allocation failed\n");
+		ret = -EINVAL;
+		goto free_vint_desc;
+
 	}
 	vint_desc->parent_virq = parent_virq;
 
@@ -171,6 +227,11 @@ static struct ti_sci_inta_vint_desc *ti_sci_inta_alloc_parent_irq(struct irq_dom
 					 ti_sci_inta_irq_handler, vint_desc);
 
 	return vint_desc;
+free_vint_desc:
+	kfree(vint_desc);
+free_vint:
+	ti_sci_release_resource(inta->vint, vint_id);
+	return ERR_PTR(ret);
 }
 
 /**
@@ -202,7 +263,7 @@ static struct ti_sci_inta_event_desc *ti_sci_inta_alloc_event(struct ti_sci_inta
 
 	err = inta->sci->ops.rm_irq_ops.set_event_map(inta->sci,
 						      dev_id, dev_index,
-						      inta->pdev->id,
+						      inta->ti_sci_id,
 						      vint_desc->vint_id,
 						      event_desc->global_event,
 						      free_bit);
@@ -299,7 +360,7 @@ static void ti_sci_inta_free_irq(struct ti_sci_inta_event_desc *event_desc,
 	inta->sci->ops.rm_irq_ops.free_event_map(inta->sci,
 						 HWIRQ_TO_DEVID(hwirq),
 						 HWIRQ_TO_IRQID(hwirq),
-						 inta->pdev->id,
+						 inta->ti_sci_id,
 						 vint_desc->vint_id,
 						 event_desc->global_event,
 						 event_desc->vint_bit);
@@ -547,21 +608,21 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &pdev->id);
+	ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &inta->ti_sci_id);
 	if (ret) {
 		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
 		return -EINVAL;
 	}
 
-	inta->vint = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id,
-						 "ti,sci-rm-range-vint");
+	inta->vint = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id,
+					      TI_SCI_RESASG_SUBTYPE_IA_VINT);
 	if (IS_ERR(inta->vint)) {
 		dev_err(dev, "VINT resource allocation failed\n");
 		return PTR_ERR(inta->vint);
 	}
 
-	inta->global_event = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id,
-						"ti,sci-rm-range-global-event");
+	inta->global_event = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id,
+						      TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT);
 	if (IS_ERR(inta->global_event)) {
 		dev_err(dev, "Global event resource allocation failed\n");
 		return PTR_ERR(inta->global_event);
@@ -592,6 +653,8 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&inta->vint_list);
 	mutex_init(&inta->vint_mutex);
 
+	dev_info(dev, "Interrupt Aggregator domain %d created\n", pdev->id);
+
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c
index 5ea148faf2ab..cbc1758228d9 100644
--- a/drivers/irqchip/irq-ti-sci-intr.c
+++ b/drivers/irqchip/irq-ti-sci-intr.c
@@ -17,29 +17,20 @@
 #include <linux/of_irq.h>
 #include <linux/soc/ti/ti_sci_protocol.h>
 
-#define TI_SCI_DEV_ID_MASK	0xffff
-#define TI_SCI_DEV_ID_SHIFT	16
-#define TI_SCI_IRQ_ID_MASK	0xffff
-#define TI_SCI_IRQ_ID_SHIFT	0
-#define HWIRQ_TO_DEVID(hwirq)	(((hwirq) >> (TI_SCI_DEV_ID_SHIFT)) & \
-				 (TI_SCI_DEV_ID_MASK))
-#define HWIRQ_TO_IRQID(hwirq)	((hwirq) & (TI_SCI_IRQ_ID_MASK))
-#define TO_HWIRQ(dev, index)	((((dev) & TI_SCI_DEV_ID_MASK) << \
-				 TI_SCI_DEV_ID_SHIFT) | \
-				((index) & TI_SCI_IRQ_ID_MASK))
-
 /**
  * struct ti_sci_intr_irq_domain - Structure representing a TISCI based
  *				   Interrupt Router IRQ domain.
  * @sci:	Pointer to TISCI handle
- * @dst_irq:	TISCI resource pointer representing GIC irq controller.
- * @dst_id:	TISCI device ID of the GIC irq controller.
+ * @out_irqs:	TISCI resource pointer representing INTR irqs.
+ * @dev:	Struct device pointer.
+ * @ti_sci_id:	TI-SCI device identifier
  * @type:	Specifies the trigger type supported by this Interrupt Router
  */
 struct ti_sci_intr_irq_domain {
 	const struct ti_sci_handle *sci;
-	struct ti_sci_resource *dst_irq;
-	u32 dst_id;
+	struct ti_sci_resource *out_irqs;
+	struct device *dev;
+	u32 ti_sci_id;
 	u32 type;
 };
 
@@ -70,16 +61,45 @@ static int ti_sci_intr_irq_domain_translate(struct irq_domain *domain,
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
 
-	if (fwspec->param_count != 2)
+	if (fwspec->param_count != 1)
 		return -EINVAL;
 
-	*hwirq = TO_HWIRQ(fwspec->param[0], fwspec->param[1]);
+	*hwirq = fwspec->param[0];
 	*type = intr->type;
 
 	return 0;
 }
 
 /**
+ * ti_sci_intr_xlate_irq() - Translate hwirq to parent's hwirq.
+ * @intr:	IRQ domain corresponding to Interrupt Router
+ * @irq:	Hardware irq corresponding to the above irq domain
+ *
+ * Return parent irq number if translation is available else -ENOENT.
+ */
+static int ti_sci_intr_xlate_irq(struct ti_sci_intr_irq_domain *intr, u32 irq)
+{
+	struct device_node *np = dev_of_node(intr->dev);
+	u32 base, pbase, size, len;
+	const __be32 *range;
+
+	range = of_get_property(np, "ti,interrupt-ranges", &len);
+	if (!range)
+		return irq;
+
+	for (len /= sizeof(*range); len >= 3; len -= 3) {
+		base = be32_to_cpu(*range++);
+		pbase = be32_to_cpu(*range++);
+		size = be32_to_cpu(*range++);
+
+		if (base <= irq && irq < base + size)
+			return irq - base + pbase;
+	}
+
+	return -ENOENT;
+}
+
+/**
  * ti_sci_intr_irq_domain_free() - Free the specified IRQs from the domain.
  * @domain:	Domain to which the irqs belong
  * @virq:	Linux virtual IRQ to be freed.
@@ -89,66 +109,76 @@ static void ti_sci_intr_irq_domain_free(struct irq_domain *domain,
 					unsigned int virq, unsigned int nr_irqs)
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
-	struct irq_data *data, *parent_data;
-	u16 dev_id, irq_index;
+	struct irq_data *data;
+	int out_irq;
 
-	parent_data = irq_domain_get_irq_data(domain->parent, virq);
 	data = irq_domain_get_irq_data(domain, virq);
-	irq_index = HWIRQ_TO_IRQID(data->hwirq);
-	dev_id = HWIRQ_TO_DEVID(data->hwirq);
+	out_irq = (uintptr_t)data->chip_data;
 
-	intr->sci->ops.rm_irq_ops.free_irq(intr->sci, dev_id, irq_index,
-					   intr->dst_id, parent_data->hwirq);
-	ti_sci_release_resource(intr->dst_irq, parent_data->hwirq);
+	intr->sci->ops.rm_irq_ops.free_irq(intr->sci,
+					   intr->ti_sci_id, data->hwirq,
+					   intr->ti_sci_id, out_irq);
+	ti_sci_release_resource(intr->out_irqs, out_irq);
 	irq_domain_free_irqs_parent(domain, virq, 1);
 	irq_domain_reset_irq_data(data);
 }
 
 /**
- * ti_sci_intr_alloc_gic_irq() - Allocate GIC specific IRQ
+ * ti_sci_intr_alloc_parent_irq() - Allocate parent IRQ
  * @domain:	Pointer to the interrupt router IRQ domain
  * @virq:	Corresponding Linux virtual IRQ number
  * @hwirq:	Corresponding hwirq for the IRQ within this IRQ domain
  *
- * Returns 0 if all went well else appropriate error pointer.
+ * Returns parent irq if all went well else appropriate error pointer.
  */
-static int ti_sci_intr_alloc_gic_irq(struct irq_domain *domain,
-				     unsigned int virq, u32 hwirq)
+static int ti_sci_intr_alloc_parent_irq(struct irq_domain *domain,
+					unsigned int virq, u32 hwirq)
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
+	struct device_node *parent_node;
 	struct irq_fwspec fwspec;
-	u16 dev_id, irq_index;
-	u16 dst_irq;
-	int err;
-
-	dev_id = HWIRQ_TO_DEVID(hwirq);
-	irq_index = HWIRQ_TO_IRQID(hwirq);
+	u16 out_irq, p_hwirq;
+	int err = 0;
 
-	dst_irq = ti_sci_get_free_resource(intr->dst_irq);
-	if (dst_irq == TI_SCI_RESOURCE_NULL)
+	out_irq = ti_sci_get_free_resource(intr->out_irqs);
+	if (out_irq == TI_SCI_RESOURCE_NULL)
 		return -EINVAL;
 
-	fwspec.fwnode = domain->parent->fwnode;
-	fwspec.param_count = 3;
-	fwspec.param[0] = 0;	/* SPI */
-	fwspec.param[1] = dst_irq - 32; /* SPI offset */
-	fwspec.param[2] = intr->type;
+	p_hwirq = ti_sci_intr_xlate_irq(intr, out_irq);
+	if (p_hwirq < 0)
+		goto err_irqs;
+
+	parent_node = of_irq_find_parent(dev_of_node(intr->dev));
+	fwspec.fwnode = of_node_to_fwnode(parent_node);
+
+	if (of_device_is_compatible(parent_node, "arm,gic-v3")) {
+		/* Parent is GIC */
+		fwspec.param_count = 3;
+		fwspec.param[0] = 0;	/* SPI */
+		fwspec.param[1] = p_hwirq - 32; /* SPI offset */
+		fwspec.param[2] = intr->type;
+	} else {
+		/* Parent is Interrupt Router */
+		fwspec.param_count = 1;
+		fwspec.param[0] = p_hwirq;
+	}
 
 	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
 	if (err)
 		goto err_irqs;
 
-	err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci, dev_id, irq_index,
-						intr->dst_id, dst_irq);
+	err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci,
+						intr->ti_sci_id, hwirq,
+						intr->ti_sci_id, out_irq);
 	if (err)
 		goto err_msg;
 
-	return 0;
+	return p_hwirq;
 
 err_msg:
 	irq_domain_free_irqs_parent(domain, virq, 1);
 err_irqs:
-	ti_sci_release_resource(intr->dst_irq, dst_irq);
+	ti_sci_release_resource(intr->out_irqs, out_irq);
 	return err;
 }
 
@@ -168,18 +198,19 @@ static int ti_sci_intr_irq_domain_alloc(struct irq_domain *domain,
 	struct irq_fwspec *fwspec = data;
 	unsigned long hwirq;
 	unsigned int flags;
-	int err;
+	int err, p_hwirq;
 
 	err = ti_sci_intr_irq_domain_translate(domain, fwspec, &hwirq, &flags);
 	if (err)
 		return err;
 
-	err = ti_sci_intr_alloc_gic_irq(domain, virq, hwirq);
-	if (err)
-		return err;
+	p_hwirq = ti_sci_intr_alloc_parent_irq(domain, virq, hwirq);
+	if (p_hwirq < 0)
+		return p_hwirq;
 
 	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
-				      &ti_sci_intr_irq_chip, NULL);
+				      &ti_sci_intr_irq_chip,
+				      (void *)(uintptr_t)p_hwirq);
 
 	return 0;
 }
@@ -214,6 +245,7 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev)
 	if (!intr)
 		return -ENOMEM;
 
+	intr->dev = dev;
 	ret = of_property_read_u32(dev_of_node(dev), "ti,intr-trigger-type",
 				   &intr->type);
 	if (ret) {
@@ -230,19 +262,19 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dst-id",
-				   &intr->dst_id);
+	ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dev-id",
+				   &intr->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "missing 'ti,sci-dst-id' property\n");
+		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
 		return -EINVAL;
 	}
 
-	intr->dst_irq = devm_ti_sci_get_of_resource(intr->sci, dev,
-						    intr->dst_id,
-						    "ti,sci-rm-range-girq");
-	if (IS_ERR(intr->dst_irq)) {
+	intr->out_irqs = devm_ti_sci_get_resource(intr->sci, dev,
+						  intr->ti_sci_id,
+						  TI_SCI_RESASG_SUBTYPE_IR_OUTPUT);
+	if (IS_ERR(intr->out_irqs)) {
 		dev_err(dev, "Destination irq resource allocation failed\n");
-		return PTR_ERR(intr->dst_irq);
+		return PTR_ERR(intr->out_irqs);
 	}
 
 	domain = irq_domain_add_hierarchy(parent_domain, 0, 0, dev_of_node(dev),
@@ -252,6 +284,8 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	dev_info(dev, "Interrupt Router %d domain created\n", intr->ti_sci_id);
+
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index bc235db8a4c5..e46036374227 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -455,7 +455,7 @@ static void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
 		return;
 	default:
 		printk(KERN_WARNING "VIC: unknown vendor, continuing anyways\n");
-		/* fall through */
+		fallthrough;
 	case AMBA_VENDOR_ARM:
 		break;
 	}
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index 1bb0e36c2bf3..d2341153e181 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -52,7 +52,7 @@ int platform_irqchip_probe(struct platform_device *pdev)
 	 * interrupt controller. The actual initialization callback of this
 	 * interrupt controller can check for specific domains as necessary.
 	 */
-	if (par_np && !irq_find_matching_host(np, DOMAIN_BUS_ANY))
+	if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY))
 		return -EPROBE_DEFER;
 
 	return irq_init_cb(np, par_np);
diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c
index c1c5dfad57cc..6ae9e1f0819d 100644
--- a/drivers/irqchip/qcom-pdc.c
+++ b/drivers/irqchip/qcom-pdc.c
@@ -11,11 +11,9 @@
 #include <linux/irqdomain.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/soc/qcom/irq.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
@@ -432,8 +430,4 @@ fail:
 	return ret;
 }
 
-IRQCHIP_PLATFORM_DRIVER_BEGIN(qcom_pdc)
-IRQCHIP_MATCH("qcom,pdc", qcom_pdc_init)
-IRQCHIP_PLATFORM_DRIVER_END(qcom_pdc)
-MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Power Domain Controller");
-MODULE_LICENSE("GPL v2");
+IRQCHIP_DECLARE(qcom_pdc, "qcom,pdc", qcom_pdc_init);
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index ecc1ef6c386d..f68569bfef7a 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -348,7 +348,7 @@ modehdlc(struct bchannel *bch, int protocol)
 	switch (protocol) {
 	case -1: /* used for init */
 		bch->state = -1;
-		/* fall through */
+		fallthrough;
 	case ISDN_P_NONE:
 		if (bch->state == ISDN_P_NONE)
 			break;
diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
index b0d772340e16..448ded8f9d24 100644
--- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
+++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
@@ -121,7 +121,6 @@ setup_embedded(struct hfc_multi *hc, struct hm_map *m)
 	case HFC_IO_MODE_EMBSD:
 		test_and_set_bit(HFC_CHIP_EMBSD, &hc->chip);
 		hc->slots = 128; /* required */
-		/* fall through */
 		hc->HFC_outb = HFC_outb_embsd;
 		hc->HFC_inb = HFC_inb_embsd;
 		hc->HFC_inw = HFC_inw_embsd;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 904a4f4c5ff9..56bd2e9db6ed 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1280,7 +1280,7 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 	case (-1): /* used for init */
 		bch->state = -1;
 		bch->nr = bc;
-		/* fall through */
+		fallthrough;
 	case (ISDN_P_NONE):
 		if (bch->state == ISDN_P_NONE)
 			return 0;
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 4274906f8654..70061991915a 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -695,7 +695,7 @@ hfcsusb_setup_bch(struct bchannel *bch, int protocol)
 	switch (protocol) {
 	case (-1):	/* used for init */
 		bch->state = -1;
-		/* fall through */
+		fallthrough;
 	case (ISDN_P_NONE):
 		if (bch->state == ISDN_P_NONE)
 			return 0; /* already in idle state */
diff --git a/drivers/isdn/hardware/mISDN/isdnhdlc.c b/drivers/isdn/hardware/mISDN/isdnhdlc.c
index 9fea16ed3dd8..985367e6711d 100644
--- a/drivers/isdn/hardware/mISDN/isdnhdlc.c
+++ b/drivers/isdn/hardware/mISDN/isdnhdlc.c
@@ -397,7 +397,7 @@ int isdnhdlc_encode(struct isdnhdlc_vars *hdlc, const u8 *src, u16 slen,
 				dsize--;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case HDLC_SENDFLAG_ONE:
 			if (hdlc->bit_shift == 8) {
 				hdlc->cbin = hdlc->ffvalue >>
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index f4cb29766888..a16c7a2a7f3d 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -875,7 +875,7 @@ release_card(struct inf_hw *card) {
 				release_card(card->sc[i]);
 			card->sc[i] = NULL;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		pci_disable_device(card->pdev);
 		pci_set_drvdata(card->pdev, NULL);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index 11e8c7d8b6e8..56943409b60d 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -957,7 +957,7 @@ isar_pump_statev_fax(struct isar_ch *ch, u8 devt) {
 				break;
 			case PCTRL_CMD_FTM:
 				p1 = 2;
-				/* fall through */
+				fallthrough;
 			case PCTRL_CMD_FTH:
 				send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL,
 					  PCTRL_CMD_SILON, 1, &p1);
@@ -1163,7 +1163,7 @@ setup_pump(struct isar_ch *ch) {
 			send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG,
 				  PMOD_DTMF, 1, param);
 		}
-		/* fall through */
+		fallthrough;
 	case ISDN_P_B_MODEM_ASYNC:
 		ctrl = PMOD_DATAMODEM;
 		if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) {
@@ -1255,7 +1255,7 @@ setup_iom2(struct isar_ch *ch) {
 	case ISDN_P_B_MODEM_ASYNC:
 	case ISDN_P_B_T30_FAX:
 		cmsb |= IOM_CTRL_RCV;
-		/* fall through */
+		fallthrough;
 	case ISDN_P_B_L2DTMF:
 		if (test_bit(FLG_DTMFSEND, &ch->bch.Flags))
 			cmsb |= IOM_CTRL_RCV;
@@ -1548,7 +1548,7 @@ isar_l2l1(struct mISDNchannel *ch, struct sk_buff *skb)
 				ich->is->name, hh->id);
 			ret = -EINVAL;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		pr_info("%s: %s unknown prim(%x,%x)\n",
 			ich->is->name, __func__, hh->prim, hh->id);
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 27aa32914425..c2f76f398613 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -528,7 +528,7 @@ create_l2entity(struct mISDNdevice *dev, struct mISDNchannel *ch,
 		rq.protocol = ISDN_P_NT_S0;
 		if (dev->Dprotocols & (1 << ISDN_P_NT_E1))
 			rq.protocol = ISDN_P_NT_E1;
-		/* fall through */
+		fallthrough;
 	case ISDN_P_LAPD_TE:
 		ch->recv = mISDN_queue_message;
 		ch->peer = &dev->D.st->own;
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index b413bafe93fd..97c68731406b 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -301,7 +301,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	switch (type) {
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
-		/* fall through */
+		fallthrough;
 	case PBLK_WRITE_INT:
 		pool = &pblk->w_rq_pool;
 		break;
diff --git a/drivers/macintosh/adbhid.c b/drivers/macintosh/adbhid.c
index 75482eeab2c4..994ba5cb3678 100644
--- a/drivers/macintosh/adbhid.c
+++ b/drivers/macintosh/adbhid.c
@@ -881,7 +881,7 @@ adbhid_input_register(int id, int default_id, int original_handler_id,
 		}
 		if (hid->name[0])
 			break;
-		/* else fall through */
+		fallthrough;
 
 	default:
 		pr_info("Trying to register unknown ADB device to input layer.\n");
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 23f1f41c8602..96684581a25d 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -852,7 +852,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd)
 		break;
 	case SMU_I2C_TRANSFER_COMBINED:
 		cmd->info.devaddr &= 0xfe;
-		/* fall through */
+		fallthrough;
 	case SMU_I2C_TRANSFER_STDSUB:
 		if (cmd->info.sublen > 3)
 			return -EINVAL;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 77fbfd52edcf..c1227bdb57e7 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -608,7 +608,7 @@ static void do_journal_discard(struct cache *ca)
 			ca->sb.njournal_buckets;
 
 		atomic_set(&ja->discard_in_flight, DISCARD_READY);
-		/* fallthrough */
+		fallthrough;
 
 	case DISCARD_READY:
 		if (ja->discard_idx == ja->last_idx)
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 62fb917f7a4f..ae380bc3992e 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -33,27 +33,27 @@ int bch_ ## name ## _h(const char *cp, type *res)		\
 	case 'y':						\
 	case 'z':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 'e':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 'p':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 't':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 'g':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 'm':						\
 		u++;						\
-		/* fall through */				\
+		fallthrough;					\
 	case 'k':						\
 		u++;						\
 		if (e++ == cp)					\
 			return -EINVAL;				\
-		/* fall through */				\
+		fallthrough;					\
 	case '\n':						\
 	case '\0':						\
 		if (*e == '\n')					\
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 151aa95775be..af6d4f898e4c 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -537,12 +537,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
 					  CACHE_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(cmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(cmd->bm);
+		r = PTR_ERR(cmd->bm);
+		cmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(cmd, may_format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(cmd->bm);
+		cmd->bm = NULL;
+	}
 
 	return r;
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 148960721254..380386c36921 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -739,7 +739,7 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv,
 	u8 buf[MAX_CIPHER_BLOCKSIZE] __aligned(__alignof__(__le64));
 	struct skcipher_request *req;
 	struct scatterlist src, dst;
-	struct crypto_wait wait;
+	DECLARE_CRYPTO_WAIT(wait);
 	int err;
 
 	req = skcipher_request_alloc(any_tfm(cc), GFP_NOIO);
@@ -936,7 +936,7 @@ static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *d
 	u8 *es, *ks, *data, *data2, *data_offset;
 	struct skcipher_request *req;
 	struct scatterlist *sg, *sg2, src, dst;
-	struct crypto_wait wait;
+	DECLARE_CRYPTO_WAIT(wait);
 	int i, r;
 
 	req = skcipher_request_alloc(elephant->tfm, GFP_NOIO);
@@ -1552,7 +1552,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		case -EBUSY:
 			wait_for_completion(&ctx->restart);
 			reinit_completion(&ctx->restart);
-			/* fall through */
+			fallthrough;
 		/*
 		 * The request is queued and processed asynchronously,
 		 * completion function kcryptd_async_done() will be called.
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 8c8d940e532e..3fc3757def55 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2487,6 +2487,7 @@ next_chunk:
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
 	if (unlikely(range.logical_sector >= ic->provided_data_sectors)) {
 		if (ic->mode == 'B') {
+			block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
 			DEBUG_print("queue_delayed_work: bitmap_flush_work\n");
 			queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, 0);
 		}
@@ -2564,6 +2565,17 @@ next_chunk:
 		goto err;
 	}
 
+	if (ic->mode == 'B') {
+		sector_t start, end;
+		start = (range.logical_sector >>
+			 (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) <<
+			(ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
+		end = ((range.logical_sector + range.n_sectors) >>
+		       (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) <<
+			(ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
+		block_bitmap_op(ic, ic->recalc_bitmap, start, end - start, BITMAP_OP_CLEAR);
+	}
+
 advance_and_next:
 	cond_resched();
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 53645a6f474c..de4da825ade6 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1287,17 +1287,25 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m)
 static void flush_multipath_work(struct multipath *m)
 {
 	if (m->hw_handler_name) {
-		set_bit(MPATHF_PG_INIT_DISABLED, &m->flags);
-		smp_mb__after_atomic();
+		unsigned long flags;
+
+		if (!atomic_read(&m->pg_init_in_progress))
+			goto skip;
+
+		spin_lock_irqsave(&m->lock, flags);
+		if (atomic_read(&m->pg_init_in_progress) &&
+		    !test_and_set_bit(MPATHF_PG_INIT_DISABLED, &m->flags)) {
+			spin_unlock_irqrestore(&m->lock, flags);
 
-		if (atomic_read(&m->pg_init_in_progress))
 			flush_workqueue(kmpath_handlerd);
-		multipath_wait_for_pg_init_completion(m);
+			multipath_wait_for_pg_init_completion(m);
 
-		clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags);
-		smp_mb__after_atomic();
+			spin_lock_irqsave(&m->lock, flags);
+			clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags);
+		}
+		spin_unlock_irqrestore(&m->lock, flags);
 	}
-
+skip:
 	if (m->queue_mode == DM_TYPE_BIO_BASED)
 		flush_work(&m->process_queued_bios);
 	flush_work(&m->trigger_event);
@@ -1554,7 +1562,7 @@ static void pg_init_done(void *data, int errors)
 	case SCSI_DH_RETRY:
 		/* Wait before retrying. */
 		delay_retry = true;
-		/* fall through */
+		fallthrough;
 	case SCSI_DH_IMM_RETRY:
 	case SCSI_DH_RES_TEMP_UNAVAIL:
 		if (pg_init_limit_reached(m, pgpath))
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 76b6b323bf4b..b461836b6d26 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -739,12 +739,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(pmd->bm);
+		r = PTR_ERR(pmd->bm);
+		pmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(pmd, format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(pmd->bm);
+		pmd->bm = NULL;
+	}
 
 	return r;
 }
@@ -954,7 +958,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 	}
 
 	pmd_write_lock_in_core(pmd);
-	if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) {
+	if (!pmd->fail_io && !dm_bm_is_read_only(pmd->bm)) {
 		r = __commit_transaction(pmd);
 		if (r < 0)
 			DMWARN("%s: __commit_transaction() failed, error = %d",
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 86dbe0c8b45c..6271d1e741cf 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -231,6 +231,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	pfn_t pfn;
 	int id;
 	struct page **pages;
+	sector_t offset;
 
 	wc->memory_vmapped = false;
 
@@ -245,9 +246,16 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		goto err1;
 	}
 
+	offset = get_start_sect(wc->ssd_dev->bdev);
+	if (offset & (PAGE_SIZE / 512 - 1)) {
+		r = -EINVAL;
+		goto err1;
+	}
+	offset >>= PAGE_SHIFT - 9;
+
 	id = dax_read_lock();
 
-	da = dax_direct_access(wc->ssd_dev->dax_dev, 0, p, &wc->memory_map, &pfn);
+	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
 	if (da < 0) {
 		wc->memory_map = NULL;
 		r = da;
@@ -269,7 +277,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		i = 0;
 		do {
 			long daa;
-			daa = dax_direct_access(wc->ssd_dev->dax_dev, i, p - i,
+			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
 						NULL, &pfn);
 			if (daa <= 0) {
 				r = daa ? daa : -EINVAL;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 32fa6499739f..fb0255d25e4b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1021,7 +1021,7 @@ static void clone_endio(struct bio *bio)
 		switch (r) {
 		case DM_ENDIO_REQUEUE:
 			error = BLK_STS_DM_REQUEUE;
-			/*FALLTHRU*/
+			fallthrough;
 		case DM_ENDIO_DONE:
 			break;
 		case DM_ENDIO_INCOMPLETE:
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 6bbec89976a7..2cf973722f59 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -102,10 +102,10 @@ static int __init md_setup(char *str)
 				pername = "raid0";
 			break;
 		}
-		/* FALL THROUGH */
+		fallthrough;
 	case 1: /* the first device is numeric */
 		str = str1;
-		/* FALL THROUGH */
+		fallthrough;
 	case 0:
 		md_setup_args[ent].level = LEVEL_NONE;
 		pername="super-block";
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index d61b524ae440..b10c51988c8e 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1433,7 +1433,7 @@ int md_bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long s
 		case 0:
 			md_bitmap_file_set_bit(bitmap, offset);
 			md_bitmap_count_page(&bitmap->counts, offset, 1);
-			/* fall through */
+			fallthrough;
 		case 1:
 			*bmc = 2;
 		}
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 749ec268d957..54c089a50b15 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -493,7 +493,7 @@ int dm_bm_write_lock(struct dm_block_manager *bm,
 	void *p;
 	int r;
 
-	if (bm->read_only)
+	if (dm_bm_is_read_only(bm))
 		return -EPERM;
 
 	p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result);
@@ -562,7 +562,7 @@ int dm_bm_write_lock_zero(struct dm_block_manager *bm,
 	struct buffer_aux *aux;
 	void *p;
 
-	if (bm->read_only)
+	if (dm_bm_is_read_only(bm))
 		return -EPERM;
 
 	p = dm_bufio_new(bm->bufio, b, (struct dm_buffer **) result);
@@ -602,7 +602,7 @@ EXPORT_SYMBOL_GPL(dm_bm_unlock);
 
 int dm_bm_flush(struct dm_block_manager *bm)
 {
-	if (bm->read_only)
+	if (dm_bm_is_read_only(bm))
 		return -EPERM;
 
 	return dm_bufio_write_dirty_buffers(bm->bufio);
@@ -616,19 +616,21 @@ void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b)
 
 bool dm_bm_is_read_only(struct dm_block_manager *bm)
 {
-	return bm->read_only;
+	return (bm ? bm->read_only : true);
 }
 EXPORT_SYMBOL_GPL(dm_bm_is_read_only);
 
 void dm_bm_set_read_only(struct dm_block_manager *bm)
 {
-	bm->read_only = true;
+	if (bm)
+		bm->read_only = true;
 }
 EXPORT_SYMBOL_GPL(dm_bm_set_read_only);
 
 void dm_bm_set_read_write(struct dm_block_manager *bm)
 {
-	bm->read_only = false;
+	if (bm)
+		bm->read_only = false;
 }
 EXPORT_SYMBOL_GPL(dm_bm_set_read_write);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ef0fd4830803..225380efd1e2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4083,7 +4083,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 			break;
 		}
 		dev = &sh->dev[s->failed_num[0]];
-		/* fall through */
+		fallthrough;
 	case check_state_compute_result:
 		sh->check_state = check_state_idle;
 		if (!dev)
@@ -4214,7 +4214,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 
 		/* we have 2-disk failure */
 		BUG_ON(s->failed != 2);
-		/* fall through */
+		fallthrough;
 	case check_state_compute_result:
 		sh->check_state = check_state_idle;
 
@@ -6514,9 +6514,12 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 
 	/*
 	 * The value should not be bigger than PAGE_SIZE. It requires to
-	 * be multiple of DEFAULT_STRIPE_SIZE.
+	 * be multiple of DEFAULT_STRIPE_SIZE and the value should be power
+	 * of two.
 	 */
-	if (new % DEFAULT_STRIPE_SIZE != 0 || new > PAGE_SIZE || new == 0)
+	if (new % DEFAULT_STRIPE_SIZE != 0 ||
+			new > PAGE_SIZE || new == 0 ||
+			new != roundup_pow_of_two(new))
 		return -EINVAL;
 
 	err = mddev_lock(mddev);
diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
index 630a75e0eeb1..7607b516a7c4 100644
--- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
+++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
@@ -210,7 +210,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 		tpg->vdownsampling[1] = 1;
 		tpg->hdownsampling[1] = 1;
 		tpg->planes = 2;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_RGB332:
 	case V4L2_PIX_FMT_RGB565:
 	case V4L2_PIX_FMT_RGB565X:
@@ -271,7 +271,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 	case V4L2_PIX_FMT_YUV420M:
 	case V4L2_PIX_FMT_YVU420M:
 		tpg->buffers = 3;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YVU420:
 		tpg->vdownsampling[1] = 2;
@@ -284,7 +284,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 	case V4L2_PIX_FMT_YUV422M:
 	case V4L2_PIX_FMT_YVU422M:
 		tpg->buffers = 3;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_YUV422P:
 		tpg->vdownsampling[1] = 1;
 		tpg->vdownsampling[2] = 1;
@@ -296,7 +296,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 	case V4L2_PIX_FMT_NV16M:
 	case V4L2_PIX_FMT_NV61M:
 		tpg->buffers = 2;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 		tpg->vdownsampling[1] = 1;
@@ -308,7 +308,7 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 	case V4L2_PIX_FMT_NV12M:
 	case V4L2_PIX_FMT_NV21M:
 		tpg->buffers = 2;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV21:
 		tpg->vdownsampling[1] = 2;
@@ -1275,7 +1275,7 @@ static void gen_twopix(struct tpg_data *tpg,
 	case V4L2_PIX_FMT_RGB444:
 	case V4L2_PIX_FMT_XRGB444:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_YUV444:
 	case V4L2_PIX_FMT_ARGB444:
 		buf[0][offset] = (g_u_s << 4) | b_v;
@@ -1283,21 +1283,21 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_RGBX444:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_RGBA444:
 		buf[0][offset] = (b_v << 4) | (alpha >> 4);
 		buf[0][offset + 1] = (r_y_h << 4) | g_u_s;
 		break;
 	case V4L2_PIX_FMT_XBGR444:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_ABGR444:
 		buf[0][offset] = (g_u_s << 4) | r_y_h;
 		buf[0][offset + 1] = (alpha & 0xf0) | b_v;
 		break;
 	case V4L2_PIX_FMT_BGRX444:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_BGRA444:
 		buf[0][offset] = (r_y_h << 4) | (alpha >> 4);
 		buf[0][offset + 1] = (b_v << 4) | g_u_s;
@@ -1305,7 +1305,7 @@ static void gen_twopix(struct tpg_data *tpg,
 	case V4L2_PIX_FMT_RGB555:
 	case V4L2_PIX_FMT_XRGB555:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_YUV555:
 	case V4L2_PIX_FMT_ARGB555:
 		buf[0][offset] = (g_u_s << 5) | b_v;
@@ -1314,7 +1314,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_RGBX555:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_RGBA555:
 		buf[0][offset] = (g_u_s << 6) | (b_v << 1) |
 				 ((alpha & 0x80) >> 7);
@@ -1322,7 +1322,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_XBGR555:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_ABGR555:
 		buf[0][offset] = (g_u_s << 5) | r_y_h;
 		buf[0][offset + 1] = (alpha & 0x80) | (b_v << 2)
@@ -1330,7 +1330,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_BGRX555:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_BGRA555:
 		buf[0][offset] = (g_u_s << 6) | (r_y_h << 1) |
 				 ((alpha & 0x80) >> 7);
@@ -1339,7 +1339,7 @@ static void gen_twopix(struct tpg_data *tpg,
 	case V4L2_PIX_FMT_RGB555X:
 	case V4L2_PIX_FMT_XRGB555X:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_ARGB555X:
 		buf[0][offset] = (alpha & 0x80) | (r_y_h << 2) | (g_u_s >> 3);
 		buf[0][offset + 1] = (g_u_s << 5) | b_v;
@@ -1366,7 +1366,7 @@ static void gen_twopix(struct tpg_data *tpg,
 	case V4L2_PIX_FMT_HSV32:
 	case V4L2_PIX_FMT_XYUV32:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_YUV32:
 	case V4L2_PIX_FMT_ARGB32:
 	case V4L2_PIX_FMT_AYUV32:
@@ -1377,7 +1377,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_RGBX32:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_RGBA32:
 		buf[0][offset] = r_y_h;
 		buf[0][offset + 1] = g_u_s;
@@ -1388,7 +1388,7 @@ static void gen_twopix(struct tpg_data *tpg,
 	case V4L2_PIX_FMT_XBGR32:
 	case V4L2_PIX_FMT_VUYX32:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_ABGR32:
 	case V4L2_PIX_FMT_VUYA32:
 		buf[0][offset] = b_v;
@@ -1398,7 +1398,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		break;
 	case V4L2_PIX_FMT_BGRX32:
 		alpha = 0;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_BGRA32:
 		buf[0][offset] = alpha;
 		buf[0][offset + 1] = b_v;
diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index 630509ecee20..89620da983ba 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -546,7 +546,7 @@ static int dvb_net_ule_new_payload(struct dvb_net_ule_handle *h)
 		h->priv->ule_sndu_type_1 = 1;
 		h->ts_remain -= 1;
 		h->from_where += 1;
-		/* fallthrough */
+		fallthrough;
 	case 0:
 		h->new_ts = 1;
 		h->ts += TS_SZ;
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index e92542b92d34..da0ff7b44da4 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -773,7 +773,7 @@ static int bcm3510_init(struct dvb_frontend* fe)
 			deb_info("attempting to download firmware\n");
 			if ((ret = bcm3510_init_cold(st)) < 0)
 				return ret;
-			/* fall-through */
+			fallthrough;
 		case JDEC_EEPROM_LOAD_WAIT:
 			deb_info("firmware is loaded\n");
 			bcm3510_check_firmware_version(st);
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index bc374750529b..08a85831e917 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -1693,7 +1693,7 @@ static int dib0090_dc_offset_calibration(struct dib0090_state *state, enum front
 		if (state->identity.p1g)
 			state->dc = dc_p1g_table;
 
-		/* fall through */
+		fallthrough;
 	case CT_TUNER_STEP_0:
 		dprintk("Start/continue DC calibration for %s path\n",
 			(state->dc->i == 1) ? "I" : "Q");
diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c
index 0f0480d8576d..a6c2fc4586eb 100644
--- a/drivers/media/dvb-frontends/dib3000mb.c
+++ b/drivers/media/dvb-frontends/dib3000mb.c
@@ -224,7 +224,7 @@ static int dib3000mb_set_frontend(struct dvb_frontend *fe, int tuner)
 	switch (c->hierarchy) {
 		case HIERARCHY_NONE:
 			deb_setf("hierarchy: none\n");
-			/* fall through */
+			fallthrough;
 		case HIERARCHY_1:
 			deb_setf("hierarchy: alpha=1\n");
 			wr(DIB3000MB_REG_VIT_ALPHA, DIB3000_ALPHA_1);
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 0a7790c4bad3..55bee50aa871 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -276,7 +276,7 @@ static int dib7000p_set_power_mode(struct dib7000p_state *state, enum dib7000p_p
 		if (state->version != SOC7090)
 			reg_1280 &= ~((1 << 11));
 		reg_1280 &= ~(1 << 6);
-		/* fall-through */
+		fallthrough;
 	case DIB7000P_POWER_INTERFACE_ONLY:
 		/* just leave power on the control-interfaces: GPIO and (I2C or SDIO) */
 		/* TODO power up either SDIO or I2C */
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 5de016412c42..237b9d04c076 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -2306,7 +2306,7 @@ hi_command(struct i2c_device_addr *dev_addr, const struct drxj_hi_cmd *cmd, u16
 			pr_err("error %d\n", rc);
 			goto rw_error;
 		}
-		/* fallthrough */
+		fallthrough;
 	case SIO_HI_RA_RAM_CMD_BRDCTRL:
 		rc = drxj_dap_write_reg16(dev_addr, SIO_HI_RA_RAM_PAR_2__A, cmd->param2, 0);
 		if (rc != 0) {
@@ -2318,7 +2318,7 @@ hi_command(struct i2c_device_addr *dev_addr, const struct drxj_hi_cmd *cmd, u16
 			pr_err("error %d\n", rc);
 			goto rw_error;
 		}
-		/* fallthrough */
+		fallthrough;
 	case SIO_HI_RA_RAM_CMD_NULL:
 		/* No parameters */
 		break;
@@ -2841,7 +2841,7 @@ ctrl_set_cfg_mpeg_output(struct drx_demod_instance *demod, struct drx_cfg_mpeg_o
 			/* coef = 188/204                          */
 			max_bit_rate =
 			    (ext_attr->curr_symbol_rate / 8) * nr_bits * 188;
-			/* fall-through - as b/c Annex A/C need following settings */
+			fallthrough;	/* as b/c Annex A/C need following settings */
 		case DRX_STANDARD_ITU_B:
 			rc = drxj_dap_write_reg16(dev_addr, FEC_OC_FCT_USAGE__A, FEC_OC_FCT_USAGE__PRE, 0);
 			if (rc != 0) {
@@ -3555,8 +3555,8 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg
 		if (!ext_attr->has_smatx)
 			return -EIO;
 		switch (uio_cfg->mode) {
-		case DRX_UIO_MODE_FIRMWARE_SMA:	/* fall through */
-		case DRX_UIO_MODE_FIRMWARE_SAW:	/* fall through */
+		case DRX_UIO_MODE_FIRMWARE_SMA:
+		case DRX_UIO_MODE_FIRMWARE_SAW:
 		case DRX_UIO_MODE_READWRITE:
 			ext_attr->uio_sma_tx_mode = uio_cfg->mode;
 			break;
@@ -3579,7 +3579,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg
 		if (!ext_attr->has_smarx)
 			return -EIO;
 		switch (uio_cfg->mode) {
-		case DRX_UIO_MODE_FIRMWARE0:	/* fall through */
+		case DRX_UIO_MODE_FIRMWARE0:
 		case DRX_UIO_MODE_READWRITE:
 			ext_attr->uio_sma_rx_mode = uio_cfg->mode;
 			break;
@@ -3603,7 +3603,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg
 		if (!ext_attr->has_gpio)
 			return -EIO;
 		switch (uio_cfg->mode) {
-		case DRX_UIO_MODE_FIRMWARE0:	/* fall through */
+		case DRX_UIO_MODE_FIRMWARE0:
 		case DRX_UIO_MODE_READWRITE:
 			ext_attr->uio_gpio_mode = uio_cfg->mode;
 			break;
@@ -3639,7 +3639,7 @@ static int ctrl_set_uio_cfg(struct drx_demod_instance *demod, struct drxuio_cfg
 			}
 			ext_attr->uio_irqn_mode = uio_cfg->mode;
 			break;
-		case DRX_UIO_MODE_FIRMWARE0:	/* fall through */
+		case DRX_UIO_MODE_FIRMWARE0:
 		default:
 			return -EINVAL;
 			break;
@@ -4004,31 +4004,36 @@ static int scu_command(struct i2c_device_addr *dev_addr, struct drxjscu_cmd *cmd
 		if (rc != 0) {
 			pr_err("error %d\n", rc);
 			goto rw_error;
-		}	/* fallthrough */
+		}
+		fallthrough;
 	case 4:
 		rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_3__A, *(cmd->parameter + 3), 0);
 		if (rc != 0) {
 			pr_err("error %d\n", rc);
 			goto rw_error;
-		}	/* fallthrough */
+		}
+		fallthrough;
 	case 3:
 		rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_2__A, *(cmd->parameter + 2), 0);
 		if (rc != 0) {
 			pr_err("error %d\n", rc);
 			goto rw_error;
-		}	/* fallthrough */
+		}
+		fallthrough;
 	case 2:
 		rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_1__A, *(cmd->parameter + 1), 0);
 		if (rc != 0) {
 			pr_err("error %d\n", rc);
 			goto rw_error;
-		}	/* fallthrough */
+		}
+		fallthrough;
 	case 1:
 		rc = drxj_dap_write_reg16(dev_addr, SCU_RAM_PARAM_0__A, *(cmd->parameter + 0), 0);
 		if (rc != 0) {
 			pr_err("error %d\n", rc);
 			goto rw_error;
-		}	/* fallthrough */
+		}
+		fallthrough;
 	case 0:
 		/* do nothing */
 		break;
@@ -4068,25 +4073,29 @@ static int scu_command(struct i2c_device_addr *dev_addr, struct drxjscu_cmd *cmd
 			if (rc != 0) {
 				pr_err("error %d\n", rc);
 				goto rw_error;
-			}	/* fallthrough */
+			}
+			fallthrough;
 		case 3:
 			rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_2__A, cmd->result + 2, 0);
 			if (rc != 0) {
 				pr_err("error %d\n", rc);
 				goto rw_error;
-			}	/* fallthrough */
+			}
+			fallthrough;
 		case 2:
 			rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_1__A, cmd->result + 1, 0);
 			if (rc != 0) {
 				pr_err("error %d\n", rc);
 				goto rw_error;
-			}	/* fallthrough */
+			}
+			fallthrough;
 		case 1:
 			rc = drxj_dap_read_reg16(dev_addr, SCU_RAM_PARAM_0__A, cmd->result + 0, 0);
 			if (rc != 0) {
 				pr_err("error %d\n", rc);
 				goto rw_error;
-			}	/* fallthrough */
+			}
+			fallthrough;
 		case 0:
 			/* do nothing */
 			break;
@@ -4791,7 +4800,7 @@ set_frequency(struct drx_demod_instance *demod,
 		   Sound carrier is already 3Mhz above centre frequency due
 		   to tuner setting so now add an extra shift of 1MHz... */
 		fm_frequency_shift = 1000;
-		/*fall through */
+		fallthrough;
 	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_NTSC:
 	case DRX_STANDARD_PAL_SECAM_BG:
@@ -10475,11 +10484,11 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel)
 	    (standard == DRX_STANDARD_NTSC)) {
 		switch (channel->bandwidth) {
 		case DRX_BANDWIDTH_6MHZ:
-		case DRX_BANDWIDTH_UNKNOWN:	/* fall through */
+		case DRX_BANDWIDTH_UNKNOWN:
 			channel->bandwidth = DRX_BANDWIDTH_6MHZ;
 			break;
-		case DRX_BANDWIDTH_8MHZ:	/* fall through */
-		case DRX_BANDWIDTH_7MHZ:	/* fall through */
+		case DRX_BANDWIDTH_8MHZ:
+		case DRX_BANDWIDTH_7MHZ:
 		default:
 			return -EINVAL;
 		}
@@ -10511,10 +10520,10 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel)
 		}
 
 		switch (channel->constellation) {
-		case DRX_CONSTELLATION_QAM16:	/* fall through */
-		case DRX_CONSTELLATION_QAM32:	/* fall through */
-		case DRX_CONSTELLATION_QAM64:	/* fall through */
-		case DRX_CONSTELLATION_QAM128:	/* fall through */
+		case DRX_CONSTELLATION_QAM16:
+		case DRX_CONSTELLATION_QAM32:
+		case DRX_CONSTELLATION_QAM64:
+		case DRX_CONSTELLATION_QAM128:
 		case DRX_CONSTELLATION_QAM256:
 			bandwidth_temp = channel->symbolrate * bw_rolloff_factor;
 			bandwidth = bandwidth_temp / 100;
@@ -10628,8 +10637,8 @@ ctrl_set_channel(struct drx_demod_instance *demod, struct drx_channel *channel)
 		}
 		break;
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 		rc = set_qam_channel(demod, channel, tuner_freq_offset);
 		if (rc != 0) {
@@ -10820,7 +10829,7 @@ ctrl_lock_status(struct drx_demod_instance *demod, enum drx_lock_status *lock_st
 		    SCU_RAM_COMMAND_CMD_DEMOD_GET_LOCK;
 		break;
 #endif
-	case DRX_STANDARD_UNKNOWN:	/* fallthrough */
+	case DRX_STANDARD_UNKNOWN:
 	default:
 		return -EIO;
 	}
@@ -10888,8 +10897,8 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard)
 	 */
 	switch (prev_standard) {
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 		rc = power_down_qam(demod, false);
 		if (rc != 0) {
@@ -10908,7 +10917,7 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard)
 	case DRX_STANDARD_UNKNOWN:
 		/* Do nothing */
 		break;
-	case DRX_STANDARD_AUTO:	/* fallthrough */
+	case DRX_STANDARD_AUTO:
 	default:
 		return -EINVAL;
 	}
@@ -10921,8 +10930,8 @@ ctrl_set_standard(struct drx_demod_instance *demod, enum drx_standard *standard)
 
 	switch (*standard) {
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 		do {
 			u16 dummy;
@@ -11111,12 +11120,12 @@ ctrl_power_mode(struct drx_demod_instance *demod, enum drx_power_mode *mode)
 				goto rw_error;
 			}
 			break;
-		case DRX_STANDARD_PAL_SECAM_BG:	/* fallthrough */
-		case DRX_STANDARD_PAL_SECAM_DK:	/* fallthrough */
-		case DRX_STANDARD_PAL_SECAM_I:	/* fallthrough */
-		case DRX_STANDARD_PAL_SECAM_L:	/* fallthrough */
-		case DRX_STANDARD_PAL_SECAM_LP:	/* fallthrough */
-		case DRX_STANDARD_NTSC:	/* fallthrough */
+		case DRX_STANDARD_PAL_SECAM_BG:
+		case DRX_STANDARD_PAL_SECAM_DK:
+		case DRX_STANDARD_PAL_SECAM_I:
+		case DRX_STANDARD_PAL_SECAM_L:
+		case DRX_STANDARD_PAL_SECAM_LP:
+		case DRX_STANDARD_NTSC:
 		case DRX_STANDARD_FM:
 			rc = power_down_atv(demod, ext_attr->standard, true);
 			if (rc != 0) {
@@ -11127,7 +11136,7 @@ ctrl_power_mode(struct drx_demod_instance *demod, enum drx_power_mode *mode)
 		case DRX_STANDARD_UNKNOWN:
 			/* Do nothing */
 			break;
-		case DRX_STANDARD_AUTO:	/* fallthrough */
+		case DRX_STANDARD_AUTO:
 		default:
 			return -EIO;
 		}
@@ -11220,8 +11229,8 @@ ctrl_set_cfg_pre_saw(struct drx_demod_instance *demod, struct drxj_cfg_pre_saw *
 		ext_attr->vsb_pre_saw_cfg = *pre_saw;
 		break;
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 		ext_attr->qam_pre_saw_cfg = *pre_saw;
 		break;
@@ -11264,10 +11273,10 @@ ctrl_set_cfg_afe_gain(struct drx_demod_instance *demod, struct drxj_cfg_afe_gain
 	ext_attr = (struct drxj_data *) demod->my_ext_attr;
 
 	switch (afe_gain->standard) {
-	case DRX_STANDARD_8VSB:	/* fallthrough */
+	case DRX_STANDARD_8VSB:	fallthrough;
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 #endif
 		/* Do nothing */
@@ -11301,8 +11310,8 @@ ctrl_set_cfg_afe_gain(struct drx_demod_instance *demod, struct drxj_cfg_afe_gain
 		ext_attr->vsb_pga_cfg = gain * 13 + 140;
 		break;
 #ifndef DRXJ_VSB_ONLY
-	case DRX_STANDARD_ITU_A:	/* fallthrough */
-	case DRX_STANDARD_ITU_B:	/* fallthrough */
+	case DRX_STANDARD_ITU_A:
+	case DRX_STANDARD_ITU_B:
 	case DRX_STANDARD_ITU_C:
 		ext_attr->qam_pga_cfg = gain * 13 + 140;
 		break;
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index fae6f3763364..45f982863904 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -1512,14 +1512,14 @@ static int SetDeviceTypeId(struct drxd_state *state)
 			switch (deviceId) {
 			case 4:
 				state->diversity = 1;
-				/* fall through */
+				fallthrough;
 			case 3:
 			case 7:
 				state->PGA = 1;
 				break;
 			case 6:
 				state->diversity = 1;
-				/* fall through */
+				fallthrough;
 			case 5:
 			case 8:
 				break;
@@ -1966,7 +1966,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->transmission_mode) {
 		default:	/* Not set, detect it automatically */
 			operationMode |= SC_RA_RAM_OP_AUTO_MODE__M;
-			/* fall through - try first guess DRX_FFTMODE_8K */
+			fallthrough;	/* try first guess DRX_FFTMODE_8K */
 		case TRANSMISSION_MODE_8K:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_MODE_8K;
 			if (state->type_A) {
@@ -2139,7 +2139,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->modulation) {
 		default:
 			operationMode |= SC_RA_RAM_OP_AUTO_CONST__M;
-			/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
+			fallthrough;	/* try first guess DRX_CONSTELLATION_QAM64 */
 		case QAM_64:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_CONST_QAM64;
 			if (state->type_A) {
@@ -2266,7 +2266,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 			break;
 		default:
 			operationMode |= SC_RA_RAM_OP_AUTO_RATE__M;
-			/* fall through */
+			fallthrough;
 		case FEC_2_3:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_RATE_2_3;
 			if (state->type_A)
@@ -2301,7 +2301,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->bandwidth_hz) {
 		case 0:
 			p->bandwidth_hz = 8000000;
-			/* fall through */
+			fallthrough;
 		case 8000000:
 			/* (64/7)*(8/8)*1000000 */
 			bandwidth = DRXD_BANDWIDTH_8MHZ_IN_HZ;
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index 0ae9d8c72d8d..32f9346deb3e 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -1756,7 +1756,7 @@ static int setoperation_mode(struct drxk_state *state,
 			goto error;
 		state->m_operation_mode = OM_NONE;
 		break;
-	case OM_QAM_ITU_A:	/* fallthrough */
+	case OM_QAM_ITU_A:
 	case OM_QAM_ITU_C:
 		status = mpegts_stop(state);
 		if (status < 0)
@@ -1783,7 +1783,7 @@ static int setoperation_mode(struct drxk_state *state,
 		if (status < 0)
 			goto error;
 		break;
-	case OM_QAM_ITU_A:	/* fallthrough */
+	case OM_QAM_ITU_A:
 	case OM_QAM_ITU_C:
 		dprintk(1, ": DVB-C Annex %c\n",
 			(state->m_operation_mode == OM_QAM_ITU_A) ? 'A' : 'C');
@@ -2012,7 +2012,7 @@ static int mpegts_dto_setup(struct drxk_state *state,
 		fec_oc_rcn_ctl_rate = 0xC00000;
 		static_clk = state->m_dvbt_static_clk;
 		break;
-	case OM_QAM_ITU_A:	/* fallthrough */
+	case OM_QAM_ITU_A:
 	case OM_QAM_ITU_C:
 		fec_oc_tmd_mode = 0x0004;
 		fec_oc_rcn_ctl_rate = 0xD2B4EE;	/* good for >63 Mb/s */
@@ -3249,11 +3249,11 @@ static int dvbt_sc_command(struct drxk_state *state,
 	case OFDM_SC_RA_RAM_CMD_SET_PREF_PARAM:
 	case OFDM_SC_RA_RAM_CMD_PROGRAM_PARAM:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM1__A, param1);
-		/* fall through - All commands using 1 parameters */
+		fallthrough;	/* All commands using 1 parameters */
 	case OFDM_SC_RA_RAM_CMD_SET_ECHO_TIMING:
 	case OFDM_SC_RA_RAM_CMD_USER_IO:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM0__A, param0);
-		/* fall through - All commands using 0 parameters */
+		fallthrough;	/* All commands using 0 parameters */
 	case OFDM_SC_RA_RAM_CMD_GET_OP_PARAM:
 	case OFDM_SC_RA_RAM_CMD_NULL:
 		/* Write command */
@@ -3761,7 +3761,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case TRANSMISSION_MODE_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_MODE__M;
-		/* fall through - try first guess DRX_FFTMODE_8K */
+		fallthrough;	/* try first guess DRX_FFTMODE_8K */
 	case TRANSMISSION_MODE_8K:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_MODE_8K;
 		break;
@@ -3775,7 +3775,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	default:
 	case GUARD_INTERVAL_AUTO:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_GUARD__M;
-		/* fall through - try first guess DRX_GUARD_1DIV4 */
+		fallthrough;	/* try first guess DRX_GUARD_1DIV4 */
 	case GUARD_INTERVAL_1_4:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_GUARD_4;
 		break;
@@ -3798,7 +3798,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_HIER__M;
 		/* try first guess SC_RA_RAM_OP_PARAM_HIER_NO */
 		/* transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_HIER_NO; */
-		/* fall through */
+		fallthrough;
 	case HIERARCHY_1:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_HIER_A1;
 		break;
@@ -3816,7 +3816,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case QAM_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_CONST__M;
-		/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
+		fallthrough;	/* try first guess DRX_CONSTELLATION_QAM64 */
 	case QAM_64:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_CONST_QAM64;
 		break;
@@ -3841,7 +3841,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 		WR16(dev_addr, OFDM_EC_SB_PRIOR__A,
 			OFDM_EC_SB_PRIOR_HI));
 		break;
-	case DRX_PRIORITY_UNKNOWN:	/* fall through */
+	case DRX_PRIORITY_UNKNOWN:
 	default:
 		status = -EINVAL;
 		goto error;
@@ -3859,7 +3859,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case FEC_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_RATE__M;
-		/* fall through - try first guess DRX_CODERATE_2DIV3 */
+		fallthrough;	/* try first guess DRX_CODERATE_2DIV3 */
 	case FEC_2_3:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_RATE_2_3;
 		break;
@@ -3893,7 +3893,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	switch (state->props.bandwidth_hz) {
 	case 0:
 		state->props.bandwidth_hz = 8000000;
-		/* fall through */
+		fallthrough;
 	case 8000000:
 		bandwidth = DRXK_BANDWIDTH_8MHZ_IN_HZ;
 		status = write16(state, OFDM_SC_RA_RAM_SRMM_FIX_FACT_8K__A,
diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c
index d3c330e035c4..722576f1732a 100644
--- a/drivers/media/dvb-frontends/lgdt3306a.c
+++ b/drivers/media/dvb-frontends/lgdt3306a.c
@@ -768,7 +768,7 @@ static int lgdt3306a_set_if(struct lgdt3306a_state *state,
 	default:
 		pr_warn("IF=%d KHz is not supported, 3250 assumed\n",
 			if_freq_khz);
-		/* fallthrough */
+		fallthrough;
 	case 3250: /* 3.25Mhz */
 		nco1 = 0x34;
 		nco2 = 0x00;
diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c
index 881897583cf2..399d5c519027 100644
--- a/drivers/media/dvb-frontends/mt352.c
+++ b/drivers/media/dvb-frontends/mt352.c
@@ -201,7 +201,7 @@ static int mt352_set_parameters(struct dvb_frontend *fe)
 			if (op->hierarchy == HIERARCHY_AUTO ||
 			    op->hierarchy == HIERARCHY_NONE)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c
index 290b9eab099f..4404ace82981 100644
--- a/drivers/media/dvb-frontends/mxl5xx.c
+++ b/drivers/media/dvb-frontends/mxl5xx.c
@@ -739,7 +739,7 @@ static int get_frontend(struct dvb_frontend *fe,
 		default:
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	case SYS_DVBS:
 		switch ((enum MXL_HYDRA_MODULATION_E)
 			reg_data[DMD_MODULATION_SCHEME_ADDR]) {
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index 35a3e47497c2..24de1b115158 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -482,7 +482,7 @@ start:
 	switch (reg&0xff) {
 	case 0x06:
 		if (reg & 0x1000) usK = 3 << 24;
-		/* fall through */
+		fallthrough;
 	case 0x43: /* QAM64 */
 		c = 150204167;
 		break;
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index 89402916d301..c1334d7eb442 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -398,7 +398,7 @@ static int s5h1411_set_if_freq(struct dvb_frontend *fe, int KHz)
 	default:
 		dprintk("%s(%d KHz) Invalid, defaulting to 5380\n",
 			__func__, KHz);
-		/* fall through */
+		fallthrough;
 	case 5380:
 	case 44000:
 		s5h1411_writereg(state, S5H1411_I2C_TOP_ADDR, 0x38, 0x1be4);
diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c
index 2fc6aea580f9..2a2cf20a73d6 100644
--- a/drivers/media/dvb-frontends/zl10353.c
+++ b/drivers/media/dvb-frontends/zl10353.c
@@ -201,7 +201,7 @@ static int zl10353_set_parameters(struct dvb_frontend *fe)
 		break;
 	default:
 		c->bandwidth_hz = 8000000;
-		/* fall through */
+		fallthrough;
 	case 8000000:
 		zl10353_single_write(fe, MCLK_RATIO, 0x75);
 		zl10353_single_write(fe, 0x64, 0x36);
@@ -258,7 +258,7 @@ static int zl10353_set_parameters(struct dvb_frontend *fe)
 		if (c->hierarchy == HIERARCHY_AUTO ||
 		    c->hierarchy == HIERARCHY_NONE)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 48ae60a2c603..c7ba76fee599 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -467,7 +467,7 @@ config VIDEO_VPX3220
 config VIDEO_MAX9286
 	tristate "Maxim MAX9286 GMSL deserializer support"
 	depends on I2C && I2C_MUX
-	depends on OF
+	depends on OF_GPIO
 	select V4L2_FWNODE
 	select VIDEO_V4L2_SUBDEV_API
 	select MEDIA_CONTROLLER
@@ -741,7 +741,7 @@ config VIDEO_HI556
 config VIDEO_IMX214
 	tristate "Sony IMX214 sensor support"
 	depends on GPIOLIB && I2C && VIDEO_V4L2
-	depends on V4L2_FWNODE
+	select V4L2_FWNODE
 	select MEDIA_CONTROLLER
 	select VIDEO_V4L2_SUBDEV_API
 	select REGMAP_I2C
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 570a4a09c387..03eee606af91 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -2209,7 +2209,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 		ts2->gen_ctrl_val  = 0xc; /* Serial bus + punctured clock */
 		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
 		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
-		/* fall-through */
+		fallthrough;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_5_EXP:
 		ts1->gen_ctrl_val  = 0xc; /* Serial bus + punctured clock */
 		ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */
@@ -2370,7 +2370,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 		/* Currently only enabled for the integrated IR controller */
 		if (!enable_885_ir)
 			break;
-		/* fall-through */
+		fallthrough;
 	case CX23885_BOARD_HAUPPAUGE_HVR1250:
 	case CX23885_BOARD_HAUPPAUGE_HVR1800:
 	case CX23885_BOARD_HAUPPAUGE_IMPACTVCBE:
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 7cabb9e9ffe2..92fe051c672f 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1310,7 +1310,7 @@ static void dvb_input_detach(struct ddb_input *input)
 			dvb_unregister_frontend(dvb->fe2);
 		if (dvb->fe)
 			dvb_unregister_frontend(dvb->fe);
-		/* fallthrough */
+		fallthrough;
 	case 0x30:
 		dvb_module_release(dvb->i2c_client[0]);
 		dvb->i2c_client[0] = NULL;
@@ -1321,22 +1321,22 @@ static void dvb_input_detach(struct ddb_input *input)
 			dvb_frontend_detach(dvb->fe);
 		dvb->fe = NULL;
 		dvb->fe2 = NULL;
-		/* fallthrough */
+		fallthrough;
 	case 0x20:
 		dvb_net_release(&dvb->dvbnet);
-		/* fallthrough */
+		fallthrough;
 	case 0x12:
 		dvbdemux->dmx.remove_frontend(&dvbdemux->dmx,
 					      &dvb->hw_frontend);
 		dvbdemux->dmx.remove_frontend(&dvbdemux->dmx,
 					      &dvb->mem_frontend);
-		/* fallthrough */
+		fallthrough;
 	case 0x11:
 		dvb_dmxdev_release(&dvb->dmxdev);
-		/* fallthrough */
+		fallthrough;
 	case 0x10:
 		dvb_dmx_release(&dvb->demux);
-		/* fallthrough */
+		fallthrough;
 	case 0x01:
 		break;
 	}
@@ -1559,7 +1559,7 @@ static int dvb_input_attach(struct ddb_input *input)
 			osc24 = 0;
 		else
 			osc24 = 1;
-		/* fall-through */
+		fallthrough;
 	case DDB_TUNER_DVBCT2_SONY_P:
 	case DDB_TUNER_DVBC2T2_SONY_P:
 	case DDB_TUNER_ISDBT_SONY_P:
@@ -1575,7 +1575,7 @@ static int dvb_input_attach(struct ddb_input *input)
 		break;
 	case DDB_TUNER_DVBC2T2I_SONY:
 		osc24 = 1;
-		/* fall-through */
+		fallthrough;
 	case DDB_TUNER_DVBCT2_SONY:
 	case DDB_TUNER_DVBC2T2_SONY:
 	case DDB_TUNER_ISDBT_SONY:
@@ -2036,7 +2036,7 @@ static int ddb_port_attach(struct ddb_port *port)
 		ret = ddb_ci_attach(port, ci_bitrate);
 		if (ret < 0)
 			break;
-		/* fall-through */
+		fallthrough;
 	case DDB_PORT_LOOP:
 		ret = dvb_register_device(port->dvb[0].adap,
 					  &port->dvb[0].dev,
@@ -2432,7 +2432,8 @@ void ddb_ports_init(struct ddb *dev)
 					ddb_input_init(port, 4 + i, 1, 4 + i);
 					ddb_output_init(port, i);
 					break;
-				} /* fallthrough */
+				}
+				fallthrough;
 			case DDB_OCTOPUS:
 				ddb_input_init(port, 2 * i, 0, 2 * i);
 				ddb_input_init(port, 2 * i + 1, 1, 2 * i + 1);
@@ -3417,7 +3418,7 @@ int ddb_exit_ddbridge(int stage, int error)
 	default:
 	case 2:
 		destroy_workqueue(ddb_wq);
-		/* fall-through */
+		fallthrough;
 	case 1:
 		ddb_class_destroy();
 		break;
diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c
index 7fb3b1853b87..8944e4bd4638 100644
--- a/drivers/media/pci/meye/meye.c
+++ b/drivers/media/pci/meye/meye.c
@@ -952,7 +952,7 @@ static int meyeioc_sync(struct file *file, void *fh, int *i)
 			mutex_unlock(&meye.lock);
 			return -EINTR;
 		}
-		/* fall through */
+		fallthrough;
 	case MEYE_BUF_DONE:
 		meye.grab_buffer[*i].state = MEYE_BUF_UNUSED;
 		if (kfifo_out_locked(&meye.doneq, (unsigned char *)&unused,
diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c
index bf36b1e22b63..45228f4f6fc6 100644
--- a/drivers/media/pci/ttpci/av7110.c
+++ b/drivers/media/pci/ttpci/av7110.c
@@ -637,7 +637,7 @@ static void gpioirq(unsigned long cookie)
 			iwdebi(av7110, DEBINOSWAP, RX_BUFF, 0, 2);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case DATA_TS_RECORD:
 	case DATA_PES_RECORD:
@@ -2176,7 +2176,7 @@ static int frontend_init(struct av7110 *av7110)
 				break;
 			}
 		}
-		/* fall-thru */
+			fallthrough;
 
 		case 0x0008: // Hauppauge/TT DVB-T
 			// Grundig 29504-401
diff --git a/drivers/media/pci/ttpci/av7110_hw.c b/drivers/media/pci/ttpci/av7110_hw.c
index e8a8ec5405e2..93ca31e38ddd 100644
--- a/drivers/media/pci/ttpci/av7110_hw.c
+++ b/drivers/media/pci/ttpci/av7110_hw.c
@@ -1107,7 +1107,7 @@ int av7110_osd_cmd(struct av7110 *av7110, osd_cmd_t *dc)
 		break;
 	case OSD_SetRow:
 		dc->y1 = dc->y0;
-		/* fall through */
+		fallthrough;
 	case OSD_SetBlock:
 		ret = OSDSetBlock(av7110, dc->x0, dc->y0, dc->x1, dc->y1, dc->color, dc->data);
 		break;
diff --git a/drivers/media/pci/ttpci/av7110_ipack.c b/drivers/media/pci/ttpci/av7110_ipack.c
index ec528fae7333..30330ed01ce8 100644
--- a/drivers/media/pci/ttpci/av7110_ipack.c
+++ b/drivers/media/pci/ttpci/av7110_ipack.c
@@ -182,7 +182,7 @@ int av7110_ipack_instant_repack (const u8 *buf, int count, struct ipack *p)
 			case DSM_CC_STREAM  :
 			case ISO13522_STREAM:
 				p->done = 1;
-				/* fall through */
+				fallthrough;
 			case PRIVATE_STREAM1:
 			case VIDEO_STREAM_S ... VIDEO_STREAM_E:
 			case AUDIO_STREAM_S ... AUDIO_STREAM_E:
diff --git a/drivers/media/pci/ttpci/budget-av.c b/drivers/media/pci/ttpci/budget-av.c
index 38cac508bd72..3cb83005cf09 100644
--- a/drivers/media/pci/ttpci/budget-av.c
+++ b/drivers/media/pci/ttpci/budget-av.c
@@ -1226,7 +1226,7 @@ static void frontend_init(struct budget_av *budget_av)
 		 * but so far it has been only confirmed for this type
 		 */
 		budget_av->reinitialise_demod = 1;
-		/* fall through */
+		fallthrough;
 	case SUBID_DVBS_KNC1_PLUS:
 	case SUBID_DVBS_EASYWATCH_1:
 		if (saa->pci->subsystem_vendor == 0x1894) {
diff --git a/drivers/media/pci/ttpci/budget.c b/drivers/media/pci/ttpci/budget.c
index 9c811272abfe..a88711a3ac7f 100644
--- a/drivers/media/pci/ttpci/budget.c
+++ b/drivers/media/pci/ttpci/budget.c
@@ -613,7 +613,7 @@ static void frontend_init(struct budget *budget)
 			break;
 		}
 	}
-	/* fall through */
+		fallthrough;
 	case 0x1018: // TT Budget-S-1401 (philips tda10086/philips tda8262)
 	{
 		struct dvb_frontend *fe;
@@ -638,7 +638,7 @@ static void frontend_init(struct budget *budget)
 			break;
 		}
 	}
-	/* fall through */
+		fallthrough;
 
 	case 0x101c: { /* TT S2-1600 */
 			const struct stv6110x_devctl *ctl;
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 36e5f2ff4ef1..b22dc1d72527 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -220,7 +220,7 @@ static void sh_vou_stream_config(struct sh_vou_device *vou_dev)
 		break;
 	case V4L2_PIX_FMT_RGB565:
 		dataswap ^= 1;
-		/* fall through */
+		fallthrough;
 	case V4L2_PIX_FMT_RGB565X:
 		row_coeff = 2;
 		break;
@@ -802,7 +802,7 @@ static u32 sh_vou_ntsc_mode(enum sh_vou_bus_fmt bus_fmt)
 	default:
 		pr_warn("%s(): Invalid bus-format code %d, using default 8-bit\n",
 			__func__, bus_fmt);
-		/* fall through */
+		fallthrough;
 	case SH_VOU_BUS_8BIT:
 		return 1;
 	case SH_VOU_BUS_16BIT:
diff --git a/drivers/media/platform/ti-vpe/cal.h b/drivers/media/platform/ti-vpe/cal.h
index e496083715d2..4123405ee0cf 100644
--- a/drivers/media/platform/ti-vpe/cal.h
+++ b/drivers/media/platform/ti-vpe/cal.h
@@ -226,7 +226,7 @@ static inline void cal_write_field(struct cal_dev *cal, u32 offset, u32 value,
 	u32 val = cal_read(cal, offset);
 
 	val &= ~mask;
-	val |= FIELD_PREP(mask, value);
+	val |= (value << __ffs(mask)) & mask;
 	cal_write(cal, offset, val);
 }
 
diff --git a/drivers/media/radio/radio-si476x.c b/drivers/media/radio/radio-si476x.c
index b203296de977..7e2460263882 100644
--- a/drivers/media/radio/radio-si476x.c
+++ b/drivers/media/radio/radio-si476x.c
@@ -105,7 +105,8 @@ static inline enum phase_diversity_modes_idx
 si476x_phase_diversity_mode_to_idx(enum si476x_phase_diversity_mode mode)
 {
 	switch (mode) {
-	default:		/* FALLTHROUGH */
+	default:
+		fallthrough;
 	case SI476X_PHDIV_DISABLED:
 		return SI476X_IDX_PHDIV_DISABLED;
 	case SI476X_PHDIV_PRIMARY_COMBINING:
diff --git a/drivers/media/radio/tea575x.c b/drivers/media/radio/tea575x.c
index b0303cf00387..c37315226c42 100644
--- a/drivers/media/radio/tea575x.c
+++ b/drivers/media/radio/tea575x.c
@@ -249,7 +249,7 @@ int snd_tea575x_enum_freq_bands(struct snd_tea575x *tea,
 			index = BAND_AM;
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 5bb144435c16..3fe3edd80876 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -112,7 +112,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_trace_printk:
 		if (perfmon_capable())
 			return bpf_get_trace_printk_proto();
-		/* fall through */
+		fallthrough;
 	default:
 		return NULL;
 	}
diff --git a/drivers/media/rc/gpio-ir-tx.c b/drivers/media/rc/gpio-ir-tx.c
index f33b443bfa47..c6cd2e6d8e65 100644
--- a/drivers/media/rc/gpio-ir-tx.c
+++ b/drivers/media/rc/gpio-ir-tx.c
@@ -19,8 +19,6 @@ struct gpio_ir {
 	struct gpio_desc *gpio;
 	unsigned int carrier;
 	unsigned int duty_cycle;
-	/* we need a spinlock to hold the cpu while transmitting */
-	spinlock_t lock;
 };
 
 static const struct of_device_id gpio_ir_tx_of_match[] = {
@@ -53,12 +51,11 @@ static int gpio_ir_tx_set_carrier(struct rc_dev *dev, u32 carrier)
 static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf,
 				   uint count)
 {
-	unsigned long flags;
 	ktime_t edge;
 	s32 delta;
 	int i;
 
-	spin_lock_irqsave(&gpio_ir->lock, flags);
+	local_irq_disable();
 
 	edge = ktime_get();
 
@@ -72,14 +69,11 @@ static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf,
 	}
 
 	gpiod_set_value(gpio_ir->gpio, 0);
-
-	spin_unlock_irqrestore(&gpio_ir->lock, flags);
 }
 
 static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf,
 				 uint count)
 {
-	unsigned long flags;
 	ktime_t edge;
 	/*
 	 * delta should never exceed 0.5 seconds (IR_MAX_DURATION) and on
@@ -95,7 +89,7 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf,
 	space = DIV_ROUND_CLOSEST((100 - gpio_ir->duty_cycle) *
 				  (NSEC_PER_SEC / 100), gpio_ir->carrier);
 
-	spin_lock_irqsave(&gpio_ir->lock, flags);
+	local_irq_disable();
 
 	edge = ktime_get();
 
@@ -128,19 +122,20 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf,
 			edge = last;
 		}
 	}
-
-	spin_unlock_irqrestore(&gpio_ir->lock, flags);
 }
 
 static int gpio_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 		      unsigned int count)
 {
 	struct gpio_ir *gpio_ir = dev->priv;
+	unsigned long flags;
 
+	local_irq_save(flags);
 	if (gpio_ir->carrier)
 		gpio_ir_tx_modulated(gpio_ir, txbuf, count);
 	else
 		gpio_ir_tx_unmodulated(gpio_ir, txbuf, count);
+	local_irq_restore(flags);
 
 	return count;
 }
@@ -176,7 +171,6 @@ static int gpio_ir_tx_probe(struct platform_device *pdev)
 
 	gpio_ir->carrier = 38000;
 	gpio_ir->duty_cycle = 50;
-	spin_lock_init(&gpio_ir->lock);
 
 	rc = devm_rc_register_device(&pdev->dev, rcdev);
 	if (rc < 0)
diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c
index 95727ca910f7..0cda78f72fd8 100644
--- a/drivers/media/rc/ir-rc6-decoder.c
+++ b/drivers/media/rc/ir-rc6-decoder.c
@@ -64,7 +64,7 @@ static enum rc6_mode rc6_mode(struct rc6_dec *data)
 	case 6:
 		if (!data->toggle)
 			return RC6_MODE_6A;
-		/* fall through */
+		fallthrough;
 	default:
 		return RC6_MODE_UNKNOWN;
 	}
diff --git a/drivers/media/rc/ir-sony-decoder.c b/drivers/media/rc/ir-sony-decoder.c
index 9fa58d92eb09..7d9a7c000c75 100644
--- a/drivers/media/rc/ir-sony-decoder.c
+++ b/drivers/media/rc/ir-sony-decoder.c
@@ -102,7 +102,7 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		}
 
 		data->state = STATE_FINISHED;
-		/* Fall through */
+		fallthrough;
 
 	case STATE_FINISHED:
 		if (ev.pulse)
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index f9616158bcf4..98681ba10428 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1726,7 +1726,7 @@ static int mceusb_dev_probe(struct usb_interface *intf,
 		goto mem_alloc_fail;
 
 	ir->pipe_in = pipe;
-	ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_ATOMIC, &ir->dma_in);
+	ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_KERNEL, &ir->dma_in);
 	if (!ir->buf_in)
 		goto buf_in_alloc_fail;
 
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 7b53066d9d07..dee8a9f3d80a 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1292,6 +1292,10 @@ static ssize_t store_protocols(struct device *device,
 	}
 
 	mutex_lock(&dev->lock);
+	if (!dev->registered) {
+		mutex_unlock(&dev->lock);
+		return -ENODEV;
+	}
 
 	old_protocols = *current_protocols;
 	new_protocols = old_protocols;
@@ -1430,6 +1434,10 @@ static ssize_t store_filter(struct device *device,
 		return -EINVAL;
 
 	mutex_lock(&dev->lock);
+	if (!dev->registered) {
+		mutex_unlock(&dev->lock);
+		return -ENODEV;
+	}
 
 	new_filter = *filter;
 	if (fattr->mask)
@@ -1544,6 +1552,10 @@ static ssize_t store_wakeup_protocols(struct device *device,
 	int i;
 
 	mutex_lock(&dev->lock);
+	if (!dev->registered) {
+		mutex_unlock(&dev->lock);
+		return -ENODEV;
+	}
 
 	allowed = dev->allowed_wakeup_protocols;
 
@@ -1601,25 +1613,25 @@ static void rc_dev_release(struct device *device)
 	kfree(dev);
 }
 
-#define ADD_HOTPLUG_VAR(fmt, val...)					\
-	do {								\
-		int err = add_uevent_var(env, fmt, val);		\
-		if (err)						\
-			return err;					\
-	} while (0)
-
 static int rc_dev_uevent(struct device *device, struct kobj_uevent_env *env)
 {
 	struct rc_dev *dev = to_rc_dev(device);
+	int ret = 0;
 
-	if (dev->rc_map.name)
-		ADD_HOTPLUG_VAR("NAME=%s", dev->rc_map.name);
-	if (dev->driver_name)
-		ADD_HOTPLUG_VAR("DRV_NAME=%s", dev->driver_name);
-	if (dev->device_name)
-		ADD_HOTPLUG_VAR("DEV_NAME=%s", dev->device_name);
+	mutex_lock(&dev->lock);
 
-	return 0;
+	if (!dev->registered)
+		ret = -ENODEV;
+	if (ret == 0 && dev->rc_map.name)
+		ret = add_uevent_var(env, "NAME=%s", dev->rc_map.name);
+	if (ret == 0 && dev->driver_name)
+		ret = add_uevent_var(env, "DRV_NAME=%s", dev->driver_name);
+	if (ret == 0 && dev->device_name)
+		ret = add_uevent_var(env, "DEV_NAME=%s", dev->device_name);
+
+	mutex_unlock(&dev->lock);
+
+	return ret;
 }
 
 /*
@@ -2011,14 +2023,14 @@ void rc_unregister_device(struct rc_dev *dev)
 	del_timer_sync(&dev->timer_keyup);
 	del_timer_sync(&dev->timer_repeat);
 
-	rc_free_rx_device(dev);
-
 	mutex_lock(&dev->lock);
 	if (dev->users && dev->close)
 		dev->close(dev);
 	dev->registered = false;
 	mutex_unlock(&dev->lock);
 
+	rc_free_rx_device(dev);
+
 	/*
 	 * lirc device should be freed with dev->registered = false, so
 	 * that userspace polling will get notified.
diff --git a/drivers/media/test-drivers/vicodec/vicodec-core.c b/drivers/media/test-drivers/vicodec/vicodec-core.c
index 8941d73f6611..71928e30dae8 100644
--- a/drivers/media/test-drivers/vicodec/vicodec-core.c
+++ b/drivers/media/test-drivers/vicodec/vicodec-core.c
@@ -1994,6 +1994,7 @@ static int vicodec_request_validate(struct media_request *req)
 	}
 	ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl,
 					       vicodec_ctrl_stateless_state.id);
+	v4l2_ctrl_request_hdl_put(hdl);
 	if (!ctrl) {
 		v4l2_info(&ctx->dev->v4l2_dev,
 			  "Missing required codec control\n");
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 734a92caad8d..7b7d9fe4f945 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -756,7 +756,7 @@ static int xc5000_set_digital_params(struct dvb_frontend *fe)
 		if (!bw)
 			bw = 6000000;
 		/* fall to OFDM handling */
-		/* fall through */
+		fallthrough;
 	case SYS_DMBTH:
 	case SYS_DVBT:
 	case SYS_DVBT2:
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index 198ddfb8d2b1..e3234d169065 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -525,7 +525,7 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb)
 	case USB_SPEED_HIGH:
 		info("running at HIGH speed.");
 		break;
-	case USB_SPEED_UNKNOWN: /* fall through */
+	case USB_SPEED_UNKNOWN:
 	default:
 		err("cannot handle USB speed because it is unknown.");
 		return -ENODEV;
diff --git a/drivers/media/usb/cpia2/cpia2_core.c b/drivers/media/usb/cpia2/cpia2_core.c
index 20c50c2d042e..e747548ab286 100644
--- a/drivers/media/usb/cpia2/cpia2_core.c
+++ b/drivers/media/usb/cpia2/cpia2_core.c
@@ -165,7 +165,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_BRIGHTNESS:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_BRIGHTNESS:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -176,7 +176,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_CONTRAST:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_CONTRAST:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -184,7 +184,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_SATURATION:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_SATURATION:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -195,7 +195,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_GPIO_DATA:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_GPIO_DATA:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -203,7 +203,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_GPIO_DIRECTION:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_GPIO_DIRECTION:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -211,7 +211,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VC_MP_GPIO_DATA:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VC_MP_GPIO_DATA:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC;
 		cmd.reg_count = 1;
@@ -219,7 +219,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VC_MP_GPIO_DIRECTION:
 		cmd.buffer.block_data[0] = param;
-		/*fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VC_MP_GPIO_DIRECTION:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC;
 		cmd.reg_count = 1;
@@ -234,7 +234,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_FLICKER_MODES:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_FLICKER_MODES:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -281,7 +281,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_USER_MODE:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_USER_MODE:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -301,7 +301,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_WAKEUP:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_WAKEUP:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC;
 		cmd.reg_count = 1;
@@ -309,7 +309,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_PW_CONTROL:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_PW_CONTROL:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC;
 		cmd.reg_count = 1;
@@ -322,7 +322,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_SYSTEM_CTRL:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_SYSTEM_CTRL:
 		cmd.req_mode =
 		    CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_SYSTEM;
@@ -331,7 +331,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_SYSTEM_CTRL:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_SYSTEM_CTRL:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -339,7 +339,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VP_EXP_MODES:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VP_EXP_MODES:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -347,7 +347,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_DEVICE_CONFIG:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_DEVICE_CONFIG:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -368,7 +368,7 @@ int cpia2_do_command(struct camera_data *cam,
 		break;
 	case CPIA2_CMD_SET_VC_CONTROL:
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_VC_CONTROL:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VC;
 		cmd.reg_count = 1;
@@ -403,7 +403,7 @@ int cpia2_do_command(struct camera_data *cam,
 					     this register can also affect
 					     flicker modes */
 		cmd.buffer.block_data[0] = param;
-		/* fall through */
+		fallthrough;
 	case CPIA2_CMD_GET_USER_EFFECTS:
 		cmd.req_mode = CAMERAACCESS_TYPE_BLOCK | CAMERAACCESS_VP;
 		cmd.reg_count = 1;
@@ -1751,7 +1751,7 @@ int cpia2_set_fps(struct camera_data *cam, int framerate)
 						    CPIA2_VP_SENSOR_FLAGS_500) {
 				return -EINVAL;
 			}
-			/* Fall through */
+			fallthrough;
 		case CPIA2_VP_FRAMERATE_15:
 		case CPIA2_VP_FRAMERATE_12_5:
 		case CPIA2_VP_FRAMERATE_7_5:
diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c
index d9f953f2d088..425e470b0fd3 100644
--- a/drivers/media/usb/cx231xx/cx231xx-video.c
+++ b/drivers/media/usb/cx231xx/cx231xx-video.c
@@ -996,7 +996,7 @@ void cx231xx_v4l2_create_entities(struct cx231xx *dev)
 			/* The DVB core will handle it */
 			if (dev->tuner_type == TUNER_ABSENT)
 				continue;
-			/* fall through */
+			fallthrough;
 		default: /* just to shut up a gcc warning */
 			ent->function = MEDIA_ENT_F_CONN_RF;
 			break;
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index 4ef3fa98d20f..52e648e2713a 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -1659,14 +1659,14 @@ static int dib8096_set_param_override(struct dvb_frontend *fe)
 
 	switch (band) {
 	default:
-			deb_info("Warning : Rf frequency  (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency);
-			/* fall through */
+		deb_info("Warning : Rf frequency  (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency);
+		fallthrough;
 	case BAND_VHF:
-			state->dib8000_ops.set_gpio(fe, 3, 0, 1);
-			break;
+		state->dib8000_ops.set_gpio(fe, 3, 0, 1);
+		break;
 	case BAND_UHF:
-			state->dib8000_ops.set_gpio(fe, 3, 0, 0);
-			break;
+		state->dib8000_ops.set_gpio(fe, 3, 0, 0);
+		break;
 	}
 
 	ret = state->set_param_save(fe);
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index f96626fe2c0b..a27a68440325 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -1886,12 +1886,12 @@ static int dw2102_load_firmware(struct usb_device *dev,
 		switch (le16_to_cpu(dev->descriptor.idProduct)) {
 		case USB_PID_TEVII_S650:
 			dw2104_properties.rc.core.rc_codes = RC_MAP_TEVII_NEC;
-			/* fall through */
+			fallthrough;
 		case USB_PID_DW2104:
 			reset = 1;
 			dw210x_op_rw(dev, 0xc4, 0x0000, 0, &reset, 1,
 					DW210X_WRITE_MSG);
-			/* fall through */
+			fallthrough;
 		case USB_PID_DW3101:
 			reset = 0;
 			dw210x_op_rw(dev, 0xbf, 0x0040, 0, &reset, 0,
@@ -1924,7 +1924,7 @@ static int dw2102_load_firmware(struct usb_device *dev,
 					break;
 				}
 			}
-			/* fall through */
+			fallthrough;
 		case 0x2101:
 			dw210x_op_rw(dev, 0xbc, 0x0030, 0, &reset16[0], 2,
 					DW210X_READ_MSG);
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 3f3fbcd60cc6..45a2403aa039 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -2200,7 +2200,7 @@ static int check_range(enum v4l2_ctrl_type type,
 	case V4L2_CTRL_TYPE_BOOLEAN:
 		if (step != 1 || max > 1 || min < 0)
 			return -ERANGE;
-		/* fall through */
+		fallthrough;
 	case V4L2_CTRL_TYPE_U8:
 	case V4L2_CTRL_TYPE_U16:
 	case V4L2_CTRL_TYPE_U32:
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index a556880f225a..f74b42280892 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -782,7 +782,6 @@ static void v4l_print_frmsizeenum(const void *arg, bool write_only)
 				p->stepwise.step_height);
 		break;
 	case V4L2_FRMSIZE_TYPE_CONTINUOUS:
-		/* fall through */
 	default:
 		pr_cont("\n");
 		break;
@@ -816,7 +815,6 @@ static void v4l_print_frmivalenum(const void *arg, bool write_only)
 				p->stepwise.step.denominator);
 		break;
 	case V4L2_FRMIVAL_TYPE_CONTINUOUS:
-		/* fall through */
 	default:
 		pr_cont("\n");
 		break;
@@ -3189,14 +3187,16 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd)
 #ifdef CONFIG_COMPAT_32BIT_TIME
 	case VIDIOC_DQEVENT_TIME32: {
 		struct v4l2_event *ev = parg;
-		struct v4l2_event_time32 ev32 = {
-			.type		= ev->type,
-			.pending	= ev->pending,
-			.sequence	= ev->sequence,
-			.timestamp.tv_sec  = ev->timestamp.tv_sec,
-			.timestamp.tv_nsec = ev->timestamp.tv_nsec,
-			.id		= ev->id,
-		};
+		struct v4l2_event_time32 ev32;
+
+		memset(&ev32, 0, sizeof(ev32));
+
+		ev32.type	= ev->type;
+		ev32.pending	= ev->pending;
+		ev32.sequence	= ev->sequence;
+		ev32.timestamp.tv_sec	= ev->timestamp.tv_sec;
+		ev32.timestamp.tv_nsec	= ev->timestamp.tv_nsec;
+		ev32.id		= ev->id;
 
 		memcpy(&ev32.u, &ev->u, sizeof(ev->u));
 		memcpy(&ev32.reserved, &ev->reserved, sizeof(ev->reserved));
@@ -3210,21 +3210,23 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd)
 	case VIDIOC_DQBUF_TIME32:
 	case VIDIOC_PREPARE_BUF_TIME32: {
 		struct v4l2_buffer *vb = parg;
-		struct v4l2_buffer_time32 vb32 = {
-			.index		= vb->index,
-			.type		= vb->type,
-			.bytesused	= vb->bytesused,
-			.flags		= vb->flags,
-			.field		= vb->field,
-			.timestamp.tv_sec	= vb->timestamp.tv_sec,
-			.timestamp.tv_usec	= vb->timestamp.tv_usec,
-			.timecode	= vb->timecode,
-			.sequence	= vb->sequence,
-			.memory		= vb->memory,
-			.m.userptr	= vb->m.userptr,
-			.length		= vb->length,
-			.request_fd	= vb->request_fd,
-		};
+		struct v4l2_buffer_time32 vb32;
+
+		memset(&vb32, 0, sizeof(vb32));
+
+		vb32.index	= vb->index;
+		vb32.type	= vb->type;
+		vb32.bytesused	= vb->bytesused;
+		vb32.flags	= vb->flags;
+		vb32.field	= vb->field;
+		vb32.timestamp.tv_sec	= vb->timestamp.tv_sec;
+		vb32.timestamp.tv_usec	= vb->timestamp.tv_usec;
+		vb32.timecode	= vb->timecode;
+		vb32.sequence	= vb->sequence;
+		vb32.memory	= vb->memory;
+		vb32.m.userptr	= vb->m.userptr;
+		vb32.length	= vb->length;
+		vb32.request_fd	= vb->request_fd;
 
 		if (copy_to_user(arg, &vb32, sizeof(vb32)))
 			return -EFAULT;
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 5c91fc3e65b5..606a271bdd2d 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -354,7 +354,7 @@ static void videobuf_status(struct videobuf_queue *q, struct v4l2_buffer *b,
 		break;
 	case VIDEOBUF_ERROR:
 		b->flags |= V4L2_BUF_FLAG_ERROR;
-		/* fall through */
+		fallthrough;
 	case VIDEOBUF_DONE:
 		b->flags |= V4L2_BUF_FLAG_DONE;
 		break;
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index f512cbc7a36c..ca0097664b12 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -313,7 +313,6 @@ static unsigned long gpmc_get_clk_period(int cs, enum gpmc_clk_domain cd)
 		tick_ps *= div;
 		break;
 	case GPMC_CD_FCLK:
-		/* FALL-THROUGH */
 	default:
 		break;
 	}
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index d9ee8e3dc72d..178954228631 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -371,7 +371,7 @@ again:
 			serial mode), then just fall through */
 		if (msb_read_int_reg(msb, -1))
 			return 0;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_RP_RECEIVE_INT_REQ_RESULT:
 		intreg = mrq->data[0];
@@ -403,7 +403,7 @@ again:
 	case MSB_RP_RECEIVE_STATUS_REG:
 		msb->regs.status = *(struct ms_status_register *)mrq->data;
 		msb->state = MSB_RP_SEND_OOB_READ;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_RP_SEND_OOB_READ:
 		if (!msb_read_regs(msb,
@@ -418,7 +418,7 @@ again:
 		msb->regs.extra_data =
 			*(struct ms_extra_data_register *) mrq->data;
 		msb->state = MSB_RP_SEND_READ_DATA;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_RP_SEND_READ_DATA:
 		/* Skip that state if we only read the oob */
@@ -518,7 +518,7 @@ again:
 		msb->state = MSB_WB_RECEIVE_INT_REQ;
 		if (msb_read_int_reg(msb, -1))
 			return 0;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_WB_RECEIVE_INT_REQ:
 		intreg = mrq->data[0];
@@ -549,7 +549,7 @@ again:
 
 		msb->int_polling = false;
 		msb->state = MSB_WB_SEND_WRITE_DATA;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_WB_SEND_WRITE_DATA:
 		sg_init_table(sg, ARRAY_SIZE(sg));
@@ -628,7 +628,7 @@ again:
 		msb->state = MSB_SC_RECEIVE_INT_REQ;
 		if (msb_read_int_reg(msb, -1))
 			return 0;
-		/* fallthrough */
+		fallthrough;
 
 	case MSB_SC_RECEIVE_INT_REQ:
 		intreg = mrq->data[0];
diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index 4a6b866b0291..e83c3ada9389 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -255,11 +255,11 @@ static unsigned int jmb38x_ms_write_data(struct jmb38x_ms_host *host,
 	case 3:
 		host->io_word[0] |= buf[off + 2] << 16;
 		host->io_pos++;
-		/* fall through */
+		fallthrough;
 	case 2:
 		host->io_word[0] |= buf[off + 1] << 8;
 		host->io_pos++;
-		/* fall through */
+		fallthrough;
 	case 1:
 		host->io_word[0] |= buf[off];
 		host->io_pos++;
diff --git a/drivers/memstick/host/tifm_ms.c b/drivers/memstick/host/tifm_ms.c
index fc35c7404429..786e46798da2 100644
--- a/drivers/memstick/host/tifm_ms.c
+++ b/drivers/memstick/host/tifm_ms.c
@@ -162,11 +162,11 @@ static unsigned int tifm_ms_write_data(struct tifm_ms *host,
 	case 3:
 		host->io_word |= buf[off + 2] << 16;
 		host->io_pos++;
-		/* fall through */
+		fallthrough;
 	case 2:
 		host->io_word |= buf[off + 1] << 8;
 		host->io_pos++;
-		/* fall through */
+		fallthrough;
 	case 1:
 		host->io_word |= buf[off];
 		host->io_pos++;
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 5216487db4fb..9903e9660a38 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -642,7 +642,7 @@ mptbase_reply(MPT_ADAPTER *ioc, MPT_FRAME_HDR *req, MPT_FRAME_HDR *reply)
 			freereq = 0;
 		if (event != MPI_EVENT_EVENT_CHANGE)
 			break;
-		/* fall through */
+		fallthrough;
 	case MPI_FUNCTION_CONFIG:
 	case MPI_FUNCTION_SAS_IO_UNIT_CONTROL:
 		ioc->mptbase_cmds.status |= MPT_MGMT_STATUS_COMMAND_GOOD;
@@ -1887,7 +1887,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	case MPI_MANUFACTPAGE_DEVICEID_FC939X:
 	case MPI_MANUFACTPAGE_DEVICEID_FC949X:
 		ioc->errata_flag_1064 = 1;
-		/* fall through */
+		fallthrough;
 	case MPI_MANUFACTPAGE_DEVICEID_FC909:
 	case MPI_MANUFACTPAGE_DEVICEID_FC929:
 	case MPI_MANUFACTPAGE_DEVICEID_FC919:
@@ -1932,7 +1932,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 			pcixcmd &= 0x8F;
 			pci_write_config_byte(pdev, 0x6a, pcixcmd);
 		}
-		/* fall through */
+		fallthrough;
 
 	case MPI_MANUFACTPAGE_DEVID_1030_53C1035:
 		ioc->bus_type = SPI;
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 6a79cd0ebe2b..18b91ea1a353 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -4326,7 +4326,7 @@ mptsas_hotplug_work(MPT_ADAPTER *ioc, struct fw_event_work *fw_event,
 			}
 		}
 		mpt_findImVolumes(ioc);
-		/* fall through */
+		fallthrough;
 
 	case MPTSAS_ADD_DEVICE:
 		memset(&sas_device, 0, sizeof(struct mptsas_devinfo));
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index 1491561d2e5c..8543f0324d5a 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -784,7 +784,7 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr)
 			/*
 			 * Allow non-SAS & non-NEXUS_LOSS to drop into below code
 			 */
-			/* Fall through */
+			fallthrough;
 
 		case MPI_IOCSTATUS_SCSI_TASK_TERMINATED:	/* 0x0048 */
 			/* Linux handles an unsolicited DID_RESET better
@@ -881,7 +881,7 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr)
 
 		case MPI_IOCSTATUS_SCSI_DATA_OVERRUN:		/* 0x0044 */
 			scsi_set_resid(sc, 0);
-			/* Fall through */
+			fallthrough;
 		case MPI_IOCSTATUS_SCSI_RECOVERED_ERROR:	/* 0x0040 */
 		case MPI_IOCSTATUS_SUCCESS:			/* 0x0000 */
 			sc->result = (DID_OK << 16) | scsi_status;
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index a9d9c1cdf546..a5983d515db0 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -1515,10 +1515,10 @@ static unsigned long dsiclk_rate(u8 n)
 	switch (divsel) {
 	case PRCM_DSI_PLLOUT_SEL_PHI_4:
 		div *= 2;
-		/* Fall through */
+		fallthrough;
 	case PRCM_DSI_PLLOUT_SEL_PHI_2:
 		div *= 2;
-		/* Fall through */
+		fallthrough;
 	case PRCM_DSI_PLLOUT_SEL_PHI:
 		return pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK),
 			PLL_RAW) / div;
diff --git a/drivers/mfd/iqs62x.c b/drivers/mfd/iqs62x.c
index af764bc87d7c..761b4ef3a381 100644
--- a/drivers/mfd/iqs62x.c
+++ b/drivers/mfd/iqs62x.c
@@ -136,7 +136,7 @@ static int iqs62x_dev_init(struct iqs62x_core *iqs62x)
 		if (val & IQS620_PROX_SETTINGS_4_SAR_EN)
 			iqs62x->ui_sel = IQS62X_UI_SAR1;
 
-		/* fall through */
+		fallthrough;
 
 	case IQS621_PROD_NUM:
 		ret = regmap_write(iqs62x->regmap, IQS620_GLBL_EVENT_MASK,
@@ -470,7 +470,7 @@ static irqreturn_t iqs62x_irq(int irq, void *context)
 		case IQS62X_EVENT_UI_LO:
 			event_data.ui_data = get_unaligned_le16(&event_map[i]);
 
-			/* fall through */
+			fallthrough;
 
 		case IQS62X_EVENT_UI_HI:
 		case IQS62X_EVENT_NONE:
@@ -491,7 +491,7 @@ static irqreturn_t iqs62x_irq(int irq, void *context)
 		case IQS62X_EVENT_HYST:
 			event_map[i] <<= iqs62x->dev_desc->hyst_shift;
 
-			/* fall through */
+			fallthrough;
 
 		case IQS62X_EVENT_WHEEL:
 		case IQS62X_EVENT_HALL:
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index c3651f06684f..fc00aaccb5f7 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -126,10 +126,6 @@ static int mfd_match_of_node_to_dev(struct platform_device *pdev,
 	const __be32 *reg;
 	u64 of_node_addr;
 
-	/* Skip devices 'disabled' by Device Tree */
-	if (!of_device_is_available(np))
-		return -ENODEV;
-
 	/* Skip if OF node has previously been allocated to a device */
 	list_for_each_entry(of_entry, &mfd_of_node_list, list)
 		if (of_entry->np == np)
@@ -212,6 +208,12 @@ static int mfd_add_device(struct device *parent, int id,
 	if (IS_ENABLED(CONFIG_OF) && parent->of_node && cell->of_compatible) {
 		for_each_child_of_node(parent->of_node, np) {
 			if (of_device_is_compatible(np, cell->of_compatible)) {
+				/* Ignore 'disabled' devices error free */
+				if (!of_device_is_available(np)) {
+					ret = 0;
+					goto fail_alias;
+				}
+
 				ret = mfd_match_of_node_to_dev(pdev, np, cell);
 				if (ret == -EAGAIN)
 					continue;
@@ -370,8 +372,6 @@ static int mfd_remove_devices_fn(struct device *dev, void *data)
 	regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies,
 					       cell->num_parent_supplies);
 
-	kfree(cell);
-
 	platform_device_unregister(pdev);
 	return 0;
 }
diff --git a/drivers/mfd/mxs-lradc.c b/drivers/mfd/mxs-lradc.c
index 5bef142c4835..111d11fd25aa 100644
--- a/drivers/mfd/mxs-lradc.c
+++ b/drivers/mfd/mxs-lradc.c
@@ -172,7 +172,7 @@ static int mxs_lradc_probe(struct platform_device *pdev)
 					MXS_LRADC_TOUCHSCREEN_5WIRE;
 				break;
 			}
-			/* fall through - to an error message for i.MX23 */
+			fallthrough;	/* to an error message for i.MX23 */
 		default:
 			dev_err(&pdev->dev,
 				"Unsupported number of touchscreen wires (%d)\n"
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 1e6431cb8536..2a3a240b4619 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -308,7 +308,7 @@ static int usbhs_runtime_resume(struct device *dev)
 					 i, r);
 				}
 			}
-		/* Fall through - as HSIC mode needs utmi_clk */
+			fallthrough;	/* as HSIC mode needs utmi_clk */
 
 		case OMAP_EHCI_PORT_MODE_TLL:
 			if (!IS_ERR(omap->utmi_clk[i])) {
@@ -344,7 +344,7 @@ static int usbhs_runtime_suspend(struct device *dev)
 
 			if (!IS_ERR(omap->hsic480m_clk[i]))
 				clk_disable_unprepare(omap->hsic480m_clk[i]);
-		/* Fall through - as utmi_clks were used in HSIC mode */
+			fallthrough;	/* as utmi_clks were used in HSIC mode */
 
 		case OMAP_EHCI_PORT_MODE_TLL:
 			if (!IS_ERR(omap->utmi_clk[i]))
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index abaab541df19..545196c85b5c 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -270,7 +270,7 @@ static void *stuff(unsigned char *dest, const unsigned char *src, size_t n)
 		case RAVE_SP_ETX:
 		case RAVE_SP_DLE:
 			*dest++ = RAVE_SP_DLE;
-			/* FALLTHROUGH */
+			fallthrough;
 		default:
 			*dest++ = byte;
 		}
@@ -541,7 +541,7 @@ static int rave_sp_receive_buf(struct serdev_device *serdev,
 			 * deframer buffer
 			 */
 
-			/* FALLTHROUGH */
+			fallthrough;
 
 		case RAVE_SP_EXPECT_ESCAPED_DATA:
 			if (deframer->length == sizeof(deframer->data)) {
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index 75859e492984..df5cebb372a5 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -95,7 +95,7 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_clk)
 			break;
 		default:
 			pr_err("Failed to retrieve valid hwlock: %d\n", ret);
-			/* fall-through */
+			fallthrough;
 		case -EPROBE_DEFER:
 			goto err_regmap;
 		}
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 2591c21b2b5d..26a23abc053d 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -692,10 +692,6 @@ static int at24_probe(struct i2c_client *client)
 	nvmem_config.word_size = 1;
 	nvmem_config.size = byte_len;
 
-	at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
-	if (IS_ERR(at24->nvmem))
-		return PTR_ERR(at24->nvmem);
-
 	i2c_set_clientdata(client, at24);
 
 	err = regulator_enable(at24->vcc_reg);
@@ -708,6 +704,13 @@ static int at24_probe(struct i2c_client *client)
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
+	at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
+	if (IS_ERR(at24->nvmem)) {
+		pm_runtime_disable(dev);
+		regulator_disable(at24->vcc_reg);
+		return PTR_ERR(at24->nvmem);
+	}
+
 	/*
 	 * Perform a one-byte test read to verify that the
 	 * chip is functional.
diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c
index cde9a2fc1325..ed8d38b09925 100644
--- a/drivers/misc/eeprom/at25.c
+++ b/drivers/misc/eeprom/at25.c
@@ -90,10 +90,10 @@ static int at25_ee_read(void *priv, unsigned int offset,
 	switch (at25->addrlen) {
 	default:	/* case 3 */
 		*cp++ = offset >> 16;
-		/* fall through */
+		fallthrough;
 	case 2:
 		*cp++ = offset >> 8;
-		/* fall through */
+		fallthrough;
 	case 1:
 	case 0:	/* can't happen: for better codegen */
 		*cp++ = offset >> 0;
@@ -178,10 +178,10 @@ static int at25_ee_write(void *priv, unsigned int off, void *val, size_t count)
 		switch (at25->addrlen) {
 		default:	/* case 3 */
 			*cp++ = offset >> 16;
-			/* fall through */
+			fallthrough;
 		case 2:
 			*cp++ = offset >> 8;
-			/* fall through */
+			fallthrough;
 		case 1:
 		case 0:	/* can't happen: for better codegen */
 			*cp++ = offset >> 0;
@@ -278,7 +278,7 @@ static int at25_fw_to_chip(struct device *dev, struct spi_eeprom *chip)
 		switch (val) {
 		case 9:
 			chip->flags |= EE_INSTR_BIT3_IS_ADDR;
-			/* fall through */
+			fallthrough;
 		case 8:
 			chip->flags |= EE_ADDR1;
 			break;
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 7c38c4f7f9c0..a8004911c977 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -10,6 +10,7 @@
 
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <linux/genalloc.h>
 
 static void cb_fini(struct hl_device *hdev, struct hl_cb *cb)
@@ -300,7 +301,7 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 	struct hl_device *hdev = hpriv->hdev;
 	struct hl_cb *cb;
 	phys_addr_t address;
-	u32 handle;
+	u32 handle, user_cb_size;
 	int rc;
 
 	handle = vma->vm_pgoff;
@@ -314,7 +315,8 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 	}
 
 	/* Validation check */
-	if ((vma->vm_end - vma->vm_start) != ALIGN(cb->size, PAGE_SIZE)) {
+	user_cb_size = vma->vm_end - vma->vm_start;
+	if (user_cb_size != ALIGN(cb->size, PAGE_SIZE)) {
 		dev_err(hdev->dev,
 			"CB mmap failed, mmap size 0x%lx != 0x%x cb size\n",
 			vma->vm_end - vma->vm_start, cb->size);
@@ -322,6 +324,16 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 		goto put_cb;
 	}
 
+	if (!access_ok((void __user *) (uintptr_t) vma->vm_start,
+							user_cb_size)) {
+		dev_err(hdev->dev,
+			"user pointer is invalid - 0x%lx\n",
+			vma->vm_start);
+
+		rc = -EINVAL;
+		goto put_cb;
+	}
+
 	spin_lock(&cb->lock);
 
 	if (cb->mmap) {
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index b9840e368eb5..2e3fcbc794db 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -808,6 +808,14 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 
 	/* currently it is guaranteed to have only one chunk */
 	chunk = &cs_chunk_array[0];
+
+	if (chunk->queue_index >= hdev->asic_prop.max_queues) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n",
+			chunk->queue_index);
+		rc = -EINVAL;
+		goto free_cs_chunk_array;
+	}
+
 	q_idx = chunk->queue_index;
 	hw_queue_prop = &hdev->asic_prop.hw_queues_props[q_idx];
 	q_type = hw_queue_prop->type;
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index c50c6fc9e905..aa77771635d3 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -19,7 +19,7 @@
 static struct dentry *hl_debug_root;
 
 static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
-				u8 i2c_reg, u32 *val)
+				u8 i2c_reg, long *val)
 {
 	struct armcp_packet pkt;
 	int rc;
@@ -36,7 +36,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 	pkt.i2c_reg = i2c_reg;
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, (long *) val);
+						0, val);
 
 	if (rc)
 		dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc);
@@ -827,7 +827,7 @@ static ssize_t hl_i2c_data_read(struct file *f, char __user *buf,
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
 	char tmp_buf[32];
-	u32 val;
+	long val;
 	ssize_t rc;
 
 	if (*ppos)
@@ -842,7 +842,7 @@ static ssize_t hl_i2c_data_read(struct file *f, char __user *buf,
 		return rc;
 	}
 
-	sprintf(tmp_buf, "0x%02x\n", val);
+	sprintf(tmp_buf, "0x%02lx\n", val);
 	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
 			strlen(tmp_buf));
 
@@ -982,7 +982,7 @@ static ssize_t hl_clk_gate_read(struct file *f, char __user *buf,
 		return 0;
 
 	sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask);
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
+	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
 			strlen(tmp_buf) + 1);
 
 	return rc;
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index be16b75bdfdb..24b01cce0a38 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -288,7 +288,7 @@ static int device_early_init(struct hl_device *hdev)
 	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) {
 		snprintf(workq_name, 32, "hl-free-jobs-%u", i);
 		hdev->cq_wq[i] = create_singlethread_workqueue(workq_name);
-		if (hdev->cq_wq == NULL) {
+		if (hdev->cq_wq[i] == NULL) {
 			dev_err(hdev->dev, "Failed to allocate CQ workqueue\n");
 			rc = -ENOMEM;
 			goto free_cq_wq;
@@ -1069,7 +1069,7 @@ again:
 			goto out_err;
 		}
 
-		hl_set_max_power(hdev, hdev->max_power);
+		hl_set_max_power(hdev);
 	} else {
 		rc = hdev->asic_funcs->soft_reset_late_init(hdev);
 		if (rc) {
@@ -1318,6 +1318,11 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 		goto out_disabled;
 	}
 
+	/* Need to call this again because the max power might change,
+	 * depending on card type for certain ASICs
+	 */
+	hl_set_max_power(hdev);
+
 	/*
 	 * hl_hwmon_init() must be called after device_late_init(), because only
 	 * there we get the information from the device about which
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index f70302cdab1b..f52bc690dfc5 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -13,6 +13,7 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/slab.h>
 
+#define FW_FILE_MAX_SIZE	0x1400000 /* maximum size of 20MB */
 /**
  * hl_fw_load_fw_to_device() - Load F/W code to device's memory.
  *
@@ -48,6 +49,14 @@ int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,
 
 	dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size);
 
+	if (fw_size > FW_FILE_MAX_SIZE) {
+		dev_err(hdev->dev,
+			"FW file size %zu exceeds maximum of %u bytes\n",
+			fw_size, FW_FILE_MAX_SIZE);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	fw_data = (const u64 *) fw->data;
 
 	memcpy_toio(dst, fw_data, fw_size);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 018d9d67e8e6..edbd627b29d2 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1462,6 +1462,8 @@ struct hl_device_idle_busy_ts {
  *                     details.
  * @in_reset: is device in reset flow.
  * @curr_pll_profile: current PLL profile.
+ * @card_type: Various ASICs have several card types. This indicates the card
+ *             type of the current device.
  * @cs_active_cnt: number of active command submissions on this device (active
  *                 means already in H/W queues)
  * @major: habanalabs kernel driver major.
@@ -1566,6 +1568,7 @@ struct hl_device {
 	u64				clock_gating_mask;
 	atomic_t			in_reset;
 	enum hl_pll_frequency		curr_pll_profile;
+	enum armcp_card_types		card_type;
 	int				cs_active_cnt;
 	u32				major;
 	u32				high_pll;
@@ -1651,7 +1654,7 @@ struct hl_ioctl_desc {
  *
  * Return: true if the area is inside the valid range, false otherwise.
  */
-static inline bool hl_mem_area_inside_range(u64 address, u32 size,
+static inline bool hl_mem_area_inside_range(u64 address, u64 size,
 				u64 range_start_address, u64 range_end_address)
 {
 	u64 end_address = address + size;
@@ -1858,7 +1861,7 @@ int hl_get_pwm_info(struct hl_device *hdev,
 void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
 			long value);
 u64 hl_get_max_power(struct hl_device *hdev);
-void hl_set_max_power(struct hl_device *hdev, u64 value);
+void hl_set_max_power(struct hl_device *hdev);
 int hl_set_voltage(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev,
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
index dce9273e557a..5ff4688683fd 100644
--- a/drivers/misc/habanalabs/common/memory.c
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -66,6 +66,11 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	num_pgs = (args->alloc.mem_size + (page_size - 1)) >> page_shift;
 	total_size = num_pgs << page_shift;
 
+	if (!total_size) {
+		dev_err(hdev->dev, "Cannot allocate 0 bytes\n");
+		return -EINVAL;
+	}
+
 	contiguous = args->flags & HL_MEM_CONTIGUOUS;
 
 	if (contiguous) {
@@ -93,7 +98,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	phys_pg_pack->contiguous = contiguous;
 
 	phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL);
-	if (!phys_pg_pack->pages) {
+	if (ZERO_OR_NULL_PTR(phys_pg_pack->pages)) {
 		rc = -ENOMEM;
 		goto pages_arr_err;
 	}
@@ -683,7 +688,7 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 
 	phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64),
 						GFP_KERNEL);
-	if (!phys_pg_pack->pages) {
+	if (ZERO_OR_NULL_PTR(phys_pg_pack->pages)) {
 		rc = -ENOMEM;
 		goto page_pack_arr_mem_err;
 	}
diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c
index edcc11d5eaf1..3fc0f497fab3 100644
--- a/drivers/misc/habanalabs/common/mmu.c
+++ b/drivers/misc/habanalabs/common/mmu.c
@@ -450,7 +450,7 @@ int hl_mmu_init(struct hl_device *hdev)
 	hdev->mmu_shadow_hop0 = kvmalloc_array(prop->max_asid,
 					prop->mmu_hop_table_size,
 					GFP_KERNEL | __GFP_ZERO);
-	if (!hdev->mmu_shadow_hop0) {
+	if (ZERO_OR_NULL_PTR(hdev->mmu_shadow_hop0)) {
 		rc = -ENOMEM;
 		goto err_pool_add;
 	}
diff --git a/drivers/misc/habanalabs/common/pci.c b/drivers/misc/habanalabs/common/pci.c
index 7bd3737571f3..2770f03b6cbb 100644
--- a/drivers/misc/habanalabs/common/pci.c
+++ b/drivers/misc/habanalabs/common/pci.c
@@ -227,7 +227,7 @@ int hl_pci_set_inbound_region(struct hl_device *hdev, u8 region,
 	}
 
 	/* Point to the specified address */
-	rc = hl_pci_iatu_write(hdev, offset + 0x14,
+	rc |= hl_pci_iatu_write(hdev, offset + 0x14,
 			lower_32_bits(pci_region->addr));
 	rc |= hl_pci_iatu_write(hdev, offset + 0x18,
 			upper_32_bits(pci_region->addr));
@@ -369,15 +369,17 @@ int hl_pci_init(struct hl_device *hdev)
 	rc = hdev->asic_funcs->init_iatu(hdev);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to initialize iATU\n");
-		goto disable_device;
+		goto unmap_pci_bars;
 	}
 
 	rc = hl_pci_set_dma_mask(hdev);
 	if (rc)
-		goto disable_device;
+		goto unmap_pci_bars;
 
 	return 0;
 
+unmap_pci_bars:
+	hl_pci_bars_unmap(hdev);
 disable_device:
 	pci_clear_master(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index b3cb0ac4721c..5ae484cc84cd 100644
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -81,7 +81,7 @@ u64 hl_get_max_power(struct hl_device *hdev)
 	return result;
 }
 
-void hl_set_max_power(struct hl_device *hdev, u64 value)
+void hl_set_max_power(struct hl_device *hdev)
 {
 	struct armcp_packet pkt;
 	int rc;
@@ -90,7 +90,7 @@ void hl_set_max_power(struct hl_device *hdev, u64 value)
 
 	pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_SET <<
 				ARMCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.value = cpu_to_le64(value);
+	pkt.value = cpu_to_le64(hdev->max_power);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, NULL);
@@ -316,7 +316,7 @@ static ssize_t max_power_store(struct device *dev,
 	}
 
 	hdev->max_power = value;
-	hl_set_max_power(hdev, value);
+	hl_set_max_power(hdev);
 
 out:
 	return count;
@@ -422,6 +422,7 @@ int hl_sysfs_init(struct hl_device *hdev)
 		hdev->pm_mng_profile = PM_AUTO;
 	else
 		hdev->pm_mng_profile = PM_MANUAL;
+
 	hdev->max_power = hdev->asic_prop.max_power_default;
 
 	hdev->asic_funcs->add_device_attr(hdev, &hl_dev_clks_attr_group);
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 00a0a7238d81..4009b7df4caf 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -154,6 +154,29 @@ static const u16 gaudi_packet_sizes[MAX_PACKET_ID] = {
 	[PACKET_LOAD_AND_EXE]	= sizeof(struct packet_load_and_exe)
 };
 
+static inline bool validate_packet_id(enum packet_id id)
+{
+	switch (id) {
+	case PACKET_WREG_32:
+	case PACKET_WREG_BULK:
+	case PACKET_MSG_LONG:
+	case PACKET_MSG_SHORT:
+	case PACKET_CP_DMA:
+	case PACKET_REPEAT:
+	case PACKET_MSG_PROT:
+	case PACKET_FENCE:
+	case PACKET_LIN_DMA:
+	case PACKET_NOP:
+	case PACKET_STOP:
+	case PACKET_ARB_POINT:
+	case PACKET_WAIT:
+	case PACKET_LOAD_AND_EXE:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const char * const
 gaudi_tpc_interrupts_cause[GAUDI_NUM_OF_TPC_INTR_CAUSE] = {
 	"tpc_address_exceed_slm",
@@ -433,7 +456,7 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev)
 	prop->num_of_events = GAUDI_EVENT_SIZE;
 	prop->tpc_enabled_mask = TPC_ENABLED_MASK;
 
-	prop->max_power_default = MAX_POWER_DEFAULT;
+	prop->max_power_default = MAX_POWER_DEFAULT_PCI;
 
 	prop->cb_pool_cb_cnt = GAUDI_CB_POOL_CB_CNT;
 	prop->cb_pool_cb_size = GAUDI_CB_POOL_CB_SIZE;
@@ -2485,6 +2508,7 @@ static void gaudi_set_clock_gating(struct hl_device *hdev)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 qman_offset;
+	bool enable;
 	int i;
 
 	/* In case we are during debug session, don't enable the clock gate
@@ -2494,46 +2518,43 @@ static void gaudi_set_clock_gating(struct hl_device *hdev)
 		return;
 
 	for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) {
-		if (!(hdev->clock_gating_mask &
-					(BIT_ULL(gaudi_dma_assignment[i]))))
-			continue;
+		enable = !!(hdev->clock_gating_mask &
+				(BIT_ULL(gaudi_dma_assignment[i])));
 
 		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
-		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN);
+		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset,
+				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
 		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
-				QMAN_UPPER_CP_CGM_PWR_GATE_EN);
+				enable ? QMAN_UPPER_CP_CGM_PWR_GATE_EN : 0);
 	}
 
 	for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) {
-		if (!(hdev->clock_gating_mask &
-					(BIT_ULL(gaudi_dma_assignment[i]))))
-			continue;
+		enable = !!(hdev->clock_gating_mask &
+				(BIT_ULL(gaudi_dma_assignment[i])));
 
 		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
-		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN);
+		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset,
+				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
 		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
-				QMAN_COMMON_CP_CGM_PWR_GATE_EN);
+				enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
 	}
 
-	if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) {
-		WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
-		WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN);
-	}
+	enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0)));
+	WREG32(mmMME0_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0);
+	WREG32(mmMME0_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
 
-	if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) {
-		WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
-		WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN);
-	}
+	enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2)));
+	WREG32(mmMME2_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0);
+	WREG32(mmMME2_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
 
 	for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) {
-		if (!(hdev->clock_gating_mask &
-					(BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i))))
-			continue;
+		enable = !!(hdev->clock_gating_mask &
+				(BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)));
 
 		WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset,
-				QMAN_CGM1_PWR_GATE_EN);
+				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
 		WREG32(mmTPC0_QM_CGM_CFG + qman_offset,
-				QMAN_COMMON_CP_CGM_PWR_GATE_EN);
+				enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
 
 		qman_offset += TPC_QMAN_OFFSET;
 	}
@@ -3772,6 +3793,12 @@ static int gaudi_validate_cb(struct hl_device *hdev,
 				PACKET_HEADER_PACKET_ID_MASK) >>
 					PACKET_HEADER_PACKET_ID_SHIFT);
 
+		if (!validate_packet_id(pkt_id)) {
+			dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id);
+			rc = -EINVAL;
+			break;
+		}
+
 		pkt_size = gaudi_packet_sizes[pkt_id];
 		cb_parsed_length += pkt_size;
 		if (cb_parsed_length > parser->user_cb_size) {
@@ -3995,6 +4022,12 @@ static int gaudi_patch_cb(struct hl_device *hdev,
 				PACKET_HEADER_PACKET_ID_MASK) >>
 					PACKET_HEADER_PACKET_ID_SHIFT);
 
+		if (!validate_packet_id(pkt_id)) {
+			dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id);
+			rc = -EINVAL;
+			break;
+		}
+
 		pkt_size = gaudi_packet_sizes[pkt_id];
 		cb_parsed_length += pkt_size;
 		if (cb_parsed_length > parser->user_cb_size) {
@@ -5215,7 +5248,7 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev,
 	*memory_wrapper_idx = 0xFF;
 
 	/* Iterate through memory wrappers, a single bit must be set */
-	for (i = 0 ; i > num_mem_regs ; i++) {
+	for (i = 0 ; i < num_mem_regs ; i++) {
 		err_addr += i * 4;
 		err_word = RREG32(err_addr);
 		if (err_word) {
@@ -6022,6 +6055,15 @@ static int gaudi_armcp_info_get(struct hl_device *hdev)
 		strncpy(prop->armcp_info.card_name, GAUDI_DEFAULT_CARD_NAME,
 				CARD_NAME_MAX_LEN);
 
+	hdev->card_type = le32_to_cpu(hdev->asic_prop.armcp_info.card_type);
+
+	if (hdev->card_type == armcp_card_type_pci)
+		prop->max_power_default = MAX_POWER_DEFAULT_PCI;
+	else if (hdev->card_type == armcp_card_type_pmc)
+		prop->max_power_default = MAX_POWER_DEFAULT_PMC;
+
+	hdev->max_power = prop->max_power_default;
+
 	return 0;
 }
 
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 5dc99f6f0296..82137c3f3e2e 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -41,7 +41,8 @@
 
 #define GAUDI_MAX_CLK_FREQ		2200000000ull	/* 2200 MHz */
 
-#define MAX_POWER_DEFAULT		200000		/* 200W */
+#define MAX_POWER_DEFAULT_PCI		200000		/* 200W */
+#define MAX_POWER_DEFAULT_PMC		350000		/* 350W */
 
 #define GAUDI_CPU_TIMEOUT_USEC		15000000	/* 15s */
 
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index 5673ee49819e..881531d4d9da 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -527,7 +527,7 @@ static int gaudi_config_etf(struct hl_device *hdev,
 }
 
 static bool gaudi_etr_validate_address(struct hl_device *hdev, u64 addr,
-					u32 size, bool *is_host)
+					u64 size, bool *is_host)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct gaudi_device *gaudi = hdev->asic_specific;
@@ -539,6 +539,12 @@ static bool gaudi_etr_validate_address(struct hl_device *hdev, u64 addr,
 		return false;
 	}
 
+	if (addr > (addr + size)) {
+		dev_err(hdev->dev,
+			"ETR buffer size %llu overflow\n", size);
+		return false;
+	}
+
 	/* PMMU and HPMMU addresses are equal, check only one of them */
 	if ((gaudi->hw_cap_initialized & HW_CAP_MMU) &&
 		hl_mem_area_inside_range(addr, size,
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 85030759b2af..33cd2ae653d2 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -139,6 +139,25 @@ static u16 goya_packet_sizes[MAX_PACKET_ID] = {
 	[PACKET_STOP]		= sizeof(struct packet_stop)
 };
 
+static inline bool validate_packet_id(enum packet_id id)
+{
+	switch (id) {
+	case PACKET_WREG_32:
+	case PACKET_WREG_BULK:
+	case PACKET_MSG_LONG:
+	case PACKET_MSG_SHORT:
+	case PACKET_CP_DMA:
+	case PACKET_MSG_PROT:
+	case PACKET_FENCE:
+	case PACKET_LIN_DMA:
+	case PACKET_NOP:
+	case PACKET_STOP:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static u64 goya_mmu_regs[GOYA_MMU_REGS_NUM] = {
 	mmDMA_QM_0_GLBL_NON_SECURE_PROPS,
 	mmDMA_QM_1_GLBL_NON_SECURE_PROPS,
@@ -3455,6 +3474,12 @@ static int goya_validate_cb(struct hl_device *hdev,
 				PACKET_HEADER_PACKET_ID_MASK) >>
 					PACKET_HEADER_PACKET_ID_SHIFT);
 
+		if (!validate_packet_id(pkt_id)) {
+			dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id);
+			rc = -EINVAL;
+			break;
+		}
+
 		pkt_size = goya_packet_sizes[pkt_id];
 		cb_parsed_length += pkt_size;
 		if (cb_parsed_length > parser->user_cb_size) {
@@ -3690,6 +3715,12 @@ static int goya_patch_cb(struct hl_device *hdev,
 				PACKET_HEADER_PACKET_ID_MASK) >>
 					PACKET_HEADER_PACKET_ID_SHIFT);
 
+		if (!validate_packet_id(pkt_id)) {
+			dev_err(hdev->dev, "Invalid packet id %u\n", pkt_id);
+			rc = -EINVAL;
+			break;
+		}
+
 		pkt_size = goya_packet_sizes[pkt_id];
 		cb_parsed_length += pkt_size;
 		if (cb_parsed_length > parser->user_cb_size) {
diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c
index b03912483de0..4027a6a334d7 100644
--- a/drivers/misc/habanalabs/goya/goya_coresight.c
+++ b/drivers/misc/habanalabs/goya/goya_coresight.c
@@ -362,11 +362,17 @@ static int goya_config_etf(struct hl_device *hdev,
 }
 
 static int goya_etr_validate_address(struct hl_device *hdev, u64 addr,
-		u32 size)
+		u64 size)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u64 range_start, range_end;
 
+	if (addr > (addr + size)) {
+		dev_err(hdev->dev,
+			"ETR buffer size %llu overflow\n", size);
+		return false;
+	}
+
 	if (hdev->mmu_enable) {
 		range_start = prop->dmmu.start_addr;
 		range_end = prop->dmmu.end_addr;
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index 13ef6b2887fd..3510c42d24e3 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -378,15 +378,15 @@ enum axi_id {
 	((((y) & RAZWI_INITIATOR_Y_MASK) << RAZWI_INITIATOR_Y_SHIFT) | \
 		(((x) & RAZWI_INITIATOR_X_MASK) << RAZWI_INITIATOR_X_SHIFT))
 
-#define RAZWI_INITIATOR_ID_X_Y_TPC0_NIC0	RAZWI_INITIATOR_ID_X_Y(1, 0)
-#define RAZWI_INITIATOR_ID_X_Y_TPC1		RAZWI_INITIATOR_ID_X_Y(2, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME0_0		RAZWI_INITIATOR_ID_X_Y(3, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME0_1		RAZWI_INITIATOR_ID_X_Y(4, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME1_0		RAZWI_INITIATOR_ID_X_Y(5, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME1_1		RAZWI_INITIATOR_ID_X_Y(6, 0)
-#define RAZWI_INITIATOR_ID_X_Y_TPC2		RAZWI_INITIATOR_ID_X_Y(7, 0)
+#define RAZWI_INITIATOR_ID_X_Y_TPC0_NIC0	RAZWI_INITIATOR_ID_X_Y(1, 1)
+#define RAZWI_INITIATOR_ID_X_Y_TPC1		RAZWI_INITIATOR_ID_X_Y(2, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME0_0		RAZWI_INITIATOR_ID_X_Y(3, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME0_1		RAZWI_INITIATOR_ID_X_Y(4, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME1_0		RAZWI_INITIATOR_ID_X_Y(5, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME1_1		RAZWI_INITIATOR_ID_X_Y(6, 1)
+#define RAZWI_INITIATOR_ID_X_Y_TPC2		RAZWI_INITIATOR_ID_X_Y(7, 1)
 #define RAZWI_INITIATOR_ID_X_Y_TPC3_PCI_CPU_PSOC \
-						RAZWI_INITIATOR_ID_X_Y(8, 0)
+						RAZWI_INITIATOR_ID_X_Y(8, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_0	RAZWI_INITIATOR_ID_X_Y(0, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_S_0	RAZWI_INITIATOR_ID_X_Y(9, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_1	RAZWI_INITIATOR_ID_X_Y(0, 2)
@@ -395,14 +395,14 @@ enum axi_id {
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_0	RAZWI_INITIATOR_ID_X_Y(9, 3)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_N_1	RAZWI_INITIATOR_ID_X_Y(0, 4)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_1	RAZWI_INITIATOR_ID_X_Y(9, 4)
-#define RAZWI_INITIATOR_ID_X_Y_TPC4_NIC1_NIC2	RAZWI_INITIATOR_ID_X_Y(1, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC5		RAZWI_INITIATOR_ID_X_Y(2, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME2_0		RAZWI_INITIATOR_ID_X_Y(3, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME2_1		RAZWI_INITIATOR_ID_X_Y(4, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME3_0		RAZWI_INITIATOR_ID_X_Y(5, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME3_1		RAZWI_INITIATOR_ID_X_Y(6, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC6		RAZWI_INITIATOR_ID_X_Y(7, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC7_NIC4_NIC5	RAZWI_INITIATOR_ID_X_Y(8, 5)
+#define RAZWI_INITIATOR_ID_X_Y_TPC4_NIC1_NIC2	RAZWI_INITIATOR_ID_X_Y(1, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC5		RAZWI_INITIATOR_ID_X_Y(2, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME2_0		RAZWI_INITIATOR_ID_X_Y(3, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME2_1		RAZWI_INITIATOR_ID_X_Y(4, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME3_0		RAZWI_INITIATOR_ID_X_Y(5, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME3_1		RAZWI_INITIATOR_ID_X_Y(6, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC6		RAZWI_INITIATOR_ID_X_Y(7, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC7_NIC4_NIC5	RAZWI_INITIATOR_ID_X_Y(8, 6)
 
 #define PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT                           1
 
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c
index d1d3e025ca0e..9ae9669e46ea 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.c
+++ b/drivers/misc/mei/hdcp/mei_hdcp.c
@@ -546,38 +546,46 @@ static int mei_hdcp_verify_mprime(struct device *dev,
 				  struct hdcp_port_data *data,
 				  struct hdcp2_rep_stream_ready *stream_ready)
 {
-	struct wired_cmd_repeater_auth_stream_req_in
-					verify_mprime_in = { { 0 } };
+	struct wired_cmd_repeater_auth_stream_req_in *verify_mprime_in;
 	struct wired_cmd_repeater_auth_stream_req_out
 					verify_mprime_out = { { 0 } };
 	struct mei_cl_device *cldev;
 	ssize_t byte;
+	size_t cmd_size;
 
 	if (!dev || !stream_ready || !data)
 		return -EINVAL;
 
 	cldev = to_mei_cl_device(dev);
 
-	verify_mprime_in.header.api_version = HDCP_API_VERSION;
-	verify_mprime_in.header.command_id = WIRED_REPEATER_AUTH_STREAM_REQ;
-	verify_mprime_in.header.status = ME_HDCP_STATUS_SUCCESS;
-	verify_mprime_in.header.buffer_len =
+	cmd_size = struct_size(verify_mprime_in, streams, data->k);
+	if (cmd_size == SIZE_MAX)
+		return -EINVAL;
+
+	verify_mprime_in = kzalloc(cmd_size, GFP_KERNEL);
+	if (!verify_mprime_in)
+		return -ENOMEM;
+
+	verify_mprime_in->header.api_version = HDCP_API_VERSION;
+	verify_mprime_in->header.command_id = WIRED_REPEATER_AUTH_STREAM_REQ;
+	verify_mprime_in->header.status = ME_HDCP_STATUS_SUCCESS;
+	verify_mprime_in->header.buffer_len =
 			WIRED_CMD_BUF_LEN_REPEATER_AUTH_STREAM_REQ_MIN_IN;
 
-	verify_mprime_in.port.integrated_port_type = data->port_type;
-	verify_mprime_in.port.physical_port = (u8)data->fw_ddi;
-	verify_mprime_in.port.attached_transcoder = (u8)data->fw_tc;
+	verify_mprime_in->port.integrated_port_type = data->port_type;
+	verify_mprime_in->port.physical_port = (u8)data->fw_ddi;
+	verify_mprime_in->port.attached_transcoder = (u8)data->fw_tc;
+
+	memcpy(verify_mprime_in->m_prime, stream_ready->m_prime, HDCP_2_2_MPRIME_LEN);
+	drm_hdcp_cpu_to_be24(verify_mprime_in->seq_num_m, data->seq_num_m);
 
-	memcpy(verify_mprime_in.m_prime, stream_ready->m_prime,
-	       HDCP_2_2_MPRIME_LEN);
-	drm_hdcp_cpu_to_be24(verify_mprime_in.seq_num_m, data->seq_num_m);
-	memcpy(verify_mprime_in.streams, data->streams,
+	memcpy(verify_mprime_in->streams, data->streams,
 	       array_size(data->k, sizeof(*data->streams)));
 
-	verify_mprime_in.k = cpu_to_be16(data->k);
+	verify_mprime_in->k = cpu_to_be16(data->k);
 
-	byte = mei_cldev_send(cldev, (u8 *)&verify_mprime_in,
-			      sizeof(verify_mprime_in));
+	byte = mei_cldev_send(cldev, (u8 *)verify_mprime_in, cmd_size);
+	kfree(verify_mprime_in);
 	if (byte < 0) {
 		dev_dbg(dev, "mei_cldev_send failed. %zd\n", byte);
 		return byte;
diff --git a/drivers/misc/mic/scif/scif_api.c b/drivers/misc/mic/scif/scif_api.c
index 9cc6b2a6cf22..304d6c833712 100644
--- a/drivers/misc/mic/scif/scif_api.c
+++ b/drivers/misc/mic/scif/scif_api.c
@@ -178,7 +178,7 @@ int scif_close(scif_epd_t epd)
 	case SCIFEP_ZOMBIE:
 		dev_err(scif_info.mdev.this_device,
 			"SCIFAPI close: zombie state unexpected\n");
-		/* fall through */
+		fallthrough;
 	case SCIFEP_DISCONNECTED:
 		spin_unlock(&ep->lock);
 		scif_unregister_all_windows(epd);
@@ -645,7 +645,7 @@ int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block)
 		ep->port.port = err;
 		ep->port.node = scif_info.nodeid;
 		ep->conn_async_state = ASYNC_CONN_IDLE;
-		/* Fall through */
+		fallthrough;
 	case SCIFEP_BOUND:
 		/*
 		 * If a non-blocking connect has been already initiated
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index de8f61efaef5..2da3b474f486 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -657,7 +657,7 @@ int scif_unregister_window(struct scif_window *window)
 		window->unreg_state = OP_IN_PROGRESS;
 		send_msg = true;
 	}
-		/* fall through */
+		fallthrough;
 	case OP_IN_PROGRESS:
 	{
 		scif_get_window(window, 1);
diff --git a/drivers/misc/sgi-gru/grukservices.c b/drivers/misc/sgi-gru/grukservices.c
index f6e600bfac5d..0ea923fe6371 100644
--- a/drivers/misc/sgi-gru/grukservices.c
+++ b/drivers/misc/sgi-gru/grukservices.c
@@ -622,7 +622,7 @@ static int send_noop_message(void *cb, struct gru_message_queue_desc *mqd,
 			break;
 		case CBSS_PAGE_OVERFLOW:
 			STAT(mesq_noop_page_overflow);
-			/* fall through */
+			fallthrough;
 		default:
 			BUG();
 		}
@@ -780,7 +780,7 @@ static int send_message_failure(void *cb, struct gru_message_queue_desc *mqd,
 		break;
 	case CBSS_PAGE_OVERFLOW:
 		STAT(mesq_page_overflow);
-		/* fall through */
+		fallthrough;
 	default:
 		BUG();
 	}
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index d5e097cd556d..8a495dc82f16 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -1173,7 +1173,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *_die_args)
 		if (!xpc_kdebug_ignore)
 			break;
 
-		/* fall through */
+		fallthrough;
 	case DIE_MCA_MONARCH_ENTER:
 	case DIE_INIT_MONARCH_ENTER:
 		xpc_arch_ops.offline_heartbeat();
@@ -1184,7 +1184,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *_die_args)
 		if (!xpc_kdebug_ignore)
 			break;
 
-		/* fall through */
+		fallthrough;
 	case DIE_MCA_MONARCH_LEAVE:
 	case DIE_INIT_MONARCH_LEAVE:
 		xpc_arch_ops.online_heartbeat();
diff --git a/drivers/misc/sgi-xp/xpc_partition.c b/drivers/misc/sgi-xp/xpc_partition.c
index 21a04bc97d40..099a53bdbb7d 100644
--- a/drivers/misc/sgi-xp/xpc_partition.c
+++ b/drivers/misc/sgi-xp/xpc_partition.c
@@ -441,10 +441,10 @@ xpc_discovery(void)
 		switch (region_size) {
 		case 128:
 			max_regions *= 2;
-			/* fall through */
+			fallthrough;
 		case 64:
 			max_regions *= 2;
-			/* fall through */
+			fallthrough;
 		case 32:
 			max_regions *= 2;
 			region_size = 16;
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 98c60f11b76b..7791bde81a36 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -574,7 +574,7 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part,
 
 		xpc_wakeup_channel_mgr(part);
 	}
-		/* fall through */
+		fallthrough;
 	case XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV:
 		spin_lock_irqsave(&part_uv->flags_lock, irq_flags);
 		part_uv->flags |= XPC_P_ENGAGED_UV;
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index ce43f7573d80..c8fae6611b73 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -191,7 +191,7 @@ int mmc_of_parse(struct mmc_host *host)
 	switch (bus_width) {
 	case 8:
 		host->caps |= MMC_CAP_8_BIT_DATA;
-		/* fall through - Hosts capable of 8-bit can also do 4 bits */
+		fallthrough;	/* Hosts capable of 8-bit can also do 4 bits */
 	case 4:
 		host->caps |= MMC_CAP_4_BIT_DATA;
 		break;
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index 93d346c01110..4c229dd2b6e5 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -121,6 +121,7 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	struct sg_table sgtable;
 	unsigned int nents, left_size, i;
 	unsigned int seg_size = card->host->max_seg_size;
+	int err;
 
 	WARN_ON(blksz == 0);
 
@@ -170,28 +171,32 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 
 	mmc_set_data_timeout(&data, card);
 
-	mmc_wait_for_req(card->host, &mrq);
+	mmc_pre_req(card->host, &mrq);
 
-	if (nents > 1)
-		sg_free_table(&sgtable);
+	mmc_wait_for_req(card->host, &mrq);
 
 	if (cmd.error)
-		return cmd.error;
-	if (data.error)
-		return data.error;
-
-	if (mmc_host_is_spi(card->host)) {
+		err = cmd.error;
+	else if (data.error)
+		err = data.error;
+	else if (mmc_host_is_spi(card->host))
 		/* host driver already reported errors */
-	} else {
-		if (cmd.resp[0] & R5_ERROR)
-			return -EIO;
-		if (cmd.resp[0] & R5_FUNCTION_NUMBER)
-			return -EINVAL;
-		if (cmd.resp[0] & R5_OUT_OF_RANGE)
-			return -ERANGE;
-	}
+		err = 0;
+	else if (cmd.resp[0] & R5_ERROR)
+		err = -EIO;
+	else if (cmd.resp[0] & R5_FUNCTION_NUMBER)
+		err = -EINVAL;
+	else if (cmd.resp[0] & R5_OUT_OF_RANGE)
+		err = -ERANGE;
+	else
+		err = 0;
 
-	return 0;
+	mmc_post_req(card->host, &mrq, err);
+
+	if (nents > 1)
+		sg_free_table(&sgtable);
+
+	return err;
 }
 
 int sdio_reset(struct mmc_host *host)
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 9c89a5b780e8..9a34c827c96e 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -602,7 +602,7 @@ config MMC_GOLDFISH
 
 config MMC_SPI
 	tristate "MMC/SD/SDIO over SPI"
-	depends on SPI_MASTER && HAS_DMA
+	depends on SPI_MASTER
 	select CRC7
 	select CRC_ITU_T
 	help
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 300901415aa2..3fc3bbea8536 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -2418,7 +2418,7 @@ static void atmci_get_cap(struct atmel_mci *host)
 	case 0x600:
 	case 0x500:
 		host->caps.has_odd_clk_div = 1;
-		/* Fall through */
+		fallthrough;
 	case 0x400:
 	case 0x300:
 		host->caps.has_dma_conf_reg = 1;
@@ -2426,16 +2426,16 @@ static void atmci_get_cap(struct atmel_mci *host)
 		host->caps.has_cfg_reg = 1;
 		host->caps.has_cstor_reg = 1;
 		host->caps.has_highspeed = 1;
-		/* Fall through */
+		fallthrough;
 	case 0x200:
 		host->caps.has_rwproof = 1;
 		host->caps.need_blksz_mul_4 = 0;
 		host->caps.need_notbusy_for_read_ops = 1;
-		/* Fall through */
+		fallthrough;
 	case 0x100:
 		host->caps.has_bad_data_ordering = 0;
 		host->caps.need_reset_after_xfer = 0;
-		/* Fall through */
+		fallthrough;
 	case 0x0:
 		break;
 	default:
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index f01fecd75833..e50a08bce7ef 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -300,7 +300,7 @@ static void mmc_davinci_start_command(struct mmc_davinci_host *host,
 		 * then it's harmless for us to allow it.
 		 */
 		cmd_reg |= MMCCMD_BSYEXP;
-		/* FALLTHROUGH */
+		fallthrough;
 	case MMC_RSP_R1:		/* 48 bits, CRC */
 		cmd_reg |= MMCCMD_RSPFMT_R1456;
 		break;
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 50977ff18074..db1a84b2ba61 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -238,7 +238,7 @@ static void dw_mci_hs_set_timing(struct dw_mci *host, int timing,
 		if (smpl_phase >= USE_DLY_MIN_SMPL &&
 				smpl_phase <= USE_DLY_MAX_SMPL)
 			use_smpl_dly = 1;
-			/* fallthrough */
+		fallthrough;
 	case MMC_TIMING_UHS_SDR50:
 		if (smpl_phase >= ENABLE_SHIFT_MIN_SMPL &&
 				smpl_phase <= ENABLE_SHIFT_MAX_SMPL)
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 35ae5737c622..0fba940544ca 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2030,7 +2030,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			}
 
 			prev_state = state = STATE_SENDING_DATA;
-			/* fall through */
+			fallthrough;
 
 		case STATE_SENDING_DATA:
 			/*
@@ -2088,7 +2088,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			}
 			prev_state = state = STATE_DATA_BUSY;
 
-			/* fall through */
+			fallthrough;
 
 		case STATE_DATA_BUSY:
 			if (!dw_mci_clear_pending_data_complete(host)) {
@@ -2141,7 +2141,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			 */
 			prev_state = state = STATE_SENDING_STOP;
 
-			/* fall through */
+			fallthrough;
 
 		case STATE_SENDING_STOP:
 			if (!dw_mci_clear_pending_cmd_complete(host))
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index 447552ac25c4..81d71010b474 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -739,7 +739,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 			break;
 
 		jz_mmc_prepare_data_transfer(host);
-		/* fall through */
+		fallthrough;
 
 	case JZ4740_MMC_STATE_TRANSFER_DATA:
 		if (host->use_dma) {
@@ -774,7 +774,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 			break;
 		}
 		jz4740_mmc_write_irq_reg(host, JZ_MMC_IRQ_DATA_TRAN_DONE);
-		/* fall through */
+		fallthrough;
 
 	case JZ4740_MMC_STATE_SEND_STOP:
 		if (!req->stop)
diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c
index 9b2cf7afc246..703d5834f9a5 100644
--- a/drivers/mmc/host/meson-mx-sdio.c
+++ b/drivers/mmc/host/meson-mx-sdio.c
@@ -294,7 +294,7 @@ static void meson_mx_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
 		vdd = 0;
-		/* fall through */
+		fallthrough;
 	case MMC_POWER_UP:
 		if (!IS_ERR(mmc->supply.vmmc)) {
 			host->error = mmc_regulator_set_ocr(mmc,
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 39bb1e30c2d7..5055a7eb134a 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1278,6 +1278,52 @@ mmc_spi_detect_irq(int irq, void *mmc)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_HAS_DMA
+static int mmc_spi_dma_alloc(struct mmc_spi_host *host)
+{
+	struct spi_device *spi = host->spi;
+	struct device *dev;
+
+	if (!spi->master->dev.parent->dma_mask)
+		return 0;
+
+	dev = spi->master->dev.parent;
+
+	host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE,
+					DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, host->ones_dma))
+		return -ENOMEM;
+
+	host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data),
+					DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, host->data_dma)) {
+		dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
+				 DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data),
+				DMA_BIDIRECTIONAL);
+
+	host->dma_dev = dev;
+	return 0;
+}
+
+static void mmc_spi_dma_free(struct mmc_spi_host *host)
+{
+	if (!host->dma_dev)
+		return;
+
+	dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
+			 DMA_TO_DEVICE);
+	dma_unmap_single(host->dma_dev, host->data_dma,	sizeof(*host->data),
+			 DMA_BIDIRECTIONAL);
+}
+#else
+static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
+static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {}
+#endif
+
 static int mmc_spi_probe(struct spi_device *spi)
 {
 	void			*ones;
@@ -1374,23 +1420,9 @@ static int mmc_spi_probe(struct spi_device *spi)
 	if (!host->data)
 		goto fail_nobuf1;
 
-	if (spi->master->dev.parent->dma_mask) {
-		struct device	*dev = spi->master->dev.parent;
-
-		host->dma_dev = dev;
-		host->ones_dma = dma_map_single(dev, ones,
-				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, host->ones_dma))
-			goto fail_ones_dma;
-		host->data_dma = dma_map_single(dev, host->data,
-				sizeof(*host->data), DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(dev, host->data_dma))
-			goto fail_data_dma;
-
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-	}
+	status = mmc_spi_dma_alloc(host);
+	if (status)
+		goto fail_dma;
 
 	/* setup message for status/busy readback */
 	spi_message_init(&host->readback);
@@ -1458,20 +1490,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 fail_add_host:
 	mmc_remove_host(mmc);
 fail_glue_init:
-	if (host->dma_dev)
-		dma_unmap_single(host->dma_dev, host->data_dma,
-				sizeof(*host->data), DMA_BIDIRECTIONAL);
-fail_data_dma:
-	if (host->dma_dev)
-		dma_unmap_single(host->dma_dev, host->ones_dma,
-				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-fail_ones_dma:
+	mmc_spi_dma_free(host);
+fail_dma:
 	kfree(host->data);
-
 fail_nobuf1:
 	mmc_free_host(mmc);
 	mmc_spi_put_pdata(spi);
-
 nomem:
 	kfree(ones);
 	return status;
@@ -1489,13 +1513,7 @@ static int mmc_spi_remove(struct spi_device *spi)
 
 	mmc_remove_host(mmc);
 
-	if (host->dma_dev) {
-		dma_unmap_single(host->dma_dev, host->ones_dma,
-			MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-		dma_unmap_single(host->dma_dev, host->data_dma,
-			sizeof(*host->data), DMA_BIDIRECTIONAL);
-	}
-
+	mmc_spi_dma_free(host);
 	kfree(host->data);
 	kfree(host->ones);
 
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 4e2583f69a63..b0c27944db7f 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/reset.h>
 
 #include <linux/mmc/card.h>
 #include <linux/mmc/core.h>
@@ -419,6 +420,7 @@ struct msdc_host {
 	struct pinctrl_state *pins_uhs;
 	struct delayed_work req_timeout;
 	int irq;		/* host interrupt */
+	struct reset_control *reset;
 
 	struct clk *src_clk;	/* msdc source clock */
 	struct clk *h_clk;      /* msdc h_clk */
@@ -1592,6 +1594,12 @@ static void msdc_init_hw(struct msdc_host *host)
 	u32 val;
 	u32 tune_reg = host->dev_comp->pad_tune_reg;
 
+	if (host->reset) {
+		reset_control_assert(host->reset);
+		usleep_range(10, 50);
+		reset_control_deassert(host->reset);
+	}
+
 	/* Configure to MMC/SD mode, clock free running */
 	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_MODE | MSDC_CFG_CKPDN);
 
@@ -2390,6 +2398,11 @@ static int msdc_drv_probe(struct platform_device *pdev)
 	if (IS_ERR(host->src_clk_cg))
 		host->src_clk_cg = NULL;
 
+	host->reset = devm_reset_control_get_optional_exclusive(&pdev->dev,
+								"hrst");
+	if (IS_ERR(host->reset))
+		return PTR_ERR(host->reset);
+
 	host->irq = platform_get_irq(pdev, 0);
 	if (host->irq < 0) {
 		ret = -EINVAL;
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 15e21894bd44..904f5237d8f7 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -685,7 +685,7 @@ static int renesas_sdhi_write16_hook(struct tmio_mmc_host *host, int addr)
 	case HOST_MODE:
 		if (host->pdata->flags & TMIO_MMC_HAVE_CBSY)
 			bit = TMIO_STAT_CMD_BUSY;
-		/* fallthrough */
+		fallthrough;
 	case CTL_SD_CARD_CLK_CTL:
 		return renesas_sdhi_wait_idle(host, bit);
 	}
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 48ecbd0b180d..284cba11e279 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -535,6 +535,11 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_qcom_sd = {
 	.caps    = MMC_CAP_NONREMOVABLE,
 };
 
+struct amd_sdhci_host {
+	bool	tuned_clock;
+	bool	dll_enabled;
+};
+
 /* AMD sdhci reset dll register. */
 #define SDHCI_AMD_RESET_DLL_REGISTER    0x908
 
@@ -546,39 +551,96 @@ static int amd_select_drive_strength(struct mmc_card *card,
 	return MMC_SET_DRIVER_TYPE_A;
 }
 
-static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host)
+static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host, bool enable)
 {
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
+
 	/* AMD Platform requires dll setting */
 	sdhci_writel(host, 0x40003210, SDHCI_AMD_RESET_DLL_REGISTER);
 	usleep_range(10, 20);
-	sdhci_writel(host, 0x40033210, SDHCI_AMD_RESET_DLL_REGISTER);
+	if (enable)
+		sdhci_writel(host, 0x40033210, SDHCI_AMD_RESET_DLL_REGISTER);
+
+	amd_host->dll_enabled = enable;
 }
 
 /*
- * For AMD Platform it is required to disable the tuning
- * bit first controller to bring to HS Mode from HS200
- * mode, later enable to tune to HS400 mode.
+ * The initialization sequence for HS400 is:
+ *     HS->HS200->Perform Tuning->HS->HS400
+ *
+ * The re-tuning sequence is:
+ *     HS400->DDR52->HS->HS200->Perform Tuning->HS->HS400
+ *
+ * The AMD eMMC Controller can only use the tuned clock while in HS200 and HS400
+ * mode. If we switch to a different mode, we need to disable the tuned clock.
+ * If we have previously performed tuning and switch back to HS200 or
+ * HS400, we can re-enable the tuned clock.
+ *
  */
 static void amd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
 	unsigned int old_timing = host->timing;
+	u16 val;
 
 	sdhci_set_ios(mmc, ios);
-	if (old_timing == MMC_TIMING_MMC_HS200 &&
-	    ios->timing == MMC_TIMING_MMC_HS)
-		sdhci_writew(host, 0x9, SDHCI_HOST_CONTROL2);
-	if (old_timing != MMC_TIMING_MMC_HS400 &&
-	    ios->timing == MMC_TIMING_MMC_HS400) {
-		sdhci_writew(host, 0x80, SDHCI_HOST_CONTROL2);
-		sdhci_acpi_amd_hs400_dll(host);
+
+	if (old_timing != host->timing && amd_host->tuned_clock) {
+		if (host->timing == MMC_TIMING_MMC_HS400 ||
+		    host->timing == MMC_TIMING_MMC_HS200) {
+			val = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+			val |= SDHCI_CTRL_TUNED_CLK;
+			sdhci_writew(host, val, SDHCI_HOST_CONTROL2);
+		} else {
+			val = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+			val &= ~SDHCI_CTRL_TUNED_CLK;
+			sdhci_writew(host, val, SDHCI_HOST_CONTROL2);
+		}
+
+		/* DLL is only required for HS400 */
+		if (host->timing == MMC_TIMING_MMC_HS400 &&
+		    !amd_host->dll_enabled)
+			sdhci_acpi_amd_hs400_dll(host, true);
+	}
+}
+
+static int amd_sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	int err;
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
+
+	amd_host->tuned_clock = false;
+
+	err = sdhci_execute_tuning(mmc, opcode);
+
+	if (!err && !host->tuning_err)
+		amd_host->tuned_clock = true;
+
+	return err;
+}
+
+static void amd_sdhci_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
+
+	if (mask & SDHCI_RESET_ALL) {
+		amd_host->tuned_clock = false;
+		sdhci_acpi_amd_hs400_dll(host, false);
 	}
+
+	sdhci_reset(host, mask);
 }
 
 static const struct sdhci_ops sdhci_acpi_ops_amd = {
 	.set_clock	= sdhci_set_clock,
 	.set_bus_width	= sdhci_set_bus_width,
-	.reset		= sdhci_reset,
+	.reset		= amd_sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
@@ -602,6 +664,7 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev,
 
 	host->mmc_host_ops.select_drive_strength = amd_select_drive_strength;
 	host->mmc_host_ops.set_ios = amd_set_ios;
+	host->mmc_host_ops.execute_tuning = amd_sdhci_execute_tuning;
 	return 0;
 }
 
@@ -613,6 +676,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = {
 			  SDHCI_QUIRK_32BIT_ADMA_SIZE,
 	.quirks2	= SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
 	.probe_slot     = sdhci_acpi_emmc_amd_probe_slot,
+	.priv_size	= sizeof(struct amd_sdhci_host),
 };
 
 struct sdhci_acpi_uid_slot {
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index a76b4513fbec..d738907a622f 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1556,7 +1556,7 @@ static int sdhci_esdhc_imx_probe_nondt(struct platform_device *pdev,
 				"failed to request card-detect gpio!\n");
 			return err;
 		}
-		/* fall through */
+		fallthrough;
 
 	case ESDHC_CD_CONTROLLER:
 		/* we have a working card_detect back */
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 5a33389037cd..729868abd2db 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -1166,7 +1166,7 @@ static void sdhci_msm_set_cdr(struct sdhci_host *host, bool enable)
 static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
-	int tuning_seq_cnt = 3;
+	int tuning_seq_cnt = 10;
 	u8 phase, tuned_phases[16], tuned_phase_cnt = 0;
 	int rc;
 	struct mmc_ios ios = host->mmc->ios;
@@ -1222,6 +1222,22 @@ retry:
 	} while (++phase < ARRAY_SIZE(tuned_phases));
 
 	if (tuned_phase_cnt) {
+		if (tuned_phase_cnt == ARRAY_SIZE(tuned_phases)) {
+			/*
+			 * All phases valid is _almost_ as bad as no phases
+			 * valid.  Probably all phases are not really reliable
+			 * but we didn't detect where the unreliable place is.
+			 * That means we'll essentially be guessing and hoping
+			 * we get a good phase.  Better to try a few times.
+			 */
+			dev_dbg(mmc_dev(mmc), "%s: All phases valid; try again\n",
+				mmc_hostname(mmc));
+			if (--tuning_seq_cnt) {
+				tuned_phase_cnt = 0;
+				goto retry;
+			}
+		}
+
 		rc = msm_find_most_appropriate_phase(host, tuned_phases,
 						     tuned_phase_cnt);
 		if (rc < 0)
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 7c73d243dc6c..45881b309956 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -81,6 +81,7 @@ struct sdhci_esdhc {
 	bool quirk_tuning_erratum_type2;
 	bool quirk_ignore_data_inhibit;
 	bool quirk_delay_before_data_reset;
+	bool quirk_trans_complete_erratum;
 	bool in_sw_tuning;
 	unsigned int peripheral_clock;
 	const struct esdhc_clk_fixup *clk_fixup;
@@ -1177,10 +1178,11 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host,
 
 static u32 esdhc_irq(struct sdhci_host *host, u32 intmask)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 	u32 command;
 
-	if (of_find_compatible_node(NULL, NULL,
-				"fsl,p2020-esdhc")) {
+	if (esdhc->quirk_trans_complete_erratum) {
 		command = SDHCI_GET_CMD(sdhci_readw(host,
 					SDHCI_COMMAND));
 		if (command == MMC_WRITE_MULTIPLE_BLOCK &&
@@ -1334,8 +1336,10 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
 		esdhc->clk_fixup = match->data;
 	np = pdev->dev.of_node;
 
-	if (of_device_is_compatible(np, "fsl,p2020-esdhc"))
+	if (of_device_is_compatible(np, "fsl,p2020-esdhc")) {
 		esdhc->quirk_delay_before_data_reset = true;
+		esdhc->quirk_trans_complete_erratum = true;
+	}
 
 	clk = of_clk_get(np, 0);
 	if (!IS_ERR(clk)) {
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index bb6802448b2f..af413805bbf1 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -232,6 +232,14 @@ static void sdhci_pci_dumpregs(struct mmc_host *mmc)
 	sdhci_dumpregs(mmc_priv(mmc));
 }
 
+static void sdhci_cqhci_reset(struct sdhci_host *host, u8 mask)
+{
+	if ((host->mmc->caps2 & MMC_CAP2_CQE) && (mask & SDHCI_RESET_ALL) &&
+	    host->mmc->cqe_private)
+		cqhci_deactivate(host->mmc);
+	sdhci_reset(host, mask);
+}
+
 /*****************************************************************************\
  *                                                                           *
  * Hardware specific quirk handling                                          *
@@ -718,7 +726,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = {
 	.set_power		= sdhci_intel_set_power,
 	.enable_dma		= sdhci_pci_enable_dma,
 	.set_bus_width		= sdhci_set_bus_width,
-	.reset			= sdhci_reset,
+	.reset			= sdhci_cqhci_reset,
 	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
 	.irq			= sdhci_cqhci_irq,
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 9194bb73e601..080ced1e63f0 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -609,7 +609,7 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	switch (pdata->max_width) {
 	case 8:
 		host->mmc->caps |= MMC_CAP_8_BIT_DATA;
-		/* Fall through */
+		fallthrough;
 	case 4:
 		host->mmc->caps |= MMC_CAP_4_BIT_DATA;
 		break;
diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c
index a910cb461ed7..bafa2e41c8b6 100644
--- a/drivers/mmc/host/sdhci-sprd.c
+++ b/drivers/mmc/host/sdhci-sprd.c
@@ -470,7 +470,7 @@ static int sdhci_sprd_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios)
 		break;
 
 	default:
-		/* fall-through */
+		fallthrough;
 	case MMC_SIGNAL_VOLTAGE_330:
 		ret = pinctrl_select_state(sprd_host->pinctrl,
 					   sprd_host->pins_default);
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 0a3f9d024f2a..13fbf70b5fde 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -110,6 +110,12 @@
 #define NVQUIRK_DIS_CARD_CLK_CONFIG_TAP			BIT(8)
 #define NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING		BIT(9)
 
+/*
+ * NVQUIRK_HAS_TMCLK is for SoC's having separate timeout clock for Tegra
+ * SDMMC hardware data timeout.
+ */
+#define NVQUIRK_HAS_TMCLK				BIT(10)
+
 /* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */
 #define SDHCI_TEGRA_CQE_BASE_ADDR			0xF000
 
@@ -140,6 +146,7 @@ struct sdhci_tegra_autocal_offsets {
 struct sdhci_tegra {
 	const struct sdhci_tegra_soc_data *soc_data;
 	struct gpio_desc *power_gpio;
+	struct clk *tmclk;
 	bool ddr_signaling;
 	bool pad_calib_required;
 	bool pad_control_available;
@@ -1418,7 +1425,6 @@ static const struct sdhci_ops tegra210_sdhci_ops = {
 
 static const struct sdhci_pltfm_data sdhci_tegra210_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
-		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
@@ -1434,7 +1440,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra210 = {
 		    NVQUIRK_HAS_PADCALIB |
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |
 		    NVQUIRK_ENABLE_SDR50 |
-		    NVQUIRK_ENABLE_SDR104,
+		    NVQUIRK_ENABLE_SDR104 |
+		    NVQUIRK_HAS_TMCLK,
 	.min_tap_delay = 106,
 	.max_tap_delay = 185,
 };
@@ -1456,7 +1463,6 @@ static const struct sdhci_ops tegra186_sdhci_ops = {
 
 static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
-		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
@@ -1473,6 +1479,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra186 = {
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |
 		    NVQUIRK_ENABLE_SDR50 |
 		    NVQUIRK_ENABLE_SDR104 |
+		    NVQUIRK_HAS_TMCLK |
 		    NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING,
 	.min_tap_delay = 84,
 	.max_tap_delay = 136,
@@ -1485,7 +1492,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra194 = {
 		    NVQUIRK_HAS_PADCALIB |
 		    NVQUIRK_DIS_CARD_CLK_CONFIG_TAP |
 		    NVQUIRK_ENABLE_SDR50 |
-		    NVQUIRK_ENABLE_SDR104,
+		    NVQUIRK_ENABLE_SDR104 |
+		    NVQUIRK_HAS_TMCLK,
 	.min_tap_delay = 96,
 	.max_tap_delay = 139,
 };
@@ -1613,6 +1621,43 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 		goto err_power_req;
 	}
 
+	/*
+	 * Tegra210 has a separate SDMMC_LEGACY_TM clock used for host
+	 * timeout clock and SW can choose TMCLK or SDCLK for hardware
+	 * data timeout through the bit USE_TMCLK_FOR_DATA_TIMEOUT of
+	 * the register SDHCI_TEGRA_VENDOR_SYS_SW_CTRL.
+	 *
+	 * USE_TMCLK_FOR_DATA_TIMEOUT bit default is set to 1 and SDMMC uses
+	 * 12Mhz TMCLK which is advertised in host capability register.
+	 * With TMCLK of 12Mhz provides maximum data timeout period that can
+	 * be achieved is 11s better than using SDCLK for data timeout.
+	 *
+	 * So, TMCLK is set to 12Mhz and kept enabled all the time on SoC's
+	 * supporting separate TMCLK.
+	 */
+
+	if (soc_data->nvquirks & NVQUIRK_HAS_TMCLK) {
+		clk = devm_clk_get(&pdev->dev, "tmclk");
+		if (IS_ERR(clk)) {
+			rc = PTR_ERR(clk);
+			if (rc == -EPROBE_DEFER)
+				goto err_power_req;
+
+			dev_warn(&pdev->dev, "failed to get tmclk: %d\n", rc);
+			clk = NULL;
+		}
+
+		clk_set_rate(clk, 12000000);
+		rc = clk_prepare_enable(clk);
+		if (rc) {
+			dev_err(&pdev->dev,
+				"failed to enable tmclk: %d\n", rc);
+			goto err_power_req;
+		}
+
+		tegra_host->tmclk = clk;
+	}
+
 	clk = devm_clk_get(mmc_dev(host->mmc), NULL);
 	if (IS_ERR(clk)) {
 		rc = PTR_ERR(clk);
@@ -1656,6 +1701,7 @@ err_add_host:
 err_rst_get:
 	clk_disable_unprepare(pltfm_host->clk);
 err_clk_get:
+	clk_disable_unprepare(tegra_host->tmclk);
 err_power_req:
 err_parse_dt:
 	sdhci_pltfm_free(pdev);
@@ -1673,6 +1719,7 @@ static int sdhci_tegra_remove(struct platform_device *pdev)
 	reset_control_assert(tegra_host->rst);
 	usleep_range(2000, 4000);
 	clk_disable_unprepare(pltfm_host->clk);
+	clk_disable_unprepare(tegra_host->tmclk);
 
 	sdhci_pltfm_free(pdev);
 
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index e6e9e286cc34..03ce57ef4585 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -527,7 +527,7 @@ static bool xenon_emmc_phy_slow_mode(struct sdhci_host *host,
 			ret = true;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		reg &= ~XENON_TIMING_ADJUST_SLOW_MODE;
 		ret = false;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 3ad394b40eb1..592a55a34b58 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2825,7 +2825,7 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	case MMC_TIMING_UHS_SDR50:
 		if (host->flags & SDHCI_SDR50_NEEDS_TUNING)
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 
 	default:
 		goto out;
diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c
index 5987656e0474..fd8b72d3e02c 100644
--- a/drivers/mmc/host/tifm_sd.c
+++ b/drivers/mmc/host/tifm_sd.c
@@ -335,7 +335,7 @@ static unsigned int tifm_sd_op_flags(struct mmc_command *cmd)
 		break;
 	case MMC_RSP_R1B:
 		rc |= TIFM_MMCSD_RSP_BUSY;
-		/* fall-through */
+		fallthrough;
 	case MMC_RSP_R1:
 		rc |= TIFM_MMCSD_RSP_R1;
 		break;
diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c
index 369b8dee2e3d..7666c90054ae 100644
--- a/drivers/mmc/host/usdhi6rol0.c
+++ b/drivers/mmc/host/usdhi6rol0.c
@@ -1343,7 +1343,7 @@ static int usdhi6_stop_cmd(struct usdhi6_host *host)
 			host->wait = USDHI6_WAIT_FOR_STOP;
 			return 0;
 		}
-		/* fall through - Unsupported STOP command. */
+		fallthrough;	/* Unsupported STOP command */
 	default:
 		dev_err(mmc_dev(host->mmc),
 			"unsupported stop CMD%d for CMD%d\n",
@@ -1691,7 +1691,7 @@ static void usdhi6_timeout_work(struct work_struct *work)
 	switch (host->wait) {
 	default:
 		dev_err(mmc_dev(host->mmc), "Invalid state %u\n", host->wait);
-		/* fall through - mrq can be NULL, but is impossible. */
+		fallthrough;	/* mrq can be NULL, but is impossible */
 	case USDHI6_WAIT_FOR_CMD:
 		usdhi6_error_code(host);
 		if (mrq)
@@ -1713,7 +1713,7 @@ static void usdhi6_timeout_work(struct work_struct *work)
 			host->offset, data->blocks, data->blksz, data->sg_len,
 			sg_dma_len(sg), sg->offset);
 		usdhi6_sg_unmap(host, true);
-		/* fall through - page unmapped in USDHI6_WAIT_FOR_DATA_END. */
+		fallthrough;	/* page unmapped in USDHI6_WAIT_FOR_DATA_END */
 	case USDHI6_WAIT_FOR_DATA_END:
 		usdhi6_error_code(host);
 		data->error = -ETIMEDOUT;
diff --git a/drivers/mux/adgs1408.c b/drivers/mux/adgs1408.c
index 12466b06692c..22ed051eb1a4 100644
--- a/drivers/mux/adgs1408.c
+++ b/drivers/mux/adgs1408.c
@@ -93,7 +93,7 @@ static int adgs1408_probe(struct spi_device *spi)
 			mux->idle_state = idle_state;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		dev_err(dev, "invalid idle-state %d\n", idle_state);
 		return -EINVAL;
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index 18428e104445..1c6c27f35ac4 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -301,7 +301,7 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr)
 			dev->irq = cops_irq(ioaddr, board);
 			if (dev->irq)
 				break;
-			/* fall through - Once no IRQ found on this port. */
+			fallthrough;	/* Once no IRQ found on this port */
 		case 1:
 			retval = -EINVAL;
 			goto err_out;
diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c
index 14a5fb378145..98df38fe553c 100644
--- a/drivers/net/arcnet/arc-rimi.c
+++ b/drivers/net/arcnet/arc-rimi.c
@@ -363,13 +363,13 @@ static int __init arcrimi_setup(char *s)
 	switch (ints[0]) {
 	default:		/* ERROR */
 		pr_err("Too many arguments\n");
-		/* Fall through */
+		fallthrough;
 	case 3:		/* Node ID */
 		node = ints[3];
-		/* Fall through */
+		fallthrough;
 	case 2:		/* IRQ */
 		irq = ints[2];
-		/* Fall through */
+		fallthrough;
 	case 1:		/* IO address */
 		io = ints[1];
 	}
diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c
index cd27fdc1059b..f983c4ce6b07 100644
--- a/drivers/net/arcnet/com20020-isa.c
+++ b/drivers/net/arcnet/com20020-isa.c
@@ -197,22 +197,22 @@ static int __init com20020isa_setup(char *s)
 	switch (ints[0]) {
 	default:		/* ERROR */
 		pr_info("Too many arguments\n");
-		/* Fall through */
+		fallthrough;
 	case 6:		/* Timeout */
 		timeout = ints[6];
-		/* Fall through */
+		fallthrough;
 	case 5:		/* CKP value */
 		clockp = ints[5];
-		/* Fall through */
+		fallthrough;
 	case 4:		/* Backplane flag */
 		backplane = ints[4];
-		/* Fall through */
+		fallthrough;
 	case 3:		/* Node ID */
 		node = ints[3];
-		/* Fall through */
+		fallthrough;
 	case 2:		/* IRQ */
 		irq = ints[2];
-		/* Fall through */
+		fallthrough;
 	case 1:		/* IO address */
 		io = ints[1];
 	}
diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c
index 186bbf87bc84..cf214b730671 100644
--- a/drivers/net/arcnet/com90io.c
+++ b/drivers/net/arcnet/com90io.c
@@ -363,10 +363,10 @@ static int __init com90io_setup(char *s)
 	switch (ints[0]) {
 	default:		/* ERROR */
 		pr_err("Too many arguments\n");
-		/* Fall through */
+		fallthrough;
 	case 2:		/* IRQ */
 		irq = ints[2];
-		/* Fall through */
+		fallthrough;
 	case 1:		/* IO address */
 		io = ints[1];
 	}
diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c
index bd75d06ad7df..3dc3d533cb19 100644
--- a/drivers/net/arcnet/com90xx.c
+++ b/drivers/net/arcnet/com90xx.c
@@ -693,13 +693,13 @@ static int __init com90xx_setup(char *s)
 	switch (ints[0]) {
 	default:		/* ERROR */
 		pr_err("Too many arguments\n");
-		/* Fall through */
+		fallthrough;
 	case 3:		/* Mem address */
 		shmem = ints[3];
-		/* Fall through */
+		fallthrough;
 	case 2:		/* IRQ */
 		irq = ints[2];
-		/* Fall through */
+		fallthrough;
 	case 1:		/* IO address */
 		io = ints[1];
 	}
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 31e43a2197a3..aa001b16765a 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -130,7 +130,7 @@ static inline struct bonding *__get_bond_by_port(struct port *port)
 
 /**
  * __get_first_agg - get the first aggregator in the bond
- * @bond: the bond we're looking at
+ * @port: the port we're looking at
  *
  * Return the aggregator of the first slave in @bond, or %NULL if it can't be
  * found.
@@ -1149,7 +1149,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			port->actor_oper_port_state &= ~LACP_STATE_EXPIRED;
 			port->sm_rx_state = AD_RX_PORT_DISABLED;
 
-			/* Fall Through */
+			fallthrough;
 		case AD_RX_PORT_DISABLED:
 			port->sm_vars &= ~AD_PORT_MATCHED;
 			break;
@@ -1588,7 +1588,7 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best,
 		if (__agg_active_ports(curr) < __agg_active_ports(best))
 			return best;
 
-		/*FALLTHROUGH*/
+		fallthrough;
 	case BOND_AD_STABLE:
 	case BOND_AD_BANDWIDTH:
 		if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best))
@@ -1626,7 +1626,7 @@ static int agg_device_up(const struct aggregator *agg)
 
 /**
  * ad_agg_selection_logic - select an aggregation group for a team
- * @aggregator: the aggregator we're looking at
+ * @agg: the aggregator we're looking at
  * @update_slave_arr: Does slave array need update?
  *
  * It is assumed that only one aggregator may be selected for a team.
@@ -1810,7 +1810,7 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 
 /**
  * ad_initialize_port - initialize a given port's parameters
- * @aggregator: the aggregator we're looking at
+ * @port: the port we're looking at
  * @lacp_fast: boolean. whether fast periodic should be used
  */
 static void ad_initialize_port(struct port *port, int lacp_fast)
@@ -1967,6 +1967,7 @@ static void ad_marker_response_received(struct bond_marker *marker,
 /**
  * bond_3ad_initiate_agg_selection - initate aggregator selection
  * @bond: bonding struct
+ * @timeout: timeout value to set
  *
  * Set the aggregation selection timer, to initiate an agg selection in
  * the very near future.  Called during first initialization, and during
@@ -2259,7 +2260,7 @@ void bond_3ad_update_ad_actor_settings(struct bonding *bond)
 
 /**
  * bond_3ad_state_machine_handler - handle state machines timeout
- * @bond: bonding struct to work on
+ * @work: work context to fetch bonding struct to work on from
  *
  * The state machine handling concept in this module is to check every tick
  * which state machine should operate any function. The execution order is
@@ -2500,7 +2501,7 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
 /**
  * bond_3ad_handle_link_change - handle a slave's link status change indication
  * @slave: slave struct to work on
- * @status: whether the link is now up or down
+ * @link: whether the link is now up or down
  *
  * Handle reselection of aggregator (if needed) for this port.
  */
@@ -2551,7 +2552,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 
 /**
  * bond_3ad_set_carrier - set link state for bonding master
- * @bond - bonding structure
+ * @bond: bonding structure
  *
  * if we have an active aggregator, we're up, if not, we're down.
  * Presumes that we cannot have an active aggregator if there are
@@ -2664,7 +2665,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 
 /**
  * bond_3ad_update_lacp_rate - change the lacp rate
- * @bond - bonding struct
+ * @bond: bonding struct
  *
  * When modify lacp_rate parameter via sysfs,
  * update actor_oper_port_state of each port.
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 095ea51d1853..4e1b7deb724b 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1206,8 +1206,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 
 /**
  * alb_set_mac_address
- * @bond:
- * @addr:
+ * @bond: bonding we're working on
+ * @addr: MAC address to set
  *
  * In TLB mode all slaves are configured to the bond's hw address, but set
  * their dev_addr field to different addresses (based on their permanent hw
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5ad43aaf76e5..42ef25ec0af5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -322,6 +322,7 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
 /**
  * bond_vlan_rx_add_vid - Propagates adding an id to slaves
  * @bond_dev: bonding net device that got called
+ * @proto: network protocol ID
  * @vid: vlan id being added
  */
 static int bond_vlan_rx_add_vid(struct net_device *bond_dev,
@@ -355,6 +356,7 @@ unwind:
 /**
  * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
  * @bond_dev: bonding net device that got called
+ * @proto: network protocol ID
  * @vid: vlan id being removed
  */
 static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
@@ -948,7 +950,7 @@ static bool bond_should_notify_peers(struct bonding *bond)
 /**
  * change_active_interface - change the active slave into the specified one
  * @bond: our bonding struct
- * @new: the new slave to make the active one
+ * @new_active: the new slave to make the active one
  *
  * Set the new slave to the bond's settings and unset them on the old
  * curr_active_slave.
@@ -2205,7 +2207,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
 	int ret;
 
 	ret = __bond_release_one(bond_dev, slave_dev, false, true);
-	if (ret == 0 && !bond_has_slaves(bond)) {
+	if (ret == 0 && !bond_has_slaves(bond) &&
+	    bond_dev->reg_state != NETREG_UNREGISTERING) {
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond\n");
 		bond_remove_proc_entry(bond);
@@ -2271,7 +2274,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 					     "active " : "backup ") : "",
 					   bond->params.downdelay * bond->params.miimon);
 			}
-			/*FALLTHRU*/
+			fallthrough;
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
@@ -2307,7 +2310,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 					   bond->params.updelay *
 					   bond->params.miimon);
 			}
-			/*FALLTHRU*/
+			fallthrough;
 		case BOND_LINK_BACK:
 			if (!link_state) {
 				bond_propose_link_state(slave, BOND_LINK_DOWN);
@@ -2945,6 +2948,9 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 			if (bond_time_in_interval(bond, last_rx, 1)) {
 				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
+			} else if (slave->link == BOND_LINK_BACK) {
+				bond_propose_link_state(slave, BOND_LINK_FAIL);
+				commit++;
 			}
 			continue;
 		}
@@ -3053,6 +3059,19 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_NOW);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
+
+			/* A slave has just been enslaved and has become
+			 * the current active slave.
+			 */
+			if (rtnl_dereference(bond->curr_active_slave))
+				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
+			continue;
+
 		default:
 			slave_err(bond->dev, slave->dev,
 				  "impossible: link_new_state %d on slave\n",
@@ -3103,8 +3122,6 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
-
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && bond_slave_is_up(slave))
 			before = slave;
@@ -3305,7 +3322,7 @@ static int bond_slave_netdev_event(unsigned long event,
 
 		if (BOND_MODE(bond) == BOND_MODE_8023AD)
 			bond_3ad_adapter_speed_duplex_changed(slave);
-		/* Fallthrough */
+		fallthrough;
 	case NETDEV_DOWN:
 		/* Refresh slave-array if applicable!
 		 * If the setup does not use miimon or arpmon (mode-specific!),
@@ -3743,7 +3760,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 			return -EINVAL;
 
 		mii->phy_id = 0;
-		/* Fall Through */
+		fallthrough;
 	case SIOCGMIIREG:
 		/* We do this again just in case we were called by SIOCGMIIREG
 		 * instead of SIOCGMIIPHY.
@@ -4552,13 +4569,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
+{
+	if (speed == 0 || speed == SPEED_UNKNOWN)
+		speed = slave->speed;
+	else
+		speed = min(speed, slave->speed);
+
+	return speed;
+}
+
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 					   struct ethtool_link_ksettings *cmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	unsigned long speed = 0;
 	struct list_head *iter;
 	struct slave *slave;
+	u32 speed = 0;
 
 	cmd->base.duplex = DUPLEX_UNKNOWN;
 	cmd->base.port = PORT_OTHER;
@@ -4570,8 +4597,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 	 */
 	bond_for_each_slave(bond, slave, iter) {
 		if (bond_slave_can_tx(slave)) {
-			if (slave->speed != SPEED_UNKNOWN)
-				speed += slave->speed;
+			if (slave->speed != SPEED_UNKNOWN) {
+				if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
+					speed = bond_mode_bcast_speed(slave,
+								      speed);
+				else
+					speed += slave->speed;
+			}
 			if (cmd->base.duplex == DUPLEX_UNKNOWN &&
 			    slave->duplex != DUPLEX_UNKNOWN)
 				cmd->base.duplex = slave->duplex;
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 9df2007b5e56..38e9f80ed1ef 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -898,7 +898,7 @@ static void at91_irq_err_state(struct net_device *dev,
 				CAN_ERR_CRTL_TX_WARNING :
 				CAN_ERR_CRTL_RX_WARNING;
 		}
-		/* fall through */
+		fallthrough;
 	case CAN_STATE_ERROR_WARNING:
 		/*
 		 * from: ERROR_ACTIVE, ERROR_WARNING
@@ -948,7 +948,7 @@ static void at91_irq_err_state(struct net_device *dev,
 		netdev_dbg(dev, "Error Active\n");
 		cf->can_id |= CAN_ERR_PROT;
 		cf->data[2] = CAN_ERR_PROT_ACTIVE;
-		/* fall through */
+		fallthrough;
 	case CAN_STATE_ERROR_WARNING:
 		reg_idr = AT91_IRQ_ERRA | AT91_IRQ_WARN | AT91_IRQ_BOFF;
 		reg_ier = AT91_IRQ_ERRP;
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 6ad83a881039..9469d4421afe 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -659,7 +659,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd)
 		pciefd_can_writereg(priv, CANFD_CLK_SEL_80MHZ,
 				    PCIEFD_REG_CAN_CLK_SEL);
 
-		/* fall through */
+		fallthrough;
 	case CANFD_CLK_SEL_80MHZ:
 		priv->ucan.can.clock.freq = 80 * 1000 * 1000;
 		break;
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index d7222ba46622..d7c2ec529b8f 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -150,7 +150,7 @@ static void sp_populate_of(struct sja1000_priv *priv, struct device_node *of)
 		priv->read_reg = sp_read_reg16;
 		priv->write_reg = sp_write_reg16;
 		break;
-	case 1:	/* fallthrough */
+	case 1:
 	default:
 		priv->read_reg = sp_read_reg8;
 		priv->write_reg = sp_write_reg8;
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 91cdc0a2b1a7..b4a39f0449ba 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -153,7 +153,7 @@ static void slc_bump(struct slcan *sl)
 	switch (*cmd) {
 	case 'r':
 		cf.can_id = CAN_RTR_FLAG;
-		/* fallthrough */
+		fallthrough;
 	case 't':
 		/* store dlc ASCII value and terminate SFF CAN ID string */
 		cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN];
@@ -163,7 +163,7 @@ static void slc_bump(struct slcan *sl)
 		break;
 	case 'R':
 		cf.can_id = CAN_RTR_FLAG;
-		/* fallthrough */
+		fallthrough;
 	case 'T':
 		cf.can_id |= CAN_EFF_FLAG;
 		/* store dlc ASCII value and terminate EFF CAN ID string */
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 5009ff294941..d17608870f2d 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -864,7 +864,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 			if (new_state >= CAN_STATE_ERROR_WARNING &&
 			    new_state <= CAN_STATE_BUS_OFF)
 				priv->can.can_stats.error_warning++;
-			/* fall through */
+			fallthrough;
 		case CAN_STATE_ERROR_WARNING:
 			if (new_state >= CAN_STATE_ERROR_PASSIVE &&
 			    new_state <= CAN_STATE_BUS_OFF)
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index d2539c95adb6..66d0198e7834 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -415,7 +415,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 			new_state = CAN_STATE_ERROR_WARNING;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case CAN_STATE_ERROR_WARNING:
 		if (n & PCAN_USB_ERROR_BUS_HEAVY) {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 0b7766b715fd..d91df34e7fa8 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -345,7 +345,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb,
 		default:
 			netdev_warn(netdev, "tx urb submitting failed err=%d\n",
 				    err);
-			/* fall through */
+			fallthrough;
 		case -ENOENT:
 			/* cable unplugged */
 			stats->tx_dropped++;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 53cb2f72bdd0..1689ab387612 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -133,10 +133,10 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, int id, ...)
 	switch (id) {
 	case PCAN_USBPRO_TXMSG8:
 		i += 4;
-		/* fall through */
+		fallthrough;
 	case PCAN_USBPRO_TXMSG4:
 		i += 4;
-		/* fall through */
+		fallthrough;
 	case PCAN_USBPRO_TXMSG0:
 		*pc++ = va_arg(ap, int);
 		*pc++ = va_arg(ap, int);
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 6500179c2ca2..e731db900ee0 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1061,7 +1061,7 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 	switch (speed) {
 	case 2000:
 		reg |= PORT_OVERRIDE_SPEED_2000M;
-		/* fallthrough */
+		fallthrough;
 	case SPEED_1000:
 		reg |= PORT_OVERRIDE_SPEED_1000M;
 		break;
@@ -1554,6 +1554,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		return ret;
 
 	switch (ret) {
+	case -ETIMEDOUT:
+		return ret;
 	case -ENOSPC:
 		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
 			addr, vid);
diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c
index 629bf14128a2..5ae3d9783b68 100644
--- a/drivers/net/dsa/b53/b53_serdes.c
+++ b/drivers/net/dsa/b53/b53_serdes.c
@@ -170,7 +170,7 @@ void b53_serdes_phylink_validate(struct b53_device *dev, int port,
 	switch (lane) {
 	case 0:
 		phylink_set(supported, 2500baseX_Full);
-		/* fallthrough */
+		fallthrough;
 	case 1:
 		phylink_set(supported, 1000baseX_Full);
 		break;
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index bafddb35f3a9..5ebff986a1ac 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -566,7 +566,7 @@ static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port,
 	switch (state->interface) {
 	case PHY_INTERFACE_MODE_RGMII:
 		id_mode_dis = 1;
-		/* fallthrough */
+		fallthrough;
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		port_mode = EXT_GPHY;
 		break;
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index dc999406ce86..3cb22d149813 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1083,7 +1083,7 @@ static phy_interface_t ksz9477_get_interface(struct ksz_device *dev, int port)
 		interface = PHY_INTERFACE_MODE_GMII;
 		if (gbit)
 			break;
-		/* fall through */
+		fallthrough;
 	case 0:
 		interface = PHY_INTERFACE_MODE_MII;
 		break;
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 8dcb8a49ab67..1aaf47a0da2b 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -566,7 +566,7 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface)
 	case P5_INTF_SEL_PHY_P0:
 		/* MT7530_P5_MODE_GPHY_P0: 2nd GMAC -> P5 -> P0 */
 		val |= MHWTRAP_PHY0_SEL;
-		/* fall through */
+		fallthrough;
 	case P5_INTF_SEL_PHY_P4:
 		/* MT7530_P5_MODE_GPHY_P4: 2nd GMAC -> P5 -> P4 */
 		val &= ~MHWTRAP_P5_MAC_SEL & ~MHWTRAP_P5_DIS;
@@ -1326,14 +1326,17 @@ mt7530_setup(struct dsa_switch *ds)
 
 			if (phy_node->parent == priv->dev->of_node->parent) {
 				ret = of_get_phy_mode(mac_np, &interface);
-				if (ret && ret != -ENODEV)
+				if (ret && ret != -ENODEV) {
+					of_node_put(mac_np);
 					return ret;
+				}
 				id = of_mdio_parse_addr(ds->dev, phy_node);
 				if (id == 0)
 					priv->p5_intf_sel = P5_INTF_SEL_PHY_P0;
 				if (id == 4)
 					priv->p5_intf_sel = P5_INTF_SEL_PHY_P4;
 			}
+			of_node_put(mac_np);
 			of_node_put(phy_node);
 			break;
 		}
@@ -1501,7 +1504,7 @@ unsupported:
 		phylink_set(mask, 100baseT_Full);
 
 		if (state->interface != PHY_INTERFACE_MODE_MII) {
-			phylink_set(mask, 1000baseT_Half);
+			/* This switch only supports 1G full-duplex. */
 			phylink_set(mask, 1000baseT_Full);
 			if (port == 5)
 				phylink_set(mask, 1000baseX_Full);
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 7a71c9902e73..f0dbc05e30a4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -875,7 +875,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
 		break;
 	case STATS_TYPE_BANK1:
 		reg = bank1_select;
-		/* fall through */
+		fallthrough;
 	case STATS_TYPE_BANK0:
 		reg |= s->reg | histogram;
 		mv88e6xxx_g1_stats_read(chip, reg, &low);
diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig
index f121619d81fe..2d23ccef7d0e 100644
--- a/drivers/net/dsa/ocelot/Kconfig
+++ b/drivers/net/dsa/ocelot/Kconfig
@@ -9,7 +9,7 @@ config NET_DSA_MSCC_FELIX
 	select NET_DSA_TAG_OCELOT
 	select FSL_ENETC_MDIO
 	help
-	  This driver supports network switches from the the Vitesse /
+	  This driver supports network switches from the Vitesse /
 	  Microsemi / Microchip Ocelot family of switching cores that are
 	  connected to their host CPU via Ethernet.
 	  The following switches are supported:
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index c69d9592a2b7..04bfa6e465ff 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -400,6 +400,7 @@ static int felix_parse_ports_node(struct felix *felix,
 		if (err < 0) {
 			dev_err(dev, "Unsupported PHY mode %s on port %d\n",
 				phy_modes(phy_mode), port);
+			of_node_put(child);
 			return err;
 		}
 
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index c3f6f124e5f0..5a28dfb36ec3 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -3415,7 +3415,7 @@ static int sja1105_check_device_id(struct sja1105_private *priv)
 
 	sja1105_unpack(prod_id, &part_no, 19, 4, SJA1105_SIZE_DEVICE_ID);
 
-	for (match = sja1105_dt_ids; match->compatible; match++) {
+	for (match = sja1105_dt_ids; match->compatible[0]; match++) {
 		const struct sja1105_info *info = match->data;
 
 		/* Is what's been probed in our match table at all? */
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index 139d0120f511..667f38c9e4c6 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -1259,14 +1259,14 @@ el3_up(struct net_device *dev)
 					pr_cont("Forcing 3c5x9b full-duplex mode");
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			case 8:
 				/* set full-duplex mode based on eeprom config setting */
 				if ((sw_info & 0x000f) && (sw_info & 0x8000)) {
 					pr_cont("Setting 3c5x9b full-duplex mode (from EEPROM configuration bit)");
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				/* xcvr=(0 || 4) OR user has an old 3c5x9 non "B" model */
 				pr_cont("Setting 3c5x9/3c5x9B half-duplex mode");
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index ef1c3151fbb2..f66e7fb9a2bb 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -951,7 +951,7 @@ static struct net_device_stats *el3_get_stats(struct net_device *dev)
 static void update_stats(struct net_device *dev)
 {
 	unsigned int ioaddr = dev->base_addr;
-	u8 rx, tx, up;
+	u8 up;
 
 	pr_debug("%s: updating the statistics.\n", dev->name);
 
@@ -972,8 +972,8 @@ static void update_stats(struct net_device *dev)
 	dev->stats.tx_packets			+= (up&0x30) << 4;
 	/* Rx packets   */			   inb(ioaddr + 7);
 	/* Tx deferrals */			   inb(ioaddr + 8);
-	rx		 			 = inw(ioaddr + 10);
-	tx					 = inw(ioaddr + 12);
+	/* rx */				   inw(ioaddr + 10);
+	/* tx */				   inw(ioaddr + 12);
 
 	EL3WINDOW(4);
 	/* BadSSD */				   inb(ioaddr + 12);
@@ -1046,7 +1046,7 @@ static int el3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch(cmd) {
 	case SIOCGMIIPHY:		/* Get the address of the PHY in use. */
 		data->phy_id = phy;
-		/* fall through */
+		fallthrough;
 	case SIOCGMIIREG:		/* Read the specified MII register. */
 		{
 			int saved_window;
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index aeae7966a082..a00b36f91d9f 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -610,7 +610,7 @@ static int axnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     switch (cmd) {
     case SIOCGMIIPHY:
 	data->phy_id = info->phy_id;
-	/* Fall through */
+	fallthrough;
     case SIOCGMIIREG:		/* Read MII PHY register. */
 	data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f);
 	return 0;
@@ -898,6 +898,7 @@ static int ax_close(struct net_device *dev)
 /**
  * axnet_tx_timeout - handle transmit time out condition
  * @dev: network device which has apparently fallen asleep
+ * @txqueue: unused
  *
  * Called by kernel when device never acknowledges a transmit has
  * completed (or failed) - i.e. never posted a Tx related interrupt.
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 645efac6310d..164c3ed550bf 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -1108,7 +1108,7 @@ static int ei_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     switch (cmd) {
     case SIOCGMIIPHY:
 	data->phy_id = info->phy_id;
-	/* fall through */
+	fallthrough;
     case SIOCGMIIREG:		/* Read MII PHY register. */
 	data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f);
 	return 0;
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 6234fcd844ee..696517eae77f 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -1712,13 +1712,13 @@ static bool slic_is_fiber(unsigned short subdev)
 {
 	switch (subdev) {
 	/* Mojave */
-	case PCI_SUBDEVICE_ID_ALACRITECH_1000X1F: /* fallthrough */
-	case PCI_SUBDEVICE_ID_ALACRITECH_SES1001F: /* fallthrough */
+	case PCI_SUBDEVICE_ID_ALACRITECH_1000X1F:
+	case PCI_SUBDEVICE_ID_ALACRITECH_SES1001F: fallthrough;
 	/* Oasis */
-	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2002XF: /* fallthrough */
-	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2001XF: /* fallthrough */
-	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2104EF: /* fallthrough */
-	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2102EF: /* fallthrough */
+	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2002XF:
+	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2001XF:
+	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2104EF:
+	case PCI_SUBDEVICE_ID_ALACRITECH_SEN2102EF:
 		return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index ac86fcae1582..8470c836fa18 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -547,7 +547,7 @@ static int acenic_probe_one(struct pci_dev *pdev,
 			       ap->name);
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	case PCI_VENDOR_ID_SGI:
 		printk(KERN_INFO "%s: SGI AceNIC ", ap->name);
 		break;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 2a6c9725e092..a3a8edf9a734 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2180,13 +2180,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter,
 	int i;
 
 	for (i = first_index; i < first_index + count; i++) {
-		/* Check if napi was initialized before */
-		if (!ENA_IS_XDP_INDEX(adapter, i) ||
-		    adapter->ena_napi[i].xdp_ring)
-			netif_napi_del(&adapter->ena_napi[i].napi);
-		else
-			WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
-				adapter->ena_napi[i].xdp_ring);
+		netif_napi_del(&adapter->ena_napi[i].napi);
+
+		WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) &&
+			adapter->ena_napi[i].xdp_ring);
 	}
 }
 
@@ -3601,16 +3598,14 @@ static void ena_fw_reset_device(struct work_struct *work)
 {
 	struct ena_adapter *adapter =
 		container_of(work, struct ena_adapter, reset_task);
-	struct pci_dev *pdev = adapter->pdev;
 
-	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
-		dev_err(&pdev->dev,
-			"device reset schedule while reset bit is off\n");
-		return;
-	}
 	rtnl_lock();
-	ena_destroy_device(adapter, false);
-	ena_restore_device(adapter);
+
+	if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		ena_destroy_device(adapter, false);
+		ena_restore_device(adapter);
+	}
+
 	rtnl_unlock();
 }
 
@@ -3692,7 +3687,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 	}
 
 	u64_stats_update_begin(&tx_ring->syncp);
-	tx_ring->tx_stats.missed_tx = missed_tx;
+	tx_ring->tx_stats.missed_tx += missed_tx;
 	u64_stats_update_end(&tx_ring->syncp);
 
 	return rc;
@@ -4389,8 +4384,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 		netdev->rx_cpu_rmap = NULL;
 	}
 #endif /* CONFIG_RFS_ACCEL */
-	del_timer_sync(&adapter->timer_service);
 
+	/* Make sure timer and reset routine won't be called after
+	 * freeing device resources.
+	 */
+	del_timer_sync(&adapter->timer_service);
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
@@ -4558,6 +4556,9 @@ static void ena_keep_alive_wd(void *adapter_data,
 	tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low;
 
 	u64_stats_update_begin(&adapter->syncp);
+	/* These stats are accumulated by the device, so the counters indicate
+	 * all drops since last reset.
+	 */
 	adapter->dev_stats.rx_drops = rx_drops;
 	adapter->dev_stats.tx_drops = tx_drops;
 	u64_stats_update_end(&adapter->syncp);
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index b6c43b58ed3d..960d483e8997 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1475,7 +1475,7 @@ static int amd8111e_ioctl(struct net_device *dev , struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		data->phy_id = lp->ext_phy_addr;
 
-	/* fallthru */
+		fallthrough;
 	case SIOCGMIIREG:
 
 		spin_lock_irq(&lp->lock);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 43294a148f8a..4ba75551cb17 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1538,7 +1538,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, any kind of event packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		/* Fall through - to PTP v1, UDP, any kind of event packet */
+		fallthrough;	/* to PTP v1, UDP, any kind of event packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
@@ -1549,7 +1549,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, Sync packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		/* Fall through - to PTP v1, UDP, Sync packet */
+		fallthrough;	/* to PTP v1, UDP, Sync packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
@@ -1560,7 +1560,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, Delay_req packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		/* Fall through - to PTP v1, UDP, Delay_req packet */
+		fallthrough;	/* to PTP v1, UDP, Delay_req packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 46c3c1ca38d6..859ded0c06b0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -166,6 +166,7 @@ enum xgbe_port_mode {
 	XGBE_PORT_MODE_10GBASE_T,
 	XGBE_PORT_MODE_10GBASE_R,
 	XGBE_PORT_MODE_SFP,
+	XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG,
 	XGBE_PORT_MODE_MAX,
 };
 
@@ -1634,6 +1635,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata)
 	if (ad_reg & 0x80) {
 		switch (phy_data->port_mode) {
 		case XGBE_PORT_MODE_BACKPLANE:
+		case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 			mode = XGBE_MODE_KR;
 			break;
 		default:
@@ -1643,6 +1645,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata)
 	} else if (ad_reg & 0x20) {
 		switch (phy_data->port_mode) {
 		case XGBE_PORT_MODE_BACKPLANE:
+		case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 			mode = XGBE_MODE_KX_1000;
 			break;
 		case XGBE_PORT_MODE_1000BASE_X:
@@ -1782,6 +1785,7 @@ static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata,
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		XGBE_SET_ADV(dlks, 10000baseKR_Full);
 		break;
 	case XGBE_PORT_MODE_BACKPLANE_2500:
@@ -1874,6 +1878,7 @@ static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata)
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
 		return XGBE_AN_MODE_CL73;
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		return XGBE_AN_MODE_NONE;
 	case XGBE_PORT_MODE_1000BASE_T:
@@ -2156,6 +2161,7 @@ static enum xgbe_mode xgbe_phy_switch_mode(struct xgbe_prv_data *pdata)
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		return xgbe_phy_switch_bp_mode(pdata);
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		return xgbe_phy_switch_bp_2500_mode(pdata);
@@ -2251,6 +2257,7 @@ static enum xgbe_mode xgbe_phy_get_mode(struct xgbe_prv_data *pdata,
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		return xgbe_phy_get_bp_mode(speed);
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		return xgbe_phy_get_bp_2500_mode(speed);
@@ -2426,6 +2433,7 @@ static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode)
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		return xgbe_phy_use_bp_mode(pdata, mode);
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		return xgbe_phy_use_bp_2500_mode(pdata, mode);
@@ -2515,6 +2523,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		return xgbe_phy_valid_speed_bp_mode(speed);
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		return xgbe_phy_valid_speed_bp_2500_mode(speed);
@@ -2792,6 +2801,7 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata)
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) ||
 		    (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000))
 			return false;
@@ -2844,6 +2854,7 @@ static bool xgbe_phy_conn_type_mismatch(struct xgbe_prv_data *pdata)
 
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_BACKPLANE:
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 	case XGBE_PORT_MODE_BACKPLANE_2500:
 		if (phy_data->conn_type == XGBE_CONN_TYPE_BACKPLANE)
 			return false;
@@ -3160,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 	/* Backplane support */
 	case XGBE_PORT_MODE_BACKPLANE:
 		XGBE_SET_SUP(lks, Autoneg);
+		fallthrough;
+	case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG:
 		XGBE_SET_SUP(lks, Pause);
 		XGBE_SET_SUP(lks, Asym_Pause);
 		XGBE_SET_SUP(lks, Backplane);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 16a944707ba9..8941ac4df9e3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1631,8 +1631,8 @@ static int hw_atl_b0_get_mac_temp(struct aq_hw_s *self, u32 *temp)
 		hw_atl_ts_reset_set(self, 0);
 	}
 
-	err = readx_poll_timeout_atomic(hw_atl_b0_ts_ready_and_latch_high_get,
-					self, val, val == 1, 10000U, 500000U);
+	err = readx_poll_timeout(hw_atl_b0_ts_ready_and_latch_high_get, self,
+				 val, val == 1, 10000U, 500000U);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c
index 0187dbf3b87d..54cdafdd067d 100644
--- a/drivers/net/ethernet/arc/emac_mdio.c
+++ b/drivers/net/ethernet/arc/emac_mdio.c
@@ -153,6 +153,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv)
 	if (IS_ERR(data->reset_gpio)) {
 		error = PTR_ERR(data->reset_gpio);
 		dev_err(priv->dev, "Failed to request gpio: %d\n", error);
+		mdiobus_free(bus);
 		return error;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index dfed9ade6950..0762d5d1a810 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2491,8 +2491,10 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 	priv->tx_rings = devm_kcalloc(&pdev->dev, txq,
 				      sizeof(struct bcm_sysport_tx_ring),
 				      GFP_KERNEL);
-	if (!priv->tx_rings)
-		return -ENOMEM;
+	if (!priv->tx_rings) {
+		ret = -ENOMEM;
+		goto err_free_netdev;
+	}
 
 	priv->is_lite = params->is_lite;
 	priv->num_rx_desc_words = params->num_rx_desc_words;
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 34d18302b1a3..a5fd161ab5ee 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -217,7 +217,7 @@ static int bgmac_probe(struct bcma_device *core)
 	/* BCM 471X/535X family */
 	case BCMA_CHIP_ID_BCM4716:
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		/* fallthrough */
+		fallthrough;
 	case BCMA_CHIP_ID_BCM47162:
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2;
 		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 6795b6d95f54..f37f1c58f368 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -131,7 +131,7 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev)
 	switch (bgmac->net_dev->phydev->speed) {
 	default:
 		netdev_err(net_dev, "Unsupported speed. Defaulting to 1000Mb\n");
-		/* fall through */
+		fallthrough;
 	case SPEED_1000:
 		val |= NICPM_IOMUX_CTRL_SPD_1000M << NICPM_IOMUX_CTRL_SPD_SHIFT;
 		break;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index c8cc14eadbb4..3e8a179f39db 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -1337,13 +1337,13 @@ bnx2_set_mac_link(struct bnx2 *bp)
 					val |= BNX2_EMAC_MODE_PORT_MII_10M;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			case SPEED_100:
 				val |= BNX2_EMAC_MODE_PORT_MII;
 				break;
 			case SPEED_2500:
 				val |= BNX2_EMAC_MODE_25G_MODE;
-				/* fall through */
+				fallthrough;
 			case SPEED_1000:
 				val |= BNX2_EMAC_MODE_PORT_GMII;
 				break;
@@ -1995,26 +1995,26 @@ bnx2_remote_phy_event(struct bnx2 *bp)
 		switch (speed) {
 			case BNX2_LINK_STATUS_10HALF:
 				bp->duplex = DUPLEX_HALF;
-				/* fall through */
+				fallthrough;
 			case BNX2_LINK_STATUS_10FULL:
 				bp->line_speed = SPEED_10;
 				break;
 			case BNX2_LINK_STATUS_100HALF:
 				bp->duplex = DUPLEX_HALF;
-				/* fall through */
+				fallthrough;
 			case BNX2_LINK_STATUS_100BASE_T4:
 			case BNX2_LINK_STATUS_100FULL:
 				bp->line_speed = SPEED_100;
 				break;
 			case BNX2_LINK_STATUS_1000HALF:
 				bp->duplex = DUPLEX_HALF;
-				/* fall through */
+				fallthrough;
 			case BNX2_LINK_STATUS_1000FULL:
 				bp->line_speed = SPEED_1000;
 				break;
 			case BNX2_LINK_STATUS_2500HALF:
 				bp->duplex = DUPLEX_HALF;
-				/* fall through */
+				fallthrough;
 			case BNX2_LINK_STATUS_2500FULL:
 				bp->line_speed = SPEED_2500;
 				break;
@@ -7856,7 +7856,7 @@ bnx2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		data->phy_id = bp->phy_addr;
 
-		/* fallthru */
+		fallthrough;
 	case SIOCGMIIREG: {
 		u32 mii_regval;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 1426c691c7c4..4e85e7dbc2be 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -4712,14 +4712,14 @@ static void bnx2x_sync_link(struct link_params *params,
 			LINK_STATUS_SPEED_AND_DUPLEX_MASK) {
 		case LINK_10THD:
 			vars->duplex = DUPLEX_HALF;
-			/* Fall thru */
+			fallthrough;
 		case LINK_10TFD:
 			vars->line_speed = SPEED_10;
 			break;
 
 		case LINK_100TXHD:
 			vars->duplex = DUPLEX_HALF;
-			/* Fall thru */
+			fallthrough;
 		case LINK_100T4:
 		case LINK_100TXFD:
 			vars->line_speed = SPEED_100;
@@ -4727,14 +4727,14 @@ static void bnx2x_sync_link(struct link_params *params,
 
 		case LINK_1000THD:
 			vars->duplex = DUPLEX_HALF;
-			/* Fall thru */
+			fallthrough;
 		case LINK_1000TFD:
 			vars->line_speed = SPEED_1000;
 			break;
 
 		case LINK_2500THD:
 			vars->duplex = DUPLEX_HALF;
-			/* Fall thru */
+			fallthrough;
 		case LINK_2500TFD:
 			vars->line_speed = SPEED_2500;
 			break;
@@ -6339,7 +6339,7 @@ int bnx2x_set_led(struct link_params *params,
 		 */
 		if (!vars->link_up)
 			break;
-		/* fall through */
+		fallthrough;
 	case LED_MODE_ON:
 		if (((params->phy[EXT_PHY1].type ==
 			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
@@ -12508,13 +12508,13 @@ static void bnx2x_phy_def_cfg(struct link_params *params,
 	switch (link_config  & PORT_FEATURE_LINK_SPEED_MASK) {
 	case PORT_FEATURE_LINK_SPEED_10M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
-		/* fall through */
+		fallthrough;
 	case PORT_FEATURE_LINK_SPEED_10M_FULL:
 		phy->req_line_speed = SPEED_10;
 		break;
 	case PORT_FEATURE_LINK_SPEED_100M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
-		/* fall through */
+		fallthrough;
 	case PORT_FEATURE_LINK_SPEED_100M_FULL:
 		phy->req_line_speed = SPEED_100;
 		break;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 7f24d2689fdd..3c543dd7a8f3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8600,11 +8600,11 @@ int bnx2x_set_int_mode(struct bnx2x *bp)
 			       bp->num_queues,
 			       1 + bp->num_cnic_queues);
 
-		/* fall through */
+		fallthrough;
 	case BNX2X_INT_MODE_MSI:
 		bnx2x_enable_msi(bp);
 
-		/* fall through */
+		fallthrough;
 	case BNX2X_INT_MODE_INTX:
 		bp->num_ethernet_queues = 1;
 		bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 80d250a6d048..e26f4da5a6d7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -3258,7 +3258,7 @@ static int bnx2x_mcast_validate_e2(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* fall through */
+		fallthrough;
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
@@ -3592,7 +3592,7 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* fall through */
+		fallthrough;
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index b4476f44e386..9c2f51f23035 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1809,7 +1809,7 @@ get_vf:
 		DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n",
 		   vf->abs_vfid, qidx);
 		bnx2x_vf_handle_rss_update_eqe(bp, vf);
-		/* fall through */
+		fallthrough;
 	case EVENT_RING_OPCODE_VF_FLR:
 		/* Do nothing for now */
 		return 0;
@@ -2207,7 +2207,7 @@ int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		rc = bnx2x_vf_close(bp, vf);
 		if (rc)
 			goto op_err;
-		/* Fall through - to release resources */
+		fallthrough;	/* to release resources */
 	case VF_ACQUIRED:
 		DP(BNX2X_MSG_IOV, "about to free resources\n");
 		bnx2x_vf_free_resc(bp, vf);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 31fb5a28e1c4..b167066af450 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1141,6 +1141,9 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
 {
+	if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
+		return;
+
 	if (BNXT_PF(bp))
 		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
 	else
@@ -1157,10 +1160,12 @@ static void bnxt_queue_sp_work(struct bnxt *bp)
 
 static void bnxt_cancel_sp_work(struct bnxt *bp)
 {
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
 		flush_workqueue(bnxt_pf_wq);
-	else
+	} else {
 		cancel_work_sync(&bp->sp_task);
+		cancel_delayed_work_sync(&bp->fw_reset_task);
+	}
 }
 
 static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -1923,7 +1928,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx)
 		break;
 	case BNXT_FW_HEALTH_REG_TYPE_GRC:
 		reg_off = fw_health->mapped_regs[reg_idx];
-		/* fall through */
+		fallthrough;
 	case BNXT_FW_HEALTH_REG_TYPE_BAR0:
 		val = readl(bp->bar0 + reg_off);
 		break;
@@ -1966,11 +1971,11 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		}
 		set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
 	}
-	/* fall through */
+		fallthrough;
 	case ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE:
 	case ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE:
 		set_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT, &bp->sp_event);
-		/* fall through */
+		fallthrough;
 	case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
 		set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event);
 		break;
@@ -6102,6 +6107,21 @@ static int bnxt_get_func_stat_ctxs(struct bnxt *bp)
 	return cp + ulp_stat;
 }
 
+/* Check if a default RSS map needs to be setup.  This function is only
+ * used on older firmware that does not require reserving RX rings.
+ */
+static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp)
+{
+	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+
+	/* The RSS map is valid for RX rings set to resv_rx_rings */
+	if (hw_resc->resv_rx_rings != bp->rx_nr_rings) {
+		hw_resc->resv_rx_rings = bp->rx_nr_rings;
+		if (!netif_is_rxfh_configured(bp->dev))
+			bnxt_set_dflt_rss_indir_tbl(bp);
+	}
+}
+
 static bool bnxt_need_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
@@ -6110,22 +6130,28 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 	int rx = bp->rx_nr_rings, stat;
 	int vnic = 1, grp = rx;
 
-	if (bp->hwrm_spec_code < 0x10601)
-		return false;
-
-	if (hw_resc->resv_tx_rings != bp->tx_nr_rings)
+	if (hw_resc->resv_tx_rings != bp->tx_nr_rings &&
+	    bp->hwrm_spec_code >= 0x10601)
 		return true;
 
+	/* Old firmware does not need RX ring reservations but we still
+	 * need to setup a default RSS map when needed.  With new firmware
+	 * we go through RX ring reservations first and then set up the
+	 * RSS map for the successfully reserved RX rings when needed.
+	 */
+	if (!BNXT_NEW_RM(bp)) {
+		bnxt_check_rss_tbl_no_rmgr(bp);
+		return false;
+	}
 	if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5))
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
 	stat = bnxt_get_func_stat_ctxs(bp);
-	if (BNXT_NEW_RM(bp) &&
-	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
-	     hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat ||
-	     (hw_resc->resv_hw_ring_grps != grp &&
-	      !(bp->flags & BNXT_FLAG_CHIP_P5))))
+	if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
+	    hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat ||
+	    (hw_resc->resv_hw_ring_grps != grp &&
+	     !(bp->flags & BNXT_FLAG_CHIP_P5)))
 		return true;
 	if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) &&
 	    hw_resc->resv_irqs != nq)
@@ -6214,6 +6240,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	if (!tx || !rx || !cp || !grp || !vnic || !stat)
 		return -ENOMEM;
 
+	if (!netif_is_rxfh_configured(bp->dev))
+		bnxt_set_dflt_rss_indir_tbl(bp);
+
 	return rc;
 }
 
@@ -8495,9 +8524,6 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 			rc = bnxt_init_int_mode(bp);
 		bnxt_ulp_irq_restart(bp, rc);
 	}
-	if (!netif_is_rxfh_configured(bp->dev))
-		bnxt_set_dflt_rss_indir_tbl(bp);
-
 	if (rc) {
 		netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
 		return rc;
@@ -9284,16 +9310,19 @@ static ssize_t bnxt_show_temp(struct device *dev,
 	struct hwrm_temp_monitor_query_input req = {0};
 	struct hwrm_temp_monitor_query_output *resp;
 	struct bnxt *bp = dev_get_drvdata(dev);
-	u32 temp = 0;
+	u32 len = 0;
 
 	resp = bp->hwrm_cmd_resp_addr;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
 	mutex_lock(&bp->hwrm_cmd_lock);
-	if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
-		temp = resp->temp * 1000; /* display millidegree */
+	if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+		len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
-	return sprintf(buf, "%u\n", temp);
+	if (len)
+		return len;
+
+	return sprintf(buf, "unknown\n");
 }
 static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
 
@@ -9475,15 +9504,15 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		}
 	}
 
-	bnxt_enable_napi(bp);
-	bnxt_debug_dev_init(bp);
-
 	rc = bnxt_init_nic(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
-		goto open_err;
+		goto open_err_irq;
 	}
 
+	bnxt_enable_napi(bp);
+	bnxt_debug_dev_init(bp);
+
 	if (link_re_init) {
 		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
@@ -9514,10 +9543,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		bnxt_vf_reps_open(bp);
 	return 0;
 
-open_err:
-	bnxt_debug_dev_exit(bp);
-	bnxt_disable_napi(bp);
-
 open_err_irq:
 	bnxt_del_napi(bp);
 
@@ -9765,7 +9790,7 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		mdio->phy_id = bp->link_info.phy_addr;
 
-		/* fallthru */
+		fallthrough;
 	case SIOCGMIIREG: {
 		u16 mii_regval = 0;
 
@@ -11022,7 +11047,7 @@ static void bnxt_fw_reset_writel(struct bnxt *bp, int reg_idx)
 		writel(reg_off & BNXT_GRC_BASE_MASK,
 		       bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + 4);
 		reg_off = (reg_off & BNXT_GRC_OFFSET_MASK) + 0x2000;
-		/* fall through */
+		fallthrough;
 	case BNXT_FW_HEALTH_REG_TYPE_BAR0:
 		writel(val, bp->bar0 + reg_off);
 		break;
@@ -11135,7 +11160,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW;
 	}
-	/* fall through */
+		fallthrough;
 	case BNXT_FW_RESET_STATE_RESET_FW:
 		bnxt_reset_all(bp);
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
@@ -11158,7 +11183,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		pci_set_master(bp->pdev);
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW;
-		/* fall through */
+		fallthrough;
 	case BNXT_FW_RESET_STATE_POLL_FW:
 		bp->hwrm_cmd_timeout = SHORT_HWRM_CMD_TIMEOUT;
 		rc = __bnxt_hwrm_ver_get(bp, true);
@@ -11173,7 +11198,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT;
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
-		/* fall through */
+		fallthrough;
 	case BNXT_FW_RESET_STATE_OPENING:
 		while (!rtnl_trylock()) {
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
@@ -11761,6 +11786,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	unregister_netdev(dev);
 	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
 
@@ -12200,6 +12226,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (BNXT_CHIP_P5(bp))
 		bp->flags |= BNXT_FLAG_CHIP_P5;
 
+	rc = bnxt_alloc_rss_indir_tbl(bp);
+	if (rc)
+		goto init_err_pci_clean;
+
 	rc = bnxt_fw_init_one_p2(bp);
 	if (rc)
 		goto init_err_pci_clean;
@@ -12304,11 +12334,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 
-	rc = bnxt_alloc_rss_indir_tbl(bp);
-	if (rc)
-		goto init_err_pci_clean;
-	bnxt_set_dflt_rss_indir_tbl(bp);
-
 	if (BNXT_PF(bp)) {
 		if (!bnxt_pf_wq) {
 			bnxt_pf_wq =
@@ -12339,6 +12364,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		    (long)pci_resource_start(pdev, 0), dev->dev_addr);
 	pcie_print_link_status(pdev);
 
+	pci_save_state(pdev);
 	return 0;
 
 init_err_cleanup:
@@ -12536,6 +12562,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 			"Cannot re-enable PCI device after reset.\n");
 	} else {
 		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
 
 		err = bnxt_hwrm_func_reset(bp);
 		if (!err) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 64da654f1038..d0928334bdc8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -472,20 +472,13 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 static int bnxt_get_num_ring_stats(struct bnxt *bp)
 {
 	int rx, tx, cmn;
-	bool sh = false;
-
-	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
-		sh = true;
 
 	rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS +
 	     bnxt_get_num_tpa_ring_stats(bp);
 	tx = NUM_RING_TX_HW_STATS;
 	cmn = NUM_RING_CMN_SW_STATS;
-	if (sh)
-		return (rx + tx + cmn) * bp->cp_nr_rings;
-	else
-		return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings +
-		       cmn * bp->cp_nr_rings;
+	return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings +
+	       cmn * bp->cp_nr_rings;
 }
 
 static int bnxt_get_num_stats(struct bnxt *bp)
@@ -806,7 +799,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	int max_tx_sch_inputs;
 
 	/* Get the most up-to-date max_tx_sch_inputs. */
-	if (BNXT_NEW_RM(bp))
+	if (netif_running(dev) && BNXT_NEW_RM(bp))
 		bnxt_hwrm_func_resc_qcaps(bp, false);
 	max_tx_sch_inputs = hw_resc->max_tx_sch_inputs;
 
@@ -1073,7 +1066,7 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4)
 			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
 				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* fall through */
+		fallthrough;
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -1092,7 +1085,7 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6)
 			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
 				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* fall through */
+		fallthrough;
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
@@ -2323,6 +2316,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data)
 	if (rc != 0)
 		return rc;
 
+	if (!dir_entries || !entry_length)
+		return -EIO;
+
 	/* Insert 2 bytes of directory info (count and size of entries) */
 	if (len < 2)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 2704a4709bc7..fcc262064766 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -201,10 +201,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* Fall thru */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(bp->dev, xdp_prog, act);
-		/* Fall thru */
+		fallthrough;
 	case XDP_DROP:
 		bnxt_reuse_rx_data(rxr, cons, page);
 		break;
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index c5cca63b8571..84536292b031 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -3311,7 +3311,7 @@ static int cnic_ctl(void *data, struct cnic_ctl_info *info)
 	}
 	case CNIC_CTL_FCOE_STATS_GET_CMD:
 		ulp_type = CNIC_ULP_FCOE;
-		/* fall through */
+		fallthrough;
 	case CNIC_CTL_ISCSI_STATS_GET_CMD:
 		cnic_hold(dev);
 		cnic_copy_ulp_stats(dev, ulp_type);
@@ -4044,7 +4044,7 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe)
 			    l4kcqe->status, l5kcqe->completion_status);
 		opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP;
 	}
-		/* Fall through */
+		fallthrough;
 	case L4_KCQE_OPCODE_VALUE_RESET_RECEIVED:
 	case L4_KCQE_OPCODE_VALUE_CLOSE_COMP:
 	case L4_KCQE_OPCODE_VALUE_RESET_COMP:
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1fecc25767bd..be85dad2e3bc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1185,10 +1185,10 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 			continue;
 		case BCMGENET_STAT_RUNT:
 			offset += BCMGENET_STAT_OFFSET;
-			/* fall through */
+			fallthrough;
 		case BCMGENET_STAT_MIB_TX:
 			offset += BCMGENET_STAT_OFFSET;
-			/* fall through */
+			fallthrough;
 		case BCMGENET_STAT_MIB_RX:
 			val = bcmgenet_umac_readl(priv,
 						  UMAC_MIB_START + j + offset);
@@ -1364,7 +1364,7 @@ static int bcmgenet_validate_flow(struct net_device *dev,
 	case ETHER_FLOW:
 		eth_mask = &cmd->fs.m_u.ether_spec;
 		/* don't allow mask which isn't valid */
-		if (VALIDATE_MASK(eth_mask->h_source) ||
+		if (VALIDATE_MASK(eth_mask->h_dest) ||
 		    VALIDATE_MASK(eth_mask->h_source) ||
 		    VALIDATE_MASK(eth_mask->h_proto)) {
 			netdev_err(dev, "rxnfc: Unsupported mask\n");
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 511d553a4d11..6fb6c3556285 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -192,7 +192,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	switch (priv->phy_interface) {
 	case PHY_INTERFACE_MODE_INTERNAL:
 		phy_name = "internal PHY";
-		/* fall through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_MOCA:
 		/* Irrespective of the actually configured PHY speed (100 or
 		 * 1000) GENETv4 only has an internal GPHY so we will just end
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ebff1fc0d8ce..5143cdd0eeca 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -715,7 +715,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return 0;
-		/* fall through */
+		fallthrough;
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -776,7 +776,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return;
-		/* fall through */
+		fallthrough;
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -1586,7 +1586,7 @@ static int tg3_mdio_init(struct tg3 *tp)
 			phydev->dev_flags |= PHY_BRCM_EXT_IBND_RX_ENABLE;
 		if (tg3_flag(tp, RGMII_EXT_IBND_TX_EN))
 			phydev->dev_flags |= PHY_BRCM_EXT_IBND_TX_ENABLE;
-		/* fall through */
+		fallthrough;
 	case PHY_ID_RTL8211C:
 		phydev->interface = PHY_INTERFACE_MODE_RGMII;
 		break;
@@ -2114,7 +2114,7 @@ static int tg3_phy_init(struct tg3 *tp)
 			phy_support_asym_pause(phydev);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_MII:
 		phy_set_max_speed(phydev, SPEED_100);
 		phy_support_asym_pause(phydev);
@@ -4390,7 +4390,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl)
 				      MII_TG3_DSP_TAP26_RMRXSTO |
 				      MII_TG3_DSP_TAP26_OPCSINPT;
 			tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val);
-			/* Fall through */
+			fallthrough;
 		case ASIC_REV_5720:
 		case ASIC_REV_5762:
 			if (!tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val))
@@ -4538,7 +4538,7 @@ static int tg3_phy_pull_config(struct tg3 *tp)
 				tp->link_config.speed = SPEED_1000;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		default:
 			goto done;
 		}
@@ -5209,7 +5209,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp,
 		if (ap->flags & (MR_AN_ENABLE | MR_RESTART_AN))
 			ap->state = ANEG_STATE_AN_ENABLE;
 
-		/* fall through */
+		fallthrough;
 	case ANEG_STATE_AN_ENABLE:
 		ap->flags &= ~(MR_AN_COMPLETE | MR_PAGE_RX);
 		if (ap->flags & MR_AN_ENABLE) {
@@ -5239,7 +5239,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp,
 		ret = ANEG_TIMER_ENAB;
 		ap->state = ANEG_STATE_RESTART;
 
-		/* fall through */
+		fallthrough;
 	case ANEG_STATE_RESTART:
 		delta = ap->cur_time - ap->link_time;
 		if (delta > ANEG_STATE_SETTLE_TIME)
@@ -5282,7 +5282,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp,
 
 		ap->state = ANEG_STATE_ACK_DETECT;
 
-		/* fall through */
+		fallthrough;
 	case ANEG_STATE_ACK_DETECT:
 		if (ap->ack_match != 0) {
 			if ((ap->rxconfig & ~ANEG_CFG_ACK) ==
@@ -7221,8 +7221,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp)
 
 static inline void tg3_reset_task_cancel(struct tg3 *tp)
 {
-	cancel_work_sync(&tp->reset_task);
-	tg3_flag_clear(tp, RESET_TASK_PENDING);
+	if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags))
+		cancel_work_sync(&tp->reset_task);
 	tg3_flag_clear(tp, TX_RECOVERY_PENDING);
 }
 
@@ -10720,40 +10720,40 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 	switch (limit) {
 	case 16:
 		tw32(MAC_RCV_RULE_15,  0); tw32(MAC_RCV_VALUE_15,  0);
-		/* fall through */
+		fallthrough;
 	case 15:
 		tw32(MAC_RCV_RULE_14,  0); tw32(MAC_RCV_VALUE_14,  0);
-		/* fall through */
+		fallthrough;
 	case 14:
 		tw32(MAC_RCV_RULE_13,  0); tw32(MAC_RCV_VALUE_13,  0);
-		/* fall through */
+		fallthrough;
 	case 13:
 		tw32(MAC_RCV_RULE_12,  0); tw32(MAC_RCV_VALUE_12,  0);
-		/* fall through */
+		fallthrough;
 	case 12:
 		tw32(MAC_RCV_RULE_11,  0); tw32(MAC_RCV_VALUE_11,  0);
-		/* fall through */
+		fallthrough;
 	case 11:
 		tw32(MAC_RCV_RULE_10,  0); tw32(MAC_RCV_VALUE_10,  0);
-		/* fall through */
+		fallthrough;
 	case 10:
 		tw32(MAC_RCV_RULE_9,  0); tw32(MAC_RCV_VALUE_9,  0);
-		/* fall through */
+		fallthrough;
 	case 9:
 		tw32(MAC_RCV_RULE_8,  0); tw32(MAC_RCV_VALUE_8,  0);
-		/* fall through */
+		fallthrough;
 	case 8:
 		tw32(MAC_RCV_RULE_7,  0); tw32(MAC_RCV_VALUE_7,  0);
-		/* fall through */
+		fallthrough;
 	case 7:
 		tw32(MAC_RCV_RULE_6,  0); tw32(MAC_RCV_VALUE_6,  0);
-		/* fall through */
+		fallthrough;
 	case 6:
 		tw32(MAC_RCV_RULE_5,  0); tw32(MAC_RCV_VALUE_5,  0);
-		/* fall through */
+		fallthrough;
 	case 5:
 		tw32(MAC_RCV_RULE_4,  0); tw32(MAC_RCV_VALUE_4,  0);
-		/* fall through */
+		fallthrough;
 	case 4:
 		/* tw32(MAC_RCV_RULE_3,  0); tw32(MAC_RCV_VALUE_3,  0); */
 	case 3:
@@ -11209,18 +11209,27 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 0);
 	err = tg3_init_hw(tp, true);
-	if (err)
+	if (err) {
+		tg3_full_unlock(tp);
+		tp->irq_sync = 0;
+		tg3_napi_enable(tp);
+		/* Clear this flag so that tg3_reset_task_cancel() will not
+		 * call cancel_work_sync() and wait forever.
+		 */
+		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		dev_close(tp->dev);
 		goto out;
+	}
 
 	tg3_netif_start(tp);
 
-out:
 	tg3_full_unlock(tp);
 
 	if (!err)
 		tg3_phy_start(tp);
 
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
+out:
 	rtnl_unlock();
 }
 
@@ -13998,7 +14007,7 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		data->phy_id = tp->phy_addr;
 
-		/* fall through */
+		fallthrough;
 	case SIOCGMIIREG: {
 		u32 mii_regval;
 
@@ -17136,7 +17145,7 @@ static u32 tg3_calc_dma_bndry(struct tg3 *tp, u32 val)
 				val |= DMA_RWCTRL_WRITE_BNDRY_64_PCIE;
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case 128:
 		default:
 			val &= ~DMA_RWCTRL_WRITE_BNDRY_DISAB_PCIE;
@@ -17151,28 +17160,28 @@ static u32 tg3_calc_dma_bndry(struct tg3 *tp, u32 val)
 					DMA_RWCTRL_WRITE_BNDRY_16);
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case 32:
 			if (goal == BOUNDARY_SINGLE_CACHELINE) {
 				val |= (DMA_RWCTRL_READ_BNDRY_32 |
 					DMA_RWCTRL_WRITE_BNDRY_32);
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case 64:
 			if (goal == BOUNDARY_SINGLE_CACHELINE) {
 				val |= (DMA_RWCTRL_READ_BNDRY_64 |
 					DMA_RWCTRL_WRITE_BNDRY_64);
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case 128:
 			if (goal == BOUNDARY_SINGLE_CACHELINE) {
 				val |= (DMA_RWCTRL_READ_BNDRY_128 |
 					DMA_RWCTRL_WRITE_BNDRY_128);
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case 256:
 			val |= (DMA_RWCTRL_READ_BNDRY_256 |
 				DMA_RWCTRL_WRITE_BNDRY_256);
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 49358d42a0e2..b9dd06b12945 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -321,7 +321,7 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event)
 	case IOC_E_PFFAILED:
 	case IOC_E_HWERROR:
 		del_timer(&ioc->ioc_timer);
-		/* fall through */
+		fallthrough;
 	case IOC_E_TIMEOUT:
 		ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_fail);
@@ -780,7 +780,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_INITFAIL:
 		del_timer(&ioc->iocpf_timer);
-		/* fall through */
+		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
 		bfa_nw_ioc_hw_sem_release(ioc);
@@ -849,7 +849,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_FAIL:
 		del_timer(&ioc->iocpf_timer);
-		/* fall through*/
+		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
 		bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL);
diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c
index 40107a9bd120..a2c983f56b00 100644
--- a/drivers/net/ethernet/brocade/bna/bna_enet.c
+++ b/drivers/net/ethernet/brocade/bna/bna_enet.c
@@ -1084,7 +1084,7 @@ bna_enet_sm_cfg_wait(struct bna_enet *enet,
 
 	case ENET_E_CHLD_STOPPED:
 		bna_enet_rx_start(enet);
-		/* Fall through */
+		fallthrough;
 	case ENET_E_FWRESP_PAUSE:
 		if (enet->flags & BNA_ENET_F_PAUSE_CHANGED) {
 			enet->flags &= ~BNA_ENET_F_PAUSE_CHANGED;
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index b5ecbfe13ab0..2623a0da4682 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -1636,7 +1636,7 @@ bna_bfi_rx_enet_start(struct bna_rx *rx)
 						&q1->qpt);
 			cfg_req->q_cfg[i].qs.rx_buffer_size =
 				htons((u16)q1->buffer_size);
-			/* Fall through */
+			fallthrough;
 
 		case BNA_RXP_SINGLE:
 			/* Large/Single RxQ */
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 31ebf3ee7ec0..283918aeb741 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -460,7 +460,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		if (gem_ptp_set_one_step_sync(bp, 1) != 0)
 			return -ERANGE;
-		/* fall through */
+		fallthrough;
 	case HWTSTAMP_TX_ON:
 		tx_bd_control = TSTAMP_ALL_FRAMES;
 		break;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index e73bc211779a..8e0ed01e7f03 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -977,15 +977,14 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		schedule_timeout_uninterruptible(HZ / 10);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_HOST_OK:
 
-		/* fallthrough */
 	case OCT_DEV_CONSOLE_INIT_DONE:
 		/* Remove any consoles */
 		octeon_remove_consoles(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_IO_QUEUES_DONE:
 		if (lio_wait_for_instr_fetch(oct))
 			dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
@@ -1027,7 +1026,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		octeon_free_sc_done_list(oct);
 		octeon_free_sc_zombie_list(oct);
 
-	/* fallthrough */
+		fallthrough;
 	case OCT_DEV_INTR_SET_DONE:
 		/* Disable interrupts  */
 		oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
@@ -1062,17 +1061,17 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		kfree(oct->irq_name_storage);
 		oct->irq_name_storage = NULL;
 
-	/* fallthrough */
+		fallthrough;
 	case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
 		if (OCTEON_CN23XX_PF(oct))
 			octeon_free_ioq_vector(oct);
 
-	/* fallthrough */
+		fallthrough;
 	case OCT_DEV_MBOX_SETUP_DONE:
 		if (OCTEON_CN23XX_PF(oct))
 			oct->fn_list.free_mbox(oct);
 
-	/* fallthrough */
+		fallthrough;
 	case OCT_DEV_IN_RESET:
 	case OCT_DEV_DROQ_INIT_DONE:
 		/* Wait for any pending operations */
@@ -1095,11 +1094,11 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 			}
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_RESP_LIST_INIT_DONE:
 		octeon_delete_response_list(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_INSTR_QUEUE_INIT_DONE:
 		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
 			if (!(oct->io_qmask.iq & BIT_ULL(i)))
@@ -1110,16 +1109,16 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		if (oct->sriov_info.sriov_enabled)
 			pci_disable_sriov(oct->pci_dev);
 #endif
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_SC_BUFF_POOL_INIT_DONE:
 		octeon_free_sc_buffer_pool(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_DISPATCH_INIT_DONE:
 		octeon_delete_dispatch_list(oct);
 		cancel_delayed_work_sync(&oct->nic_poll_work.work);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_PCI_MAP_DONE:
 		refcount = octeon_deregister_device(oct);
 
@@ -1137,13 +1136,13 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_PCI_ENABLE_DONE:
 		pci_clear_master(oct->pci_dev);
 		/* Disable the device, releasing the PCI INT */
 		pci_disable_device(oct->pci_dev);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_BEGIN_STATE:
 		/* Nothing to be done here either */
 		break;
@@ -2168,7 +2167,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (lio->oct_dev->ptp_enable)
 			return hwtstamp_ioctl(netdev, ifr);
-		/* fall through */
+		fallthrough;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 90ef21086f27..8c5879e31240 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -460,9 +460,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		schedule_timeout_uninterruptible(HZ / 10);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_HOST_OK:
-		/* fallthrough */
 	case OCT_DEV_IO_QUEUES_DONE:
 		if (lio_wait_for_instr_fetch(oct))
 			dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
@@ -504,7 +503,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		octeon_free_sc_done_list(oct);
 		octeon_free_sc_zombie_list(oct);
 
-	/* fall through */
+		fallthrough;
 	case OCT_DEV_INTR_SET_DONE:
 		/* Disable interrupts  */
 		oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
@@ -533,15 +532,15 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		else
 			cn23xx_vf_ask_pf_to_do_flr(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
 		octeon_free_ioq_vector(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_MBOX_SETUP_DONE:
 		oct->fn_list.free_mbox(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_IN_RESET:
 	case OCT_DEV_DROQ_INIT_DONE:
 		mdelay(100);
@@ -551,11 +550,11 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 			octeon_delete_droq(oct, i);
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_RESP_LIST_INIT_DONE:
 		octeon_delete_response_list(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_INSTR_QUEUE_INIT_DONE:
 		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
 			if (!(oct->io_qmask.iq & BIT_ULL(i)))
@@ -563,27 +562,27 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 			octeon_delete_instr_queue(oct, i);
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_SC_BUFF_POOL_INIT_DONE:
 		octeon_free_sc_buffer_pool(oct);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_DISPATCH_INIT_DONE:
 		octeon_delete_dispatch_list(oct);
 		cancel_delayed_work_sync(&oct->nic_poll_work.work);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_PCI_MAP_DONE:
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_PCI_ENABLE_DONE:
 		pci_clear_master(oct->pci_dev);
 		/* Disable the device, releasing the PCI INT */
 		pci_disable_device(oct->pci_dev);
 
-		/* fallthrough */
+		fallthrough;
 	case OCT_DEV_BEGIN_STATE:
 		/* Nothing to be done here either */
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 83dabcffc789..c7bdac79299a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -522,7 +522,7 @@ static int nicvf_get_rss_hash_opts(struct nicvf *nic,
 	case SCTP_V4_FLOW:
 	case SCTP_V6_FLOW:
 		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* Fall through */
+		fallthrough;
 	case IPV4_FLOW:
 	case IPV6_FLOW:
 		info->data |= RXH_IP_SRC | RXH_IP_DST;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index c1378b5c780c..063e560d9c1b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -594,10 +594,10 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(action);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(nic->netdev, prog, action);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		/* Check if it's a recycled page, if not
 		 * unmap the DMA mapping.
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 42c6e9379882..387c357e1b8e 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2543,7 +2543,7 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 		    !(data->phy_id & 0xe0e0))
 			data->phy_id = mdio_phy_id_c45(data->phy_id >> 8,
 						       data->phy_id & 0x1f);
-		/* FALLTHRU */
+		fallthrough;
 	case SIOCGMIIPHY:
 		return mdio_mii_ioctl(&pi->phy.mdio, data, cmd);
 	case SIOCCHIOCTL:
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index b3e4118a15e7..9749d1239f58 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -136,7 +136,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
-		/* fall through */
+		fallthrough;
 	case L2T_STATE_VALID:	/* fast-path, send the packet on */
 		return cxgb3_ofld_send(dev, skb);
 	case L2T_STATE_RESOLVING:
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
index e3510e9b21f3..9a6d65243334 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
@@ -62,6 +62,7 @@ static struct thermal_zone_device_ops cxgb4_thermal_ops = {
 int cxgb4_thermal_init(struct adapter *adap)
 {
 	struct ch_thermal *ch_thermal = &adap->ch_thermal;
+	char ch_tz_name[THERMAL_NAME_LENGTH];
 	int num_trip = CXGB4_NUM_TRIPS;
 	u32 param, val;
 	int ret;
@@ -82,7 +83,8 @@ int cxgb4_thermal_init(struct adapter *adap)
 		ch_thermal->trip_type = THERMAL_TRIP_CRITICAL;
 	}
 
-	ch_thermal->tzdev = thermal_zone_device_register("cxgb4", num_trip,
+	snprintf(ch_tz_name, sizeof(ch_tz_name), "cxgb4_%s", adap->name);
+	ch_thermal->tzdev = thermal_zone_device_register(ch_tz_name, num_trip,
 							 0, adap,
 							 &cxgb4_thermal_ops,
 							 NULL, 0, 0);
@@ -105,7 +107,9 @@ int cxgb4_thermal_init(struct adapter *adap)
 
 int cxgb4_thermal_remove(struct adapter *adap)
 {
-	if (adap->ch_thermal.tzdev)
+	if (adap->ch_thermal.tzdev) {
 		thermal_zone_device_unregister(adap->ch_thermal.tzdev);
+		adap->ch_thermal.tzdev = NULL;
+	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index c4864125fe02..a10a6862a9a4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -231,7 +231,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
-		/* fall through */
+		fallthrough;
 	case L2T_STATE_VALID:     /* fast-path, send the packet on */
 		return t4_ofld_send(adap, skb);
 	case L2T_STATE_RESOLVING:
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index d2b587d1670a..869431a1eedd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2553,19 +2553,22 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev)
 
 	pkt_len = ETH_HLEN + sizeof(CXGB4_SELFTEST_LB_STR);
 
-	flits = DIV_ROUND_UP(pkt_len + sizeof(struct cpl_tx_pkt) +
-			     sizeof(*wr), sizeof(__be64));
+	flits = DIV_ROUND_UP(pkt_len + sizeof(*cpl) + sizeof(*wr),
+			     sizeof(__be64));
 	ndesc = flits_to_desc(flits);
 
 	lb = &pi->ethtool_lb;
 	lb->loopback = 1;
 
 	q = &adap->sge.ethtxq[pi->first_qset];
+	__netif_tx_lock(q->txq, smp_processor_id());
 
 	reclaim_completed_tx(adap, &q->q, -1, true);
 	credits = txq_avail(&q->q) - ndesc;
-	if (unlikely(credits < 0))
+	if (unlikely(credits < 0)) {
+		__netif_tx_unlock(q->txq);
 		return -ENOMEM;
+	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
 	memset(wr, 0, sizeof(struct tx_desc));
@@ -2598,6 +2601,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev)
 	init_completion(&lb->completion);
 	txq_advance(&q->q, ndesc);
 	cxgb4_ring_tx_db(adap, &q->q, ndesc);
+	__netif_tx_unlock(q->txq);
 
 	/* wait for the pkt to return */
 	ret = wait_for_completion_timeout(&lb->completion, 10 * HZ);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 8a56491bb034..fa3367966f4b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -7656,13 +7656,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		switch (nmac) {
 		case 5:
 			memcpy(mac + 24, c.nmac3, sizeof(c.nmac3));
-			/* Fall through */
+			fallthrough;
 		case 4:
 			memcpy(mac + 18, c.nmac2, sizeof(c.nmac2));
-			/* Fall through */
+			fallthrough;
 		case 3:
 			memcpy(mac + 12, c.nmac1, sizeof(c.nmac1));
-			/* Fall through */
+			fallthrough;
 		case 2:
 			memcpy(mac + 6,  c.nmac0, sizeof(c.nmac0));
 		}
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index dbe8ee7e0e21..e2fe78e2e242 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -517,7 +517,7 @@ static int fwevtq_handler(struct sge_rspq *rspq, const __be64 *rsp,
 		}
 		cpl = (void *)p;
 	}
-		/* Fall through */
+		fallthrough;
 
 	case CPL_SGE_EGR_UPDATE: {
 		/*
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 6bc7e7ba38c3..552d89fdf54a 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -272,7 +272,7 @@ static netdev_features_t enic_features_check(struct sk_buff *skb,
 	case ntohs(ETH_P_IPV6):
 		if (!(enic->vxlan.flags & ENIC_VXLAN_INNER_IPV6))
 			goto out;
-		/* Fall through */
+		fallthrough;
 	case ntohs(ETH_P_IP):
 		break;
 	default:
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 66e67b24a887..ffec0f3dd957 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2389,7 +2389,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	dev_info(dev, "probe %s ID %d\n", dev_name(dev), id);
 
-	netdev = alloc_etherdev_mq(sizeof(*port), TX_QUEUE_NUM);
+	netdev = devm_alloc_etherdev_mqs(dev, sizeof(*port), TX_QUEUE_NUM, TX_QUEUE_NUM);
 	if (!netdev) {
 		dev_err(dev, "Can't allocate ethernet device #%d\n", id);
 		return -ENOMEM;
@@ -2446,8 +2446,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	port->reset = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(port->reset)) {
 		dev_err(dev, "no reset\n");
-		clk_disable_unprepare(port->pclk);
-		return PTR_ERR(port->reset);
+		ret = PTR_ERR(port->reset);
+		goto unprepare;
 	}
 	reset_control_reset(port->reset);
 	usleep_range(100, 500);
@@ -2502,26 +2502,25 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 					IRQF_SHARED,
 					port_names[port->id],
 					port);
-	if (ret) {
-		clk_disable_unprepare(port->pclk);
-		return ret;
-	}
+	if (ret)
+		goto unprepare;
 
 	ret = register_netdev(netdev);
-	if (!ret) {
+	if (ret)
+		goto unprepare;
+
+	netdev_info(netdev,
+		    "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n",
+		    port->irq, &dmares->start,
+		    &gmacres->start);
+	ret = gmac_setup_phy(netdev);
+	if (ret)
 		netdev_info(netdev,
-			    "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n",
-			    port->irq, &dmares->start,
-			    &gmacres->start);
-		ret = gmac_setup_phy(netdev);
-		if (ret)
-			netdev_info(netdev,
-				    "PHY init failed, deferring to ifup time\n");
-		return 0;
-	}
+			    "PHY init failed, deferring to ifup time\n");
+	return 0;
 
-	port->netdev = NULL;
-	free_netdev(netdev);
+unprepare:
+	clk_disable_unprepare(port->pclk);
 	return ret;
 }
 
@@ -2530,7 +2529,6 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev)
 	struct gemini_ethernet_port *port = platform_get_drvdata(pdev);
 
 	gemini_port_remove(port);
-	free_netdev(port->netdev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 7f7705138262..5c6c8c5ec747 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -385,7 +385,7 @@ static void dm9000_set_io(struct board_info *db, int byte_width)
 
 	case 3:
 		dev_dbg(db->dev, ": 3 byte IO, falling back to 16bit\n");
-		/* fall through */
+		fallthrough;
 	case 2:
 		db->dumpblk = dm9000_dumpblk_16bit;
 		db->outblk  = dm9000_outblk_16bit;
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 0ccd9994ad45..f9dd1aa9f2da 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -3203,7 +3203,7 @@ srom_map_media(struct net_device *dev)
       case SROM_10BASETF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
-	/* fall through */
+	fallthrough;
 
       case SROM_10BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
@@ -3225,7 +3225,7 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASETF:
         if (!lp->params.fdx) return -1;
 	lp->fdx = true;
-	/* fall through */
+	fallthrough;
 
       case SROM_100BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
@@ -3239,7 +3239,7 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASEFF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
-	/* fall through */
+	fallthrough;
 
       case SROM_100BASEF:
 	if (lp->params.fdx && !lp->fdx) return -1;
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 9db23527275a..3a8659c5da06 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -911,7 +911,7 @@ static int private_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
 			data->phy_id = 1;
 		else
 			return -ENODEV;
-		/* Fall through */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		if (data->phy_id == 32 && (tp->flags & HAS_NWAY)) {
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 5dcc66f60144..5a43be327f58 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -1443,7 +1443,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch(cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = ((struct netdev_private *)netdev_priv(dev))->phys[0] & 0x1f;
-		/* Fall Through */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		spin_lock_irq(&np->lock);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index d6ed1d943762..99cc1c46fb30 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -571,7 +571,7 @@ static u32 convert_to_et_setting(struct be_adapter *adapter, u32 if_speeds)
 				break;
 			}
 		}
-		/* fall through */
+		fallthrough;
 	case PHY_TYPE_SFP_PLUS_10GB:
 	case PHY_TYPE_XFP_10GB:
 	case PHY_TYPE_SFP_1GB:
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 43570f4911ea..fdff3b4723ba 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -945,7 +945,7 @@ static void dpaa_fq_setup(struct dpaa_priv *priv,
 			break;
 		case FQ_TYPE_TX_CONF_MQ:
 			priv->conf_fqs[conf_cnt++] = &fq->fq_base;
-			/* fall through */
+			fallthrough;
 		case FQ_TYPE_TX_CONFIRM:
 			dpaa_setup_ingress(priv, fq, &fq_cbs->tx_defq);
 			break;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 9db2a02fb531..1268996b7030 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -375,7 +375,7 @@ static int dpaa_get_hash_opts(struct net_device *dev,
 	case UDP_V6_FLOW:
 		if (priv->keygen_in_use)
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* Fall through */
+		fallthrough;
 	case IPV4_FLOW:
 	case IPV6_FLOW:
 	case SCTP_V4_FLOW:
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 457106e761be..cf5383bb8331 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -376,10 +376,10 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(xdp_act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		xdp_release_buf(priv, ch, addr);
 		ch->stats.xdp_drop++;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 9934421814b4..fb37816a74db 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3715,11 +3715,11 @@ failed_mii_init:
 failed_irq:
 failed_init:
 	fec_ptp_stop(pdev);
-	if (fep->reg_phy)
-		regulator_disable(fep->reg_phy);
 failed_reset:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	if (fep->reg_phy)
+		regulator_disable(fep->reg_phy);
 failed_regulator:
 	clk_disable_unprepare(fep->clk_ahb);
 failed_clk_ahb:
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 645764abdaae..bb9887f98841 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -528,7 +528,7 @@ static void setup_sgmii_internal_phy(struct fman_mac *memac,
 		case 100:
 			tmp_reg16 |= IF_MODE_SGMII_SPEED_100M;
 		break;
-		case 1000: /* fallthrough */
+		case 1000:
 		default:
 			tmp_reg16 |= IF_MODE_SGMII_SPEED_1G;
 		break;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index c27df153f895..624b2eb6f01d 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1344,10 +1344,10 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 	switch (port->port_type) {
 	case FMAN_PORT_TYPE_RX:
 		set_rx_dflt_cfg(port, params);
-		/* fall through */
+		fallthrough;
 	case FMAN_PORT_TYPE_TX:
 		set_tx_dflt_cfg(port, params, &port->dts_params);
-		/* fall through */
+		fallthrough;
 	default:
 		set_dflt_cfg(port, params);
 	}
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index b513b8c5c3b5..41dd3d0f3452 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -750,8 +750,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 				continue;
 
 			err = gfar_parse_group(child, priv, model);
-			if (err)
+			if (err) {
+				of_node_put(child);
 				goto err_grp_init;
+			}
 		}
 	} else { /* SQ_SG_MODE */
 		err = gfar_parse_group(np, priv, model);
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index db791f60b884..714b501be7d0 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1348,7 +1348,7 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth)
 		switch (ugeth->max_speed) {
 		case SPEED_10:
 			upsmr |= UCC_GETH_UPSMR_R10M;
-			/* FALLTHROUGH */
+			fallthrough;
 		case SPEED_100:
 			if (ugeth->phy_interface != PHY_INTERFACE_MODE_RTBI)
 				upsmr |= UCC_GETH_UPSMR_RMM;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 23f278e46975..22522f8a5299 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2282,8 +2282,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			priv->enet_ver = AE_VERSION_1;
 		else if (acpi_dev_found(hns_enet_acpi_match[1].id))
 			priv->enet_ver = AE_VERSION_2;
-		else
-			return -ENXIO;
+		else {
+			ret = -ENXIO;
+			goto out_read_prop_fail;
+		}
 
 		/* try to find port-idx-in-ae first */
 		ret = acpi_node_get_property_reference(dev->fwnode,
@@ -2299,7 +2301,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		priv->fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto out_read_prop_fail;
 	}
 
 	ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 49624acf2473..4eb50296f653 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -305,7 +305,7 @@ static int __lb_setup(struct net_device *ndev,
 		break;
 	case MAC_LOOP_PHY_NONE:
 		ret = hns_nic_config_phy_loopback(phy_dev, 0x0);
-		/* fall through */
+		fallthrough;
 	case MAC_LOOP_NONE:
 		if (!ret && h->dev->ops->set_loopback) {
 			if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 87776ce3539b..a4f1d515e5e0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -21,6 +21,7 @@
 #include <net/pkt_cls.h>
 #include <net/tcp.h>
 #include <net/vxlan.h>
+#include <net/geneve.h>
 
 #include "hnae3.h"
 #include "hns3_enet.h"
@@ -780,7 +781,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
  * and it is udp packet, which has a dest port as the IANA assigned.
  * the hardware is expected to do the checksum offload, but the
  * hardware will not do the checksum offload when udp dest port is
- * 4789.
+ * 4789 or 6081.
  */
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
@@ -789,7 +790,8 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 	l4.hdr = skb_transport_header(skb);
 
 	if (!(!skb->encapsulation &&
-	      l4.udp->dest == htons(IANA_VXLAN_UDP_PORT)))
+	      (l4.udp->dest == htons(IANA_VXLAN_UDP_PORT) ||
+	      l4.udp->dest == htons(GENEVE_UDP_PORT))))
 		return false;
 
 	skb_checksum_help(skb);
@@ -2746,7 +2748,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	case HNS3_OL4_TYPE_MAC_IN_UDP:
 	case HNS3_OL4_TYPE_NVGRE:
 		skb->csum_level = 1;
-		/* fall through */
+		fallthrough;
 	case HNS3_OL4_TYPE_NO_TUN:
 		l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
 					  HNS3_RXD_L3ID_S);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 36575e72a915..d553ed7ee64c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3061,7 +3061,7 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 		 *    by first decoding the types of errors.
 		 */
 		set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request);
-		/* fall through */
+		fallthrough;
 	case HCLGE_VECTOR0_EVENT_RST:
 		hclge_reset_task_schedule(hdev);
 		break;
@@ -3686,12 +3686,10 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev)
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
-		/* fall through */
 	case HNAE3_FLR_RESET:
 		ret = hclge_set_all_vf_rst(hdev, false);
 		break;
 	case HNAE3_GLOBAL_RESET:
-		/* fall through */
 	case HNAE3_IMP_RESET:
 		ret = hclge_set_rst_done(hdev);
 		break;
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 0273fb7a9d01..3153d62cc73e 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3247,7 +3247,7 @@ static int ehea_mem_notifier(struct notifier_block *nb,
 	switch (action) {
 	case MEM_CANCEL_OFFLINE:
 		pr_info("memory offlining canceled");
-		/* Fall through - re-add canceled memory block */
+		fallthrough;	/* re-add canceled memory block */
 
 	case MEM_ONLINE:
 		pr_info("memory is going online");
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 06248a7db7f2..c00b9097eeea 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2319,7 +2319,7 @@ static int emac_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:
 		data->phy_id = dev->phy.address;
-		/* Fall through */
+		fallthrough;
 	case SIOCGMIIREG:
 		data->val_out = emac_mdio_read(ndev, dev->phy.address,
 					       data->reg_num);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5afb3c9c52d2..d3a774331afc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -479,6 +479,9 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter)
 	int i, j, rc;
 	u64 *size_array;
 
+	if (!adapter->rx_pool)
+		return -1;
+
 	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 		be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
 
@@ -649,6 +652,9 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter)
 	int tx_scrqs;
 	int i, rc;
 
+	if (!adapter->tx_pool)
+		return -1;
+
 	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
 	for (i = 0; i < tx_scrqs; i++) {
 		rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]);
@@ -2011,7 +2017,10 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 		    adapter->req_rx_add_entries_per_subcrq !=
 		    old_num_rx_slots ||
 		    adapter->req_tx_entries_per_subcrq !=
-		    old_num_tx_slots) {
+		    old_num_tx_slots ||
+		    !adapter->rx_pool ||
+		    !adapter->tso_pool ||
+		    !adapter->tx_pool) {
 			release_rx_pools(adapter);
 			release_tx_pools(adapter);
 			release_napi(adapter);
@@ -2024,10 +2033,14 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 		} else {
 			rc = reset_tx_pools(adapter);
 			if (rc)
+				netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n",
+						rc);
 				goto out;
 
 			rc = reset_rx_pools(adapter);
 			if (rc)
+				netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n",
+						rc);
 				goto out;
 		}
 		ibmvnic_disable_irqs(adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 63dde3bcf5bc..664e8ccc88d2 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -4079,7 +4079,6 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
-		fallthrough;
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 		fc->refresh_time = 0xFFFF;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index a62ddd626929..c0c8efe42fce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -981,7 +981,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes {
 #define I40E_AQC_SET_VSI_PROMISC_BROADCAST	0x04
 #define I40E_AQC_SET_VSI_DEFAULT		0x08
 #define I40E_AQC_SET_VSI_PROMISC_VLAN		0x10
-#define I40E_AQC_SET_VSI_PROMISC_TX		0x8000
+#define I40E_AQC_SET_VSI_PROMISC_RX_ONLY	0x8000
 	__le16	seid;
 	__le16	vlan_tag;
 #define I40E_AQC_SET_VSI_VLAN_VALID		0x8000
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index afad5e9f80e0..6ab52cbd697a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1967,6 +1967,21 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 }
 
 /**
+ * i40e_is_aq_api_ver_ge
+ * @aq: pointer to AdminQ info containing HW API version to compare
+ * @maj: API major value
+ * @min: API minor value
+ *
+ * Assert whether current HW API version is greater/equal than provided.
+ **/
+static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj,
+				  u16 min)
+{
+	return (aq->api_maj_ver > maj ||
+		(aq->api_maj_ver == maj && aq->api_min_ver >= min));
+}
+
+/**
  * i40e_aq_add_vsi
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -2091,18 +2106,16 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 
 	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
-		if (rx_only_promisc &&
-		    (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) ||
-		     (hw->aq.api_maj_ver > 1)))
-			flags |= I40E_AQC_SET_VSI_PROMISC_TX;
+		if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
 	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
-	if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) ||
-	    (hw->aq.api_maj_ver > 1))
-		cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX);
+	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		cmd->valid_flags |=
+			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 
 	cmd->seid = cpu_to_le16(seid);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2199,11 +2212,17 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
-	if (enable)
+	if (enable) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
+		if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
+	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
+	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		cmd->valid_flags |=
+			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 	cmd->seid = cpu_to_le16(seid);
 	cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b5399357a667..2e433fdbf2c3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -15463,6 +15463,9 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
+	while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+		usleep_range(1000, 2000);
+
 	/* no more scheduling of any task */
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4f05f6efe6af..d9c3a6b169f9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -718,7 +718,6 @@ static void igb_cache_ring_register(struct igb_adapter *adapter)
 	case e1000_i354:
 	case e1000_i210:
 	case e1000_i211:
-		fallthrough;
 	default:
 		for (; i < adapter->num_rx_queues; i++)
 			adapter->rx_ring[i]->reg_idx = rbase_offset + i;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 7a6f2a0d413f..9593aa4eea36 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -5142,6 +5142,8 @@ static int igc_probe(struct pci_dev *pdev,
 	device_set_wakeup_enable(&adapter->pdev->dev,
 				 adapter->flags & IGC_FLAG_WOL_SUPPORTED);
 
+	igc_ptp_init(adapter);
+
 	/* reset the hardware with the new settings */
 	igc_reset(adapter);
 
@@ -5158,9 +5160,6 @@ static int igc_probe(struct pci_dev *pdev,
 	 /* carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
-	/* do hw tstamp init after resetting */
-	igc_ptp_init(adapter);
-
 	/* Check if Media Autosense is enabled */
 	adapter->ei = *ei;
 
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index e67d4655b47e..36c999250fcc 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -496,8 +496,6 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 
-	igc_ptp_reset(adapter);
-
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index e67b1a59ecb7..0fcd82036d4e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -193,7 +193,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid,
 	}
 
 	/* alloc the udl from per cpu ddp pool */
-	ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_KERNEL, &ddp->udp);
+	ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp);
 	if (!ddp->udl) {
 		e_err(drv, "failed allocated ddp context\n");
 		goto out_noddp_unmap;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 832bbb8b05c8..dfcb1767acbb 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2205,10 +2205,10 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(pp->dev, prog, act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		mvneta_xdp_put_buff(pp, rxq, xdp, sync, true);
 		ret = MVNETA_XDP_DROPPED;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index d4a4e241333d..41d935d1aaf6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1638,7 +1638,7 @@ int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
 		if (info->data & RXH_L4_B_2_3)
 			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
-		/* Fallthrough */
+		fallthrough;
 	case MVPP22_FLOW_IP4:
 	case MVPP22_FLOW_IP6:
 		if (info->data & RXH_L2DA)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2a8a5842eaef..6e140d1b8967 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5437,7 +5437,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
 		}
 		if (state->interface != PHY_INTERFACE_MODE_NA)
 			break;
-		/* Fall-through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
@@ -5451,7 +5451,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
 		phylink_set(mask, 1000baseX_Full);
 		if (state->interface != PHY_INTERFACE_MODE_NA)
 			break;
-		/* Fall-through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_1000BASEX:
 	case PHY_INTERFACE_MODE_2500BASEX:
 		if (port->comphy ||
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 36953d4f51c7..01a793105599 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -737,7 +737,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 		else if (req->ctype == NIX_AQ_CTYPE_MCE)
 			memcpy(mask, &req->mce_mask,
 			       sizeof(struct nix_rx_mce_s));
-		/* Fall through */
+		fallthrough;
 	case NIX_AQ_INSTOP_INIT:
 		if (req->ctype == NIX_AQ_CTYPE_RQ)
 			memcpy(ctx, &req->rq, sizeof(struct nix_rq_ctx_s));
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 5975521a4c86..93c4cf7fedbf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1226,8 +1226,8 @@ int otx2_config_npa(struct otx2_nic *pfvf)
 	if (!hw->pool_cnt)
 		return -EINVAL;
 
-	qset->pool = devm_kzalloc(pfvf->dev, sizeof(struct otx2_pool) *
-				  hw->pool_cnt, GFP_KERNEL);
+	qset->pool = devm_kcalloc(pfvf->dev, hw->pool_cnt,
+				  sizeof(struct otx2_pool), GFP_KERNEL);
 	if (!qset->pool)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index b792f6306a64..6a930351cb23 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -2448,7 +2448,7 @@ static int skge_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		data->phy_id = hw->phy_addr;
 
-		/* fallthru */
+		fallthrough;
 	case SIOCGMIIREG: {
 		u16 val = 0;
 		spin_lock_bh(&hw->phy_lock);
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index cec8124301c7..344864275ed5 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1376,7 +1376,7 @@ static int sky2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 		data->phy_id = PHY_ADDR_MARV;
 
-		/* fallthru */
+		fallthrough;
 	case SIOCGMIIREG: {
 		u16 val = 0;
 
@@ -2764,7 +2764,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do, u16 idx)
 
 		case OP_RXCHKSVLAN:
 			sky2_rx_tag(sky2, length);
-			/* fall through */
+			fallthrough;
 		case OP_RXCHKS:
 			if (likely(dev->features & NETIF_F_RXCSUM))
 				sky2_rx_checksum(sky2, status);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 0870fe78ea38..6d2d60675ffd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -228,7 +228,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			if (!MTK_HAS_CAPS(mac->hw->soc->caps,
 					  MTK_GMAC1_TRGMII))
 				goto err_phy;
-			/* fall through */
+			fallthrough;
 		case PHY_INTERFACE_MODE_RGMII_TXID:
 		case PHY_INTERFACE_MODE_RGMII_RXID:
 		case PHY_INTERFACE_MODE_RGMII_ID:
@@ -501,11 +501,11 @@ static void mtk_validate(struct phylink_config *config,
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		phylink_set(mask, 1000baseT_Half);
-		/* fall through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_SGMII:
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseX_Full);
-		/* fall through */
+		fallthrough;
 	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_RMII:
 	case PHY_INTERFACE_MODE_REVMII:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index d2986f1f2db0..d7444782bfdd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -114,7 +114,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 		goto err_out;
 
 	for (i = 0; i <= buddy->max_order; ++i) {
-		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
+		s = BITS_TO_LONGS(1UL << (buddy->max_order - i));
 		buddy->bits[i] = kvmalloc_array(s, sizeof(long), GFP_KERNEL | __GFP_ZERO);
 		if (!buddy->bits[i])
 			goto err_out_free;
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 7a04c626a2aa..bcd166911d44 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -72,7 +72,7 @@ static int mlxfw_fsm_state_err(struct mlxfw_dev *mlxfw_dev,
 	case MLXFW_FSM_STATE_ERR_BLOCKED_PENDING_RESET:
 		MLXFW_ERR_MSG(mlxfw_dev, extack, "pending reset", err);
 		break;
-	case MLXFW_FSM_STATE_ERR_OK: /* fall through */
+	case MLXFW_FSM_STATE_ERR_OK:
 	case MLXFW_FSM_STATE_ERR_MAX:
 		MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown error", err);
 		break;
@@ -155,7 +155,7 @@ mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev,
 	case MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED:
 		MLXFW_REACT_ERR("fw already activated", err);
 		break;
-	case MLXFW_FSM_REACTIVATE_STATUS_OK: /* fall through */
+	case MLXFW_FSM_REACTIVATE_STATUS_OK:
 	case MLXFW_FSM_REACTIVATE_STATUS_MAX:
 		MLXFW_REACT_ERR("unexpected error", err);
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 08d101138fbe..ec45a03140d7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -2289,21 +2289,21 @@ int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module)
 	/* Here we need to get the module width according to the module type. */
 
 	switch (module_type) {
-	case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: /* fall through */
-	case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: /* fall through */
+	case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X:
+	case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD:
 	case MLXSW_REG_PMTM_MODULE_TYPE_OSFP:
 		return 8;
-	case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: /* fall through */
-	case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: /* fall through */
+	case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X:
+	case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X:
 	case MLXSW_REG_PMTM_MODULE_TYPE_QSFP:
 		return 4;
-	case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: /* fall through */
-	case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: /* fall through */
-	case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: /* fall through */
+	case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X:
+	case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X:
+	case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD:
 	case MLXSW_REG_PMTM_MODULE_TYPE_DSFP:
 		return 2;
-	case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: /* fall through */
-	case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: /* fall through */
+	case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X:
+	case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X:
 	case MLXSW_REG_PMTM_MODULE_TYPE_SFP:
 		return 1;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 44fa02cbb683..056eeb85be60 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -30,8 +30,8 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
 	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
 		*qsfp = false;
 		break;
-	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */
-	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP:
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
 	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
 		*qsfp = true;
 		break;
@@ -205,7 +205,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
 		modinfo->type       = ETH_MODULE_SFF_8436;
 		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		break;
-	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
 	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
 		if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 ||
 		    module_rev_id >=
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 3fe878d7c94c..61719ec89808 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -259,8 +259,8 @@ static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev,
 		 */
 		fault = 1;
 		break;
-	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
-	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_NO_CONN:
+	case MLXSW_REG_MTBR_NO_TEMP_SENS:
 	case MLXSW_REG_MTBR_INDEX_NA:
 	default:
 		fault = 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index fdf9aa8314b2..4186e29119c2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -517,8 +517,8 @@ enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state)
 		return MLXSW_REG_SPMS_STATE_FORWARDING;
 	case BR_STATE_LEARNING:
 		return MLXSW_REG_SPMS_STATE_LEARNING;
-	case BR_STATE_LISTENING: /* fall-through */
-	case BR_STATE_DISABLED: /* fall-through */
+	case BR_STATE_LISTENING:
+	case BR_STATE_DISABLED:
 	case BR_STATE_BLOCKING:
 		return MLXSW_REG_SPMS_STATE_DISCARDING;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f9ba59641b4d..5240bf11b6c4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -636,11 +636,11 @@ static inline unsigned int
 mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type)
 {
 	switch (type) {
-	case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: /* fall through */
-	case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: /* fall through */
-	case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: /* fall through */
-	case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: /* fall through */
-	case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ:
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET:
+	case MLXSW_SP_KVDL_ENTRY_TYPE_PBS:
+	case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR:
+	case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT:
 	default:
 		return 1;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0521e9d48c45..24f1fd1f8d56 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1164,7 +1164,7 @@ mlxsw_sp_router_ip2me_fib_entry_find(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
 		addr_len = 4;
 		addr_prefix_len = 32;
 		break;
-	case MLXSW_SP_L3_PROTO_IPV6: /* fall through */
+	case MLXSW_SP_L3_PROTO_IPV6:
 	default:
 		WARN_ON(1);
 		return NULL;
@@ -4555,14 +4555,14 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 			fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP;
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	case RTN_BROADCAST:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
 		return 0;
 	case RTN_BLACKHOLE:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
 		return 0;
-	case RTN_UNREACHABLE: /* fall through */
+	case RTN_UNREACHABLE:
 	case RTN_PROHIBIT:
 		/* Packets hitting these routes need to be trapped, but
 		 * can do so with a lower priority than packets directed
@@ -5990,7 +5990,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work)
 		mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
 		fib_info_put(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_ADD:
 	case FIB_EVENT_NH_DEL:
 		mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event,
 					fib_work->fnh_info.fib_nh);
@@ -6050,7 +6050,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work)
 	rtnl_lock();
 	mutex_lock(&mlxsw_sp->router->lock);
 	switch (fib_work->event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_ADD:
 		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
 
@@ -6089,7 +6089,7 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
 	struct fib_nh_notifier_info *fnh_info;
 
 	switch (fib_work->event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_DEL:
 		fen_info = container_of(info, struct fib_entry_notifier_info,
 					info);
@@ -6099,7 +6099,7 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_ADD:
 	case FIB_EVENT_NH_DEL:
 		fnh_info = container_of(info, struct fib_nh_notifier_info,
 					info);
@@ -6116,8 +6116,8 @@ static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
 	int err;
 
 	switch (fib_work->event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
-	case FIB_EVENT_ENTRY_APPEND: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
+	case FIB_EVENT_ENTRY_APPEND:
 	case FIB_EVENT_ENTRY_DEL:
 		fen6_info = container_of(info, struct fib6_entry_notifier_info,
 					 info);
@@ -6136,13 +6136,13 @@ mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work,
 			    struct fib_notifier_info *info)
 {
 	switch (fib_work->event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
-	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
+	case FIB_EVENT_ENTRY_ADD:
 	case FIB_EVENT_ENTRY_DEL:
 		memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info));
 		mr_cache_hold(fib_work->men_info.mfc);
 		break;
-	case FIB_EVENT_VIF_ADD: /* fall through */
+	case FIB_EVENT_VIF_ADD:
 	case FIB_EVENT_VIF_DEL:
 		memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info));
 		dev_hold(fib_work->ven_info.dev);
@@ -6215,13 +6215,13 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	router = container_of(nb, struct mlxsw_sp_router, fib_nb);
 
 	switch (event) {
-	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_ADD:
 	case FIB_EVENT_RULE_DEL:
 		err = mlxsw_sp_router_fib_rule_event(event, info,
 						     router->mlxsw_sp);
 		return notifier_from_errno(err);
-	case FIB_EVENT_ENTRY_ADD: /* fall through */
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_ADD:
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_APPEND:
 		if (router->aborted) {
 			NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
@@ -7277,7 +7277,7 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
 		goto out;
 
 	switch (event) {
-	case NETDEV_CHANGEMTU: /* fall through */
+	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGEADDR:
 		err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif);
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 5c959a995199..1d18e41ab255 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -1523,12 +1523,12 @@ mlxsw_sp_span_trigger_ops_set(struct mlxsw_sp_span_trigger_entry *trigger_entry)
 	enum mlxsw_sp_span_trigger_type type;
 
 	switch (trigger_entry->trigger) {
-	case MLXSW_SP_SPAN_TRIGGER_INGRESS: /* fall-through */
+	case MLXSW_SP_SPAN_TRIGGER_INGRESS:
 	case MLXSW_SP_SPAN_TRIGGER_EGRESS:
 		type = MLXSW_SP_SPAN_TRIGGER_TYPE_PORT;
 		break;
-	case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: /* fall-through */
-	case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: /* fall-through */
+	case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP:
+	case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP:
 	case MLXSW_SP_SPAN_TRIGGER_ECN:
 		type = MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index a26162b08b7d..72912afa6f72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1297,7 +1297,7 @@ static int mlxsw_sp_port_fdb_tunnel_uc_op(struct mlxsw_sp *mlxsw_sp,
 		uip = be32_to_cpu(addr->addr4);
 		sfd_proto = MLXSW_REG_SFD_UC_TUNNEL_PROTOCOL_IPV4;
 		break;
-	case MLXSW_SP_L3_PROTO_IPV6: /* fall through */
+	case MLXSW_SP_L3_PROTO_IPV6:
 	default:
 		WARN_ON(1);
 		return -EOPNOTSUPP;
@@ -2870,7 +2870,7 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work)
 		fdb_info = &switchdev_work->fdb_info;
 		mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false);
 		break;
-	case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
+	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 	case SWITCHDEV_FDB_DEL_TO_BRIDGE:
 		/* These events are only used to potentially update an existing
 		 * SPAN mirror.
@@ -3116,9 +3116,9 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 	switchdev_work->event = event;
 
 	switch (event) {
-	case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */
-	case SWITCHDEV_FDB_DEL_TO_DEVICE: /* fall through */
-	case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 	case SWITCHDEV_FDB_DEL_TO_BRIDGE:
 		fdb_info = container_of(info,
 					struct switchdev_notifier_fdb_info,
@@ -3138,7 +3138,7 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 		 */
 		dev_hold(dev);
 		break;
-	case SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE: /* fall through */
+	case SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE:
 		INIT_WORK(&switchdev_work->work,
 			  mlxsw_sp_switchdev_vxlan_fdb_event_work);
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index c533d06fbe3a..dcde496da7fb 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -548,7 +548,7 @@ static int lan743x_ethtool_get_rxnfc(struct net_device *netdev,
 		case TCP_V4_FLOW:case UDP_V4_FLOW:
 		case TCP_V6_FLOW:case UDP_V6_FLOW:
 			rxnfc->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			/* fall through */
+			fallthrough;
 		case IPV4_FLOW: case IPV6_FLOW:
 			rxnfc->data |= RXH_IP_SRC | RXH_IP_DST;
 			return 0;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 867c680f5917..5abb7d2b0a9e 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -859,7 +859,7 @@ void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state)
 	switch (state) {
 	case BR_STATE_FORWARDING:
 		ocelot->bridge_fwd_mask |= BIT(port);
-		/* Fallthrough */
+		fallthrough;
 	case BR_STATE_LEARNING:
 		port_cfg |= ANA_PORT_PORT_CFG_LEARN_ENA;
 		break;
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index c2867fe995bc..3de8430ee8c5 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -3081,7 +3081,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch(cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = np->phy_addr_external;
-		/* Fall Through */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		/* The phy_id is not enough to uniquely identify
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 4f1f90f5e178..78eba10300ae 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -3768,20 +3768,20 @@ vxge_hw_rts_rth_data0_data1_get(u32 j, u64 *data0, u64 *data1,
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
-		/* fall through */
+		fallthrough;
 	case 2:
 		*data0 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA(
 			itable[j]);
-		/* fall through */
+		fallthrough;
 	case 3:
 		*data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
-		/* fall through */
+		fallthrough;
 	case 4:
 		*data1 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(j)|
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/tls.c b/drivers/net/ethernet/netronome/nfp/crypto/tls.c
index 7c50e3dfb9d5..76c51da5b66f 100644
--- a/drivers/net/ethernet/netronome/nfp/crypto/tls.c
+++ b/drivers/net/ethernet/netronome/nfp/crypto/tls.c
@@ -296,7 +296,7 @@ nfp_net_tls_add(struct net_device *netdev, struct sock *sk,
 			break;
 		}
 #endif
-		/* fall through */
+		fallthrough;
 	case AF_INET:
 		req_sz = sizeof(struct nfp_crypto_req_add_v4);
 		ipv6 = false;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index ff844e5cc41f..1cbe2c9f3959 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -297,7 +297,7 @@ nfp_fl_get_tun_from_act(struct nfp_app *app,
 	case htons(GENEVE_UDP_PORT):
 		if (priv->flower_ext_feats & NFP_FL_FEATS_GENEVE)
 			return NFP_FL_TUNNEL_GENEVE;
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		return NFP_FL_TUNNEL_NONE;
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index a050cb898782..f21cf1f40f98 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -289,7 +289,7 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 			skb_stored = nfp_flower_lag_unprocessed_msg(app, skb);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 err_default:
 		nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 4651fe417b7f..36356f96661d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -784,7 +784,7 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len,
 		case NFP_FL_ACTION_OPCODE_PRE_TUNNEL:
 			if (tunnel_act)
 				*tunnel_act = true;
-			/* fall through */
+			fallthrough;
 		case NFP_FL_ACTION_OPCODE_PRE_LAG:
 			memcpy(act_dst + act_off, act_src + act_off, act_len);
 			break;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 2df3deedf9fd..7248d248f604 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -61,6 +61,7 @@ struct nfp_tun_active_tuns {
  * @flags:		options part of the request
  * @tun_info.ipv6:		dest IPv6 address of active route
  * @tun_info.egress_port:	port the encapsulated packet egressed
+ * @tun_info.extra:		reserved for future use
  * @tun_info:		tunnels that have sent traffic in reported period
  */
 struct nfp_tun_active_tuns_v6 {
@@ -70,6 +71,7 @@ struct nfp_tun_active_tuns_v6 {
 	struct route_ip_info_v6 {
 		struct in6_addr ipv6;
 		__be32 egress_port;
+		__be32 extra[2];
 	} tun_info[];
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
index b04b83687fe2..2643ea5948f4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
@@ -137,7 +137,7 @@ static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst)
 				val;
 		case NN_LM_MOD_DEC:
 			lm_dec = true;
-			/* fall through */
+			fallthrough;
 		case NN_LM_MOD_INC:
 			if (val) {
 				pr_err("LM offset in inc/dev mode\n");
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 39ee23e8c0bf..21ea22694e47 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1940,10 +1940,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 				continue;
 			default:
 				bpf_warn_invalid_xdp_action(act);
-				/* fall through */
+				fallthrough;
 			case XDP_ABORTED:
 				trace_xdp_exception(dp->netdev, xdp_prog, act);
-				/* fall through */
+				fallthrough;
 			case XDP_DROP:
 				nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
 						    rxbuf->dma_addr);
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index a486008eb80a..252fe06f58aa 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -340,12 +340,12 @@ static int matching_bar(struct nfp_bar *bar, u32 tgt, u32 act, u32 tok,
 	switch (maptype) {
 	case NFP_PCIE_BAR_PCIE2CPP_MapType_TARGET:
 		bartok = -1;
-		/* FALLTHROUGH */
+		fallthrough;
 	case NFP_PCIE_BAR_PCIE2CPP_MapType_BULK:
 		baract = NFP_CPP_ACTION_RW;
 		if (act == 0)
 			act = NFP_CPP_ACTION_RW;
-		/* FALLTHROUGH */
+		fallthrough;
 	case NFP_PCIE_BAR_PCIE2CPP_MapType_FIXED:
 		break;
 	default:
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c
index 75f012444796..2260c2403a83 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c
@@ -213,7 +213,7 @@ u64 nfp_rtsym_size(const struct nfp_rtsym *sym)
 		return 0;
 	default:
 		pr_warn("rtsym '%s': unknown type: %d\n", sym->name, sym->type);
-		/* fall through */
+		fallthrough;
 	case NFP_RTSYM_TYPE_OBJECT:
 	case NFP_RTSYM_TYPE_FUNCTION:
 		return sym->size;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
index a26966fa40b9..dceec80fd642 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
@@ -410,7 +410,7 @@ static void pch_gbe_check_copper_options(struct pch_gbe_adapter *adapter)
 	case SPEED_1000 + HALF_DUPLEX:
 		netdev_dbg(adapter->netdev,
 			   "Half Duplex is not supported at 1000 Mbps\n");
-		/* fall through */
+		fallthrough;
 	case SPEED_1000 + FULL_DUPLEX:
 full_duplex_only:
 		netdev_dbg(adapter->netdev,
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 647a1431b359..3da075307178 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -1356,7 +1356,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch(cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = np->phys[0] & 0x1f;
-		/* Fall Through */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		data->val_out = mdio_read(ioaddr, data->phy_id & 0x1f, data->reg_num & 0x1f);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 8107d32c2767..def65fee27b5 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -496,9 +496,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	struct ionic_cq *txcq;
 	u32 rx_work_done = 0;
 	u32 tx_work_done = 0;
-	u32 work_done = 0;
 	u32 flags = 0;
-	bool unmask;
 
 	lif = rxcq->bound_q->lif;
 	idev = &lif->ionic->idev;
@@ -512,17 +510,12 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	if (rx_work_done)
 		ionic_rx_fill_cb(rxcq->bound_q);
 
-	unmask = (rx_work_done < budget) && (tx_work_done < lif->tx_budget);
-
-	if (unmask && napi_complete_done(napi, rx_work_done)) {
+	if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
 		flags |= IONIC_INTR_CRED_UNMASK;
 		DEBUG_STATS_INTR_REARM(rxcq->bound_intr);
-		work_done = rx_work_done;
-	} else {
-		work_done = budget;
 	}
 
-	if (work_done || flags) {
+	if (rx_work_done || flags) {
 		flags |= IONIC_INTR_CRED_RESET_COALESCE;
 		ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index,
 				   tx_work_done + rx_work_done, flags);
@@ -531,7 +524,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	DEBUG_STATS_NAPI_POLL(qcq, rx_work_done);
 	DEBUG_STATS_NAPI_POLL(qcq, tx_work_done);
 
-	return work_done;
+	return rx_work_done;
 }
 
 static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index 66f45fce90fa..c3f50ddbe824 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -153,7 +153,7 @@ skip:
 	case NETXEN_BRDTYPE_P3_4_GB_MM:
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
-		/* fall through */
+		fallthrough;
 	case NETXEN_BRDTYPE_P2_SB31_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4_LP:
@@ -182,7 +182,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(dev) &&
 			adapter->has_link_events;
-		/* fall through */
+		fallthrough;
 	case NETXEN_BRDTYPE_P2_SB31_10G:
 	case NETXEN_BRDTYPE_P3_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 876743a79c1f..0e4cd8890cff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -2046,7 +2046,7 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 					       rdma_tasks);
 		/* no need for break since RoCE coexist with Ethernet */
 	}
-	/* fall through */
+		fallthrough;
 	case QED_PCI_ETH:
 	{
 		struct qed_eth_pf_params *p_params =
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index b3c9ebaf2280..b8f076e4e6b8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3109,14 +3109,14 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 						p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
-		/* Fall through */
+			fallthrough;
 		case FW_MSG_CODE_DRV_LOAD_PORT:
 			rc = qed_hw_init_port(p_hwfn, p_hwfn->p_main_ptt,
 					      p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
 
-		/* Fall through */
+			fallthrough;
 		case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 			rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
 					    p_params->p_tunn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 2558cb680db3..f39f629242a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -761,7 +761,7 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode)
 		kfree(int_params->msix_table);
 		if (force_mode)
 			goto out;
-		/* Fallthrough */
+		fallthrough;
 
 	case QED_INT_MODE_MSI:
 		if (cdev->num_hwfns == 1) {
@@ -775,7 +775,7 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode)
 			if (force_mode)
 				goto out;
 		}
-		/* Fallthrough */
+		fallthrough;
 
 	case QED_INT_MODE_INTA:
 			int_params->out.int_mode = QED_INT_MODE_INTA;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 5be08f83e0aa..cd882c453394 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1085,7 +1085,7 @@ int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		DP_NOTICE(p_hwfn,
 			  "Unknown WoL configuration %02x\n",
 			  p_hwfn->cdev->wol_config);
-		/* Fallthrough */
+		fallthrough;
 	case QED_OV_WOL_DEFAULT:
 		wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
 	}
@@ -1365,7 +1365,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn,
 		break;
 	case LINK_STATUS_SPEED_AND_DUPLEX_1000THD:
 		p_link->full_duplex = false;
-	/* Fall-through */
+		fallthrough;
 	case LINK_STATUS_SPEED_AND_DUPLEX_1000TFD:
 		p_link->speed = 1000;
 		break;
@@ -2451,7 +2451,7 @@ qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn,
 		break;
 	case FUNC_MF_CFG_PROTOCOL_ROCE:
 		DP_NOTICE(p_hwfn, "RoCE personality is not a valid value!\n");
-	/* Fallthrough */
+		fallthrough;
 	default:
 		rc = -EINVAL;
 	}
@@ -3546,7 +3546,7 @@ qed_mcp_resc_allocation_msg(struct qed_hwfn *p_hwfn,
 	switch (p_in_params->cmd) {
 	case DRV_MSG_SET_RESOURCE_VALUE_MSG:
 		mfw_resc_info.size = p_in_params->resc_max_val;
-		/* Fallthrough */
+		fallthrough;
 	case DRV_MSG_GET_RESOURCE_ALLOC_MSG:
 		break;
 	default:
@@ -3823,7 +3823,7 @@ qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
 		DP_INFO(p_hwfn,
 			"Resource unlock request for an already released resource [%d]\n",
 			p_params->resource);
-		/* Fallthrough */
+		fallthrough;
 	case RESOURCE_OPCODE_RELEASED:
 		p_params->b_released = true;
 		break;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 0d0e38debbc2..569e2a7a64e5 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1542,7 +1542,7 @@ static void ql_link_state_machine_work(struct work_struct *work)
 		if (test_bit(QL_LINK_MASTER, &qdev->flags))
 			ql_port_start(qdev);
 		qdev->port_link_state = LS_DOWN;
-		/* Fall Through */
+		fallthrough;
 
 	case LS_DOWN:
 		if (curr_link_state == LS_UP) {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 5c2a3acf1e89..b9894d54469c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -353,7 +353,7 @@ skip:
 	case QLCNIC_BRDTYPE_P3P_4_GB_MM:
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
-		/* fall through */
+		fallthrough;
 	case QLCNIC_BRDTYPE_P3P_10G_CX4:
 	case QLCNIC_BRDTYPE_P3P_10G_CX4_LP:
 	case QLCNIC_BRDTYPE_P3P_10000_BASE_T:
@@ -377,7 +377,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(adapter->netdev) &&
 				   ahw->has_link_events;
-		/* fall through */
+		fallthrough;
 	case QLCNIC_BRDTYPE_P3P_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
 		advertising |= ADVERTISED_FIBRE;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index d1da92ac7fbe..fc9e6626db55 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4994,7 +4994,7 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		rtl_unlock_config_regs(tp);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		rtl_lock_config_regs(tp);
-		/* fall through */
+		fallthrough;
 	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_17:
 		flags = PCI_IRQ_LEGACY;
 		break;
@@ -5137,7 +5137,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp)
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_52:
 		rtl8168ep_stop_cmac(tp);
-		/* fall through */
+		fallthrough;
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 99f7aae102ce..df89d09b253e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1342,6 +1342,51 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler,
 	return error;
 }
 
+/* MDIO bus init function */
+static int ravb_mdio_init(struct ravb_private *priv)
+{
+	struct platform_device *pdev = priv->pdev;
+	struct device *dev = &pdev->dev;
+	int error;
+
+	/* Bitbang init */
+	priv->mdiobb.ops = &bb_ops;
+
+	/* MII controller setting */
+	priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
+	if (!priv->mii_bus)
+		return -ENOMEM;
+
+	/* Hook up MII support for ethtool */
+	priv->mii_bus->name = "ravb_mii";
+	priv->mii_bus->parent = dev;
+	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+		 pdev->name, pdev->id);
+
+	/* Register MDIO bus */
+	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+	if (error)
+		goto out_free_bus;
+
+	return 0;
+
+out_free_bus:
+	free_mdio_bitbang(priv->mii_bus);
+	return error;
+}
+
+/* MDIO bus release function */
+static int ravb_mdio_release(struct ravb_private *priv)
+{
+	/* Unregister mdio bus */
+	mdiobus_unregister(priv->mii_bus);
+
+	/* Free bitbang info */
+	free_mdio_bitbang(priv->mii_bus);
+
+	return 0;
+}
+
 /* Network device open function for Ethernet AVB */
 static int ravb_open(struct net_device *ndev)
 {
@@ -1350,6 +1395,13 @@ static int ravb_open(struct net_device *ndev)
 	struct device *dev = &pdev->dev;
 	int error;
 
+	/* MDIO bus init */
+	error = ravb_mdio_init(priv);
+	if (error) {
+		netdev_err(ndev, "failed to initialize MDIO\n");
+		return error;
+	}
+
 	napi_enable(&priv->napi[RAVB_BE]);
 	napi_enable(&priv->napi[RAVB_NC]);
 
@@ -1427,6 +1479,7 @@ out_free_irq:
 out_napi_off:
 	napi_disable(&priv->napi[RAVB_NC]);
 	napi_disable(&priv->napi[RAVB_BE]);
+	ravb_mdio_release(priv);
 	return error;
 }
 
@@ -1736,6 +1789,8 @@ static int ravb_close(struct net_device *ndev)
 	ravb_ring_free(ndev, RAVB_BE);
 	ravb_ring_free(ndev, RAVB_NC);
 
+	ravb_mdio_release(priv);
+
 	return 0;
 }
 
@@ -1887,51 +1942,6 @@ static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_set_features	= ravb_set_features,
 };
 
-/* MDIO bus init function */
-static int ravb_mdio_init(struct ravb_private *priv)
-{
-	struct platform_device *pdev = priv->pdev;
-	struct device *dev = &pdev->dev;
-	int error;
-
-	/* Bitbang init */
-	priv->mdiobb.ops = &bb_ops;
-
-	/* MII controller setting */
-	priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
-	if (!priv->mii_bus)
-		return -ENOMEM;
-
-	/* Hook up MII support for ethtool */
-	priv->mii_bus->name = "ravb_mii";
-	priv->mii_bus->parent = dev;
-	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
-		 pdev->name, pdev->id);
-
-	/* Register MDIO bus */
-	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
-	if (error)
-		goto out_free_bus;
-
-	return 0;
-
-out_free_bus:
-	free_mdio_bitbang(priv->mii_bus);
-	return error;
-}
-
-/* MDIO bus release function */
-static int ravb_mdio_release(struct ravb_private *priv)
-{
-	/* Unregister mdio bus */
-	mdiobus_unregister(priv->mii_bus);
-
-	/* Free bitbang info */
-	free_mdio_bitbang(priv->mii_bus);
-
-	return 0;
-}
-
 static const struct of_device_id ravb_match_table[] = {
 	{ .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 },
 	{ .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 },
@@ -2174,13 +2184,6 @@ static int ravb_probe(struct platform_device *pdev)
 		eth_hw_addr_random(ndev);
 	}
 
-	/* MDIO bus init */
-	error = ravb_mdio_init(priv);
-	if (error) {
-		dev_err(&pdev->dev, "failed to initialize MDIO\n");
-		goto out_dma_free;
-	}
-
 	netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64);
 	netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64);
 
@@ -2202,8 +2205,6 @@ static int ravb_probe(struct platform_device *pdev)
 out_napi_del:
 	netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
-	ravb_mdio_release(priv);
-out_dma_free:
 	dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
 			  priv->desc_bat_dma);
 
@@ -2235,7 +2236,6 @@ static int ravb_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 	netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
-	ravb_mdio_release(priv);
 	pm_runtime_disable(&pdev->dev);
 	free_netdev(ndev);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fc99e7118e49..42458a46ffaf 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2169,7 +2169,7 @@ static void rocker_router_fib_event_work(struct work_struct *work)
 		rocker_world_fib4_del(rocker, &fib_work->fen_info);
 		fib_info_put(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_ADD:
 	case FIB_EVENT_RULE_DEL:
 		rule = fib_work->fr_info.rule;
 		if (!fib4_rule_default(rule))
@@ -2201,7 +2201,7 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 	fib_work->event = event;
 
 	switch (event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_DEL:
 		if (info->family == AF_INET) {
 			struct fib_entry_notifier_info *fen_info = ptr;
@@ -2224,7 +2224,7 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_ADD:
 	case FIB_EVENT_RULE_DEL:
 		memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
 		fib_rule_get(fib_work->fr_info.rule);
@@ -2811,7 +2811,7 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 	switchdev_work->event = event;
 
 	switch (event) {
-	case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		memcpy(&switchdev_work->fdb_info, ptr,
 		       sizeof(switchdev_work->fdb_info));
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index 21465cb3d60a..7f8b10c49660 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -316,7 +316,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* Fall through */
+		fallthrough;
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -327,7 +327,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-		/* Fall through */
+		fallthrough;
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c
index 9729983f4840..c54b7f8243f3 100644
--- a/drivers/net/ethernet/sfc/ef100.c
+++ b/drivers/net/ethernet/sfc/ef100.c
@@ -142,7 +142,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio
 
 		/* Temporarily map new BAR. */
 		rc = efx_init_io(efx, bar,
-				 DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
+				 (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
 				 pci_resource_len(efx->pci_dev, bar));
 		if (rc) {
 			netif_err(efx, probe, efx->net_dev,
@@ -160,7 +160,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio
 
 		/* Put old BAR back. */
 		rc = efx_init_io(efx, previous_bar,
-				 DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
+				 (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
 				 pci_resource_len(efx->pci_dev, previous_bar));
 		if (rc) {
 			netif_err(efx, probe, efx->net_dev,
@@ -334,7 +334,7 @@ static int ef100_pci_parse_xilinx_cap(struct efx_nic *efx, int vndr_cap,
 
 	/* Temporarily map BAR. */
 	rc = efx_init_io(efx, bar,
-			 DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
+			 (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
 			 pci_resource_len(efx->pci_dev, bar));
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
@@ -495,7 +495,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev,
 
 	/* Set up basic I/O (BAR mappings etc) */
 	rc = efx_init_io(efx, fcw.bar,
-			 DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
+			 (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH),
 			 pci_resource_len(efx->pci_dev, fcw.bar));
 	if (rc)
 		goto fail;
diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index 206d70f9d95b..19fe86b3b316 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -431,18 +431,18 @@ static int ef100_reset(struct efx_nic *efx, enum reset_type reset_type)
 		/* A RESET_TYPE_ALL will cause filters to be removed, so we remove filters
 		 * and reprobe after reset to avoid removing filters twice
 		 */
-		down_read(&efx->filter_sem);
+		down_write(&efx->filter_sem);
 		ef100_filter_table_down(efx);
-		up_read(&efx->filter_sem);
+		up_write(&efx->filter_sem);
 		rc = efx_mcdi_reset(efx, reset_type);
 		if (rc)
 			return rc;
 
 		netif_device_attach(efx->net_dev);
 
-		down_read(&efx->filter_sem);
+		down_write(&efx->filter_sem);
 		rc = ef100_filter_table_up(efx);
-		up_read(&efx->filter_sem);
+		up_write(&efx->filter_sem);
 		if (rc)
 			return rc;
 
@@ -739,6 +739,7 @@ const struct efx_nic_type ef100_pf_nic_type = {
 	.rx_remove = efx_mcdi_rx_remove,
 	.rx_write = ef100_rx_write,
 	.rx_packet = __ef100_rx_packet,
+	.rx_buf_hash_valid = ef100_rx_buf_hash_valid,
 	.fini_dmaq = efx_fini_dmaq,
 	.max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS,
 	.filter_table_probe = ef100_filter_table_up,
@@ -820,6 +821,7 @@ const struct efx_nic_type ef100_vf_nic_type = {
 	.rx_remove = efx_mcdi_rx_remove,
 	.rx_write = ef100_rx_write,
 	.rx_packet = __ef100_rx_packet,
+	.rx_buf_hash_valid = ef100_rx_buf_hash_valid,
 	.fini_dmaq = efx_fini_dmaq,
 	.max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS,
 	.filter_table_probe = ef100_filter_table_up,
diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c
index 13ba1a4f66fc..85207acf7dee 100644
--- a/drivers/net/ethernet/sfc/ef100_rx.c
+++ b/drivers/net/ethernet/sfc/ef100_rx.c
@@ -31,7 +31,12 @@
 #define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_WIDTH	\
 		ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH
 
-static bool check_fcs(struct efx_channel *channel, u32 *prefix)
+bool ef100_rx_buf_hash_valid(const u8 *prefix)
+{
+	return PREFIX_FIELD(prefix, RSS_HASH_VALID);
+}
+
+static bool ef100_has_fcs_error(struct efx_channel *channel, u32 *prefix)
 {
 	u16 rxclass;
 	u8 l2status;
@@ -41,11 +46,11 @@ static bool check_fcs(struct efx_channel *channel, u32 *prefix)
 
 	if (likely(l2status == ESE_GZ_RH_HCLASS_L2_STATUS_OK))
 		/* Everything is ok */
-		return 0;
+		return false;
 
 	if (l2status == ESE_GZ_RH_HCLASS_L2_STATUS_FCS_ERR)
 		channel->n_rx_eth_crc_err++;
-	return 1;
+	return true;
 }
 
 void __ef100_rx_packet(struct efx_channel *channel)
@@ -58,7 +63,7 @@ void __ef100_rx_packet(struct efx_channel *channel)
 
 	prefix = (u32 *)(eh - ESE_GZ_RX_PKT_PREFIX_LEN);
 
-	if (check_fcs(channel, prefix) &&
+	if (ef100_has_fcs_error(channel, prefix) &&
 	    unlikely(!(efx->net_dev->features & NETIF_F_RXALL)))
 		goto out;
 
diff --git a/drivers/net/ethernet/sfc/ef100_rx.h b/drivers/net/ethernet/sfc/ef100_rx.h
index f2f266863966..fe45b36458d1 100644
--- a/drivers/net/ethernet/sfc/ef100_rx.h
+++ b/drivers/net/ethernet/sfc/ef100_rx.h
@@ -14,6 +14,7 @@
 
 #include "net_driver.h"
 
+bool ef100_rx_buf_hash_valid(const u8 *prefix);
 void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event);
 void ef100_rx_write(struct efx_rx_queue *rx_queue);
 void __ef100_rx_packet(struct efx_channel *channel);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index a9808e86068d..daf0c00c1242 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -45,6 +45,14 @@ static inline void efx_rx_flush_packet(struct efx_channel *channel)
 				__ef100_rx_packet, __efx_rx_packet,
 				channel);
 }
+static inline bool efx_rx_buf_hash_valid(struct efx_nic *efx, const u8 *prefix)
+{
+	if (efx->type->rx_buf_hash_valid)
+		return INDIRECT_CALL_1(efx->type->rx_buf_hash_valid,
+				       ef100_rx_buf_hash_valid,
+				       prefix);
+	return true;
+}
 
 /* Maximum number of TCP segments we support for soft-TSO */
 #define EFX_TSO_MAX_SEGS	100
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index db90d94e24c9..a6bae6a234ba 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -957,7 +957,7 @@ ef4_ethtool_get_rxnfc(struct net_device *net_dev,
 		switch (info->flow_type) {
 		case TCP_V4_FLOW:
 			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			/* Fall through */
+			fallthrough;
 		case UDP_V4_FLOW:
 		case SCTP_V4_FLOW:
 		case AH_ESP_V4_FLOW:
diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c
index 332183280a45..fa1ade856b10 100644
--- a/drivers/net/ethernet/sfc/falcon/farch.c
+++ b/drivers/net/ethernet/sfc/falcon/farch.c
@@ -1049,10 +1049,10 @@ ef4_farch_handle_rx_event(struct ef4_channel *channel, const ef4_qword_t *event)
 		switch (rx_ev_hdr_type) {
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP:
 			flags |= EF4_RX_PKT_TCP;
-			/* fall through */
+			fallthrough;
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP:
 			flags |= EF4_RX_PKT_CSUMMED;
-			/* fall through */
+			fallthrough;
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
 		case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
 			break;
@@ -1310,7 +1310,7 @@ int ef4_farch_ev_process(struct ef4_channel *channel, int budget)
 			if (efx->type->handle_global_event &&
 			    efx->type->handle_global_event(channel, &event))
 				break;
-			/* else fall through */
+			fallthrough;
 		default:
 			netif_err(channel->efx, hw, channel->efx->net_dev,
 				  "channel %d unknown event type %d (data "
@@ -1983,7 +1983,7 @@ ef4_farch_filter_from_gen_spec(struct ef4_farch_filter_spec *spec,
 	      EF4_FILTER_MATCH_LOC_HOST | EF4_FILTER_MATCH_LOC_PORT |
 	      EF4_FILTER_MATCH_REM_HOST | EF4_FILTER_MATCH_REM_PORT):
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case (EF4_FILTER_MATCH_ETHER_TYPE | EF4_FILTER_MATCH_IP_PROTO |
 	      EF4_FILTER_MATCH_LOC_HOST | EF4_FILTER_MATCH_LOC_PORT): {
 		__be32 rhost, host1, host2;
@@ -2034,7 +2034,7 @@ ef4_farch_filter_from_gen_spec(struct ef4_farch_filter_spec *spec,
 
 	case EF4_FILTER_MATCH_LOC_MAC | EF4_FILTER_MATCH_OUTER_VID:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EF4_FILTER_MATCH_LOC_MAC:
 		spec->type = (is_full ? EF4_FARCH_FILTER_MAC_FULL :
 			      EF4_FARCH_FILTER_MAC_WILD);
@@ -2081,7 +2081,7 @@ ef4_farch_filter_to_gen_spec(struct ef4_filter_spec *gen_spec,
 	case EF4_FARCH_FILTER_TCP_FULL:
 	case EF4_FARCH_FILTER_UDP_FULL:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EF4_FARCH_FILTER_TCP_WILD:
 	case EF4_FARCH_FILTER_UDP_WILD: {
 		__be32 host1, host2;
@@ -2125,7 +2125,7 @@ ef4_farch_filter_to_gen_spec(struct ef4_filter_spec *gen_spec,
 
 	case EF4_FARCH_FILTER_MAC_FULL:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EF4_FARCH_FILTER_MAC_WILD:
 		gen_spec->match_flags = EF4_FILTER_MATCH_LOC_MAC;
 		if (is_full)
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index d07eeaad9bdf..4002f9a3ae90 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -1038,10 +1038,10 @@ efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
 		switch (rx_ev_hdr_type) {
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP:
 			flags |= EFX_RX_PKT_TCP;
-			/* fall through */
+			fallthrough;
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP:
 			flags |= EFX_RX_PKT_CSUMMED;
-			/* fall through */
+			fallthrough;
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
 		case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
 			break;
@@ -1316,7 +1316,7 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget)
 			if (efx->type->handle_global_event &&
 			    efx->type->handle_global_event(channel, &event))
 				break;
-			/* else fall through */
+			fallthrough;
 		default:
 			netif_err(channel->efx, hw, channel->efx->net_dev,
 				  "channel %d unknown event type %d (data "
@@ -2043,7 +2043,7 @@ efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec,
 	      EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
 	      EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT):
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
 	      EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT): {
 		__be32 rhost, host1, host2;
@@ -2094,7 +2094,7 @@ efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec,
 
 	case EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_OUTER_VID:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EFX_FILTER_MATCH_LOC_MAC:
 		spec->type = (is_full ? EFX_FARCH_FILTER_MAC_FULL :
 			      EFX_FARCH_FILTER_MAC_WILD);
@@ -2141,7 +2141,7 @@ efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec,
 	case EFX_FARCH_FILTER_TCP_FULL:
 	case EFX_FARCH_FILTER_UDP_FULL:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EFX_FARCH_FILTER_TCP_WILD:
 	case EFX_FARCH_FILTER_UDP_WILD: {
 		__be32 host1, host2;
@@ -2185,7 +2185,7 @@ efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec,
 
 	case EFX_FARCH_FILTER_MAC_FULL:
 		is_full = true;
-		/* fall through */
+		fallthrough;
 	case EFX_FARCH_FILTER_MAC_WILD:
 		gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC;
 		if (is_full)
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index 5a74d880b733..1523be77b9db 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -140,7 +140,7 @@ efx_mcdi_filter_push_prep_set_match_fields(struct efx_nic *efx,
 		switch (encap_type & EFX_ENCAP_TYPES_MASK) {
 		case EFX_ENCAP_TYPE_VXLAN:
 			vni_type = MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_VXLAN;
-			/* fallthrough */
+			fallthrough;
 		case EFX_ENCAP_TYPE_GENEVE:
 			COPY_VALUE(ether_type, ETHER_TYPE);
 			outer_ip_proto = IPPROTO_UDP;
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
index 56af8b54a864..714d7f937212 100644
--- a/drivers/net/ethernet/sfc/mcdi_port_common.c
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -282,7 +282,7 @@ void efx_mcdi_phy_decode_link(struct efx_nic *efx,
 		break;
 	default:
 		WARN_ON(1);
-		/* Fall through */
+		fallthrough;
 	case MC_CMD_FCNTL_OFF:
 		link_state->fc = 0;
 		break;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 7bb7ecb480ae..062462a13847 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -846,6 +846,7 @@ struct efx_async_filter_insertion {
  * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds
  * @timer_max_ns: Interrupt timer maximum value, in nanoseconds
  * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues
+ * @irqs_hooked: Channel interrupts are hooked
  * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues
  * @irq_rx_moderation_us: IRQ moderation time for RX event queues
  * @msg_enable: Log message enable flags
@@ -1004,6 +1005,7 @@ struct efx_nic {
 	unsigned int timer_quantum_ns;
 	unsigned int timer_max_ns;
 	bool irq_rx_adaptive;
+	bool irqs_hooked;
 	unsigned int irq_mod_step_us;
 	unsigned int irq_rx_moderation_us;
 	u32 msg_enable;
@@ -1265,6 +1267,7 @@ struct efx_udp_tunnel {
  * @rx_write: Write RX descriptors and doorbell
  * @rx_defer_refill: Generate a refill reminder event
  * @rx_packet: Receive the queued RX buffer on a channel
+ * @rx_buf_hash_valid: Determine whether the RX prefix contains a valid hash
  * @ev_probe: Allocate resources for event queue
  * @ev_init: Initialise event queue on the NIC
  * @ev_fini: Deinitialise event queue on the NIC
@@ -1409,6 +1412,7 @@ struct efx_nic_type {
 	void (*rx_write)(struct efx_rx_queue *rx_queue);
 	void (*rx_defer_refill)(struct efx_rx_queue *rx_queue);
 	void (*rx_packet)(struct efx_channel *channel);
+	bool (*rx_buf_hash_valid)(const u8 *prefix);
 	int (*ev_probe)(struct efx_channel *channel);
 	int (*ev_init)(struct efx_channel *channel);
 	void (*ev_fini)(struct efx_channel *channel);
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index d994d136bb03..d1e908846f5d 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -129,6 +129,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
 #endif
 	}
 
+	efx->irqs_hooked = true;
 	return 0;
 
  fail2:
@@ -154,6 +155,8 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 	efx->net_dev->rx_cpu_rmap = NULL;
 #endif
 
+	if (!efx->irqs_hooked)
+		return;
 	if (EFX_INT_MODE_USE_MSI(efx)) {
 		/* Disable MSI/MSI-X interrupts */
 		efx_for_each_channel(channel, efx)
@@ -163,6 +166,7 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 		/* Disable legacy interrupt */
 		free_irq(efx->legacy_irq, efx);
 	}
+	efx->irqs_hooked = false;
 }
 
 /* Register dump */
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 59a43d586967..aaa112877561 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -358,7 +358,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 
 	case XDP_ABORTED:
 		trace_xdp_exception(efx->net_dev, xdp_prog, xdp_act);
-		/* Fall through */
+		fallthrough;
 	case XDP_DROP:
 		efx_free_rx_buffers(rx_queue, rx_buf, 1);
 		channel->n_rx_xdp_drops++;
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index fb77c7bbe4af..5e29284c89c9 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -525,7 +525,8 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
 		return;
 	}
 
-	if (efx->net_dev->features & NETIF_F_RXHASH)
+	if (efx->net_dev->features & NETIF_F_RXHASH &&
+	    efx_rx_buf_hash_valid(efx, eh))
 		skb_set_hash(skb, efx_rx_buf_hash(efx, eh),
 			     PKT_HASH_TYPE_L3);
 	if (csum) {
@@ -848,6 +849,7 @@ void efx_remove_filters(struct efx_nic *efx)
 	efx_for_each_channel(channel, efx) {
 		cancel_delayed_work_sync(&channel->filter_work);
 		kfree(channel->rps_flow_id);
+		channel->rps_flow_id = NULL;
 	}
 #endif
 	down_write(&efx->filter_sem);
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 336105f77313..cfa460c7db23 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -2228,7 +2228,7 @@ static int mii_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 	switch(cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = sis_priv->mii->phy_addr;
-		/* Fall Through */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		data->val_out = mdio_read(net_dev, data->phy_id & 0x1f, data->reg_num & 0x1f);
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 186c0bddbe5f..01069dfaf75c 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -712,7 +712,7 @@ static void smc911x_phy_detect(struct net_device *dev)
 					/* Found an external PHY */
 					break;
 			}
-			/* Else, fall through */
+			fallthrough;
 		default:
 			/* Internal media only */
 			SMC_GET_PHY_ID1(lp, 1, id1);
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 25db667fa879..806eb651cea3 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -919,10 +919,10 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(priv->ndev, prog, act);
-		/* fall through -- handle aborts by dropping packet */
+		fallthrough;	/* handle aborts by dropping packet */
 	case XDP_DROP:
 		ret = NETSEC_XDP_CONSUMED;
 		page = virt_to_head_page(xdp->data);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
index d0d2d0fc5f0a..08c76636c164 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
@@ -84,9 +84,10 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
 		return ERR_PTR(err);
 
 	switch (phy_mode) {
-	case PHY_INTERFACE_MODE_RGMII:		/* Fall through */
-	case PHY_INTERFACE_MODE_RGMII_ID	/* Fall through */:
-	case PHY_INTERFACE_MODE_RGMII_RXID:	/* Fall through */
+	case PHY_INTERFACE_MODE_RGMII:
+		fallthrough;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		gmac->phy_intf_sel = GMAC_CONFIG_INTF_RGMII;
 		break;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index e113b1376fdd..bf195adee393 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -1985,7 +1985,7 @@ void stmmac_selftest_run(struct net_device *dev,
 				ret = phy_loopback(dev->phydev, true);
 			if (!ret)
 				break;
-			/* Fallthrough */
+			fallthrough;
 		case STMMAC_LOOPBACK_MAC:
 			ret = stmmac_set_mac_loopback(priv, priv->ioaddr, true);
 			break;
@@ -2018,7 +2018,7 @@ void stmmac_selftest_run(struct net_device *dev,
 				ret = phy_loopback(dev->phydev, false);
 			if (!ret)
 				break;
-			/* Fallthrough */
+			fallthrough;
 		case STMMAC_LOOPBACK_MAC:
 			stmmac_set_mac_loopback(priv, priv->ioaddr, false);
 			break;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 3d747846f482..cc27d660a818 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -228,7 +228,7 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv,
 	switch (cls->command) {
 	case TC_CLSU32_REPLACE_KNODE:
 		tc_unfill_entry(priv, cls);
-		/* Fall through */
+		fallthrough;
 	case TC_CLSU32_NEW_KNODE:
 		return tc_config_knode(priv, cls);
 	case TC_CLSU32_DELETE_KNODE:
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index e2bc7a25f6d1..b624e177ec71 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4759,7 +4759,7 @@ static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = cp->phy_addr;
-		/* Fallthrough... */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		spin_lock_irqsave(&cp->lock, flags);
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 9b5effb72657..68695d4afacd 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -8835,7 +8835,7 @@ static int walk_phys(struct niu *np, struct niu_parent *parent)
 			else
 				goto unknown_vg_1g_port;
 
-			/* fallthru */
+			fallthrough;
 		case 0x22:
 			val = (phy_encode(PORT_TYPE_10G, 0) |
 			       phy_encode(PORT_TYPE_10G, 1) |
@@ -8860,7 +8860,7 @@ static int walk_phys(struct niu *np, struct niu_parent *parent)
 			else
 				goto unknown_vg_1g_port;
 
-			/* fallthru */
+			fallthrough;
 		case 0x13:
 			if ((lowest_10g & 0x7) == 0)
 				val = (phy_encode(PORT_TYPE_10G, 0) |
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index eeb8518c8a84..8deb943ca5de 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2712,7 +2712,7 @@ static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:		/* Get address of MII PHY in use. */
 		data->phy_id = gp->mii_phy_addr;
-		/* Fallthrough... */
+		fallthrough;
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		data->val_out = __sungem_phy_read(gp, data->phy_id & 0x1f,
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index cb994f66c3be..9baf3f3da91e 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -174,6 +174,8 @@ void am65_cpsw_nuss_adjust_link(struct net_device *ndev)
 		if (phy->speed == 10 && phy_interface_is_rgmii(phy))
 			/* Can be used with in band mode only */
 			mac_control |= CPSW_SL_CTL_EXT_EN;
+		if (phy->speed == 100 && phy->interface == PHY_INTERFACE_MODE_RMII)
+			mac_control |= CPSW_SL_CTL_IFCTL_A;
 		if (phy->duplex)
 			mac_control |= CPSW_SL_CTL_FULLDUPLEX;
 
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 4e184eecc8e1..6e72ecbe5cf7 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -67,7 +67,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 		dev_warn(priv->dev,
 			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
 			phy_modes(phy_mode));
-		/* fallthrough */
+		fallthrough;
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
@@ -122,7 +122,7 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 		dev_warn(priv->dev,
 			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
 			phy_modes(phy_mode));
-		/* fallthrough */
+		fallthrough;
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 9b17bbbe102f..4a65edc5a375 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1116,7 +1116,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 				  HOST_PORT_NUM, ALE_VLAN, vid);
 	ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
 				  0, ALE_VLAN, vid);
-	ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid);
+	ret |= cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid);
 err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 1247d35d42ef..8ed78577cded 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1032,19 +1032,34 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 		return ret;
 	}
 
+	/* reset the return code as pm_runtime_get_sync() can return
+	 * non zero values as well.
+	 */
+	ret = 0;
 	for (i = 0; i < cpsw->data.slaves; i++) {
 		if (cpsw->slaves[i].ndev &&
-		    vid == cpsw->slaves[i].port_vlan)
+		    vid == cpsw->slaves[i].port_vlan) {
+			ret = -EINVAL;
 			goto err;
+		}
 	}
 
 	dev_dbg(priv->dev, "removing vlanid %d from vlan filter\n", vid);
-	cpsw_ale_del_vlan(cpsw->ale, vid, 0);
-	cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
-			   HOST_PORT_NUM, ALE_VLAN, vid);
-	cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
-			   0, ALE_VLAN, vid);
-	cpsw_ale_flush_multicast(cpsw->ale, 0, vid);
+	ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0);
+	if (ret)
+		dev_err(priv->dev, "cpsw_ale_del_vlan() failed: ret %d\n", ret);
+	ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+				 HOST_PORT_NUM, ALE_VLAN, vid);
+	if (ret)
+		dev_err(priv->dev, "cpsw_ale_del_ucast() failed: ret %d\n",
+			ret);
+	ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
+				 0, ALE_VLAN, vid);
+	if (ret)
+		dev_err(priv->dev, "cpsw_ale_del_mcast failed. ret %d\n",
+			ret);
+	cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid);
+	ret = 0;
 err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index d6d7a7d9c7ad..482a1a451e43 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1371,10 +1371,10 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(ndev, prog, act);
-		/* fall through -- handle aborts by dropping packet */
+		fallthrough;	/* handle aborts by dropping packet */
 	case XDP_DROP:
 		goto drop;
 	}
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 58623e974a0c..76a342ea3797 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -948,7 +948,7 @@ static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:		/* get address of MII PHY in use. */
 		data->phy_id = phy;
-		/* fall through */
+		fallthrough;
 
 
 	case SIOCGMIIREG:		/* read MII PHY register. */
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
index 2db546b27ee0..dc14a66583ff 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
@@ -877,7 +877,7 @@ static int gelic_wl_set_auth(struct net_device *netdev,
 	case IW_AUTH_KEY_MGMT:
 		if (param->value & IW_AUTH_KEY_MGMT_PSK)
 			break;
-		/* intentionally fall through */
+		fallthrough;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 07389702a540..5f5b33e6653b 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -786,7 +786,7 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal)
 			/* fallthrough, if we release the descriptors
 			 * brutally (then we don't care about
 			 * SPIDER_NET_DESCR_CARDOWNED) */
-			/* Fall through */
+			fallthrough;
 
 		case SPIDER_NET_DESCR_RESPONSE_ERROR:
 		case SPIDER_NET_DESCR_PROTECTION_ERROR:
@@ -1397,9 +1397,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg,
 		show_error = 0;
 		break;
 
-	case SPIDER_NET_GDDDEN0INT: /* fallthrough */
-	case SPIDER_NET_GDCDEN0INT: /* fallthrough */
-	case SPIDER_NET_GDBDEN0INT: /* fallthrough */
+	case SPIDER_NET_GDDDEN0INT:
+	case SPIDER_NET_GDCDEN0INT:
+	case SPIDER_NET_GDBDEN0INT:
 	case SPIDER_NET_GDADEN0INT:
 		/* someone has set RX_DMA_EN to 0 */
 		show_error = 0;
@@ -1449,10 +1449,10 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg,
 		 * Logging is not needed. */
 		show_error = 0;
 		break;
-	case SPIDER_NET_GRFDFLLINT: /* fallthrough */
-	case SPIDER_NET_GRFCFLLINT: /* fallthrough */
-	case SPIDER_NET_GRFBFLLINT: /* fallthrough */
-	case SPIDER_NET_GRFAFLLINT: /* fallthrough */
+	case SPIDER_NET_GRFDFLLINT:
+	case SPIDER_NET_GRFCFLLINT:
+	case SPIDER_NET_GRFBFLLINT:
+	case SPIDER_NET_GRFAFLLINT:
 	case SPIDER_NET_GRMFLLINT:
 		/* Could happen when rx chain is full */
 		if (card->ignore_rx_ramfull == 0) {
@@ -1473,9 +1473,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg,
 		break;
 
 	/* chain end */
-	case SPIDER_NET_GDDDCEINT: /* fallthrough */
-	case SPIDER_NET_GDCDCEINT: /* fallthrough */
-	case SPIDER_NET_GDBDCEINT: /* fallthrough */
+	case SPIDER_NET_GDDDCEINT:
+	case SPIDER_NET_GDCDCEINT:
+	case SPIDER_NET_GDBDCEINT:
 	case SPIDER_NET_GDADCEINT:
 		spider_net_resync_head_ptr(card);
 		spider_net_refill_rx_chain(card);
@@ -1486,9 +1486,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg,
 		break;
 
 	/* invalid descriptor */
-	case SPIDER_NET_GDDINVDINT: /* fallthrough */
-	case SPIDER_NET_GDCINVDINT: /* fallthrough */
-	case SPIDER_NET_GDBINVDINT: /* fallthrough */
+	case SPIDER_NET_GDDINVDINT:
+	case SPIDER_NET_GDCINVDINT:
+	case SPIDER_NET_GDBINVDINT:
 	case SPIDER_NET_GDAINVDINT:
 		/* Could happen when rx chain is full */
 		spider_net_resync_head_ptr(card);
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 3e3883ad88b0..3e337142b516 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1434,7 +1434,7 @@ do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     switch(cmd) {
       case SIOCGMIIPHY:		/* Get the address of the PHY in use. */
 	data->phy_id = 0;	/* we have only this address */
-	/* fall through */
+	fallthrough;
       case SIOCGMIIREG:		/* Read the specified MII register. */
 	data->val_out = mii_rd(ioaddr, data->phy_id & 0x1f,
 			       data->reg_num & 0x1f);
diff --git a/drivers/net/fddi/skfp/cfm.c b/drivers/net/fddi/skfp/cfm.c
index e9bf42996de8..4eea3408034b 100644
--- a/drivers/net/fddi/skfp/cfm.c
+++ b/drivers/net/fddi/skfp/cfm.c
@@ -36,10 +36,6 @@
 #define KERNEL
 #include "h/smtstate.h"
 
-#ifndef	lint
-static const char ID_sccs[] = "@(#)cfm.c	2.18 98/10/06 (C) SK " ;
-#endif
-
 /*
  * FSM Macros
  */
@@ -208,7 +204,6 @@ void cfm(struct s_smc *smc, int event)
 {
 	int	state ;		/* remember last state */
 	int	cond ;
-	int	oldstate ;
 
 	/* We will do the following: */
 	/*  - compute the variable WC_Flag for every port (This is where */
@@ -222,7 +217,6 @@ void cfm(struct s_smc *smc, int event)
 	/*  - change the portstates */
 	cem_priv_state (smc, event);
 
-	oldstate = smc->mib.fddiSMTCF_State ;
 	do {
 		DB_CFM("CFM : state %s%s event %s",
 		       smc->mib.fddiSMTCF_State & AFLAG ? "ACTIONS " : "",
@@ -250,18 +244,11 @@ void cfm(struct s_smc *smc, int event)
 	if (cond != smc->mib.fddiSMTPeerWrapFlag)
 		smt_srf_event(smc,SMT_COND_SMT_PEER_WRAP,0,cond) ;
 
-#if	0
 	/*
-	 * Don't send ever MAC_PATH_CHANGE events. Our MAC is hard-wired
+	 * Don't ever send MAC_PATH_CHANGE events. Our MAC is hard-wired
 	 * to the primary path.
 	 */
-	/*
-	 * path change
-	 */
-	if (smc->mib.fddiSMTCF_State != oldstate) {
-		smt_srf_event(smc,SMT_EVENT_MAC_PATH_CHANGE,INDEX_MAC,0) ;
-	}
-#endif
+
 #endif	/* no SLIM_SMT */
 
 	/*
diff --git a/drivers/net/fddi/skfp/fplustm.c b/drivers/net/fddi/skfp/fplustm.c
index 02966d141948..4cbb145c74ab 100644
--- a/drivers/net/fddi/skfp/fplustm.c
+++ b/drivers/net/fddi/skfp/fplustm.c
@@ -21,10 +21,6 @@
 #include <linux/bitrev.h>
 #include <linux/etherdevice.h>
 
-#ifndef	lint
-static const char ID_sccs[] = "@(#)fplustm.c	1.32 99/02/23 (C) SK " ;
-#endif
-
 #ifndef UNUSED
 #ifdef  lint
 #define UNUSED(x)	(x) = (x)
diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c
index 3412e0fb0ac4..107039056511 100644
--- a/drivers/net/fddi/skfp/hwmtm.c
+++ b/drivers/net/fddi/skfp/hwmtm.c
@@ -10,10 +10,6 @@
  *
  ******************************************************************************/
 
-#ifndef	lint
-static char const ID_sccs[] = "@(#)hwmtm.c	1.40 99/05/31 (C) SK" ;
-#endif
-
 #define	HWMTM
 
 #ifndef FDDI
diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c
index 1be039579d70..554cde8d6073 100644
--- a/drivers/net/fddi/skfp/pcmplc.c
+++ b/drivers/net/fddi/skfp/pcmplc.c
@@ -847,7 +847,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd)
 
 	case ACTIONS(PC5_SIGNAL) :
 		ACTIONS_DONE() ;
-		/* fall through */
+		fallthrough;
 	case PC5_SIGNAL :
 		if ((cmd != PC_SIGNAL) && (cmd != PC_TIMEOUT_LCT))
 			break ;
@@ -946,7 +946,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd)
 		SETMASK(PLC(np,PL_CNTRL_B),PL_PC_JOIN,PL_PC_JOIN) ;
 		ACTIONS_DONE() ;
 		cmd = 0 ;
-		/* fall thru */
+		fallthrough;
 	case PC6_JOIN :
 		switch (plc->p_state) {
 		case PS_ACTIVE:
diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c
index b8c59d803ce6..774a6e3b0a67 100644
--- a/drivers/net/fddi/skfp/smt.c
+++ b/drivers/net/fddi/skfp/smt.c
@@ -20,10 +20,6 @@
 #define KERNEL
 #include "h/smtstate.h"
 
-#ifndef	lint
-static const char ID_sccs[] = "@(#)smt.c	2.43 98/11/23 (C) SK " ;
-#endif
-
 /*
  * FC in SMbuf
  */
@@ -1561,7 +1557,7 @@ u_long smt_get_tid(struct s_smc *smc)
 	return tid & 0x3fffffffL;
 }
 
-
+#ifdef	LITTLE_ENDIAN
 /*
  * table of parameter lengths
  */
@@ -1641,6 +1637,7 @@ static const struct smt_pdef {
 } ;
 
 #define N_SMT_PLEN	ARRAY_SIZE(smt_pdef)
+#endif
 
 int smt_check_para(struct s_smc *smc, struct smt_header	*sm,
 		   const u_short list[])
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index 8c810edece86..466622664424 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -974,7 +974,7 @@ static void fjes_stop_req_irq(struct fjes_adapter *adapter, int src_epid)
 				FJES_RX_STOP_REQ_DONE;
 		spin_unlock_irqrestore(&hw->rx_status_lock, flags);
 		clear_bit(src_epid, &hw->txrx_stop_req_bit);
-		/* fall through */
+		fallthrough;
 	case EP_PARTNER_UNSHARE:
 	case EP_PARTNER_COMPLETE:
 	default:
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 21640a035d7d..8e47d0112e5d 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1179,6 +1179,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
 		goto nlmsg_failure;
 
 	if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
+	    nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) ||
 	    nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
 	    nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
 		goto nla_put_failure;
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 4476491b58f9..e4e4981ac1d2 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -500,7 +500,7 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat)
 				}
 				break;
 			}
-			/* fall through */
+			fallthrough;
 
 		default:
 			if (bc->hdlctx.calibrate <= 0)
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index deef14215110..17be2bb2985c 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -482,7 +482,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
 		case CRC_MODE_SMACK_TEST:
 			ax->crcmode  = CRC_MODE_FLEX_TEST;
 			printk(KERN_INFO "mkiss: %s: Trying crc-smack\n", ax->dev->name);
-			// fall through
+			fallthrough;
 		case CRC_MODE_SMACK:
 			*p |= 0x80;
 			crc = swab16(crc16(0, p, len));
@@ -491,7 +491,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
 		case CRC_MODE_FLEX_TEST:
 			ax->crcmode = CRC_MODE_NONE;
 			printk(KERN_INFO "mkiss: %s: Trying crc-flexnet\n", ax->dev->name);
-			// fall through
+			fallthrough;
 		case CRC_MODE_FLEX:
 			*p |= 0x20;
 			crc = calc_crc_flex(p, len);
@@ -744,7 +744,6 @@ static int mkiss_open(struct tty_struct *tty)
 		       ax->dev->name);
 		break;
 	case 0:
-		/* fall through */
 	default:
 		crc_force = 0;
 		printk(KERN_INFO "mkiss: %s: crc mode is auto.\n",
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 787f17e2a971..64b0a74c1523 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -367,7 +367,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	}
 	rcu_read_unlock();
 
-	while (unlikely(txq >= ndev->real_num_tx_queues))
+	while (txq >= ndev->real_num_tx_queues)
 		txq -= ndev->real_num_tx_queues;
 
 	return txq;
@@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
 	int rc;
 
 	skb->dev = vf_netdev;
-	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+	skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
 
 	rc = dev_queue_xmit(skb);
 	if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 15e87c097b0b..5bca94c99006 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree(port);
 }
 
+#define IPVLAN_ALWAYS_ON_OFLOADS \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | \
+	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
+
+#define IPVLAN_ALWAYS_ON \
+	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+
 #define IPVLAN_FEATURES \
-	(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \
 	 NETIF_F_GRO | NETIF_F_RXCSUM | \
 	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
 
+	/* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */
+
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
@@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev)
 	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
 		     (phy_dev->state & IPVLAN_STATE_MASK);
 	dev->features = phy_dev->features & IPVLAN_FEATURES;
-	dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED;
+	dev->features |= IPVLAN_ALWAYS_ON;
+	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
+	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->hw_enc_features |= dev->features;
 	dev->gso_max_size = phy_dev->gso_max_size;
 	dev->gso_max_segs = phy_dev->gso_max_segs;
@@ -227,7 +238,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev,
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features |= NETIF_F_ALL_FOR_ALL;
+	features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features = netdev_increment_features(ipvlan->phy_dev->features,
+					     features, features);
+	features |= IPVLAN_ALWAYS_ON;
+	features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON);
+
+	return features;
 }
 
 static void ipvlan_change_rx_flags(struct net_device *dev, int change)
@@ -734,10 +752,9 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
 			ipvlan->dev->gso_max_size = dev->gso_max_size;
 			ipvlan->dev->gso_max_segs = dev->gso_max_segs;
-			netdev_features_change(ipvlan->dev);
+			netdev_update_features(ipvlan->dev);
 		}
 		break;
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 4942f6112e51..c8d803d3616c 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -842,7 +842,7 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (!net_eq(dev_net(dev), &init_net))
 			break;
-		/* fall through */
+		fallthrough;
 	case SIOCGHWTSTAMP:
 		if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
 			err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
@@ -1269,6 +1269,9 @@ static void macvlan_port_destroy(struct net_device *dev)
 static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			    struct netlink_ext_ack *extack)
 {
+	struct nlattr *nla, *head;
+	int rem, len;
+
 	if (tb[IFLA_ADDRESS]) {
 		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
 			return -EINVAL;
@@ -1316,6 +1319,20 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			return -EADDRNOTAVAIL;
 	}
 
+	if (data[IFLA_MACVLAN_MACADDR_DATA]) {
+		head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]);
+		len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]);
+
+		nla_for_each_attr(nla, head, len, rem) {
+			if (nla_type(nla) != IFLA_MACVLAN_MACADDR ||
+			    nla_len(nla) != ETH_ALEN)
+				return -EINVAL;
+
+			if (!is_valid_ether_addr(nla_data(nla)))
+				return -EADDRNOTAVAIL;
+		}
+	}
+
 	if (data[IFLA_MACVLAN_MACADDR_COUNT])
 		return -EINVAL;
 
@@ -1372,10 +1389,6 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
 		len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]);
 
 		nla_for_each_attr(nla, head, len, rem) {
-			if (nla_type(nla) != IFLA_MACVLAN_MACADDR ||
-			    nla_len(nla) != ETH_ALEN)
-				continue;
-
 			addr = nla_data(nla);
 			ret = macvlan_hash_add_source(vlan, addr);
 			if (ret)
diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index 44612122338b..f6a97c859f3a 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -597,7 +597,7 @@ int generic_mii_ioctl(struct mii_if_info *mii_if,
 	switch(cmd) {
 	case SIOCGMIIPHY:
 		mii_data->phy_id = mii_if->phy_id;
-		/* fall through */
+		fallthrough;
 
 	case SIOCGMIIREG:
 		mii_data->val_out =
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 7971dc4f54f1..0e9511661601 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -193,7 +193,7 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count)
 	switch (err) {
 	case 1:
 		port_count = 1;
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (id > INT_MAX) {
 			pr_err("Value of \"id\" is too big.\n");
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index f32d56ac3e80..deea17a0e79c 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -760,14 +760,14 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
 	spin_lock_bh(&data->fib_lock);
 
 	switch (event) {
-	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_ADD:
 	case FIB_EVENT_RULE_DEL:
 		err = nsim_fib_rule_event(data, info,
 					  event == FIB_EVENT_RULE_ADD);
 		break;
 
-	case FIB_EVENT_ENTRY_REPLACE:  /* fall through */
-	case FIB_EVENT_ENTRY_APPEND:  /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
+	case FIB_EVENT_ENTRY_APPEND:
 	case FIB_EVENT_ENTRY_DEL:
 		err = nsim_fib_event(data, info, event);
 		break;
diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 7471a8b90873..307f0ac1287b 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -366,10 +366,10 @@ static int adin_set_edpd(struct phy_device *phydev, u16 tx_interval)
 
 	switch (tx_interval) {
 	case 1000: /* 1 second */
-		/* fallthrough */
+		fallthrough;
 	case ETHTOOL_PHY_EDPD_DFLT_TX_MSECS:
 		val |= ADIN1300_NRG_PD_TX_EN;
-		/* fallthrough */
+		fallthrough;
 	case ETHTOOL_PHY_EDPD_NO_TX:
 		break;
 	default:
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 50fb7d16b75a..79e67f2fe00a 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -766,13 +766,13 @@ static int decode_evnt(struct dp83640_private *dp83640,
 	switch (words) {
 	case 3:
 		dp83640->edata.sec_hi = phy_txts->sec_hi;
-		/* fall through */
+		fallthrough;
 	case 2:
 		dp83640->edata.sec_lo = phy_txts->sec_lo;
-		/* fall through */
+		fallthrough;
 	case 1:
 		dp83640->edata.ns_hi = phy_txts->ns_hi;
-		/* fall through */
+		fallthrough;
 	case 0:
 		dp83640->edata.ns_lo = phy_txts->ns_lo;
 	}
@@ -1409,7 +1409,7 @@ static void dp83640_txtstamp(struct mii_timestamper *mii_ts,
 			kfree_skb(skb);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	case HWTSTAMP_TX_ON:
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index f3c04981b8da..cd7032628a28 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -215,9 +215,9 @@ static int dp83867_set_wol(struct phy_device *phydev,
 		if (wol->wolopts & WAKE_MAGICSECURE) {
 			phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1,
 				      (wol->sopass[1] << 8) | wol->sopass[0]);
-			phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1,
+			phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP2,
 				      (wol->sopass[3] << 8) | wol->sopass[2]);
-			phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1,
+			phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP3,
 				      (wol->sopass[5] << 8) | wol->sopass[4]);
 
 			val_rxcfg |= DP83867_WOL_SEC_EN;
diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c
index 58103152c601..6b98d74b5102 100644
--- a/drivers/net/phy/dp83869.c
+++ b/drivers/net/phy/dp83869.c
@@ -427,18 +427,18 @@ static int dp83869_config_init(struct phy_device *phydev)
 			return ret;
 
 		val = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL);
-		val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN |
-			 DP83869_RGMII_RX_CLK_DELAY_EN);
+		val |= (DP83869_RGMII_TX_CLK_DELAY_EN |
+			DP83869_RGMII_RX_CLK_DELAY_EN);
 
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
-			val |= (DP83869_RGMII_TX_CLK_DELAY_EN |
-				DP83869_RGMII_RX_CLK_DELAY_EN);
+			val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN |
+				 DP83869_RGMII_RX_CLK_DELAY_EN);
 
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
-			val |= DP83869_RGMII_TX_CLK_DELAY_EN;
+			val &= ~DP83869_RGMII_TX_CLK_DELAY_EN;
 
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
-			val |= DP83869_RGMII_RX_CLK_DELAY_EN;
+			val &= ~DP83869_RGMII_RX_CLK_DELAY_EN;
 
 		ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL,
 				    val);
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index c4641b1704d6..18d81f43f2a8 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -279,13 +279,13 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
 				 phy->supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
 				 phy->supported);
-		/* fall through */
+		fallthrough;
 	case SPEED_100:
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
 				 phy->supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 				 phy->supported);
-		/* fall through */
+		fallthrough;
 	case SPEED_10:
 	default:
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index a4fbf3a4fa97..6bc7406a1ce7 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -1738,13 +1738,13 @@ static int __phy_write_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb,
 	return 0;
 }
 
-/* Trigger a read to the spcified MCB */
+/* Trigger a read to the specified MCB */
 static int phy_update_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb)
 {
 	return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_READ);
 }
 
-/* Trigger a write to the spcified MCB */
+/* Trigger a write to the specified MCB */
 static int phy_commit_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb)
 {
 	return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_WRITE);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 79b4f35d151e..735a806045ac 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -355,7 +355,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:
 		mii_data->phy_id = phydev->mdio.addr;
-		/* fall through */
+		fallthrough;
 
 	case SIOCGMIIREG:
 		if (mdio_phy_id_is_c45(mii_data->phy_id)) {
@@ -433,7 +433,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (phydev->mii_ts && phydev->mii_ts->hwtstamp)
 			return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr);
-		/* fall through */
+		fallthrough;
 
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 57d44648c8dd..8adfbad0a1e8 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1979,7 +1979,7 @@ static int genphy_setup_master_slave(struct phy_device *phydev)
 		break;
 	case MASTER_SLAVE_CFG_MASTER_FORCE:
 		ctl |= CTL1000_AS_MASTER;
-		/* fallthrough */
+		fallthrough;
 	case MASTER_SLAVE_CFG_SLAVE_FORCE:
 		ctl |= CTL1000_ENABLE_MASTER;
 		break;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 32b4bd6a5b55..32f4e8ec96cf 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1905,7 +1905,7 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd)
 		switch (cmd) {
 		case SIOCGMIIPHY:
 			mii->phy_id = pl->phydev->mdio.addr;
-			/* fall through */
+			fallthrough;
 
 		case SIOCGMIIREG:
 			ret = phylink_phy_read(pl, mii->phy_id, mii->reg_num);
@@ -1928,7 +1928,7 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd)
 		switch (cmd) {
 		case SIOCGMIIPHY:
 			mii->phy_id = 0;
-			/* fall through */
+			fallthrough;
 
 		case SIOCGMIIREG:
 			ret = phylink_mii_read(pl, mii->phy_id, mii->reg_num);
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 6900c68260e0..58014feedf6c 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -149,7 +149,7 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 			port = PORT_TP;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case SFF8024_CONNECTOR_SG: /* guess */
 	case SFF8024_CONNECTOR_HSSDC_II:
 	case SFF8024_CONNECTOR_NOSEPARATE:
@@ -301,7 +301,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 		break;
 	case SFF8024_ECC_100GBASE_CR4:
 		phylink_set(modes, 100000baseCR4_Full);
-		/* fallthrough */
+		fallthrough;
 	case SFF8024_ECC_25GBASE_CR_S:
 	case SFF8024_ECC_25GBASE_CR_N:
 		phylink_set(modes, 25000baseCR_Full);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index c24b0e83dd32..cf83314c8591 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -552,7 +552,7 @@ static umode_t sfp_hwmon_is_visible(const void *data,
 		case hwmon_temp_crit:
 			if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN))
 				return 0;
-			/* fall through */
+			fallthrough;
 		case hwmon_temp_input:
 		case hwmon_temp_label:
 			return 0444;
@@ -571,7 +571,7 @@ static umode_t sfp_hwmon_is_visible(const void *data,
 		case hwmon_in_crit:
 			if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN))
 				return 0;
-			/* fall through */
+			fallthrough;
 		case hwmon_in_input:
 		case hwmon_in_label:
 			return 0444;
@@ -590,7 +590,7 @@ static umode_t sfp_hwmon_is_visible(const void *data,
 		case hwmon_curr_crit:
 			if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN))
 				return 0;
-			/* fall through */
+			fallthrough;
 		case hwmon_curr_input:
 		case hwmon_curr_label:
 			return 0444;
@@ -618,7 +618,7 @@ static umode_t sfp_hwmon_is_visible(const void *data,
 		case hwmon_power_crit:
 			if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN))
 				return 0;
-			/* fall through */
+			fallthrough;
 		case hwmon_power_input:
 		case hwmon_power_label:
 			return 0444;
@@ -1872,7 +1872,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event)
 			dev_warn(sfp->dev, "hwmon probe failed: %d\n", err);
 
 		sfp_sm_mod_next(sfp, SFP_MOD_WAITDEV, 0);
-		/* fall through */
+		fallthrough;
 	case SFP_MOD_WAITDEV:
 		/* Ensure that the device is attached before proceeding */
 		if (sfp->sm_dev_state < SFP_DEV_DOWN)
@@ -1890,7 +1890,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event)
 			goto insert;
 
 		sfp_sm_mod_next(sfp, SFP_MOD_HPOWER, 0);
-		/* fall through */
+		fallthrough;
 	case SFP_MOD_HPOWER:
 		/* Enable high power mode */
 		err = sfp_sm_mod_hpower(sfp, true);
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index d82016dcde3b..4406b353123e 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -498,7 +498,7 @@ plip_receive(unsigned short nibble_timeout, struct net_device *dev,
 		*data_p = (c0 >> 3) & 0x0f;
 		write_data (dev, 0x10); /* send ACK */
 		*ns_p = PLIP_NB_1;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_NB_1:
 		cx = nibble_timeout;
@@ -594,7 +594,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl,
 			printk(KERN_DEBUG "%s: receive start\n", dev->name);
 		rcv->state = PLIP_PK_LENGTH_LSB;
 		rcv->nibble = PLIP_NB_BEGIN;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_LENGTH_LSB:
 		if (snd->state != PLIP_PK_DONE) {
@@ -615,7 +615,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl,
 				return TIMEOUT;
 		}
 		rcv->state = PLIP_PK_LENGTH_MSB;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_LENGTH_MSB:
 		if (plip_receive(nibble_timeout, dev,
@@ -638,7 +638,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl,
 		rcv->state = PLIP_PK_DATA;
 		rcv->byte = 0;
 		rcv->checksum = 0;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_DATA:
 		lbuf = rcv->skb->data;
@@ -651,7 +651,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl,
 			rcv->checksum += lbuf[--rcv->byte];
 		} while (rcv->byte);
 		rcv->state = PLIP_PK_CHECKSUM;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_CHECKSUM:
 		if (plip_receive(nibble_timeout, dev,
@@ -664,7 +664,7 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl,
 			return ERROR;
 		}
 		rcv->state = PLIP_PK_DONE;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_DONE:
 		/* Inform the upper layer for the arrival of a packet. */
@@ -710,7 +710,7 @@ plip_send(unsigned short nibble_timeout, struct net_device *dev,
 	case PLIP_NB_BEGIN:
 		write_data (dev, data & 0x0f);
 		*ns_p = PLIP_NB_1;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_NB_1:
 		write_data (dev, 0x10 | (data & 0x0f));
@@ -725,7 +725,7 @@ plip_send(unsigned short nibble_timeout, struct net_device *dev,
 		}
 		write_data (dev, 0x10 | (data >> 4));
 		*ns_p = PLIP_NB_2;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_NB_2:
 		write_data (dev, (data >> 4));
@@ -814,7 +814,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
 			      &snd->nibble, snd->length.b.lsb))
 			return TIMEOUT;
 		snd->state = PLIP_PK_LENGTH_MSB;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_LENGTH_MSB:
 		if (plip_send(nibble_timeout, dev,
@@ -823,7 +823,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
 		snd->state = PLIP_PK_DATA;
 		snd->byte = 0;
 		snd->checksum = 0;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_DATA:
 		do {
@@ -835,7 +835,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
 			snd->checksum += lbuf[--snd->byte];
 		} while (snd->byte);
 		snd->state = PLIP_PK_CHECKSUM;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_CHECKSUM:
 		if (plip_send(nibble_timeout, dev,
@@ -846,7 +846,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
 		dev_kfree_skb(snd->skb);
 		dev->stats.tx_packets++;
 		snd->state = PLIP_PK_DONE;
-		/* fall through */
+		fallthrough;
 
 	case PLIP_PK_DONE:
 		/* Close the connection */
@@ -935,7 +935,7 @@ plip_interrupt(void *dev_id)
 	switch (nl->connection) {
 	case PLIP_CN_CLOSING:
 		netif_wake_queue (dev);
-		/* fall through */
+		fallthrough;
 	case PLIP_CN_NONE:
 	case PLIP_CN_SEND:
 		rcv->state = PLIP_PK_TRIGGER;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3c11a77f5709..7959b5c2d11f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1590,10 +1590,10 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(tun->dev, xdp_prog, act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		this_cpu_inc(tun->pcpu_stats->rx_dropped);
 		break;
@@ -2417,7 +2417,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 		switch (err) {
 		case XDP_REDIRECT:
 			*flush = true;
-			/* fall through */
+			fallthrough;
 		case XDP_TX:
 			return 0;
 		case XDP_PASS:
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index a7fbc3ccd29e..c7bcfca7d70b 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -252,6 +252,7 @@ config USB_NET_CDC_EEM
 config USB_NET_CDC_NCM
 	tristate "CDC NCM support"
 	depends on USB_USBNET
+	select USB_NET_CDCETHER
 	default y
 	help
 	  This driver provides support for CDC NCM (Network Control Model
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 7e44110746dd..0717c18015c9 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -333,13 +333,13 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 		switch (speed) {
 		case SPEED_5000:
 			aqc111_data->phy_cfg |= AQ_ADV_5G;
-			/* fall-through */
+			fallthrough;
 		case SPEED_2500:
 			aqc111_data->phy_cfg |= AQ_ADV_2G5;
-			/* fall-through */
+			fallthrough;
 		case SPEED_1000:
 			aqc111_data->phy_cfg |= AQ_ADV_1G;
-			/* fall-through */
+			fallthrough;
 		case SPEED_100:
 			aqc111_data->phy_cfg |= AQ_ADV_100M;
 			/* fall-through */
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index e39f41efda3e..7bc6e8f856fe 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -296,7 +296,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal)
 
 	netdev_dbg(dev->net, "asix_get_phy_addr()\n");
 
-	if (ret < 0) {
+	if (ret < 2) {
 		netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret);
 		goto out;
 	}
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index d387bc7ac1b6..97ba67042d12 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -858,7 +858,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 		default:
 			dev_warn(&intf->dev,
 				 "Couldn't detect memory size, assuming 32k\n");
-			/* fall through */
+			fallthrough;
 		case 0x87654321:
 			catc_set_reg(catc, TxBufCount, 4);
 			catc_set_reg(catc, RxBufCount, 16);
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 9bdbd7b472a0..dba847f28096 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -97,7 +97,7 @@ static void tx_complete(struct urb *req)
 	case -ECONNRESET:
 	case -ESHUTDOWN:
 		dev->stats.tx_aborted_errors++;
-		/* fall through */
+		fallthrough;
 	default:
 		dev->stats.tx_errors++;
 		dev_dbg(&dev->dev, "TX error (%d)\n", status);
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index b91f92e4e5f2..915ac75b55fc 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -625,6 +625,10 @@ static const struct usb_device_id products[] = {
 	 USB_DEVICE(0x0a46, 0x1269),	/* DM9621A USB to Fast Ethernet Adapter */
 	 .driver_info = (unsigned long)&dm9601_info,
 	},
+	{
+	 USB_DEVICE(0x0586, 0x3427),	/* ZyXEL Keenetic Plus DSL xDSL modem */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
 	{},			// END
 };
 
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 442507f25aad..65b315bc60ab 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3192,7 +3192,7 @@ static void rx_complete(struct urb *urb)
 	case -EPIPE:
 		dev->net->stats.rx_errors++;
 		lan78xx_defer_kevent(dev, EVENT_RX_HALT);
-		/* FALLTHROUGH */
+		fallthrough;
 	case -ECONNRESET:				/* async unlink */
 	case -ESHUTDOWN:				/* hardware gone */
 		netif_dbg(dev, ifdown, dev->net,
@@ -3213,7 +3213,7 @@ static void rx_complete(struct urb *urb)
 	/* data overrun ... flush fifo? */
 	case -EOVERFLOW:
 		dev->net->stats.rx_over_errors++;
-		/* FALLTHROUGH */
+		fallthrough;
 
 	default:
 		state = rx_cleanup;
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 0ef7e1f443e3..e92cb51a2c77 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -629,7 +629,7 @@ static void write_bulk_callback(struct urb *urb)
 		return;
 	default:
 		netif_info(pegasus, tx_err, net, "TX status %d\n", status);
-		/* FALL THROUGH */
+		fallthrough;
 	case 0:
 		break;
 	}
@@ -1009,7 +1009,7 @@ static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCDEVPRIVATE:
 		data[0] = pegasus->phy;
-		/* fall through */
+		fallthrough;
 	case SIOCDEVPRIVATE + 1:
 		read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]);
 		res = 0;
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2b02fefd094d..b1770489aca5 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1682,7 +1682,7 @@ static void intr_callback(struct urb *urb)
 	case -ECONNRESET:	/* unlink */
 	case -ESHUTDOWN:
 		netif_device_detach(tp->netdev);
-		/* fall through */
+		fallthrough;
 	case -ENOENT:
 	case -EPROTO:
 		netif_info(tp, intr, tp->netdev,
@@ -3251,7 +3251,7 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable)
 			r8152_mdio_write(tp, MII_BMCR, data);
 
 			data = r8153_phy_status(tp, PHY_STAT_LAN_ON);
-			/* fall through */
+			fallthrough;
 
 		default:
 			if (data != PHY_STAT_LAN_ON)
@@ -4849,7 +4849,7 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
 				tp->ups_info.speed_duplex = NWAY_1000M_FULL;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			ret = -EINVAL;
 			goto out;
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index e7c630d37589..733f120c852b 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -843,7 +843,7 @@ static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCDEVPRIVATE:
 		data[0] = dev->phy;
-		/* fall through */
+		fallthrough;
 	case SIOCDEVPRIVATE + 1:
 		read_mii_word(dev, dev->phy, (data[1] & 0x1f), &data[3]);
 		break;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index e45935a5856a..2b2a841cd938 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -110,7 +110,7 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf)
 				if (!usb_endpoint_dir_in(&e->desc))
 					continue;
 				intr = 1;
-				/* FALLTHROUGH */
+				fallthrough;
 			case USB_ENDPOINT_XFER_BULK:
 				break;
 			default:
@@ -628,7 +628,7 @@ block:
 	/* data overrun ... flush fifo? */
 	case -EOVERFLOW:
 		dev->net->stats.rx_over_errors++;
-		// FALLTHROUGH
+		fallthrough;
 
 	default:
 		state = rx_cleanup;
@@ -1530,7 +1530,7 @@ static void usbnet_bh (struct timer_list *t)
 			continue;
 		case tx_done:
 			kfree(entry->urb->sg);
-			/* fall through */
+			fallthrough;
 		case rx_cleanup:
 			usb_free_urb (entry->urb);
 			dev_kfree_skb (skb);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index e56cd562a664..a475f48d43c4 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -610,10 +610,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
-			/* fall through */
+			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(rq->dev, xdp_prog, act);
-			/* fall through */
+			fallthrough;
 		case XDP_DROP:
 			stats->xdp_drops++;
 			goto err_xdp;
@@ -745,10 +745,10 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 		goto xdp_xmit;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(rq->dev, xdp_prog, act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		stats->xdp_drops++;
 		goto xdp_drop;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0ada48edf749..263b005981bd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -724,7 +724,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
-			/* fall through */
+			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
 		case XDP_DROP:
@@ -922,10 +922,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
-			/* fall through */
+			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
-			/* fall through */
+			fallthrough;
 		case XDP_DROP:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index def27afa1c69..1014693a5ceb 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -743,7 +743,7 @@ vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter,
 	case ESP_V4_FLOW:
 		if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4)
 			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			/* fallthrough */
+		fallthrough;
 	case SCTP_V4_FLOW:
 	case IPV4_FLOW:
 		info->data |= RXH_IP_SRC | RXH_IP_DST;
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 7bcee41905cf..3ca4daf63389 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -295,14 +295,13 @@ static int dlci_close(struct net_device *dev)
 {
 	struct dlci_local	*dlp;
 	struct frad_local	*flp;
-	int			err;
 
 	netif_stop_queue(dev);
 
 	dlp = netdev_priv(dev);
 
 	flp = netdev_priv(dlp->slave);
-	err = (*flp->deactivate)(dlp->slave, dev);
+	(*flp->deactivate)(dlp->slave, dev);
 
 	return 0;
 }
diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c
index dfc16770458d..9b00708676cf 100644
--- a/drivers/net/wan/hdlc.c
+++ b/drivers/net/wan/hdlc.c
@@ -229,7 +229,8 @@ static void hdlc_setup_dev(struct net_device *dev)
 	dev->min_mtu		 = 68;
 	dev->max_mtu		 = HDLC_MAX_MTU;
 	dev->type		 = ARPHRD_RAWHDLC;
-	dev->hard_header_len	 = 16;
+	dev->hard_header_len	 = 0;
+	dev->needed_headroom	 = 0;
 	dev->addr_len		 = 0;
 	dev->header_ops		 = &hdlc_null_ops;
 }
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index d8cba3625c18..444130655d8e 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -370,6 +370,7 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr)
 		memcpy(&state(hdlc)->settings, &new_settings, size);
 		spin_lock_init(&state(hdlc)->lock);
 		dev->header_ops = &cisco_header_ops;
+		dev->hard_header_len = sizeof(struct hdlc_header);
 		dev->type = ARPHRD_CISCO;
 		call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev);
 		netif_dormant_on(dev);
diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index f70336bb6f52..f52b9fed0593 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -107,8 +107,14 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	int result;
 
+	/* There should be a pseudo header of 1 byte added by upper layers.
+	 * Check to make sure it is there before reading it.
+	 */
+	if (skb->len < 1) {
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
 
-	/* X.25 to LAPB */
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:	/* Data to be transmitted */
 		skb_pull(skb, 1);
@@ -294,6 +300,15 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 			return result;
 
 		memcpy(&state(hdlc)->settings, &new_settings, size);
+
+		/* There's no header_ops so hard_header_len should be 0. */
+		dev->hard_header_len = 0;
+		/* When transmitting data:
+		 * first we'll remove a pseudo header of 1 byte,
+		 * then we'll prepend an LAPB header of at most 3 bytes.
+		 */
+		dev->needed_headroom = 3 - 1;
+
 		dev->type = ARPHRD_X25;
 		call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev);
 		netif_dormant_off(dev);
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 1ea15f2123ed..732a6c1851f5 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -173,7 +173,7 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 	case X25_IFACE_DISCONNECT:
 		if ((err = lapb_disconnect_request(dev)) != LAPB_OK)
 			pr_err("lapb_disconnect_request err: %d\n", err);
-		/* Fall thru */
+		fallthrough;
 	default:
 		goto drop;
 	}
@@ -210,6 +210,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb)
 
 	skb->dev = dev = lapbeth->ethdev;
 
+	skb_reset_network_header(skb);
+
 	dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0);
 
 	dev_queue_xmit(skb);
@@ -340,6 +342,7 @@ static int lapbeth_new_device(struct net_device *dev)
 	 */
 	ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len
 					   + dev->needed_headroom;
+	ndev->needed_tailroom = dev->needed_tailroom;
 
 	lapbeth = netdev_priv(ndev);
 	lapbeth->axdev = ndev;
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index 77ccf3672ede..bc2c1c7fb1a4 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -413,7 +413,7 @@ static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int
 		case SDLA_RET_NO_BUFS:
 			if (cmd == SDLA_INFORMATION_WRITE)
 				break;
-			/* Else, fall through */
+			fallthrough;
 
 		default: 
 			netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n",
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index de7984463595..7ee980575208 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -330,7 +330,7 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
 		if (err != LAPB_OK)
 			netdev_err(dev, "lapb_disconnect_request error: %d\n",
 				   err);
-		/* fall through */
+		fallthrough;
 	default:
 		kfree_skb(skb);
 		return NETDEV_TX_OK;
diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
index 4fe7c7e132c4..9afed3b133d3 100644
--- a/drivers/net/wimax/i2400m/control.c
+++ b/drivers/net/wimax/i2400m/control.c
@@ -352,7 +352,7 @@ void i2400m_report_tlv_system_state(struct i2400m *i2400m,
 
 	case I2400M_SS_IDLE:
 		d_printf(1, dev, "entering BS-negotiated idle mode\n");
-		/* Fall through */
+		fallthrough;
 	case I2400M_SS_DISCONNECTING:
 	case I2400M_SS_DATA_PATH_CONNECTED:
 		wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED);
diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
index 1f7709d24f35..27ab233650d5 100644
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ b/drivers/net/wimax/i2400m/usb-fw.c
@@ -135,7 +135,7 @@ retry:
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
-		/* fall through */
+		fallthrough;
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c
index 3a0e7226768a..3ba9d70cca1b 100644
--- a/drivers/net/wimax/i2400m/usb-tx.c
+++ b/drivers/net/wimax/i2400m/usb-tx.c
@@ -136,7 +136,7 @@ retry:
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
-		/* fall through */
+		fallthrough;
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c
index 9659f9e1aaa6..b684e97ac976 100644
--- a/drivers/net/wimax/i2400m/usb.c
+++ b/drivers/net/wimax/i2400m/usb.c
@@ -195,7 +195,7 @@ retry:
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
-		/* fall through */
+		fallthrough;
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index 6b7532f7c936..ff96f22648ef 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -393,7 +393,7 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
 
 	case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
 		seq_puts(m, "Hash Algorithm: NONE\n");
-		/* FALLTHRU */
+		fallthrough;
 	default:
 		return;
 	}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7e62a6ee7622..f1c1624cec8f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -448,7 +448,7 @@ static void frontend_changed(struct xenbus_device *dev,
 		set_backend_state(be, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
-		/* fall through - if not online */
+		fallthrough;	/* if not online */
 	case XenbusStateUnknown:
 		set_backend_state(be, XenbusStateClosed);
 		device_unregister(&dev->dev);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 458be6882b98..3e9895bec15f 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2341,7 +2341,7 @@ static void netback_changed(struct xenbus_device *dev,
 	case XenbusStateClosed:
 		if (dev->state == XenbusStateClosed)
 			break;
-		/* Fall through - Missed the backend's CLOSING state. */
+		fallthrough;	/* Missed the backend's CLOSING state */
 	case XenbusStateClosing:
 		xenbus_frontend_closed(dev);
 		break;
diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c
index 346e084387f7..f7464bd6d57c 100644
--- a/drivers/nfc/pn533/pn533.c
+++ b/drivers/nfc/pn533/pn533.c
@@ -2321,7 +2321,7 @@ static int pn533_transceive(struct nfc_dev *nfc_dev,
 
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		/* jumbo frame ? */
 		if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
@@ -2448,7 +2448,7 @@ static void pn533_wq_mi_recv(struct work_struct *work)
 
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		skb_put_u8(skb, 1); /*TG*/
 
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index 0b9ca6d20ffa..8874d605b14f 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -611,7 +611,7 @@ static void st21nfca_im_recv_dep_res_cb(void *context, struct sk_buff *skb,
 		switch (ST21NFCA_NFC_DEP_PFB_TYPE(dep_res->pfb)) {
 		case ST21NFCA_NFC_DEP_PFB_ACK_NACK_PDU:
 			pr_err("Received a ACK/NACK PDU\n");
-			/* fall through */
+			fallthrough;
 		case ST21NFCA_NFC_DEP_PFB_I_PDU:
 			info->dep_info.curr_nfc_dep_pni =
 			    ST21NFCA_NFC_DEP_PFB_PNI(dep_res->pfb + 1);
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index 9642971e89ce..457854765983 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -966,7 +966,7 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev,
 	rc = down_killable(&stcontext->exchange_lock);
 	if (rc) {
 		WARN(1, "Semaphore is not found up in st95hf_in_send_cmd\n");
-		return rc;
+		goto free_skb_resp;
 	}
 
 	rc = st95hf_spi_send(&stcontext->spicontext, skb->data,
diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c
index e46adaac1c63..3bd97c73f983 100644
--- a/drivers/nfc/trf7970a.c
+++ b/drivers/nfc/trf7970a.c
@@ -1153,7 +1153,7 @@ static int trf7970a_switch_rf(struct nfc_digital_dev *ddev, bool on)
 			dev_err(trf->dev, "%s - Invalid request: %d %d\n",
 				__func__, trf->state, on);
 			ret = -EINVAL;
-			/* FALLTHROUGH */
+			fallthrough;
 		case TRF7970A_ST_IDLE:
 		case TRF7970A_ST_IDLE_RX_BLOCKED:
 		case TRF7970A_ST_WAIT_FOR_RX_DATA:
@@ -1960,7 +1960,7 @@ static void trf7970a_shutdown(struct trf7970a *trf)
 	case TRF7970A_ST_WAIT_TO_ISSUE_EOF:
 	case TRF7970A_ST_LISTENING:
 		trf7970a_send_err_upstream(trf, -ECANCELED);
-		/* FALLTHROUGH */
+		fallthrough;
 	case TRF7970A_ST_IDLE:
 	case TRF7970A_ST_IDLE_RX_BLOCKED:
 		trf7970a_switch_rf_off(trf);
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index e6d1f5b298f3..4a02561cfb96 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1483,7 +1483,7 @@ static void ntb_rx_copy_callback(void *data,
 		case DMA_TRANS_READ_FAILED:
 		case DMA_TRANS_WRITE_FAILED:
 			entry->errors++;
-			/* fall through */
+			fallthrough;
 		case DMA_TRANS_ABORTED:
 		{
 			struct ntb_transport_qp *qp = entry->qp;
@@ -1739,7 +1739,7 @@ static void ntb_tx_copy_callback(void *data,
 		case DMA_TRANS_READ_FAILED:
 		case DMA_TRANS_WRITE_FAILED:
 			entry->errors++;
-			/* fall through */
+			fallthrough;
 		case DMA_TRANS_ABORTED:
 		{
 			void __iomem *offset =
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 61374def5155..b59032e0859b 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -529,6 +529,7 @@ static DEVICE_ATTR_ADMIN_RW(activate);
 static struct attribute *nvdimm_firmware_attributes[] = {
 	&dev_attr_activate.attr,
 	&dev_attr_result.attr,
+	NULL,
 };
 
 static umode_t nvdimm_firmware_visible(struct kobject *kobj, struct attribute *a, int n)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 88cff309d8e4..f3a61a24d45f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -241,17 +241,6 @@ static blk_status_t nvme_error_status(u16 status)
 	}
 }
 
-static inline bool nvme_req_needs_retry(struct request *req)
-{
-	if (blk_noretry_request(req))
-		return false;
-	if (nvme_req(req)->status & NVME_SC_DNR)
-		return false;
-	if (nvme_req(req)->retries >= nvme_max_retries)
-		return false;
-	return true;
-}
-
 static void nvme_retry_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
@@ -268,34 +257,67 @@ static void nvme_retry_req(struct request *req)
 	blk_mq_delay_kick_requeue_list(req->q, delay);
 }
 
-void nvme_complete_rq(struct request *req)
+enum nvme_disposition {
+	COMPLETE,
+	RETRY,
+	FAILOVER,
+};
+
+static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 {
-	blk_status_t status = nvme_error_status(nvme_req(req)->status);
+	if (likely(nvme_req(req)->status == 0))
+		return COMPLETE;
 
-	trace_nvme_complete_rq(req);
+	if (blk_noretry_request(req) ||
+	    (nvme_req(req)->status & NVME_SC_DNR) ||
+	    nvme_req(req)->retries >= nvme_max_retries)
+		return COMPLETE;
 
-	nvme_cleanup_cmd(req);
+	if (req->cmd_flags & REQ_NVME_MPATH) {
+		if (nvme_is_path_error(nvme_req(req)->status) ||
+		    blk_queue_dying(req->q))
+			return FAILOVER;
+	} else {
+		if (blk_queue_dying(req->q))
+			return COMPLETE;
+	}
 
-	if (nvme_req(req)->ctrl->kas)
-		nvme_req(req)->ctrl->comp_seen = true;
+	return RETRY;
+}
 
-	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
-			return;
+static inline void nvme_end_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-		if (!blk_queue_dying(req->q)) {
-			nvme_retry_req(req);
-			return;
-		}
-	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		   req_op(req) == REQ_OP_ZONE_APPEND) {
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
-	}
 
 	nvme_trace_bio_complete(req, status);
 	blk_mq_end_request(req, status);
 }
+
+void nvme_complete_rq(struct request *req)
+{
+	trace_nvme_complete_rq(req);
+	nvme_cleanup_cmd(req);
+
+	if (nvme_req(req)->ctrl->kas)
+		nvme_req(req)->ctrl->comp_seen = true;
+
+	switch (nvme_decide_disposition(req)) {
+	case COMPLETE:
+		nvme_end_req(req);
+		return;
+	case RETRY:
+		nvme_retry_req(req);
+		return;
+	case FAILOVER:
+		nvme_failover_req(req);
+		return;
+	}
+}
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
 bool nvme_cancel_request(struct request *req, void *data, bool reserved)
@@ -330,7 +352,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -340,7 +362,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -350,7 +372,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -361,7 +383,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -371,7 +393,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_DELETING:
 		case NVME_CTRL_DEAD:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -380,7 +402,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_DELETING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -2004,13 +2026,49 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
+static inline bool nvme_first_scan(struct gendisk *disk)
+{
+	/* nvme_alloc_ns() scans the disk prior to adding it */
+	return !(disk->flags & GENHD_FL_UP);
+}
+
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	u32 iob;
+
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
+		iob = ctrl->max_hw_sectors;
+	else
+		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
+
+	if (!iob)
+		return;
+
+	if (!is_power_of_2(iob)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring unaligned IO boundary:%u\n",
+				ns->disk->disk_name, iob);
+		return;
+	}
+
+	if (blk_queue_is_zoned(ns->disk->queue)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring zoned namespace IO boundary\n",
+				ns->disk->disk_name);
+		return;
+	}
+
+	blk_queue_chunk_sectors(ns->queue, iob);
+}
+
 static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
-	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
@@ -2038,12 +2096,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		return -ENODEV;
 	}
 
-	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ctrl->max_hw_sectors))
-		iob = ctrl->max_hw_sectors;
-	else
-		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
-
 	ns->features = 0;
 	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
@@ -2075,8 +2127,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		}
 	}
 
-	if (iob)
-		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
+	nvme_set_chunk_sectors(ns, id);
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
@@ -2965,14 +3016,14 @@ static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
 	struct nvme_cel *cel, *ret = NULL;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_for_each_entry(cel, &ctrl->cels, entry) {
 		if (cel->csi == csi) {
 			ret = cel;
 			break;
 		}
 	}
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 
 	return ret;
 }
@@ -2999,9 +3050,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 
 	cel->csi = csi;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_add_tail(&cel->entry, &ctrl->cels);
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 out:
 	*log = &cel->log;
 	return 0;
@@ -3474,10 +3525,6 @@ static ssize_t nvme_sysfs_delete(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	/* Can't delete non-created controllers */
-	if (!ctrl->created)
-		return -EBUSY;
-
 	if (device_remove_file_self(dev, attr))
 		nvme_delete_ctrl_sync(ctrl);
 	return count;
@@ -3654,6 +3701,10 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 		return 0;
 	if (a == &dev_attr_hostid.attr && !ctrl->opts)
 		return 0;
+	if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts)
+		return 0;
 
 	return a->mode;
 }
@@ -4348,7 +4399,6 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
 	}
-	ctrl->created = true;
 }
 EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
@@ -4368,7 +4418,7 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_subsystem *subsys = ctrl->subsys;
 	struct nvme_cel *cel, *next;
 
-	if (subsys && ctrl->instance != subsys->instance)
+	if (!subsys || ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
 	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
@@ -4512,7 +4562,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
 
@@ -4523,6 +4573,7 @@ void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 			break;
 	}
 	up_read(&ctrl->namespaces_rwsem);
+	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4ec4829d6233..8575724734e0 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -565,10 +565,14 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	struct nvme_request *req = nvme_req(rq);
 
 	/*
-	 * If we are in some state of setup or teardown only allow
-	 * internally generated commands.
+	 * currently we have a problem sending passthru commands
+	 * on the admin_q if the controller is not LIVE because we can't
+	 * make sure that they are going out after the admin connect,
+	 * controller enable and/or other commands in the initialization
+	 * sequence. until the controller will be LIVE, fail with
+	 * BLK_STS_RESOURCE so that they will be rescheduled.
 	 */
-	if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
+	if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
 		return false;
 
 	/*
@@ -576,9 +580,8 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	 * which is require to set the queue live in the appropinquate states.
 	 */
 	switch (ctrl->state) {
-	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
-		if (nvme_is_fabrics(req->cmd) &&
+		if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
 			return true;
 		break;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index eae43bb444e0..e8ef42b9d50c 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2035,7 +2035,7 @@ done:
 	}
 
 	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
-	if (!nvme_end_request(rq, status, result))
+	if (!nvme_try_complete_req(rq, status, result))
 		nvme_fc_complete_rq(rq);
 
 check_error:
@@ -2078,7 +2078,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.cmddma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - cmdiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 		goto out_on_error;
 	}
 
@@ -2088,7 +2088,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.rspdma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - rspiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 	}
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
@@ -2160,6 +2160,7 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl)
 	struct nvme_fc_fcp_op *aen_op;
 	int i;
 
+	cancel_work_sync(&ctrl->ctrl.async_event_work);
 	aen_op = ctrl->aen_ops;
 	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) {
 		__nvme_fc_exit_request(ctrl, aen_op);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 3ded54d2c9c6..d4ba736c6c89 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -65,51 +65,30 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	}
 }
 
-bool nvme_failover_req(struct request *req)
+void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
-	u16 status = nvme_req(req)->status;
+	u16 status = nvme_req(req)->status & 0x7ff;
 	unsigned long flags;
 
-	switch (status & 0x7ff) {
-	case NVME_SC_ANA_TRANSITION:
-	case NVME_SC_ANA_INACCESSIBLE:
-	case NVME_SC_ANA_PERSISTENT_LOSS:
-		/*
-		 * If we got back an ANA error we know the controller is alive,
-		 * but not ready to serve this namespaces.  The spec suggests
-		 * we should update our general state here, but due to the fact
-		 * that the admin and I/O queues are not serialized that is
-		 * fundamentally racy.  So instead just clear the current path,
-		 * mark the the path as pending and kick of a re-read of the ANA
-		 * log page ASAP.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		if (ns->ctrl->ana_log_buf) {
-			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
-			queue_work(nvme_wq, &ns->ctrl->ana_work);
-		}
-		break;
-	case NVME_SC_HOST_PATH_ERROR:
-	case NVME_SC_HOST_ABORTED_CMD:
-		/*
-		 * Temporary transport disruption in talking to the controller.
-		 * Try to send on a new path.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		break;
-	default:
-		/* This was a non-ANA error so follow the normal error path. */
-		return false;
+	nvme_mpath_clear_current_path(ns);
+
+	/*
+	 * If we got back an ANA error, we know the controller is alive but not
+	 * ready to serve this namespace.  Kick of a re-read of the ANA
+	 * information page, and just try any other available path for now.
+	 */
+	if (nvme_is_ana_error(status) && ns->ctrl->ana_log_buf) {
+		set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+		queue_work(nvme_wq, &ns->ctrl->ana_work);
 	}
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
-	blk_mq_end_request(req, 0);
 
+	blk_mq_end_request(req, 0);
 	kblockd_schedule_work(&ns->head->requeue_work);
-	return true;
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -233,7 +212,7 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
 static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 		int node, struct nvme_ns *old)
 {
-	struct nvme_ns *ns, *found, *fallback = NULL;
+	struct nvme_ns *ns, *found = NULL;
 
 	if (list_is_singular(&head->list)) {
 		if (nvme_path_is_disabled(old))
@@ -252,18 +231,22 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			goto out;
 		}
 		if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
-			fallback = ns;
+			found = ns;
 	}
 
-	/* No optimized path found, re-check the current path */
+	/*
+	 * The loop above skips the current path for round-robin semantics.
+	 * Fall back to the current path if either:
+	 *  - no other optimized path found and current is optimized,
+	 *  - no other usable path found and current is usable.
+	 */
 	if (!nvme_path_is_disabled(old) &&
-	    old->ana_state == NVME_ANA_OPTIMIZED) {
-		found = old;
-		goto out;
-	}
-	if (!fallback)
+	    (old->ana_state == NVME_ANA_OPTIMIZED ||
+	     (!found && old->ana_state == NVME_ANA_NONOPTIMIZED)))
+		return old;
+
+	if (!found)
 		return NULL;
-	found = fallback;
 out:
 	rcu_assign_pointer(head->current_path[node], found);
 	return found;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ebb8c3ed3885..9fd45ff656da 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -307,7 +307,6 @@ struct nvme_ctrl {
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
 	unsigned long events;
-	bool created;
 
 #ifdef CONFIG_NVME_MULTIPATH
 	/* asymmetric namespace access: */
@@ -523,7 +522,31 @@ static inline u32 nvme_bytes_to_numd(size_t len)
 	return (len >> 2) - 1;
 }
 
-static inline bool nvme_end_request(struct request *req, __le16 status,
+static inline bool nvme_is_ana_error(u16 status)
+{
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool nvme_is_path_error(u16 status)
+{
+	/* check for a status code type of 'path related status' */
+	return (status & 0x700) == 0x300;
+}
+
+/*
+ * Fill in the status and result information from the CQE, and then figure out
+ * if blk-mq will need to use IPI magic to complete the request, and if yes do
+ * so.  If not let the caller complete the request without an indirect function
+ * call.
+ */
+static inline bool nvme_try_complete_req(struct request *req, __le16 status,
 		union nvme_result result)
 {
 	struct nvme_request *rq = nvme_req(req);
@@ -581,7 +604,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl);
 void nvme_sync_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
 #define NVME_QID_ANY -1
@@ -629,7 +652,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
-bool nvme_failover_req(struct request *req);
+void nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
@@ -688,9 +711,8 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
 }
 
-static inline bool nvme_failover_req(struct request *req)
+static inline void nvme_failover_req(struct request *req)
 {
-	return false;
 }
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ba725ae47305..899d2f4d7ab6 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -120,7 +120,7 @@ struct nvme_dev {
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	u16 q_depth;
+	u32 q_depth;
 	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
@@ -157,13 +157,13 @@ struct nvme_dev {
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
 	int ret;
-	u16 n;
+	u32 n;
 
-	ret = kstrtou16(val, 10, &n);
+	ret = kstrtou32(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_ushort(val, kp);
+	return param_set_uint(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -195,7 +195,7 @@ struct nvme_queue {
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
-	u16 q_depth;
+	u32 q_depth;
 	u16 cq_vector;
 	u16 sq_tail;
 	u16 cq_head;
@@ -961,7 +961,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 
 	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
-	if (!nvme_end_request(req, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
 		nvme_pci_complete_rq(req);
 }
 
@@ -1244,13 +1244,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_CONNECTING:
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
-		/* fall through */
+		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, true);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
+		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
 	case NVME_CTRL_RESETTING:
 		return BLK_EH_RESET_TIMER;
@@ -1267,10 +1267,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
 
-		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	}
 
@@ -2320,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
-	dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1,
+	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
 	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
@@ -2460,7 +2460,8 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
-						PAGE_SIZE, PAGE_SIZE, 0);
+						NVME_CTRL_PAGE_SIZE,
+						NVME_CTRL_PAGE_SIZE, 0);
 	if (!dev->prp_page_pool)
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 44c76ffbb264..9e378d0a0c01 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,6 +122,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -834,6 +835,7 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 	}
 	if (ctrl->async_event_sqe.data) {
+		cancel_work_sync(&ctrl->ctrl.async_event_work);
 		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
 				sizeof(struct nvme_command), DMA_TO_DEVICE);
 		ctrl->async_event_sqe.data = NULL;
@@ -975,7 +977,15 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(&ctrl->ctrl);
-		nvme_wait_freeze(&ctrl->ctrl);
+		if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
 			ctrl->ctrl.queue_count - 1);
 		nvme_unfreeze(&ctrl->ctrl);
@@ -983,6 +993,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(&ctrl->ctrl);
+	nvme_rdma_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
@@ -997,6 +1010,7 @@ out_free_io_queues:
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
@@ -1007,11 +1021,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
@@ -1025,6 +1041,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1180,6 +1197,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
@@ -1189,7 +1207,7 @@ static void nvme_rdma_end_request(struct nvme_rdma_request *req)
 
 	if (!refcount_dec_and_test(&req->ref))
 		return;
-	if (!nvme_end_request(rq, req->status, req->result))
+	if (!nvme_try_complete_req(rq, req->status, req->result))
 		nvme_rdma_complete_rq(rq);
 }
 
@@ -1915,7 +1933,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 		nvme_rdma_destroy_queue_ib(queue);
-		/* fall through */
+		fallthrough;
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);
@@ -1946,6 +1964,22 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	return 0;
 }
 
+static void nvme_rdma_complete_timed_out(struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&ctrl->teardown_lock);
+	nvme_rdma_stop_queue(queue);
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&ctrl->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
@@ -1956,29 +1990,29 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
-		 * or we are already started error recovery. all outstanding
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_rdma_teardown_io_queues(ctrl, false);
-		nvme_rdma_teardown_admin_queue(ctrl, false);
+		nvme_rdma_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
 	nvme_rdma_error_recovery(ctrl);
-
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2278,6 +2312,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 62fbaecdc960..8f4f29f18b8c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,6 +124,7 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
+	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -464,6 +465,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
@@ -481,7 +483,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		return -EINVAL;
 	}
 
-	if (!nvme_end_request(rq, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -672,7 +674,7 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
 	union nvme_result res = {};
 
-	if (!nvme_end_request(rq, cpu_to_le16(status << 1), res))
+	if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
 		nvme_complete_rq(rq);
 }
 
@@ -866,7 +868,6 @@ static void nvme_tcp_state_change(struct sock *sk)
 	case TCP_LAST_ACK:
 	case TCP_FIN_WAIT1:
 	case TCP_FIN_WAIT2:
-		/* fallthrough */
 		nvme_tcp_error_recovery(&queue->ctrl->ctrl);
 		break;
 	default:
@@ -1527,7 +1528,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 
 	if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return;
-
 	__nvme_tcp_stop_queue(queue);
 }
 
@@ -1596,6 +1596,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
 static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (to_tcp_ctrl(ctrl)->async_req.pdu) {
+		cancel_work_sync(&ctrl->async_event_work);
 		nvme_tcp_free_async_req(to_tcp_ctrl(ctrl));
 		to_tcp_ctrl(ctrl)->async_req.pdu = NULL;
 	}
@@ -1782,7 +1783,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(ctrl);
-		nvme_wait_freeze(ctrl);
+		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
 			ctrl->queue_count - 1);
 		nvme_unfreeze(ctrl);
@@ -1790,6 +1799,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(ctrl);
+	nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
@@ -1875,6 +1887,7 @@ out_free_queue:
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
@@ -1885,13 +1898,16 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		return;
+		goto out;
+	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
@@ -1903,6 +1919,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
+out:
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2149,40 +2167,55 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
 
+static void nvme_tcp_complete_timed_out(struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
+	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_tcp_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
-	dev_warn(ctrl->ctrl.device,
+	dev_warn(ctrl->device,
 		"queue %d: timeout request %#x type %d\n",
 		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (ctrl->state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
-		 * or we are already started error recovery. all outstanding
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
-		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
+		nvme_tcp_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
-	nvme_tcp_error_recovery(&ctrl->ctrl);
-
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
+	nvme_tcp_error_recovery(ctrl);
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2423,6 +2456,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 74b2b61c773b..37e1d7784e17 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1136,6 +1136,7 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
 	up_write(&nvmet_config_sem);
 
 	kfree_rcu(new_model, rcuhead);
+	kfree(new_model_number);
 
 	return count;
 }
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b92f45f5cd5b..b7b63330b5ef 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -73,7 +73,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
 		status = NVME_SC_ACCESS_DENIED;
 		break;
 	case -EIO:
-		/* FALLTHRU */
+		fallthrough;
 	default:
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		status = NVME_SC_INTERNAL | NVME_SC_DNR;
@@ -397,6 +397,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
@@ -406,6 +409,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 
 static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
 
 	cancel_delayed_work_sync(&ctrl->ka_work);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 55bafd56166a..e6861cc10e7d 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -2342,9 +2342,9 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
-			spin_lock(&fod->flock);
+			spin_lock_irqsave(&fod->flock, flags);
 			fod->abort = true;
-			spin_unlock(&fod->flock);
+			spin_unlock_irqrestore(&fod->flock, flags);
 
 			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c97e60b71bbc..3da067a8311e 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -812,7 +812,7 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 			break;
 
 		/* Fall-Thru to RSP handling */
-		/* FALLTHRU */
+		fallthrough;
 
 	case NVMET_FCOP_RSP:
 		if (fcpreq) {
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 3dd6f566a240..125dde3f410e 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -139,7 +139,6 @@ static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
 		req->error_loc = offsetof(struct nvme_rw_command, nsid);
 		break;
 	case BLK_STS_IOERR:
-		/* fallthru */
 	default:
 		status = NVME_SC_INTERNAL | NVME_SC_DNR;
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 4884ef1e46a2..0d6008cf66a2 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -115,7 +115,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 			return;
 		}
 
-		if (!nvme_end_request(rq, cqe->status, cqe->result))
+		if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
 			nvme_loop_complete_rq(rq);
 	}
 }
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 89d91dc999a6..8bd7f656e240 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -165,7 +165,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, status);
-	blk_put_request(rq);
+	blk_mq_free_request(rq);
 }
 
 static void nvmet_passthru_req_done(struct request *rq,
@@ -175,7 +175,7 @@ static void nvmet_passthru_req_done(struct request *rq,
 
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, nvme_req(rq)->status);
-	blk_put_request(rq);
+	blk_mq_free_request(rq);
 }
 
 static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
@@ -230,7 +230,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		if (unlikely(!ns)) {
 			pr_err("failed to get passthru ns nsid:%u\n", nsid);
 			status = NVME_SC_INVALID_NS | NVME_SC_DNR;
-			goto fail_out;
+			goto out;
 		}
 
 		q = ns->queue;
@@ -238,16 +238,15 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 
 	rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(rq)) {
-		rq = NULL;
 		status = NVME_SC_INTERNAL;
-		goto fail_out;
+		goto out_put_ns;
 	}
 
 	if (req->sg_cnt) {
 		ret = nvmet_passthru_map_sg(req, rq);
 		if (unlikely(ret)) {
 			status = NVME_SC_INTERNAL;
-			goto fail_out;
+			goto out_put_req;
 		}
 	}
 
@@ -274,11 +273,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 
 	return;
 
-fail_out:
+out_put_req:
+	blk_mq_free_request(rq);
+out_put_ns:
 	if (ns)
 		nvme_put_ns(ns);
+out:
 	nvmet_req_complete(req, status);
-	blk_put_request(rq);
 }
 
 /*
@@ -326,6 +327,10 @@ static u16 nvmet_setup_passthru_command(struct nvmet_req *req)
 
 u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
 {
+	/* Reject any commands with non-sgl flags set (ie. fused commands) */
+	if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL)
+		return NVME_SC_INVALID_FIELD;
+
 	switch (req->cmd->common.opcode) {
 	case nvme_cmd_resv_register:
 	case nvme_cmd_resv_report:
@@ -396,6 +401,10 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
 
 u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 {
+	/* Reject any commands with non-sgl flags set (ie. fused commands) */
+	if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL)
+		return NVME_SC_INVALID_FIELD;
+
 	/*
 	 * Passthru all vendor specific commands
 	 */
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 3ccb59260b4a..ae6620489457 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1758,7 +1758,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
 			schedule_delayed_work(&port->repair_work, 0);
 			break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case RDMA_CM_EVENT_DISCONNECTED:
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
 		nvmet_rdma_queue_disconnect(queue);
@@ -1769,7 +1769,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_REJECTED:
 		pr_debug("Connection rejected: %s\n",
 			 rdma_reject_msg(cm_id, event->status));
-		/* FALLTHROUGH */
+		fallthrough;
 	case RDMA_CM_EVENT_UNREACHABLE:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 		nvmet_rdma_queue_connect_fail(cm_id, queue);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 9eda91162fe4..8e0d766d2722 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -160,6 +160,11 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd);
 static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
 		struct nvmet_tcp_cmd *cmd)
 {
+	if (unlikely(!queue->nr_cmds)) {
+		/* We didn't allocate cmds yet, send 0xffff */
+		return USHRT_MAX;
+	}
+
 	return cmd - queue->cmds;
 }
 
@@ -866,7 +871,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
 
-	cmd = &queue->cmds[data->ttag];
+	if (likely(queue->nr_cmds))
+		cmd = &queue->cmds[data->ttag];
+	else
+		cmd = &queue->connect;
 
 	if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) {
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 590493e04b01..da4f7341323f 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -128,15 +128,29 @@ static unsigned int of_bus_pci_get_flags(const __be32 *addr)
  * PCI bus specific translator
  */
 
+static bool of_node_is_pcie(struct device_node *np)
+{
+	bool is_pcie = of_node_name_eq(np, "pcie");
+
+	if (is_pcie)
+		pr_warn_once("%pOF: Missing device_type\n", np);
+
+	return is_pcie;
+}
+
 static int of_bus_pci_match(struct device_node *np)
 {
 	/*
  	 * "pciex" is PCI Express
 	 * "vci" is for the /chaos bridge on 1st-gen PCI powermacs
 	 * "ht" is hypertransport
+	 *
+	 * If none of the device_type match, and that the node name is
+	 * "pcie", accept the device as PCI (with a warning).
 	 */
 	return of_node_is_type(np, "pci") || of_node_is_type(np, "pciex") ||
-		of_node_is_type(np, "vci") || of_node_is_type(np, "ht");
+		of_node_is_type(np, "vci") || of_node_is_type(np, "ht") ||
+		of_node_is_pcie(np);
 }
 
 static void of_bus_pci_count_cells(struct device_node *np,
@@ -985,6 +999,11 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 			/* Don't error out as we'd break some existing DTs */
 			continue;
 		}
+		if (range.cpu_addr == OF_BAD_ADDR) {
+			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
+			       range.bus_addr, node);
+			continue;
+		}
 		dma_offset = range.cpu_addr - range.bus_addr;
 
 		/* Take lower and upper limits */
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 9d7fb45b1786..3ca7543142bf 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -893,8 +893,10 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		 * have OPP table for the device, while others don't and
 		 * opp_set_rate() just needs to behave like clk_set_rate().
 		 */
-		if (!_get_opp_count(opp_table))
-			return 0;
+		if (!_get_opp_count(opp_table)) {
+			ret = 0;
+			goto put_opp_table;
+		}
 
 		if (!opp_table->required_opp_tables && !opp_table->regulators &&
 		    !opp_table->paths) {
@@ -905,7 +907,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 		ret = _set_opp_bw(opp_table, NULL, dev, true);
 		if (ret)
-			return ret;
+			goto put_opp_table;
 
 		if (opp_table->regulator_enabled) {
 			regulator_disable(opp_table->regulators[0]);
@@ -932,10 +934,13 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	/* Return early if nothing to do */
 	if (old_freq == freq) {
-		dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
-			__func__, freq);
-		ret = 0;
-		goto put_opp_table;
+		if (!opp_table->required_opp_tables && !opp_table->regulators &&
+		    !opp_table->paths) {
+			dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
+				__func__, freq);
+			ret = 0;
+			goto put_opp_table;
+		}
 	}
 
 	/*
@@ -1291,13 +1296,19 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-void _opp_remove_all_static(struct opp_table *opp_table)
+bool _opp_remove_all_static(struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp, *tmp;
+	bool ret = true;
 
 	mutex_lock(&opp_table->lock);
 
-	if (!opp_table->parsed_static_opps || --opp_table->parsed_static_opps)
+	if (!opp_table->parsed_static_opps) {
+		ret = false;
+		goto unlock;
+	}
+
+	if (--opp_table->parsed_static_opps)
 		goto unlock;
 
 	list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
@@ -1307,6 +1318,8 @@ void _opp_remove_all_static(struct opp_table *opp_table)
 
 unlock:
 	mutex_unlock(&opp_table->lock);
+
+	return ret;
 }
 
 /**
@@ -2409,13 +2422,15 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev)
 		return;
 	}
 
-	_opp_remove_all_static(opp_table);
+	/*
+	 * Drop the extra reference only if the OPP table was successfully added
+	 * with dev_pm_opp_of_add_table() earlier.
+	 **/
+	if (_opp_remove_all_static(opp_table))
+		dev_pm_opp_put_opp_table(opp_table);
 
 	/* Drop reference taken by _find_opp_table() */
 	dev_pm_opp_put_opp_table(opp_table);
-
-	/* Drop reference taken while the OPP table was added */
-	dev_pm_opp_put_opp_table(opp_table);
 }
 
 /**
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index e51646ff279e..c3fcd571e446 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -212,7 +212,7 @@ struct opp_table {
 
 /* Routines internal to opp core */
 void dev_pm_opp_get(struct dev_pm_opp *opp);
-void _opp_remove_all_static(struct opp_table *opp_table);
+bool _opp_remove_all_static(struct opp_table *opp_table);
 void _get_opp_table_kref(struct opp_table *opp_table);
 int _get_opp_count(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
diff --git a/drivers/parport/ieee1284.c b/drivers/parport/ieee1284.c
index f28d6a3c5a68..4547ac44c8d4 100644
--- a/drivers/parport/ieee1284.c
+++ b/drivers/parport/ieee1284.c
@@ -260,7 +260,7 @@ static void parport_ieee1284_terminate (struct parport *port)
 			port->ieee1284.phase = IEEE1284_PH_FWD_IDLE;
 		}
 
-		/* fall through */
+		fallthrough;
 
 	default:
 		/* Terminate from all other modes. */
@@ -598,7 +598,7 @@ ssize_t parport_write (struct parport *port, const void *buffer, size_t len)
 	case IEEE1284_MODE_NIBBLE:
 	case IEEE1284_MODE_BYTE:
 		parport_negotiate (port, IEEE1284_MODE_COMPAT);
-		/* fall through */
+		fallthrough;
 	case IEEE1284_MODE_COMPAT:
 		pr_debug("%s: Using compatibility mode\n", port->name);
 		fn = port->ops->compat_write_data;
@@ -702,7 +702,7 @@ ssize_t parport_read (struct parport *port, void *buffer, size_t len)
 		if (parport_negotiate (port, IEEE1284_MODE_NIBBLE)) {
 			return -EIO;
 		}
-		/* fall through - to NIBBLE */
+		fallthrough;	/* to NIBBLE */
 	case IEEE1284_MODE_NIBBLE:
 		pr_debug("%s: Using nibble mode\n", port->name);
 		fn = port->ops->nibble_read_data;
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 77e37e3cb3a0..eda4ded4d5e5 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -1647,7 +1647,7 @@ static int parport_ECP_supported(struct parport *pb)
 		break;
 	default:
 		pr_warn("0x%lx: Unknown implementation ID\n", pb->base);
-		/* Fall through - Assume 1 */
+		fallthrough;	/* Assume 1 */
 	case 1:
 		pword = 1;
 	}
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 90df28c7cb0c..5fef2613b223 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -439,7 +439,7 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN, 0);
 		break;
-	case IMX6QP:		/* FALLTHROUGH */
+	case IMX6QP:
 	case IMX6Q:
 		/* power up core phy and enable ref clock */
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
@@ -642,7 +642,7 @@ static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie)
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				   IMX6SX_GPR12_PCIE_RX_EQ_MASK,
 				   IMX6SX_GPR12_PCIE_RX_EQ_2);
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				   IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
@@ -1105,7 +1105,7 @@ static int imx6_pcie_probe(struct platform_device *pdev)
 			dev_err(dev, "pcie_aux clock source missing or invalid\n");
 			return PTR_ERR(imx6_pcie->pcie_aux);
 		}
-		/* fall through */
+		fallthrough;
 	case IMX7D:
 		if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR)
 			imx6_pcie->controller_id = 1;
diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c
index c9530038ca9a..afde4aa8f6dc 100644
--- a/drivers/pci/controller/pci-rcar-gen2.c
+++ b/drivers/pci/controller/pci-rcar-gen2.c
@@ -223,7 +223,7 @@ static void rcar_pci_setup(struct rcar_pci_priv *priv)
 		pr_warn("unknown window size %ld - defaulting to 256M\n",
 			window_size);
 		window_size = SZ_256M;
-		/* fall-through */
+		fallthrough;
 	case SZ_256M:
 		val |= RCAR_USBCTR_PCIAHB_WIN1_256M;
 		break;
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
index 5c93aa14f0de..ae9acc77d14f 100644
--- a/drivers/pci/hotplug/ibmphp_res.c
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -1941,7 +1941,7 @@ static int __init update_bridge_ranges(struct bus_node **bus)
 						break;
 					case PCI_HEADER_TYPE_BRIDGE:
 						function = 0x8;
-						/* fall through */
+						fallthrough;
 					case PCI_HEADER_TYPE_MULTIBRIDGE:
 						/* We assume here that only 1 bus behind the bridge
 						   TO DO: add functionality for several:
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 6503d15effbb..9f85815b4f53 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -236,7 +236,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 	switch (ctrl->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&ctrl->button_work);
-		/* fall through */
+		fallthrough;
 	case ON_STATE:
 		ctrl->state = POWEROFF_STATE;
 		mutex_unlock(&ctrl->state_lock);
@@ -265,7 +265,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 	switch (ctrl->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&ctrl->button_work);
-		/* fall through */
+		fallthrough;
 	case OFF_STATE:
 		ctrl->state = POWERON_STATE;
 		mutex_unlock(&ctrl->state_lock);
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index b59f84918fe0..c9e790c74051 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -83,21 +83,19 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 	struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev,
 					     hotplug_slot);
 	struct pci_dev *pdev;
-	struct zpci_bus *zbus = zdev->zbus;
 	int rc;
 
 	if (!zpci_fn_configured(zdev->state))
 		return -EIO;
 
-	pdev = pci_get_slot(zbus->bus, zdev->devfn);
-	if (pdev) {
-		if (pci_num_vf(pdev))
-			return -EBUSY;
-
-		pci_stop_and_remove_bus_device_locked(pdev);
+	pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
+	if (pdev && pci_num_vf(pdev)) {
 		pci_dev_put(pdev);
+		return -EBUSY;
 	}
 
+	zpci_remove_device(zdev);
+
 	rc = zpci_disable_device(zdev);
 	if (rc)
 		return rc;
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index afdc52d1cae7..65502e3f7b4f 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -642,7 +642,7 @@ int shpchp_sysfs_enable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&p_slot->work);
-		/* fall through */
+		fallthrough;
 	case STATIC_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
@@ -678,7 +678,7 @@ int shpchp_sysfs_disable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
-		/* fall through */
+		fallthrough;
 	case STATIC_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 64ebed129dbf..f357f9a32b3a 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -556,13 +556,14 @@ int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients,
 		return -1;
 
 	for (i = 0; i < num_clients; i++) {
-		if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) &&
-		    clients[i]->dma_ops == &dma_virt_ops) {
+#ifdef CONFIG_DMA_VIRT_OPS
+		if (clients[i]->dma_ops == &dma_virt_ops) {
 			if (verbose)
 				dev_warn(clients[i],
 					 "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n");
 			return -1;
 		}
+#endif
 
 		pci_client = find_parent_pci_dev(clients[i]);
 		if (!pci_client) {
@@ -842,9 +843,10 @@ static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap,
 	 * this should never happen because it will be prevented
 	 * by the check in pci_p2pdma_distance_many()
 	 */
-	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) &&
-			 dev->dma_ops == &dma_virt_ops))
+#ifdef CONFIG_DMA_VIRT_OPS
+	if (WARN_ON_ONCE(dev->dma_ops == &dma_virt_ops))
 		return 0;
+#endif
 
 	for_each_sg(sg, s, nents, i) {
 		paddr = sg_phys(s);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a458c46d7e39..e39c5499770f 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1049,7 +1049,7 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
 		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
 		 && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
 			need_restore = true;
-		/* Fall-through - force to D0 */
+		fallthrough;	/* force to D0 */
 	default:
 		pmcsr = 0;
 		break;
@@ -2541,7 +2541,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 		case PCI_D2:
 			if (pci_no_d1d2(dev))
 				break;
-			/* else, fall through */
+			fallthrough;
 		default:
 			target_state = state;
 		}
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index bd2b691fa7a3..d35186b01d98 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -231,7 +231,7 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 		}
 		/* If arch decided it can't, fall through... */
 #endif /* HAVE_PCI_MMAP */
-		/* fall through */
+		fallthrough;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index bdf9b52567e0..2a589b6d6ed8 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1730,7 +1730,7 @@ static void quirk_jmicron_ata(struct pci_dev *pdev)
 	case PCI_DEVICE_ID_JMICRON_JMB366:
 		/* Redirect IDE second PATA port to the right spot */
 		conf5 |= (1 << 24);
-		/* Fall through */
+		fallthrough;
 	case PCI_DEVICE_ID_JMICRON_JMB361:
 	case PCI_DEVICE_ID_JMICRON_JMB363:
 	case PCI_DEVICE_ID_JMICRON_JMB369:
@@ -2224,7 +2224,7 @@ static void quirk_netmos(struct pci_dev *dev)
 		if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM &&
 				dev->subsystem_device == 0x0299)
 			return;
-		/* else, fall through */
+		fallthrough;
 	case PCI_DEVICE_ID_NETMOS_9735:
 	case PCI_DEVICE_ID_NETMOS_9745:
 	case PCI_DEVICE_ID_NETMOS_9845:
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 3951e02b7ded..2ce636937c6e 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1253,7 +1253,7 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head)
 			additional_mmio_size = pci_hotplug_mmio_size;
 			additional_mmio_pref_size = pci_hotplug_mmio_pref_size;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		pbus_size_io(bus, realloc_head ? 0 : additional_io_size,
 			     additional_io_size, realloc_head);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index fab267e359e7..c0e85be598c1 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -1096,7 +1096,7 @@ static void __ref pcifront_backend_changed(struct xenbus_device *xdev,
 	case XenbusStateClosed:
 		if (xdev->state == XenbusStateClosed)
 			break;
-		/* fall through - Missed the backend's CLOSING state. */
+		fallthrough;	/* Missed the backend's CLOSING state */
 	case XenbusStateClosing:
 		dev_warn(&xdev->dev, "backend going away!\n");
 		pcifront_try_disconnect(pdev);
diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 590e594092f2..a7c7c7cd2326 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -255,10 +255,10 @@ static int db1x_pcmcia_configure(struct pcmcia_socket *skt,
 	switch (state->Vcc) {
 	case 50:
 		++v;
-		/* fall through */
+		fallthrough;
 	case 33:
 		++v;
-		/* fall through */
+		fallthrough;
 	case 0:
 		break;
 	default:
@@ -269,11 +269,11 @@ static int db1x_pcmcia_configure(struct pcmcia_socket *skt,
 	switch (state->Vpp) {
 	case 12:
 		++p;
-		/* fall through */
+		fallthrough;
 	case 33:
 	case 50:
 		++p;
-		/* fall through */
+		fallthrough;
 	case 0:
 		break;
 	default:
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 7b7d23f25713..a0a71c1df042 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1404,7 +1404,7 @@ static int arm_ccn_init_nodes(struct arm_ccn *ccn, int region,
 		break;
 	case CCN_TYPE_SBAS:
 		ccn->sbas_present = 1;
-		/* Fall-through */
+		fallthrough;
 	default:
 		component = &ccn->node[id];
 		break;
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index e51ddb6d63ed..cc00915ad6d1 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1002,7 +1002,7 @@ static void __arm_spe_pmu_dev_probe(void *info)
 	default:
 		dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n",
 			 fld);
-		/* Fallthrough */
+		fallthrough;
 	case 8:
 		spe_pmu->min_period = 4096;
 	}
@@ -1021,7 +1021,7 @@ static void __arm_spe_pmu_dev_probe(void *info)
 	default:
 		dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n",
 			 fld);
-		/* Fallthrough */
+		fallthrough;
 	case 2:
 		spe_pmu->counter_sz = 12;
 	}
diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
index 71f257b4a7f5..9061ece7ff6a 100644
--- a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
@@ -505,9 +505,9 @@ static int qcom_ipq806x_usb_phy_probe(struct platform_device *pdev)
 	size = resource_size(res);
 	phy_dwc3->base = devm_ioremap(phy_dwc3->dev, res->start, size);
 
-	if (IS_ERR(phy_dwc3->base)) {
+	if (!phy_dwc3->base) {
 		dev_err(phy_dwc3->dev, "failed to map reg\n");
-		return PTR_ERR(phy_dwc3->base);
+		return -ENOMEM;
 	}
 
 	phy_dwc3->ref_clk = devm_clk_get(phy_dwc3->dev, "ref");
@@ -557,7 +557,6 @@ static struct platform_driver qcom_ipq806x_usb_phy_driver = {
 	.probe		= qcom_ipq806x_usb_phy_probe,
 	.driver		= {
 		.name	= "qcom-ipq806x-usb-phy",
-		.owner	= THIS_MODULE,
 		.of_match_table = qcom_ipq806x_usb_phy_table,
 	},
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 562053ce9455..6e6f992a9524 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -604,8 +604,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0x1f),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0),
@@ -631,7 +631,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0),
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_CTRL, 0xa),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1),
@@ -640,7 +639,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19),
-	QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_CNTRL, 0x7),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
@@ -648,6 +646,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_TX_EMP_POST1_LVL, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_TX_SLEW_CNTL, 0x0a),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
@@ -658,7 +658,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4),
-	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_pcs_tbl[] = {
@@ -2046,6 +2045,9 @@ static const struct qmp_phy_cfg msm8996_usb3phy_cfg = {
 	.pwrdn_ctrl		= SW_PWRDN,
 };
 
+static const char * const ipq8074_pciephy_clk_l[] = {
+	"aux", "cfg_ahb",
+};
 /* list of resets */
 static const char * const ipq8074_pciephy_reset_l[] = {
 	"phy", "common",
@@ -2063,8 +2065,8 @@ static const struct qmp_phy_cfg ipq8074_pciephy_cfg = {
 	.rx_tbl_num		= ARRAY_SIZE(ipq8074_pcie_rx_tbl),
 	.pcs_tbl		= ipq8074_pcie_pcs_tbl,
 	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_pcie_pcs_tbl),
-	.clk_list		= NULL,
-	.num_clks		= 0,
+	.clk_list		= ipq8074_pciephy_clk_l,
+	.num_clks		= ARRAY_SIZE(ipq8074_pciephy_clk_l),
 	.reset_list		= ipq8074_pciephy_reset_l,
 	.num_resets		= ARRAY_SIZE(ipq8074_pciephy_reset_l),
 	.vreg_list		= NULL,
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 4277f592684b..904b80ab9009 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -77,6 +77,8 @@
 #define QSERDES_COM_CORECLK_DIV_MODE1			0x1bc
 
 /* Only for QMP V2 PHY - TX registers */
+#define QSERDES_TX_EMP_POST1_LVL			0x018
+#define QSERDES_TX_SLEW_CNTL				0x040
 #define QSERDES_TX_RES_CODE_LANE_OFFSET			0x054
 #define QSERDES_TX_DEBUG_BUS_SEL			0x064
 #define QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN	0x068
diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs.c b/drivers/phy/qualcomm/phy-qcom-usb-hs.c
index 61054272a7c8..327df1a99f77 100644
--- a/drivers/phy/qualcomm/phy-qcom-usb-hs.c
+++ b/drivers/phy/qualcomm/phy-qcom-usb-hs.c
@@ -53,7 +53,7 @@ static int qcom_usb_hs_phy_set_mode(struct phy *phy,
 		case PHY_MODE_USB_OTG:
 		case PHY_MODE_USB_HOST:
 			val |= ULPI_INT_IDGRD;
-			/* fall through */
+			fallthrough;
 		case PHY_MODE_USB_DEVICE:
 			val |= ULPI_INT_SESS_VALID;
 		default:
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index a84e9f027fc4..46ebdb1460a3 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -546,7 +546,7 @@ static void rockchip_usb2phy_otg_sm_work(struct work_struct *work)
 		rport->state = OTG_STATE_B_IDLE;
 		if (!vbus_attach)
 			rockchip_usb2phy_power_off(rport->phy);
-		/* fall through */
+		fallthrough;
 	case OTG_STATE_B_IDLE:
 		if (extcon_get_state(rphy->edev, EXTCON_USB_HOST) > 0) {
 			dev_dbg(&rport->phy->dev, "usb otg host connect\n");
@@ -754,11 +754,11 @@ static void rockchip_chg_detect_work(struct work_struct *work)
 			rphy->chg_type = POWER_SUPPLY_TYPE_USB_DCP;
 		else
 			rphy->chg_type = POWER_SUPPLY_TYPE_USB_CDP;
-		/* fall through */
+		fallthrough;
 	case USB_CHG_STATE_SECONDARY_DONE:
 		rphy->chg_state = USB_CHG_STATE_DETECTED;
 		delay = 0;
-		/* fall through */
+		fallthrough;
 	case USB_CHG_STATE_DETECTED:
 		/* put the controller in normal mode */
 		property_enable(base, &rphy->phy_cfg->chg_det.opmode, true);
@@ -835,7 +835,7 @@ static void rockchip_usb2phy_sm_work(struct work_struct *work)
 			dev_dbg(&rport->phy->dev, "FS/LS online\n");
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case PHY_STATE_CONNECT:
 		if (rport->suspended) {
 			dev_dbg(&rport->phy->dev, "Connected\n");
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index cb2dd3230fa7..507f79d14adb 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -22,10 +22,15 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 #include <linux/of_platform.h>
+#include <linux/sys_soc.h>
 
 #define USB2PHY_ANA_CONFIG1		0x4c
 #define USB2PHY_DISCON_BYP_LATCH	BIT(31)
 
+#define USB2PHY_CHRG_DET			0x14
+#define USB2PHY_CHRG_DET_USE_CHG_DET_REG	BIT(29)
+#define USB2PHY_CHRG_DET_DIS_CHG_DET		BIT(28)
+
 /* SoC Specific USB2_OTG register definitions */
 #define AM654_USB2_OTG_PD		BIT(8)
 #define AM654_USB2_VBUS_DET_EN		BIT(5)
@@ -43,6 +48,7 @@
 #define OMAP_USB2_HAS_START_SRP			BIT(0)
 #define OMAP_USB2_HAS_SET_VBUS			BIT(1)
 #define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT	BIT(2)
+#define OMAP_USB2_DISABLE_CHRG_DET		BIT(3)
 
 struct omap_usb {
 	struct usb_phy		phy;
@@ -236,6 +242,13 @@ static int omap_usb_init(struct phy *x)
 		omap_usb_writel(phy->phy_base, USB2PHY_ANA_CONFIG1, val);
 	}
 
+	if (phy->flags & OMAP_USB2_DISABLE_CHRG_DET) {
+		val = omap_usb_readl(phy->phy_base, USB2PHY_CHRG_DET);
+		val |= USB2PHY_CHRG_DET_USE_CHG_DET_REG |
+		       USB2PHY_CHRG_DET_DIS_CHG_DET;
+		omap_usb_writel(phy->phy_base, USB2PHY_CHRG_DET, val);
+	}
+
 	return 0;
 }
 
@@ -329,6 +342,26 @@ static const struct of_device_id omap_usb2_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, omap_usb2_id_table);
 
+static void omap_usb2_init_errata(struct omap_usb *phy)
+{
+	static const struct soc_device_attribute am65x_sr10_soc_devices[] = {
+		{ .family = "AM65X", .revision = "SR1.0" },
+		{ /* sentinel */ }
+	};
+
+	/*
+	 * Errata i2075: USB2PHY: USB2PHY Charger Detect is Enabled by
+	 * Default Without VBUS Presence.
+	 *
+	 * AM654x SR1.0 has a silicon bug due to which D+ is pulled high after
+	 * POR, which could cause enumeration failure with some USB hubs.
+	 * Disabling the USB2_PHY Charger Detect function will put D+
+	 * into the normal state.
+	 */
+	if (soc_device_match(am65x_sr10_soc_devices))
+		phy->flags |= OMAP_USB2_DISABLE_CHRG_DET;
+}
+
 static int omap_usb2_probe(struct platform_device *pdev)
 {
 	struct omap_usb	*phy;
@@ -366,14 +399,14 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	phy->mask		= phy_data->mask;
 	phy->power_on		= phy_data->power_on;
 	phy->power_off		= phy_data->power_off;
+	phy->flags		= phy_data->flags;
 
-	if (phy_data->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) {
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(phy->phy_base))
-			return PTR_ERR(phy->phy_base);
-		phy->flags |= OMAP_USB2_CALIBRATE_FALSE_DISCONNECT;
-	}
+	omap_usb2_init_errata(phy);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(phy->phy_base))
+		return PTR_ERR(phy->phy_base);
 
 	phy->syscon_phy_power = syscon_regmap_lookup_by_phandle(node,
 							"syscon-phy-power");
diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c
index 5e1d14e35f20..0d46706afd2d 100644
--- a/drivers/platform/olpc/olpc-xo175-ec.c
+++ b/drivers/platform/olpc/olpc-xo175-ec.c
@@ -431,7 +431,7 @@ static void olpc_xo175_ec_complete(void *arg)
 			input_sync(priv->pwrbtn);
 			input_report_key(priv->pwrbtn, KEY_POWER, 0);
 			input_sync(priv->pwrbtn);
-			/* fall through */
+			fallthrough;
 		case EVENT_POWER_PRESS_WAKE:
 		case EVENT_TIMED_HOST_WAKE:
 			pm_wakeup_event(priv->pwrbtn->dev.parent,
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 60c18f21588d..49f4b73be513 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -1001,7 +1001,7 @@ static acpi_status WMID_get_u32(u32 *value, u32 cap)
 			*value = tmp & 0x1;
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return AE_ERROR;
 	}
@@ -1328,7 +1328,7 @@ static acpi_status get_u32(u32 *value, u32 cap)
 			status = AMW0_get_u32(value, cap);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case ACER_WMID:
 		status = WMID_get_u32(value, cap);
 		break;
@@ -1371,7 +1371,7 @@ static acpi_status set_u32(u32 value, u32 cap)
 
 				return AMW0_set_u32(value, cap);
 			}
-			/* fall through */
+			fallthrough;
 		case ACER_WMID:
 			return WMID_set_u32(value, cap);
 		case ACER_WMID_v2:
@@ -1381,7 +1381,7 @@ static acpi_status set_u32(u32 value, u32 cap)
 				return wmid_v2_set_u32(value, cap);
 			else if (wmi_has_guid(WMID_GUID2))
 				return WMID_set_u32(value, cap);
-			/* fall through */
+			fallthrough;
 		default:
 			return AE_BAD_PARAMETER;
 		}
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index 5e9c2296931c..70edc5bb3a14 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -1587,10 +1587,10 @@ static ssize_t kbd_led_timeout_store(struct device *dev,
 		switch (unit) {
 		case KBD_TIMEOUT_DAYS:
 			value *= 24;
-			/* fall through */
+			fallthrough;
 		case KBD_TIMEOUT_HOURS:
 			value *= 60;
-			/* fall through */
+			fallthrough;
 		case KBD_TIMEOUT_MINUTES:
 			value *= 60;
 			unit = KBD_TIMEOUT_SECONDS;
diff --git a/drivers/platform/x86/surfacepro3_button.c b/drivers/platform/x86/surfacepro3_button.c
index ec515223f654..d8afed5db94c 100644
--- a/drivers/platform/x86/surfacepro3_button.c
+++ b/drivers/platform/x86/surfacepro3_button.c
@@ -84,28 +84,28 @@ static void surface_button_notify(struct acpi_device *device, u32 event)
 	/* Power button press,release handle */
 	case SURFACE_BUTTON_NOTIFY_PRESS_POWER:
 		pressed = true;
-		/*fall through*/
+		fallthrough;
 	case SURFACE_BUTTON_NOTIFY_RELEASE_POWER:
 		key_code = KEY_POWER;
 		break;
 	/* Home button press,release handle */
 	case SURFACE_BUTTON_NOTIFY_PRESS_HOME:
 		pressed = true;
-		/*fall through*/
+		fallthrough;
 	case SURFACE_BUTTON_NOTIFY_RELEASE_HOME:
 		key_code = KEY_LEFTMETA;
 		break;
 	/* Volume up button press,release handle */
 	case SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_UP:
 		pressed = true;
-		/*fall through*/
+		fallthrough;
 	case SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_UP:
 		key_code = KEY_VOLUMEUP;
 		break;
 	/* Volume down button press,release handle */
 	case SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_DOWN:
 		pressed = true;
-		/*fall through*/
+		fallthrough;
 	case SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_DOWN:
 		key_code = KEY_VOLUMEDOWN;
 		break;
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 4864a5c189d4..9c4df41687a3 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -4060,7 +4060,7 @@ static bool hotkey_notify_6xxx(const u32 hkey,
 		 * AC status changed; can be triggered by plugging or
 		 * unplugging AC adapter, docking or undocking. */
 
-		/* fallthrough */
+		fallthrough;
 
 	case TP_HKEY_EV_KEY_NUMLOCK:
 	case TP_HKEY_EV_KEY_FN:
@@ -4176,7 +4176,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 				known_ev = true;
 				break;
 			}
-			/* fallthrough - to default */
+			fallthrough;	/* to default */
 		default:
 			known_ev = false;
 		}
@@ -6266,7 +6266,7 @@ static int thermal_get_sensor(int idx, s32 *value)
 			idx -= 8;
 		}
 #endif
-		/* fallthrough */
+		fallthrough;
 	case TPACPI_THERMAL_TPEC_8:
 		if (idx <= 7) {
 			if (!acpi_ec_read(t + idx, &tmp))
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 36fff00af9eb..e557d757c647 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -2748,7 +2748,7 @@ static void toshiba_acpi_process_hotkeys(struct toshiba_acpi_dev *dev)
 				result = hci_write(dev, HCI_SYSTEM_EVENT, 1);
 				if (result == TOS_SUCCESS)
 					pr_notice("Re-enabled hotkeys\n");
-				/* Fall through */
+				fallthrough;
 			default:
 				retries--;
 				break;
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index 9469fe182d02..db65be026920 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -748,7 +748,7 @@ static int ab8500_charger_max_usb_curr(struct ab8500_charger *di,
 						USB_CH_IP_CUR_LVL_1P5;
 			break;
 		}
-		/* else, fall through */
+		fallthrough;
 	case USB_STAT_HM_IDGND:
 		dev_err(di->dev, "USB Type - Charging not allowed\n");
 		di->max_usb_in_curr.usb_type_max = USB_CH_IP_CUR_LVL_0P05;
@@ -2410,7 +2410,7 @@ static void ab8500_charger_usb_state_changed_work(struct work_struct *work)
 		 * of 1sec for enabling charging
 		 */
 		msleep(1000);
-		/* Intentional fall through */
+		fallthrough;
 	case AB8500_BM_USB_STATE_CONFIGURED:
 		/*
 		 * USB is configured, enable charging with the charging
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 751c4f6c7487..7eec415c82a3 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -1542,7 +1542,7 @@ static void ab8500_fg_algorithm_discharging(struct ab8500_fg *di)
 		ab8500_fg_discharge_state_to(di,
 			AB8500_FG_DISCHARGE_INITMEASURING);
 
-		/* Intentional fallthrough */
+		fallthrough;
 	case AB8500_FG_DISCHARGE_INITMEASURING:
 		/*
 		 * Discard a number of samples during startup.
@@ -1572,7 +1572,7 @@ static void ab8500_fg_algorithm_discharging(struct ab8500_fg *di)
 		ab8500_fg_discharge_state_to(di,
 			AB8500_FG_DISCHARGE_RECOVERY);
 
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case AB8500_FG_DISCHARGE_RECOVERY:
 		sleep_time = di->bm->fg_params->recovery_sleep_timer;
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index 2fb33a07879a..175c4f3d7955 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -1419,7 +1419,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 		abx500_chargalg_stop_charging(di);
 		di->charge_status = POWER_SUPPLY_STATUS_DISCHARGING;
 		abx500_chargalg_state_to(di, STATE_HANDHELD);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_HANDHELD:
 		break;
@@ -1435,7 +1435,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 		di->maintenance_chg = false;
 		abx500_chargalg_state_to(di, STATE_SUSPENDED);
 		power_supply_changed(di->chargalg_psy);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_SUSPENDED:
 		/* CHARGING is suspended */
@@ -1444,7 +1444,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_BATT_REMOVED_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_BATT_REMOVED);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_BATT_REMOVED:
 		if (!di->events.batt_rem)
@@ -1454,7 +1454,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_HW_TEMP_PROTECT_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_HW_TEMP_PROTECT);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_HW_TEMP_PROTECT:
 		if (!di->events.main_thermal_prot &&
@@ -1465,7 +1465,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_OVV_PROTECT_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_OVV_PROTECT);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_OVV_PROTECT:
 		if (!di->events.vbus_ovv &&
@@ -1479,7 +1479,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_CHG_NOT_OK_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_CHG_NOT_OK);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_CHG_NOT_OK:
 		if (!di->events.mainextchnotok &&
@@ -1490,7 +1490,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_SAFETY_TIMER_EXPIRED_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_SAFETY_TIMER_EXPIRED);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_SAFETY_TIMER_EXPIRED:
 		/* We exit this state when charger is removed */
@@ -1537,7 +1537,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_WAIT_FOR_RECHARGE_INIT:
 		abx500_chargalg_hold_charging(di);
 		abx500_chargalg_state_to(di, STATE_WAIT_FOR_RECHARGE);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_WAIT_FOR_RECHARGE:
 		if (di->batt_data.percent <=
@@ -1558,7 +1558,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 				di->bm->batt_id].maint_a_cur_lvl);
 		abx500_chargalg_state_to(di, STATE_MAINTENANCE_A);
 		power_supply_changed(di->chargalg_psy);
-		/* Intentional fallthrough*/
+		fallthrough;
 
 	case STATE_MAINTENANCE_A:
 		if (di->events.maintenance_timer_expired) {
@@ -1578,7 +1578,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 				di->bm->batt_id].maint_b_cur_lvl);
 		abx500_chargalg_state_to(di, STATE_MAINTENANCE_B);
 		power_supply_changed(di->chargalg_psy);
-		/* Intentional fallthrough*/
+		fallthrough;
 
 	case STATE_MAINTENANCE_B:
 		if (di->events.maintenance_timer_expired) {
@@ -1597,7 +1597,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 		di->charge_status = POWER_SUPPLY_STATUS_CHARGING;
 		abx500_chargalg_state_to(di, STATE_TEMP_LOWHIGH);
 		power_supply_changed(di->chargalg_psy);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_TEMP_LOWHIGH:
 		if (!di->events.btemp_lowhigh)
@@ -1607,7 +1607,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_WD_EXPIRED_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_WD_EXPIRED);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_WD_EXPIRED:
 		if (!di->events.ac_wd_expired &&
@@ -1618,7 +1618,7 @@ static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
 	case STATE_TEMP_UNDEROVER_INIT:
 		abx500_chargalg_stop_charging(di);
 		abx500_chargalg_state_to(di, STATE_TEMP_UNDEROVER);
-		/* Intentional fallthrough */
+		fallthrough;
 
 	case STATE_TEMP_UNDEROVER:
 		if (!di->events.btemp_underover)
diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index d01dc0332edc..0eaa86c52874 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -349,7 +349,7 @@ static int axp20x_usb_power_set_current_max(struct axp20x_usb_power *power,
 	case 100000:
 		if (power->axp20x_id == AXP221_ID)
 			return -EINVAL;
-		/* fall through */
+		fallthrough;
 	case 500000:
 	case 900000:
 		val = (900000 - intval) / 400000;
diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c
index 2a45e84447fe..d89e08efd2ad 100644
--- a/drivers/power/supply/cros_usbpd-charger.c
+++ b/drivers/power/supply/cros_usbpd-charger.c
@@ -383,7 +383,7 @@ static int cros_usbpd_charger_get_prop(struct power_supply *psy,
 		 */
 		if (ec_device->mkbp_event_supported || port->psy_online)
 			break;
-		/* fall through */
+		fallthrough;
 	case POWER_SUPPLY_PROP_CURRENT_MAX:
 	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
diff --git a/drivers/power/supply/max8925_power.c b/drivers/power/supply/max8925_power.c
index 5fca4960f440..8878f9131184 100644
--- a/drivers/power/supply/max8925_power.c
+++ b/drivers/power/supply/max8925_power.c
@@ -121,7 +121,7 @@ static irqreturn_t max8925_charger_handler(int irq, void *data)
 	case MAX8925_IRQ_VCHG_THM_OK_F:
 		/* Battery is not ready yet */
 		dev_dbg(chip->dev, "Battery temperature is out of range\n");
-		/* Fall through */
+		fallthrough;
 	case MAX8925_IRQ_VCHG_DC_OVP:
 		dev_dbg(chip->dev, "Error detection\n");
 		__set_charger(info, 0);
diff --git a/drivers/power/supply/wm831x_power.c b/drivers/power/supply/wm831x_power.c
index 65832bc229f6..18b33f14dfee 100644
--- a/drivers/power/supply/wm831x_power.c
+++ b/drivers/power/supply/wm831x_power.c
@@ -665,7 +665,7 @@ static int wm831x_power_probe(struct platform_device *pdev)
 		break;
 	default:
 		dev_err(&pdev->dev, "Failed to find USB phy: %d\n", ret);
-		/* fall-through */
+		fallthrough;
 	case -EPROBE_DEFER:
 		goto err_bat_irq;
 		break;
diff --git a/drivers/power/supply/wm8350_power.c b/drivers/power/supply/wm8350_power.c
index 26923af574f4..e05cee457471 100644
--- a/drivers/power/supply/wm8350_power.c
+++ b/drivers/power/supply/wm8350_power.c
@@ -227,7 +227,7 @@ static irqreturn_t wm8350_charger_handler(int irq, void *data)
 	case WM8350_IRQ_EXT_USB_FB:
 	case WM8350_IRQ_EXT_WALL_FB:
 		wm8350_charger_config(wm8350, policy);
-		/* Fall through */
+		fallthrough;
 	case WM8350_IRQ_EXT_BAT_FB:
 		power_supply_changed(power->battery);
 		power_supply_changed(power->usb);
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 6f55aaef8afc..25c764905f9b 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1035,6 +1035,9 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&rapl_defaults_spr_server),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&rapl_defaults_byt),
diff --git a/drivers/ps3/ps3av.c b/drivers/ps3/ps3av.c
index 24f04ffdd986..9d66257e1da5 100644
--- a/drivers/ps3/ps3av.c
+++ b/drivers/ps3/ps3av.c
@@ -769,7 +769,7 @@ static int ps3av_auto_videomode(struct ps3av_pkt_av_get_hw_conf *av_hw_conf)
 		switch (info->monitor_type) {
 		case PS3AV_MONITOR_TYPE_DVI:
 			dvi = PS3AV_MODE_DVI;
-			/* fall through */
+			fallthrough;
 		case PS3AV_MONITOR_TYPE_HDMI:
 			id = ps3av_hdmi_get_id(info);
 			break;
diff --git a/drivers/ps3/ps3av_cmd.c b/drivers/ps3/ps3av_cmd.c
index f0e650cc866e..c22206652f06 100644
--- a/drivers/ps3/ps3av_cmd.c
+++ b/drivers/ps3/ps3av_cmd.c
@@ -693,11 +693,11 @@ void ps3av_cmd_set_audio_mode(struct ps3av_pkt_audio_mode *audio, u32 avport,
 	switch (ch) {
 	case PS3AV_CMD_AUDIO_NUM_OF_CH_8:
 		audio->audio_enable[3] = 1;
-		/* fall through */
+		fallthrough;
 	case PS3AV_CMD_AUDIO_NUM_OF_CH_6:
 		audio->audio_enable[2] = 1;
 		audio->audio_enable[1] = 1;
-		/* fall through */
+		fallthrough;
 	case PS3AV_CMD_AUDIO_NUM_OF_CH_2:
 	default:
 		audio->audio_enable[0] = 1;
diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index 73aaae5574ed..e020faff7da5 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -142,16 +142,15 @@ static int idtcm_strverscmp(const char *ver1, const char *ver2)
 	return result;
 }
 
-static int idtcm_xfer(struct idtcm *idtcm,
-		      u8 regaddr,
-		      u8 *buf,
-		      u16 count,
-		      bool write)
+static int idtcm_xfer_read(struct idtcm *idtcm,
+			   u8 regaddr,
+			   u8 *buf,
+			   u16 count)
 {
 	struct i2c_client *client = idtcm->client;
 	struct i2c_msg msg[2];
 	int cnt;
-	char *fmt = "i2c_transfer failed at %d in %s for %s, at addr: %04X!\n";
+	char *fmt = "i2c_transfer failed at %d in %s, at addr: %04X!\n";
 
 	msg[0].addr = client->addr;
 	msg[0].flags = 0;
@@ -159,7 +158,7 @@ static int idtcm_xfer(struct idtcm *idtcm,
 	msg[0].buf = &regaddr;
 
 	msg[1].addr = client->addr;
-	msg[1].flags = write ? 0 : I2C_M_RD;
+	msg[1].flags = I2C_M_RD;
 	msg[1].len = count;
 	msg[1].buf = buf;
 
@@ -170,7 +169,6 @@ static int idtcm_xfer(struct idtcm *idtcm,
 			fmt,
 			__LINE__,
 			__func__,
-			write ? "write" : "read",
 			regaddr);
 		return cnt;
 	} else if (cnt != 2) {
@@ -182,6 +180,37 @@ static int idtcm_xfer(struct idtcm *idtcm,
 	return 0;
 }
 
+static int idtcm_xfer_write(struct idtcm *idtcm,
+			    u8 regaddr,
+			    u8 *buf,
+			    u16 count)
+{
+	struct i2c_client *client = idtcm->client;
+	/* we add 1 byte for device register */
+	u8 msg[IDTCM_MAX_WRITE_COUNT + 1];
+	int cnt;
+	char *fmt = "i2c_master_send failed at %d in %s, at addr: %04X!\n";
+
+	if (count > IDTCM_MAX_WRITE_COUNT)
+		return -EINVAL;
+
+	msg[0] = regaddr;
+	memcpy(&msg[1], buf, count);
+
+	cnt = i2c_master_send(client, msg, count + 1);
+
+	if (cnt < 0) {
+		dev_err(&client->dev,
+			fmt,
+			__LINE__,
+			__func__,
+			regaddr);
+		return cnt;
+	}
+
+	return 0;
+}
+
 static int idtcm_page_offset(struct idtcm *idtcm, u8 val)
 {
 	u8 buf[4];
@@ -195,7 +224,7 @@ static int idtcm_page_offset(struct idtcm *idtcm, u8 val)
 	buf[2] = 0x10;
 	buf[3] = 0x20;
 
-	err = idtcm_xfer(idtcm, PAGE_ADDR, buf, sizeof(buf), 1);
+	err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf));
 
 	if (err) {
 		idtcm->page_offset = 0xff;
@@ -223,11 +252,12 @@ static int _idtcm_rdwr(struct idtcm *idtcm,
 	err = idtcm_page_offset(idtcm, hi);
 
 	if (err)
-		goto out;
+		return err;
 
-	err = idtcm_xfer(idtcm, lo, buf, count, write);
-out:
-	return err;
+	if (write)
+		return idtcm_xfer_write(idtcm, lo, buf, count);
+
+	return idtcm_xfer_read(idtcm, lo, buf, count);
 }
 
 static int idtcm_read(struct idtcm *idtcm,
diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h
index ffae56c5d97f..82840d72364a 100644
--- a/drivers/ptp/ptp_clockmatrix.h
+++ b/drivers/ptp/ptp_clockmatrix.h
@@ -55,6 +55,8 @@
 
 #define PEROUT_ENABLE_OUTPUT_MASK		(0xdeadbeef)
 
+#define IDTCM_MAX_WRITE_COUNT			(512)
+
 /* Values of DPLL_N.DPLL_MODE.PLL_MODE */
 enum pll_mode {
 	PLL_MODE_MIN = 0,
diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig
index e4c422d806be..b9f8514909bf 100644
--- a/drivers/rapidio/Kconfig
+++ b/drivers/rapidio/Kconfig
@@ -37,7 +37,7 @@ config RAPIDIO_ENABLE_RX_TX_PORTS
 config RAPIDIO_DMA_ENGINE
 	bool "DMA Engine support for RapidIO"
 	depends on RAPIDIO
-	select DMADEVICES
+	depends on DMADEVICES
 	select DMA_ENGINE
 	help
 	  Say Y here if you want to use DMA Engine frameork for RapidIO data
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index c07ceec3c6d4..a30342942e26 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -2150,7 +2150,7 @@ static void mport_release_mapping(struct kref *ref)
 	switch (map->dir) {
 	case MAP_INBOUND:
 		rio_unmap_inb_region(mport, map->phys_addr);
-		/* fall through */
+		fallthrough;
 	case MAP_DMA:
 		dma_free_coherent(mport->dev.parent, map->size,
 				  map->virt_addr, map->phys_addr);
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index fbc95cadaf53..1bacb37e8a99 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -399,7 +399,7 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
 		if (rate_count > 0)
 			break;
 
-		/* fall through */
+		fallthrough;
 	default:
 		/* Not supported for this regulator */
 		return -ENOTSUPP;
@@ -1022,7 +1022,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
 		 * (See include/linux/mfd/axp20x.h)
 		 */
 		reg = AXP803_DCDC_FREQ_CTRL;
-		/* Fall through - to the check below.*/
+		fallthrough;	/* to the check below */
 	case AXP806_ID:
 		/*
 		 * AXP806 also have DCDC work frequency setting register at a
@@ -1030,7 +1030,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
 		 */
 		if (axp20x->variant == AXP806_ID)
 			reg = AXP806_DCDC_FREQ_CTRL;
-		/* Fall through */
+		fallthrough;
 	case AXP221_ID:
 	case AXP223_ID:
 	case AXP809_ID:
@@ -1118,7 +1118,7 @@ static int axp20x_set_dcdc_workmode(struct regulator_dev *rdev, int id, u32 work
 		 * (See include/linux/mfd/axp20x.h)
 		 */
 		reg = AXP806_DCDC_MODE_CTRL2;
-		 /* Fall through - to the check below. */
+		fallthrough;	/* to the check below */
 	case AXP221_ID:
 	case AXP223_ID:
 	case AXP809_ID:
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 75ff7c563c5d..7ff507ec875a 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -236,8 +236,8 @@ static bool regulator_supply_is_couple(struct regulator_dev *rdev)
 static void regulator_unlock_recursive(struct regulator_dev *rdev,
 				       unsigned int n_coupled)
 {
-	struct regulator_dev *c_rdev;
-	int i;
+	struct regulator_dev *c_rdev, *supply_rdev;
+	int i, supply_n_coupled;
 
 	for (i = n_coupled; i > 0; i--) {
 		c_rdev = rdev->coupling_desc.coupled_rdevs[i - 1];
@@ -245,10 +245,13 @@ static void regulator_unlock_recursive(struct regulator_dev *rdev,
 		if (!c_rdev)
 			continue;
 
-		if (c_rdev->supply && !regulator_supply_is_couple(c_rdev))
-			regulator_unlock_recursive(
-					c_rdev->supply->rdev,
-					c_rdev->coupling_desc.n_coupled);
+		if (c_rdev->supply && !regulator_supply_is_couple(c_rdev)) {
+			supply_rdev = c_rdev->supply->rdev;
+			supply_n_coupled = supply_rdev->coupling_desc.n_coupled;
+
+			regulator_unlock_recursive(supply_rdev,
+						   supply_n_coupled);
+		}
 
 		regulator_unlock(c_rdev);
 	}
@@ -1461,7 +1464,7 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 				      const char *consumer_dev_name,
 				      const char *supply)
 {
-	struct regulator_map *node;
+	struct regulator_map *node, *new_node;
 	int has_dev;
 
 	if (supply == NULL)
@@ -1472,6 +1475,22 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 	else
 		has_dev = 0;
 
+	new_node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	new_node->regulator = rdev;
+	new_node->supply = supply;
+
+	if (has_dev) {
+		new_node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
+		if (new_node->dev_name == NULL) {
+			kfree(new_node);
+			return -ENOMEM;
+		}
+	}
+
+	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(node, &regulator_map_list, list) {
 		if (node->dev_name && consumer_dev_name) {
 			if (strcmp(node->dev_name, consumer_dev_name) != 0)
@@ -1489,26 +1508,19 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 			 node->regulator->desc->name,
 			 supply,
 			 dev_name(&rdev->dev), rdev_get_name(rdev));
-		return -EBUSY;
+		goto fail;
 	}
 
-	node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
-	if (node == NULL)
-		return -ENOMEM;
-
-	node->regulator = rdev;
-	node->supply = supply;
-
-	if (has_dev) {
-		node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
-		if (node->dev_name == NULL) {
-			kfree(node);
-			return -ENOMEM;
-		}
-	}
+	list_add(&new_node->list, &regulator_map_list);
+	mutex_unlock(&regulator_list_mutex);
 
-	list_add(&node->list, &regulator_map_list);
 	return 0;
+
+fail:
+	mutex_unlock(&regulator_list_mutex);
+	kfree(new_node->dev_name);
+	kfree(new_node);
+	return -EBUSY;
 }
 
 static void unset_regulator_supplies(struct regulator_dev *rdev)
@@ -1580,44 +1592,53 @@ static struct regulator *create_regulator(struct regulator_dev *rdev,
 					  const char *supply_name)
 {
 	struct regulator *regulator;
-	char buf[REG_STR_SIZE];
-	int err, size;
+	int err;
+
+	if (dev) {
+		char buf[REG_STR_SIZE];
+		int size;
+
+		size = snprintf(buf, REG_STR_SIZE, "%s-%s",
+				dev->kobj.name, supply_name);
+		if (size >= REG_STR_SIZE)
+			return NULL;
+
+		supply_name = kstrdup(buf, GFP_KERNEL);
+		if (supply_name == NULL)
+			return NULL;
+	} else {
+		supply_name = kstrdup_const(supply_name, GFP_KERNEL);
+		if (supply_name == NULL)
+			return NULL;
+	}
 
 	regulator = kzalloc(sizeof(*regulator), GFP_KERNEL);
-	if (regulator == NULL)
+	if (regulator == NULL) {
+		kfree(supply_name);
 		return NULL;
+	}
 
-	regulator_lock(rdev);
 	regulator->rdev = rdev;
+	regulator->supply_name = supply_name;
+
+	regulator_lock(rdev);
 	list_add(&regulator->list, &rdev->consumer_list);
+	regulator_unlock(rdev);
 
 	if (dev) {
 		regulator->dev = dev;
 
 		/* Add a link to the device sysfs entry */
-		size = snprintf(buf, REG_STR_SIZE, "%s-%s",
-				dev->kobj.name, supply_name);
-		if (size >= REG_STR_SIZE)
-			goto overflow_err;
-
-		regulator->supply_name = kstrdup(buf, GFP_KERNEL);
-		if (regulator->supply_name == NULL)
-			goto overflow_err;
-
 		err = sysfs_create_link_nowarn(&rdev->dev.kobj, &dev->kobj,
-					buf);
+					       supply_name);
 		if (err) {
 			rdev_dbg(rdev, "could not add device link %s err %d\n",
 				  dev->kobj.name, err);
 			/* non-fatal */
 		}
-	} else {
-		regulator->supply_name = kstrdup_const(supply_name, GFP_KERNEL);
-		if (regulator->supply_name == NULL)
-			goto overflow_err;
 	}
 
-	regulator->debugfs = debugfs_create_dir(regulator->supply_name,
+	regulator->debugfs = debugfs_create_dir(supply_name,
 						rdev->debugfs);
 	if (!regulator->debugfs) {
 		rdev_dbg(rdev, "Failed to create debugfs directory\n");
@@ -1642,13 +1663,7 @@ static struct regulator *create_regulator(struct regulator_dev *rdev,
 	    _regulator_is_enabled(rdev))
 		regulator->always_on = true;
 
-	regulator_unlock(rdev);
 	return regulator;
-overflow_err:
-	list_del(&regulator->list);
-	kfree(regulator);
-	regulator_unlock(rdev);
-	return NULL;
 }
 
 static int _regulator_get_enable_time(struct regulator_dev *rdev)
@@ -1895,7 +1910,7 @@ struct regulator *_regulator_get(struct device *dev, const char *id,
 		case EXCLUSIVE_GET:
 			dev_warn(dev,
 				 "dummy supplies not allowed for exclusive requests\n");
-			/* fall through */
+			fallthrough;
 
 		default:
 			return ERR_PTR(-ENODEV);
@@ -2230,10 +2245,13 @@ EXPORT_SYMBOL_GPL(regulator_bulk_unregister_supply_alias);
 static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 				const struct regulator_config *config)
 {
-	struct regulator_enable_gpio *pin;
+	struct regulator_enable_gpio *pin, *new_pin;
 	struct gpio_desc *gpiod;
 
 	gpiod = config->ena_gpiod;
+	new_pin = kzalloc(sizeof(*new_pin), GFP_KERNEL);
+
+	mutex_lock(&regulator_list_mutex);
 
 	list_for_each_entry(pin, &regulator_ena_gpio_list, list) {
 		if (pin->gpiod == gpiod) {
@@ -2242,9 +2260,13 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 		}
 	}
 
-	pin = kzalloc(sizeof(struct regulator_enable_gpio), GFP_KERNEL);
-	if (pin == NULL)
+	if (new_pin == NULL) {
+		mutex_unlock(&regulator_list_mutex);
 		return -ENOMEM;
+	}
+
+	pin = new_pin;
+	new_pin = NULL;
 
 	pin->gpiod = gpiod;
 	list_add(&pin->list, &regulator_ena_gpio_list);
@@ -2252,6 +2274,10 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 update_ena_gpio_to_rdev:
 	pin->request_count++;
 	rdev->ena_pin = pin;
+
+	mutex_unlock(&regulator_list_mutex);
+	kfree(new_pin);
+
 	return 0;
 }
 
@@ -2264,19 +2290,19 @@ static void regulator_ena_gpio_free(struct regulator_dev *rdev)
 
 	/* Free the GPIO only in case of no use */
 	list_for_each_entry_safe(pin, n, &regulator_ena_gpio_list, list) {
-		if (pin->gpiod == rdev->ena_pin->gpiod) {
-			if (pin->request_count <= 1) {
-				pin->request_count = 0;
-				gpiod_put(pin->gpiod);
-				list_del(&pin->list);
-				kfree(pin);
-				rdev->ena_pin = NULL;
-				return;
-			} else {
-				pin->request_count--;
-			}
-		}
+		if (pin != rdev->ena_pin)
+			continue;
+
+		if (--pin->request_count)
+			break;
+
+		gpiod_put(pin->gpiod);
+		list_del(&pin->list);
+		kfree(pin);
+		break;
 	}
+
+	rdev->ena_pin = NULL;
 }
 
 /**
@@ -4949,13 +4975,9 @@ static void regulator_resolve_coupling(struct regulator_dev *rdev)
 			return;
 		}
 
-		regulator_lock(c_rdev);
-
 		c_desc->coupled_rdevs[i] = c_rdev;
 		c_desc->n_resolved++;
 
-		regulator_unlock(c_rdev);
-
 		regulator_resolve_coupling(c_rdev);
 	}
 }
@@ -5040,7 +5062,10 @@ static int regulator_init_coupling(struct regulator_dev *rdev)
 	if (!of_check_coupling_data(rdev))
 		return -EPERM;
 
+	mutex_lock(&regulator_list_mutex);
 	rdev->coupling_desc.coupler = regulator_find_coupler(rdev);
+	mutex_unlock(&regulator_list_mutex);
+
 	if (IS_ERR(rdev->coupling_desc.coupler)) {
 		err = PTR_ERR(rdev->coupling_desc.coupler);
 		rdev_err(rdev, "failed to get coupler: %d\n", err);
@@ -5141,6 +5166,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 		ret = -ENOMEM;
 		goto rinse;
 	}
+	device_initialize(&rdev->dev);
 
 	/*
 	 * Duplicate the config so the driver could override it after
@@ -5148,9 +5174,8 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	 */
 	config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL);
 	if (config == NULL) {
-		kfree(rdev);
 		ret = -ENOMEM;
-		goto rinse;
+		goto clean;
 	}
 
 	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
@@ -5162,10 +5187,8 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	 * from a gpio extender or something else.
 	 */
 	if (PTR_ERR(init_data) == -EPROBE_DEFER) {
-		kfree(config);
-		kfree(rdev);
 		ret = -EPROBE_DEFER;
-		goto rinse;
+		goto clean;
 	}
 
 	/*
@@ -5206,9 +5229,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	}
 
 	if (config->ena_gpiod) {
-		mutex_lock(&regulator_list_mutex);
 		ret = regulator_ena_gpio_request(rdev, config);
-		mutex_unlock(&regulator_list_mutex);
 		if (ret != 0) {
 			rdev_err(rdev, "Failed to request enable GPIO: %d\n",
 				 ret);
@@ -5220,7 +5241,6 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	}
 
 	/* register with sysfs */
-	device_initialize(&rdev->dev);
 	rdev->dev.class = &regulator_class;
 	rdev->dev.parent = dev;
 	dev_set_name(&rdev->dev, "regulator.%lu",
@@ -5248,27 +5268,22 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	if (ret < 0)
 		goto wash;
 
-	mutex_lock(&regulator_list_mutex);
 	ret = regulator_init_coupling(rdev);
-	mutex_unlock(&regulator_list_mutex);
 	if (ret < 0)
 		goto wash;
 
 	/* add consumers devices */
 	if (init_data) {
-		mutex_lock(&regulator_list_mutex);
 		for (i = 0; i < init_data->num_consumer_supplies; i++) {
 			ret = set_consumer_device_supply(rdev,
 				init_data->consumer_supplies[i].dev_name,
 				init_data->consumer_supplies[i].supply);
 			if (ret < 0) {
-				mutex_unlock(&regulator_list_mutex);
 				dev_err(dev, "Failed to set supply %s\n",
 					init_data->consumer_supplies[i].supply);
 				goto unset_supplies;
 			}
 		}
-		mutex_unlock(&regulator_list_mutex);
 	}
 
 	if (!rdev->desc->ops->get_voltage &&
@@ -5303,13 +5318,11 @@ wash:
 	mutex_lock(&regulator_list_mutex);
 	regulator_ena_gpio_free(rdev);
 	mutex_unlock(&regulator_list_mutex);
-	put_device(&rdev->dev);
-	rdev = NULL;
 clean:
 	if (dangling_of_gpiod)
 		gpiod_put(config->ena_gpiod);
-	kfree(rdev);
 	kfree(config);
+	put_device(&rdev->dev);
 rinse:
 	if (dangling_cfg_gpiod)
 		gpiod_put(cfg->ena_gpiod);
diff --git a/drivers/regulator/cros-ec-regulator.c b/drivers/regulator/cros-ec-regulator.c
index 3117bbd2826b..eb3fc1db4edc 100644
--- a/drivers/regulator/cros-ec-regulator.c
+++ b/drivers/regulator/cros-ec-regulator.c
@@ -170,6 +170,9 @@ static int cros_ec_regulator_init_info(struct device *dev,
 	data->voltages_mV =
 		devm_kmemdup(dev, resp.voltages_mv,
 			     sizeof(u16) * data->num_voltages, GFP_KERNEL);
+	if (!data->voltages_mV)
+		return -ENOMEM;
+
 	data->desc.n_voltages = data->num_voltages;
 
 	/* Make sure the returned name is always a valid string */
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index d54830e48b8d..142a70a89153 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -182,7 +182,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 
 		drvdata->enable_clock = devm_clk_get(dev, NULL);
 		if (IS_ERR(drvdata->enable_clock)) {
-			dev_err(dev, "Cant get enable-clock from devicetree\n");
+			dev_err(dev, "Can't get enable-clock from devicetree\n");
 			return -ENOENT;
 		}
 	} else {
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 3234b118b53e..990bd50771d8 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -279,7 +279,7 @@ static int pwm_regulator_init_table(struct platform_device *pdev,
 		return ret;
 	}
 
-	drvdata->state			= -EINVAL;
+	drvdata->state			= -ENOTRECOVERABLE;
 	drvdata->duty_cycle_table	= duty_cycle_table;
 	drvdata->desc.ops = &pwm_regulator_voltage_table_ops;
 	drvdata->desc.n_voltages	= length / sizeof(*duty_cycle_table);
diff --git a/drivers/regulator/slg51000-regulator.c b/drivers/regulator/slg51000-regulator.c
index 44e4cecbf6de..87b020d0b958 100644
--- a/drivers/regulator/slg51000-regulator.c
+++ b/drivers/regulator/slg51000-regulator.c
@@ -319,7 +319,7 @@ static int slg51000_regulator_init(struct slg51000 *chip)
 				rdesc->linear_min_sel = 0;
 				break;
 			}
-			/* Fall through - to the check below.*/
+			fallthrough;	/* to the check below */
 
 		default:
 			rdesc->linear_min_sel = vsel_range[0];
diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c
index f7db250a7583..430265c404d6 100644
--- a/drivers/regulator/twl6030-regulator.c
+++ b/drivers/regulator/twl6030-regulator.c
@@ -312,7 +312,7 @@ static int twl6030smps_list_voltage(struct regulator_dev *rdev, unsigned index)
 	switch (info->flags) {
 	case SMPS_OFFSET_EN:
 		voltage = 100000;
-		/* fall through */
+		fallthrough;
 	case 0:
 		switch (index) {
 		case 0:
diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c
index 6955fab0a78b..d94b7391bf9d 100644
--- a/drivers/remoteproc/omap_remoteproc.c
+++ b/drivers/remoteproc/omap_remoteproc.c
@@ -511,7 +511,6 @@ static void omap_rproc_mbox_callback(struct mbox_client *client, void *data)
 		dev_info(dev, "received echo reply from %s\n", name);
 		break;
 	case RP_MBOX_SUSPEND_ACK:
-		/* Fall through */
 	case RP_MBOX_SUSPEND_CANCEL:
 		oproc->suspend_acked = msg == RP_MBOX_SUSPEND_ACK;
 		complete(&oproc->pm_comp);
diff --git a/drivers/reset/reset-imx7.c b/drivers/reset/reset-imx7.c
index d170fe663210..e8aa8691deb2 100644
--- a/drivers/reset/reset-imx7.c
+++ b/drivers/reset/reset-imx7.c
@@ -222,7 +222,7 @@ static int imx8mq_reset_set(struct reset_controller_dev *rcdev,
 
 	switch (id) {
 	case IMX8MQ_RESET_PCIEPHY:
-	case IMX8MQ_RESET_PCIEPHY2: /* fallthrough */
+	case IMX8MQ_RESET_PCIEPHY2:
 		/*
 		 * wait for more than 10us to release phy g_rst and
 		 * btnrst
@@ -232,12 +232,12 @@ static int imx8mq_reset_set(struct reset_controller_dev *rcdev,
 		break;
 
 	case IMX8MQ_RESET_PCIE_CTRL_APPS_EN:
-	case IMX8MQ_RESET_PCIE2_CTRL_APPS_EN:	/* fallthrough */
-	case IMX8MQ_RESET_MIPI_DSI_PCLK_RESET_N:	/* fallthrough */
-	case IMX8MQ_RESET_MIPI_DSI_ESC_RESET_N:	/* fallthrough */
-	case IMX8MQ_RESET_MIPI_DSI_DPI_RESET_N:	/* fallthrough */
-	case IMX8MQ_RESET_MIPI_DSI_RESET_N:	/* fallthrough */
-	case IMX8MQ_RESET_MIPI_DSI_RESET_BYTE_N:	/* fallthrough */
+	case IMX8MQ_RESET_PCIE2_CTRL_APPS_EN:
+	case IMX8MQ_RESET_MIPI_DSI_PCLK_RESET_N:
+	case IMX8MQ_RESET_MIPI_DSI_ESC_RESET_N:
+	case IMX8MQ_RESET_MIPI_DSI_DPI_RESET_N:
+	case IMX8MQ_RESET_MIPI_DSI_RESET_N:
+	case IMX8MQ_RESET_MIPI_DSI_RESET_BYTE_N:
 		value = assert ? 0 : bit;
 		break;
 	}
diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c
index 1995f5b3ea67..f40312b16da0 100644
--- a/drivers/rpmsg/qcom_glink_native.c
+++ b/drivers/rpmsg/qcom_glink_native.c
@@ -553,7 +553,7 @@ static void qcom_glink_receive_version(struct qcom_glink *glink,
 		break;
 	case GLINK_VERSION_1:
 		glink->features &= features;
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		qcom_glink_send_version_ack(glink);
 		break;
@@ -584,7 +584,7 @@ static void qcom_glink_receive_version_ack(struct qcom_glink *glink,
 			break;
 
 		glink->features &= features;
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		qcom_glink_send_version(glink);
 		break;
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 9b70b371bd0c..8a89bc52b0d4 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -740,7 +740,7 @@ static int wdt_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		wdt_margin = new_margin;
 		wdt_ping();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(wdt_margin, (int __user *)arg);
 
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index ca55ba975aeb..f8b99cb72959 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -353,7 +353,7 @@ static int pcf85063_load_capacitance(struct pcf85063 *pcf85063,
 	default:
 		dev_warn(&pcf85063->rtc->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 7000",
 			 load);
-		/* fall through */
+		fallthrough;
 	case 7000:
 		break;
 	case 12500:
diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c
index 47e0f411dd5c..57d351dfe272 100644
--- a/drivers/rtc/rtc-pcf8523.c
+++ b/drivers/rtc/rtc-pcf8523.c
@@ -108,7 +108,7 @@ static int pcf8523_load_capacitance(struct i2c_client *client)
 	default:
 		dev_warn(&client->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 12500",
 			 load);
-		/* fall through */
+		fallthrough;
 	case 12500:
 		value |= REG_CONTROL1_CAP_SEL;
 		break;
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index c9bc3d4a1e66..0a969af80af7 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -331,7 +331,7 @@ static int stmp3xxx_rtc_probe(struct platform_device *pdev)
 	default:
 		dev_warn(&pdev->dev,
 			 "invalid crystal-freq specified in device-tree. Assuming no crystal\n");
-		/* fall-through */
+		fallthrough;
 	case 0:
 		/* keep XTAL on in low-power mode */
 		pers0_set = STMP3XXX_RTC_PERSISTENT0_XTAL24MHZ_PWRUP;
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 94edbb33d0d1..aca022239b33 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -677,6 +677,11 @@ static int slow_eval_known_fn(struct subchannel *sch, void *data)
 		rc = css_evaluate_known_subchannel(sch, 1);
 		if (rc == -EAGAIN)
 			css_schedule_eval(sch->schid);
+		/*
+		 * The loop might take long time for platforms with lots of
+		 * known devices. Allow scheduling here.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c
index 3ce99e4db44d..661d2a49bce9 100644
--- a/drivers/s390/net/ctcm_fsms.c
+++ b/drivers/s390/net/ctcm_fsms.c
@@ -1695,7 +1695,7 @@ static void ctcmpc_chx_attnbusy(fsm_instance *fsm, int event, void *arg)
 			grp->changed_side = 2;
 			break;
 		}
-		/* Else, fall through */
+		fallthrough;
 	case MPCG_STATE_XID0IOWAIX:
 	case MPCG_STATE_XID7INITW:
 	case MPCG_STATE_XID7INITX:
diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c
index ab316baa8284..85a1a4533cbe 100644
--- a/drivers/s390/net/ctcm_mpc.c
+++ b/drivers/s390/net/ctcm_mpc.c
@@ -357,7 +357,7 @@ int ctc_mpc_alloc_channel(int port_num, void (*callback)(int, int))
 		/*fsm_newstate(grp->fsm, MPCG_STATE_XID2INITW);*/
 		if (callback)
 			grp->send_qllc_disc = 1;
-		/* Else, fall through */
+		fallthrough;
 	case MPCG_STATE_XID0IOWAIT:
 		fsm_deltimer(&grp->timer);
 		grp->outstanding_xid2 = 0;
@@ -1470,7 +1470,7 @@ static void mpc_action_timeout(fsm_instance *fi, int event, void *arg)
 		if ((fsm_getstate(rch->fsm) == CH_XID0_PENDING) &&
 		   (fsm_getstate(wch->fsm) == CH_XID0_PENDING))
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		fsm_event(grp->fsm, MPCG_EVENT_INOP, dev);
 	}
@@ -2089,7 +2089,7 @@ static int mpc_send_qllc_discontact(struct net_device *dev)
 			grp->estconnfunc = NULL;
 			break;
 		}
-		/* Else, fall through */
+		fallthrough;
 	case MPCG_STATE_FLOWC:
 	case MPCG_STATE_READY:
 		grp->send_qllc_disc = 2;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index bba1b54b8aa3..6a7398251423 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1071,7 +1071,7 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
 		break;
 	case -EIO:
 		qeth_schedule_recovery(card);
-		/* fall through */
+		fallthrough;
 	default:
 		qeth_clear_ipacmd_list(card);
 		goto err_idx;
@@ -2886,7 +2886,7 @@ void qeth_print_status_message(struct qeth_card *card)
 				card->info.mcl_level[3]);
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case QETH_CARD_TYPE_IQD:
 		if (IS_VM_NIC(card) || (card->info.mcl_level[0] & 0x80)) {
 			card->info.mcl_level[0] = (char) _ebcasc[(__u8)
diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c
index ebdc03210608..f870c5322bfe 100644
--- a/drivers/s390/net/qeth_ethtool.c
+++ b/drivers/s390/net/qeth_ethtool.c
@@ -356,7 +356,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd,
 						     10000baseT_Full);
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     10000baseT_Full);
-		/* fall through */
+		fallthrough;
 	case SPEED_1000:
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     1000baseT_Full);
@@ -366,7 +366,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd,
 						     1000baseT_Half);
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     1000baseT_Half);
-		/* fall through */
+		fallthrough;
 	case SPEED_100:
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     100baseT_Full);
@@ -376,7 +376,7 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd,
 						     100baseT_Half);
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     100baseT_Half);
-		/* fall through */
+		fallthrough;
 	case SPEED_10:
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     10baseT_Full);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8b342a88ff5c..3a94f6cad167 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -488,7 +488,7 @@ static void qeth_l2_rx_mode_work(struct work_struct *work)
 				kfree(mac);
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			/* for next call to set_rx_mode(): */
 			mac->disp_flag = QETH_DISP_ADDR_DELETE;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index fe44b0249e34..4d461960370d 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1235,7 +1235,7 @@ static void qeth_l3_rx_mode_work(struct work_struct *work)
 					break;
 				}
 				addr->ref_counter = 1;
-				/* fall through */
+				fallthrough;
 			default:
 				/* for next call to set_rx_mode(): */
 				addr->disp_flag = QETH_DISP_ADDR_DELETE;
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index c795f22249d8..140186fe1d1e 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -434,7 +434,7 @@ static void zfcp_fsf_req_complete(struct zfcp_fsf_req *req)
 		return;
 	}
 
-	del_timer(&req->timer);
+	del_timer_sync(&req->timer);
 	zfcp_fsf_protstatus_eval(req);
 	zfcp_fsf_fsfstatus_eval(req);
 	req->handler(req);
@@ -867,7 +867,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req)
 	req->qdio_req.qdio_outb_usage = atomic_read(&qdio->req_q_free);
 	req->issued = get_tod_clock();
 	if (zfcp_qdio_send(qdio, &req->qdio_req)) {
-		del_timer(&req->timer);
+		del_timer_sync(&req->timer);
 		/* lookup request again, list might have changed */
 		zfcp_reqlist_find_rm(adapter->req_list, req_id);
 		zfcp_erp_adapter_reopen(adapter, 0, "fsrs__1");
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 461b3babb601..84b57a8f86bf 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1832,7 +1832,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 	case REQUEST_SENSE:
 		/* clear the internal sense magic */
 		SCp->cmnd[6] = 0;
-		/* fall through */
+		fallthrough;
 	default:
 		/* OK, get it from the command */
 		switch(SCp->sc_data_direction) {
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index bb49d83cadc7..ccb061ab0a0a 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -2635,7 +2635,7 @@ static int blogic_resultcode(struct blogic_adapter *adapter,
 	case BLOGIC_BAD_CMD_PARAM:
 		blogic_warn("BusLogic Driver Protocol Error 0x%02X\n",
 				adapter, adapter_status);
-		/* fall through */
+		fallthrough;
 	case BLOGIC_DATA_UNDERRUN:
 	case BLOGIC_DATA_OVERRUN:
 	case BLOGIC_NOEXPECT_BUSFREE:
diff --git a/drivers/scsi/FlashPoint.c b/drivers/scsi/FlashPoint.c
index 0f17bd51088a..24ace1824048 100644
--- a/drivers/scsi/FlashPoint.c
+++ b/drivers/scsi/FlashPoint.c
@@ -1034,11 +1034,14 @@ static int FlashPoint_ProbeHostAdapter(struct sccb_mgr_info *pCardInfo)
 			temp6 >>= 1;
 			switch (temp & 0x3) {
 			case AUTO_RATE_20:	/* Synchronous, 20 mega-transfers/second */
-				temp6 |= 0x8000;	/* Fall through */
+				temp6 |= 0x8000;
+				fallthrough;
 			case AUTO_RATE_10:	/* Synchronous, 10 mega-transfers/second */
-				temp5 |= 0x8000;	/* Fall through */
+				temp5 |= 0x8000;
+				fallthrough;
 			case AUTO_RATE_05:	/* Synchronous, 5 mega-transfers/second */
-				temp2 |= 0x8000;	/* Fall through */
+				temp2 |= 0x8000;
+				fallthrough;
 			case AUTO_RATE_00:	/* Asynchronous */
 				break;
 			}
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index f2f7e6e76c07..d654a6cc4162 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -1943,7 +1943,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						return;
 
 					/* Reject message */
-					/* Fall through */
+					fallthrough;
 				default:
 					/*
 					 * If we get something weird that we aren't expecting,
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 769af4ca9ca9..fd6ae5c38086 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -2809,7 +2809,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 					    !(dev->raw_io_64) ||
 					    ((scsicmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
 						break;
-					/* fall through */
+					fallthrough;
 				case INQUIRY:
 				case READ_CAPACITY:
 				case TEST_UNIT_READY:
@@ -2884,7 +2884,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		/* Issue FIB to tell Firmware to flush it's cache */
 		if ((aac_cache & 6) != 2)
 			return aac_synchronize(scsicmd);
-		/* fall through */
+		fallthrough;
 	case INQUIRY:
 	{
 		struct inquiry_data inq_data;
@@ -3240,7 +3240,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				     SCSI_SENSE_BUFFERSIZE));
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case RESERVE:
 	case RELEASE:
 	case REZERO_UNIT:
@@ -3253,7 +3253,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 	case START_STOP:
 		return aac_start_stop(scsicmd);
 
-	/* FALLTHRU */
+		fallthrough;
 	default:
 	/*
 	 *	Unhandled commands
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index adbdc3b7c7a7..383e74fea6ed 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1431,7 +1431,7 @@ retry_next:
 						"enclosure services event");
 				scsi_device_set_state(device, SDEV_RUNNING);
 			}
-			/* FALLTHRU */
+			fallthrough;
 		case CHANGE:
 			if ((channel == CONTAINER_CHANNEL)
 			 && (!dev->fsa_dev[container].valid)) {
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 8588da0a0655..a3aee146537b 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -765,7 +765,7 @@ static int aac_eh_abort(struct scsi_cmnd* cmd)
 			    !(aac->raw_io_64) ||
 			    ((cmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
 				break;
-			/* fall through */
+			fallthrough;
 		case INQUIRY:
 		case READ_CAPACITY:
 			/*
diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c
index c912d29b8bdf..1c617c0d5899 100644
--- a/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -2274,7 +2274,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat)
 			switch (scb->hscb->task_management) {
 			case SIU_TASKMGMT_ABORT_TASK:
 				tag = SCB_GET_TAG(scb);
-				/* fall through */
+				fallthrough;
 			case SIU_TASKMGMT_ABORT_TASK_SET:
 			case SIU_TASKMGMT_CLEAR_TASK_SET:
 				lun = scb->hscb->lun;
@@ -2285,7 +2285,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat)
 				break;
 			case SIU_TASKMGMT_LUN_RESET:
 				lun = scb->hscb->lun;
-				/* fall through */
+				fallthrough;
 			case SIU_TASKMGMT_TARGET_RESET:
 			{
 				struct ahd_devinfo devinfo;
@@ -3791,7 +3791,7 @@ ahd_validate_width(struct ahd_softc *ahd, struct ahd_initiator_tinfo *tinfo,
 			*bus_width = MSG_EXT_WDTR_BUS_16_BIT;
 			break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case MSG_EXT_WDTR_BUS_8_BIT:
 		*bus_width = MSG_EXT_WDTR_BUS_8_BIT;
 		break;
@@ -5104,7 +5104,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo)
 		break;
 	case MSG_MESSAGE_REJECT:
 		response = ahd_handle_msg_reject(ahd, devinfo);
-		/* FALLTHROUGH */
+		fallthrough;
 	case MSG_NOOP:
 		done = MSGLOOP_MSGCOMPLETE;
 		break;
@@ -5454,7 +5454,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo)
 			       ahd_name(ahd), ahd_inb(ahd, SCSISIGI));
 #endif
 		ahd->msg_flags |= MSG_FLAG_EXPECT_QASREJ_BUSFREE;
-		/* FALLTHROUGH */
+		fallthrough;
 	case MSG_TERM_IO_PROC:
 	default:
 		reject = TRUE;
@@ -6117,17 +6117,17 @@ ahd_free(struct ahd_softc *ahd)
 	default:
 	case 5:
 		ahd_shutdown(ahd);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 4:
 		ahd_dmamap_unload(ahd, ahd->shared_data_dmat,
 				  ahd->shared_data_map.dmamap);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 3:
 		ahd_dmamem_free(ahd, ahd->shared_data_dmat, ahd->qoutfifo,
 				ahd->shared_data_map.dmamap);
 		ahd_dmamap_destroy(ahd, ahd->shared_data_dmat,
 				   ahd->shared_data_map.dmamap);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 2:
 		ahd_dma_tag_destroy(ahd, ahd->shared_data_dmat);
 	case 1:
@@ -6513,7 +6513,7 @@ ahd_fini_scbdata(struct ahd_softc *ahd)
 		}
 		ahd_dma_tag_destroy(ahd, scb_data->sense_dmat);
 	}
-		/* fall through */
+		fallthrough;
 	case 6:
 	{
 		struct map_node *sg_map;
@@ -6528,7 +6528,7 @@ ahd_fini_scbdata(struct ahd_softc *ahd)
 		}
 		ahd_dma_tag_destroy(ahd, scb_data->sg_dmat);
 	}
-		/* fall through */
+		fallthrough;
 	case 5:
 	{
 		struct map_node *hscb_map;
@@ -7171,7 +7171,7 @@ ahd_init(struct ahd_softc *ahd)
 		case FLX_CSTAT_OVER:
 		case FLX_CSTAT_UNDER:
 			warn_user++;
-			/* fall through */
+			fallthrough;
 		case FLX_CSTAT_INVALID:
 		case FLX_CSTAT_OKAY:
 			if (warn_user == 0 && bootverbose == 0)
@@ -8175,12 +8175,12 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel,
 				if ((scb->flags & SCB_ACTIVE) == 0)
 					printk("Inactive SCB in qinfifo\n");
 				ahd_done_with_status(ahd, scb, status);
-				/* FALLTHROUGH */
+				fallthrough;
 			case SEARCH_REMOVE:
 				break;
 			case SEARCH_PRINT:
 				printk(" 0x%x", ahd->qinfifo[qinpos]);
-				/* FALLTHROUGH */
+				fallthrough;
 			case SEARCH_COUNT:
 				ahd_qinfifo_requeue(ahd, prev_scb, scb);
 				prev_scb = scb;
@@ -8271,7 +8271,7 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel,
 				if ((mk_msg_scb->flags & SCB_ACTIVE) == 0)
 					printk("Inactive SCB pending MK_MSG\n");
 				ahd_done_with_status(ahd, mk_msg_scb, status);
-				/* FALLTHROUGH */
+				fallthrough;
 			case SEARCH_REMOVE:
 			{
 				u_int tail_offset;
@@ -8295,7 +8295,7 @@ ahd_search_qinfifo(struct ahd_softc *ahd, int target, char channel,
 			}
 			case SEARCH_PRINT:
 				printk(" 0x%x", SCB_GET_TAG(scb));
-				/* FALLTHROUGH */
+				fallthrough;
 			case SEARCH_COUNT:
 				break;
 			}
@@ -8376,7 +8376,7 @@ ahd_search_scb_list(struct ahd_softc *ahd, int target, char channel,
 			if ((scb->flags & SCB_ACTIVE) == 0)
 				printk("Inactive SCB in Waiting List\n");
 			ahd_done_with_status(ahd, scb, status);
-			/* fall through */
+			fallthrough;
 		case SEARCH_REMOVE:
 			ahd_rem_wscb(ahd, scbid, prev, next, tid);
 			*list_tail = prev;
@@ -8385,7 +8385,7 @@ ahd_search_scb_list(struct ahd_softc *ahd, int target, char channel,
 			break;
 		case SEARCH_PRINT:
 			printk("0x%x ", scbid);
-			/* fall through */
+			fallthrough;
 		case SEARCH_COUNT:
 			prev = scbid;
 			break;
@@ -9023,7 +9023,7 @@ ahd_handle_scsi_status(struct ahd_softc *ahd, struct scb *scb)
 	case SCSI_STATUS_OK:
 		printk("%s: Interrupted for status of 0???\n",
 		       ahd_name(ahd));
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		ahd_done(ahd, scb);
 		break;
@@ -9512,7 +9512,7 @@ ahd_download_instr(struct ahd_softc *ahd, u_int instrptr, uint8_t *dconsts)
 		fmt3_ins = &instr.format3;
 		fmt3_ins->address = ahd_resolve_seqaddr(ahd, fmt3_ins->address);
 	}
-		/* fall through */
+		fallthrough;
 	case AIC_OP_OR:
 	case AIC_OP_AND:
 	case AIC_OP_XOR:
@@ -9523,7 +9523,7 @@ ahd_download_instr(struct ahd_softc *ahd, u_int instrptr, uint8_t *dconsts)
 			fmt1_ins->immediate = dconsts[fmt1_ins->immediate];
 		}
 		fmt1_ins->parity = 0;
-		/* fall through */
+		fallthrough;
 	case AIC_OP_ROL:
 	{
 		int i, count;
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index d019e3f2bb9b..7c321303969e 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -2035,7 +2035,7 @@ ahd_linux_queue_cmd_complete(struct ahd_softc *ahd, struct scsi_cmnd *cmd)
 		break;
 	case CAM_AUTOSENSE_FAIL:
 		new_status = DID_ERROR;
-		/* Fallthrough */
+		fallthrough;
 	case CAM_SCSI_STATUS_ERROR:
 		scsi_status = ahd_cmd_get_scsi_status(cmd);
 
diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c
index 3d4df906fa4f..2231c4afa531 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_core.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_core.c
@@ -2404,7 +2404,7 @@ ahc_validate_width(struct ahc_softc *ahc, struct ahc_initiator_tinfo *tinfo,
 			*bus_width = MSG_EXT_WDTR_BUS_16_BIT;
 			break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case MSG_EXT_WDTR_BUS_8_BIT:
 		*bus_width = MSG_EXT_WDTR_BUS_8_BIT;
 		break;
@@ -3599,7 +3599,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 		break;
 	case MSG_MESSAGE_REJECT:
 		response = ahc_handle_msg_reject(ahc, devinfo);
-		/* FALLTHROUGH */
+		fallthrough;
 	case MSG_NOOP:
 		done = MSGLOOP_MSGCOMPLETE;
 		break;
@@ -4465,17 +4465,17 @@ ahc_free(struct ahc_softc *ahc)
 	default:
 	case 5:
 		ahc_shutdown(ahc);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 4:
 		ahc_dmamap_unload(ahc, ahc->shared_data_dmat,
 				  ahc->shared_data_dmamap);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 3:
 		ahc_dmamem_free(ahc, ahc->shared_data_dmat, ahc->qoutfifo,
 				ahc->shared_data_dmamap);
 		ahc_dmamap_destroy(ahc, ahc->shared_data_dmat,
 				   ahc->shared_data_dmamap);
-		/* FALLTHROUGH */
+		fallthrough;
 	case 2:
 		ahc_dma_tag_destroy(ahc, ahc->shared_data_dmat);
 	case 1:
@@ -4893,30 +4893,30 @@ ahc_fini_scbdata(struct ahc_softc *ahc)
 		}
 		ahc_dma_tag_destroy(ahc, scb_data->sg_dmat);
 	}
-		/* fall through */
+		fallthrough;
 	case 6:
 		ahc_dmamap_unload(ahc, scb_data->sense_dmat,
 				  scb_data->sense_dmamap);
-		/* fall through */
+		fallthrough;
 	case 5:
 		ahc_dmamem_free(ahc, scb_data->sense_dmat, scb_data->sense,
 				scb_data->sense_dmamap);
 		ahc_dmamap_destroy(ahc, scb_data->sense_dmat,
 				   scb_data->sense_dmamap);
-		/* fall through */
+		fallthrough;
 	case 4:
 		ahc_dma_tag_destroy(ahc, scb_data->sense_dmat);
-		/* fall through */
+		fallthrough;
 	case 3:
 		ahc_dmamap_unload(ahc, scb_data->hscb_dmat,
 				  scb_data->hscb_dmamap);
-		/* fall through */
+		fallthrough;
 	case 2:
 		ahc_dmamem_free(ahc, scb_data->hscb_dmat, scb_data->hscbs,
 				scb_data->hscb_dmamap);
 		ahc_dmamap_destroy(ahc, scb_data->hscb_dmat,
 				   scb_data->hscb_dmamap);
-		/* fall through */
+		fallthrough;
 	case 1:
 		ahc_dma_tag_destroy(ahc, scb_data->hscb_dmat);
 		break;
@@ -5981,7 +5981,7 @@ ahc_search_qinfifo(struct ahc_softc *ahc, int target, char channel,
 					printk("Inactive SCB in Waiting List\n");
 				ahc_done(ahc, scb);
 			}
-				/* fall through */
+				fallthrough;
 			case SEARCH_REMOVE:
 				next = ahc_rem_wscb(ahc, next, prev);
 				break;
@@ -6987,7 +6987,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts)
 		address -= address_offset;
 		fmt3_ins->address = address;
 	}
-		/* fall through */
+		fallthrough;
 	case AIC_OP_OR:
 	case AIC_OP_AND:
 	case AIC_OP_XOR:
@@ -7013,7 +7013,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts)
 			fmt1_ins->opcode = AIC_OP_AND;
 			fmt1_ins->immediate = 0xff;
 		}
-		/* fall through */
+		fallthrough;
 	case AIC_OP_ROL:
 		if ((ahc->features & AHC_ULTRA2) != 0) {
 			int i, count;
diff --git a/drivers/scsi/aic94xx/aic94xx_scb.c b/drivers/scsi/aic94xx/aic94xx_scb.c
index c264b4b56970..e2d880a5f391 100644
--- a/drivers/scsi/aic94xx/aic94xx_scb.c
+++ b/drivers/scsi/aic94xx/aic94xx_scb.c
@@ -706,11 +706,11 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd)
 	switch (pd->max_sas_lrate) {
 	case SAS_LINK_RATE_6_0_GBPS:
 		*speed_mask &= ~SAS_SPEED_60_DIS;
-		/* fall through*/
+		fallthrough;
 	default:
 	case SAS_LINK_RATE_3_0_GBPS:
 		*speed_mask &= ~SAS_SPEED_30_DIS;
-		/* fall through*/
+		fallthrough;
 	case SAS_LINK_RATE_1_5_GBPS:
 		*speed_mask &= ~SAS_SPEED_15_DIS;
 	}
@@ -718,7 +718,7 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd)
 	switch (pd->min_sas_lrate) {
 	case SAS_LINK_RATE_6_0_GBPS:
 		*speed_mask |= SAS_SPEED_30_DIS;
-		/* fall through*/
+		fallthrough;
 	case SAS_LINK_RATE_3_0_GBPS:
 		*speed_mask |= SAS_SPEED_15_DIS;
 	default:
@@ -730,7 +730,7 @@ static void set_speed_mask(u8 *speed_mask, struct asd_phy_desc *pd)
 	switch (pd->max_sata_lrate) {
 	case SAS_LINK_RATE_3_0_GBPS:
 		*speed_mask &= ~SATA_SPEED_30_DIS;
-		/* fall through*/
+		fallthrough;
 	default:
 	case SAS_LINK_RATE_1_5_GBPS:
 		*speed_mask &= ~SATA_SPEED_15_DIS;
@@ -789,7 +789,7 @@ void asd_build_control_phy(struct asd_ascb *ascb, int phy_id, u8 subfunc)
 
 		/* link reset retries, this should be nominal */
 		control_phy->link_reset_retries = 10;
-		/* fall through */
+		fallthrough;
 
 	case RELEASE_SPINUP_HOLD: /* 0x02 */
 		/* decide the func_mask */
diff --git a/drivers/scsi/aic94xx/aic94xx_tmf.c b/drivers/scsi/aic94xx/aic94xx_tmf.c
index 1fcee65193a3..0eb6e206a2b4 100644
--- a/drivers/scsi/aic94xx/aic94xx_tmf.c
+++ b/drivers/scsi/aic94xx/aic94xx_tmf.c
@@ -490,7 +490,7 @@ int asd_abort_task(struct sas_task *task)
 		switch (tcs.dl_opcode) {
 		default:
 			res = asd_clear_nexus(task);
-			/* fallthrough */
+			fallthrough;
 		case TC_NO_ERROR:
 			break;
 			/* The task hasn't been sent to the device xor
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index fa562a085600..ec895d0319f0 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -4470,7 +4470,7 @@ static const char *arcmsr_info(struct Scsi_Host *host)
 	case PCI_DEVICE_ID_ARECA_1202:
 	case PCI_DEVICE_ID_ARECA_1210:
 		raid6 = 0;
-		/*FALLTHRU*/
+		fallthrough;
 	case PCI_DEVICE_ID_ARECA_1120:
 	case PCI_DEVICE_ID_ARECA_1130:
 	case PCI_DEVICE_ID_ARECA_1160:
diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index 6c68c2303638..2e687ce60753 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -603,7 +603,7 @@ static void fas216_handlesync(FAS216_Info *info, char *msg)
 		msgqueue_flush(&info->scsi.msgs);
 		msgqueue_addmsg(&info->scsi.msgs, 1, MESSAGE_REJECT);
 		info->scsi.phase = PHASE_MSGOUT_EXPECT;
-		/* fall through */
+		fallthrough;
 
 	case async:
 		dev->period = info->ifcfg.asyncperiod / 4;
@@ -916,7 +916,7 @@ static void fas216_disconnect_intr(FAS216_Info *info)
 			fas216_done(info, DID_ABORT);
 			break;
 		}
-		/* else, fall through */
+		fallthrough;
 
 	default:				/* huh?					*/
 		printk(KERN_ERR "scsi%d.%c: unexpected disconnect in phase %s\n",
@@ -1413,7 +1413,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne
 	case STATE(STAT_STATUS, PHASE_DATAOUT): /* Data Out     -> Status       */
 	case STATE(STAT_STATUS, PHASE_DATAIN):  /* Data In      -> Status       */
 		fas216_stoptransfer(info);
-		/* fall through */
+		fallthrough;
 
 	case STATE(STAT_STATUS, PHASE_SELSTEPS):/* Sel w/ steps -> Status       */
 	case STATE(STAT_STATUS, PHASE_MSGOUT):  /* Message Out  -> Status       */
@@ -1426,7 +1426,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne
 	case STATE(STAT_MESGIN, PHASE_DATAOUT): /* Data Out     -> Message In   */
 	case STATE(STAT_MESGIN, PHASE_DATAIN):  /* Data In      -> Message In   */
 		fas216_stoptransfer(info);
-		/* fall through */
+		fallthrough;
 
 	case STATE(STAT_MESGIN, PHASE_COMMAND):	/* Command	-> Message In	*/
 	case STATE(STAT_MESGIN, PHASE_SELSTEPS):/* Sel w/ steps -> Message In   */
@@ -1581,7 +1581,7 @@ static void fas216_funcdone_intr(FAS216_Info *info, unsigned int stat, unsigned
 			fas216_message(info);
 			break;
 		}
-		/* else, fall through */
+		fallthrough;
 
 	default:
 		fas216_log(info, 0, "internal phase %s for function done?"
@@ -1964,7 +1964,7 @@ static void fas216_kick(FAS216_Info *info)
 	switch (where_from) {
 	case TYPE_QUEUE:
 		fas216_allocate_tag(info, SCpnt);
-		/* fall through */
+		fallthrough;
 	case TYPE_OTHER:
 		fas216_start_command(info, SCpnt);
 		break;
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index 93da6344424d..a13c203ef7a9 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -677,7 +677,7 @@ int beiscsi_set_param(struct iscsi_cls_conn *cls_conn,
 	case ISCSI_PARAM_MAX_XMIT_DLENGTH:
 		if (conn->max_xmit_dlength > 65536)
 			conn->max_xmit_dlength = 65536;
-		/* fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 8dc2e0824ad7..5c3513a4b450 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -1532,7 +1532,7 @@ beiscsi_hdl_get_handle(struct beiscsi_conn *beiscsi_conn,
 		break;
 	case UNSOL_DATA_DIGEST_ERROR_NOTIFY:
 		error = 1;
-		/* fall through */
+		fallthrough;
 	case UNSOL_DATA_NOTIFY:
 		pasync_handle = pasync_ctx->async_entry[ci].data;
 		break;
diff --git a/drivers/scsi/bfa/bfa_fcpim.c b/drivers/scsi/bfa/bfa_fcpim.c
index 29f99561dfc3..38d1c453074d 100644
--- a/drivers/scsi/bfa/bfa_fcpim.c
+++ b/drivers/scsi/bfa/bfa_fcpim.c
@@ -2572,7 +2572,7 @@ bfa_ioim_send_ioreq(struct bfa_ioim_s *ioim)
 	case FCP_IODIR_RW:
 		bfa_stats(itnim, input_reqs);
 		bfa_stats(itnim, output_reqs);
-		/* fall through */
+		fallthrough;
 	default:
 		bfi_h2i_set(m->mh, BFI_MC_IOIM_IO, 0, bfa_fn_lpu(ioim->bfa));
 	}
@@ -2807,7 +2807,7 @@ bfa_ioim_isr(struct bfa_s *bfa, struct bfi_msg_s *m)
 
 	case BFI_IOIM_STS_TIMEDOUT:
 		bfa_stats(ioim->itnim, iocomp_timedout);
-		/* fall through */
+		fallthrough;
 	case BFI_IOIM_STS_ABORTED:
 		rsp->io_status = BFI_IOIM_STS_ABORTED;
 		bfa_stats(ioim->itnim, iocomp_aborted);
@@ -3203,7 +3203,7 @@ bfa_tskim_sm_cleanup_qfull(struct bfa_tskim_s *tskim,
 	switch (event) {
 	case BFA_TSKIM_SM_DONE:
 		bfa_reqq_wcancel(&tskim->reqq_wait);
-		/* fall through */
+		fallthrough;
 	case BFA_TSKIM_SM_QRESUME:
 		bfa_sm_set_state(tskim, bfa_tskim_sm_cleanup);
 		bfa_tskim_send_abort(tskim);
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index 297a77f5806c..3486e402bfc1 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -6422,7 +6422,7 @@ bfa_fcs_vport_sm_logo_for_stop(struct bfa_fcs_vport_s *vport,
 	switch (event) {
 	case BFA_FCS_VPORT_SM_OFFLINE:
 		bfa_sm_send_event(vport->lps, BFA_LPS_SM_OFFLINE);
-		/* fall through */
+		fallthrough;
 
 	case BFA_FCS_VPORT_SM_RSP_OK:
 	case BFA_FCS_VPORT_SM_RSP_ERROR:
@@ -6448,7 +6448,7 @@ bfa_fcs_vport_sm_logo(struct bfa_fcs_vport_s *vport,
 	switch (event) {
 	case BFA_FCS_VPORT_SM_OFFLINE:
 		bfa_sm_send_event(vport->lps, BFA_LPS_SM_OFFLINE);
-		/* fall through */
+		fallthrough;
 
 	case BFA_FCS_VPORT_SM_RSP_OK:
 	case BFA_FCS_VPORT_SM_RSP_ERROR:
diff --git a/drivers/scsi/bfa/bfa_fcs_rport.c b/drivers/scsi/bfa/bfa_fcs_rport.c
index 143c35bd668c..c21aa37b8adb 100644
--- a/drivers/scsi/bfa/bfa_fcs_rport.c
+++ b/drivers/scsi/bfa/bfa_fcs_rport.c
@@ -419,13 +419,13 @@ bfa_fcs_rport_sm_plogi(struct bfa_fcs_rport_s *rport, enum rport_event event)
 
 	case RPSM_EVENT_LOGO_RCVD:
 		bfa_fcs_rport_send_logo_acc(rport);
-		/* fall through */
+		fallthrough;
 	case RPSM_EVENT_PRLO_RCVD:
 		if (rport->prlo == BFA_TRUE)
 			bfa_fcs_rport_send_prlo_acc(rport);
 
 		bfa_fcxp_discard(rport->fcxp);
-		/* fall through */
+		fallthrough;
 	case RPSM_EVENT_FAILED:
 		if (rport->plogi_retries < BFA_FCS_RPORT_MAX_RETRIES) {
 			rport->plogi_retries++;
@@ -856,7 +856,7 @@ bfa_fcs_rport_sm_adisc_online(struct bfa_fcs_rport_s *rport,
 		 * At least go offline when a PLOGI is received.
 		 */
 		bfa_fcxp_discard(rport->fcxp);
-		/* fall through */
+		fallthrough;
 
 	case RPSM_EVENT_FAILED:
 	case RPSM_EVENT_ADDRESS_CHANGE:
@@ -1042,7 +1042,7 @@ bfa_fcs_rport_sm_fc4_logosend(struct bfa_fcs_rport_s *rport,
 
 	case RPSM_EVENT_LOGO_RCVD:
 		bfa_fcs_rport_send_logo_acc(rport);
-		/* fall through */
+		fallthrough;
 	case RPSM_EVENT_PRLO_RCVD:
 		if (rport->prlo == BFA_TRUE)
 			bfa_fcs_rport_send_prlo_acc(rport);
@@ -1131,7 +1131,7 @@ bfa_fcs_rport_sm_hcb_offline(struct bfa_fcs_rport_s *rport,
 			bfa_fcs_rport_send_plogiacc(rport, NULL);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case RPSM_EVENT_ADDRESS_CHANGE:
 		if (!bfa_fcs_lport_is_online(rport->port)) {
@@ -1288,7 +1288,7 @@ bfa_fcs_rport_sm_hcb_logosend(struct bfa_fcs_rport_s *rport,
 
 	case RPSM_EVENT_LOGO_RCVD:
 		bfa_fcs_rport_send_logo_acc(rport);
-		/* fall through */
+		fallthrough;
 	case RPSM_EVENT_PRLO_RCVD:
 		if (rport->prlo == BFA_TRUE)
 			bfa_fcs_rport_send_prlo_acc(rport);
@@ -1332,7 +1332,7 @@ bfa_fcs_rport_sm_logo_sending(struct bfa_fcs_rport_s *rport,
 
 	case RPSM_EVENT_LOGO_RCVD:
 		bfa_fcs_rport_send_logo_acc(rport);
-		/* fall through */
+		fallthrough;
 	case RPSM_EVENT_PRLO_RCVD:
 		if (rport->prlo == BFA_TRUE)
 			bfa_fcs_rport_send_prlo_acc(rport);
diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c
index dd5821dfcac2..325ad8a592bb 100644
--- a/drivers/scsi/bfa/bfa_ioc.c
+++ b/drivers/scsi/bfa/bfa_ioc.c
@@ -969,7 +969,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf_s *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_INITFAIL:
 		bfa_iocpf_timer_stop(ioc);
-		/* fall through */
+		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
 		writel(1, ioc->ioc_regs.ioc_sem_reg);
@@ -1045,7 +1045,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf_s *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_FAIL:
 		bfa_iocpf_timer_stop(ioc);
-		/* fall through */
+		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
 		bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL);
@@ -5988,7 +5988,7 @@ bfa_dconf_sm_final_sync(struct bfa_dconf_mod_s *dconf,
 	case BFA_DCONF_SM_IOCDISABLE:
 	case BFA_DCONF_SM_FLASH_COMP:
 		bfa_timer_stop(&dconf->timer);
-		/* fall through */
+		fallthrough;
 	case BFA_DCONF_SM_TIMEOUT:
 		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
 		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
diff --git a/drivers/scsi/bfa/bfa_svc.c b/drivers/scsi/bfa/bfa_svc.c
index 1e266c1ef793..11c0c3e6f014 100644
--- a/drivers/scsi/bfa/bfa_svc.c
+++ b/drivers/scsi/bfa/bfa_svc.c
@@ -6397,7 +6397,7 @@ bfa_dport_sm_starting(struct bfa_dport_s *dport, enum bfa_dport_sm_event event)
 			dport->test_state = BFA_DPORT_ST_INP;
 			bfa_dport_result_start(dport, BFA_DPORT_OPMODE_MANU);
 		}
-		/* fall thru */
+		fallthrough;
 
 	case BFA_DPORT_SM_REQFAIL:
 		bfa_sm_set_state(dport, bfa_dport_sm_enabled);
diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
index e72d7bb7f4f4..08992095ce7a 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
@@ -1404,7 +1404,6 @@ void bnx2fc_indicate_kcqe(void *context, struct kcqe *kcq[],
 			break;
 
 		case FCOE_KCQE_OPCODE_FCOE_ERROR:
-			/* fall thru */
 		default:
 			printk(KERN_ERR PFX "unknown opcode 0x%x\n",
 								kcqe->op_code);
diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index 98d4d39aaa57..7fa20609d5e7 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -2939,7 +2939,7 @@ csio_hws_quiescing(struct csio_hw *hw, enum csio_hw_ev evt)
 		case CSIO_HWE_FW_DLOAD:
 			csio_set_state(&hw->sm, csio_hws_resetting);
 			/* Download firmware */
-			/* Fall through */
+			fallthrough;
 
 		case CSIO_HWE_HBA_RESET:
 			csio_set_state(&hw->sm, csio_hws_resetting);
diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c
index 61cf54208451..dc98f51f466f 100644
--- a/drivers/scsi/csiostor/csio_lnode.c
+++ b/drivers/scsi/csiostor/csio_lnode.c
@@ -1187,7 +1187,6 @@ csio_lns_online(struct csio_lnode *ln, enum csio_ln_ev evt)
 		break;
 
 	case CSIO_LNE_LINK_DOWN:
-		/* Fall through */
 	case CSIO_LNE_DOWN_LINK:
 		csio_set_state(&ln->sm, csio_lns_uninit);
 		if (csio_is_phys_ln(ln)) {
diff --git a/drivers/scsi/csiostor/csio_wr.c b/drivers/scsi/csiostor/csio_wr.c
index 0ca695110f54..9010cb6045dc 100644
--- a/drivers/scsi/csiostor/csio_wr.c
+++ b/drivers/scsi/csiostor/csio_wr.c
@@ -808,7 +808,7 @@ csio_wr_destroy_queues(struct csio_hw *hw, bool cmd)
 
 				csio_q_eqid(hw, i) = CSIO_MAX_QID;
 			}
-			/* fall through */
+			fallthrough;
 		case CSIO_INGRESS:
 			if (csio_q_iqid(hw, i) != CSIO_MAX_QID) {
 				csio_wr_cleanup_iq_ftr(hw, i);
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index 2b48954b6b1e..37d99357120f 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -643,7 +643,7 @@ static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason,
 				 int *need_rst)
 {
 	switch (abort_reason) {
-	case CPL_ERR_BAD_SYN: /* fall through */
+	case CPL_ERR_BAD_SYN:
 	case CPL_ERR_CONN_RESET:
 		return csk->state > CTP_ESTABLISHED ? -EPIPE : -ECONNRESET;
 	case CPL_ERR_XMIT_TIMEDOUT:
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 4e82c14cb795..2c3491528d42 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -1133,7 +1133,7 @@ static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason,
 								int *need_rst)
 {
 	switch (abort_reason) {
-	case CPL_ERR_BAD_SYN: /* fall through */
+	case CPL_ERR_BAD_SYN:
 	case CPL_ERR_CONN_RESET:
 		return csk->state > CTP_ESTABLISHED ?
 			-EPIPE : -ECONNRESET;
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 71aebaf533ea..0e8621a6956d 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -2457,10 +2457,10 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
 		return err;
 	}
 
-	__kfree_skb(skb);
 	log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
 		  "itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
 		  task->itt, skb, skb->len, skb->data_len, err);
+	__kfree_skb(skb);
 	iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
 	iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
 	return err;
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 94250ebe9e80..e72440d919d2 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -748,16 +748,16 @@ static void term_intr(struct cxlflash_cfg *cfg, enum undo_level level,
 		/* SISL_MSI_ASYNC_ERROR is setup only for the primary HWQ */
 		if (index == PRIMARY_HWQ)
 			cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 3, hwq);
-		/* fall through */
+		fallthrough;
 	case UNMAP_TWO:
 		cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 2, hwq);
-		/* fall through */
+		fallthrough;
 	case UNMAP_ONE:
 		cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 1, hwq);
-		/* fall through */
+		fallthrough;
 	case FREE_IRQ:
 		cfg->ops->free_afu_irqs(hwq->ctx_cookie);
-		/* fall through */
+		fallthrough;
 	case UNDO_NOOP:
 		/* No action required */
 		break;
@@ -971,18 +971,18 @@ static void cxlflash_remove(struct pci_dev *pdev)
 	switch (cfg->init_state) {
 	case INIT_STATE_CDEV:
 		cxlflash_release_chrdev(cfg);
-		/* fall through */
+		fallthrough;
 	case INIT_STATE_SCSI:
 		cxlflash_term_local_luns(cfg);
 		scsi_remove_host(cfg->host);
-		/* fall through */
+		fallthrough;
 	case INIT_STATE_AFU:
 		term_afu(cfg);
-		/* fall through */
+		fallthrough;
 	case INIT_STATE_PCI:
 		cfg->ops->destroy_afu(cfg->afu_cookie);
 		pci_disable_device(pdev);
-		/* fall through */
+		fallthrough;
 	case INIT_STATE_NONE:
 		free_mem(cfg);
 		scsi_host_put(cfg->host);
@@ -2355,11 +2355,11 @@ retry:
 			cxlflash_schedule_async_reset(cfg);
 			break;
 		}
-		/* fall through - to retry */
+		fallthrough;	/* to retry */
 	case -EAGAIN:
 		if (++nretry < 2)
 			goto retry;
-		/* fall through - to exit */
+		fallthrough;	/* to exit */
 	default:
 		break;
 	}
@@ -2533,12 +2533,12 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 			cfg->state = STATE_NORMAL;
 		wake_up_all(&cfg->reset_waitq);
 		ssleep(1);
-		/* fall through */
+		fallthrough;
 	case STATE_RESET:
 		wait_event(cfg->reset_waitq, cfg->state != STATE_RESET);
 		if (cfg->state == STATE_NORMAL)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		rc = FAILED;
 		break;
@@ -3019,7 +3019,7 @@ retry:
 		wait_event(cfg->reset_waitq, cfg->state != STATE_RESET);
 		if (cfg->state == STATE_NORMAL)
 			goto retry;
-		/* else, fall through */
+		fallthrough;
 	default:
 		/* Ideally should not happen */
 		dev_err(dev, "%s: Device is not ready, state=%d\n",
@@ -3531,7 +3531,7 @@ static long cxlflash_chr_ioctl(struct file *file, unsigned int cmd,
 		if (likely(do_ioctl))
 			break;
 
-		/* fall through */
+		fallthrough;
 	default:
 		rc = -EINVAL;
 		goto out;
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index 593669ac3669..5dddf67dfa24 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -375,14 +375,13 @@ retry:
 			switch (sshdr.sense_key) {
 			case NO_SENSE:
 			case RECOVERED_ERROR:
-				/* fall through */
 			case NOT_READY:
 				result &= ~SAM_STAT_CHECK_CONDITION;
 				break;
 			case UNIT_ATTENTION:
 				switch (sshdr.asc) {
 				case 0x29: /* Power on Reset or Device Reset */
-					/* fall through */
+					fallthrough;
 				case 0x2A: /* Device capacity changed */
 				case 0x3F: /* Report LUNs changed */
 					/* Retry the command once more */
@@ -1791,13 +1790,12 @@ static int process_sense(struct scsi_device *sdev,
 	switch (sshdr.sense_key) {
 	case NO_SENSE:
 	case RECOVERED_ERROR:
-		/* fall through */
 	case NOT_READY:
 		break;
 	case UNIT_ATTENTION:
 		switch (sshdr.asc) {
 		case 0x29: /* Power on Reset or Device Reset */
-			/* fall through */
+			fallthrough;
 		case 0x2A: /* Device settings/capacity changed */
 			rc = read_cap16(sdev, lli);
 			if (rc) {
@@ -2157,7 +2155,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd, void __user *arg)
 		if (unlikely(rc))
 			goto cxlflash_ioctl_exit;
 
-		/* fall through */
+		fallthrough;
 
 	case DK_CXLFLASH_MANAGE_LUN:
 		known_ioctl = true;
@@ -2168,7 +2166,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd, void __user *arg)
 		if (likely(do_ioctl))
 			break;
 
-		/* fall through */
+		fallthrough;
 	default:
 		rc = -EINVAL;
 		goto cxlflash_ioctl_exit;
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 8acd4bb9fefb..4a3f7831a2d6 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -60,7 +60,7 @@ static int tur_done(struct scsi_device *sdev, struct hp_sw_dh_data *h,
 			ret = SCSI_DH_OK;
 			break;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		sdev_printk(KERN_WARNING, sdev,
 			   "%s: sending tur failed, sense %x/%x/%x\n",
@@ -147,7 +147,7 @@ retry:
 				rc = SCSI_DH_RETRY;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			sdev_printk(KERN_WARNING, sdev,
 				    "%s: sending start_stop_unit failed, "
diff --git a/drivers/scsi/esas2r/esas2r_flash.c b/drivers/scsi/esas2r/esas2r_flash.c
index b02ac389e6c6..429d64299fe9 100644
--- a/drivers/scsi/esas2r/esas2r_flash.c
+++ b/drivers/scsi/esas2r/esas2r_flash.c
@@ -1500,7 +1500,7 @@ bool esas2r_fm_api(struct esas2r_adapter *a, struct esas2r_flash_img *fi,
 			return complete_fmapi_req(a, rq, FI_STAT_SUCCESS);
 		}
 
-	/* fall through */
+		fallthrough;
 
 	case FI_ACT_UP: /* Upload the components */
 	default:
diff --git a/drivers/scsi/esas2r/esas2r_init.c b/drivers/scsi/esas2r/esas2r_init.c
index eb7d139ffc00..09c5c24bf391 100644
--- a/drivers/scsi/esas2r/esas2r_init.c
+++ b/drivers/scsi/esas2r/esas2r_init.c
@@ -1236,7 +1236,7 @@ static bool esas2r_format_init_msg(struct esas2r_adapter *a,
 			a->init_msg = ESAS2R_INIT_MSG_GET_INIT;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case ESAS2R_INIT_MSG_GET_INIT:
 		if (msg == ESAS2R_INIT_MSG_GET_INIT) {
@@ -1250,7 +1250,7 @@ static bool esas2r_format_init_msg(struct esas2r_adapter *a,
 				esas2r_hdebug("FAILED");
 			}
 		}
-		/* fall through */
+		fallthrough;
 
 	default:
 		rq->req_stat = RS_SUCCESS;
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 89afa31e33cb..43a1fd11df5e 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -307,7 +307,7 @@ static void esp_reset_esp(struct esp *esp)
 
 	case FASHME:
 		esp->config2 |= (ESP_CONFIG2_HME32 | ESP_CONFIG2_HMEFENAB);
-		/* fallthrough... */
+		fallthrough;
 
 	case FAS236:
 	case PCSCSI:
@@ -1741,7 +1741,7 @@ again:
 
 	case ESP_EVENT_DATA_IN:
 		write = 1;
-		/* fallthru */
+		fallthrough;
 
 	case ESP_EVENT_DATA_OUT: {
 		struct esp_cmd_entry *ent = esp->active_cmd;
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 1409c7687853..5ea426effa60 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -450,10 +450,10 @@ void fcoe_ctlr_link_up(struct fcoe_ctlr *fip)
 		switch (fip->mode) {
 		default:
 			LIBFCOE_FIP_DBG(fip, "invalid mode %d\n", fip->mode);
-			/* fall-through */
+			fallthrough;
 		case FIP_MODE_AUTO:
 			LIBFCOE_FIP_DBG(fip, "%s", "setting AUTO mode.\n");
-			/* fall-through */
+			fallthrough;
 		case FIP_MODE_FABRIC:
 		case FIP_MODE_NON_FIP:
 			mutex_unlock(&fip->ctlr_mutex);
@@ -773,7 +773,7 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 			fc_fcoe_set_mac(mac, fh->fh_d_id);
 			fip->update_mac(lport, mac);
 		}
-		/* fall through */
+		fallthrough;
 	case ELS_LS_RJT:
 		op = fr_encaps(fp);
 		if (op)
@@ -2439,7 +2439,7 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip,
 					  frport->enode_mac, 0);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case FIP_ST_VNMP_START:
 		LIBFCOE_FIP_DBG(fip, "vn_probe_req: "
 				"restart VN2VN negotiation\n");
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 2cc676e3df6a..29e4cdcade72 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -340,7 +340,7 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 			break;
 		case BOARD_DTC3181E:
 			hostdata->io_width = 2;	/* 16-bit PDMA */
-			/* fall through */
+			fallthrough;
 		case BOARD_NCR53C400A:
 		case BOARD_HP_C2502:
 			hostdata->c400_ctl_status = 9;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 11caa4b0d797..d9d21d23372e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1144,7 +1144,7 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func,
 			hisi_hba->hw->get_events(hisi_hba, phy_no);
 			break;
 		}
-		/* fallthru */
+		fallthrough;
 	case PHY_FUNC_RELEASE_SPINUP_HOLD:
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 91794a50b31f..48d5da59262b 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -4697,7 +4697,7 @@ static int fixup_ioaccel_cdb(u8 *cdb, int *cdb_len)
 	case WRITE_6:
 	case WRITE_12:
 		is_write = 1;
-		/* fall through */
+		fallthrough;
 	case READ_6:
 	case READ_12:
 		if (*cdb_len == 6) {
@@ -5147,7 +5147,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 	switch (cmd->cmnd[0]) {
 	case WRITE_6:
 		is_write = 1;
-		/* fall through */
+		fallthrough;
 	case READ_6:
 		first_block = (((cmd->cmnd[1] & 0x1F) << 16) |
 				(cmd->cmnd[2] << 8) |
@@ -5158,7 +5158,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		break;
 	case WRITE_10:
 		is_write = 1;
-		/* fall through */
+		fallthrough;
 	case READ_10:
 		first_block =
 			(((u64) cmd->cmnd[2]) << 24) |
@@ -5171,7 +5171,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		break;
 	case WRITE_12:
 		is_write = 1;
-		/* fall through */
+		fallthrough;
 	case READ_12:
 		first_block =
 			(((u64) cmd->cmnd[2]) << 24) |
@@ -5186,7 +5186,7 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		break;
 	case WRITE_16:
 		is_write = 1;
-		/* fall through */
+		fallthrough;
 	case READ_16:
 		first_block =
 			(((u64) cmd->cmnd[2]) << 56) |
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 77f4d37d5bd6..ea7c8930592d 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1866,7 +1866,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job)
 		port_id = (bsg_request->rqst_data.h_els.port_id[0] << 16) |
 			(bsg_request->rqst_data.h_els.port_id[1] << 8) |
 			bsg_request->rqst_data.h_els.port_id[2];
-		/* fall through */
+		fallthrough;
 	case FC_BSG_RPT_ELS:
 		fc_flags = IBMVFC_FC_ELS;
 		break;
@@ -1875,7 +1875,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job)
 		port_id = (bsg_request->rqst_data.h_ct.port_id[0] << 16) |
 			(bsg_request->rqst_data.h_ct.port_id[1] << 8) |
 			bsg_request->rqst_data.h_ct.port_id[2];
-		/* fall through */
+		fallthrough;
 	case FC_BSG_RPT_CT:
 		fc_flags = IBMVFC_FC_CT_IU;
 		break;
@@ -4122,7 +4122,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt)
 		return;
 	case IBMVFC_MAD_CRQ_ERROR:
 		ibmvfc_retry_host_init(vhost);
-		/* fall through */
+		fallthrough;
 	case IBMVFC_MAD_DRIVER_FAILED:
 		ibmvfc_free_event(evt);
 		return;
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index d9e94e81da01..cc3908c2d2f9 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -1581,7 +1581,7 @@ static long ibmvscsis_adapter_info(struct scsi_info *vscsi,
 	case H_PERMISSION:
 		if (connection_broken(vscsi))
 			flag_bits = (RESPONSE_Q_DOWN | CLIENT_FAILED);
-		/* Fall through */
+		fallthrough;
 	default:
 		dev_err(&vscsi->dev, "adapter_info: h_copy_rdma to client failed, rc %ld\n",
 			rc);
@@ -2489,10 +2489,10 @@ static long ibmvscsis_ping_response(struct scsi_info *vscsi)
 		break;
 	case H_CLOSED:
 		vscsi->flags |= CLIENT_FAILED;
-		/* Fall through */
+		fallthrough;
 	case H_DROPPED:
 		vscsi->flags |= RESPONSE_Q_DOWN;
-		/* Fall through */
+		fallthrough;
 	case H_REMOTE_PARM:
 		dev_err(&vscsi->dev, "ping_response: h_send_crq failed, rc %ld\n",
 			rc);
diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c
index 1459b1467027..862d35a098cf 100644
--- a/drivers/scsi/imm.c
+++ b/drivers/scsi/imm.c
@@ -801,7 +801,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 	case 1:		/* Phase 1 - Connected */
 		imm_connect(dev, CONNECT_EPP_MAYBE);
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 2:		/* Phase 2 - We are now talking to the scsi bus */
 		if (!imm_select(dev, scmd_id(cmd))) {
@@ -809,7 +809,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 			return 0;
 		}
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 3:		/* Phase 3 - Ready to accept a command */
 		w_ctr(ppb, 0x0c);
@@ -819,7 +819,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 		if (!imm_send_command(cmd))
 			return 0;
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 4:		/* Phase 4 - Setup scatter/gather buffers */
 		if (scsi_bufflen(cmd)) {
@@ -835,7 +835,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 		cmd->SCp.phase++;
 		if (cmd->SCp.this_residual & 0x01)
 			cmd->SCp.this_residual++;
-		/* fall through */
+		fallthrough;
 
 	case 5:		/* Phase 5 - Pre-Data transfer stage */
 		/* Spin lock for BUSY */
@@ -852,7 +852,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 			if (imm_negotiate(dev))
 				return 0;
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 6:		/* Phase 6 - Data transfer stage */
 		/* Spin lock for BUSY */
@@ -868,7 +868,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 				return 1;
 		}
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 7:		/* Phase 7 - Post data transfer stage */
 		if ((dev->dp) && (dev->rd)) {
@@ -880,7 +880,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 			}
 		}
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 8:		/* Phase 8 - Read status/message */
 		/* Check for data overrun */
diff --git a/drivers/scsi/isci/phy.c b/drivers/scsi/isci/phy.c
index 7f9b3f20e5e4..4cacb800b530 100644
--- a/drivers/scsi/isci/phy.c
+++ b/drivers/scsi/isci/phy.c
@@ -778,7 +778,7 @@ enum sci_status sci_phy_event_handler(struct isci_phy *iphy, u32 event_code)
 			break;
 		case SCU_EVENT_LINK_FAILURE:
 			scu_link_layer_set_txcomsas_timeout(iphy, SCU_SAS_LINK_LAYER_TXCOMSAS_NEGTIME_DEFAULT);
-			/* fall through */
+			fallthrough;
 		case SCU_EVENT_HARD_RESET_RECEIVED:
 			/* Start the oob/sn state machine over again */
 			sci_change_state(&iphy->sm, SCI_PHY_STARTING);
diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c
index cd1e4b4d95bb..c3f540b55689 100644
--- a/drivers/scsi/isci/remote_device.c
+++ b/drivers/scsi/isci/remote_device.c
@@ -310,7 +310,7 @@ static void isci_remote_device_not_ready(struct isci_host *ihost,
 		/* Kill all outstanding requests for the device. */
 		sci_remote_device_terminate_requests(idev);
 
-		/* Fall through - into the default case... */
+		fallthrough;	/* into the default case */
 	default:
 		clear_bit(IDEV_IO_READY, &idev->flags);
 		break;
@@ -593,7 +593,7 @@ enum sci_status sci_remote_device_event_handler(struct isci_remote_device *idev,
 
 			break;
 		}
-		/* fall through - and treat as unhandled... */
+		fallthrough;	/* and treat as unhandled */
 	default:
 		dev_dbg(scirdev_to_dev(idev),
 			"%s: device: %p event code: %x: %s\n",
diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c
index 474a43460963..68333f523b35 100644
--- a/drivers/scsi/isci/remote_node_context.c
+++ b/drivers/scsi/isci/remote_node_context.c
@@ -225,7 +225,7 @@ static void sci_remote_node_context_continue_state_transitions(struct sci_remote
 	case RNC_DEST_READY:
 	case RNC_DEST_SUSPENDED_RESUME:
 		rnc->destination_state = RNC_DEST_READY;
-		/* Fall through... */
+		fallthrough;
 	case RNC_DEST_FINAL:
 		sci_remote_node_context_resume(rnc, rnc->user_callback,
 					       rnc->user_cookie);
@@ -601,9 +601,9 @@ enum sci_status sci_remote_node_context_suspend(
 				 __func__, sci_rnc);
 			return SCI_FAILURE_INVALID_STATE;
 		}
-		/* Fall through - and handle like SCI_RNC_POSTING */
+		fallthrough;	/* and handle like SCI_RNC_POSTING */
 	case SCI_RNC_RESUMING:
-		/* Fall through - and handle like SCI_RNC_POSTING */
+		fallthrough;	/* and handle like SCI_RNC_POSTING */
 	case SCI_RNC_POSTING:
 		/* Set the destination state to AWAIT - this signals the
 		 * entry into the SCI_RNC_READY state that a suspension
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 6561a07db189..6e0817941fa7 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -894,7 +894,7 @@ sci_io_request_terminate(struct isci_request *ireq)
 		 * and don't wait for the task response.
 		 */
 		sci_change_state(&ireq->sm, SCI_REQ_ABORTING);
-		/* Fall through - and handle like ABORTING... */
+		fallthrough;	/* and handle like ABORTING */
 	case SCI_REQ_ABORTING:
 		if (!isci_remote_device_is_safe_to_abort(ireq->target_device))
 			set_bit(IREQ_PENDING_ABORT, &ireq->flags);
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index d8cbc9c0e766..e67abb184a8a 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -634,8 +634,6 @@ free_fp:
 	fc_frame_free(fp);
 out:
 	kref_put(&rdata->kref, fc_rport_destroy);
-	if (!IS_ERR(fp))
-		fc_frame_free(fp);
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 16eb3b60ed58..96a2952cf626 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -2108,7 +2108,7 @@ static void fc_exch_rrq_resp(struct fc_seq *sp, struct fc_frame *fp, void *arg)
 	switch (op) {
 	case ELS_LS_RJT:
 		FC_EXCH_DBG(aborted_ep, "LS_RJT for RRQ\n");
-		/* fall through */
+		fallthrough;
 	case ELS_LS_ACC:
 		goto cleanup;
 	default:
@@ -2622,7 +2622,7 @@ void fc_exch_recv(struct fc_lport *lport, struct fc_frame *fp)
 	case FC_EOF_T:
 		if (f_ctl & FC_FC_END_SEQ)
 			skb_trim(fp_skb(fp), fr_len(fp) - FC_FC_FILL(f_ctl));
-		/* fall through */
+		fallthrough;
 	case FC_EOF_N:
 		if (fh->fh_type == FC_TYPE_BLS)
 			fc_exch_recv_bls(ema->mp, fp);
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index e11d4f002bd4..7cfeb6886237 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -752,7 +752,7 @@ static void fc_fcp_abts_resp(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		brp = fc_frame_payload_get(fp, sizeof(*brp));
 		if (brp && brp->br_reason == FC_BA_RJT_LOG_ERR)
 			break;
-		/* fall thru */
+		fallthrough;
 	default:
 		/*
 		 * we will let the command timeout
@@ -1536,7 +1536,7 @@ static void fc_fcp_rec_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 				   "device %x invalid REC reject %d/%d\n",
 				   fsp->rport->port_id, rjt->er_reason,
 				   rjt->er_explan);
-			/* fall through */
+			fallthrough;
 		case ELS_RJT_UNSUP:
 			FC_FCP_DBG(fsp, "device does not support REC\n");
 			rpriv = fsp->rport->dd_data;
@@ -1668,7 +1668,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		FC_FCP_DBG(fsp, "REC %p fid %6.6x error unexpected error %d\n",
 			   fsp, fsp->rport->port_id, error);
 		fsp->status_code = FC_CMD_PLOGO;
-		/* fall through */
+		fallthrough;
 
 	case -FC_EX_TIMEOUT:
 		/*
@@ -1830,7 +1830,7 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		break;
 	case -FC_EX_CLOSED:			/* e.g., link failure */
 		FC_FCP_DBG(fsp, "SRR error, exchange closed\n");
-		/* fall through */
+		fallthrough;
 	default:
 		fc_fcp_retry_cmd(fsp, FC_ERROR);
 		break;
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index b84dbc316df1..6557fda85c5c 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -1578,7 +1578,7 @@ static void fc_lport_timeout(struct work_struct *work)
 	case LPORT_ST_DPRT:
 		FC_LPORT_DBG(lport, "Skipping lport state %s to SCR\n",
 			     fc_lport_state(lport));
-		/* fall thru */
+		fallthrough;
 	case LPORT_ST_SCR:
 		fc_lport_enter_scr(lport);
 		break;
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 18663a82865f..a60b228d13f1 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1723,7 +1723,7 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 			kref_put(&rdata->kref, fc_rport_destroy);
 			goto busy;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		FC_RPORT_DBG(rdata,
 			     "Reject ELS 0x%02x while in state %s\n",
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 49c8a1818baf..1e9c3171fa9f 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -248,7 +248,7 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode)
 		hdr_lun = scsilun_to_int(&tmf->lun);
 		if (hdr_lun != task->sc->device->lun)
 			return 0;
-		/* fall through */
+		fallthrough;
 	case ISCSI_TM_FUNC_TARGET_WARM_RESET:
 		/*
 		 * Fail all SCSI cmd PDUs
@@ -1674,7 +1674,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 				sc->result = DID_NO_CONNECT << 16;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case ISCSI_STATE_IN_RECOVERY:
 			reason = FAILURE_SESSION_IN_RECOVERY;
 			sc->result = DID_IMM_RETRY << 16;
@@ -2239,7 +2239,7 @@ int iscsi_eh_abort(struct scsi_cmnd *sc)
 					      "progress\n");
 			goto success;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		conn->tmf_state = TMF_INITIAL;
 		goto failed;
diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c
index 6ef93c7af954..37e5d4e48c2f 100644
--- a/drivers/scsi/libiscsi_tcp.c
+++ b/drivers/scsi/libiscsi_tcp.c
@@ -772,7 +772,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
 			iscsi_tcp_data_recv_prep(tcp_conn);
 			return 0;
 		}
-	/* fall through */
+		fallthrough;
 	case ISCSI_OP_LOGOUT_RSP:
 	case ISCSI_OP_NOOP_IN:
 	case ISCSI_OP_SCSI_TMFUNC_RSP:
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 1b93332daa6b..a4887985aad6 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -209,7 +209,10 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		task->num_scatter = si;
 	}
 
-	task->data_dir = qc->dma_dir;
+	if (qc->tf.protocol == ATA_PROT_NODATA)
+		task->data_dir = DMA_NONE;
+	else
+		task->data_dir = qc->dma_dir;
 	task->scatter = qc->sg;
 	task->ata_task.retry_count = 1;
 	task->task_state_flags = SAS_TASK_STATE_PENDING;
@@ -324,7 +327,7 @@ static int smp_ata_check_ready(struct ata_link *link)
 	case SAS_END_DEVICE:
 		if (ex_phy->attached_sata_dev)
 			return sas_ata_clear_pending(dev, ex_phy);
-		/* fall through */
+		fallthrough;
 	default:
 		return -ENODEV;
 	}
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index daf951b0b3f5..cd7c7d269f6f 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -108,7 +108,7 @@ static int sas_get_port_device(struct asd_sas_port *port)
 			rphy = NULL;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case SAS_END_DEVICE:
 		rphy = sas_end_device_alloc(port->port);
 		break;
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index b7d1b1ea185d..8d6bcc19359f 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -1096,7 +1096,7 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id)
 		} else
 			memcpy(dev->port->disc.fanout_sas_addr,
 			       ex_phy->attached_sas_addr, SAS_ADDR_SIZE);
-		/* fallthrough */
+		fallthrough;
 	case SAS_EDGE_EXPANDER_DEVICE:
 		child = sas_ex_discover_expander(dev, phy_id);
 		break;
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 9e0975e55c27..1bf939818c98 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -622,7 +622,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 				sas_scsi_clear_queue_lu(work_q, cmd);
 				goto Again;
 			}
-			/* fallthrough */
+			fallthrough;
 		case TASK_IS_NOT_AT_LU:
 		case TASK_ABORT_FAILED:
 			pr_notice("task 0x%p is not at LU: I_T recover\n",
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index ef2015fad2d5..d0141a23a833 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -3202,7 +3202,7 @@ port_out:
 	case SLI_MGMT_GHAT:
 	case SLI_MGMT_GRPL:
 		rsp_size = FC_MAX_NS_RSP;
-		/* fall through */
+		fallthrough;
 	case SLI_MGMT_DHBA:
 	case SLI_MGMT_DHAT:
 		pe = (struct lpfc_fdmi_port_entry *)&CtReq->un.PortID;
@@ -3215,7 +3215,7 @@ port_out:
 	case SLI_MGMT_GPAT:
 	case SLI_MGMT_GPAS:
 		rsp_size = FC_MAX_NS_RSP;
-		/* fall through */
+		fallthrough;
 	case SLI_MGMT_DPRT:
 	case SLI_MGMT_DPA:
 		pe = (struct lpfc_fdmi_port_entry *)&CtReq->un.PortID;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 48dc63f22cca..b60945182db8 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3517,6 +3517,9 @@ lpfc_issue_els_rdf(struct lpfc_vport *vport, uint8_t retry)
 				FC_TLV_DESC_LENGTH_FROM_SZ(prdf->reg_d1));
 	prdf->reg_d1.reg_desc.count = cpu_to_be32(ELS_RDF_REG_TAG_CNT);
 	prdf->reg_d1.desc_tags[0] = cpu_to_be32(ELS_DTAG_LNK_INTEGRITY);
+	prdf->reg_d1.desc_tags[1] = cpu_to_be32(ELS_DTAG_DELIVERY);
+	prdf->reg_d1.desc_tags[2] = cpu_to_be32(ELS_DTAG_PEER_CONGEST);
+	prdf->reg_d1.desc_tags[3] = cpu_to_be32(ELS_DTAG_CONGESTION);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 			      "Issue RDF:       did:x%x",
@@ -4656,7 +4659,9 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 out:
 	if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) {
 		spin_lock_irq(shost->host_lock);
-		ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI);
+		if (mbox)
+			ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
+		ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI;
 		spin_unlock_irq(shost->host_lock);
 
 		/* If the node is not being used by another discovery thread,
@@ -9134,7 +9139,7 @@ lpfc_cmpl_reg_new_vport(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				lpfc_nlp_put(ndlp);
 				return;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			/* Try to recover from this error */
 			if (phba->sli_rev == LPFC_SLI_REV4)
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 142a02114479..d32c7e7ab09d 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -4728,15 +4728,14 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 		case CMD_GEN_REQUEST64_CR:
 			if (iocb->context_un.ndlp == ndlp)
 				return 1;
-			/* fall through */
+			fallthrough;
 		case CMD_ELS_REQUEST64_CR:
 			if (icmd->un.elsreq64.remoteID == ndlp->nlp_DID)
 				return 1;
-			/* fall through */
+			fallthrough;
 		case CMD_XMIT_ELS_RSP64_CX:
 			if (iocb->context1 == (uint8_t *) ndlp)
 				return 1;
-			/* fall through */
 		}
 	} else if (pring->ringno == LPFC_FCP_RING) {
 		/* Skip match check if waiting to relogin to FCP target */
@@ -6055,7 +6054,7 @@ restart_disc:
 
 	case LPFC_LINK_UP:
 		lpfc_issue_clear_la(phba, vport);
-		/* fall through */
+		fallthrough;
 	case LPFC_LINK_UNKNOWN:
 	case LPFC_WARM_START:
 	case LPFC_INIT_START:
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index c4ba8273a63f..12e4e76233e6 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -4800,7 +4800,7 @@ struct send_frame_wqe {
 	uint32_t fc_hdr_wd5;           /* word 15 */
 };
 
-#define ELS_RDF_REG_TAG_CNT		1
+#define ELS_RDF_REG_TAG_CNT		4
 struct lpfc_els_rdf_reg_desc {
 	struct fc_df_desc_fpin_reg	reg_desc;	/* descriptor header */
 	__be32				desc_tags[ELS_RDF_REG_TAG_CNT];
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index c69725999315..ca25e54bb782 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -11376,7 +11376,6 @@ lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl)
 {
 	cpumask_clear(&eqhdl->aff_mask);
 	irq_clear_status_flags(eqhdl->irq, IRQ_NO_BALANCING);
-	irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask);
 }
 
 /**
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index cad53d19cb25..92d6e7b98770 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -464,7 +464,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	case  NLP_STE_NPR_NODE:
 		if (!(ndlp->nlp_flag & NLP_NPR_ADISC))
 			break;
-		/* fall through */
+		fallthrough;
 	case  NLP_STE_REG_LOGIN_ISSUE:
 	case  NLP_STE_PRLI_ISSUE:
 	case  NLP_STE_UNMAPPED_NODE:
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index e5be334d6a11..0c39ed50998c 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1225,7 +1225,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 					 lpfc_ncmd, nCmd,
 					 lpfc_ncmd->cur_iocbq.sli4_xritag,
 					 bf_get(lpfc_wcqe_c_xb, wcqe));
-			/* fall through */
+			fallthrough;
 		default:
 out_err:
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 5e802c8b22a9..983eeb0e3d07 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1093,7 +1093,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			case SCSI_PROT_WRITE_INSERT:
 				/*
 				 * For WRITE_INSERT, force the error
@@ -1213,7 +1213,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 					rc = BG_ERR_TGT | BG_ERR_CHECK;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			case SCSI_PROT_WRITE_INSERT:
 				/*
 				 * For WRITE_INSERT, force the
@@ -1295,7 +1295,7 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 			switch (op) {
 			case SCSI_PROT_WRITE_PASS:
 				rc = BG_ERR_CHECK;
-				/* fall through */
+				fallthrough;
 
 			case SCSI_PROT_WRITE_INSERT:
 				/*
@@ -3980,7 +3980,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 					lpfc_cmd->cur_iocbq.sli4_lxritag,
 					0, 0);
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			cmd->result = DID_ERROR << 16;
 			break;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 4cd7ded656b7..e158cd77d387 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -9339,7 +9339,7 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 			 */
 			if (piocb->iocb_cmpl)
 				piocb->iocb_cmpl = NULL;
-			/*FALLTHROUGH*/
+			fallthrough;
 		case CMD_CREATE_XRI_CR:
 		case CMD_CLOSE_XRI_CN:
 		case CMD_CLOSE_XRI_CX:
@@ -9653,7 +9653,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		cmnd = CMD_XMIT_SEQUENCE64_CR;
 		if (phba->link_flag & LS_LOOPBACK_MODE)
 			bf_set(wqe_xo, &wqe->xmit_sequence.wge_ctl, 1);
-		/* fall through */
+		fallthrough;
 	case CMD_XMIT_SEQUENCE64_CR:
 		/* word3 iocb=io_tag32 wqe=reserved */
 		wqe->xmit_sequence.rsvd3 = 0;
@@ -13630,7 +13630,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 				"2537 Receive Frame Truncated!!\n");
-		/* fall through */
+		fallthrough;
 	case FC_STATUS_RQ_SUCCESS:
 		spin_lock_irqsave(&phba->hbalock, iflags);
 		lpfc_sli4_rq_release(hrq, drq);
@@ -13678,7 +13678,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 					atomic_read(&tgtp->rcv_fcp_cmd_out),
 					atomic_read(&tgtp->xmt_fcp_release));
 		}
-		/* fallthrough */
+		fallthrough;
 
 	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
@@ -14162,7 +14162,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 				"6126 Receive Frame Truncated!!\n");
-		/* fall through */
+		fallthrough;
 	case FC_STATUS_RQ_SUCCESS:
 		spin_lock_irqsave(&phba->hbalock, iflags);
 		lpfc_sli4_rq_release(hrq, drq);
@@ -14209,7 +14209,7 @@ drop:
 					atomic_read(&tgtp->rcv_fcp_cmd_out),
 					atomic_read(&tgtp->xmt_fcp_release));
 		}
-		/* fallthrough */
+		fallthrough;
 
 	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
@@ -15096,7 +15096,7 @@ lpfc_eq_create(struct lpfc_hba *phba, struct lpfc_queue *eq, uint32_t imax)
 			status = -EINVAL;
 			goto out;
 		}
-		/* fall through - otherwise default to smallest count */
+		fallthrough;	/* otherwise default to smallest count */
 	case 256:
 		bf_set(lpfc_eq_context_count, &eq_create->u.request.context,
 		       LPFC_EQ_CNT_256);
@@ -15238,7 +15238,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			       LPFC_CQ_CNT_WORD7);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 				"0361 Unsupported CQ count: "
@@ -15249,7 +15249,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			status = -EINVAL;
 			goto out;
 		}
-		/* fall through - otherwise default to smallest count */
+		fallthrough;	/* otherwise default to smallest count */
 	case 256:
 		bf_set(lpfc_cq_context_count, &cq_create->u.request.context,
 		       LPFC_CQ_CNT_256);
@@ -15417,7 +15417,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
 					       LPFC_CQ_CNT_WORD7);
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 						"3118 Bad CQ count. (%d)\n",
@@ -15426,7 +15426,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
 					status = -EINVAL;
 					goto out;
 				}
-				/* fall through - otherwise default to smallest */
+				fallthrough;	/* otherwise default to smallest */
 			case 256:
 				bf_set(lpfc_mbx_cq_create_set_cqe_cnt,
 				       &cq_set->u.request, LPFC_CQ_CNT_256);
@@ -15702,7 +15702,7 @@ lpfc_mq_create(struct lpfc_hba *phba, struct lpfc_queue *mq,
 			status = -EINVAL;
 			goto out;
 		}
-		/* fall through - otherwise default to smallest count */
+		fallthrough;	/* otherwise default to smallest count */
 	case 16:
 		bf_set(lpfc_mq_context_ring_size,
 		       &mq_create_ext->u.request.context,
@@ -16123,7 +16123,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 				status = -EINVAL;
 				goto out;
 			}
-			/* fall through - otherwise default to smallest count */
+			fallthrough;	/* otherwise default to smallest count */
 		case 512:
 			bf_set(lpfc_rq_context_rqe_count,
 			       &rq_create->u.request.context,
@@ -16260,7 +16260,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 				status = -EINVAL;
 				goto out;
 			}
-			/* fall through - otherwise default to smallest count */
+			fallthrough;	/* otherwise default to smallest count */
 		case 512:
 			bf_set(lpfc_rq_context_rqe_count,
 			       &rq_create->u.request.context,
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 20adec4387f0..c657abf22b75 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.8.0.3"
+#define LPFC_DRIVER_VERSION "12.8.0.4"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 0484ee52ae80..ac406049e7c8 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -491,9 +491,9 @@ mega_get_ldrv_num(adapter_t *adapter, struct scsi_cmnd *cmd, int channel)
 
 	if (adapter->support_random_del && adapter->read_ldidmap )
 		switch (cmd->cmnd[0]) {
-		case READ_6:	/* fall through */
-		case WRITE_6:	/* fall through */
-		case READ_10:	/* fall through */
+		case READ_6:
+		case WRITE_6:
+		case READ_10:
 		case WRITE_10:
 			ldrv_num += 0x80;
 		}
@@ -852,7 +852,7 @@ mega_build_cmd(adapter_t *adapter, struct scsi_cmnd *cmd, int *busy)
 			return scb;
 
 #if MEGA_HAVE_CLUSTERING
-		case RESERVE:	/* Fall through */
+		case RESERVE:
 		case RELEASE:
 
 			/*
@@ -987,7 +987,7 @@ mega_prepare_passthru(adapter_t *adapter, scb_t *scb, struct scsi_cmnd *cmd,
 
 			adapter->flag |= (1L << cmd->device->channel);
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		pthru->numsgelements = mega_build_sglist(adapter, scb,
 				&pthru->dataxferaddr, &pthru->dataxferlen);
@@ -1050,7 +1050,7 @@ mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb,
 
 			adapter->flag |= (1L << cmd->device->channel);
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		epthru->numsgelements = mega_build_sglist(adapter, scb,
 				&epthru->dataxferaddr, &epthru->dataxferlen);
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index 19469a2c0ea3..4a27ac869f2e 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -1581,7 +1581,7 @@ megaraid_mbox_build_cmd(adapter_t *adapter, struct scsi_cmnd *scp, int *busy)
 				return NULL;
 			}
 
-			/* Fall through */
+			fallthrough;
 
 		case READ_CAPACITY:
 			/*
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 861f7140f52e..2b7e7b5f38ed 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -3522,7 +3522,7 @@ megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd,
 			megasas_complete_int_cmd(instance, cmd);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case MFI_CMD_LD_READ:
 	case MFI_CMD_LD_WRITE:
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 0824410f78f8..b0c01cf0428f 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -3534,7 +3534,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex,
 				atomic_dec(&lbinfo->scsi_pending_cmds[cmd_fusion->pd_r1_lb]);
 				cmd_fusion->scmd->SCp.Status &= ~MEGASAS_LOAD_BALANCE_FLAG;
 			}
-			/* Fall through - and complete IO */
+			fallthrough;	/* and complete IO */
 		case MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST: /* LD-IO Path */
 			atomic_dec(&instance->fw_outstanding);
 			if (cmd_fusion->r1_alt_dev_handle == MR_DEVHANDLE_INVALID) {
@@ -3689,7 +3689,7 @@ int megasas_irqpoll(struct irq_poll *irqpoll, int budget)
 	instance = irq_ctx->instance;
 
 	if (irq_ctx->irq_line_enable) {
-		disable_irq(irq_ctx->os_irq);
+		disable_irq_nosync(irq_ctx->os_irq);
 		irq_ctx->irq_line_enable = false;
 	}
 
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index fd1d03064079..0a9f4e44ab2c 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -1457,7 +1457,7 @@ static void cmd_complete(struct mesh_state *ms)
 		/* huh?  we expected a phase mismatch */
 		ms->n_msgin = 0;
 		ms->msgphase = msg_in;
-		/* fall through */
+		fallthrough;
 
 	case msg_in:
 		/* should have some message bytes in fifo */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 1d64524cd863..8062bd99add8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1733,7 +1733,7 @@ _base_irqpoll(struct irq_poll *irqpoll, int budget)
 	reply_q = container_of(irqpoll, struct adapter_reply_queue,
 			irqpoll);
 	if (reply_q->irq_line_enable) {
-		disable_irq(reply_q->os_irq);
+		disable_irq_nosync(reply_q->os_irq);
 		reply_q->irq_line_enable = false;
 	}
 	num_entries = _base_process_reply_queue(reply_q);
@@ -4681,7 +4681,7 @@ _base_update_ioc_page1_inlinewith_perf_mode(struct MPT3SAS_ADAPTER *ioc)
 			ioc_info(ioc, "performance mode: balanced\n");
 			return;
 		}
-		/* Fall through */
+		fallthrough;
 	case MPT_PERF_MODE_LATENCY:
 		/*
 		 * Enable interrupt coalescing on all reply queues
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 43260306668c..7c119b904834 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -1002,7 +1002,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		}
 		/* drop to default case for posting the request */
 	}
-		/* fall through */
+		fallthrough;
 	default:
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 08fc4b381056..2e2756d8a49b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -5470,7 +5470,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 
 	case MPI2_IOCSTATUS_SCSI_DATA_OVERRUN:
 		scsi_set_resid(scmd, 0);
-		/* fall through */
+		fallthrough;
 	case MPI2_IOCSTATUS_SCSI_RECOVERED_ERROR:
 	case MPI2_IOCSTATUS_SUCCESS:
 		scmd->result = (DID_OK << 16) | scsi_status;
@@ -6480,7 +6480,7 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			if (!test_bit(handle, ioc->pend_os_device_add))
 				break;
 
-			/* fall through */
+			fallthrough;
 
 		case MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED:
 
@@ -7208,7 +7208,7 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			event_data->PortEntry[i].PortStatus &= 0xF0;
 			event_data->PortEntry[i].PortStatus |=
 				MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED;
-			/* fall through */
+			fallthrough;
 		case MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED:
 			if (ioc->shost_recovery)
 				break;
@@ -10653,7 +10653,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		case MPI26_MFGPAGE_DEVID_CFG_SEC_3916:
 			dev_info(&pdev->dev,
 			    "HBA is in Configurable Secure mode\n");
-			/* fall through */
+			fallthrough;
 		case MPI26_MFGPAGE_DEVID_HARD_SEC_3816:
 		case MPI26_MFGPAGE_DEVID_HARD_SEC_3916:
 			ioc->is_aero_ioc = ioc->is_gen35_ioc = 1;
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index d4bd31a75b9d..b2869c5dd7fb 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -650,7 +650,7 @@ static void myrb_bgi_control(struct myrb_hba *cb)
 		if (sdev && cb->bgi_status.status == MYRB_BGI_INPROGRESS)
 			sdev_printk(KERN_INFO, sdev,
 				    "Background Initialization Aborted\n");
-		/* Fallthrough */
+		fallthrough;
 	case MYRB_STATUS_NO_BGI_INPROGRESS:
 		cb->bgi_status.status = MYRB_BGI_INVALID;
 		break;
@@ -1528,7 +1528,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost,
 			scmd->scsi_done(scmd);
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	case WRITE_6:
 		lba = (((scmd->cmnd[1] & 0x1F) << 16) |
 		       (scmd->cmnd[2] << 8) |
@@ -1545,7 +1545,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost,
 			scmd->scsi_done(scmd);
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	case WRITE_10:
 	case VERIFY:		/* 0x2F */
 	case WRITE_VERIFY:	/* 0x2E */
@@ -1562,7 +1562,7 @@ static int myrb_ldev_queuecommand(struct Scsi_Host *shost,
 			scmd->scsi_done(scmd);
 			return 0;
 		}
-		/* fall through */
+		fallthrough;
 	case WRITE_12:
 	case VERIFY_12: /* 0xAF */
 	case WRITE_VERIFY_12:	/* 0xAE */
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index f88adab3f913..03d70138ad58 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -3640,7 +3640,7 @@ ncr_script_copy_and_bind (struct ncb *np, ncrcmd *src, ncrcmd *dst, int len)
 						new = old;
 						break;
 					}
-					/* fall through */
+					fallthrough;
 				default:
 					panic("ncr_script_copy_and_bind: weird relocation %x\n", old);
 					break;
@@ -3910,14 +3910,14 @@ static void __init ncr_prepare_setting(struct ncb *np)
 					np->scsi_mode = SMODE_HVD;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case 3:	/* SYMBIOS controllers report HVD through GPIO3 */
 			if (INB(nc_gpreg) & 0x08)
 				break;
-			/* fall through */
+			fallthrough;
 		case 2:	/* Set HVD unconditionally */
 			np->scsi_mode = SMODE_HVD;
-			/* fall through */
+			fallthrough;
 		case 1:	/* Trust previous settings for HVD */
 			if (np->sv_stest2 & 0x20)
 				np->scsi_mode = SMODE_HVD;
@@ -4296,7 +4296,7 @@ static int ncr_queue_command (struct ncb *np, struct scsi_cmnd *cmd)
 			break;
 		cp->phys.header.wgoalp	= cpu_to_scr(goalp);
 		cp->phys.header.wlastp	= cpu_to_scr(lastp);
-		/* fall through */
+		fallthrough;
 	case DMA_FROM_DEVICE:
 		goalp = NCB_SCRIPT_PHYS (np, data_in2) + 8;
 		if (segments <= MAX_SCATTERL)
@@ -6717,7 +6717,7 @@ void ncr_int_sir (struct ncb *np)
 			OUTL_DSP (scr_to_cpu(tp->lp[0]->jump_ccb[0]));
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	case SIR_RESEL_BAD_TARGET:	/* Will send a TARGET RESET message */
 	case SIR_RESEL_BAD_LUN:		/* Will send a TARGET RESET message */
 	case SIR_RESEL_BAD_I_T_L_Q:	/* Will send an ABORT TAG message   */
@@ -6825,7 +6825,7 @@ void ncr_int_sir (struct ncb *np)
 		*/
 		OUTB (HS_PRT, HS_BUSY);
 
-		/* fall through */
+		fallthrough;
 
 	case SIR_NEGO_PROTO:
 		/*-------------------------------------------------------
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index 8655ff1249bb..bc5a623519e7 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -1113,7 +1113,7 @@ static irqreturn_t nspintr(int irq, void *dev_id)
 			nsp_scsi_done(tmpSC);
 			return IRQ_HANDLED;
 		}
-		/* fall thru */
+		fallthrough;
 	default:
 		if ((irq_status & (IRQSTATUS_SCSI | IRQSTATUS_FIFO)) == 0) {
 			return IRQ_HANDLED;
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 337e79d6837f..9889bab7d31c 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -818,7 +818,7 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha,
 
 		res = pm8001_tag_alloc(pm8001_ha, &ccb_tag);
 		if (res)
-			return res;
+			goto ex_err;
 		ccb = &pm8001_ha->ccb_info[ccb_tag];
 		ccb->device = pm8001_dev;
 		ccb->ccb_tag = ccb_tag;
diff --git a/drivers/scsi/ppa.c b/drivers/scsi/ppa.c
index 0ae800c5b739..aa41f7ac91cb 100644
--- a/drivers/scsi/ppa.c
+++ b/drivers/scsi/ppa.c
@@ -717,7 +717,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
 			}
 			cmd->SCp.phase++;
 		}
-		/* fall through */
+		fallthrough;
 
 	case 2:		/* Phase 2 - We are now talking to the scsi bus */
 		if (!ppa_select(dev, scmd_id(cmd))) {
@@ -725,7 +725,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
 			return 0;
 		}
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 3:		/* Phase 3 - Ready to accept a command */
 		w_ctr(ppb, 0x0c);
@@ -735,7 +735,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
 		if (!ppa_send_command(cmd))
 			return 0;
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 4:		/* Phase 4 - Setup scatter/gather buffers */
 		if (scsi_bufflen(cmd)) {
@@ -749,7 +749,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
 		}
 		cmd->SCp.buffers_residual = scsi_sg_count(cmd) - 1;
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 5:		/* Phase 5 - Data transfer stage */
 		w_ctr(ppb, 0x0c);
@@ -762,7 +762,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
 		if (retv == 0)
 			return 1;
 		cmd->SCp.phase++;
-		/* fall through */
+		fallthrough;
 
 	case 6:		/* Phase 6 - Read status/message */
 		cmd->result = DID_OK << 16;
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 3f04f2c81366..5ca424df355c 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -3863,7 +3863,7 @@ void qedf_stag_change_work(struct work_struct *work)
 	    container_of(work, struct qedf_ctx, stag_work.work);
 
 	if (!qedf) {
-		QEDF_ERR(&qedf->dbg_ctx, "qedf is NULL");
+		QEDF_ERR(NULL, "qedf is NULL");
 		return;
 	}
 	QEDF_ERR(&qedf->dbg_ctx, "Performing software context reset.\n");
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index 91eb6901815c..e1d7de63e8f8 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -380,5 +380,8 @@ extern int qla24xx_soft_reset(struct qla_hw_data *);
 static inline int
 ql_mask_match(uint level)
 {
+	if (ql2xextended_error_logging == 1)
+		ql2xextended_error_logging = QL_DBG_DEFAULT1_MASK;
+
 	return (level & ql2xextended_error_logging) == level;
 }
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 8c92af5e4390..a165120d2976 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1626,7 +1626,7 @@ typedef struct {
 	 */
 	uint8_t	 firmware_options[2];
 
-	uint16_t frame_payload_size;
+	__le16	frame_payload_size;
 	__le16	max_iocb_allocation;
 	__le16	execution_throttle;
 	uint8_t	 retry_count;
@@ -3880,6 +3880,7 @@ struct qla_hw_data {
 		uint32_t	scm_supported_f:1;
 				/* Enabled in Driver */
 		uint32_t	scm_enabled:1;
+		uint32_t	max_req_queue_warned:1;
 	} flags;
 
 	uint16_t max_exchg;
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index df670fba2ab8..b569fd6e96d6 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -177,7 +177,7 @@ qla2x00_chk_ms_status(scsi_qla_host_t *vha, ms_iocb_entry_t *ms_pkt,
 			break;
 		case CS_TIMEOUT:
 			rval = QLA_FUNCTION_TIMEOUT;
-			/* fall through */
+			fallthrough;
 		default:
 			ql_dbg(ql_dbg_disc, vha, 0x2033,
 			    "%s failed, completion status (%x) on port_id: "
@@ -1505,11 +1505,11 @@ qla2x00_prep_ct_fdmi_req(struct ct_sns_pkt *p, uint16_t cmd,
 static uint
 qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha)
 {
+	uint speeds = 0;
+
 	if (IS_CNA_CAPABLE(ha))
 		return FDMI_PORT_SPEED_10GB;
 	if (IS_QLA28XX(ha) || IS_QLA27XX(ha)) {
-		uint speeds = 0;
-
 		if (ha->max_supported_speed == 2) {
 			if (ha->min_supported_speed <= 6)
 				speeds |= FDMI_PORT_SPEED_64GB;
@@ -1536,9 +1536,16 @@ qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha)
 		}
 		return speeds;
 	}
-	if (IS_QLA2031(ha))
-		return FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB|
-			FDMI_PORT_SPEED_4GB;
+	if (IS_QLA2031(ha)) {
+		if ((ha->pdev->subsystem_vendor == 0x103C) &&
+		    (ha->pdev->subsystem_device == 0x8002)) {
+			speeds = FDMI_PORT_SPEED_16GB;
+		} else {
+			speeds = FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB|
+				FDMI_PORT_SPEED_4GB;
+		}
+		return speeds;
+	}
 	if (IS_QLA25XX(ha))
 		return FDMI_PORT_SPEED_8GB|FDMI_PORT_SPEED_4GB|
 			FDMI_PORT_SPEED_2GB|FDMI_PORT_SPEED_1GB;
@@ -3436,7 +3443,6 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 			list_for_each_entry(fcport, &vha->vp_fcports, list) {
 				if ((fcport->flags & FCF_FABRIC_DEVICE) != 0) {
 					fcport->scan_state = QLA_FCPORT_SCAN;
-					fcport->logout_on_delete = 0;
 				}
 			}
 			goto login_logout;
@@ -3532,10 +3538,22 @@ login_logout:
 		}
 
 		if (fcport->scan_state != QLA_FCPORT_FOUND) {
+			bool do_delete = false;
+
+			if (fcport->scan_needed &&
+			    fcport->disc_state == DSC_LOGIN_PEND) {
+				/* Cable got disconnected after we sent
+				 * a login. Do delete to prevent timeout.
+				 */
+				fcport->logout_on_delete = 1;
+				do_delete = true;
+			}
+
 			fcport->scan_needed = 0;
-			if ((qla_dual_mode_enabled(vha) ||
-				qla_ini_mode_enabled(vha)) &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
+			if (((qla_dual_mode_enabled(vha) ||
+			      qla_ini_mode_enabled(vha)) &&
+			    atomic_read(&fcport->state) == FCS_ONLINE) ||
+				do_delete) {
 				if (fcport->loop_id != FC_NO_LOOP_ID) {
 					if (fcport->flags & FCF_FCP2_DEVICE)
 						fcport->logout_on_delete = 0;
@@ -3736,6 +3754,18 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res)
 		unsigned long flags;
 		const char *name = sp->name;
 
+		if (res == QLA_OS_TIMER_EXPIRED) {
+			/* switch is ignoring all commands.
+			 * This might be a zone disable behavior.
+			 * This means we hit 64s timeout.
+			 * 22s GPNFT + 44s Abort = 64s
+			 */
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			       "%s: Switch Zone check please .\n",
+			       name);
+			qla2x00_mark_all_devices_lost(vha);
+		}
+
 		/*
 		 * We are in an Interrupt context, queue up this
 		 * sp for GNNFT_DONE work. This will allow all
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 57a2d76aa691..0bd04a62af83 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -857,7 +857,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 					    fcport);
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				if (fcport_is_smaller(fcport)) {
 					/* local adapter is bigger */
@@ -4603,18 +4603,18 @@ qla2x00_nvram_config(scsi_qla_host_t *vha)
 			nv->firmware_options[1] = BIT_7 | BIT_5;
 			nv->add_firmware_options[0] = BIT_5;
 			nv->add_firmware_options[1] = BIT_5 | BIT_4;
-			nv->frame_payload_size = 2048;
+			nv->frame_payload_size = cpu_to_le16(2048);
 			nv->special_options[1] = BIT_7;
 		} else if (IS_QLA2200(ha)) {
 			nv->firmware_options[0] = BIT_2 | BIT_1;
 			nv->firmware_options[1] = BIT_7 | BIT_5;
 			nv->add_firmware_options[0] = BIT_5;
 			nv->add_firmware_options[1] = BIT_5 | BIT_4;
-			nv->frame_payload_size = 1024;
+			nv->frame_payload_size = cpu_to_le16(1024);
 		} else if (IS_QLA2100(ha)) {
 			nv->firmware_options[0] = BIT_3 | BIT_1;
 			nv->firmware_options[1] = BIT_5;
-			nv->frame_payload_size = 1024;
+			nv->frame_payload_size = cpu_to_le16(1024);
 		}
 
 		nv->max_iocb_allocation = cpu_to_le16(256);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index e3d2dea0b057..0954fa41911c 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2874,7 +2874,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 					    &vha->dpc_flags);
 					qla2xxx_wake_dpc(vha);
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				ql_dbg(ql_dbg_disc, vha, 0x20eb,
 				    "%s %8phC cmd error fw_status 0x%x 0x%x 0x%x\n",
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 27bcd346af7c..25e0a1684763 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1580,11 +1580,11 @@ global_port_update:
 				qla2xxx_wake_dpc(vha);
 			}
 		}
-		/* fall through */
+		fallthrough;
 	case MBA_IDC_COMPLETE:
 		if (ha->notify_lb_portup_comp && !vha->vp_idx)
 			complete(&ha->lb_portup_comp);
-		/* Fallthru */
+		fallthrough;
 	case MBA_IDC_TIME_EXT:
 		if (IS_QLA81XX(vha->hw) || IS_QLA8031(vha->hw) ||
 		    IS_QLA8044(ha))
@@ -2024,8 +2024,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 				res = DID_ERROR << 16;
 			}
 		}
-		ql_dbg(ql_dbg_user, vha, 0x503f,
-		    "ELS IOCB Done -%s error hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n",
+		ql_dbg(ql_dbg_disc, vha, 0x503f,
+		    "ELS IOCB Done -%s hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n",
 		    type, sp->handle, comp_status, fw_status[1], fw_status[2],
 		    le32_to_cpu(ese->total_byte_count));
 		goto els_ct_done;
@@ -2188,7 +2188,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 				set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
 			qla2xxx_wake_dpc(vha);
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		data[0] = MBS_COMMAND_ERROR;
 		break;
@@ -2368,7 +2368,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	case CS_PORT_UNAVAILABLE:
 	case CS_PORT_LOGGED_OUT:
 		fcport->nvme_flag |= NVME_FLAG_RESETTING;
-		/* fall through */
+		fallthrough;
 	case CS_ABORTED:
 	case CS_PORT_BUSY:
 		fd->transferred_length = 0;
@@ -3485,7 +3485,7 @@ process_err:
 			} else {
 				qlt_24xx_process_atio_queue(vha, 1);
 			}
-			/* fall through */
+			fallthrough;
 		case ABTS_RESP_24XX:
 		case CTIO_TYPE7:
 		case CTIO_CRC2:
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 73883435ab58..226f1428d3e5 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -334,14 +334,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			if (time_after(jiffies, wait_time))
 				break;
 
-			/*
-			 * Check if it's UNLOADING, cause we cannot poll in
-			 * this case, or else a NULL pointer dereference
-			 * is triggered.
-			 */
-			if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags)))
-				return QLA_FUNCTION_TIMEOUT;
-
 			/* Check for pending interrupts. */
 			qla2x00_poll(ha->rsp_q_map[0]);
 
@@ -5240,7 +5232,7 @@ qla2x00_read_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t *data)
 	mcp->mb[8] = MSW(risc_addr);
 	mcp->out_mb = MBX_8|MBX_1|MBX_0;
 	mcp->in_mb = MBX_3|MBX_2|MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 	rval = qla2x00_mailbox_command(vha, mcp);
 	if (rval != QLA_SUCCESS) {
@@ -5428,7 +5420,7 @@ qla2x00_write_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t data)
 	mcp->mb[8] = MSW(risc_addr);
 	mcp->out_mb = MBX_8|MBX_3|MBX_2|MBX_1|MBX_0;
 	mcp->in_mb = MBX_1|MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 	rval = qla2x00_mailbox_command(vha, mcp);
 	if (rval != QLA_SUCCESS) {
@@ -5700,7 +5692,7 @@ qla24xx_set_fcp_prio(scsi_qla_host_t *vha, uint16_t loop_id, uint16_t priority,
 	mcp->mb[9] = vha->vp_idx;
 	mcp->out_mb = MBX_9|MBX_4|MBX_3|MBX_2|MBX_1|MBX_0;
 	mcp->in_mb = MBX_4|MBX_3|MBX_1|MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 	rval = qla2x00_mailbox_command(vha, mcp);
 	if (mb != NULL) {
@@ -5787,7 +5779,7 @@ qla82xx_mbx_intr_enable(scsi_qla_host_t *vha)
 
 	mcp->out_mb = MBX_1|MBX_0;
 	mcp->in_mb = MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 
 	rval = qla2x00_mailbox_command(vha, mcp);
@@ -5822,7 +5814,7 @@ qla82xx_mbx_intr_disable(scsi_qla_host_t *vha)
 
 	mcp->out_mb = MBX_1|MBX_0;
 	mcp->in_mb = MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 
 	rval = qla2x00_mailbox_command(vha, mcp);
@@ -6014,7 +6006,7 @@ qla81xx_set_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg)
 	if (IS_QLA8031(ha))
 		mcp->out_mb |= MBX_6|MBX_5|MBX_4|MBX_3;
 	mcp->in_mb = MBX_0;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 
 	rval = qla2x00_mailbox_command(vha, mcp);
@@ -6050,7 +6042,7 @@ qla81xx_get_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg)
 	mcp->in_mb = MBX_2|MBX_1|MBX_0;
 	if (IS_QLA8031(ha))
 		mcp->in_mb |= MBX_6|MBX_5|MBX_4|MBX_3;
-	mcp->tov = 30;
+	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 
 	rval = qla2x00_mailbox_command(vha, mcp);
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index fa695a4007f8..90bbc61f361b 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -536,6 +536,11 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport,
 	struct nvme_private *priv = fd->private;
 	struct qla_nvme_rport *qla_rport = rport->private;
 
+	if (!priv) {
+		/* nvme association has been torn down */
+		return rval;
+	}
+
 	fcport = qla_rport->fcport;
 
 	if (!qpair || !fcport || (qpair && !qpair->fw_started) ||
@@ -687,7 +692,15 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha)
 	tmpl = &qla_nvme_fc_transport;
 
 	WARN_ON(vha->nvme_local_port);
-	WARN_ON(ha->max_req_queues < 3);
+
+	if (ha->max_req_queues < 3) {
+		if (!ha->flags.max_req_queue_warned)
+			ql_log(ql_log_info, vha, 0x2120,
+			       "%s: Disabling FC-NVME due to lack of free queue pairs (%d).\n",
+			       __func__, ha->max_req_queues);
+		ha->flags.max_req_queue_warned = 1;
+		return ret;
+	}
 
 	qla_nvme_fc_transport.max_hw_queues =
 	    min((uint8_t)(qla_nvme_fc_transport.max_hw_queues),
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 9b59f032a569..8da00ba54aec 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2017,6 +2017,11 @@ skip_pio:
 	/* Determine queue resources */
 	ha->max_req_queues = ha->max_rsp_queues = 1;
 	ha->msix_count = QLA_BASE_VECTORS;
+
+	/* Check if FW supports MQ or not */
+	if (!(ha->fw_attributes & BIT_6))
+		goto mqiobase_exit;
+
 	if (!ql2xmqsupport || !ql2xnvmeenable ||
 	    (!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
 		goto mqiobase_exit;
@@ -2829,10 +2834,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* This may fail but that's ok */
 	pci_enable_pcie_error_reporting(pdev);
 
-	/* Turn off T10-DIF when FC-NVMe is enabled */
-	if (ql2xnvmeenable)
-		ql2xenabledif = 0;
-
 	ha = kzalloc(sizeof(struct qla_hw_data), GFP_KERNEL);
 	if (!ha) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0009,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index e161c05d7d82..411b8a9ff393 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -2457,7 +2457,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf,
 				sec_mask = 0x10000;
 				break;
 			}
-			/* Fall through... */
+			fallthrough;
 
 		case 0x1f: /* Atmel flash. */
 			/* 512k sector size. */
@@ -2466,7 +2466,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf,
 				sec_mask =   0x80000000;
 				break;
 			}
-			/* Fall through... */
+			fallthrough;
 
 		case 0x01: /* AMD flash. */
 			if (flash_id == 0x38 || flash_id == 0x40 ||
@@ -2499,7 +2499,7 @@ qla2x00_write_optrom_data(struct scsi_qla_host *vha, void *buf,
 				sec_mask = 0x1e000;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			/* Default to 16 kb sector size. */
 			rest_addr = 0x3fff;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index fbb80a043b4f..2d445bdb2129 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -442,7 +442,7 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha,
 		ql_dbg(ql_dbg_tgt, vha, 0xe073,
 			"qla_target(%d):%s: CRC2 Response pkt\n",
 			vha->vp_idx, __func__);
-		/* fall through */
+		fallthrough;
 	case CTIO_TYPE7:
 	{
 		struct ctio7_from_24xx *entry = (struct ctio7_from_24xx *)pkt;
@@ -1270,7 +1270,7 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 
 	qla24xx_chk_fcp_state(sess);
 
-	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
+	ql_dbg(ql_dbg_disc, sess->vha, 0xe001,
 	    "Scheduling sess %p for deletion %8phC\n",
 	    sess, sess->port_name);
 
@@ -4423,7 +4423,7 @@ static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun,
 	case QLA_TGT_CLEAR_TS:
 	case QLA_TGT_ABORT_TS:
 		abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
-		/* fall through */
+		fallthrough;
 	case QLA_TGT_CLEAR_ACA:
 		h = qlt_find_qphint(vha, mcmd->unpacked_lun);
 		mcmd->qpair = h->qpair;
@@ -5057,7 +5057,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 			res = 1;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case ELS_LOGO:
 	case ELS_PRLO:
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index bab87e47b238..676778cbc550 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -2907,7 +2907,7 @@ static int qla4xxx_session_get_param(struct iscsi_cls_session *cls_sess,
 						chap_tbl.secret_len);
 			}
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return iscsi_session_get_param(cls_sess, param, buf);
 	}
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 3790e8b70bba..48ff7d88af86 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -200,15 +200,15 @@ static int qlogicpti_mbox_command(struct qlogicpti *qpti, u_short param[], int f
 	/* Write mailbox command registers. */
 	switch (mbox_param[param[0]] >> 4) {
 	case 6: sbus_writew(param[5], qpti->qregs + MBOX5);
-		/* Fall through */
+		fallthrough;
 	case 5: sbus_writew(param[4], qpti->qregs + MBOX4);
-		/* Fall through */
+		fallthrough;
 	case 4: sbus_writew(param[3], qpti->qregs + MBOX3);
-		/* Fall through */
+		fallthrough;
 	case 3: sbus_writew(param[2], qpti->qregs + MBOX2);
-		/* Fall through */
+		fallthrough;
 	case 2: sbus_writew(param[1], qpti->qregs + MBOX1);
-		/* Fall through */
+		fallthrough;
 	case 1: sbus_writew(param[0], qpti->qregs + MBOX0);
 	}
 
@@ -259,15 +259,15 @@ static int qlogicpti_mbox_command(struct qlogicpti *qpti, u_short param[], int f
 	/* Read back output parameters. */
 	switch (mbox_param[param[0]] & 0xf) {
 	case 6: param[5] = sbus_readw(qpti->qregs + MBOX5);
-		/* Fall through */
+		fallthrough;
 	case 5: param[4] = sbus_readw(qpti->qregs + MBOX4);
-		/* Fall through */
+		fallthrough;
 	case 4: param[3] = sbus_readw(qpti->qregs + MBOX3);
-		/* Fall through */
+		fallthrough;
 	case 3: param[2] = sbus_readw(qpti->qregs + MBOX2);
-		/* Fall through */
+		fallthrough;
 	case 2: param[1] = sbus_readw(qpti->qregs + MBOX1);
-		/* Fall through */
+		fallthrough;
 	case 1: param[0] = sbus_readw(qpti->qregs + MBOX0);
 	}
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 064ed680c053..1ad7260d4758 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4482,8 +4482,6 @@ static int resp_open_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 		goto fini;
 	}
 
-	if (zc == ZC2_IMPLICIT_OPEN)
-		zbc_close_zone(devip, zsp);
 	zbc_open_zone(devip, zsp, true);
 fini:
 	write_unlock(macc_lckp);
@@ -5490,9 +5488,11 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 				u64 d = ktime_get_boottime_ns() - ns_from_boot;
 
 				if (kt <= d) {	/* elapsed duration >= kt */
+					spin_lock_irqsave(&sqp->qc_lock, iflags);
 					sqcp->a_cmnd = NULL;
 					atomic_dec(&devip->num_in_q);
 					clear_bit(k, sqp->in_use_bm);
+					spin_unlock_irqrestore(&sqp->qc_lock, iflags);
 					if (new_sd_dp)
 						kfree(sd_dp);
 					/* call scsi_done() from this thread */
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 927b1e641842..7d3571a2bd89 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -599,7 +599,7 @@ int scsi_check_sense(struct scsi_cmnd *scmd)
 			set_host_byte(scmd, DID_ALLOC_FAILURE);
 			return SUCCESS;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case COPY_ABORTED:
 	case VOLUME_OVERFLOW:
 	case MISCOMPARE:
@@ -621,7 +621,7 @@ int scsi_check_sense(struct scsi_cmnd *scmd)
 			return ADD_TO_MLQUEUE;
 		else
 			set_host_byte(scmd, DID_TARGET_FAILURE);
-		/* FALLTHROUGH */
+		fallthrough;
 
 	case ILLEGAL_REQUEST:
 		if (sshdr.asc == 0x20 || /* Invalid command operation code */
@@ -734,7 +734,7 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd)
 	switch (status_byte(scmd->result)) {
 	case GOOD:
 		scsi_handle_queue_ramp_up(scmd->device);
-		/* FALLTHROUGH */
+		fallthrough;
 	case COMMAND_TERMINATED:
 		return SUCCESS;
 	case CHECK_CONDITION:
@@ -755,7 +755,7 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd)
 		return FAILED;
 	case QUEUE_FULL:
 		scsi_handle_queue_full(scmd->device);
-		/* fall through */
+		fallthrough;
 	case BUSY:
 		return NEEDS_RETRY;
 	default:
@@ -1302,7 +1302,7 @@ retry_tur:
 	case NEEDS_RETRY:
 		if (retry_cnt--)
 			goto retry_tur;
-		/*FALLTHRU*/
+		fallthrough;
 	case SUCCESS:
 		return 0;
 	default:
@@ -1739,7 +1739,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd)
 		if (msg_byte(scmd->result) == COMMAND_COMPLETE &&
 		    status_byte(scmd->result) == RESERVATION_CONFLICT)
 			return 0;
-		/* fall through */
+		fallthrough;
 	case DID_SOFT_ERROR:
 		return (scmd->request->cmd_flags & REQ_FAILFAST_DRIVER);
 	}
@@ -1810,7 +1810,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 			set_host_byte(scmd, DID_TIME_OUT);
 			return SUCCESS;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case DID_NO_CONNECT:
 	case DID_BAD_TARGET:
 		/*
@@ -1854,7 +1854,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 			 * lower down
 			 */
 			break;
-		/* fallthrough */
+		fallthrough;
 	case DID_BUS_BUSY:
 	case DID_PARITY:
 		goto maybe_retry;
@@ -1892,7 +1892,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 		 * the case of trying to send too many commands to a
 		 * tagged queueing device.
 		 */
-		/* FALLTHROUGH */
+		fallthrough;
 	case BUSY:
 		/*
 		 * device can't talk to us at the moment.  Should only
@@ -1905,7 +1905,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 		if (scmd->cmnd[0] == REPORT_LUNS)
 			scmd->device->sdev_target->expecting_lun_change = 0;
 		scsi_handle_queue_ramp_up(scmd->device);
-		/* FALLTHROUGH */
+		fallthrough;
 	case COMMAND_TERMINATED:
 		return SUCCESS;
 	case TASK_ABORTED:
@@ -2376,22 +2376,22 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 		rtn = scsi_try_bus_device_reset(scmd);
 		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case SG_SCSI_RESET_TARGET:
 		rtn = scsi_try_target_reset(scmd);
 		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case SG_SCSI_RESET_BUS:
 		rtn = scsi_try_bus_reset(scmd);
 		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case SG_SCSI_RESET_HOST:
 		rtn = scsi_try_host_reset(scmd);
 		if (rtn == SUCCESS)
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	default:
 		rtn = FAILED;
 		break;
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 45d04b7b2643..14872c9dc78c 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -117,14 +117,14 @@ static int ioctl_internal_command(struct scsi_device *sdev, char *cmd,
 		case NOT_READY:	/* This happens if there is no disc in drive */
 			if (sdev->removable)
 				break;
-			/* FALLTHROUGH */
+			fallthrough;
 		case UNIT_ATTENTION:
 			if (sdev->removable) {
 				sdev->changed = 1;
 				result = 0;	/* This is no longer considered an error */
 				break;
 			}
-			/* FALLTHROUGH -- for non-removable media */
+			fallthrough;	/* for non-removable media */
 		default:
 			sdev_printk(KERN_INFO, sdev,
 				    "ioctl_internal_command return code = %x\n",
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7c6dd6f75190..7affaaf8b98e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -795,7 +795,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 		}
 		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req)))
 			return;
-		/*FALLTHRU*/
+		fallthrough;
 	case ACTION_REPREP:
 		scsi_io_completion_reprep(cmd, q);
 		break;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index bd38c8cea56e..ca1e6cf6a38e 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -516,7 +516,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
 		break;
 	case BMIC_SENSE_DIAG_OPTIONS:
 		cdb_length = 0;
-		/* fall through */
+		fallthrough;
 	case BMIC_IDENTIFY_CONTROLLER:
 	case BMIC_IDENTIFY_PHYSICAL_DEVICE:
 	case BMIC_SENSE_SUBSYSTEM_INFORMATION:
@@ -527,7 +527,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
 		break;
 	case BMIC_SET_DIAG_OPTIONS:
 		cdb_length = 0;
-		/* fall through */
+		fallthrough;
 	case BMIC_WRITE_HOST_WELLNESS:
 		request->data_direction = SOP_WRITE_FLAG;
 		cdb[0] = BMIC_WRITE;
@@ -2324,7 +2324,7 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info,
 	switch (scmd->cmnd[0]) {
 	case WRITE_6:
 		is_write = true;
-		/* fall through */
+		fallthrough;
 	case READ_6:
 		first_block = (u64)(((scmd->cmnd[1] & 0x1f) << 16) |
 			(scmd->cmnd[2] << 8) | scmd->cmnd[3]);
@@ -2334,21 +2334,21 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info,
 		break;
 	case WRITE_10:
 		is_write = true;
-		/* fall through */
+		fallthrough;
 	case READ_10:
 		first_block = (u64)get_unaligned_be32(&scmd->cmnd[2]);
 		block_cnt = (u32)get_unaligned_be16(&scmd->cmnd[7]);
 		break;
 	case WRITE_12:
 		is_write = true;
-		/* fall through */
+		fallthrough;
 	case READ_12:
 		first_block = (u64)get_unaligned_be32(&scmd->cmnd[2]);
 		block_cnt = get_unaligned_be32(&scmd->cmnd[6]);
 		break;
 	case WRITE_16:
 		is_write = true;
-		/* fall through */
+		fallthrough;
 	case READ_16:
 		first_block = get_unaligned_be64(&scmd->cmnd[2]);
 		block_cnt = get_unaligned_be32(&scmd->cmnd[10]);
@@ -2948,7 +2948,7 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info,
 		case PQI_RESPONSE_IU_AIO_PATH_IO_SUCCESS:
 			if (io_request->scmd)
 				io_request->scmd->result = 0;
-			/* fall through */
+			fallthrough;
 		case PQI_RESPONSE_IU_GENERAL_MANAGEMENT:
 			break;
 		case PQI_RESPONSE_IU_VENDOR_GENERAL:
@@ -3115,12 +3115,11 @@ static void pqi_process_soft_reset(struct pqi_ctrl_info *ctrl_info,
 
 	switch (reset_status) {
 	case RESET_INITIATE_DRIVER:
-		/* fall through */
 	case RESET_TIMEDOUT:
 		dev_info(&ctrl_info->pci_dev->dev,
 			"resetting controller %u\n", ctrl_info->ctrl_id);
 		sis_soft_reset(ctrl_info);
-		/* fall through */
+		fallthrough;
 	case RESET_INITIATE_FIRMWARE:
 		rc = pqi_ofa_ctrl_restart(ctrl_info);
 		pqi_ofa_free_host_buffer(ctrl_info);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 0c4aa4665a2f..3b3a53c6a0de 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -877,10 +877,10 @@ static void get_sectorsize(struct scsi_cd *cd)
 		case 2340:
 		case 2352:
 			sector_size = 2048;
-			/* fall through */
+			fallthrough;
 		case 2048:
 			cd->capacity *= 4;
-			/* fall through */
+			fallthrough;
 		case 512:
 			break;
 		default:
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 87fbc0ea350b..e2e5356a997d 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -339,14 +339,14 @@ static void st_analyze_sense(struct st_request *SRpnt, struct st_cmdstatus *s)
 		switch (sense[0] & 0x7f) {
 		case 0x71:
 			s->deferred = 1;
-			/* fall through */
+			fallthrough;
 		case 0x70:
 			s->fixed_format = 1;
 			s->flags = sense[2] & 0xe0;
 			break;
 		case 0x73:
 			s->deferred = 1;
-			/* fall through */
+			fallthrough;
 		case 0x72:
 			s->fixed_format = 0;
 			ucp = scsi_sense_desc_find(sense, SCSI_SENSE_BUFFERSIZE, 4);
@@ -2723,7 +2723,7 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 	switch (cmd_in) {
 	case MTFSFM:
 		chg_eof = 0;	/* Changed from the FSF after this */
-		/* fall through */
+		fallthrough;
 	case MTFSF:
 		cmd[0] = SPACE;
 		cmd[1] = 0x01;	/* Space FileMarks */
@@ -2738,7 +2738,7 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 		break;
 	case MTBSFM:
 		chg_eof = 0;	/* Changed from the FSF after this */
-		/* fall through */
+		fallthrough;
 	case MTBSF:
 		cmd[0] = SPACE;
 		cmd[1] = 0x01;	/* Space FileMarks */
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index 701b842296f0..2e3fbc2fae97 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -397,12 +397,12 @@ static int sun3scsi_dma_finish(int write_flag)
 		case CSR_LEFT_3:
 			*vaddr = (dregs->bpack_lo & 0xff00) >> 8;
 			vaddr--;
-			/* Fall through */
+			fallthrough;
 
 		case CSR_LEFT_2:
 			*vaddr = (dregs->bpack_hi & 0x00ff);
 			vaddr--;
-			/* Fall through */
+			fallthrough;
 
 		case CSR_LEFT_1:
 			*vaddr = (dregs->bpack_hi & 0xff00) >> 8;
diff --git a/drivers/scsi/sym53c8xx_2/sym_fw.c b/drivers/scsi/sym53c8xx_2/sym_fw.c
index 6d7651a7847e..c6db61b61de3 100644
--- a/drivers/scsi/sym53c8xx_2/sym_fw.c
+++ b/drivers/scsi/sym53c8xx_2/sym_fw.c
@@ -523,7 +523,7 @@ void sym_fw_bind_script(struct sym_hcb *np, u32 *start, int len)
 					new = old;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				new = 0;
 				panic("sym_fw_bind_script: "
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index 8410117d5aa4..cc11daa1222b 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3059,7 +3059,7 @@ static void sym_sir_bad_scsi_status(struct sym_hcb *np, int num, struct sym_ccb
 			sym_print_addr(cp->cmd, "%s\n",
 			        s_status == S_BUSY ? "BUSY" : "QUEUE FULL\n");
 		}
-		/* fall through */
+		fallthrough;
 	default:	/* S_INT, S_INT_COND_MET, S_CONFLICT */
 		sym_complete_error (np, cp);
 		break;
@@ -4620,7 +4620,7 @@ static void sym_int_sir(struct sym_hcb *np)
 	 *  Negotiation failed.
 	 *  Target does not want answer message.
 	 */
-	/* fall through */
+		fallthrough;
 	case SIR_NEGO_PROTO:
 		sym_nego_default(np, tp, cp);
 		goto out;
diff --git a/drivers/scsi/sym53c8xx_2/sym_nvram.c b/drivers/scsi/sym53c8xx_2/sym_nvram.c
index d37e2a69136a..e13d5351f155 100644
--- a/drivers/scsi/sym53c8xx_2/sym_nvram.c
+++ b/drivers/scsi/sym53c8xx_2/sym_nvram.c
@@ -695,7 +695,7 @@ static int sym_read_Tekram_nvram (struct sym_device *np, Tekram_nvram *nvram)
 					  data, len);
 		if (!x)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		x = sym_read_T93C46_nvram(np, nvram);
 		break;
diff --git a/drivers/scsi/ufs/ti-j721e-ufs.c b/drivers/scsi/ufs/ti-j721e-ufs.c
index 46bb905b4d6a..eafe0db98d54 100644
--- a/drivers/scsi/ufs/ti-j721e-ufs.c
+++ b/drivers/scsi/ufs/ti-j721e-ufs.c
@@ -38,6 +38,7 @@ static int ti_j721e_ufs_probe(struct platform_device *pdev)
 	/* Select MPHY refclk frequency */
 	clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
 		dev_err(dev, "Cannot claim MPHY clock.\n");
 		goto clk_err;
 	}
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 29cd017c1aa0..1755dd6b04ae 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -212,7 +212,7 @@ static int ufs_mtk_wait_link_state(struct ufs_hba *hba, u32 state,
 	ktime_t timeout, time_checked;
 	u32 val;
 
-	timeout = ktime_add_us(ktime_get(), ms_to_ktime(max_wait_ms));
+	timeout = ktime_add_ms(ktime_get(), max_wait_ms);
 	do {
 		time_checked = ktime_get();
 		ufshcd_writel(hba, 0x20, REG_UFS_DEBUG_SEL);
diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c
index bcfbbd0d5c45..5b2bc1a6f922 100644
--- a/drivers/scsi/ufs/ufs_bsg.c
+++ b/drivers/scsi/ufs/ufs_bsg.c
@@ -110,7 +110,7 @@ static int ufs_bsg_request(struct bsg_job *job)
 			goto out;
 		}
 
-		/* fall through */
+		fallthrough;
 	case UPIU_TRANSACTION_NOP_OUT:
 	case UPIU_TRANSACTION_TASK_REQ:
 		ret = ufshcd_exec_raw_upiu_cmd(hba, &bsg_request->upiu_req,
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index f407b13883ac..5a95a7bfbab0 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -44,11 +44,23 @@ static int ufs_intel_link_startup_notify(struct ufs_hba *hba,
 	return err;
 }
 
+static int ufs_intel_ehl_init(struct ufs_hba *hba)
+{
+	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
+	return 0;
+}
+
 static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = {
 	.name                   = "intel-pci",
 	.link_startup_notify	= ufs_intel_link_startup_notify,
 };
 
+static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = {
+	.name                   = "intel-pci",
+	.init			= ufs_intel_ehl_init,
+	.link_startup_notify	= ufs_intel_link_startup_notify,
+};
+
 #ifdef CONFIG_PM_SLEEP
 /**
  * ufshcd_pci_suspend - suspend power management function
@@ -177,8 +189,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = {
 static const struct pci_device_id ufshcd_pci_tbl[] = {
 	{ PCI_VENDOR_ID_SAMSUNG, 0xC00C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
 	{ PCI_VDEVICE(INTEL, 0x9DFA), (kernel_ulong_t)&ufs_intel_cnl_hba_vops },
-	{ PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_cnl_hba_vops },
-	{ PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_cnl_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
 	{ }	/* terminate list */
 };
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 307622284239..1d157ff58d81 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1561,6 +1561,7 @@ unblock_reqs:
 int ufshcd_hold(struct ufs_hba *hba, bool async)
 {
 	int rc = 0;
+	bool flush_result;
 	unsigned long flags;
 
 	if (!ufshcd_is_clkgating_allowed(hba))
@@ -1592,7 +1593,9 @@ start:
 				break;
 			}
 			spin_unlock_irqrestore(hba->host->host_lock, flags);
-			flush_work(&hba->clk_gating.ungate_work);
+			flush_result = flush_work(&hba->clk_gating.ungate_work);
+			if (hba->clk_gating.is_suspended && !flush_result)
+				goto out;
 			spin_lock_irqsave(hba->host->host_lock, flags);
 			goto start;
 		}
@@ -1609,7 +1612,7 @@ start:
 		 * currently running. Hence, fall through to cancel gating
 		 * work and to enable clocks.
 		 */
-		/* fallthrough */
+		fallthrough;
 	case CLKS_OFF:
 		ufshcd_scsi_block_requests(hba);
 		hba->clk_gating.state = REQ_CLKS_ON;
@@ -1621,7 +1624,7 @@ start:
 		 * fall through to check if we should wait for this
 		 * work to be done or not.
 		 */
-		/* fallthrough */
+		fallthrough;
 	case REQ_CLKS_ON:
 		if (async) {
 			rc = -EAGAIN;
@@ -4734,7 +4737,7 @@ ufshcd_scsi_cmd_status(struct ufshcd_lrb *lrbp, int scsi_status)
 	switch (scsi_status) {
 	case SAM_STAT_CHECK_CONDITION:
 		ufshcd_copy_sense_data(lrbp);
-		/* fallthrough */
+		fallthrough;
 	case SAM_STAT_GOOD:
 		result |= DID_OK << 16 |
 			  COMMAND_COMPLETE << 8 |
@@ -5941,7 +5944,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
  */
 static irqreturn_t ufshcd_intr(int irq, void *__hba)
 {
-	u32 intr_status, enabled_intr_status;
+	u32 intr_status, enabled_intr_status = 0;
 	irqreturn_t retval = IRQ_NONE;
 	struct ufs_hba *hba = __hba;
 	int retries = hba->nutrs;
@@ -5955,7 +5958,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 	 * read, make sure we handle them by checking the interrupt status
 	 * again in a loop until we process all of the reqs before returning.
 	 */
-	do {
+	while (intr_status && retries--) {
 		enabled_intr_status =
 			intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE);
 		if (intr_status)
@@ -5964,9 +5967,9 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 			retval |= ufshcd_sl_intr(hba, enabled_intr_status);
 
 		intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
-	} while (intr_status && --retries);
+	}
 
-	if (retval == IRQ_NONE) {
+	if (enabled_intr_status && retval == IRQ_NONE) {
 		dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n",
 					__func__, intr_status);
 		ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: ");
@@ -6274,7 +6277,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
 	switch (msgcode) {
 	case UPIU_TRANSACTION_NOP_OUT:
 		cmd_type = DEV_CMD_TYPE_NOP;
-		/* fall through */
+		fallthrough;
 	case UPIU_TRANSACTION_QUERY_REQ:
 		ufshcd_hold(hba, false);
 		mutex_lock(&hba->dev_cmd.lock);
@@ -6434,14 +6437,8 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		goto out;
 	}
 
-	if (!(reg & (1 << tag))) {
-		dev_err(hba->dev,
-		"%s: cmd was completed, but without a notifying intr, tag = %d",
-		__func__, tag);
-	}
-
 	/* Print Transfer Request of aborted task */
-	dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag);
+	dev_info(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag);
 
 	/*
 	 * Print detailed info about aborted request.
@@ -6462,6 +6459,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	}
 	hba->req_abort_count++;
 
+	if (!(reg & (1 << tag))) {
+		dev_err(hba->dev,
+		"%s: cmd was completed, but without a notifying intr, tag = %d",
+		__func__, tag);
+		goto cleanup;
+	}
+
 	/* Skip task abort in case previous aborts failed and report failure */
 	if (lrbp->req_abort_skip) {
 		err = -EIO;
@@ -6492,7 +6496,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 			/* command completed already */
 			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
 				__func__, tag);
-			goto out;
+			goto cleanup;
 		} else {
 			dev_err(hba->dev,
 				"%s: no response from device. tag = %d, err %d\n",
@@ -6526,6 +6530,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		goto out;
 	}
 
+cleanup:
 	scsi_dma_unmap(cmd);
 
 	spin_lock_irqsave(host->host_lock, flags);
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index b2ef18f1b746..363589c0bd37 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -520,6 +520,12 @@ enum ufshcd_quirks {
 	 * OCS FATAL ERROR with device error through sense data
 	 */
 	UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR		= 1 << 10,
+
+	/*
+	 * This quirk needs to be enabled if the host controller has
+	 * auto-hibernate capability but it doesn't work.
+	 */
+	UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8		= 1 << 11,
 };
 
 enum ufshcd_caps {
@@ -803,7 +809,8 @@ return true;
 
 static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba)
 {
-	return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT);
+	return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) &&
+		!(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8);
 }
 
 static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba)
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index ca1c39b6f631..3b1803432090 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -148,7 +148,7 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 	default:
 		scmd_printk(KERN_WARNING, sc, "Unknown response %d",
 			    resp->response);
-		/* fall through */
+		fallthrough;
 	case VIRTIO_SCSI_S_FAILURE:
 		set_host_byte(sc, DID_ERROR);
 		break;
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 8dbb4db6831a..081f54ab7d86 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -607,7 +607,7 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
 		case BTSTAT_TAGREJECT:
 		case BTSTAT_BADMSG:
 			cmd->result = (DRIVER_INVALID << 24);
-			/* fall through */
+			fallthrough;
 
 		case BTSTAT_HAHARDWARE:
 		case BTSTAT_INVPHASE:
diff --git a/drivers/scsi/wd33c93.c b/drivers/scsi/wd33c93.c
index f81046f0e68a..87dafbc942d3 100644
--- a/drivers/scsi/wd33c93.c
+++ b/drivers/scsi/wd33c93.c
@@ -1854,7 +1854,7 @@ round_4(unsigned int x)
 		case 1: --x;
 			break;
 		case 2: ++x;
-			/* fall through */
+			fallthrough;
 		case 3: ++x;
 	}
 	return x;
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index f0068e96a177..259fc248d06c 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -1111,7 +1111,7 @@ static void scsifront_backend_changed(struct xenbus_device *dev,
 	case XenbusStateClosed:
 		if (dev->state == XenbusStateClosed)
 			break;
-		/* fall through - Missed the backend's Closing state */
+		fallthrough;	/* Missed the backend's Closing state */
 	case XenbusStateClosing:
 		scsifront_disconnect(info);
 		break;
diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
index e19102f46302..b25d0f7dac9e 100644
--- a/drivers/soc/qcom/socinfo.c
+++ b/drivers/soc/qcom/socinfo.c
@@ -353,7 +353,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 
 		debugfs_create_u32("nmodem_supported", 0400, qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.nmodem_supported);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 14):
 		qcom_socinfo->info.num_clusters = __le32_to_cpu(info->num_clusters);
 		qcom_socinfo->info.ncluster_array_offset = __le32_to_cpu(info->ncluster_array_offset);
@@ -368,14 +368,14 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 				   &qcom_socinfo->info.num_defective_parts);
 		debugfs_create_u32("ndefective_parts_array_offset", 0400, qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.ndefective_parts_array_offset);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 13):
 		qcom_socinfo->info.nproduct_id = __le32_to_cpu(info->nproduct_id);
 
 		debugfs_create_u32("nproduct_id", 0400, qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.nproduct_id);
 		DEBUGFS_ADD(info, chip_id);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 12):
 		qcom_socinfo->info.chip_family =
 			__le32_to_cpu(info->chip_family);
@@ -392,7 +392,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 		debugfs_create_x32("raw_device_number", 0400,
 				   qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.raw_device_num);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 11):
 	case SOCINFO_VERSION(0, 10):
 	case SOCINFO_VERSION(0, 9):
@@ -400,12 +400,12 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 
 		debugfs_create_u32("foundry_id", 0400, qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.foundry_id);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 8):
 	case SOCINFO_VERSION(0, 7):
 		DEBUGFS_ADD(info, pmic_model);
 		DEBUGFS_ADD(info, pmic_die_rev);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 6):
 		qcom_socinfo->info.hw_plat_subtype =
 			__le32_to_cpu(info->hw_plat_subtype);
@@ -413,7 +413,7 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 		debugfs_create_u32("hardware_platform_subtype", 0400,
 				   qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.hw_plat_subtype);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 5):
 		qcom_socinfo->info.accessory_chip =
 			__le32_to_cpu(info->accessory_chip);
@@ -421,27 +421,27 @@ static void socinfo_debugfs_init(struct qcom_socinfo *qcom_socinfo,
 		debugfs_create_u32("accessory_chip", 0400,
 				   qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.accessory_chip);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 4):
 		qcom_socinfo->info.plat_ver = __le32_to_cpu(info->plat_ver);
 
 		debugfs_create_u32("platform_version", 0400,
 				   qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.plat_ver);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 3):
 		qcom_socinfo->info.hw_plat = __le32_to_cpu(info->hw_plat);
 
 		debugfs_create_u32("hardware_platform", 0400,
 				   qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.hw_plat);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 2):
 		qcom_socinfo->info.raw_ver  = __le32_to_cpu(info->raw_ver);
 
 		debugfs_create_u32("raw_version", 0400, qcom_socinfo->dbg_root,
 				   &qcom_socinfo->info.raw_ver);
-		/* Fall through */
+		fallthrough;
 	case SOCINFO_VERSION(0, 1):
 		DEBUGFS_ADD(info, build_id);
 		break;
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index 42cf37a0556b..d332e5d9abac 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -2229,7 +2229,7 @@ static int tegra_pmc_clk_notify_cb(struct notifier_block *nb,
 
 	case POST_RATE_CHANGE:
 		pmc->rate = data->new_rate;
-		/* fall through */
+		fallthrough;
 
 	case ABORT_RATE_CHANGE:
 		mutex_unlock(&pmc->powergates_lock);
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index e6e0fb9a81b4..da0201693c24 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1372,7 +1372,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		return ret;
 	}
 
-	/* Read Instat 1, Instat 2 and Instat 3 registers */
+	/* Read Intstat 1, Intstat 2 and Intstat 3 registers */
 	ret = sdw_read(slave, SDW_SCP_INT1);
 	if (ret < 0) {
 		dev_err(slave->bus->dev,
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 37290a799023..6e36deb505b1 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -717,6 +717,7 @@ error:
 	kfree(wbuf);
 error_1:
 	kfree(wr_msg);
+	bus->defer_msg.msg = NULL;
 	return ret;
 }
 
@@ -840,9 +841,10 @@ static int do_bank_switch(struct sdw_stream_runtime *stream)
 error:
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
 		bus = m_rt->bus;
-
-		kfree(bus->defer_msg.msg->buf);
-		kfree(bus->defer_msg.msg);
+		if (bus->defer_msg.msg) {
+			kfree(bus->defer_msg.msg->buf);
+			kfree(bus->defer_msg.msg);
+		}
 	}
 
 msg_unlock:
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index c3008e423f59..c6ea760ea5f0 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -1017,4 +1017,7 @@ config SPI_SLAVE_SYSTEM_CONTROL
 
 endif # SPI_SLAVE
 
+config SPI_DYNAMIC
+	def_bool ACPI || OF_DYNAMIC || SPI_SLAVE
+
 endif # SPI
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 2f717812c766..03b034c15d2b 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -164,10 +164,10 @@ static inline void bcm2835aux_rd_fifo(struct bcm2835aux_spi *bs)
 		switch (count) {
 		case 3:
 			*bs->rx_buf++ = (data >> 16) & 0xff;
-			/* fallthrough */
+			fallthrough;
 		case 2:
 			*bs->rx_buf++ = (data >> 8) & 0xff;
-			/* fallthrough */
+			fallthrough;
 		case 1:
 			*bs->rx_buf++ = (data >> 0) & 0xff;
 			/* fallthrough - no default */
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 1c1a9d17eec0..c6795c684b16 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -907,14 +907,16 @@ static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
 	struct dma_async_tx_descriptor *tx;
 	dma_cookie_t cookie;
 	dma_addr_t dma_dst;
+	struct device *ddev;
 
 	if (!cqspi->rx_chan || !virt_addr_valid(buf)) {
 		memcpy_fromio(buf, cqspi->ahb_base + from, len);
 		return 0;
 	}
 
-	dma_dst = dma_map_single(dev, buf, len, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, dma_dst)) {
+	ddev = cqspi->rx_chan->device->dev;
+	dma_dst = dma_map_single(ddev, buf, len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(ddev, dma_dst)) {
 		dev_err(dev, "dma mapping failed\n");
 		return -ENOMEM;
 	}
@@ -948,7 +950,7 @@ static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
 	}
 
 err_unmap:
-	dma_unmap_single(dev, dma_dst, len, DMA_FROM_DEVICE);
+	dma_unmap_single(ddev, dma_dst, len, DMA_FROM_DEVICE);
 
 	return ret;
 }
@@ -1128,8 +1130,17 @@ static int cqspi_request_mmap_dma(struct cqspi_st *cqspi)
 	return 0;
 }
 
+static const char *cqspi_get_name(struct spi_mem *mem)
+{
+	struct cqspi_st *cqspi = spi_master_get_devdata(mem->spi->master);
+	struct device *dev = &cqspi->pdev->dev;
+
+	return devm_kasprintf(dev, GFP_KERNEL, "%s.%d", dev_name(dev), mem->spi->chip_select);
+}
+
 static const struct spi_controller_mem_ops cqspi_mem_ops = {
 	.exec_op = cqspi_exec_mem_op,
+	.get_name = cqspi_get_name,
 };
 
 static int cqspi_setup_flash(struct cqspi_st *cqspi)
diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c
index 54ad0ac121e5..ee905880769e 100644
--- a/drivers/spi/spi-fsl-cpm.c
+++ b/drivers/spi/spi-fsl-cpm.c
@@ -226,7 +226,7 @@ static void fsl_spi_free_dummy_rx(void)
 	case 1:
 		kfree(fsl_dummy_rx);
 		fsl_dummy_rx = NULL;
-		/* fall through */
+		fallthrough;
 	default:
 		fsl_dummy_rx_refcnt--;
 		break;
@@ -294,7 +294,7 @@ int fsl_spi_cpm_init(struct mpc8xxx_spi *mspi)
 		switch (mspi->subblock) {
 		default:
 			dev_warn(dev, "cell-index unspecified, assuming SPI1\n");
-			/* fall through */
+			fallthrough;
 		case 0:
 			mspi->subblock = QE_CR_SUBBLOCK_SPI1;
 			break;
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 9522d1b5786d..df981e55c24c 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -90,7 +90,7 @@ static struct spi_test spi_tests[] = {
 	{
 		.description	= "tx/rx-transfer - crossing PAGE_SIZE",
 		.fill_option	= FILL_COUNT_8,
-		.iterate_len    = { ITERATE_MAX_LEN },
+		.iterate_len    = { ITERATE_LEN },
 		.iterate_tx_align = ITERATE_ALIGN,
 		.iterate_rx_align = ITERATE_ALIGN,
 		.transfer_count = 1,
diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c
index bd23c4689b46..127b8bd25831 100644
--- a/drivers/spi/spi-sprd-adi.c
+++ b/drivers/spi/spi-sprd-adi.c
@@ -506,7 +506,7 @@ static int sprd_adi_probe(struct platform_device *pdev)
 		default:
 			dev_err(&pdev->dev,
 				"failed to find hwlock id, %d\n", ret);
-			/* fall-through */
+			fallthrough;
 		case -EPROBE_DEFER:
 			goto put_ctlr;
 		}
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 4c643dfc7fbb..3056428b09f3 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -13,6 +13,7 @@
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/spi/spi.h>
@@ -441,7 +442,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz,
 {
 	u32 div, mbrdiv;
 
-	div = DIV_ROUND_UP(spi->clk_rate, speed_hz);
+	/* Ensure spi->clk_rate is even */
+	div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz);
 
 	/*
 	 * SPI framework set xfer->speed_hz to master->max_speed_hz if
@@ -467,20 +469,27 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz,
 /**
  * stm32h7_spi_prepare_fthlv - Determine FIFO threshold level
  * @spi: pointer to the spi controller data structure
+ * @xfer_len: length of the message to be transferred
  */
-static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi)
+static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len)
 {
-	u32 fthlv, half_fifo;
+	u32 fthlv, half_fifo, packet;
 
 	/* data packet should not exceed 1/2 of fifo space */
 	half_fifo = (spi->fifo_size / 2);
 
+	/* data_packet should not exceed transfer length */
+	if (half_fifo > xfer_len)
+		packet = xfer_len;
+	else
+		packet = half_fifo;
+
 	if (spi->cur_bpw <= 8)
-		fthlv = half_fifo;
+		fthlv = packet;
 	else if (spi->cur_bpw <= 16)
-		fthlv = half_fifo / 2;
+		fthlv = packet / 2;
 	else
-		fthlv = half_fifo / 4;
+		fthlv = packet / 4;
 
 	/* align packet size with data registers access */
 	if (spi->cur_bpw > 8)
@@ -488,6 +497,9 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi)
 	else
 		fthlv -= (fthlv % 4); /* multiple of 4 */
 
+	if (!fthlv)
+		fthlv = 1;
+
 	return fthlv;
 }
 
@@ -924,7 +936,11 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 	}
 
 	if (sr & STM32H7_SPI_SR_SUSP) {
-		dev_warn(spi->dev, "Communication suspended\n");
+		static DEFINE_RATELIMIT_STATE(rs,
+					      DEFAULT_RATELIMIT_INTERVAL * 10,
+					      1);
+		if (__ratelimit(&rs))
+			dev_dbg_ratelimited(spi->dev, "Communication suspended\n");
 		if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0)))
 			stm32h7_spi_read_rxfifo(spi, false);
 		/*
@@ -966,13 +982,13 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 		if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0)))
 			stm32h7_spi_read_rxfifo(spi, false);
 
-	writel_relaxed(mask, spi->base + STM32H7_SPI_IFCR);
+	writel_relaxed(sr & mask, spi->base + STM32H7_SPI_IFCR);
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 
 	if (end) {
-		spi_finalize_current_transfer(master);
 		stm32h7_spi_disable(spi);
+		spi_finalize_current_transfer(master);
 	}
 
 	return IRQ_HANDLED;
@@ -1393,7 +1409,7 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi)
 	cfg1_setb |= (bpw << STM32H7_SPI_CFG1_DSIZE_SHIFT) &
 		     STM32H7_SPI_CFG1_DSIZE;
 
-	spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi);
+	spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi, spi->cur_xferlen);
 	fthlv = spi->cur_fthlv - 1;
 
 	cfg1_clrb |= STM32H7_SPI_CFG1_FTHLV;
@@ -1585,39 +1601,33 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 	unsigned long flags;
 	unsigned int comm_type;
 	int nb_words, ret = 0;
+	int mbr;
 
 	spin_lock_irqsave(&spi->lock, flags);
 
-	if (spi->cur_bpw != transfer->bits_per_word) {
-		spi->cur_bpw = transfer->bits_per_word;
-		spi->cfg->set_bpw(spi);
-	}
+	spi->cur_xferlen = transfer->len;
 
-	if (spi->cur_speed != transfer->speed_hz) {
-		int mbr;
+	spi->cur_bpw = transfer->bits_per_word;
+	spi->cfg->set_bpw(spi);
 
-		/* Update spi->cur_speed with real clock speed */
-		mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz,
-					    spi->cfg->baud_rate_div_min,
-					    spi->cfg->baud_rate_div_max);
-		if (mbr < 0) {
-			ret = mbr;
-			goto out;
-		}
-
-		transfer->speed_hz = spi->cur_speed;
-		stm32_spi_set_mbr(spi, mbr);
+	/* Update spi->cur_speed with real clock speed */
+	mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz,
+				    spi->cfg->baud_rate_div_min,
+				    spi->cfg->baud_rate_div_max);
+	if (mbr < 0) {
+		ret = mbr;
+		goto out;
 	}
 
-	comm_type = stm32_spi_communication_type(spi_dev, transfer);
-	if (spi->cur_comm != comm_type) {
-		ret = spi->cfg->set_mode(spi, comm_type);
+	transfer->speed_hz = spi->cur_speed;
+	stm32_spi_set_mbr(spi, mbr);
 
-		if (ret < 0)
-			goto out;
+	comm_type = stm32_spi_communication_type(spi_dev, transfer);
+	ret = spi->cfg->set_mode(spi, comm_type);
+	if (ret < 0)
+		goto out;
 
-		spi->cur_comm = comm_type;
-	}
+	spi->cur_comm = comm_type;
 
 	if (spi->cfg->set_data_idleness)
 		spi->cfg->set_data_idleness(spi, transfer->len);
@@ -1635,8 +1645,6 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 			goto out;
 	}
 
-	spi->cur_xferlen = transfer->len;
-
 	dev_dbg(spi->dev, "transfer communication mode set to %d\n",
 		spi->cur_comm);
 	dev_dbg(spi->dev,
@@ -1996,6 +2004,8 @@ static int stm32_spi_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(&pdev->dev);
 
+	pinctrl_pm_select_sleep_state(&pdev->dev);
+
 	return 0;
 }
 
@@ -2007,13 +2017,18 @@ static int stm32_spi_runtime_suspend(struct device *dev)
 
 	clk_disable_unprepare(spi->clk);
 
-	return 0;
+	return pinctrl_pm_select_sleep_state(dev);
 }
 
 static int stm32_spi_runtime_resume(struct device *dev)
 {
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct stm32_spi *spi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = pinctrl_pm_select_default_state(dev);
+	if (ret)
+		return ret;
 
 	return clk_prepare_enable(spi->clk);
 }
@@ -2043,10 +2058,23 @@ static int stm32_spi_resume(struct device *dev)
 		return ret;
 
 	ret = spi_master_resume(master);
-	if (ret)
+	if (ret) {
 		clk_disable_unprepare(spi->clk);
+		return ret;
+	}
 
-	return ret;
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Unable to power device:%d\n", ret);
+		return ret;
+	}
+
+	spi->cfg->config(spi);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return 0;
 }
 #endif
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 6626587e77b4..0cab239d8e7f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -475,6 +475,12 @@ static LIST_HEAD(spi_controller_list);
  */
 static DEFINE_MUTEX(board_lock);
 
+/*
+ * Prevents addition of devices with same chip select and
+ * addition of devices below an unregistering controller.
+ */
+static DEFINE_MUTEX(spi_add_lock);
+
 /**
  * spi_alloc_device - Allocate a new SPI device
  * @ctlr: Controller to which device is connected
@@ -554,7 +560,6 @@ static int spi_dev_check(struct device *dev, void *data)
  */
 int spi_add_device(struct spi_device *spi)
 {
-	static DEFINE_MUTEX(spi_add_lock);
 	struct spi_controller *ctlr = spi->controller;
 	struct device *dev = ctlr->dev.parent;
 	int status;
@@ -582,6 +587,13 @@ int spi_add_device(struct spi_device *spi)
 		goto done;
 	}
 
+	/* Controller may unregister concurrently */
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC) &&
+	    !device_is_registered(&ctlr->dev)) {
+		status = -ENODEV;
+		goto done;
+	}
+
 	/* Descriptors take precedence */
 	if (ctlr->cs_gpiods)
 		spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select];
@@ -1315,8 +1327,6 @@ out:
 	if (msg->status && ctlr->handle_err)
 		ctlr->handle_err(ctlr, msg);
 
-	spi_res_release(ctlr, msg);
-
 	spi_finalize_current_message(ctlr);
 
 	return ret;
@@ -1713,6 +1723,13 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 
 	spi_unmap_msg(ctlr, mesg);
 
+	/* In the prepare_messages callback the spi bus has the opportunity to
+	 * split a transfer to smaller chunks.
+	 * Release splited transfers here since spi_map_msg is done on the
+	 * splited transfers.
+	 */
+	spi_res_release(ctlr, mesg);
+
 	if (ctlr->cur_msg_prepared && ctlr->unprepare_message) {
 		ret = ctlr->unprepare_message(ctlr, mesg);
 		if (ret) {
@@ -2795,6 +2812,10 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	struct spi_controller *found;
 	int id = ctlr->bus_num;
 
+	/* Prevent addition of new devices, unregister existing ones */
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
+		mutex_lock(&spi_add_lock);
+
 	device_for_each_child(&ctlr->dev, NULL, __unregister);
 
 	/* First make sure that this controller was ever added */
@@ -2815,6 +2836,9 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	if (found == ctlr)
 		idr_remove(&spi_master_idr, id);
 	mutex_unlock(&board_lock);
+
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
+		mutex_unlock(&spi_add_lock);
 }
 EXPORT_SYMBOL_GPL(spi_unregister_controller);
 
diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 823dc99be46f..a8d2525e7af9 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -425,7 +425,7 @@ void ssb_chipco_get_clockcontrol(struct ssb_chipcommon *cc,
 			*m = chipco_read32(cc, SSB_CHIPCO_CLOCK_M2);
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		*m = chipco_read32(cc, SSB_CHIPCO_CLOCK_SB);
 	}
diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index 1ca2ac5ef2b8..354486b7ed3a 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -342,7 +342,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 				set_irq(dev, irq++);
 				break;
 			}
-			/* fallthrough */
+			fallthrough;
 		case SSB_DEV_EXTIF:
 			set_irq(dev, 0);
 			break;
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index b97a5c32d44a..f49ab1aa2149 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -228,7 +228,7 @@ static void __iomem *ssb_ioremap(struct ssb_bus *bus,
 	switch (bus->bustype) {
 	case SSB_BUSTYPE_SSB:
 		/* Only map the first core for now. */
-		/* fallthrough... */
+		fallthrough;
 	case SSB_BUSTYPE_PCMCIA:
 		mmio = ioremap(baseaddr, SSB_CORE_SIZE);
 		break;
diff --git a/drivers/staging/greybus/audio_helper.c b/drivers/staging/greybus/audio_helper.c
index 8b100a71f02e..237531ba60f3 100644
--- a/drivers/staging/greybus/audio_helper.c
+++ b/drivers/staging/greybus/audio_helper.c
@@ -173,8 +173,7 @@ static int gbaudio_remove_controls(struct snd_card *card, struct device *dev,
 		id.index = control->index;
 		kctl = snd_ctl_find_id(card, &id);
 		if (!kctl) {
-			dev_err(dev, "%d: Failed to find %s\n", err,
-				control->name);
+			dev_err(dev, "Failed to find %s\n", control->name);
 			continue;
 		}
 		err = snd_ctl_remove(card, kctl);
diff --git a/drivers/staging/greybus/audio_topology.c b/drivers/staging/greybus/audio_topology.c
index 2f9fdbdcd547..83b38ae8908c 100644
--- a/drivers/staging/greybus/audio_topology.c
+++ b/drivers/staging/greybus/audio_topology.c
@@ -456,6 +456,15 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 	val = ucontrol->value.integer.value[0] & mask;
 	connect = !!val;
 
+	ret = gb_pm_runtime_get_sync(bundle);
+	if (ret)
+		return ret;
+
+	ret = gb_audio_gb_get_control(module->mgmt_connection, data->ctl_id,
+				      GB_AUDIO_INVALID_INDEX, &gbvalue);
+	if (ret)
+		goto exit;
+
 	/* update ucontrol */
 	if (gbvalue.value.integer_value[0] != val) {
 		for (wi = 0; wi < wlist->num_widgets; wi++) {
@@ -466,25 +475,17 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 		gbvalue.value.integer_value[0] =
 			cpu_to_le32(ucontrol->value.integer.value[0]);
 
-		ret = gb_pm_runtime_get_sync(bundle);
-		if (ret)
-			return ret;
-
 		ret = gb_audio_gb_set_control(module->mgmt_connection,
 					      data->ctl_id,
 					      GB_AUDIO_INVALID_INDEX, &gbvalue);
-
-		gb_pm_runtime_put_autosuspend(bundle);
-
-		if (ret) {
-			dev_err_ratelimited(codec_dev,
-					    "%d:Error in %s for %s\n", ret,
-					    __func__, kcontrol->id.name);
-			return ret;
-		}
 	}
 
-	return 0;
+exit:
+	gb_pm_runtime_put_autosuspend(bundle);
+	if (ret)
+		dev_err_ratelimited(codec_dev, "%d:Error in %s for %s\n", ret,
+				    __func__, kcontrol->id.name);
+	return ret;
 }
 
 #define SOC_DAPM_MIXER_GB(xname, kcount, data) \
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index 8ea65bef35d2..a4e4eef55f35 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -4984,7 +4984,7 @@ enum mipi_port_id __get_mipi_port(struct atomisp_device *isp,
 		if (MIPI_PORT1_ID + 1 != N_MIPI_PORT_ID) {
 			return MIPI_PORT1_ID + 1;
 		}
-	/* fall through */
+		fallthrough;
 	default:
 		dev_err(isp->dev, "unsupported port: %d\n", port);
 		return MIPI_PORT0_ID;
diff --git a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c
index cccc5bfa1057..1b2b2c68025b 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c
@@ -704,14 +704,14 @@ static bool is_pipe_valid_to_current_run_mode(struct atomisp_sub_device *asd,
 
 			return false;
 		}
-	/* fall-through */
+		fallthrough;
 	case ATOMISP_RUN_MODE_CONTINUOUS_CAPTURE:
 		if (pipe_id == IA_CSS_PIPE_ID_CAPTURE ||
 		    pipe_id == IA_CSS_PIPE_ID_PREVIEW)
 			return true;
 
 		return false;
-	/* fall-through */
+		fallthrough;
 	case ATOMISP_RUN_MODE_VIDEO:
 		if (!asd->continuous_mode->val) {
 			if (pipe_id == IA_CSS_PIPE_ID_VIDEO ||
@@ -720,7 +720,7 @@ static bool is_pipe_valid_to_current_run_mode(struct atomisp_sub_device *asd,
 			else
 				return false;
 		}
-	/* fall through  */
+		fallthrough;
 	case ATOMISP_RUN_MODE_SDV:
 		if (pipe_id == IA_CSS_PIPE_ID_CAPTURE ||
 		    pipe_id == IA_CSS_PIPE_ID_VIDEO)
@@ -2765,7 +2765,7 @@ static unsigned int atomisp_get_pipe_index(struct atomisp_sub_device *asd,
 		if (!atomisp_is_mbuscode_raw(asd->fmt[asd->capture_pad].fmt.code)) {
 			return IA_CSS_PIPE_ID_CAPTURE;
 		}
-		/* fall through */
+		fallthrough;
 	case ATOMISP_SUBDEV_PAD_SOURCE_PREVIEW:
 		if (asd->yuvpp_mode)
 			return IA_CSS_PIPE_ID_YUVPP;
diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
index f8d616f08b51..65b0c8a662a0 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
@@ -1467,7 +1467,6 @@ enum ia_css_pipe_id atomisp_get_css_pipe_id(struct atomisp_sub_device *asd)
 	case ATOMISP_RUN_MODE_VIDEO:
 		return IA_CSS_PIPE_ID_VIDEO;
 	case ATOMISP_RUN_MODE_STILL_CAPTURE:
-	/* fall through */
 	default:
 		return IA_CSS_PIPE_ID_CAPTURE;
 	}
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index a000a1e316f7..0114b040247b 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -1086,7 +1086,7 @@ static int atomisp_subdev_probe(struct atomisp_device *isp)
 		case RAW_CAMERA:
 			dev_dbg(isp->dev, "raw_index: %d\n", raw_index);
 			raw_index = isp->input_cnt;
-			/* fall through */
+			fallthrough;
 		case SOC_CAMERA:
 			dev_dbg(isp->dev, "SOC_INDEX: %d\n", isp->input_cnt);
 			if (isp->input_cnt >= ATOM_ISP_MAX_INPUTS) {
diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
index 4fb9bfdd2f4c..f13af2329f48 100644
--- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
+++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
@@ -660,7 +660,7 @@ static void free_private_bo_pages(struct hmm_buffer_object *bo,
 				break;
 			}
 
-			/* fall through */
+			fallthrough;
 
 		/*
 		 * if dynamic memory pool doesn't exist, need to free
diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c
index 54434c2dbaf9..a68cbb4995f0 100644
--- a/drivers/staging/media/atomisp/pci/sh_css.c
+++ b/drivers/staging/media/atomisp/pci/sh_css.c
@@ -4510,7 +4510,7 @@ ia_css_pipe_dequeue_buffer(struct ia_css_pipe *pipe,
 #endif
 					pipe->stop_requested = false;
 				}
-				/* fall through */
+				fallthrough;
 			case IA_CSS_BUFFER_TYPE_VF_OUTPUT_FRAME:
 			case IA_CSS_BUFFER_TYPE_SEC_VF_OUTPUT_FRAME:
 				frame = (struct ia_css_frame *)HOST_ADDRESS(ddr_buffer.kernel_ptr);
diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
index 24041849384a..6386a3989bfe 100644
--- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
@@ -110,7 +110,7 @@ hantro_g1_mpeg2_dec_set_buffers(struct hantro_dev *vpu, struct hantro_ctx *ctx,
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_B:
 		backward_addr = hantro_get_ref(ctx,
 					       slice_params->backward_ref_ts);
-		/* fall-through */
+		fallthrough;
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_P:
 		forward_addr = hantro_get_ref(ctx,
 					      slice_params->forward_ref_ts);
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
index 7e9aad671489..f610fa5b4335 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
@@ -112,7 +112,7 @@ rk3399_vpu_mpeg2_dec_set_buffers(struct hantro_dev *vpu,
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_B:
 		backward_addr = hantro_get_ref(ctx,
 					       slice_params->backward_ref_ts);
-		/* fall-through */
+		fallthrough;
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_P:
 		forward_addr = hantro_get_ref(ctx,
 					      slice_params->forward_ref_ts);
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index d92fd804488e..21ebf7769696 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -488,7 +488,7 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 			passthrough_cycles = incc->cycles;
 			break;
 		}
-		/* fallthrough - non-passthrough RGB565 (CSI-2 bus) */
+		fallthrough;	/* non-passthrough RGB565 (CSI-2 bus) */
 	default:
 		burst_size = (image.pix.width & 0xf) ? 8 : 16;
 		passthrough_bits = 16;
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c
index bc27f9430eeb..7c6b91f0e780 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.c
@@ -199,6 +199,7 @@ static int cedrus_request_validate(struct media_request *req)
 	struct v4l2_ctrl *ctrl_test;
 	unsigned int count;
 	unsigned int i;
+	int ret = 0;
 
 	list_for_each_entry(obj, &req->objects, list) {
 		struct vb2_buffer *vb;
@@ -243,12 +244,16 @@ static int cedrus_request_validate(struct media_request *req)
 		if (!ctrl_test) {
 			v4l2_info(&ctx->dev->v4l2_dev,
 				  "Missing required codec control\n");
-			return -ENOENT;
+			ret = -ENOENT;
+			break;
 		}
 	}
 
 	v4l2_ctrl_request_hdl_put(hdl);
 
+	if (ret)
+		return ret;
+
 	return vb2_request_validate(req);
 }
 
diff --git a/drivers/staging/media/usbvision/usbvision-i2c.c b/drivers/staging/media/usbvision/usbvision-i2c.c
index 6e4df3335b1b..aa3ff67a3cb1 100644
--- a/drivers/staging/media/usbvision/usbvision-i2c.c
+++ b/drivers/staging/media/usbvision/usbvision-i2c.c
@@ -303,13 +303,13 @@ usbvision_i2c_read_max4(struct usb_usbvision *usbvision, unsigned char addr,
 	switch (len) {
 	case 4:
 		buf[3] = usbvision_read_reg(usbvision, USBVISION_SER_DAT4);
-		/* fall through */
+		fallthrough;
 	case 3:
 		buf[2] = usbvision_read_reg(usbvision, USBVISION_SER_DAT3);
-		/* fall through */
+		fallthrough;
 	case 2:
 		buf[1] = usbvision_read_reg(usbvision, USBVISION_SER_DAT2);
-		/* fall through */
+		fallthrough;
 	case 1:
 		buf[0] = usbvision_read_reg(usbvision, USBVISION_SER_DAT1);
 		break;
diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c
index fa1bf8b069fd..2720f7319a3d 100644
--- a/drivers/staging/wlan-ng/hfa384x_usb.c
+++ b/drivers/staging/wlan-ng/hfa384x_usb.c
@@ -524,13 +524,8 @@ static void hfa384x_usb_defer(struct work_struct *data)
  */
 void hfa384x_create(struct hfa384x *hw, struct usb_device *usb)
 {
-	memset(hw, 0, sizeof(*hw));
 	hw->usb = usb;
 
-	/* set up the endpoints */
-	hw->endp_in = usb_rcvbulkpipe(usb, 1);
-	hw->endp_out = usb_sndbulkpipe(usb, 2);
-
 	/* Set up the waitq */
 	init_waitqueue_head(&hw->cmdq);
 
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index 456603fd26c0..4b08dc1da4f9 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -61,23 +61,14 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 			       const struct usb_device_id *id)
 {
 	struct usb_device *dev;
-	const struct usb_endpoint_descriptor *epd;
-	const struct usb_host_interface *iface_desc = interface->cur_altsetting;
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct wlandevice *wlandev = NULL;
 	struct hfa384x *hw = NULL;
 	int result = 0;
 
-	if (iface_desc->desc.bNumEndpoints != 2) {
-		result = -ENODEV;
-		goto failed;
-	}
-
-	result = -EINVAL;
-	epd = &iface_desc->endpoint[1].desc;
-	if (!usb_endpoint_is_bulk_in(epd))
-		goto failed;
-	epd = &iface_desc->endpoint[2].desc;
-	if (!usb_endpoint_is_bulk_out(epd))
+	result = usb_find_common_endpoints(iface_desc, &bulk_in, &bulk_out, NULL, NULL);
+	if (result)
 		goto failed;
 
 	dev = interface_to_usbdev(interface);
@@ -96,6 +87,8 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 	}
 
 	/* Initialize the hw data */
+	hw->endp_in = usb_rcvbulkpipe(dev, bulk_in->bEndpointAddress);
+	hw->endp_out = usb_sndbulkpipe(dev, bulk_out->bEndpointAddress);
 	hfa384x_create(hw, dev);
 	hw->wlandev = wlandev;
 
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c
index 30ea37e1a3f5..bd37f2afadea 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_main.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c
@@ -444,7 +444,7 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
 	case CPL_RX_ISCSI_DDP:
 	case CPL_FW4_ACK:
 		lro_flush = false;
-		/* fall through */
+		fallthrough;
 	case CPL_ABORT_RPL_RSS:
 	case CPL_PASS_ESTABLISH:
 	case CPL_PEER_CLOSE:
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index c9689610e186..7b56fe9f1062 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1389,14 +1389,27 @@ static u32 iscsit_do_crypto_hash_sg(
 	sg = cmd->first_data_sg;
 	page_off = cmd->first_data_sg_off;
 
+	if (data_length && page_off) {
+		struct scatterlist first_sg;
+		u32 len = min_t(u32, data_length, sg->length - page_off);
+
+		sg_init_table(&first_sg, 1);
+		sg_set_page(&first_sg, sg_page(sg), len, sg->offset + page_off);
+
+		ahash_request_set_crypt(hash, &first_sg, NULL, len);
+		crypto_ahash_update(hash);
+
+		data_length -= len;
+		sg = sg_next(sg);
+	}
+
 	while (data_length) {
-		u32 cur_len = min_t(u32, data_length, (sg->length - page_off));
+		u32 cur_len = min_t(u32, data_length, sg->length);
 
 		ahash_request_set_crypt(hash, sg, NULL, cur_len);
 		crypto_ahash_update(hash);
 
 		data_length -= cur_len;
-		page_off = 0;
 		/* iscsit_map_iovec has already checked for invalid sg pointers */
 		sg = sg_next(sg);
 	}
@@ -3740,7 +3753,7 @@ check_rsp_state:
 	case ISTATE_SEND_LOGOUTRSP:
 		if (!iscsit_logout_post_handler(cmd, conn))
 			return -ECONNRESET;
-		/* fall through */
+		fallthrough;
 	case ISTATE_SEND_STATUS:
 	case ISTATE_SEND_ASYNCMSG:
 	case ISTATE_SEND_NOPIN:
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 85748e338858..893d1b406c29 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1149,7 +1149,7 @@ void iscsit_free_conn(struct iscsi_conn *conn)
 }
 
 void iscsi_target_login_sess_out(struct iscsi_conn *conn,
-		struct iscsi_np *np, bool zero_tsih, bool new_sess)
+				 bool zero_tsih, bool new_sess)
 {
 	if (!new_sess)
 		goto old_sess_out;
@@ -1167,7 +1167,6 @@ void iscsi_target_login_sess_out(struct iscsi_conn *conn,
 	conn->sess = NULL;
 
 old_sess_out:
-	iscsi_stop_login_thread_timer(np);
 	/*
 	 * If login negotiation fails check if the Time2Retain timer
 	 * needs to be restarted.
@@ -1407,8 +1406,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 new_sess_out:
 	new_sess = true;
 old_sess_out:
+	iscsi_stop_login_thread_timer(np);
 	tpg_np = conn->tpg_np;
-	iscsi_target_login_sess_out(conn, np, zero_tsih, new_sess);
+	iscsi_target_login_sess_out(conn, zero_tsih, new_sess);
 	new_sess = false;
 
 	if (tpg) {
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 3b8e3639ff5d..fc95e6150253 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -22,8 +22,7 @@ extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_conn *);
 extern int iscsit_start_kthreads(struct iscsi_conn *);
 extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
-extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
-				bool, bool);
+extern void iscsi_target_login_sess_out(struct iscsi_conn *, bool, bool);
 extern int iscsi_target_login_thread(void *);
 extern void iscsi_handle_login_thread_timeout(struct timer_list *t);
 
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index f88a52fec889..8b40f10976ff 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -535,12 +535,11 @@ static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned in
 
 static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
 {
-	struct iscsi_np *np = login->np;
 	bool zero_tsih = login->zero_tsih;
 
 	iscsi_remove_failed_auth_entry(conn);
 	iscsi_target_nego_release(conn);
-	iscsi_target_login_sess_out(conn, np, zero_tsih, true);
+	iscsi_target_login_sess_out(conn, zero_tsih, true);
 }
 
 struct conn_timeout {
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 8fc88654bff6..5f79ea05f9b8 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -345,7 +345,7 @@ static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type,
 		break;
 	case PR_TYPE_WRITE_EXCLUSIVE_REGONLY:
 		we = 1;
-		/* fall through */
+		fallthrough;
 	case PR_TYPE_EXCLUSIVE_ACCESS_REGONLY:
 		/*
 		 * Some commands are only allowed for registered I_T Nexuses.
@@ -354,7 +354,7 @@ static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type,
 		break;
 	case PR_TYPE_WRITE_EXCLUSIVE_ALLREG:
 		we = 1;
-		/* fall through */
+		fallthrough;
 	case PR_TYPE_EXCLUSIVE_ACCESS_ALLREG:
 		/*
 		 * Each registered I_T Nexus is a reservation holder.
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index f1e81886122d..6e8b8d30938f 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -734,7 +734,7 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
 		}
 		if (!protect)
 			return TCM_NO_SENSE;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		pr_err("Unable to determine pi_prot_type for CDB: 0x%02x "
 		       "PROTECT: 0x%02x\n", cdb[0], protect);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9fb0be0aa620..590eac2df909 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2236,7 +2236,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
 			ret = cmd->se_tfo->queue_data_in(cmd);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case DMA_NONE:
 queue_status:
 		trace_target_cmd_complete(cmd);
@@ -2431,7 +2431,7 @@ queue_rsp:
 				goto queue_full;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case DMA_NONE:
 queue_status:
 		trace_target_cmd_complete(cmd);
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index e9f0dda5ff92..a7ed56602c6c 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -537,7 +537,7 @@ static void ft_send_work(struct work_struct *work)
 	case FCP_PTA_ACA:
 		task_attr = TCM_ACA_TAG;
 		break;
-	case FCP_PTA_SIMPLE: /* Fallthrough */
+	case FCP_PTA_SIMPLE:
 	default:
 		task_attr = TCM_SIMPLE_TAG;
 	}
diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
index bf7bae42c141..6dc879fea9c8 100644
--- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2011-2015, 2017, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2011-2015, 2017, 2020, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/bitops.h>
@@ -191,7 +191,7 @@ static int qpnp_tm_get_temp(void *data, int *temp)
 		chip->temp = mili_celsius;
 	}
 
-	*temp = chip->temp < 0 ? 0 : chip->temp;
+	*temp = chip->temp;
 
 	return 0;
 }
diff --git a/drivers/thermal/qcom/tsens-v0_1.c b/drivers/thermal/qcom/tsens-v0_1.c
index e64db5f80d90..4ffa2e2c0145 100644
--- a/drivers/thermal/qcom/tsens-v0_1.c
+++ b/drivers/thermal/qcom/tsens-v0_1.c
@@ -220,7 +220,7 @@ static int calibrate_8916(struct tsens_priv *priv)
 		p2[4] = (qfprom_cdata[1] & MSM8916_S4_P2_MASK) >> MSM8916_S4_P2_SHIFT;
 		for (i = 0; i < priv->num_sensors; i++)
 			p2[i] = ((base1 + p2[i]) << 3);
-		/* Fall through */
+		fallthrough;
 	case ONE_PT_CALIB2:
 		base0 = (qfprom_cdata[0] & MSM8916_BASE0_MASK);
 		p1[0] = (qfprom_cdata[0] & MSM8916_S0_P1_MASK) >> MSM8916_S0_P1_SHIFT;
@@ -355,7 +355,7 @@ static int calibrate_8974(struct tsens_priv *priv)
 			p2[8] = (calib[5] & S8_P2_BKP_MASK) >> S8_P2_BKP_SHIFT;
 			p2[9] = (calib[5] & S9_P2_BKP_MASK) >> S9_P2_BKP_SHIFT;
 			p2[10] = (calib[5] & S10_P2_BKP_MASK) >> S10_P2_BKP_SHIFT;
-			/* Fall through */
+			fallthrough;
 		case ONE_PT_CALIB:
 		case ONE_PT_CALIB2:
 			base1 = bkp[0] & BASE1_MASK;
@@ -390,7 +390,7 @@ static int calibrate_8974(struct tsens_priv *priv)
 			p2[8] = (calib[4] & S8_P2_MASK) >> S8_P2_SHIFT;
 			p2[9] = (calib[4] & S9_P2_MASK) >> S9_P2_SHIFT;
 			p2[10] = (calib[4] & S10_P2_MASK) >> S10_P2_SHIFT;
-			/* Fall through */
+			fallthrough;
 		case ONE_PT_CALIB:
 		case ONE_PT_CALIB2:
 			base1 = calib[0] & BASE1_MASK;
@@ -420,7 +420,7 @@ static int calibrate_8974(struct tsens_priv *priv)
 			p2[i] <<= 2;
 			p2[i] |= BIT_APPEND;
 		}
-		/* Fall through */
+		fallthrough;
 	case ONE_PT_CALIB2:
 		for (i = 0; i < priv->num_sensors; i++) {
 			p1[i] += base1;
diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c
index b682a4df0081..3c19a3800c6d 100644
--- a/drivers/thermal/qcom/tsens-v1.c
+++ b/drivers/thermal/qcom/tsens-v1.c
@@ -202,7 +202,7 @@ static int calibrate_v1(struct tsens_priv *priv)
 		p2[9] = (qfprom_cdata[3] & S9_P2_MASK) >> S9_P2_SHIFT;
 		for (i = 0; i < priv->num_sensors; i++)
 			p2[i] = ((base1 + p2[i]) << 2);
-		/* Fall through */
+		fallthrough;
 	case ONE_PT_CALIB2:
 		base0 = (qfprom_cdata[4] & BASE0_MASK) >> BASE0_SHIFT;
 		p1[0] = (qfprom_cdata[0] & S0_P1_MASK) >> S0_P1_SHIFT;
@@ -263,7 +263,7 @@ static int calibrate_8976(struct tsens_priv *priv)
 
 		for (i = 0; i < priv->num_sensors; i++)
 			p2[i] = ((base1 + p2[i]) << 2);
-		/* Fall through */
+		fallthrough;
 	case ONE_PT_CALIB2:
 		base0 = qfprom_cdata[0] & MSM8976_BASE0_MASK;
 		p1[0] = (qfprom_cdata[0] & MSM8976_S0_P1_MASK) >> MSM8976_S0_P1_SHIFT;
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 72bf159bcecc..a6616e530a84 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1516,7 +1516,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_device_register);
  */
 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 {
-	int i;
+	int i, tz_id;
 	const struct thermal_zone_params *tzp;
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos = NULL;
@@ -1525,6 +1525,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 		return;
 
 	tzp = tz->tzp;
+	tz_id = tz->id;
 
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
@@ -1567,7 +1568,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	mutex_destroy(&tz->lock);
 	device_unregister(&tz->device);
 
-	thermal_notify_tz_delete(tz->id);
+	thermal_notify_tz_delete(tz_id);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
 
diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
index 63b02bfb2adf..fdb8a495ab69 100644
--- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
@@ -37,20 +37,21 @@ static struct temp_sensor_data omap4430_mpu_temp_sensor_data = {
 
 /*
  * Temperature values in milli degree celsius
- * ADC code values from 530 to 923
+ * ADC code values from 13 to 107, see TRM
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
  */
 static const int
 omap4430_adc_to_temp[OMAP4430_ADC_END_VALUE - OMAP4430_ADC_START_VALUE + 1] = {
-	-38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, -22000,
-	-20000, -18000, -17000, -15000, -13000, -12000, -10000, -8000, -6000,
-	-5000, -3000, -1000, 0, 2000, 3000, 5000, 6000, 8000, 10000, 12000,
-	13000, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28000, 30000,
-	32000, 33000, 35000, 37000, 38000, 40000, 42000, 43000, 45000, 47000,
-	48000, 50000, 52000, 53000, 55000, 57000, 58000, 60000, 62000, 64000,
-	66000, 68000, 70000, 71000, 73000, 75000, 77000, 78000, 80000, 82000,
-	83000, 85000, 87000, 88000, 90000, 92000, 93000, 95000, 97000, 98000,
-	100000, 102000, 103000, 105000, 107000, 109000, 111000, 113000, 115000,
-	117000, 118000, 120000, 122000, 123000,
+	-40000, -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000,
+	-22000,	-20000, -18500, -17000, -15000, -13500, -12000, -10000, -8000,
+	-6500, -5000, -3500, -1500, 0, 2000, 3500, 5000, 6500, 8500, 10000,
+	12000, 13500, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28500,
+	30000, 32000, 33500, 35000, 37000, 38500, 40000, 42000, 43500, 45000,
+	47000, 48500, 50000, 52000, 53500, 55000, 57000, 58500, 60000, 62000,
+	64000, 66000, 68000, 70000, 71500, 73500, 75000, 77000, 78500, 80000,
+	82000, 83500, 85000, 87000, 88500, 90000, 92000, 93500, 95000, 97000,
+	98500, 100000, 102000, 103500, 105000, 107000, 109000, 111000, 113000,
+	115000, 117000, 118500, 120000, 122000, 123500, 125000,
 };
 
 /* OMAP4430 data */
diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
index a453ff8eb313..9a3955c3853b 100644
--- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
@@ -53,9 +53,13 @@
  * and thresholds for OMAP4430.
  */
 
-/* ADC conversion table limits */
-#define OMAP4430_ADC_START_VALUE			0
-#define OMAP4430_ADC_END_VALUE				127
+/*
+ * ADC conversion table limits. Ignore values outside the TRM listed
+ * range to avoid bogus thermal shutdowns. See omap4430 TRM chapter
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
+ */
+#define OMAP4430_ADC_START_VALUE			13
+#define OMAP4430_ADC_END_VALUE				107
 /* bandgap clock limits (no control on 4430) */
 #define OMAP4430_MAX_FREQ				32768
 #define OMAP4430_MIN_FREQ				32768
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index f77ceae5c7d7..394a23ce6ca4 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -453,7 +453,7 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame,
 				   "RX: checksum mismatch, dropping packet\n");
 			goto rx;
 		}
-		/* Fall through */
+		fallthrough;
 	case TB_CFG_PKG_ICM_EVENT:
 		if (tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size))
 			goto rx;
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 712395f518b8..a921de9ce7cb 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -684,6 +684,7 @@ static int tb_init_port(struct tb_port *port)
 		if (res == -ENODEV) {
 			tb_dbg(port->sw->tb, " Port %d: not implemented\n",
 			       port->port);
+			port->disabled = true;
 			return 0;
 		}
 		return res;
@@ -2092,7 +2093,7 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 		if (tb_route(sw))
 			return 0;
 
-		/* fallthrough */
+		fallthrough;
 	case 3:
 		ret = tb_switch_set_uuid(sw);
 		if (ret)
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index a413d55b5f8b..3c620a9203c5 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -186,7 +186,7 @@ struct tb_switch {
  * @cap_adap: Offset of the adapter specific capability (%0 if not present)
  * @cap_usb4: Offset to the USB4 port capability (%0 if not present)
  * @port: Port number on switch
- * @disabled: Disabled by eeprom
+ * @disabled: Disabled by eeprom or enabled but not implemented
  * @bonded: true if the port is bonded (two lanes combined as one)
  * @dual_link_port: If the switch is connected using two ports, points
  *		    to the other port.
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 2aae2c76d880..829b6ccdd5d4 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -315,7 +315,7 @@ static inline u32 tb_dp_cap_set_rate(u32 val, u32 rate)
 	switch (rate) {
 	default:
 		WARN(1, "invalid rate %u passed, defaulting to 1620 MB/s\n", rate);
-		/* Fallthrough */
+		fallthrough;
 	case 1620:
 		val |= DP_COMMON_CAP_RATE_RBR << DP_COMMON_CAP_RATE_SHIFT;
 		break;
@@ -355,7 +355,7 @@ static inline u32 tb_dp_cap_set_lanes(u32 val, u32 lanes)
 	default:
 		WARN(1, "invalid number of lanes %u passed, defaulting to 1\n",
 		     lanes);
-		/* Fallthrough */
+		fallthrough;
 	case 1:
 		val |= DP_COMMON_CAP_1_LANE << DP_COMMON_CAP_LANES_SHIFT;
 		break;
@@ -951,10 +951,18 @@ static void tb_usb3_reclaim_available_bandwidth(struct tb_tunnel *tunnel,
 	int ret, max_rate, allocate_up, allocate_down;
 
 	ret = usb4_usb3_port_actual_link_rate(tunnel->src_port);
-	if (ret <= 0) {
-		tb_tunnel_warn(tunnel, "tunnel is not up\n");
+	if (ret < 0) {
+		tb_tunnel_warn(tunnel, "failed to read actual link rate\n");
 		return;
+	} else if (!ret) {
+		/* Use maximum link rate if the link valid is not set */
+		ret = usb4_usb3_port_max_link_rate(tunnel->src_port);
+		if (ret < 0) {
+			tb_tunnel_warn(tunnel, "failed to read maximum link rate\n");
+			return;
+		}
 	}
+
 	/*
 	 * 90% of the max rate can be allocated for isochronous
 	 * transfers.
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 2a0e51a20e34..92c9a476defc 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -492,7 +492,7 @@ static void xencons_backend_changed(struct xenbus_device *dev,
 	case XenbusStateClosed:
 		if (dev->state == XenbusStateClosed)
 			break;
-		/* fall through - Missed the backend's CLOSING state. */
+		fallthrough;	/* Missed the backend's CLOSING state */
 	case XenbusStateClosing:
 		xenbus_frontend_closed(dev);
 		break;
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index 21e76a2ec182..a8e19b4833bf 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -243,7 +243,7 @@ done:
 		/* Fall back to a 3 byte encoding */
 		word.bytes = 3;
 		word.word &= 0x00ffffff;
-		/* Fall through */
+		fallthrough;
 	case 3:
 		/* 3 byte encoding */
 		word.word |= 0x82000000;
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 0a29a94ec438..35cf12147e39 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1584,7 +1584,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen)
 			gsm_process_modem(tty, dlci, modem, clen);
 			tty_kref_put(tty);
 		}
-		/* Fall through */
+		fallthrough;
 	case 1:		/* Line state will go via DLCI 0 controls only */
 	default:
 		tty_insert_flip_string(port, data, len);
@@ -1986,7 +1986,7 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c)
 		gsm->address = 0;
 		gsm->state = GSM_ADDRESS;
 		gsm->fcs = INIT_FCS;
-		/* Fall through */
+		fallthrough;
 	case GSM_ADDRESS:	/* Address continuation */
 		gsm->fcs = gsm_fcs_add(gsm->fcs, c);
 		if (gsm_read_ea(&gsm->address, c))
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index b09eac4b6d64..8e975cb29833 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -602,7 +602,7 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		case TCOFLUSH:
 			flush_tx_queue(tty);
 		}
-		/* fall through - to default */
+		fallthrough;	/* to default */
 
 	default:
 		error = n_tty_ioctl_helper(tty, file, cmd, arg);
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index f75696f0ee2d..934dd2fb2ec8 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -605,7 +605,6 @@ static void receive_char(struct r3964_info *pInfo, const unsigned char c)
 		}
 		break;
 	case R3964_WAIT_FOR_RX_REPEAT:
-		/* FALLTHROUGH */
 	case R3964_IDLE:
 		if (c == STX) {
 			/* Prevent rx_queue from overflow: */
diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c
index db88dee3a399..f8e99995eee9 100644
--- a/drivers/tty/serial/8250/8250_em.c
+++ b/drivers/tty/serial/8250/8250_em.c
@@ -39,7 +39,7 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value)
 		break;
 	case UART_IER: /* IER @ 0x04 */
 		value &= 0x0f; /* only 4 valid bits - not Xscale */
-		/* fall-through */
+		fallthrough;
 	case UART_DLL_EM: /* DLL @ 0x24 (+9) */
 	case UART_DLM_EM: /* DLM @ 0x28 (+9) */
 		writel(value, p->membase + (offset << 2));
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index 04b9af7ed941..2d0e7c7e408d 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -744,6 +744,24 @@ static const struct exar8250_board pbn_exar_XR17V35x = {
 	.exit		= pci_xr17v35x_exit,
 };
 
+static const struct exar8250_board pbn_fastcom35x_2 = {
+	.num_ports	= 2,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
+static const struct exar8250_board pbn_fastcom35x_4 = {
+	.num_ports	= 4,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
+static const struct exar8250_board pbn_fastcom35x_8 = {
+	.num_ports	= 8,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
 static const struct exar8250_board pbn_exar_XR17V4358 = {
 	.num_ports	= 12,
 	.setup		= pci_xr17v35x_setup,
@@ -811,9 +829,9 @@ static const struct pci_device_id exar_pci_tbl[] = {
 	EXAR_DEVICE(EXAR, XR17V358, pbn_exar_XR17V35x),
 	EXAR_DEVICE(EXAR, XR17V4358, pbn_exar_XR17V4358),
 	EXAR_DEVICE(EXAR, XR17V8358, pbn_exar_XR17V8358),
-	EXAR_DEVICE(COMMTECH, 4222PCIE, pbn_exar_XR17V35x),
-	EXAR_DEVICE(COMMTECH, 4224PCIE, pbn_exar_XR17V35x),
-	EXAR_DEVICE(COMMTECH, 4228PCIE, pbn_exar_XR17V35x),
+	EXAR_DEVICE(COMMTECH, 4222PCIE, pbn_fastcom35x_2),
+	EXAR_DEVICE(COMMTECH, 4224PCIE, pbn_fastcom35x_4),
+	EXAR_DEVICE(COMMTECH, 4228PCIE, pbn_fastcom35x_8),
 
 	EXAR_DEVICE(COMMTECH, 4222PCI335, pbn_fastcom335_2),
 	EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4),
diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c
index d1d253c4b518..31c9e83ea3cb 100644
--- a/drivers/tty/serial/8250/8250_fintek.c
+++ b/drivers/tty/serial/8250/8250_fintek.c
@@ -255,7 +255,7 @@ static void fintek_8250_set_irq_mode(struct fintek_8250 *pdata, bool is_level)
 	case CHIP_ID_F81866:
 		sio_write_mask_reg(pdata, F81866_FIFO_CTRL, F81866_IRQ_MODE1,
 				   0);
-		/* fall through */
+		fallthrough;
 	case CHIP_ID_F81865:
 		sio_write_mask_reg(pdata, F81866_IRQ_MODE, F81866_IRQ_SHARE,
 				   F81866_IRQ_SHARE);
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 1a74d511b02a..3eb2d485eaeb 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -631,7 +631,7 @@ pci_timedia_setup(struct serial_private *priv,
 		break;
 	case 3:
 		offset = board->uart_offset;
-		/* FALLTHROUGH */
+		fallthrough;
 	case 4: /* BAR 2 */
 	case 5: /* BAR 3 */
 	case 6: /* BAR 4 */
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 09475695effd..c71d647eb87a 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1872,7 +1872,7 @@ static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir)
 	switch (iir & 0x3f) {
 	case UART_IIR_RX_TIMEOUT:
 		serial8250_rx_dma_flush(up);
-		/* fall-through */
+		fallthrough;
 	case UART_IIR_RLSI:
 		return true;
 	}
@@ -2275,6 +2275,10 @@ int serial8250_do_startup(struct uart_port *port)
 
 	if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) {
 		unsigned char iir1;
+
+		if (port->irqflags & IRQF_SHARED)
+			disable_irq_nosync(port->irq);
+
 		/*
 		 * Test for UARTs that do not reassert THRE when the
 		 * transmitter is idle and the interrupt has already
@@ -2284,8 +2288,6 @@ int serial8250_do_startup(struct uart_port *port)
 		 * allow register changes to become visible.
 		 */
 		spin_lock_irqsave(&port->lock, flags);
-		if (up->port.irqflags & IRQF_SHARED)
-			disable_irq_nosync(port->irq);
 
 		wait_for_xmitr(up, UART_LSR_THRE);
 		serial_port_out_sync(port, UART_IER, UART_IER_THRI);
@@ -2297,9 +2299,10 @@ int serial8250_do_startup(struct uart_port *port)
 		iir = serial_port_in(port, UART_IIR);
 		serial_port_out(port, UART_IER, 0);
 
+		spin_unlock_irqrestore(&port->lock, flags);
+
 		if (port->irqflags & IRQF_SHARED)
 			enable_irq(port->irq);
-		spin_unlock_irqrestore(&port->lock, flags);
 
 		/*
 		 * If the interrupt is not reasserted, or we otherwise
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index e0b73a5402db..a2978abab0db 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -75,7 +75,7 @@ static unsigned int uniphier_serial_in(struct uart_port *p, int offset)
 		break;
 	case UART_LCR:
 		valshift = 8;
-		/* fall through */
+		fallthrough;
 	case UART_MCR:
 		offset = UNIPHIER_UART_LCR_MCR;
 		break;
@@ -101,7 +101,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value)
 	case UART_SCR:
 		/* No SCR for this hardware.  Use CHAR as a scratch register */
 		valshift = 8;
-		/* fall through */
+		fallthrough;
 	case UART_FCR:
 		offset = UNIPHIER_UART_CHAR_FCR;
 		break;
@@ -109,7 +109,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value)
 		valshift = 8;
 		/* Divisor latch access bit does not exist. */
 		value &= ~UART_LCR_DLAB;
-		/* fall through */
+		fallthrough;
 	case UART_MCR:
 		offset = UNIPHIER_UART_LCR_MCR;
 		break;
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 8a0352eb337c..9409be982aa6 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -517,6 +517,7 @@ config SERIAL_IMX_CONSOLE
 
 config SERIAL_IMX_EARLYCON
 	bool "Earlycon on IMX serial port"
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on OF
 	select SERIAL_EARLYCON
 	help
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index d056ee6cca33..caf167f0c10a 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_SERIAL_ZS) += zs.o
 obj-$(CONFIG_SERIAL_SH_SCI) += sh-sci.o
 obj-$(CONFIG_SERIAL_CPM) += cpm_uart/
 obj-$(CONFIG_SERIAL_IMX) += imx.o
+obj-$(CONFIG_SERIAL_IMX_EARLYCON) += imx_earlycon.o
 obj-$(CONFIG_SERIAL_MPC52xx) += mpc52xx_uart.o
 obj-$(CONFIG_SERIAL_ICOM) += icom.o
 obj-$(CONFIG_SERIAL_MESON) += meson_uart.o
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index c010f639298d..67498594d7d7 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2241,9 +2241,8 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 	clk_disable(uap->clk);
 }
 
-static void __init
-pl011_console_get_options(struct uart_amba_port *uap, int *baud,
-			     int *parity, int *bits)
+static void pl011_console_get_options(struct uart_amba_port *uap, int *baud,
+				      int *parity, int *bits)
 {
 	if (pl011_read(uap, REG_CR) & UART01x_CR_UARTEN) {
 		unsigned int lcr_h, ibrd, fbrd;
@@ -2276,7 +2275,7 @@ pl011_console_get_options(struct uart_amba_port *uap, int *baud,
 	}
 }
 
-static int __init pl011_console_setup(struct console *co, char *options)
+static int pl011_console_setup(struct console *co, char *options)
 {
 	struct uart_amba_port *uap;
 	int baud = 38400;
@@ -2344,8 +2343,8 @@ static int __init pl011_console_setup(struct console *co, char *options)
  *
  *	Returns 0 if console matches; otherwise non-zero to use default matching
  */
-static int __init pl011_console_match(struct console *co, char *name, int idx,
-				      char *options)
+static int pl011_console_match(struct console *co, char *name, int idx,
+			       char *options)
 {
 	unsigned char iotype;
 	resource_size_t addr;
@@ -2615,7 +2614,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap,
 
 static int pl011_register_port(struct uart_amba_port *uap)
 {
-	int ret;
+	int ret, i;
 
 	/* Ensure interrupts from this UART are masked and cleared */
 	pl011_write(0, uap, REG_IMSC);
@@ -2626,6 +2625,9 @@ static int pl011_register_port(struct uart_amba_port *uap)
 		if (ret < 0) {
 			dev_err(uap->port.dev,
 				"Failed to register AMBA-PL011 driver\n");
+			for (i = 0; i < ARRAY_SIZE(amba_ports); i++)
+				if (amba_ports[i] == uap)
+					amba_ports[i] = NULL;
 			return ret;
 		}
 	}
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index e43471b33710..bb5fc8bdd57a 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1845,7 +1845,7 @@ static void atmel_get_ip_name(struct uart_port *port)
 		version = atmel_uart_readl(port, ATMEL_US_VERSION);
 		switch (version) {
 		case 0x814:	/* sama5d2 */
-			/* fall through */
+			fallthrough;
 		case 0x701:	/* sama5d4 */
 			atmel_port->fidi_min = 3;
 			atmel_port->fidi_max = 65535;
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 8573fc9cb0cd..76b94d0ff586 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -587,7 +587,6 @@ static irqreturn_t serial_omap_irq(int irq, void *dev_id)
 			transmit_chars(up, lsr);
 			break;
 		case UART_IIR_RX_TIMEOUT:
-			/* FALLTHROUGH */
 		case UART_IIR_RDI:
 			serial_omap_rdi(up, lsr);
 			break;
@@ -598,7 +597,6 @@ static irqreturn_t serial_omap_irq(int irq, void *dev_id)
 			/* simply try again */
 			break;
 		case UART_IIR_XOFF:
-			/* FALLTHROUGH */
 		default:
 			break;
 		}
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 3aa29d201f54..184b458820a3 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -361,11 +361,16 @@ static int qcom_geni_serial_get_char(struct uart_port *uport)
 			return NO_POLL_CHAR;
 
 		if (word_cnt == 1 && (status & RX_LAST))
+			/*
+			 * NOTE: If RX_LAST_BYTE_VALID is 0 it needs to be
+			 * treated as if it was BYTES_PER_FIFO_WORD.
+			 */
 			private_data->poll_cached_bytes_cnt =
 				(status & RX_LAST_BYTE_VALID_MSK) >>
 				RX_LAST_BYTE_VALID_SHFT;
-		else
-			private_data->poll_cached_bytes_cnt = 4;
+
+		if (private_data->poll_cached_bytes_cnt == 0)
+			private_data->poll_cached_bytes_cnt = BYTES_PER_FIFO_WORD;
 
 		private_data->poll_cached_bytes =
 			readl(uport->membase + SE_GENI_RX_FIFOn);
@@ -1098,7 +1103,7 @@ static unsigned int qcom_geni_serial_tx_empty(struct uart_port *uport)
 }
 
 #ifdef CONFIG_SERIAL_QCOM_GENI_CONSOLE
-static int __init qcom_geni_console_setup(struct console *co, char *options)
+static int qcom_geni_console_setup(struct console *co, char *options)
 {
 	struct uart_port *uport;
 	struct qcom_geni_serial_port *port;
diff --git a/drivers/tty/serial/rda-uart.c b/drivers/tty/serial/rda-uart.c
index b5ef86ae2746..85366e059258 100644
--- a/drivers/tty/serial/rda-uart.c
+++ b/drivers/tty/serial/rda-uart.c
@@ -259,7 +259,7 @@ static void rda_uart_set_termios(struct uart_port *port,
 	case CS5:
 	case CS6:
 		dev_warn(port->dev, "bit size not supported, using 7 bits\n");
-		/* Fall through */
+		fallthrough;
 	case CS7:
 		ctrl &= ~RDA_UART_DBITS_8;
 		break;
diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 8ed3482d2e1e..8ae3e03fbd8c 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -1905,9 +1905,11 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport,
 		ourport->tx_irq = ret + 1;
 	}
 
-	ret = platform_get_irq(platdev, 1);
-	if (ret > 0)
-		ourport->tx_irq = ret;
+	if (!s3c24xx_serial_has_interrupt_mask(port)) {
+		ret = platform_get_irq(platdev, 1);
+		if (ret > 0)
+			ourport->tx_irq = ret;
+	}
 	/*
 	 * DMA is currently supported only on DT platforms, if DMA properties
 	 * are specified.
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index b87914ae6da8..bd13014a1c53 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -876,7 +876,7 @@ static irqreturn_t tegra_uart_isr(int irq, void *data)
 				tegra_uart_write(tup, ier, UART_IER);
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case 2: /* Receive */
 			if (!tup->use_rx_pio) {
 				is_rx_start = tup->rx_in_progress;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 3403dd790517..f797c971cd82 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2101,7 +2101,7 @@ uart_set_options(struct uart_port *port, struct console *co,
 	switch (parity) {
 	case 'o': case 'O':
 		termios.c_cflag |= PARODD;
-		/*fall through*/
+		fallthrough;
 	case 'e': case 'E':
 		termios.c_cflag |= PARENB;
 		break;
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 143300a80090..ba503dd04ce2 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -970,7 +970,7 @@ static int stm32_init_port(struct stm32_port *stm32port,
 		return ret;
 
 	if (stm32port->info->cfg.has_wakeup) {
-		stm32port->wakeirq = platform_get_irq(pdev, 1);
+		stm32port->wakeirq = platform_get_irq_optional(pdev, 1);
 		if (stm32port->wakeirq <= 0 && stm32port->wakeirq != -ENXIO)
 			return stm32port->wakeirq ? : -ENODEV;
 	}
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 8ce9a7a256e5..319e5ceb6130 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -514,7 +514,7 @@ static void receive_kbd_ms_chars(struct uart_sunsu_port *up, int is_break)
 			switch (ret) {
 			case 2:
 				sunsu_change_mouse_baud(up);
-				/* fallthru */
+				fallthrough;
 			case 1:
 				break;
 
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index 7ea06bbc6197..001e19d7c17d 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -306,7 +306,7 @@ static void sunzilog_kbdms_receive_chars(struct uart_sunzilog_port *up,
 		switch (ret) {
 		case 2:
 			sunzilog_change_mouse_baud(up);
-			/* fallthru */
+			fallthrough;
 		case 1:
 			break;
 
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 2833f1418d6d..a9b1ee27183a 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -544,7 +544,7 @@ static int cdns_uart_clk_notifier_cb(struct notifier_block *nb,
 
 		cdns_uart->baud = cdns_uart_set_baud_rate(cdns_uart->port,
 				cdns_uart->baud);
-		/* fall through */
+		fallthrough;
 	case ABORT_RATE_CHANGE:
 		if (!locked)
 			spin_lock_irqsave(&cdns_uart->port->lock, flags);
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 9245fffdbceb..e18f318586ab 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -866,7 +866,7 @@ static int __tty_perform_flush(struct tty_struct *tty, unsigned long arg)
 			ld->ops->flush_buffer(tty);
 			tty_unthrottle(tty);
 		}
-		/* fall through */
+		fallthrough;
 	case TCOFLUSH:
 		tty_driver_flush_buffer(tty);
 		break;
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index ccb533fd00a2..19cd4a4b1939 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1201,7 +1201,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	unsigned int old_rows, old_row_size, first_copied_row;
 	unsigned int new_cols, new_rows, new_row_size, new_screen_size;
 	unsigned int user;
-	unsigned short *newscreen;
+	unsigned short *oldscreen, *newscreen;
 	struct uni_screen *new_uniscr = NULL;
 
 	WARN_CONSOLE_UNLOCKED();
@@ -1299,10 +1299,11 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_scr_end > new_origin)
 		scr_memsetw((void *)new_origin, vc->vc_video_erase_char,
 			    new_scr_end - new_origin);
-	kfree(vc->vc_screenbuf);
+	oldscreen = vc->vc_screenbuf;
 	vc->vc_screenbuf = newscreen;
 	vc->vc_screenbuf_size = new_screen_size;
 	set_origin(vc);
+	kfree(oldscreen);
 
 	/* do part of a reset_terminal() */
 	vc->vc_top = 0;
@@ -1553,7 +1554,7 @@ static void csi_J(struct vc_data *vc, int vpar)
 			break;
 		case 3: /* include scrollback */
 			flush_scrollback(vc);
-			/* fallthrough */
+			fallthrough;
 		case 2: /* erase whole display */
 			vc_uniscr_clear_lines(vc, 0, vc->vc_rows);
 			count = vc->vc_cols * vc->vc_rows;
@@ -2167,7 +2168,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		lf(vc);
 		if (!is_kbd(vc, lnm))
 			return;
-		/* fall through */
+		fallthrough;
 	case 13:
 		cr(vc);
 		return;
@@ -2306,7 +2307,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 			return;
 		}
 		vc->vc_priv = EPecma;
-		/* fall through */
+		fallthrough;
 	case ESgetpars:
 		if (c == ';' && vc->vc_npar < NPAR - 1) {
 			vc->vc_npar++;
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 91c301775047..a4e520bdd521 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -806,12 +806,22 @@ static int vt_resizex(struct vc_data *vc, struct vt_consize __user *cs)
 		console_lock();
 		vcp = vc_cons[i].d;
 		if (vcp) {
+			int ret;
+			int save_scan_lines = vcp->vc_scan_lines;
+			int save_font_height = vcp->vc_font.height;
+
 			if (v.v_vlin)
 				vcp->vc_scan_lines = v.v_vlin;
 			if (v.v_clin)
 				vcp->vc_font.height = v.v_clin;
 			vcp->vc_resize_user = 1;
-			vc_resize(vcp, v.v_cols, v.v_rows);
+			ret = vc_resize(vcp, v.v_cols, v.v_rows);
+			if (ret) {
+				vcp->vc_scan_lines = save_scan_lines;
+				vcp->vc_font.height = save_font_height;
+				console_unlock();
+				return ret;
+			}
 		}
 		console_unlock();
 	}
diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c
index f7f6229082ca..60f4711717d2 100644
--- a/drivers/usb/c67x00/c67x00-sched.c
+++ b/drivers/usb/c67x00/c67x00-sched.c
@@ -710,7 +710,8 @@ static int c67x00_add_ctrl_urb(struct c67x00_hcd *c67x00, struct urb *urb)
 			if (ret)
 				return ret;
 			break;
-		}		/* else fallthrough */
+		}
+		fallthrough;
 	case STATUS_STAGE:
 		pid = !usb_pipeout(urb->pipe) ? USB_PID_OUT : USB_PID_IN;
 		ret = c67x00_create_td(c67x00, urb, NULL, 0, pid, 1,
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 991786876dbb..7f6f3ab5b8a6 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -378,21 +378,19 @@ static void acm_ctrl_irq(struct urb *urb)
 	if (current_size < expected_size) {
 		/* notification is transmitted fragmented, reassemble */
 		if (acm->nb_size < expected_size) {
-			if (acm->nb_size) {
-				kfree(acm->notification_buffer);
-				acm->nb_size = 0;
-			}
+			u8 *new_buffer;
 			alloc_size = roundup_pow_of_two(expected_size);
-			/*
-			 * kmalloc ensures a valid notification_buffer after a
-			 * use of kfree in case the previous allocation was too
-			 * small. Final freeing is done on disconnect.
-			 */
-			acm->notification_buffer =
-				kmalloc(alloc_size, GFP_ATOMIC);
-			if (!acm->notification_buffer)
+			/* Final freeing is done on disconnect. */
+			new_buffer = krealloc(acm->notification_buffer,
+					      alloc_size, GFP_ATOMIC);
+			if (!new_buffer) {
+				acm->nb_index = 0;
 				goto exit;
+			}
+
+			acm->notification_buffer = new_buffer;
 			acm->nb_size = alloc_size;
+			dr = (struct usb_cdc_notification *)acm->notification_buffer;
 		}
 
 		copy_size = min(current_size,
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index f81606c6a35b..7e73e989645b 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -905,6 +905,35 @@ static int usb_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
+static bool is_dev_usb_generic_driver(struct device *dev)
+{
+	struct usb_device_driver *udd = dev->driver ?
+		to_usb_device_driver(dev->driver) : NULL;
+
+	return udd == &usb_generic_driver;
+}
+
+static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
+{
+	struct usb_device_driver *new_udriver = data;
+	struct usb_device *udev;
+	int ret;
+
+	if (!is_dev_usb_generic_driver(dev))
+		return 0;
+
+	udev = to_usb_device(dev);
+	if (usb_device_match_id(udev, new_udriver->id_table) == NULL &&
+	    (!new_udriver->match || new_udriver->match(udev) != 0))
+		return 0;
+
+	ret = device_reprobe(dev);
+	if (ret && ret != -EPROBE_DEFER)
+		dev_err(dev, "Failed to reprobe device (error %d)\n", ret);
+
+	return 0;
+}
+
 /**
  * usb_register_device_driver - register a USB device (not interface) driver
  * @new_udriver: USB operations for the device driver
@@ -934,13 +963,20 @@ int usb_register_device_driver(struct usb_device_driver *new_udriver,
 
 	retval = driver_register(&new_udriver->drvwrap.driver);
 
-	if (!retval)
+	if (!retval) {
 		pr_info("%s: registered new device driver %s\n",
 			usbcore_name, new_udriver->name);
-	else
+		/*
+		 * Check whether any device could be better served with
+		 * this new driver
+		 */
+		bus_for_each_dev(&usb_bus_type, NULL, new_udriver,
+				 __usb_bus_reprobe_drivers);
+	} else {
 		printk(KERN_ERR "%s: error %d registering device "
 			"	driver %s\n",
 			usbcore_name, retval, new_udriver->name);
+	}
 
 	return retval;
 }
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index b6f2d4b44754..2b2f1ab6e36a 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -205,8 +205,9 @@ static int __check_usb_generic(struct device_driver *drv, void *data)
 	udrv = to_usb_device_driver(drv);
 	if (udrv == &usb_generic_driver)
 		return 0;
-
-	return usb_device_match_id(udev, udrv->id_table) != NULL;
+	if (usb_device_match_id(udev, udrv->id_table) != NULL)
+		return 1;
+	return (udrv->match && udrv->match(udev));
 }
 
 static bool usb_generic_driver_match(struct usb_device *udev)
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index 4dc443aaef5c..ec0d6c50610c 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -315,11 +315,14 @@ EXPORT_SYMBOL_GPL(usb_hcd_pci_probe);
 void usb_hcd_pci_remove(struct pci_dev *dev)
 {
 	struct usb_hcd		*hcd;
+	int			hcd_driver_flags;
 
 	hcd = pci_get_drvdata(dev);
 	if (!hcd)
 		return;
 
+	hcd_driver_flags = hcd->driver->flags;
+
 	if (pci_dev_run_wake(dev))
 		pm_runtime_get_noresume(&dev->dev);
 
@@ -347,7 +350,7 @@ void usb_hcd_pci_remove(struct pci_dev *dev)
 		up_read(&companions_rwsem);
 	}
 	usb_put_hcd(hcd);
-	if ((hcd->driver->flags & HCD_MASK) < HCD_USB3)
+	if ((hcd_driver_flags & HCD_MASK) < HCD_USB3)
 		pci_free_irq_vectors(dev);
 	pci_disable_device(dev);
 }
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 052d5accfe9b..5b768b80d1ee 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -727,7 +727,7 @@ static void hub_irq(struct urb *urb)
 		if ((++hub->nerrors < 10) || hub->error)
 			goto resubmit;
 		hub->error = status;
-		/* FALL THROUGH */
+		fallthrough;
 
 	/* let hub_wq handle things */
 	case 0:			/* we got data:  port status changed */
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 6197938dcc2d..ae1de9cc4b09 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1205,6 +1205,34 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 	}
 }
 
+/*
+ * usb_disable_device_endpoints -- Disable all endpoints for a device
+ * @dev: the device whose endpoints are being disabled
+ * @skip_ep0: 0 to disable endpoint 0, 1 to skip it.
+ */
+static void usb_disable_device_endpoints(struct usb_device *dev, int skip_ep0)
+{
+	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
+	int i;
+
+	if (hcd->driver->check_bandwidth) {
+		/* First pass: Cancel URBs, leave endpoint pointers intact. */
+		for (i = skip_ep0; i < 16; ++i) {
+			usb_disable_endpoint(dev, i, false);
+			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
+		}
+		/* Remove endpoints from the host controller internal state */
+		mutex_lock(hcd->bandwidth_mutex);
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		mutex_unlock(hcd->bandwidth_mutex);
+	}
+	/* Second pass: remove endpoint pointers */
+	for (i = skip_ep0; i < 16; ++i) {
+		usb_disable_endpoint(dev, i, true);
+		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
+	}
+}
+
 /**
  * usb_disable_device - Disable all the endpoints for a USB device
  * @dev: the device whose endpoints are being disabled
@@ -1218,7 +1246,6 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 void usb_disable_device(struct usb_device *dev, int skip_ep0)
 {
 	int i;
-	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
 
 	/* getting rid of interfaces will disconnect
 	 * any drivers bound to them (a key side effect)
@@ -1264,22 +1291,8 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0)
 
 	dev_dbg(&dev->dev, "%s nuking %s URBs\n", __func__,
 		skip_ep0 ? "non-ep0" : "all");
-	if (hcd->driver->check_bandwidth) {
-		/* First pass: Cancel URBs, leave endpoint pointers intact. */
-		for (i = skip_ep0; i < 16; ++i) {
-			usb_disable_endpoint(dev, i, false);
-			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
-		}
-		/* Remove endpoints from the host controller internal state */
-		mutex_lock(hcd->bandwidth_mutex);
-		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
-		mutex_unlock(hcd->bandwidth_mutex);
-		/* Second pass: remove endpoint pointers */
-	}
-	for (i = skip_ep0; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+
+	usb_disable_device_endpoints(dev, skip_ep0);
 }
 
 /**
@@ -1522,6 +1535,9 @@ EXPORT_SYMBOL_GPL(usb_set_interface);
  * The caller must own the device lock.
  *
  * Return: Zero on success, else a negative error code.
+ *
+ * If this routine fails the device will probably be in an unusable state
+ * with endpoints disabled, and interfaces only partially enabled.
  */
 int usb_reset_configuration(struct usb_device *dev)
 {
@@ -1537,10 +1553,7 @@ int usb_reset_configuration(struct usb_device *dev)
 	 * calls during probe() are fine
 	 */
 
-	for (i = 1; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+	usb_disable_device_endpoints(dev, 1); /* skip ep0*/
 
 	config = dev->actconfig;
 	retval = 0;
@@ -1553,34 +1566,10 @@ int usb_reset_configuration(struct usb_device *dev)
 		mutex_unlock(hcd->bandwidth_mutex);
 		return -ENOMEM;
 	}
-	/* Make sure we have enough bandwidth for each alternate setting 0 */
-	for (i = 0; i < config->desc.bNumInterfaces; i++) {
-		struct usb_interface *intf = config->interface[i];
-		struct usb_host_interface *alt;
 
-		alt = usb_altnum_to_altsetting(intf, 0);
-		if (!alt)
-			alt = &intf->altsetting[0];
-		if (alt != intf->cur_altsetting)
-			retval = usb_hcd_alloc_bandwidth(dev, NULL,
-					intf->cur_altsetting, alt);
-		if (retval < 0)
-			break;
-	}
-	/* If not, reinstate the old alternate settings */
+	/* xHCI adds all endpoints in usb_hcd_alloc_bandwidth */
+	retval = usb_hcd_alloc_bandwidth(dev, config, NULL, NULL);
 	if (retval < 0) {
-reset_old_alts:
-		for (i--; i >= 0; i--) {
-			struct usb_interface *intf = config->interface[i];
-			struct usb_host_interface *alt;
-
-			alt = usb_altnum_to_altsetting(intf, 0);
-			if (!alt)
-				alt = &intf->altsetting[0];
-			if (alt != intf->cur_altsetting)
-				usb_hcd_alloc_bandwidth(dev, NULL,
-						alt, intf->cur_altsetting);
-		}
 		usb_enable_lpm(dev);
 		mutex_unlock(hcd->bandwidth_mutex);
 		return retval;
@@ -1589,8 +1578,12 @@ reset_old_alts:
 			USB_REQ_SET_CONFIGURATION, 0,
 			config->desc.bConfigurationValue, 0,
 			NULL, 0, USB_CTRL_SET_TIMEOUT);
-	if (retval < 0)
-		goto reset_old_alts;
+	if (retval < 0) {
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		usb_enable_lpm(dev);
+		mutex_unlock(hcd->bandwidth_mutex);
+		return retval;
+	}
 	mutex_unlock(hcd->bandwidth_mutex);
 
 	/* re-init hc/hcd interface/endpoint state */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 7c1198f80c23..f232914de5fd 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -370,6 +370,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
 			USB_QUIRK_ENDPOINT_IGNORE },
 
+	/* Sound Devices MixPre-D */
+	{ USB_DEVICE(0x0926, 0x0208), .driver_info =
+			USB_QUIRK_ENDPOINT_IGNORE },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -465,6 +469,8 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x3119), .driver_info = USB_QUIRK_NO_LPM },
 
+	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
@@ -509,6 +515,7 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = {
  */
 static const struct usb_device_id usb_endpoint_ignore[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
+	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 },
 	{ }
 };
 
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index a2ca38e25e0c..8d134193fa0c 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -889,7 +889,11 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 	size_t srclen, n;
 	int cfgno;
 	void *src;
+	int retval;
 
+	retval = usb_lock_device_interruptible(udev);
+	if (retval < 0)
+		return -EINTR;
 	/* The binary attribute begins with the device descriptor.
 	 * Following that are the raw descriptor entries for all the
 	 * configurations (config plus subsidiary descriptors).
@@ -914,6 +918,7 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 			off -= srclen;
 		}
 	}
+	usb_unlock_device(udev);
 	return count - nleft;
 }
 
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 422aea24afcd..2eb34c8b4065 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -646,9 +646,8 @@ static int dwc3_phy_setup(struct dwc3 *dwc)
 			if (!(reg & DWC3_GUSB2PHYCFG_ULPI_UTMI))
 				break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case DWC3_GHWPARAMS3_HSPHY_IFC_ULPI:
-		/* FALLTHROUGH */
 	default:
 		break;
 	}
@@ -1411,7 +1410,7 @@ static void dwc3_check_params(struct dwc3 *dwc)
 	default:
 		dev_err(dev, "invalid maximum_speed parameter %d\n",
 			dwc->maximum_speed);
-		/* fall through */
+		fallthrough;
 	case USB_SPEED_UNKNOWN:
 		/* default to superspeed */
 		dwc->maximum_speed = USB_SPEED_SUPER;
diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c
index 88b75b5a039c..1f7f4d88ed9d 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -737,13 +737,13 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 		goto err_disable_clks;
 	}
 
-	ret = reset_control_deassert(priv->reset);
+	ret = reset_control_reset(priv->reset);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	ret = dwc3_meson_g12a_get_phys(priv);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	ret = priv->drvdata->setup_regmaps(priv, base);
 	if (ret)
@@ -752,7 +752,7 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 	if (priv->vbus) {
 		ret = regulator_enable(priv->vbus);
 		if (ret)
-			goto err_assert_reset;
+			goto err_disable_clks;
 	}
 
 	/* Get dr_mode */
@@ -765,13 +765,13 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 
 	ret = priv->drvdata->usb_init(priv);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	/* Init PHYs */
 	for (i = 0 ; i < PHY_COUNT ; ++i) {
 		ret = phy_init(priv->phys[i]);
 		if (ret)
-			goto err_assert_reset;
+			goto err_disable_clks;
 	}
 
 	/* Set PHY Power */
@@ -809,9 +809,6 @@ err_phys_exit:
 	for (i = 0 ; i < PHY_COUNT ; ++i)
 		phy_exit(priv->phys[i]);
 
-err_assert_reset:
-	reset_control_assert(priv->reset);
-
 err_disable_clks:
 	clk_bulk_disable_unprepare(priv->drvdata->num_clks,
 				   priv->drvdata->clks);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index e44bfc3b5096..c2a0f64f8d1e 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1054,27 +1054,25 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb,
  * dwc3_prepare_one_trb - setup one TRB from one request
  * @dep: endpoint for which this request is prepared
  * @req: dwc3_request pointer
+ * @trb_length: buffer size of the TRB
  * @chain: should this TRB be chained to the next?
  * @node: only for isochronous endpoints. First TRB needs different type.
  */
 static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
-		struct dwc3_request *req, unsigned chain, unsigned node)
+		struct dwc3_request *req, unsigned int trb_length,
+		unsigned chain, unsigned node)
 {
 	struct dwc3_trb		*trb;
-	unsigned int		length;
 	dma_addr_t		dma;
 	unsigned		stream_id = req->request.stream_id;
 	unsigned		short_not_ok = req->request.short_not_ok;
 	unsigned		no_interrupt = req->request.no_interrupt;
 	unsigned		is_last = req->request.is_last;
 
-	if (req->request.num_sgs > 0) {
-		length = sg_dma_len(req->start_sg);
+	if (req->request.num_sgs > 0)
 		dma = sg_dma_address(req->start_sg);
-	} else {
-		length = req->request.length;
+	else
 		dma = req->request.dma;
-	}
 
 	trb = &dep->trb_pool[dep->trb_enqueue];
 
@@ -1086,7 +1084,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 
 	req->num_trbs++;
 
-	__dwc3_prepare_one_trb(dep, trb, dma, length, chain, node,
+	__dwc3_prepare_one_trb(dep, trb, dma, trb_length, chain, node,
 			stream_id, short_not_ok, no_interrupt, is_last);
 }
 
@@ -1096,16 +1094,27 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 	struct scatterlist *sg = req->start_sg;
 	struct scatterlist *s;
 	int		i;
-
+	unsigned int length = req->request.length;
 	unsigned int remaining = req->request.num_mapped_sgs
 		- req->num_queued_sgs;
 
+	/*
+	 * If we resume preparing the request, then get the remaining length of
+	 * the request and resume where we left off.
+	 */
+	for_each_sg(req->request.sg, s, req->num_queued_sgs, i)
+		length -= sg_dma_len(s);
+
 	for_each_sg(sg, s, remaining, i) {
-		unsigned int length = req->request.length;
 		unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc);
 		unsigned int rem = length % maxp;
+		unsigned int trb_length;
 		unsigned chain = true;
 
+		trb_length = min_t(unsigned int, length, sg_dma_len(s));
+
+		length -= trb_length;
+
 		/*
 		 * IOMMU driver is coalescing the list of sgs which shares a
 		 * page boundary into one and giving it to USB driver. With
@@ -1113,7 +1122,7 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 		 * sgs passed. So mark the chain bit to false if it isthe last
 		 * mapped sg.
 		 */
-		if (i == remaining - 1)
+		if ((i == remaining - 1) || !length)
 			chain = false;
 
 		if (rem && usb_endpoint_dir_out(dep->endpoint.desc) && !chain) {
@@ -1123,7 +1132,7 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 			req->needs_extra_trb = true;
 
 			/* prepare normal TRB */
-			dwc3_prepare_one_trb(dep, req, true, i);
+			dwc3_prepare_one_trb(dep, req, trb_length, true, i);
 
 			/* Now prepare one extra TRB to align transfer size */
 			trb = &dep->trb_pool[dep->trb_enqueue];
@@ -1134,8 +1143,39 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 					req->request.short_not_ok,
 					req->request.no_interrupt,
 					req->request.is_last);
+		} else if (req->request.zero && req->request.length &&
+			   !usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
+			   !rem && !chain) {
+			struct dwc3	*dwc = dep->dwc;
+			struct dwc3_trb	*trb;
+
+			req->needs_extra_trb = true;
+
+			/* Prepare normal TRB */
+			dwc3_prepare_one_trb(dep, req, trb_length, true, i);
+
+			/* Prepare one extra TRB to handle ZLP */
+			trb = &dep->trb_pool[dep->trb_enqueue];
+			req->num_trbs++;
+			__dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, 0,
+					       !req->direction, 1,
+					       req->request.stream_id,
+					       req->request.short_not_ok,
+					       req->request.no_interrupt,
+					       req->request.is_last);
+
+			/* Prepare one more TRB to handle MPS alignment */
+			if (!req->direction) {
+				trb = &dep->trb_pool[dep->trb_enqueue];
+				req->num_trbs++;
+				__dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, maxp,
+						       false, 1, req->request.stream_id,
+						       req->request.short_not_ok,
+						       req->request.no_interrupt,
+						       req->request.is_last);
+			}
 		} else {
-			dwc3_prepare_one_trb(dep, req, chain, i);
+			dwc3_prepare_one_trb(dep, req, trb_length, chain, i);
 		}
 
 		/*
@@ -1150,6 +1190,16 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 
 		req->num_queued_sgs++;
 
+		/*
+		 * The number of pending SG entries may not correspond to the
+		 * number of mapped SG entries. If all the data are queued, then
+		 * don't include unused SG entries.
+		 */
+		if (length == 0) {
+			req->num_pending_sgs -= req->request.num_mapped_sgs - req->num_queued_sgs;
+			break;
+		}
+
 		if (!dwc3_calc_trbs_left(dep))
 			break;
 	}
@@ -1169,7 +1219,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep,
 		req->needs_extra_trb = true;
 
 		/* prepare normal TRB */
-		dwc3_prepare_one_trb(dep, req, true, 0);
+		dwc3_prepare_one_trb(dep, req, length, true, 0);
 
 		/* Now prepare one extra TRB to align transfer size */
 		trb = &dep->trb_pool[dep->trb_enqueue];
@@ -1180,6 +1230,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep,
 				req->request.no_interrupt,
 				req->request.is_last);
 	} else if (req->request.zero && req->request.length &&
+		   !usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
 		   (IS_ALIGNED(req->request.length, maxp))) {
 		struct dwc3	*dwc = dep->dwc;
 		struct dwc3_trb	*trb;
@@ -1187,18 +1238,29 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep,
 		req->needs_extra_trb = true;
 
 		/* prepare normal TRB */
-		dwc3_prepare_one_trb(dep, req, true, 0);
+		dwc3_prepare_one_trb(dep, req, length, true, 0);
 
-		/* Now prepare one extra TRB to handle ZLP */
+		/* Prepare one extra TRB to handle ZLP */
 		trb = &dep->trb_pool[dep->trb_enqueue];
 		req->num_trbs++;
 		__dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, 0,
-				false, 1, req->request.stream_id,
+				!req->direction, 1, req->request.stream_id,
 				req->request.short_not_ok,
 				req->request.no_interrupt,
 				req->request.is_last);
+
+		/* Prepare one more TRB to handle MPS alignment for OUT */
+		if (!req->direction) {
+			trb = &dep->trb_pool[dep->trb_enqueue];
+			req->num_trbs++;
+			__dwc3_prepare_one_trb(dep, trb, dwc->bounce_addr, maxp,
+					       false, 1, req->request.stream_id,
+					       req->request.short_not_ok,
+					       req->request.no_interrupt,
+					       req->request.is_last);
+		}
 	} else {
-		dwc3_prepare_one_trb(dep, req, false, 0);
+		dwc3_prepare_one_trb(dep, req, length, false, 0);
 	}
 }
 
@@ -2671,8 +2733,17 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
 				status);
 
 	if (req->needs_extra_trb) {
+		unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc);
+
 		ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event,
 				status);
+
+		/* Reclaim MPS padding TRB for ZLP */
+		if (!req->direction && req->request.zero && req->request.length &&
+		    !usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
+		    (IS_ALIGNED(req->request.length, maxp)))
+			ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event, status);
+
 		req->needs_extra_trb = false;
 	}
 
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 331c951d72dc..950c9435beec 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -2039,7 +2039,6 @@ static int do_scsi_command(struct fsg_common *common)
 	case RELEASE:
 	case RESERVE:
 	case SEND_DIAGNOSTIC:
-		fallthrough;
 
 	default:
 unknown_cmnd:
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 1d900081b1f0..b4206b0dede5 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1181,12 +1181,15 @@ static int ncm_unwrap_ntb(struct gether *port,
 	int		ndp_index;
 	unsigned	dg_len, dg_len2;
 	unsigned	ndp_len;
+	unsigned	block_len;
 	struct sk_buff	*skb2;
 	int		ret = -EINVAL;
-	unsigned	max_size = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
+	unsigned	ntb_max = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
+	unsigned	frame_max = le16_to_cpu(ecm_desc.wMaxSegmentSize);
 	const struct ndp_parser_opts *opts = ncm->parser_opts;
 	unsigned	crc_len = ncm->is_crc ? sizeof(uint32_t) : 0;
 	int		dgram_counter;
+	bool		ndp_after_header;
 
 	/* dwSignature */
 	if (get_unaligned_le32(tmp) != opts->nth_sign) {
@@ -1205,25 +1208,37 @@ static int ncm_unwrap_ntb(struct gether *port,
 	}
 	tmp++; /* skip wSequence */
 
+	block_len = get_ncm(&tmp, opts->block_length);
 	/* (d)wBlockLength */
-	if (get_ncm(&tmp, opts->block_length) > max_size) {
+	if (block_len > ntb_max) {
 		INFO(port->func.config->cdev, "OUT size exceeded\n");
 		goto err;
 	}
 
 	ndp_index = get_ncm(&tmp, opts->ndp_index);
+	ndp_after_header = false;
 
 	/* Run through all the NDP's in the NTB */
 	do {
-		/* NCM 3.2 */
-		if (((ndp_index % 4) != 0) &&
-				(ndp_index < opts->nth_size)) {
+		/*
+		 * NCM 3.2
+		 * dwNdpIndex
+		 */
+		if (((ndp_index % 4) != 0) ||
+				(ndp_index < opts->nth_size) ||
+				(ndp_index > (block_len -
+					      opts->ndp_size))) {
 			INFO(port->func.config->cdev, "Bad index: %#X\n",
 			     ndp_index);
 			goto err;
 		}
+		if (ndp_index == opts->nth_size)
+			ndp_after_header = true;
 
-		/* walk through NDP */
+		/*
+		 * walk through NDP
+		 * dwSignature
+		 */
 		tmp = (void *)(skb->data + ndp_index);
 		if (get_unaligned_le32(tmp) != ncm->ndp_sign) {
 			INFO(port->func.config->cdev, "Wrong NDP SIGN\n");
@@ -1234,14 +1249,15 @@ static int ncm_unwrap_ntb(struct gether *port,
 		ndp_len = get_unaligned_le16(tmp++);
 		/*
 		 * NCM 3.3.1
+		 * wLength
 		 * entry is 2 items
 		 * item size is 16/32 bits, opts->dgram_item_len * 2 bytes
 		 * minimal: struct usb_cdc_ncm_ndpX + normal entry + zero entry
 		 * Each entry is a dgram index and a dgram length.
 		 */
 		if ((ndp_len < opts->ndp_size
-				+ 2 * 2 * (opts->dgram_item_len * 2))
-				|| (ndp_len % opts->ndplen_align != 0)) {
+				+ 2 * 2 * (opts->dgram_item_len * 2)) ||
+				(ndp_len % opts->ndplen_align != 0)) {
 			INFO(port->func.config->cdev, "Bad NDP length: %#X\n",
 			     ndp_len);
 			goto err;
@@ -1258,8 +1274,21 @@ static int ncm_unwrap_ntb(struct gether *port,
 
 		do {
 			index = index2;
+			/* wDatagramIndex[0] */
+			if ((index < opts->nth_size) ||
+					(index > block_len - opts->dpe_size)) {
+				INFO(port->func.config->cdev,
+				     "Bad index: %#X\n", index);
+				goto err;
+			}
+
 			dg_len = dg_len2;
-			if (dg_len < 14 + crc_len) { /* ethernet hdr + crc */
+			/*
+			 * wDatagramLength[0]
+			 * ethernet hdr + crc or larger than max frame size
+			 */
+			if ((dg_len < 14 + crc_len) ||
+					(dg_len > frame_max)) {
 				INFO(port->func.config->cdev,
 				     "Bad dgram length: %#X\n", dg_len);
 				goto err;
@@ -1283,6 +1312,37 @@ static int ncm_unwrap_ntb(struct gether *port,
 			index2 = get_ncm(&tmp, opts->dgram_item_len);
 			dg_len2 = get_ncm(&tmp, opts->dgram_item_len);
 
+			if (index2 == 0 || dg_len2 == 0)
+				break;
+
+			/* wDatagramIndex[1] */
+			if (ndp_after_header) {
+				if (index2 < opts->nth_size + opts->ndp_size) {
+					INFO(port->func.config->cdev,
+					     "Bad index: %#X\n", index2);
+					goto err;
+				}
+			} else {
+				if (index2 < opts->nth_size + opts->dpe_size) {
+					INFO(port->func.config->cdev,
+					     "Bad index: %#X\n", index2);
+					goto err;
+				}
+			}
+			if (index2 > block_len - opts->dpe_size) {
+				INFO(port->func.config->cdev,
+				     "Bad index: %#X\n", index2);
+				goto err;
+			}
+
+			/* wDatagramLength[1] */
+			if ((dg_len2 < 14 + crc_len) ||
+					(dg_len2 > frame_max)) {
+				INFO(port->func.config->cdev,
+				     "Bad dgram length: %#X\n", dg_len);
+				goto err;
+			}
+
 			/*
 			 * Copy the data into a new skb.
 			 * This ensures the truesize is correct
@@ -1299,9 +1359,6 @@ static int ncm_unwrap_ntb(struct gether *port,
 			ndp_len -= 2 * (opts->dgram_item_len * 2);
 
 			dgram_counter++;
-
-			if (index2 == 0 || dg_len2 == 0)
-				break;
 		} while (ndp_len > 2 * (opts->dgram_item_len * 2));
 	} while (ndp_index);
 
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index d94b814328c8..184165e27908 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -753,12 +753,13 @@ static int uasp_alloc_stream_res(struct f_uas *fu, struct uas_stream *stream)
 		goto err_sts;
 
 	return 0;
+
 err_sts:
-	usb_ep_free_request(fu->ep_status, stream->req_status);
-	stream->req_status = NULL;
-err_out:
 	usb_ep_free_request(fu->ep_out, stream->req_out);
 	stream->req_out = NULL;
+err_out:
+	usb_ep_free_request(fu->ep_in, stream->req_in);
+	stream->req_in = NULL;
 out:
 	return -ENOMEM;
 }
diff --git a/drivers/usb/gadget/u_f.h b/drivers/usb/gadget/u_f.h
index eaa13fd3dc7f..e313c3b8dcb1 100644
--- a/drivers/usb/gadget/u_f.h
+++ b/drivers/usb/gadget/u_f.h
@@ -14,6 +14,7 @@
 #define __U_F_H__
 
 #include <linux/usb/gadget.h>
+#include <linux/overflow.h>
 
 /* Variable Length Array Macros **********************************************/
 #define vla_group(groupname) size_t groupname##__next = 0
@@ -21,21 +22,36 @@
 
 #define vla_item(groupname, type, name, n) \
 	size_t groupname##_##name##__offset = ({			       \
-		size_t align_mask = __alignof__(type) - 1;		       \
-		size_t offset = (groupname##__next + align_mask) & ~align_mask;\
-		size_t size = (n) * sizeof(type);			       \
-		groupname##__next = offset + size;			       \
+		size_t offset = 0;					       \
+		if (groupname##__next != SIZE_MAX) {			       \
+			size_t align_mask = __alignof__(type) - 1;	       \
+			size_t size = array_size(n, sizeof(type));	       \
+			offset = (groupname##__next + align_mask) &	       \
+				  ~align_mask;				       \
+			if (check_add_overflow(offset, size,		       \
+					       &groupname##__next)) {          \
+				groupname##__next = SIZE_MAX;		       \
+				offset = 0;				       \
+			}						       \
+		}							       \
 		offset;							       \
 	})
 
 #define vla_item_with_sz(groupname, type, name, n) \
-	size_t groupname##_##name##__sz = (n) * sizeof(type);		       \
-	size_t groupname##_##name##__offset = ({			       \
-		size_t align_mask = __alignof__(type) - 1;		       \
-		size_t offset = (groupname##__next + align_mask) & ~align_mask;\
-		size_t size = groupname##_##name##__sz;			       \
-		groupname##__next = offset + size;			       \
-		offset;							       \
+	size_t groupname##_##name##__sz = array_size(n, sizeof(type));	        \
+	size_t groupname##_##name##__offset = ({			        \
+		size_t offset = 0;						\
+		if (groupname##__next != SIZE_MAX) {				\
+			size_t align_mask = __alignof__(type) - 1;		\
+			offset = (groupname##__next + align_mask) &		\
+				  ~align_mask;					\
+			if (check_add_overflow(offset, groupname##_##name##__sz,\
+							&groupname##__next)) {	\
+				groupname##__next = SIZE_MAX;			\
+				offset = 0;					\
+			}							\
+		}								\
+		offset;								\
 	})
 
 #define vla_ptr(ptr, groupname, name) \
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index fa6793065c7c..a6426dd1cfef 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -328,7 +328,7 @@ static int usba_config_fifo_table(struct usba_udc *udc)
 	switch (fifo_mode) {
 	default:
 		fifo_mode = 0;
-		/* fall through */
+		fallthrough;
 	case 0:
 		udc->fifo_cfg = NULL;
 		n = 0;
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index b2638e83bb49..a6f7b2594c09 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -250,7 +250,7 @@ static int dr_controller_setup(struct fsl_udc *udc)
 		break;
 	case FSL_USB2_PHY_UTMI_WIDE:
 		portctrl |= PORTSCX_PTW_16BIT;
-		/* fall through */
+		fallthrough;
 	case FSL_USB2_PHY_UTMI:
 	case FSL_USB2_PHY_UTMI_DUAL:
 		if (udc->pdata->have_sysif_regs) {
diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c
index cfafdd92c2a8..10324a7334fe 100644
--- a/drivers/usb/gadget/udc/pxa25x_udc.c
+++ b/drivers/usb/gadget/udc/pxa25x_udc.c
@@ -2340,12 +2340,12 @@ static int pxa25x_udc_probe(struct platform_device *pdev)
 	case PXA250_A0:
 	case PXA250_A1:
 		/* A0/A1 "not released"; ep 13, 15 unusable */
-		/* fall through */
+		fallthrough;
 	case PXA250_B2: case PXA210_B2:
 	case PXA250_B1: case PXA210_B1:
 	case PXA250_B0: case PXA210_B0:
 		/* OUT-DMA is broken ... */
-		/* fall through */
+		fallthrough;
 	case PXA250_C0: case PXA210_C0:
 		break;
 #elif	defined(CONFIG_ARCH_IXP4XX)
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index a87c0b26279e..3055d9abfec3 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -1019,7 +1019,7 @@ static int isp116x_hub_control(struct usb_hcd *hcd,
 			spin_lock_irqsave(&isp116x->lock, flags);
 			isp116x_write_reg32(isp116x, HCRHSTATUS, RH_HS_OCIC);
 			spin_unlock_irqrestore(&isp116x->lock, flags);
-			/* fall through */
+			fallthrough;
 		case C_HUB_LOCAL_POWER:
 			DBG("C_HUB_LOCAL_POWER\n");
 			break;
@@ -1421,10 +1421,10 @@ static int isp116x_bus_suspend(struct usb_hcd *hcd)
 		isp116x_write_reg32(isp116x, HCCONTROL,
 				    (val & ~HCCONTROL_HCFS) |
 				    HCCONTROL_USB_RESET);
-		/* fall through */
+		fallthrough;
 	case HCCONTROL_USB_RESET:
 		ret = -EBUSY;
-		/* fall through */
+		fallthrough;
 	default:		/* HCCONTROL_USB_SUSPEND */
 		spin_unlock_irqrestore(&isp116x->lock, flags);
 		break;
diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c
index bd40e597f256..5f5e8a64c8e2 100644
--- a/drivers/usb/host/ohci-exynos.c
+++ b/drivers/usb/host/ohci-exynos.c
@@ -171,9 +171,8 @@ static int exynos_ohci_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(res);
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "Failed to get IRQ\n");
-		err = -ENODEV;
+	if (irq < 0) {
+		err = irq;
 		goto fail_io;
 	}
 
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index b8961c0381cf..8c1bbac6d136 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -957,7 +957,8 @@ static void quirk_usb_disable_ehci(struct pci_dev *pdev)
 			ehci_bios_handoff(pdev, op_reg_base, cap, offset);
 			break;
 		case 0: /* Illegal reserved cap, set cap=0 so we exit */
-			cap = 0; /* fall through */
+			cap = 0;
+			fallthrough;
 		default:
 			dev_warn(&pdev->dev,
 				 "EHCI: unrecognized capability %02x\n",
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index fcc5ac5ce8b1..ccb0156fcebe 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -699,7 +699,7 @@ static void dbc_handle_xfer_event(struct xhci_dbc *dbc, union xhci_trb *event)
 	switch (comp_code) {
 	case COMP_SUCCESS:
 		remain_length = 0;
-	/* FALLTHROUGH */
+		fallthrough;
 	case COMP_SHORT_PACKET:
 		status = 0;
 		break;
diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 92e25a62fdb5..c88bffd68742 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -274,7 +274,7 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused)
 
 static int xhci_endpoint_context_show(struct seq_file *s, void *unused)
 {
-	int			dci;
+	int			ep_index;
 	dma_addr_t		dma;
 	struct xhci_hcd		*xhci;
 	struct xhci_ep_ctx	*ep_ctx;
@@ -283,9 +283,9 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused)
 
 	xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus));
 
-	for (dci = 1; dci < 32; dci++) {
-		ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, dci);
-		dma = dev->out_ctx->dma + dci * CTX_SIZE(xhci->hcc_params);
+	for (ep_index = 0; ep_index < 31; ep_index++) {
+		ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
+		dma = dev->out_ctx->dma + (ep_index + 1) * CTX_SIZE(xhci->hcc_params);
 		seq_printf(s, "%pad: %s\n", &dma,
 			   xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info),
 						  le32_to_cpu(ep_ctx->ep_info2),
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index c3554e37e09f..c799ca5361d4 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -740,15 +740,6 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 {
 	u32 pls = status_reg & PORT_PLS_MASK;
 
-	/* resume state is a xHCI internal state.
-	 * Do not report it to usb core, instead, pretend to be U3,
-	 * thus usb core knows it's not ready for transfer
-	 */
-	if (pls == XDEV_RESUME) {
-		*status |= USB_SS_PORT_LS_U3;
-		return;
-	}
-
 	/* When the CAS bit is set then warm reset
 	 * should be performed on port
 	 */
@@ -771,6 +762,16 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 		pls |= USB_PORT_STAT_CONNECTION;
 	} else {
 		/*
+		 * Resume state is an xHCI internal state.  Do not report it to
+		 * usb core, instead, pretend to be U3, thus usb core knows
+		 * it's not ready for transfer.
+		 */
+		if (pls == XDEV_RESUME) {
+			*status |= USB_SS_PORT_LS_U3;
+			return;
+		}
+
+		/*
 		 * If CAS bit isn't set but the Port is already at
 		 * Compliance Mode, fake a connection so the USB core
 		 * notices the Compliance state and resets the port.
@@ -1483,7 +1484,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			break;
 		case USB_PORT_FEAT_C_SUSPEND:
 			bus_state->port_c_suspend &= ~(1 << wIndex);
-			/* fall through */
+			fallthrough;
 		case USB_PORT_FEAT_C_RESET:
 		case USB_PORT_FEAT_C_BH_PORT_RESET:
 		case USB_PORT_FEAT_C_CONNECTION:
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 696fad50b478..fe405cd38dbc 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1311,7 +1311,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev,
 			interval = xhci_parse_microframe_interval(udev, ep);
 			break;
 		}
-		/* Fall through - SS and HS isoc/int have same decoding */
+		fallthrough;	/* SS and HS isoc/int have same decoding */
 
 	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
@@ -1331,7 +1331,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev,
 		 * since it uses the same rules as low speed interrupt
 		 * endpoints.
 		 */
-		/* fall through */
+		fallthrough;
 
 	case USB_SPEED_LOW:
 		if (usb_endpoint_xfer_int(&ep->desc) ||
diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c
index 59b1965ad0a3..f97ac9f52bf4 100644
--- a/drivers/usb/host/xhci-pci-renesas.c
+++ b/drivers/usb/host/xhci-pci-renesas.c
@@ -50,20 +50,6 @@
 #define RENESAS_RETRY	10000
 #define RENESAS_DELAY	10
 
-#define ROM_VALID_01 0x2013
-#define ROM_VALID_02 0x2026
-
-static int renesas_verify_fw_version(struct pci_dev *pdev, u32 version)
-{
-	switch (version) {
-	case ROM_VALID_01:
-	case ROM_VALID_02:
-		return 0;
-	}
-	dev_err(&pdev->dev, "FW has invalid version :%d\n", version);
-	return -EINVAL;
-}
-
 static int renesas_fw_download_image(struct pci_dev *dev,
 				     const u32 *fw, size_t step, bool rom)
 {
@@ -202,10 +188,7 @@ static int renesas_check_rom_state(struct pci_dev *pdev)
 
 	version &= RENESAS_FW_VERSION_FIELD;
 	version = version >> RENESAS_FW_VERSION_OFFSET;
-
-	err = renesas_verify_fw_version(pdev, version);
-	if (err)
-		return err;
+	dev_dbg(&pdev->dev, "Found ROM version: %x\n", version);
 
 	/*
 	 * Test if ROM is present and loaded, if so we can skip everything
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 2c255d0620b0..a741a38a4c69 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -2103,7 +2103,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 			break;
 		xhci_dbg(xhci, "TRB error %u, halted endpoint index = %u\n",
 			 trb_comp_code, ep_index);
-		/* else fall through */
+		fallthrough;
 	case COMP_STALL_ERROR:
 		/* Did we transfer part of the data (middle) phase? */
 		if (trb_type == TRB_DATA || trb_type == TRB_NORMAL)
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 014d79334f50..190923d8b246 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1136,7 +1136,7 @@ static struct phy *tegra_xusb_get_phy(struct tegra_xusb *tegra, char *name,
 	unsigned int i, phy_count = 0;
 
 	for (i = 0; i < tegra->soc->num_types; i++) {
-		if (!strncmp(tegra->soc->phy_types[i].name, "usb2",
+		if (!strncmp(tegra->soc->phy_types[i].name, name,
 							    strlen(name)))
 			return tegra->phys[phy_count+port];
 
@@ -1258,6 +1258,8 @@ static int tegra_xusb_init_usb_phy(struct tegra_xusb *tegra)
 
 	INIT_WORK(&tegra->id_work, tegra_xhci_id_work);
 	tegra->id_nb.notifier_call = tegra_xhci_id_notify;
+	tegra->otg_usb2_port = -EINVAL;
+	tegra->otg_usb3_port = -EINVAL;
 
 	for (i = 0; i < tegra->num_usb_phys; i++) {
 		struct phy *phy = tegra_xusb_get_phy(tegra, "usb2", i);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 3c41b14ecce7..f4cedcaee14b 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3236,10 +3236,11 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 
 	wait_for_completion(cfg_cmd->completion);
 
-	ep->ep_state &= ~EP_SOFT_CLEAR_TOGGLE;
 	xhci_free_command(xhci, cfg_cmd);
 cleanup:
 	xhci_free_command(xhci, stop_cmd);
+	if (ep->ep_state & EP_SOFT_CLEAR_TOGGLE)
+		ep->ep_state &= ~EP_SOFT_CLEAR_TOGGLE;
 }
 
 static int xhci_check_streams_endpoint(struct xhci_hcd *xhci,
@@ -4618,7 +4619,7 @@ static unsigned long long xhci_calculate_intel_u1_timeout(
 			break;
 		}
 		/* Otherwise the calculation is the same as isoc eps */
-		/* fall through */
+		fallthrough;
 	case USB_ENDPOINT_XFER_ISOC:
 		timeout_ns = xhci_service_interval_to_ns(desc);
 		timeout_ns = DIV_ROUND_UP_ULL(timeout_ns * 105, 100);
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index 407fe7570f3b..f8686139d6f3 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -426,7 +426,7 @@ static int lvs_rh_probe(struct usb_interface *intf,
 			USB_DT_SS_HUB_SIZE, USB_CTRL_GET_TIMEOUT);
 	if (ret < (USB_DT_HUB_NONVAR_SIZE + 2)) {
 		dev_err(&hdev->dev, "wrong root hub descriptor read %d\n", ret);
-		return ret;
+		return ret < 0 ? ret : -EINVAL;
 	}
 
 	/* submit urb to poll interrupt endpoint */
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 6e7d34e7fec4..b2e09883c7e2 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -492,7 +492,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
 	prepare_to_wait(&dev->waitq, &wait, TASK_INTERRUPTIBLE);
 	dev_dbg(&dev->interface->dev, "%s - submit %c\n", __func__,
 		dev->cntl_buffer[0]);
-	retval = usb_submit_urb(dev->cntl_urb, GFP_KERNEL);
+	retval = usb_submit_urb(dev->cntl_urb, GFP_ATOMIC);
 	if (retval >= 0)
 		timeout = schedule_timeout(YUREX_WRITE_TIMEOUT);
 	finish_wait(&dev->waitq, &wait);
diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c
index c545b27ea568..edb5b63d7063 100644
--- a/drivers/usb/musb/cppi_dma.c
+++ b/drivers/usb/musb/cppi_dma.c
@@ -975,7 +975,7 @@ static int cppi_channel_program(struct dma_channel *ch,
 		musb_dbg(musb, "%cX DMA%d not allocated!",
 				cppi_ch->transmit ? 'T' : 'R',
 				cppi_ch->index);
-		/* FALLTHROUGH */
+		fallthrough;
 	case MUSB_DMA_STATUS_FREE:
 		break;
 	}
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 5a56a03996b1..849e0b770130 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -852,7 +852,7 @@ static void musb_handle_intr_suspend(struct musb *musb, u8 devctl)
 	case OTG_STATE_B_IDLE:
 		if (!musb->is_active)
 			break;
-		/* fall through */
+		fallthrough;
 	case OTG_STATE_B_PERIPHERAL:
 		musb_g_suspend(musb);
 		musb->is_active = musb->g.b_hnp_enable;
@@ -972,9 +972,8 @@ static void musb_handle_intr_disconnect(struct musb *musb, u8 devctl)
 	case OTG_STATE_A_PERIPHERAL:
 		musb_hnp_stop(musb);
 		musb_root_disconnect(musb);
-		/* FALLTHROUGH */
+		fallthrough;
 	case OTG_STATE_B_WAIT_ACON:
-		/* FALLTHROUGH */
 	case OTG_STATE_B_PERIPHERAL:
 	case OTG_STATE_B_IDLE:
 		musb_g_disconnect(musb);
@@ -1009,7 +1008,7 @@ static void musb_handle_intr_reset(struct musb *musb)
 		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_SUSPEND:
 			musb_g_reset(musb);
-			/* FALLTHROUGH */
+			fallthrough;
 		case OTG_STATE_A_WAIT_BCON:	/* OPT TD.4.7-900ms */
 			/* never use invalid T(a_wait_bcon) */
 			musb_dbg(musb, "HNP: in %s, %d msec timeout",
@@ -1030,7 +1029,7 @@ static void musb_handle_intr_reset(struct musb *musb)
 			break;
 		case OTG_STATE_B_IDLE:
 			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
-			/* FALLTHROUGH */
+			fallthrough;
 		case OTG_STATE_B_PERIPHERAL:
 			musb_g_reset(musb);
 			break;
@@ -1471,7 +1470,7 @@ static int ep_config_from_table(struct musb *musb)
 	switch (fifo_mode) {
 	default:
 		fifo_mode = 0;
-		/* FALLTHROUGH */
+		fallthrough;
 	case 0:
 		cfg = mode_0_cfg;
 		n = ARRAY_SIZE(mode_0_cfg);
@@ -2018,7 +2017,7 @@ static void musb_pm_runtime_check_session(struct musb *musb)
 			musb->quirk_retries--;
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	case MUSB_QUIRK_A_DISCONNECT_19:
 		if (musb->quirk_retries && !musb->flush_irq_work) {
 			musb_dbg(musb,
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 19556c1a8ae8..30085b2be7b9 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -232,7 +232,7 @@ static int dsps_check_status(struct musb *musb, void *unused)
 			dsps_mod_timer_optional(glue);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 
 	case OTG_STATE_A_WAIT_BCON:
 		/* keep VBUS on for host-only mode */
@@ -242,7 +242,7 @@ static int dsps_check_status(struct musb *musb, void *unused)
 		}
 		musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
 		skip_session = 1;
-		/* fall through */
+		fallthrough;
 
 	case OTG_STATE_A_IDLE:
 	case OTG_STATE_B_IDLE:
@@ -793,7 +793,7 @@ static int dsps_create_musb_pdev(struct dsps_glue *glue,
 	case USB_SPEED_SUPER:
 		dev_warn(dev, "ignore incorrect maximum_speed "
 				"(super-speed) setting in dts");
-		/* fall through */
+		fallthrough;
 	default:
 		config->maximum_speed = USB_SPEED_HIGH;
 	}
diff --git a/drivers/usb/musb/musb_gadget_ep0.c b/drivers/usb/musb/musb_gadget_ep0.c
index 0ae3e0be043e..44d3cb02fa76 100644
--- a/drivers/usb/musb/musb_gadget_ep0.c
+++ b/drivers/usb/musb/musb_gadget_ep0.c
@@ -735,7 +735,7 @@ irqreturn_t musb_g_ep0_irq(struct musb *musb)
 			musb_writeb(mbase, MUSB_TESTMODE,
 					musb->test_mode_nr);
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 
 	case MUSB_EP0_STAGE_STATUSOUT:
 		/* end of sequence #1: write to host (TX state) */
@@ -767,7 +767,7 @@ irqreturn_t musb_g_ep0_irq(struct musb *musb)
 		 */
 		retval = IRQ_HANDLED;
 		musb->ep0_state = MUSB_EP0_STAGE_SETUP;
-		/* FALLTHROUGH */
+		fallthrough;
 
 	case MUSB_EP0_STAGE_SETUP:
 setup:
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 8b7d22a0c0fb..30c5e7de0761 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -360,7 +360,7 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb,
 				qh = first_qh(head);
 				break;
 			}
-			/* fall through */
+			fallthrough;
 
 		case USB_ENDPOINT_XFER_ISOC:
 		case USB_ENDPOINT_XFER_INT:
@@ -1019,7 +1019,7 @@ static bool musb_h_ep0_continue(struct musb *musb, u16 len, struct urb *urb)
 			musb->ep0_stage = MUSB_EP0_OUT;
 			more = true;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case MUSB_EP0_OUT:
 		fifo_count = min_t(size_t, qh->maxpacket,
 				   urb->transfer_buffer_length -
@@ -2222,7 +2222,7 @@ static int musb_urb_enqueue(
 			interval = max_t(u8, epd->bInterval, 1);
 			break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case USB_ENDPOINT_XFER_ISOC:
 		/* ISO always uses logarithmic encoding */
 		interval = min_t(u8, epd->bInterval, 16);
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index cb7ae297a3af..cafc69536e1d 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -211,7 +211,7 @@ void musb_root_disconnect(struct musb *musb)
 			musb->g.is_a_peripheral = 1;
 			break;
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case OTG_STATE_A_HOST:
 		musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		musb->is_active = 0;
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index d62c78b97cad..4232f1ce3fbf 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -104,7 +104,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 			if (error)
 				break;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
-			/* Fall through */
+			fallthrough;
 		case OTG_STATE_A_WAIT_VRISE:
 		case OTG_STATE_A_WAIT_BCON:
 		case OTG_STATE_A_HOST:
diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c
index 99890d1bbfcb..c26683a2702b 100644
--- a/drivers/usb/musb/tusb6010.c
+++ b/drivers/usb/musb/tusb6010.c
@@ -464,7 +464,7 @@ static void musb_do_idle(struct timer_list *t)
 			dev_dbg(musb->controller, "Nothing connected %s, turning off VBUS\n",
 					usb_otg_state_string(musb->xceiv->otg->state));
 		}
-		/* FALLTHROUGH */
+		fallthrough;
 	case OTG_STATE_A_IDLE:
 		tusb_musb_set_vbus(musb, 0);
 	default:
diff --git a/drivers/usb/phy/phy-jz4770.c b/drivers/usb/phy/phy-jz4770.c
index d4ee3cb721ea..f6d3731581eb 100644
--- a/drivers/usb/phy/phy-jz4770.c
+++ b/drivers/usb/phy/phy-jz4770.c
@@ -176,6 +176,7 @@ static int ingenic_usb_phy_init(struct usb_phy *phy)
 
 	/* Wait for PHY to reset */
 	usleep_range(30, 300);
+	reg = readl(priv->base + REG_USBPCR_OFFSET);
 	writel(reg & ~USBPCR_POR, priv->base + REG_USBPCR_OFFSET);
 	usleep_range(300, 1000);
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 871cdccf3a5f..9823bb424abd 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -713,6 +713,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTIUSBCONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e8373528264c..b5ca17a5967a 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -160,6 +160,7 @@
 #define XSENS_AWINDA_DONGLE_PID 0x0102
 #define XSENS_MTW_PID		0x0200	/* Xsens MTw */
 #define XSENS_MTDEVBOARD_PID	0x0300	/* Motion Tracker Development Board */
+#define XSENS_MTIUSBCONVERTER_PID	0x0301	/* MTi USB converter */
 #define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
 
 /* Xsens devices using FTDI VID */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 89b3192af326..0c6f160a214a 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1094,14 +1094,18 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
 	  .driver_info = RSVD(1) | RSVD(3) },
 	/* Quectel products using Quectel vendor ID */
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
-	  .driver_info = RSVD(4) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
@@ -1819,6 +1823,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9003, 0xff) },	/* Simcom SIM7500/SIM7600 MBIM mode */
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9011, 0xff),	/* Simcom SIM7500/SIM7600 RNDIS mode */
 	  .driver_info = RSVD(7) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9205, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT+ECM mode */
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9206, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT-only mode */
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X220_X500D),
diff --git a/drivers/usb/storage/sddr55.c b/drivers/usb/storage/sddr55.c
index c8a988d2cfdd..15dc25801cdc 100644
--- a/drivers/usb/storage/sddr55.c
+++ b/drivers/usb/storage/sddr55.c
@@ -592,7 +592,7 @@ static unsigned long sddr55_get_capacity(struct us_data *us) {
 	case 0x64:
 		info->pageshift = 8;
 		info->smallpageshift = 1;
-		/* fall through */
+		fallthrough;
 	case 0x5d: // 5d is a ROM card with pagesize 512.
 		return 0x00200000;
 
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index d592071119ba..08f9296431e9 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -688,7 +688,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 		break;
 	case DMA_BIDIRECTIONAL:
 		cmdinfo->state |= ALLOC_DATA_IN_URB | SUBMIT_DATA_IN_URB;
-		/* fall through */
+		fallthrough;
 	case DMA_TO_DEVICE:
 		cmdinfo->state |= ALLOC_DATA_OUT_URB | SUBMIT_DATA_OUT_URB;
 	case DMA_NONE:
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 220ae2c356ee..5732e9691f08 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2328,7 +2328,7 @@ UNUSUAL_DEV(  0x357d, 0x7788, 0x0114, 0x0114,
 		"JMicron",
 		"USB to ATA/ATAPI Bridge",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-		US_FL_BROKEN_FUA ),
+		US_FL_BROKEN_FUA | US_FL_IGNORE_UAS ),
 
 /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */
 UNUSUAL_DEV(  0x4102, 0x1020, 0x0100,  0x0100,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 162b09d69f62..711ab240058c 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -28,6 +28,13 @@
  * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
  */
 
+/* Reported-by: Till Dörges <doerges@pre-sense.de> */
+UNUSUAL_DEV(0x054c, 0x087d, 0x0000, 0x9999,
+		"Sony",
+		"PSZ-HA*",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /* Reported-by: Julian Groß <julian.g@posteo.de> */
 UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
 		"LaCie",
@@ -80,6 +87,13 @@ UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BROKEN_FUA),
 
+/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
+UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999,
+		"PNY",
+		"Pro Elite SSD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999,
 		"VIA",
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index e4021e13af40..ec7da0fa3cf8 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -61,14 +61,11 @@ enum {
 
 #define PMC_USB_ALTMODE_ORI_SHIFT	1
 #define PMC_USB_ALTMODE_UFP_SHIFT	3
-#define PMC_USB_ALTMODE_ORI_AUX_SHIFT	4
-#define PMC_USB_ALTMODE_ORI_HSL_SHIFT	5
 
 /* DP specific Mode Data bits */
 #define PMC_USB_ALTMODE_DP_MODE_SHIFT	8
 
 /* TBT specific Mode Data bits */
-#define PMC_USB_ALTMODE_HPD_HIGH	BIT(14)
 #define PMC_USB_ALTMODE_TBT_TYPE	BIT(17)
 #define PMC_USB_ALTMODE_CABLE_TYPE	BIT(18)
 #define PMC_USB_ALTMODE_ACTIVE_LINK	BIT(20)
@@ -179,15 +176,9 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state)
 	req.mode_data = (port->orientation - 1) << PMC_USB_ALTMODE_ORI_SHIFT;
 	req.mode_data |= (port->role - 1) << PMC_USB_ALTMODE_UFP_SHIFT;
 
-	req.mode_data |= sbu_orientation(port) << PMC_USB_ALTMODE_ORI_AUX_SHIFT;
-	req.mode_data |= hsl_orientation(port) << PMC_USB_ALTMODE_ORI_HSL_SHIFT;
-
 	req.mode_data |= (state->mode - TYPEC_STATE_MODAL) <<
 			 PMC_USB_ALTMODE_DP_MODE_SHIFT;
 
-	if (data->status & DP_STATUS_HPD_STATE)
-		req.mode_data |= PMC_USB_ALTMODE_HPD_HIGH;
-
 	ret = pmc_usb_command(port, (void *)&req, sizeof(req));
 	if (ret)
 		return ret;
@@ -212,9 +203,6 @@ pmc_usb_mux_tbt(struct pmc_usb_port *port, struct typec_mux_state *state)
 	req.mode_data = (port->orientation - 1) << PMC_USB_ALTMODE_ORI_SHIFT;
 	req.mode_data |= (port->role - 1) << PMC_USB_ALTMODE_UFP_SHIFT;
 
-	req.mode_data |= sbu_orientation(port) << PMC_USB_ALTMODE_ORI_AUX_SHIFT;
-	req.mode_data |= hsl_orientation(port) << PMC_USB_ALTMODE_ORI_HSL_SHIFT;
-
 	if (TBT_ADAPTER(data->device_mode) == TBT_ADAPTER_TBT3)
 		req.mode_data |= PMC_USB_ALTMODE_TBT_TYPE;
 
@@ -497,6 +485,7 @@ err_remove_ports:
 	for (i = 0; i < pmc->num_ports; i++) {
 		typec_switch_unregister(pmc->port[i].typec_sw);
 		typec_mux_unregister(pmc->port[i].typec_mux);
+		usb_role_switch_unregister(pmc->port[i].usb_sw);
 	}
 
 	return ret;
@@ -510,6 +499,7 @@ static int pmc_usb_remove(struct platform_device *pdev)
 	for (i = 0; i < pmc->num_ports; i++) {
 		typec_switch_unregister(pmc->port[i].typec_sw);
 		typec_mux_unregister(pmc->port[i].typec_mux);
+		usb_role_switch_unregister(pmc->port[i].usb_sw);
 	}
 
 	return 0;
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index f57d91fd0e09..bd80e03b2b6f 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -157,7 +157,7 @@ static enum typec_cc_status tcpci_to_typec_cc(unsigned int cc, bool sink)
 	case 0x3:
 		if (sink)
 			return TYPEC_CC_RP_3_0;
-		/* fall through */
+		fallthrough;
 	case 0x0:
 	default:
 		return TYPEC_CC_OPEN;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 3ef37202ee37..a48e3f90d196 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3372,13 +3372,31 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_state(port, SNK_HARD_RESET_SINK_OFF, 0);
 		break;
 	case SRC_HARD_RESET_VBUS_OFF:
-		tcpm_set_vconn(port, true);
+		/*
+		 * 7.1.5 Response to Hard Resets
+		 * Hard Reset Signaling indicates a communication failure has occurred and the
+		 * Source Shall stop driving VCONN, Shall remove Rp from the VCONN pin and Shall
+		 * drive VBUS to vSafe0V as shown in Figure 7-9.
+		 */
+		tcpm_set_vconn(port, false);
 		tcpm_set_vbus(port, false);
 		tcpm_set_roles(port, port->self_powered, TYPEC_SOURCE,
 			       tcpm_data_role_for_source(port));
-		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER);
+		/*
+		 * If tcpc fails to notify vbus off, TCPM will wait for PD_T_SAFE_0V +
+		 * PD_T_SRC_RECOVER before turning vbus back on.
+		 * From Table 7-12 Sequence Description for a Source Initiated Hard Reset:
+		 * 4. Policy Engine waits tPSHardReset after sending Hard Reset Signaling and then
+		 * tells the Device Policy Manager to instruct the power supply to perform a
+		 * Hard Reset. The transition to vSafe0V Shall occur within tSafe0V (t2).
+		 * 5. After tSrcRecover the Source applies power to VBUS in an attempt to
+		 * re-establish communication with the Sink and resume USB Default Operation.
+		 * The transition to vSafe5V Shall occur within tSrcTurnOn(t4).
+		 */
+		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SAFE_0V + PD_T_SRC_RECOVER);
 		break;
 	case SRC_HARD_RESET_VBUS_ON:
+		tcpm_set_vconn(port, true);
 		tcpm_set_vbus(port, true);
 		port->tcpc->set_pd_rx(port->tcpc, true);
 		tcpm_set_attached_state(port, true);
@@ -3944,7 +3962,11 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 		tcpm_set_state(port, SNK_HARD_RESET_WAIT_VBUS, 0);
 		break;
 	case SRC_HARD_RESET_VBUS_OFF:
-		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, 0);
+		/*
+		 * After establishing the vSafe0V voltage condition on VBUS, the Source Shall wait
+		 * tSrcRecover before re-applying VCONN and restoring VBUS to vSafe5V.
+		 */
+		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER);
 		break;
 	case HARD_RESET_SEND:
 		break;
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 048381c058a5..261131c9e37c 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -288,8 +288,6 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	struct typec_altmode *alt;
 	struct ucsi_dp *dp;
 
-	mutex_lock(&con->lock);
-
 	/* We can't rely on the firmware with the capabilities. */
 	desc->vdo |= DP_CAP_DP_SIGNALING | DP_CAP_RECEPTACLE;
 
@@ -298,15 +296,12 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	desc->vdo |= all_assignments << 16;
 
 	alt = typec_port_register_altmode(con->port, desc);
-	if (IS_ERR(alt)) {
-		mutex_unlock(&con->lock);
+	if (IS_ERR(alt))
 		return alt;
-	}
 
 	dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL);
 	if (!dp) {
 		typec_unregister_altmode(alt);
-		mutex_unlock(&con->lock);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -319,7 +314,5 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	alt->ops = &ucsi_displayport_ops;
 	typec_altmode_set_drvdata(alt, dp);
 
-	mutex_unlock(&con->lock);
-
 	return alt;
 }
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index affd024190c9..e680fcfdee60 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -146,40 +146,33 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd)
 	return UCSI_CCI_LENGTH(cci);
 }
 
-static int ucsi_run_command(struct ucsi *ucsi, u64 command,
-			    void *data, size_t size)
+int ucsi_send_command(struct ucsi *ucsi, u64 command,
+		      void *data, size_t size)
 {
 	u8 length;
 	int ret;
 
+	mutex_lock(&ucsi->ppm_lock);
+
 	ret = ucsi_exec_command(ucsi, command);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	length = ret;
 
 	if (data) {
 		ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, data, size);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = ucsi_acknowledge_command(ucsi);
 	if (ret)
-		return ret;
-
-	return length;
-}
-
-int ucsi_send_command(struct ucsi *ucsi, u64 command,
-		      void *retval, size_t size)
-{
-	int ret;
+		goto out;
 
-	mutex_lock(&ucsi->ppm_lock);
-	ret = ucsi_run_command(ucsi, command, retval, size);
+	ret = length;
+out:
 	mutex_unlock(&ucsi->ppm_lock);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ucsi_send_command);
@@ -205,7 +198,7 @@ void ucsi_altmode_update_active(struct ucsi_connector *con)
 	int i;
 
 	command = UCSI_GET_CURRENT_CAM | UCSI_CONNECTOR_NUMBER(con->num);
-	ret = ucsi_run_command(con->ucsi, command, &cur, sizeof(cur));
+	ret = ucsi_send_command(con->ucsi, command, &cur, sizeof(cur));
 	if (ret < 0) {
 		if (con->ucsi->version > 0x0100) {
 			dev_err(con->ucsi->dev,
@@ -354,7 +347,7 @@ ucsi_register_altmodes_nvidia(struct ucsi_connector *con, u8 recipient)
 		command |= UCSI_GET_ALTMODE_RECIPIENT(recipient);
 		command |= UCSI_GET_ALTMODE_CONNECTOR_NUMBER(con->num);
 		command |= UCSI_GET_ALTMODE_OFFSET(i);
-		len = ucsi_run_command(con->ucsi, command, &alt, sizeof(alt));
+		len = ucsi_send_command(con->ucsi, command, &alt, sizeof(alt));
 		/*
 		 * We are collecting all altmodes first and then registering.
 		 * Some type-C device will return zero length data beyond last
@@ -431,7 +424,7 @@ static int ucsi_register_altmodes(struct ucsi_connector *con, u8 recipient)
 		command |= UCSI_GET_ALTMODE_RECIPIENT(recipient);
 		command |= UCSI_GET_ALTMODE_CONNECTOR_NUMBER(con->num);
 		command |= UCSI_GET_ALTMODE_OFFSET(i);
-		len = ucsi_run_command(con->ucsi, command, alt, sizeof(alt));
+		len = ucsi_send_command(con->ucsi, command, alt, sizeof(alt));
 		if (len <= 0)
 			return len;
 
@@ -502,7 +495,7 @@ static void ucsi_get_pdos(struct ucsi_connector *con, int is_partner)
 	command |= UCSI_GET_PDOS_PARTNER_PDO(is_partner);
 	command |= UCSI_GET_PDOS_NUM_PDOS(UCSI_MAX_PDOS - 1);
 	command |= UCSI_GET_PDOS_SRC_PDOS;
-	ret = ucsi_run_command(ucsi, command, con->src_pdos,
+	ret = ucsi_send_command(ucsi, command, con->src_pdos,
 			       sizeof(con->src_pdos));
 	if (ret < 0) {
 		dev_err(ucsi->dev, "UCSI_GET_PDOS failed (%d)\n", ret);
@@ -681,7 +674,7 @@ static void ucsi_handle_connector_change(struct work_struct *work)
 		 */
 		command = UCSI_GET_CAM_SUPPORTED;
 		command |= UCSI_CONNECTOR_NUMBER(con->num);
-		ucsi_run_command(con->ucsi, command, NULL, 0);
+		ucsi_send_command(con->ucsi, command, NULL, 0);
 	}
 
 	if (con->status.change & UCSI_CONSTAT_PARTNER_CHANGE)
@@ -736,20 +729,24 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 	u32 cci;
 	int ret;
 
+	mutex_lock(&ucsi->ppm_lock);
+
 	ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command,
 				     sizeof(command));
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
 
 	do {
-		if (time_is_before_jiffies(tmo))
-			return -ETIMEDOUT;
+		if (time_is_before_jiffies(tmo)) {
+			ret = -ETIMEDOUT;
+			goto out;
+		}
 
 		ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
 		if (ret)
-			return ret;
+			goto out;
 
 		/* If the PPM is still doing something else, reset it again. */
 		if (cci & ~UCSI_CCI_RESET_COMPLETE) {
@@ -757,13 +754,15 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 						     &command,
 						     sizeof(command));
 			if (ret < 0)
-				return ret;
+				goto out;
 		}
 
 		msleep(20);
 	} while (!(cci & UCSI_CCI_RESET_COMPLETE));
 
-	return 0;
+out:
+	mutex_unlock(&ucsi->ppm_lock);
+	return ret;
 }
 
 static int ucsi_role_cmd(struct ucsi_connector *con, u64 command)
@@ -775,9 +774,7 @@ static int ucsi_role_cmd(struct ucsi_connector *con, u64 command)
 		u64 c;
 
 		/* PPM most likely stopped responding. Resetting everything. */
-		mutex_lock(&con->ucsi->ppm_lock);
 		ucsi_reset_ppm(con->ucsi);
-		mutex_unlock(&con->ucsi->ppm_lock);
 
 		c = UCSI_SET_NOTIFICATION_ENABLE | con->ucsi->ntfy;
 		ucsi_send_command(con->ucsi, c, NULL, 0);
@@ -901,12 +898,15 @@ static int ucsi_register_port(struct ucsi *ucsi, int index)
 	con->num = index + 1;
 	con->ucsi = ucsi;
 
+	/* Delay other interactions with the con until registration is complete */
+	mutex_lock(&con->lock);
+
 	/* Get connector capability */
 	command = UCSI_GET_CONNECTOR_CAPABILITY;
 	command |= UCSI_CONNECTOR_NUMBER(con->num);
-	ret = ucsi_run_command(ucsi, command, &con->cap, sizeof(con->cap));
+	ret = ucsi_send_command(ucsi, command, &con->cap, sizeof(con->cap));
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	if (con->cap.op_mode & UCSI_CONCAP_OPMODE_DRP)
 		cap->data = TYPEC_PORT_DRD;
@@ -938,27 +938,32 @@ static int ucsi_register_port(struct ucsi *ucsi, int index)
 
 	ret = ucsi_register_port_psy(con);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* Register the connector */
 	con->port = typec_register_port(ucsi->dev, cap);
-	if (IS_ERR(con->port))
-		return PTR_ERR(con->port);
+	if (IS_ERR(con->port)) {
+		ret = PTR_ERR(con->port);
+		goto out;
+	}
 
 	/* Alternate modes */
 	ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_CON);
-	if (ret)
+	if (ret) {
 		dev_err(ucsi->dev, "con%d: failed to register alt modes\n",
 			con->num);
+		goto out;
+	}
 
 	/* Get the status */
 	command = UCSI_GET_CONNECTOR_STATUS | UCSI_CONNECTOR_NUMBER(con->num);
-	ret = ucsi_run_command(ucsi, command, &con->status,
-			       sizeof(con->status));
+	ret = ucsi_send_command(ucsi, command, &con->status, sizeof(con->status));
 	if (ret < 0) {
 		dev_err(ucsi->dev, "con%d: failed to get status\n", con->num);
-		return 0;
+		ret = 0;
+		goto out;
 	}
+	ret = 0; /* ucsi_send_command() returns length on success */
 
 	switch (UCSI_CONSTAT_PARTNER_TYPE(con->status.flags)) {
 	case UCSI_CONSTAT_PARTNER_TYPE_UFP:
@@ -983,17 +988,21 @@ static int ucsi_register_port(struct ucsi *ucsi, int index)
 
 	if (con->partner) {
 		ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_SOP);
-		if (ret)
+		if (ret) {
 			dev_err(ucsi->dev,
 				"con%d: failed to register alternate modes\n",
 				con->num);
-		else
+			ret = 0;
+		} else {
 			ucsi_altmode_update_active(con);
+		}
 	}
 
 	trace_ucsi_register_port(con->num, &con->status);
 
-	return 0;
+out:
+	mutex_unlock(&con->lock);
+	return ret;
 }
 
 /**
@@ -1009,8 +1018,6 @@ static int ucsi_init(struct ucsi *ucsi)
 	int ret;
 	int i;
 
-	mutex_lock(&ucsi->ppm_lock);
-
 	/* Reset the PPM */
 	ret = ucsi_reset_ppm(ucsi);
 	if (ret) {
@@ -1021,13 +1028,13 @@ static int ucsi_init(struct ucsi *ucsi)
 	/* Enable basic notifications */
 	ucsi->ntfy = UCSI_ENABLE_NTFY_CMD_COMPLETE | UCSI_ENABLE_NTFY_ERROR;
 	command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy;
-	ret = ucsi_run_command(ucsi, command, NULL, 0);
+	ret = ucsi_send_command(ucsi, command, NULL, 0);
 	if (ret < 0)
 		goto err_reset;
 
 	/* Get PPM capabilities */
 	command = UCSI_GET_CAPABILITY;
-	ret = ucsi_run_command(ucsi, command, &ucsi->cap, sizeof(ucsi->cap));
+	ret = ucsi_send_command(ucsi, command, &ucsi->cap, sizeof(ucsi->cap));
 	if (ret < 0)
 		goto err_reset;
 
@@ -1054,12 +1061,10 @@ static int ucsi_init(struct ucsi *ucsi)
 	/* Enable all notifications */
 	ucsi->ntfy = UCSI_ENABLE_NTFY_ALL;
 	command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy;
-	ret = ucsi_run_command(ucsi, command, NULL, 0);
+	ret = ucsi_send_command(ucsi, command, NULL, 0);
 	if (ret < 0)
 		goto err_unregister;
 
-	mutex_unlock(&ucsi->ppm_lock);
-
 	return 0;
 
 err_unregister:
@@ -1074,8 +1079,6 @@ err_unregister:
 err_reset:
 	ucsi_reset_ppm(ucsi);
 err:
-	mutex_unlock(&ucsi->ppm_lock);
-
 	return ret;
 }
 
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 9fc4f338e870..c0aca2f0f23f 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -112,11 +112,15 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 
 static int ucsi_acpi_probe(struct platform_device *pdev)
 {
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
 	int ret;
 
+	if (adev->dep_unmet)
+		return -EPROBE_DEFER;
+
 	ua = devm_kzalloc(&pdev->dev, sizeof(*ua), GFP_KERNEL);
 	if (!ua)
 		return -ENOMEM;
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index 2305d425e6c9..9d7d642022d1 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -461,6 +461,11 @@ static void stub_disconnect(struct usb_device *udev)
 	return;
 }
 
+static bool usbip_match(struct usb_device *udev)
+{
+	return true;
+}
+
 #ifdef CONFIG_PM
 
 /* These functions need usb_port_suspend and usb_port_resume,
@@ -486,6 +491,7 @@ struct usb_device_driver stub_driver = {
 	.name		= "usbip-host",
 	.probe		= stub_probe,
 	.disconnect	= stub_disconnect,
+	.match		= usbip_match,
 #ifdef CONFIG_PM
 	.suspend	= stub_suspend,
 	.resume		= stub_resume,
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index 08f267a2aafe..64696d63fe07 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -84,7 +84,7 @@ struct ifcvf_hw {
 	void __iomem * const *base;
 	char config_msix_name[256];
 	struct vdpa_callback config_cb;
-
+	unsigned int config_irq;
 };
 
 struct ifcvf_adapter {
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 076d7ac5e723..8b4028556cb6 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -55,6 +55,7 @@ static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues)
 		vf->vring[i].irq = -EINVAL;
 	}
 
+	devm_free_irq(&pdev->dev, vf->config_irq, vf);
 	ifcvf_free_irq_vectors(pdev);
 }
 
@@ -74,10 +75,14 @@ static int ifcvf_request_irq(struct ifcvf_adapter *adapter)
 	snprintf(vf->config_msix_name, 256, "ifcvf[%s]-config\n",
 		 pci_name(pdev));
 	vector = 0;
-	irq = pci_irq_vector(pdev, vector);
-	ret = devm_request_irq(&pdev->dev, irq,
+	vf->config_irq = pci_irq_vector(pdev, vector);
+	ret = devm_request_irq(&pdev->dev, vf->config_irq,
 			       ifcvf_config_changed, 0,
 			       vf->config_msix_name, vf);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request config irq\n");
+		return ret;
+	}
 
 	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
 		snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n",
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 9df69d5efe8c..70676a6d1691 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -16,19 +16,19 @@
 #define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev)
 
 #define VALID_FEATURES_MASK                                                                        \
-	(BIT(VIRTIO_NET_F_CSUM) | BIT(VIRTIO_NET_F_GUEST_CSUM) |                                   \
-	 BIT(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT(VIRTIO_NET_F_MTU) | BIT(VIRTIO_NET_F_MAC) |   \
-	 BIT(VIRTIO_NET_F_GUEST_TSO4) | BIT(VIRTIO_NET_F_GUEST_TSO6) |                             \
-	 BIT(VIRTIO_NET_F_GUEST_ECN) | BIT(VIRTIO_NET_F_GUEST_UFO) | BIT(VIRTIO_NET_F_HOST_TSO4) | \
-	 BIT(VIRTIO_NET_F_HOST_TSO6) | BIT(VIRTIO_NET_F_HOST_ECN) | BIT(VIRTIO_NET_F_HOST_UFO) |   \
-	 BIT(VIRTIO_NET_F_MRG_RXBUF) | BIT(VIRTIO_NET_F_STATUS) | BIT(VIRTIO_NET_F_CTRL_VQ) |      \
-	 BIT(VIRTIO_NET_F_CTRL_RX) | BIT(VIRTIO_NET_F_CTRL_VLAN) |                                 \
-	 BIT(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT(VIRTIO_NET_F_GUEST_ANNOUNCE) |                      \
-	 BIT(VIRTIO_NET_F_MQ) | BIT(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT(VIRTIO_NET_F_HASH_REPORT) |  \
-	 BIT(VIRTIO_NET_F_RSS) | BIT(VIRTIO_NET_F_RSC_EXT) | BIT(VIRTIO_NET_F_STANDBY) |           \
-	 BIT(VIRTIO_NET_F_SPEED_DUPLEX) | BIT(VIRTIO_F_NOTIFY_ON_EMPTY) |                          \
-	 BIT(VIRTIO_F_ANY_LAYOUT) | BIT(VIRTIO_F_VERSION_1) | BIT(VIRTIO_F_ACCESS_PLATFORM) |      \
-	 BIT(VIRTIO_F_RING_PACKED) | BIT(VIRTIO_F_ORDER_PLATFORM) | BIT(VIRTIO_F_SR_IOV))
+	(BIT_ULL(VIRTIO_NET_F_CSUM) | BIT_ULL(VIRTIO_NET_F_GUEST_CSUM) |                                   \
+	 BIT_ULL(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT_ULL(VIRTIO_NET_F_MTU) | BIT_ULL(VIRTIO_NET_F_MAC) |   \
+	 BIT_ULL(VIRTIO_NET_F_GUEST_TSO4) | BIT_ULL(VIRTIO_NET_F_GUEST_TSO6) |                             \
+	 BIT_ULL(VIRTIO_NET_F_GUEST_ECN) | BIT_ULL(VIRTIO_NET_F_GUEST_UFO) | BIT_ULL(VIRTIO_NET_F_HOST_TSO4) | \
+	 BIT_ULL(VIRTIO_NET_F_HOST_TSO6) | BIT_ULL(VIRTIO_NET_F_HOST_ECN) | BIT_ULL(VIRTIO_NET_F_HOST_UFO) |   \
+	 BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) | BIT_ULL(VIRTIO_NET_F_STATUS) | BIT_ULL(VIRTIO_NET_F_CTRL_VQ) |      \
+	 BIT_ULL(VIRTIO_NET_F_CTRL_RX) | BIT_ULL(VIRTIO_NET_F_CTRL_VLAN) |                                 \
+	 BIT_ULL(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT_ULL(VIRTIO_NET_F_GUEST_ANNOUNCE) |                      \
+	 BIT_ULL(VIRTIO_NET_F_MQ) | BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT_ULL(VIRTIO_NET_F_HASH_REPORT) |  \
+	 BIT_ULL(VIRTIO_NET_F_RSS) | BIT_ULL(VIRTIO_NET_F_RSC_EXT) | BIT_ULL(VIRTIO_NET_F_STANDBY) |           \
+	 BIT_ULL(VIRTIO_NET_F_SPEED_DUPLEX) | BIT_ULL(VIRTIO_F_NOTIFY_ON_EMPTY) |                          \
+	 BIT_ULL(VIRTIO_F_ANY_LAYOUT) | BIT_ULL(VIRTIO_F_VERSION_1) | BIT_ULL(VIRTIO_F_ACCESS_PLATFORM) |      \
+	 BIT_ULL(VIRTIO_F_RING_PACKED) | BIT_ULL(VIRTIO_F_ORDER_PLATFORM) | BIT_ULL(VIRTIO_F_SR_IOV))
 
 #define VALID_STATUS_MASK                                                                          \
 	(VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK |        \
@@ -149,7 +149,7 @@ static bool mlx5_vdpa_debug;
 
 #define MLX5_LOG_VIO_FLAG(_feature)                                                                \
 	do {                                                                                       \
-		if (features & BIT(_feature))                                                      \
+		if (features & BIT_ULL(_feature))                                                  \
 			mlx5_vdpa_info(mvdev, "%s\n", #_feature);                                  \
 	} while (0)
 
@@ -750,10 +750,10 @@ static bool vq_is_tx(u16 idx)
 
 static u16 get_features_12_3(u64 features)
 {
-	return (!!(features & BIT(VIRTIO_NET_F_HOST_TSO4)) << 9) |
-	       (!!(features & BIT(VIRTIO_NET_F_HOST_TSO6)) << 8) |
-	       (!!(features & BIT(VIRTIO_NET_F_CSUM)) << 7) |
-	       (!!(features & BIT(VIRTIO_NET_F_GUEST_CSUM)) << 6);
+	return (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << 9) |
+	       (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << 8) |
+	       (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << 7) |
+	       (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_CSUM)) << 6);
 }
 
 static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
@@ -1439,13 +1439,13 @@ static u64 mlx_to_vritio_features(u16 dev_features)
 	u64 result = 0;
 
 	if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM)
-		result |= BIT(VIRTIO_NET_F_GUEST_CSUM);
+		result |= BIT_ULL(VIRTIO_NET_F_GUEST_CSUM);
 	if (dev_features & MLX5_VIRTIO_NET_F_CSUM)
-		result |= BIT(VIRTIO_NET_F_CSUM);
+		result |= BIT_ULL(VIRTIO_NET_F_CSUM);
 	if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6)
-		result |= BIT(VIRTIO_NET_F_HOST_TSO6);
+		result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO6);
 	if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4)
-		result |= BIT(VIRTIO_NET_F_HOST_TSO4);
+		result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO4);
 
 	return result;
 }
@@ -1459,15 +1459,15 @@ static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
 	dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
 	ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features);
 	if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
-		ndev->mvdev.mlx_features |= BIT(VIRTIO_F_VERSION_1);
-	ndev->mvdev.mlx_features |= BIT(VIRTIO_F_ACCESS_PLATFORM);
+		ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1);
+	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
 	print_features(mvdev, ndev->mvdev.mlx_features, false);
 	return ndev->mvdev.mlx_features;
 }
 
 static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features)
 {
-	if (!(features & BIT(VIRTIO_F_ACCESS_PLATFORM)))
+	if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM)))
 		return -EOPNOTSUPP;
 
 	return 0;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 620465c2a1da..1ab1f5cda4ac 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -990,7 +990,7 @@ static long vfio_pci_ioctl(void *device_data,
 		case VFIO_PCI_ERR_IRQ_INDEX:
 			if (pci_is_pcie(vdev->pdev))
 				break;
-		/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 		}
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 86a02aff8735..61ca8ab165dc 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -33,12 +33,14 @@
 
 struct vfio_pci_ioeventfd {
 	struct list_head	next;
+	struct vfio_pci_device	*vdev;
 	struct virqfd		*virqfd;
 	void __iomem		*addr;
 	uint64_t		data;
 	loff_t			pos;
 	int			bar;
 	int			count;
+	bool			test_mem;
 };
 
 struct vfio_pci_irq_ctx {
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 916b184df3a5..9e353c484ace 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -37,17 +37,70 @@
 #define vfio_ioread8	ioread8
 #define vfio_iowrite8	iowrite8
 
+#define VFIO_IOWRITE(size) \
+static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev,		\
+			bool test_mem, u##size val, void __iomem *io)	\
+{									\
+	if (test_mem) {							\
+		down_read(&vdev->memory_lock);				\
+		if (!__vfio_pci_memory_enabled(vdev)) {			\
+			up_read(&vdev->memory_lock);			\
+			return -EIO;					\
+		}							\
+	}								\
+									\
+	vfio_iowrite##size(val, io);					\
+									\
+	if (test_mem)							\
+		up_read(&vdev->memory_lock);				\
+									\
+	return 0;							\
+}
+
+VFIO_IOWRITE(8)
+VFIO_IOWRITE(16)
+VFIO_IOWRITE(32)
+#ifdef iowrite64
+VFIO_IOWRITE(64)
+#endif
+
+#define VFIO_IOREAD(size) \
+static int vfio_pci_ioread##size(struct vfio_pci_device *vdev,		\
+			bool test_mem, u##size *val, void __iomem *io)	\
+{									\
+	if (test_mem) {							\
+		down_read(&vdev->memory_lock);				\
+		if (!__vfio_pci_memory_enabled(vdev)) {			\
+			up_read(&vdev->memory_lock);			\
+			return -EIO;					\
+		}							\
+	}								\
+									\
+	*val = vfio_ioread##size(io);					\
+									\
+	if (test_mem)							\
+		up_read(&vdev->memory_lock);				\
+									\
+	return 0;							\
+}
+
+VFIO_IOREAD(8)
+VFIO_IOREAD(16)
+VFIO_IOREAD(32)
+
 /*
  * Read or write from an __iomem region (MMIO or I/O port) with an excluded
  * range which is inaccessible.  The excluded range drops writes and fills
  * reads with -1.  This is intended for handling MSI-X vector tables and
  * leftover space for ROM BARs.
  */
-static ssize_t do_io_rw(void __iomem *io, char __user *buf,
+static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem,
+			void __iomem *io, char __user *buf,
 			loff_t off, size_t count, size_t x_start,
 			size_t x_end, bool iswrite)
 {
 	ssize_t done = 0;
+	int ret;
 
 	while (count) {
 		size_t fillable, filled;
@@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				vfio_iowrite32(val, io + off);
+				ret = vfio_pci_iowrite32(vdev, test_mem,
+							 val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread32(io + off);
+				ret = vfio_pci_ioread32(vdev, test_mem,
+							&val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 4))
 					return -EFAULT;
@@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				vfio_iowrite16(val, io + off);
+				ret = vfio_pci_iowrite16(vdev, test_mem,
+							 val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread16(io + off);
+				ret = vfio_pci_ioread16(vdev, test_mem,
+							&val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 2))
 					return -EFAULT;
@@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				vfio_iowrite8(val, io + off);
+				ret = vfio_pci_iowrite8(vdev, test_mem,
+							val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread8(io + off);
+				ret = vfio_pci_ioread8(vdev, test_mem,
+						       &val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 1))
 					return -EFAULT;
@@ -178,14 +249,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	count = min(count, (size_t)(end - pos));
 
-	if (res->flags & IORESOURCE_MEM) {
-		down_read(&vdev->memory_lock);
-		if (!__vfio_pci_memory_enabled(vdev)) {
-			up_read(&vdev->memory_lock);
-			return -EIO;
-		}
-	}
-
 	if (bar == PCI_ROM_RESOURCE) {
 		/*
 		 * The ROM can fill less space than the BAR, so we start the
@@ -213,7 +276,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 		x_end = vdev->msix_offset + vdev->msix_size;
 	}
 
-	done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite);
+	done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos,
+			count, x_start, x_end, iswrite);
 
 	if (done >= 0)
 		*ppos += done;
@@ -221,9 +285,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 	if (bar == PCI_ROM_RESOURCE)
 		pci_unmap_rom(pdev, io);
 out:
-	if (res->flags & IORESOURCE_MEM)
-		up_read(&vdev->memory_lock);
-
 	return done;
 }
 
@@ -278,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
 		return ret;
 	}
 
-	done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite);
+	/*
+	 * VGA MMIO is a legacy, non-BAR resource that hopefully allows
+	 * probing, so we don't currently worry about access in relation
+	 * to the memory enable bit in the command register.
+	 */
+	done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite);
 
 	vga_put(vdev->pdev, rsrc);
 
@@ -296,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
 
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_iowrite8(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem,
+				  ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_iowrite16(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_iowrite32(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_iowrite64(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
@@ -378,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
 		goto out_unlock;
 	}
 
+	ioeventfd->vdev = vdev;
 	ioeventfd->addr = vdev->barmap[bar] + pos;
 	ioeventfd->data = data;
 	ioeventfd->pos = pos;
 	ioeventfd->bar = bar;
 	ioeventfd->count = count;
+	ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM;
 
 	ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
 				 NULL, NULL, &ioeventfd->virqfd, fd);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 6990fc711a80..5fbf0c1f7433 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1424,13 +1424,16 @@ static int vfio_bus_type(struct device *dev, void *data)
 static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			     struct vfio_domain *domain)
 {
-	struct vfio_domain *d;
+	struct vfio_domain *d = NULL;
 	struct rb_node *n;
 	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	int ret;
 
 	/* Arbitrarily pick the first domain in the list for lookups */
-	d = list_first_entry(&iommu->domain_list, struct vfio_domain, next);
+	if (!list_empty(&iommu->domain_list))
+		d = list_first_entry(&iommu->domain_list,
+				     struct vfio_domain, next);
+
 	n = rb_first(&iommu->dma_list);
 
 	for (; n; n = rb_next(n)) {
@@ -1448,6 +1451,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 				phys_addr_t p;
 				dma_addr_t i;
 
+				if (WARN_ON(!d)) { /* mapped w/o a domain?! */
+					ret = -EINVAL;
+					goto unwind;
+				}
+
 				phys = iommu_iova_to_phys(d->domain, iova);
 
 				if (WARN_ON(!phys)) {
@@ -1477,7 +1485,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 				if (npage <= 0) {
 					WARN_ON(!npage);
 					ret = (int)npage;
-					return ret;
+					goto unwind;
 				}
 
 				phys = pfn << PAGE_SHIFT;
@@ -1486,14 +1494,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 
 			ret = iommu_map(domain->domain, iova, phys,
 					size, dma->prot | domain->prot);
-			if (ret)
-				return ret;
+			if (ret) {
+				if (!dma->iommu_mapped)
+					vfio_unpin_pages_remote(dma, iova,
+							phys >> PAGE_SHIFT,
+							size >> PAGE_SHIFT,
+							true);
+				goto unwind;
+			}
 
 			iova += size;
 		}
+	}
+
+	/* All dmas are now mapped, defer to second tree walk for unwind */
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+
 		dma->iommu_mapped = true;
 	}
+
 	return 0;
+
+unwind:
+	for (; n; n = rb_prev(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+		dma_addr_t iova;
+
+		if (dma->iommu_mapped) {
+			iommu_unmap(domain->domain, dma->iova, dma->size);
+			continue;
+		}
+
+		iova = dma->iova;
+		while (iova < dma->iova + dma->size) {
+			phys_addr_t phys, p;
+			size_t size;
+			dma_addr_t i;
+
+			phys = iommu_iova_to_phys(domain->domain, iova);
+			if (!phys) {
+				iova += PAGE_SIZE;
+				continue;
+			}
+
+			size = PAGE_SIZE;
+			p = phys + size;
+			i = iova + size;
+			while (i < dma->iova + dma->size &&
+			       p == iommu_iova_to_phys(domain->domain, i)) {
+				size += PAGE_SIZE;
+				p += PAGE_SIZE;
+				i += PAGE_SIZE;
+			}
+
+			iommu_unmap(domain->domain, iova, size);
+			vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT,
+						size >> PAGE_SHIFT, true);
+		}
+	}
+
+	return ret;
 }
 
 /*
@@ -2378,7 +2439,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 		break;
 	case VFIO_TYPE1_NESTING_IOMMU:
 		iommu->nesting = true;
-		/* fall through */
+		fallthrough;
 	case VFIO_TYPE1v2_IOMMU:
 		iommu->v2 = true;
 		break;
diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c
index 1f0ca6e44410..34aec4ba331e 100644
--- a/drivers/vhost/iotlb.c
+++ b/drivers/vhost/iotlb.c
@@ -159,8 +159,8 @@ vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last)
 EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first);
 
 /**
- * vhost_iotlb_itree_first - return the next overlapped range
- * @iotlb: the IOTLB
+ * vhost_iotlb_itree_next - return the next overlapped range
+ * @map: the starting map node
  * @start: start of IOVA range
  * @end: end of IOVA range
  */
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5857d4eec9d7..b45519ca66a7 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2537,7 +2537,7 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		r = vhost_update_used_flags(vq);
 		if (r)
-			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			vq_err(vq, "Failed to disable notification at %p: %d\n",
 			       &vq->used->flags, r);
 	}
 }
diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c
index ddc7f5f0401f..8ec19425671f 100644
--- a/drivers/video/backlight/adp8860_bl.c
+++ b/drivers/video/backlight/adp8860_bl.c
@@ -681,7 +681,7 @@ static int adp8860_probe(struct i2c_client *client,
 	switch (ADP8860_MANID(reg_val)) {
 	case ADP8863_MANUFID:
 		data->gdwn_dis = !!pdata->gdwn_dis;
-		/* fall through */
+		fallthrough;
 	case ADP8860_MANUFID:
 		data->en_ambl_sens = !!pdata->en_ambl_sens;
 		break;
diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c
index a88dcb63eeb4..2df56bd303d2 100644
--- a/drivers/video/fbdev/controlfb.c
+++ b/drivers/video/fbdev/controlfb.c
@@ -49,6 +49,8 @@
 #include <linux/cuda.h>
 #ifdef CONFIG_PPC_PMAC
 #include <asm/prom.h>
+#endif
+#ifdef CONFIG_BOOTX_TEXT
 #include <asm/btext.h>
 #endif
 
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 8a31fc2b2258..66167830fefd 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -2191,6 +2191,9 @@ static void updatescrollmode(struct fbcon_display *p,
 	}
 }
 
+#define PITCH(w) (((w) + 7) >> 3)
+#define CALC_FONTSZ(h, p, c) ((h) * (p) * (c)) /* size = height * pitch * charcount */
+
 static int fbcon_resize(struct vc_data *vc, unsigned int width, 
 			unsigned int height, unsigned int user)
 {
@@ -2200,6 +2203,24 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width,
 	struct fb_var_screeninfo var = info->var;
 	int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh;
 
+	if (ops->p && ops->p->userfont && FNTSIZE(vc->vc_font.data)) {
+		int size;
+		int pitch = PITCH(vc->vc_font.width);
+
+		/*
+		 * If user font, ensure that a possible change to user font
+		 * height or width will not allow a font data out-of-bounds access.
+		 * NOTE: must use original charcount in calculation as font
+		 * charcount can change and cannot be used to determine the
+		 * font data allocated size.
+		 */
+		if (pitch <= 0)
+			return -EINVAL;
+		size = CALC_FONTSZ(vc->vc_font.height, pitch, FNTCHARCNT(vc->vc_font.data));
+		if (size > FNTSIZE(vc->vc_font.data))
+			return -EINVAL;
+	}
+
 	virt_w = FBCON_SWAP(ops->rotate, width, height);
 	virt_h = FBCON_SWAP(ops->rotate, height, width);
 	virt_fw = FBCON_SWAP(ops->rotate, vc->vc_font.width,
@@ -2652,7 +2673,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font,
 	int size;
 	int i, csum;
 	u8 *new_data, *data = font->data;
-	int pitch = (font->width+7) >> 3;
+	int pitch = PITCH(font->width);
 
 	/* Is there a reason why fbconsole couldn't handle any charcount >256?
 	 * If not this check should be changed to charcount < 256 */
@@ -2668,7 +2689,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font,
 	if (fbcon_invalid_charcount(info, charcount))
 		return -EINVAL;
 
-	size = h * pitch * charcount;
+	size = CALC_FONTSZ(h, pitch, charcount);
 
 	new_data = kmalloc(FONT_EXTRA_WORDS * sizeof(int) + size, GFP_USER);
 
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 65491ae74808..e57c00824965 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -453,7 +453,7 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (efi_enabled(EFI_BOOT) &&
+	if (efi_enabled(EFI_MEMMAP) &&
 	    !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
 		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
 		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index e4c3c8b65da4..02411d89cb46 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -648,13 +648,13 @@ static int synthvid_connect_vsp(struct hv_device *hdev)
 		ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN10);
 		if (!ret)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	case VERSION_WIN8:
 	case VERSION_WIN8_1:
 		ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN8);
 		if (!ret)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	case VERSION_WS2008:
 	case VERSION_WIN7:
 		ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN7);
diff --git a/drivers/video/fbdev/mmp/fb/mmpfb.c b/drivers/video/fbdev/mmp/fb/mmpfb.c
index 01c75c031cb6..39ebbe026ddf 100644
--- a/drivers/video/fbdev/mmp/fb/mmpfb.c
+++ b/drivers/video/fbdev/mmp/fb/mmpfb.c
@@ -90,8 +90,6 @@ static int var_to_pixfmt(struct fb_var_screeninfo *var)
 			else
 				return PIXFMT_BGR888UNPACK;
 		}
-
-		/* fall through */
 	}
 
 	return -EINVAL;
diff --git a/drivers/video/fbdev/nvidia/nv_hw.c b/drivers/video/fbdev/nvidia/nv_hw.c
index 8335da4ca30e..9b0a324bb1b4 100644
--- a/drivers/video/fbdev/nvidia/nv_hw.c
+++ b/drivers/video/fbdev/nvidia/nv_hw.c
@@ -896,7 +896,7 @@ void NVCalcStateExt(struct nvidia_par *par,
 		if (!par->FlatPanel)
 			state->control = NV_RD32(par->PRAMDAC0, 0x0580) &
 				0xeffffeff;
-		/* fallthrough */
+		fallthrough;
 	case NV_ARCH_10:
 	case NV_ARCH_20:
 	case NV_ARCH_30:
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index eedfbd3572a8..47e6a1d0d229 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -60,8 +60,6 @@ static int determine_best_pix_fmt(struct fb_var_screeninfo *var)
 			else
 				return PIX_FMT_BGR1555;
 		}
-
-		/* fall through */
 	}
 
 	/*
@@ -87,8 +85,6 @@ static int determine_best_pix_fmt(struct fb_var_screeninfo *var)
 			else
 				return PIX_FMT_BGR888UNPACK;
 		}
-
-		/* fall through */
 	}
 
 	return -EINVAL;
diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c
index 9b3493846f4d..ce55b9d2e862 100644
--- a/drivers/video/fbdev/riva/fbdev.c
+++ b/drivers/video/fbdev/riva/fbdev.c
@@ -1093,7 +1093,7 @@ static int rivafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 		break;
 	case 9 ... 15:
 		var->green.length = 5;
-		/* fall through */
+		fallthrough;
 	case 16:
 		var->bits_per_pixel = 16;
 		/* The Riva128 supports RGB555 only */
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index ac140962b1bf..03c736f6f3d0 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -1739,7 +1739,7 @@ static int	sisfb_ioctl(struct fb_info *info, unsigned int cmd,
 		if(ivideo->warncount++ < 10)
 			printk(KERN_INFO
 				"sisfb: Deprecated ioctl call received - update your application!\n");
-		/* fall through */
+		fallthrough;
 	   case SISFB_GET_INFO:  /* For communication with X driver */
 		ivideo->sisfb_infoblock.sisfb_id         = SISFB_ID;
 		ivideo->sisfb_infoblock.sisfb_version    = VER_MAJOR;
@@ -1793,7 +1793,7 @@ static int	sisfb_ioctl(struct fb_info *info, unsigned int cmd,
 		if(ivideo->warncount++ < 10)
 			printk(KERN_INFO
 				"sisfb: Deprecated ioctl call received - update your application!\n");
-		/* fall through */
+		fallthrough;
 	   case SISFB_GET_VBRSTATUS:
 		if(sisfb_CheckVBRetrace(ivideo))
 			return put_user((u32)1, argp);
@@ -1804,7 +1804,7 @@ static int	sisfb_ioctl(struct fb_info *info, unsigned int cmd,
 		if(ivideo->warncount++ < 10)
 			printk(KERN_INFO
 				"sisfb: Deprecated ioctl call received - update your application!\n");
-		/* fall through */
+		fallthrough;
 	   case SISFB_GET_AUTOMAXIMIZE:
 		if(ivideo->sisfb_max)
 			return put_user((u32)1, argp);
@@ -1815,7 +1815,7 @@ static int	sisfb_ioctl(struct fb_info *info, unsigned int cmd,
 		if(ivideo->warncount++ < 10)
 			printk(KERN_INFO
 				"sisfb: Deprecated ioctl call received - update your application!\n");
-		/* fall through */
+		fallthrough;
 	   case SISFB_SET_AUTOMAXIMIZE:
 		if(get_user(gpu32, argp))
 			return -EFAULT;
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index de953ddb6312..265865610edc 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -999,7 +999,7 @@ stifb_blank(int blank_mode, struct fb_info *info)
 	case S9000_ID_HCRX:
 		HYPER_ENABLE_DISABLE_DISPLAY(fb, enable);
 		break;
-	case S9000_ID_A1659A:	/* fall through */
+	case S9000_ID_A1659A:
 	case S9000_ID_TIMBER:
 	case CRX24_OVERLAY_PLANES:
 	default:
@@ -1157,7 +1157,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 			dev_name);
 		   goto out_err0;
 		}
-		/* fall through */
+		fallthrough;
 	case S9000_ID_ARTIST:
 	case S9000_ID_HCRX:
 	case S9000_ID_TIMBER:
diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c
index 52f273af6cae..1e8a38a7967d 100644
--- a/drivers/video/fbdev/vga16fb.c
+++ b/drivers/video/fbdev/vga16fb.c
@@ -1121,7 +1121,7 @@ static void vga_8planes_imageblit(struct fb_info *info, const struct fb_image *i
         char oldop = setop(0);
         char oldsr = setsr(0);
         char oldmask = selectmask();
-        const char *cdat = image->data;
+	const unsigned char *cdat = image->data;
 	u32 dx = image->dx;
         char __iomem *where;
         int y;
diff --git a/drivers/video/fbdev/via/lcd.c b/drivers/video/fbdev/via/lcd.c
index 3fea01db58d6..4a869402d120 100644
--- a/drivers/video/fbdev/via/lcd.c
+++ b/drivers/video/fbdev/via/lcd.c
@@ -744,7 +744,7 @@ static void set_lcd_output_path(int set_iga, int output_interface)
 		    viaparinfo->chip_info->gfx_chip_name))
 			viafb_write_reg_mask(CR97, VIACR, 0x84,
 				       BIT7 + BIT2 + BIT1 + BIT0);
-		/* fall through */
+		fallthrough;
 	case INTERFACE_DVP0:
 	case INTERFACE_DVP1:
 	case INTERFACE_DFP_HIGH:
diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c
index 9673eb12dacd..f22ebe89fe13 100644
--- a/drivers/watchdog/sc1200wdt.c
+++ b/drivers/watchdog/sc1200wdt.c
@@ -234,7 +234,7 @@ static long sc1200wdt_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		timeout = new_timeout;
 		sc1200wdt_write_data(WDTO, timeout);
-		/* fall through - and return the new timeout */
+		fallthrough;	/* and return the new timeout */
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout * 60, p);
diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c
index 184a06a74f83..c00627825de8 100644
--- a/drivers/watchdog/wdrtas.c
+++ b/drivers/watchdog/wdrtas.c
@@ -332,7 +332,7 @@ static long wdrtas_ioctl(struct file *file, unsigned int cmd,
 			wdrtas_interval = i;
 		else
 			wdrtas_interval = wdrtas_get_interval(i);
-		/* fallthrough */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(wdrtas_interval, argp);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index ea6c1e7e3e42..41645fe6ad48 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -325,4 +325,14 @@ config XEN_HAVE_VPMU
 config XEN_FRONT_PGDIR_SHBUF
 	tristate
 
+config XEN_UNPOPULATED_ALLOC
+	bool "Use unpopulated memory ranges for guest mappings"
+	depends on X86 && ZONE_DEVICE
+	default XEN_BACKEND || XEN_GNTDEV || XEN_DOM0
+	help
+	  Use unpopulated memory ranges in order to create mappings for guest
+	  memory regions, including grant maps and foreign pages. This avoids
+	  having to balloon out RAM regions in order to obtain physical memory
+	  space to create such mappings.
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index c25c9a699b48..babdca808861 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -41,3 +41,4 @@ xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
 obj-$(CONFIG_XEN_FRONT_PGDIR_SHBUF)	+= xen-front-pgdir-shbuf.o
+obj-$(CONFIG_XEN_UNPOPULATED_ALLOC)	+= unpopulated-alloc.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37ffccda8bb8..51427c752b37 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -653,7 +653,7 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 static void __init balloon_add_region(unsigned long start_pfn,
 				      unsigned long pages)
 {
@@ -707,7 +707,7 @@ static int __init balloon_init(void)
 	register_sysctl_table(xen_root);
 #endif
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 	{
 		int i;
 
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 140c7bf33a98..90b8f56fbadb 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -156,7 +156,7 @@ int get_evtchn_to_irq(evtchn_port_t evtchn)
 /* Get info for IRQ */
 struct irq_info *info_for_irq(unsigned irq)
 {
-	return irq_get_handler_data(irq);
+	return irq_get_chip_data(irq);
 }
 
 /* Constructors for packed IRQ information. */
@@ -377,7 +377,7 @@ static void xen_irq_init(unsigned irq)
 	info->type = IRQT_UNBOUND;
 	info->refcnt = -1;
 
-	irq_set_handler_data(irq, info);
+	irq_set_chip_data(irq, info);
 
 	list_add_tail(&info->list, &xen_irq_list_head);
 }
@@ -426,14 +426,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 
 static void xen_free_irq(unsigned irq)
 {
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (WARN_ON(!info))
 		return;
 
 	list_del(&info->list);
 
-	irq_set_handler_data(irq, NULL);
+	irq_set_chip_data(irq, NULL);
 
 	WARN_ON(info->refcnt > 0);
 
@@ -603,7 +603,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 static void __unbind_from_irq(unsigned int irq)
 {
 	evtchn_port_t evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (info->refcnt > 0) {
 		info->refcnt--;
@@ -1108,7 +1108,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 
 void unbind_from_irqhandler(unsigned int irq, void *dev_id)
 {
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (WARN_ON(!info))
 		return;
@@ -1142,7 +1142,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn)
 	if (irq == -1)
 		return -ENOENT;
 
-	info = irq_get_handler_data(irq);
+	info = irq_get_chip_data(irq);
 
 	if (!info)
 		return -ENOENT;
@@ -1170,7 +1170,7 @@ int evtchn_get(evtchn_port_t evtchn)
 	if (irq == -1)
 		goto done;
 
-	info = irq_get_handler_data(irq);
+	info = irq_get_chip_data(irq);
 
 	if (!info)
 		goto done;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 8d06bf1cc347..523dcdf39cc9 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -801,7 +801,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 {
 	int ret;
 
-	ret = alloc_xenballooned_pages(nr_pages, pages);
+	ret = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (ret < 0)
 		return ret;
 
@@ -836,7 +836,7 @@ EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
 void gnttab_free_pages(int nr_pages, struct page **pages)
 {
 	gnttab_pages_clear_private(nr_pages, pages);
-	free_xenballooned_pages(nr_pages, pages);
+	xen_free_unpopulated_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 63abe6c3642b..b0c73c58f987 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -424,7 +424,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
 	if (pages == NULL)
 		return -ENOMEM;
 
-	rc = alloc_xenballooned_pages(numpgs, pages);
+	rc = xen_alloc_unpopulated_pages(numpgs, pages);
 	if (rc != 0) {
 		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
 			numpgs, rc);
@@ -895,7 +895,7 @@ static void privcmd_close(struct vm_area_struct *vma)
 
 	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
 	if (rc == 0)
-		free_xenballooned_pages(numpgs, pages);
+		xen_free_unpopulated_pages(numpgs, pages);
 	else
 		pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
 			numpgs, rc);
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index b43b5595e988..72d725a0ab5c 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -1263,7 +1263,7 @@ static void pvcalls_front_changed(struct xenbus_device *dev,
 		if (dev->state == XenbusStateClosed)
 			break;
 		/* Missed the backend's CLOSING state */
-		/* fall through */
+		fallthrough;
 	case XenbusStateClosing:
 		xenbus_frontend_closed(dev);
 		break;
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
new file mode 100644
index 000000000000..3b98dc921426
--- /dev/null
+++ b/drivers/xen/unpopulated-alloc.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memremap.h>
+#include <linux/slab.h>
+
+#include <asm/page.h>
+
+#include <xen/page.h>
+#include <xen/xen.h>
+
+static DEFINE_MUTEX(list_lock);
+static LIST_HEAD(page_list);
+static unsigned int list_count;
+
+static int fill_list(unsigned int nr_pages)
+{
+	struct dev_pagemap *pgmap;
+	void *vaddr;
+	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
+	int ret;
+
+	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->type = MEMORY_DEVICE_GENERIC;
+	pgmap->res.name = "Xen scratch";
+	pgmap->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = allocate_resource(&iomem_resource, &pgmap->res,
+				alloc_pages * PAGE_SIZE, 0, -1,
+				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	if (ret < 0) {
+		pr_err("Cannot allocate new IOMEM resource\n");
+		kfree(pgmap);
+		return ret;
+	}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+        /*
+         * memremap will build page tables for the new memory so
+         * the p2m must contain invalid entries so the correct
+         * non-present PTEs will be written.
+         *
+         * If a failure occurs, the original (identity) p2m entries
+         * are not restored since this region is now known not to
+         * conflict with any devices.
+         */
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		xen_pfn_t pfn = PFN_DOWN(pgmap->res.start);
+
+		for (i = 0; i < alloc_pages; i++) {
+			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
+				pr_warn("set_phys_to_machine() failed, no memory added\n");
+				release_resource(&pgmap->res);
+				kfree(pgmap);
+				return -ENOMEM;
+			}
+                }
+	}
+#endif
+
+	vaddr = memremap_pages(pgmap, NUMA_NO_NODE);
+	if (IS_ERR(vaddr)) {
+		pr_err("Cannot remap memory range\n");
+		release_resource(&pgmap->res);
+		kfree(pgmap);
+		return PTR_ERR(vaddr);
+	}
+
+	for (i = 0; i < alloc_pages; i++) {
+		struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i);
+
+		BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i));
+		list_add(&pg->lru, &page_list);
+		list_count++;
+	}
+
+	return 0;
+}
+
+/**
+ * xen_alloc_unpopulated_pages - alloc unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages returned
+ * @return 0 on success, error otherwise
+ */
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	int ret = 0;
+
+	mutex_lock(&list_lock);
+	if (list_count < nr_pages) {
+		ret = fill_list(nr_pages - list_count);
+		if (ret)
+			goto out;
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *pg = list_first_entry_or_null(&page_list,
+							   struct page,
+							   lru);
+
+		BUG_ON(!pg);
+		list_del(&pg->lru);
+		list_count--;
+		pages[i] = pg;
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			ret = xen_alloc_p2m_entry(page_to_pfn(pg));
+			if (ret < 0) {
+				unsigned int j;
+
+				for (j = 0; j <= i; j++) {
+					list_add(&pages[j]->lru, &page_list);
+					list_count++;
+				}
+				goto out;
+			}
+		}
+#endif
+	}
+
+out:
+	mutex_unlock(&list_lock);
+	return ret;
+}
+EXPORT_SYMBOL(xen_alloc_unpopulated_pages);
+
+/**
+ * xen_free_unpopulated_pages - return unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages to return
+ */
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+
+	mutex_lock(&list_lock);
+	for (i = 0; i < nr_pages; i++) {
+		list_add(&pages[i]->lru, &page_list);
+		list_count++;
+	}
+	mutex_unlock(&list_lock);
+}
+EXPORT_SYMBOL(xen_free_unpopulated_pages);
+
+#ifdef CONFIG_XEN_PV
+static int __init init(void)
+{
+	unsigned int i;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	/*
+	 * Initialize with pages from the extra memory regions (see
+	 * arch/x86/xen/setup.c).
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		unsigned int j;
+
+		for (j = 0; j < xen_extra_mem[i].n_pfns; j++) {
+			struct page *pg =
+				pfn_to_page(xen_extra_mem[i].start_pfn + j);
+
+			list_add(&pg->lru, &page_list);
+			list_count++;
+		}
+	}
+
+	return 0;
+}
+subsys_initcall(init);
+#endif
diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c
index 7457213b8915..f914b72557ef 100644
--- a/drivers/xen/xen-acpi-memhotplug.c
+++ b/drivers/xen/xen-acpi-memhotplug.c
@@ -229,7 +229,7 @@ static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data)
 	case ACPI_NOTIFY_BUS_CHECK:
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			"\nReceived BUS CHECK notification for device\n"));
-		/* Fall Through */
+		fallthrough;
 	case ACPI_NOTIFY_DEVICE_CHECK:
 		if (event == ACPI_NOTIFY_DEVICE_CHECK)
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index f2115587855f..b500466a6c37 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -545,7 +545,7 @@ static void xen_pcibk_frontend_changed(struct xenbus_device *xdev,
 		xenbus_switch_state(xdev, XenbusStateClosed);
 		if (xenbus_dev_is_online(xdev))
 			break;
-		/* fall through - if not online */
+		fallthrough;	/* if not online */
 	case XenbusStateUnknown:
 		dev_dbg(&xdev->dev, "frontend is gone! unregister device\n");
 		device_unregister(&xdev->dev);
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 75c0a2e9a6db..1e8cfd80a4e6 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1185,7 +1185,7 @@ static void scsiback_frontend_changed(struct xenbus_device *dev,
 		xenbus_switch_state(dev, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
-		/* fall through - if not online */
+		fallthrough;	/* if not online */
 	case XenbusStateUnknown:
 		device_unregister(&dev->dev);
 		break;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 786fbb7d8be0..2690318ad50f 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -379,8 +379,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 	int i, j;
 
 	for (i = 0; i < nr_pages; i++) {
-		err = gnttab_grant_foreign_access(dev->otherend_id,
-						  virt_to_gfn(vaddr), 0);
+		unsigned long gfn;
+
+		if (is_vmalloc_addr(vaddr))
+			gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr));
+		else
+			gfn = virt_to_gfn(vaddr);
+
+		err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "granting access to ring page");
@@ -615,7 +621,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 	bool leaked = false;
 	unsigned int nr_pages = XENBUS_PAGES(nr_grefs);
 
-	err = alloc_xenballooned_pages(nr_pages, node->hvm.pages);
+	err = xen_alloc_unpopulated_pages(nr_pages, node->hvm.pages);
 	if (err)
 		goto out_err;
 
@@ -656,7 +662,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 			 addr, nr_pages);
  out_free_ballooned_pages:
 	if (!leaked)
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
  out_err:
 	return err;
 }
@@ -852,7 +858,7 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 			       info.addrs);
 	if (!rv) {
 		vunmap(vaddr);
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
 	}
 	else
 		WARN(1, "Leaking %p, size %u page(s)\n", vaddr, nr_pages);
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 15379089853b..480944606a3c 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -401,12 +401,12 @@ static void xenbus_reset_frontend(char *fe, char *be, int be_state)
 	case XenbusStateConnected:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing);
 		xenbus_reset_wait_for_backend(be, XenbusStateClosing);
-		/* fall through */
+		fallthrough;
 
 	case XenbusStateClosing:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed);
 		xenbus_reset_wait_for_backend(be, XenbusStateClosed);
-		/* fall through */
+		fallthrough;
 
 	case XenbusStateClosed:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising);
diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
index 7b1077f0abcb..34742c6e189e 100644
--- a/drivers/xen/xlate_mmu.c
+++ b/drivers/xen/xlate_mmu.c
@@ -232,7 +232,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 		kfree(pages);
 		return -ENOMEM;
 	}
-	rc = alloc_xenballooned_pages(nr_pages, pages);
+	rc = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (rc) {
 		pr_warn("%s Couldn't balloon alloc %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
@@ -249,7 +249,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
-		free_xenballooned_pages(nr_pages, pages);
+		xen_free_unpopulated_pages(nr_pages, pages);
 		kfree(pages);
 		kfree(pfns);
 		return -ENOMEM;
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 92cd1d80218d..3576123d8299 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -213,7 +213,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		break;
 	default:
 		WARN_ONCE(1, "unknown lock status code: %d\n", status);
-		/* fall through */
+		fallthrough;
 	case P9_LOCK_ERROR:
 	case P9_LOCK_GRACE:
 		res = -ENOLCK;
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index 30d526fecc3f..05e963402e25 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -18,11 +18,11 @@ static inline unsigned int adfs_readval(unsigned char *p, int len)
 
 	switch (len) {
 	case 4:		val |= p[3] << 24;
-			/* fall through */
+		fallthrough;
 	case 3:		val |= p[2] << 16;
-			/* fall through */
+		fallthrough;
 	case 2:		val |= p[1] << 8;
-			/* fall through */
+		fallthrough;
 	default:	val |= p[0];
 	}
 	return val;
@@ -32,11 +32,11 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val)
 {
 	switch (len) {
 	case 4:		p[3] = val >> 24;
-			/* fall through */
+		fallthrough;
 	case 3:		p[2] = val >> 16;
-			/* fall through */
+		fallthrough;
 	case 2:		p[1] = val >> 8;
-			/* fall through */
+		fallthrough;
 	default:	p[0] = val;
 	}
 }
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index f708c45d5f66..29f11e10a7c7 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -420,24 +420,51 @@ affs_mode_to_prot(struct inode *inode)
 	u32 prot = AFFS_I(inode)->i_protect;
 	umode_t mode = inode->i_mode;
 
+	/*
+	 * First, clear all RWED bits for owner, group, other.
+	 * Then, recalculate them afresh.
+	 *
+	 * We'll always clear the delete-inhibit bit for the owner, as that is
+	 * the classic single-user mode AmigaOS protection bit and we need to
+	 * stay compatible with all scenarios.
+	 *
+	 * Since multi-user AmigaOS is an extension, we'll only set the
+	 * delete-allow bit if any of the other bits in the same user class
+	 * (group/other) are used.
+	 */
+	prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD
+		  | FIBF_NOWRITE | FIBF_NODELETE
+		  | FIBF_GRP_EXECUTE | FIBF_GRP_READ
+		  | FIBF_GRP_WRITE   | FIBF_GRP_DELETE
+		  | FIBF_OTR_EXECUTE | FIBF_OTR_READ
+		  | FIBF_OTR_WRITE   | FIBF_OTR_DELETE);
+
+	/* Classic single-user AmigaOS flags. These are inverted. */
 	if (!(mode & 0100))
 		prot |= FIBF_NOEXECUTE;
 	if (!(mode & 0400))
 		prot |= FIBF_NOREAD;
 	if (!(mode & 0200))
 		prot |= FIBF_NOWRITE;
+
+	/* Multi-user extended flags. Not inverted. */
 	if (mode & 0010)
 		prot |= FIBF_GRP_EXECUTE;
 	if (mode & 0040)
 		prot |= FIBF_GRP_READ;
 	if (mode & 0020)
 		prot |= FIBF_GRP_WRITE;
+	if (mode & 0070)
+		prot |= FIBF_GRP_DELETE;
+
 	if (mode & 0001)
 		prot |= FIBF_OTR_EXECUTE;
 	if (mode & 0004)
 		prot |= FIBF_OTR_READ;
 	if (mode & 0002)
 		prot |= FIBF_OTR_WRITE;
+	if (mode & 0007)
+		prot |= FIBF_OTR_DELETE;
 
 	AFFS_I(inode)->i_protect = prot;
 }
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a26a0f96c119..d91b0133d95d 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -429,6 +429,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+static int affs_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned int len, unsigned int copied,
+			  struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	int ret;
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
+	return ret;
+}
+
 static sector_t _affs_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,affs_get_block);
@@ -438,7 +456,7 @@ const struct address_space_operations affs_aops = {
 	.readpage = affs_readpage,
 	.writepage = affs_writepage,
 	.write_begin = affs_write_begin,
-	.write_end = generic_write_end,
+	.write_end = affs_write_end,
 	.direct_IO = affs_direct_IO,
 	.bmap = _affs_bmap
 };
@@ -795,6 +813,12 @@ done:
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
 err_first_bh:
 	unlock_page(page);
 	put_page(page);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index a346cf7659f1..044412110b52 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -93,7 +93,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 	case ST_ROOT:
 		inode->i_uid = sbi->s_uid;
 		inode->i_gid = sbi->s_gid;
-		/* fall through */
+		fallthrough;
 	case ST_USERDIR:
 		if (be32_to_cpu(tail->stype) == ST_USERDIR ||
 		    affs_test_opt(sbi->s_flags, SF_SETMODE)) {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 47107c6712a6..a100cd9950c8 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -474,7 +474,7 @@ got_root:
 	case MUFS_INTLFFS:
 	case MUFS_DCFFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall thru */
+		fallthrough;
 	case FS_INTLFFS:
 	case FS_DCFFS:
 		affs_set_opt(sbi->s_flags, SF_INTL);
@@ -486,7 +486,7 @@ got_root:
 		break;
 	case MUFS_OFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall through */
+		fallthrough;
 	case FS_OFS:
 		affs_set_opt(sbi->s_flags, SF_OFS);
 		sb->s_flags |= SB_NOEXEC;
@@ -494,7 +494,7 @@ got_root:
 	case MUFS_DCOFS:
 	case MUFS_INTLOFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall through */
+		fallthrough;
 	case FS_DCOFS:
 	case FS_INTLOFS:
 		affs_set_opt(sbi->s_flags, SF_INTL);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index bef413818af7..a4e9e6e07e93 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -252,7 +252,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the FID array and its count in two steps */
-		/* fall through */
+		fallthrough;
 	case 1:
 		_debug("extract FID count");
 		ret = afs_extract_data(call, true);
@@ -271,7 +271,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		afs_extract_to_buf(call, call->count * 3 * 4);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 2:
 		_debug("extract FID array");
 		ret = afs_extract_data(call, true);
@@ -297,7 +297,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the callback array and its count in two steps */
-		/* fall through */
+		fallthrough;
 	case 3:
 		_debug("extract CB count");
 		ret = afs_extract_data(call, true);
@@ -312,7 +312,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		iov_iter_discard(&call->def_iter, READ, call->count2 * 3 * 4);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 4:
 		_debug("extract discard %zu/%u",
 		       iov_iter_count(call->iter), call->count2 * 3 * 4);
@@ -391,7 +391,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract UUID");
 		ret = afs_extract_data(call, false);
@@ -503,7 +503,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract UUID");
 		ret = afs_extract_data(call, false);
@@ -618,7 +618,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the FID array and its count in two steps */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract FID count");
 		ret = afs_extract_data(call, true);
@@ -637,7 +637,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 2:
 		_debug("extract FID array");
 		ret = afs_extract_data(call, false);
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index b79879aacc02..7b784af604fd 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -382,15 +382,17 @@ void afs_dynroot_depopulate(struct super_block *sb)
 		net->dynroot_sb = NULL;
 	mutex_unlock(&net->proc_cells_lock);
 
-	inode_lock(root->d_inode);
-
-	/* Remove all the pins for dirs created for manually added cells */
-	list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) {
-		if (subdir->d_fsdata) {
-			subdir->d_fsdata = NULL;
-			dput(subdir);
+	if (root) {
+		inode_lock(root->d_inode);
+
+		/* Remove all the pins for dirs created for manually added cells */
+		list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) {
+			if (subdir->d_fsdata) {
+				subdir->d_fsdata = NULL;
+				dput(subdir);
+			}
 		}
-	}
 
-	inode_unlock(root->d_inode);
+		inode_unlock(root->d_inode);
+	}
 }
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 6f6ed1605cfe..371d1488cc54 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -311,7 +311,7 @@ int afs_page_filler(void *data, struct page *page)
 	case -ENOBUFS:
 		_debug("cache said ENOBUFS");
 
-		/* fall through */
+		fallthrough;
 	default:
 	go_on:
 		req = kzalloc(struct_size(req, array, 1), GFP_KERNEL);
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index ffb8575345ca..cb3054c7843e 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -376,7 +376,6 @@ again:
 		spin_unlock(&vnode->lock);
 		return;
 
-		/* Fall through */
 	default:
 		/* Looks like a lock request was withdrawn. */
 		spin_unlock(&vnode->lock);
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 24fd163c6323..97cab12b0a6c 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -235,6 +235,7 @@ int afs_put_operation(struct afs_operation *op)
 	afs_end_cursor(&op->ac);
 	afs_put_serverlist(op->net, op->server_list);
 	afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op);
+	key_put(op->key);
 	kfree(op);
 	return ret;
 }
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 5d9ef517cf81..e7e98ad63a91 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -161,8 +161,8 @@ responded:
 		}
 	}
 
-	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
-	if (rtt_us < server->probe.rtt) {
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
 		alist->preferred = index;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index acb4d0ca2649..1d95ed9dd86e 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -320,7 +320,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 			call->tmp_u = htonl(0);
 			afs_extract_to_tmp(call);
 		}
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -348,7 +348,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		call->bvec[0].bv_page = req->pages[req->index];
 		iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
 		ASSERTCMP(size, <=, PAGE_SIZE);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -375,7 +375,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		/* Discard any excess data the server gave us */
 		afs_extract_discard(call, req->actual_len - req->len);
 		call->unmarshall = 3;
-		/* Fall through */
+		fallthrough;
 
 	case 3:
 		_debug("extract discard %zu/%llu",
@@ -388,7 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 	no_more_data:
 		call->unmarshall = 4;
 		afs_extract_to_buf(call, (21 + 3 + 6) * 4);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 4:
@@ -1343,7 +1343,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 	case 0:
 		call->unmarshall++;
 		afs_extract_to_buf(call, 12 * 4);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned status record */
 	case 1:
@@ -1356,7 +1356,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		xdr_decode_AFSFetchVolumeStatus(&bp, &op->volstatus.vs);
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name length */
 	case 2:
@@ -1371,7 +1371,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name */
 	case 3:
@@ -1385,7 +1385,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("volname '%s'", p);
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message length */
 	case 4:
@@ -1400,7 +1400,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message */
 	case 5:
@@ -1415,7 +1415,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day length */
 	case 6:
@@ -1430,7 +1430,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day */
 	case 7:
@@ -1682,7 +1682,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the capabilities word count */
 	case 1:
@@ -1696,7 +1696,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 		call->count2 = count;
 		afs_extract_discard(call, count * sizeof(__be32));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract capabilities words */
 	case 2:
@@ -1776,7 +1776,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file status count and array in two steps */
 	case 1:
@@ -1794,7 +1794,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_counts:
 		afs_extract_to_buf(call, 21 * sizeof(__be32));
-		/* Fall through */
+		fallthrough;
 
 	case 2:
 		_debug("extract status array %u", call->count);
@@ -1824,7 +1824,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->count = 0;
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the callback count and array in two steps */
 	case 3:
@@ -1841,7 +1841,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_cbs:
 		afs_extract_to_buf(call, 3 * sizeof(__be32));
-		/* Fall through */
+		fallthrough;
 
 	case 4:
 		_debug("extract CB array");
@@ -1870,7 +1870,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		afs_extract_to_buf(call, 6 * sizeof(__be32));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		ret = afs_extract_data(call, false);
@@ -1974,7 +1974,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -1992,7 +1992,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 		acl->size = call->count2;
 		afs_extract_begin(call, acl->data, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -2002,7 +2002,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 
 		afs_extract_to_buf(call, (21 + 6) * 4);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 3:
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 792ac711985e..18042b7dab6a 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -401,22 +401,24 @@ struct afs_vlserver {
 #define AFS_VLSERVER_FL_PROBED	0		/* The VL server has been probed */
 #define AFS_VLSERVER_FL_PROBING	1		/* VL server is being probed */
 #define AFS_VLSERVER_FL_IS_YFS	2		/* Server is YFS not AFS */
+#define AFS_VLSERVER_FL_RESPONDING 3		/* VL server is responding */
 	rwlock_t		lock;		/* Lock on addresses */
 	atomic_t		usage;
+	unsigned int		rtt;		/* Server's current RTT in uS */
 
 	/* Probe state */
 	wait_queue_head_t	probe_wq;
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT as ktime/64 */
+		unsigned int	rtt;		/* RTT in uS */
 		u32		abort_code;
 		short		error;
-		bool		have_result;
-		bool		responded:1;
-		bool		is_yfs:1;
-		bool		not_yfs:1;
-		bool		local_failure:1;
+		unsigned short	flags;
+#define AFS_VLSERVER_PROBE_RESPONDED		0x01 /* At least once response (may be abort) */
+#define AFS_VLSERVER_PROBE_IS_YFS		0x02 /* The peer appears to be YFS */
+#define AFS_VLSERVER_PROBE_NOT_YFS		0x04 /* The peer appears not to be YFS */
+#define AFS_VLSERVER_PROBE_LOCAL_FAILURE	0x08 /* A local failure prevented a probe */
 	} probe;
 
 	u16			port;
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 5334f1bd2bca..1d1a8debe472 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -120,42 +120,42 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
 		if (e->error == -ETIMEDOUT ||
 		    e->error == -ETIME)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ETIMEDOUT:
 	case -ETIME:
 		if (e->error == -ENOMEM ||
 		    e->error == -ENONET)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ENOMEM:
 	case -ENONET:
 		if (e->error == -ERFKILL)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ERFKILL:
 		if (e->error == -EADDRNOTAVAIL)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EADDRNOTAVAIL:
 		if (e->error == -ENETUNREACH)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ENETUNREACH:
 		if (e->error == -EHOSTUNREACH)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EHOSTUNREACH:
 		if (e->error == -EHOSTDOWN)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EHOSTDOWN:
 		if (e->error == -ECONNREFUSED)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ECONNREFUSED:
 		if (e->error == -ECONNRESET)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ECONNRESET: /* Responded, but call expired. */
 		if (e->responded)
 			return;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index e817fc740ba0..e8babb62ed44 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -310,6 +310,11 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 				   alist->preferred == i ? '>' : '-',
 				   &alist->addrs[i].transport);
 	}
+	seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
+	seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
+		   vlserver->probe.flags, vlserver->probe.error,
+		   vlserver->probe.abort_code,
+		   atomic_read(&vlserver->probe_outstanding));
 	return 0;
 }
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 6a0935cb822f..d83f13c44b92 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	case -ETIME:
 		if (op->error != -EDESTADDRREQ)
 			goto iterate_address;
-		/* Fall through */
+		fallthrough;
 	case -ERFKILL:
 	case -EADDRNOTAVAIL:
 	case -ENETUNREACH:
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8fc8fb406a5a..8be709cb8542 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -568,7 +568,7 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -EIO:
 			pr_err("kAFS: Call %u in bad state %u\n",
 			       call->debug_id, state);
-			/* Fall through */
+			fallthrough;
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
@@ -669,7 +669,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
 		ret = call->ret0;
 		call->ret0 = 0;
 
-		/* Fall through */
+		fallthrough;
 	case -ECONNABORTED:
 		ac->responded = true;
 		break;
@@ -872,7 +872,7 @@ void afs_send_empty_reply(struct afs_call *call)
 		_debug("oom");
 		rxrpc_kernel_abort_call(net->socket, call->rxcall,
 					RX_USER_ABORT, -ENOMEM, "KOO");
-		/* Fall through */
+		fallthrough;
 	default:
 		_leave(" [error]");
 		return;
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 8fea54eba0c2..38b2ba1d9ec0 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -21,6 +21,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 		rwlock_init(&vlserver->lock);
 		init_waitqueue_head(&vlserver->probe_wq);
 		spin_lock_init(&vlserver->probe_lock);
+		vlserver->rtt = UINT_MAX;
 		vlserver->name_len = name_len;
 		vlserver->port = port;
 		memcpy(vlserver->name, name, name_len);
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index e3aa013c2177..d1c7068b4346 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -11,15 +11,33 @@
 #include "internal.h"
 #include "protocol_yfs.h"
 
-static bool afs_vl_probe_done(struct afs_vlserver *server)
+
+/*
+ * Handle the completion of a set of probes.
+ */
+static void afs_finished_vl_probe(struct afs_vlserver *server)
 {
-	if (!atomic_dec_and_test(&server->probe_outstanding))
-		return false;
+	if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) {
+		server->rtt = UINT_MAX;
+		clear_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags);
+	}
 
-	wake_up_var(&server->probe_outstanding);
 	clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags);
 	wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING);
-	return true;
+}
+
+/*
+ * Handle the completion of a probe RPC call.
+ */
+static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up)
+{
+	if (atomic_dec_and_test(&server->probe_outstanding)) {
+		afs_finished_vl_probe(server);
+		wake_up = true;
+	}
+
+	if (wake_up)
+		wake_up_all(&server->probe_wq);
 }
 
 /*
@@ -45,15 +63,20 @@ void afs_vlserver_probe_result(struct afs_call *call)
 		server->probe.error = 0;
 		goto responded;
 	case -ECONNABORTED:
-		if (!server->probe.responded) {
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) {
 			server->probe.abort_code = call->abort_code;
 			server->probe.error = ret;
 		}
 		goto responded;
 	case -ENOMEM:
 	case -ENONET:
-		server->probe.local_failure = true;
-		afs_io_error(call, afs_io_error_vl_probe_fail);
+	case -EKEYEXPIRED:
+	case -EKEYREVOKED:
+	case -EKEYREJECTED:
+		server->probe.flags |= AFS_VLSERVER_PROBE_LOCAL_FAILURE;
+		if (server->probe.error == 0)
+			server->probe.error = ret;
+		trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail);
 		goto out;
 	case -ECONNRESET: /* Responded, but call expired. */
 	case -ERFKILL:
@@ -67,12 +90,12 @@ void afs_vlserver_probe_result(struct afs_call *call)
 	default:
 		clear_bit(index, &alist->responded);
 		set_bit(index, &alist->failed);
-		if (!server->probe.responded &&
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) &&
 		    (server->probe.error == 0 ||
 		     server->probe.error == -ETIMEDOUT ||
 		     server->probe.error == -ETIME))
 			server->probe.error = ret;
-		afs_io_error(call, afs_io_error_vl_probe_fail);
+		trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail);
 		goto out;
 	}
 
@@ -81,39 +104,36 @@ responded:
 	clear_bit(index, &alist->failed);
 
 	if (call->service_id == YFS_VL_SERVICE) {
-		server->probe.is_yfs = true;
+		server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS;
 		set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
 		alist->addrs[index].srx_service = call->service_id;
 	} else {
-		server->probe.not_yfs = true;
-		if (!server->probe.is_yfs) {
+		server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS;
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) {
 			clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
 			alist->addrs[index].srx_service = call->service_id;
 		}
 	}
 
-	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
-	if (rtt_us < server->probe.rtt) {
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
+		server->rtt = rtt_us;
 		alist->preferred = index;
-		have_result = true;
 	}
 
 	smp_wmb(); /* Set rtt before responded. */
-	server->probe.responded = true;
+	server->probe.flags |= AFS_VLSERVER_PROBE_RESPONDED;
 	set_bit(AFS_VLSERVER_FL_PROBED, &server->flags);
+	set_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags);
+	have_result = true;
 out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
 	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
-	have_result |= afs_vl_probe_done(server);
-	if (have_result) {
-		server->probe.have_result = true;
-		wake_up_var(&server->probe.have_result);
-		wake_up_all(&server->probe_wq);
-	}
+	afs_done_one_vl_probe(server, have_result);
 }
 
 /*
@@ -151,11 +171,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 			in_progress = true;
 		} else {
 			afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code);
+			afs_done_one_vl_probe(server, false);
 		}
 	}
 
-	if (!in_progress)
-		afs_vl_probe_done(server);
 	return in_progress;
 }
 
@@ -193,7 +212,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 {
 	struct wait_queue_entry *waits;
 	struct afs_vlserver *server;
-	unsigned int rtt = UINT_MAX;
+	unsigned int rtt = UINT_MAX, rtt_s;
 	bool have_responders = false;
 	int pref = -1, i;
 
@@ -205,7 +224,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 			server = vllist->servers[i].server;
 			if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
 				__clear_bit(i, &untried);
-			if (server->probe.responded)
+			if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)
 				have_responders = true;
 		}
 	}
@@ -231,7 +250,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 		for (i = 0; i < vllist->nr_servers; i++) {
 			if (test_bit(i, &untried)) {
 				server = vllist->servers[i].server;
-				if (server->probe.responded)
+				if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)
 					goto stop;
 				if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
 					still_probing = true;
@@ -249,10 +268,11 @@ stop:
 	for (i = 0; i < vllist->nr_servers; i++) {
 		if (test_bit(i, &untried)) {
 			server = vllist->servers[i].server;
-			if (server->probe.responded &&
-			    server->probe.rtt < rtt) {
+			rtt_s = READ_ONCE(server->rtt);
+			if (test_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags) &&
+			    rtt_s < rtt) {
 				pref = i;
-				rtt = server->probe.rtt;
+				rtt = rtt_s;
 			}
 
 			remove_wait_queue(&server->probe_wq, &waits[i]);
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index f405ca8b240a..c0458c903b31 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -192,7 +192,8 @@ pick_server:
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
-		if (!test_bit(i, &vc->untried) || !s->probe.responded)
+		if (!test_bit(i, &vc->untried) ||
+		    !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
 			continue;
 		if (s->probe.rtt < rtt) {
 			vc->index = i;
@@ -262,10 +263,14 @@ no_more_servers:
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
+		if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
+			e.responded = true;
 		afs_prioritise_error(&e, READ_ONCE(s->probe.error),
 				     s->probe.abort_code);
 	}
 
+	error = e.error;
+
 failed_set_error:
 	vc->error = error;
 failed:
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index fd82850cd424..dc9327332f06 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -196,7 +196,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 
 		/* Extract the returned uuid, uniquifier, nentries and
 		 * blkaddrs size */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -221,7 +221,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		count = min(call->count, 4U);
 		afs_extract_to_buf(call, count * sizeof(__be32));
 
-		/* Fall through - and extract entries */
+		fallthrough;	/* and extract entries */
 	case 2:
 		ret = afs_extract_data(call, call->count > 4);
 		if (ret < 0)
@@ -324,7 +324,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
-		/* Fall through - and extract the capabilities word count */
+		fallthrough;	/* and extract the capabilities word count */
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -337,7 +337,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 		call->unmarshall++;
 		afs_extract_discard(call, count * sizeof(__be32));
 
-		/* Fall through - and extract capabilities words */
+		fallthrough;	/* and extract capabilities words */
 	case 2:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
@@ -436,7 +436,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		/* Extract the returned uuid, uniquifier, fsEndpoints count and
 		 * either the first fsEndpoint type or the volEndpoints
 		 * count if there are no fsEndpoints. */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -475,7 +475,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall = 2;
 
-		/* Fall through - and extract fsEndpoints[] entries */
+		fallthrough;	/* and extract fsEndpoints[] entries */
 	case 2:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -526,7 +526,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		 * extract the type of the next endpoint when we extract the
 		 * data of the current one, but this is the first...
 		 */
-		/* Fall through */
+		fallthrough;
 	case 3:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -552,7 +552,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall = 4;
 
-		/* Fall through - and extract volEndpoints[] entries */
+		fallthrough;	/* and extract volEndpoints[] entries */
 	case 4:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -587,7 +587,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_discard(call, 0);
 		call->unmarshall = 5;
 
-		/* Fall through - Done */
+		fallthrough;	/* Done */
 	case 5:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
@@ -663,7 +663,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
-		/* Fall through - and extract the cell name length */
+		fallthrough;	/* and extract the cell name length */
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -685,7 +685,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_begin(call, cell_name, namesz);
 		call->unmarshall++;
 
-		/* Fall through - and extract cell name */
+		fallthrough;	/* and extract cell name */
 	case 2:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -694,7 +694,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_discard(call, call->count2);
 		call->unmarshall++;
 
-		/* Fall through - and extract padding */
+		fallthrough;	/* and extract padding */
 	case 3:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a121c247d95a..4b2265cb1891 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -609,7 +609,7 @@ no_more:
 
 	default:
 		pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
-		/* Fall through */
+		fallthrough;
 	case -EACCES:
 	case -EPERM:
 	case -ENOKEY:
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 8c24fdc899e3..3b1239b7e90d 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -373,7 +373,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		req->offset = req->pos & (PAGE_SIZE - 1);
 		afs_extract_to_tmp64(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -401,7 +401,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		call->bvec[0].bv_page = req->pages[req->index];
 		iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
 		ASSERTCMP(size, <=, PAGE_SIZE);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -428,7 +428,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		/* Discard any excess data the server gave us */
 		afs_extract_discard(call, req->actual_len - req->len);
 		call->unmarshall = 3;
-		/* Fall through */
+		fallthrough;
 
 	case 3:
 		_debug("extract discard %zu/%llu",
@@ -444,7 +444,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 				   sizeof(struct yfs_xdr_YFSFetchStatus) +
 				   sizeof(struct yfs_xdr_YFSCallBack) +
 				   sizeof(struct yfs_xdr_YFSVolSync));
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 4:
@@ -461,7 +461,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		req->file_size = vp->scb.status.size;
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		break;
@@ -1262,7 +1262,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 	case 0:
 		call->unmarshall++;
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus));
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned status record */
 	case 1:
@@ -1275,7 +1275,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		xdr_decode_YFSFetchVolumeStatus(&bp, &op->volstatus.vs);
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name length */
 	case 2:
@@ -1290,7 +1290,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name */
 	case 3:
@@ -1304,7 +1304,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("volname '%s'", p);
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message length */
 	case 4:
@@ -1319,7 +1319,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message */
 	case 5:
@@ -1334,7 +1334,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day length */
 	case 6:
@@ -1349,7 +1349,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day */
 	case 7:
@@ -1363,7 +1363,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("motd '%s'", p);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 8:
 		break;
@@ -1622,7 +1622,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file status count and array in two steps */
 	case 1:
@@ -1640,7 +1640,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_counts:
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus));
-		/* Fall through */
+		fallthrough;
 
 	case 2:
 		_debug("extract status array %u", call->count);
@@ -1670,7 +1670,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->count = 0;
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the callback count and array in two steps */
 	case 3:
@@ -1687,7 +1687,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_cbs:
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack));
-		/* Fall through */
+		fallthrough;
 
 	case 4:
 		_debug("extract CB array");
@@ -1716,7 +1716,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		ret = afs_extract_data(call, false);
@@ -1727,7 +1727,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		xdr_decode_YFSVolSync(&bp, &op->volsync);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 6:
 		break;
@@ -1804,7 +1804,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file ACL length */
 	case 1:
@@ -1826,7 +1826,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 			afs_extract_discard(call, size);
 		}
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file ACL */
 	case 2:
@@ -1836,7 +1836,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the volume ACL length */
 	case 3:
@@ -1858,7 +1858,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 			afs_extract_discard(call, size);
 		}
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the volume ACL */
 	case 4:
@@ -1871,7 +1871,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 				   sizeof(struct yfs_xdr_YFSFetchStatus) +
 				   sizeof(struct yfs_xdr_YFSVolSync));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 5:
@@ -1886,7 +1886,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 		xdr_decode_YFSVolSync(&bp, &op->volsync);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 6:
 		break;
diff --git a/fs/aio.c b/fs/aio.c
index 5736bff48e9e..d5ec30385566 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1511,7 +1511,7 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 		 * may be already running. Just fail this IO with EINTR.
 		 */
 		ret = -EINTR;
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		req->ki_complete(req, ret, 0);
 	}
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index f2f9086ebe98..b9c658e0548e 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -576,7 +576,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 			goto err;
 		}
 
-		len = data_len + extra;
+		len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
 		len = PAGE_ALIGN(len);
 		realdatastart = vm_mmap(NULL, 0, len,
 			PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
@@ -590,7 +590,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 			vm_munmap(textpos, text_len);
 			goto err;
 		}
-		datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN);
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(unsigned long),
+				FLAT_DATA_ALIGN);
 
 		pr_debug("Allocated data+bss+stack (%u bytes): %lx\n",
 			 data_len + bss_len + stack_len, datapos);
@@ -620,7 +622,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 		memp_size = len;
 	} else {
 
-		len = text_len + data_len + extra;
+		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32);
 		len = PAGE_ALIGN(len);
 		textpos = vm_mmap(NULL, 0, len,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
@@ -635,7 +637,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 		}
 
 		realdatastart = textpos + ntohl(hdr->data_start);
-		datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN);
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(u32),
+				FLAT_DATA_ALIGN);
 
 		reloc = (__be32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
@@ -652,9 +656,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 					 (text_len + full_data
 						  - sizeof(struct flat_hdr)),
 					 0);
-			if (datapos != realdatastart)
-				memmove((void *)datapos, (void *)realdatastart,
-						full_data);
+			memmove((void *) datapos, (void *) realdatastart,
+					full_data);
 #else
 			/*
 			 * This is used on MMU systems mainly for testing.
@@ -710,7 +713,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 		if (IS_ERR_VALUE(result)) {
 			ret = result;
 			pr_err("Unable to read code+data+bss, errno %d\n", ret);
-			vm_munmap(textpos, text_len + data_len + extra);
+			vm_munmap(textpos, text_len + data_len + extra +
+				MAX_SHARED_LIBS * sizeof(u32));
 			goto err;
 		}
 	}
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 613920c17ac1..ea8aaf36647e 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1798,7 +1798,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 
 	cache->fs_info = fs_info;
 	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
-	set_free_space_tree_thresholds(cache);
 
 	cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED;
 
@@ -1912,6 +1911,8 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	if (ret < 0)
 		goto error;
 
+	set_free_space_tree_thresholds(cache);
+
 	if (need_clear) {
 		/*
 		 * When we mount with old space cache, we need to
@@ -2132,6 +2133,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 		return -ENOMEM;
 
 	cache->length = size;
+	set_free_space_tree_thresholds(cache);
 	cache->used = bytes_used;
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 70e49d8d4f6c..cd392da69b81 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -68,7 +68,7 @@ const char *btrfs_super_csum_driver(u16 csum_type)
 		btrfs_csums[csum_type].name;
 }
 
-size_t __const btrfs_get_num_csums(void)
+size_t __attribute_const__ btrfs_get_num_csums(void)
 {
 	return ARRAY_SIZE(btrfs_csums);
 }
@@ -1297,6 +1297,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	btrfs_tree_read_unlock_blocking(eb);
 	free_extent_buffer(eb);
 
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
+				       eb_rewin, btrfs_header_level(eb_rewin));
 	btrfs_tree_read_lock(eb_rewin);
 	__tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
 	WARN_ON(btrfs_header_nritems(eb_rewin) >
@@ -1370,7 +1372,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 
 	if (!eb)
 		return NULL;
-	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);
 		btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);
@@ -1378,6 +1379,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		btrfs_set_header_level(eb, old_root->level);
 		btrfs_set_header_generation(eb, old_generation);
 	}
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
+				       btrfs_header_level(eb));
+	btrfs_tree_read_lock(eb);
 	if (tm)
 		__tree_mod_log_rewind(fs_info, eb, time_seq, tm);
 	else
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9c7e466f27a9..9a72896bed2e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2262,7 +2262,7 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
 const char *btrfs_super_csum_driver(u16 csum_type);
-size_t __const btrfs_get_num_csums(void);
+size_t __attribute_const__ btrfs_get_num_csums(void);
 
 
 /*
@@ -2518,7 +2518,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 				    u64 bytenr, u64 num_bytes);
 int btrfs_exclude_logged_extents(struct extent_buffer *eb);
 int btrfs_cross_ref_exist(struct btrfs_root *root,
-			  u64 objectid, u64 offset, u64 bytenr);
+			  u64 objectid, u64 offset, u64 bytenr, bool strict);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
 					     u64 parent, u64 root_objectid,
@@ -2934,7 +2934,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 					   u64 start, u64 len);
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes);
+			      u64 *ram_bytes, bool strict);
 
 void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 				struct btrfs_inode *inode);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9ae25f632157..abf86b202b43 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3418,6 +3418,8 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
+	if (fs_info->data_reloc_root)
+		btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root);
 	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
@@ -4551,6 +4553,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
 		cache->io_ctl.inode = NULL;
 		iput(inode);
 	}
+	ASSERT(cache->io_ctl.pages == NULL);
 	btrfs_put_block_group(cache);
 }
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index de6fe176fdfb..780b9c9a98fe 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -400,12 +400,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else if (is_data == BTRFS_REF_TYPE_DATA) {
@@ -414,12 +413,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_DATA_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else {
@@ -429,8 +427,9 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 	}
 
 	btrfs_print_leaf((struct extent_buffer *)eb);
-	btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d",
-		  eb->start, type);
+	btrfs_err(eb->fs_info,
+		  "eb %llu iref 0x%lx invalid extent inline ref type %d",
+		  eb->start, (unsigned long)iref, type);
 	WARN_ON(1);
 
 	return BTRFS_REF_TYPE_INVALID;
@@ -2306,7 +2305,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 
 static noinline int check_committed_ref(struct btrfs_root *root,
 					struct btrfs_path *path,
-					u64 objectid, u64 offset, u64 bytenr)
+					u64 objectid, u64 offset, u64 bytenr,
+					bool strict)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
@@ -2348,9 +2348,13 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 	    btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY))
 		goto out;
 
-	/* If extent created before last snapshot => it's definitely shared */
-	if (btrfs_extent_generation(leaf, ei) <=
-	    btrfs_root_last_snapshot(&root->root_item))
+	/*
+	 * If extent created before last snapshot => it's shared unless the
+	 * snapshot has been deleted. Use the heuristic if strict is false.
+	 */
+	if (!strict &&
+	    (btrfs_extent_generation(leaf, ei) <=
+	     btrfs_root_last_snapshot(&root->root_item)))
 		goto out;
 
 	iref = (struct btrfs_extent_inline_ref *)(ei + 1);
@@ -2375,7 +2379,7 @@ out:
 }
 
 int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
-			  u64 bytenr)
+			  u64 bytenr, bool strict)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -2386,7 +2390,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
 
 	do {
 		ret = check_committed_ref(root, path, objectid,
-					  offset, bytenr);
+					  offset, bytenr, strict);
 		if (ret && ret != -ENOENT)
 			goto out;
 
@@ -4522,7 +4526,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		return ERR_PTR(-EUCLEAN);
 	}
 
-	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
+	btrfs_set_buffer_lockdep_class(owner, buf, level);
 	btrfs_tree_lock(buf);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6def411b2eba..a940edb1e64f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5655,9 +5655,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 	}
 }
 
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dstv,
-			       unsigned long start, unsigned long len)
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dstv,
+				       unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5677,7 +5677,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb,
 
 		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
-		if (copy_to_user(dst, kaddr + offset, cur)) {
+		if (copy_to_user_nofault(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
 			break;
 		}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 00a88f2eb5ab..30794ae58498 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -241,9 +241,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dst, unsigned long start,
-			       unsigned long len);
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dst, unsigned long start,
+				       unsigned long len);
 void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src);
 void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
 		const void *src);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index bb824c7cb7c7..4507c3d09399 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1571,7 +1571,7 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	}
 
 	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
-			NULL, NULL, NULL);
+			NULL, NULL, NULL, false);
 	if (ret <= 0) {
 		ret = 0;
 		if (!nowait)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index ef0fd7afb0b1..dc82fd0c80cb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1186,7 +1186,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 	ret = update_cache_item(trans, root, inode, path, offset,
 				io_ctl->entries, io_ctl->bitmaps);
 out:
-	io_ctl_free(io_ctl);
 	if (ret) {
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
@@ -1347,6 +1346,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	 * them out later
 	 */
 	io_ctl_drop_pages(io_ctl);
+	io_ctl_free(io_ctl);
 
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state);
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 8b1f5c8897b7..6b9faf3b0e96 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -22,6 +22,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group *cache)
 	size_t bitmap_size;
 	u64 num_bitmaps, total_bitmap_size;
 
+	if (WARN_ON(cache->length == 0))
+		btrfs_warn(cache->fs_info, "block group %llu length is zero",
+			   cache->start);
+
 	/*
 	 * We convert to bitmaps when the disk space required for using extents
 	 * exceeds that required for using bitmaps.
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 51fcd82d41c0..9570458aa847 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1610,7 +1610,7 @@ next_slot:
 				goto out_check;
 			ret = btrfs_cross_ref_exist(root, ino,
 						    found_key.offset -
-						    extent_offset, disk_bytenr);
+						    extent_offset, disk_bytenr, false);
 			if (ret) {
 				/*
 				 * ret could be -EIO if the above fails to read
@@ -2161,11 +2161,8 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
 				    u64 bio_offset)
 {
 	struct inode *inode = private_data;
-	blk_status_t ret = 0;
 
-	ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
-	BUG_ON(ret); /* -ENOMEM */
-	return 0;
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
 }
 
 /*
@@ -6953,6 +6950,8 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
  * @orig_start:	(optional) Return the original file offset of the file extent
  * @orig_len:	(optional) Return the original on-disk length of the file extent
  * @ram_bytes:	(optional) Return the ram_bytes of the file extent
+ * @strict:	if true, omit optimizations that might force us into unnecessary
+ *		cow. e.g., don't trust generation number.
  *
  * This function will flush ordered extents in the range to ensure proper
  * nocow checks for (nowait == false) case.
@@ -6967,7 +6966,7 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
  */
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes)
+			      u64 *ram_bytes, bool strict)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_path *path;
@@ -7045,8 +7044,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 * Do the same check as in btrfs_cross_ref_exist but without the
 	 * unnecessary search.
 	 */
-	if (btrfs_file_extent_generation(leaf, fi) <=
-	    btrfs_root_last_snapshot(&root->root_item))
+	if (!strict &&
+	    (btrfs_file_extent_generation(leaf, fi) <=
+	     btrfs_root_last_snapshot(&root->root_item)))
 		goto out;
 
 	backref_offset = btrfs_file_extent_offset(leaf, fi);
@@ -7082,7 +7082,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 */
 
 	ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
-				    key.offset - backref_offset, disk_bytenr);
+				    key.offset - backref_offset, disk_bytenr,
+				    strict);
 	if (ret) {
 		ret = 0;
 		goto out;
@@ -7303,7 +7304,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		block_start = em->block_start + (start - em->start);
 
 		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes) == 1 &&
+				     &orig_block_len, &ram_bytes, false) == 1 &&
 		    btrfs_inc_nocow_writers(fs_info, block_start)) {
 			struct extent_map *em2;
 
@@ -7619,10 +7620,8 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
 				    struct bio *bio, u64 offset)
 {
 	struct inode *inode = private_data;
-	blk_status_t ret;
-	ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
-	BUG_ON(ret); /* -ENOMEM */
-	return 0;
+
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
 }
 
 static void btrfs_end_dio_bio(struct bio *bio)
@@ -10136,7 +10135,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		free_extent_map(em);
 		em = NULL;
 
-		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL);
+		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true);
 		if (ret < 0) {
 			goto out;
 		} else if (ret) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bd3511c5ca81..ac45f022b495 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2086,9 +2086,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 		sh.len = item_len;
 		sh.transid = found_transid;
 
-		/* copy search result header */
-		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
-			ret = -EFAULT;
+		/*
+		 * Copy search result header. If we fault then loop again so we
+		 * can fault in the pages and -EFAULT there if there's a
+		 * problem. Otherwise we'll fault and then copy the buffer in
+		 * properly this next time through
+		 */
+		if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = 0;
 			goto out;
 		}
 
@@ -2096,10 +2101,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 
 		if (item_len) {
 			char __user *up = ubuf + *sk_offset;
-			/* copy the item */
-			if (read_extent_buffer_to_user(leaf, up,
-						       item_off, item_len)) {
-				ret = -EFAULT;
+			/*
+			 * Copy the item, same behavior as above, but reset the
+			 * * sk_offset so we copy the full thing again.
+			 */
+			if (read_extent_buffer_to_user_nofault(leaf, up,
+						item_off, item_len)) {
+				ret = 0;
+				*sk_offset -= sizeof(sh);
 				goto out;
 			}
 
@@ -2184,6 +2193,10 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
+		ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset);
+		if (ret)
+			break;
+
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);
 		if (ret != 0) {
 			if (ret > 0)
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 61f44e78e3c9..80567c11ec12 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -95,9 +95,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * offset is supposed to be a tree block which
 			 * must be aligned to nodesize.
 			 */
-			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-					offset, (unsigned long long)eb->fs_info->nodesize);
+			if (!IS_ALIGNED(offset, eb->fs_info->sectorsize))
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+					offset, eb->fs_info->sectorsize);
 			break;
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
@@ -112,8 +113,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * must be aligned to nodesize.
 			 */
 			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-				     offset, (unsigned long long)eb->fs_info->nodesize);
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+				     offset, eb->fs_info->sectorsize);
 			break;
 		default:
 			pr_cont("(extent %llu has INVALID ref type %d)\n",
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 5a6cb9db512e..354ab9985a34 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3716,50 +3716,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 	return 0;
 }
 
+static void scrub_workers_put(struct btrfs_fs_info *fs_info)
+{
+	if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt,
+					&fs_info->scrub_lock)) {
+		struct btrfs_workqueue *scrub_workers = NULL;
+		struct btrfs_workqueue *scrub_wr_comp = NULL;
+		struct btrfs_workqueue *scrub_parity = NULL;
+
+		scrub_workers = fs_info->scrub_workers;
+		scrub_wr_comp = fs_info->scrub_wr_completion_workers;
+		scrub_parity = fs_info->scrub_parity_workers;
+
+		fs_info->scrub_workers = NULL;
+		fs_info->scrub_wr_completion_workers = NULL;
+		fs_info->scrub_parity_workers = NULL;
+		mutex_unlock(&fs_info->scrub_lock);
+
+		btrfs_destroy_workqueue(scrub_workers);
+		btrfs_destroy_workqueue(scrub_wr_comp);
+		btrfs_destroy_workqueue(scrub_parity);
+	}
+}
+
 /*
  * get a reference count on fs_info->scrub_workers. start worker if necessary
  */
 static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 						int is_dev_replace)
 {
+	struct btrfs_workqueue *scrub_workers = NULL;
+	struct btrfs_workqueue *scrub_wr_comp = NULL;
+	struct btrfs_workqueue *scrub_parity = NULL;
 	unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND;
 	int max_active = fs_info->thread_pool_size;
+	int ret = -ENOMEM;
 
-	lockdep_assert_held(&fs_info->scrub_lock);
+	if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt))
+		return 0;
 
-	if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) {
-		ASSERT(fs_info->scrub_workers == NULL);
-		fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub",
-				flags, is_dev_replace ? 1 : max_active, 4);
-		if (!fs_info->scrub_workers)
-			goto fail_scrub_workers;
-
-		ASSERT(fs_info->scrub_wr_completion_workers == NULL);
-		fs_info->scrub_wr_completion_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubwrc", flags,
-					      max_active, 2);
-		if (!fs_info->scrub_wr_completion_workers)
-			goto fail_scrub_wr_completion_workers;
+	scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags,
+					      is_dev_replace ? 1 : max_active, 4);
+	if (!scrub_workers)
+		goto fail_scrub_workers;
 
-		ASSERT(fs_info->scrub_parity_workers == NULL);
-		fs_info->scrub_parity_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
+	scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_parity_workers)
-			goto fail_scrub_parity_workers;
+	if (!scrub_wr_comp)
+		goto fail_scrub_wr_completion_workers;
 
+	scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
+					     max_active, 2);
+	if (!scrub_parity)
+		goto fail_scrub_parity_workers;
+
+	mutex_lock(&fs_info->scrub_lock);
+	if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) {
+		ASSERT(fs_info->scrub_workers == NULL &&
+		       fs_info->scrub_wr_completion_workers == NULL &&
+		       fs_info->scrub_parity_workers == NULL);
+		fs_info->scrub_workers = scrub_workers;
+		fs_info->scrub_wr_completion_workers = scrub_wr_comp;
+		fs_info->scrub_parity_workers = scrub_parity;
 		refcount_set(&fs_info->scrub_workers_refcnt, 1);
-	} else {
-		refcount_inc(&fs_info->scrub_workers_refcnt);
+		mutex_unlock(&fs_info->scrub_lock);
+		return 0;
 	}
-	return 0;
+	/* Other thread raced in and created the workers for us */
+	refcount_inc(&fs_info->scrub_workers_refcnt);
+	mutex_unlock(&fs_info->scrub_lock);
 
+	ret = 0;
+	btrfs_destroy_workqueue(scrub_parity);
 fail_scrub_parity_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+	btrfs_destroy_workqueue(scrub_wr_comp);
 fail_scrub_wr_completion_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_workers);
+	btrfs_destroy_workqueue(scrub_workers);
 fail_scrub_workers:
-	return -ENOMEM;
+	return ret;
 }
 
 int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
@@ -3770,9 +3804,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	int ret;
 	struct btrfs_device *dev;
 	unsigned int nofs_flag;
-	struct btrfs_workqueue *scrub_workers = NULL;
-	struct btrfs_workqueue *scrub_wr_comp = NULL;
-	struct btrfs_workqueue *scrub_parity = NULL;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EAGAIN;
@@ -3819,13 +3850,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (IS_ERR(sctx))
 		return PTR_ERR(sctx);
 
+	ret = scrub_workers_get(fs_info, is_dev_replace);
+	if (ret)
+		goto out_free_ctx;
+
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
 	if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) &&
 		     !is_dev_replace)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -ENODEV;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	if (!is_dev_replace && !readonly &&
@@ -3834,7 +3869,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
 				rcu_str_deref(dev->name));
 		ret = -EROFS;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	mutex_lock(&fs_info->scrub_lock);
@@ -3843,7 +3878,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -EIO;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	down_read(&fs_info->dev_replace.rwsem);
@@ -3854,17 +3889,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -EINPROGRESS;
-		goto out_free_ctx;
+		goto out;
 	}
 	up_read(&fs_info->dev_replace.rwsem);
 
-	ret = scrub_workers_get(fs_info, is_dev_replace);
-	if (ret) {
-		mutex_unlock(&fs_info->scrub_lock);
-		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		goto out_free_ctx;
-	}
-
 	sctx->readonly = readonly;
 	dev->scrub_ctx = sctx;
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -3917,24 +3945,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 
 	mutex_lock(&fs_info->scrub_lock);
 	dev->scrub_ctx = NULL;
-	if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) {
-		scrub_workers = fs_info->scrub_workers;
-		scrub_wr_comp = fs_info->scrub_wr_completion_workers;
-		scrub_parity = fs_info->scrub_parity_workers;
-
-		fs_info->scrub_workers = NULL;
-		fs_info->scrub_wr_completion_workers = NULL;
-		fs_info->scrub_parity_workers = NULL;
-	}
 	mutex_unlock(&fs_info->scrub_lock);
 
-	btrfs_destroy_workqueue(scrub_workers);
-	btrfs_destroy_workqueue(scrub_wr_comp);
-	btrfs_destroy_workqueue(scrub_parity);
+	scrub_workers_put(fs_info);
 	scrub_put_ctx(sctx);
 
 	return ret;
-
+out:
+	scrub_workers_put(fs_info);
 out_free_ctx:
 	scrub_free_ctx(sctx);
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e529ddb35b87..25967ecaaf0a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -625,6 +625,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			} else if (strncmp(args[0].from, "lzo", 3) == 0) {
 				compress_type = "lzo";
 				info->compress_type = BTRFS_COMPRESS_LZO;
+				info->compress_level = 0;
 				btrfs_set_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 20c6ac1a5de7..d2fc292ac61b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1636,6 +1636,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
+		pending->snap = NULL;
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 517b44300a05..7b1fee630f97 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -984,7 +984,7 @@ static int check_inode_item(struct extent_buffer *leaf,
 	/* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */
 	if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) {
 		inode_item_err(leaf, slot,
-			"invalid inode generation: has %llu expect [0, %llu]",
+			"invalid inode transid: has %llu expect [0, %llu]",
 			       btrfs_inode_transid(leaf, iitem), super_gen + 1);
 		return -EUCLEAN;
 	}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 696dd861cc3c..39da9db35278 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3449,11 +3449,13 @@ fail:
 	btrfs_free_path(path);
 out_unlock:
 	mutex_unlock(&dir->log_mutex);
-	if (ret == -ENOSPC) {
+	if (err == -ENOSPC) {
 		btrfs_set_log_full_commit(trans);
-		ret = 0;
-	} else if (ret < 0)
-		btrfs_abort_transaction(trans, ret);
+		err = 0;
+	} else if (err < 0 && err != -ENOENT) {
+		/* ENOENT can be returned if the entry hasn't been fsynced yet */
+		btrfs_abort_transaction(trans, err);
+	}
 
 	btrfs_end_log_trans(root);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ee96c5869f57..117b43367629 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
@@ -4462,6 +4463,7 @@ int btrfs_uuid_scan_kthread(void *data)
 			goto skip;
 		}
 update_tree:
+		btrfs_release_path(path);
 		if (!btrfs_is_empty_uuid(root_item.uuid)) {
 			ret = btrfs_uuid_tree_add(trans, root_item.uuid,
 						  BTRFS_UUID_KEY_SUBVOL,
@@ -4486,6 +4488,7 @@ update_tree:
 		}
 
 skip:
+		btrfs_release_path(path);
 		if (trans) {
 			ret = btrfs_end_transaction(trans);
 			trans = NULL;
@@ -4493,7 +4496,6 @@ skip:
 				break;
 		}
 
-		btrfs_release_path(path);
 		if (key.offset < (u64)-1) {
 			key.offset++;
 		} else if (key.type < BTRFS_ROOT_ITEM_KEY) {
@@ -6483,8 +6485,17 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
 					    u64 devid, u8 *dev_uuid)
 {
 	struct btrfs_device *device;
+	unsigned int nofs_flag;
 
+	/*
+	 * We call this under the chunk_mutex, so we want to use NOFS for this
+	 * allocation, however we don't want to change btrfs_alloc_device() to
+	 * always do NOFS because we use it in a lot of other GFP_KERNEL safe
+	 * places.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	device = btrfs_alloc_device(NULL, &devid, dev_uuid);
+	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(device))
 		return device;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 061dd202979d..50bbc99e3d96 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1958,7 +1958,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		 */
 		set_buffer_new(bh);
 		set_buffer_unwritten(bh);
-		/* FALLTHRU */
+		fallthrough;
 	case IOMAP_MAPPED:
 		if ((iomap->flags & IOMAP_F_NEW) ||
 		    offset >= i_size_read(inode))
@@ -3157,6 +3157,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
 	WARN_ON(atomic_read(&bh->b_count) < 1);
 	lock_buffer(bh);
 	if (test_clear_buffer_dirty(bh)) {
+		/*
+		 * The bh should be mapped, but it might not be if the
+		 * device was hot-removed. Not much we can do but fail the I/O.
+		 */
+		if (!buffer_mapped(bh)) {
+			unlock_buffer(bh);
+			return -EIO;
+		}
+
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
 		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 55ccccf77cea..034b3f4fdd3a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -887,8 +887,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 	int have = ci->i_snap_caps;
 
 	if ((have & mask) == mask) {
-		dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s"
-		     " (mask %s)\n", ci->vfs_inode.i_ino,
+		dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s"
+		     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
 		     ceph_cap_string(have),
 		     ceph_cap_string(mask));
 		return 1;
@@ -899,8 +899,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		if (!__cap_is_valid(cap))
 			continue;
 		if ((cap->issued & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s"
-			     " (mask %s)\n", ci->vfs_inode.i_ino, cap,
+			dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s"
+			     " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap,
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch)
@@ -911,8 +911,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		/* does a combination of caps satisfy mask? */
 		have |= cap->issued;
 		if ((have & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s"
-			     " (mask %s)\n", ci->vfs_inode.i_ino,
+			dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s"
+			     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch) {
@@ -2872,7 +2872,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
 			struct cap_wait cw;
 			DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
-			cw.ino = inode->i_ino;
+			cw.ino = ceph_ino(inode);
 			cw.tgid = current->tgid;
 			cw.need = need;
 			cw.want = want;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 97539b497e4c..3e3fcda9b276 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -202,7 +202,7 @@ static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p)
 {
 	struct seq_file *s = p;
 
-	seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino,
+	seq_printf(s, "0x%-17llx%-17s%-17s\n", ceph_ino(inode),
 		   ceph_cap_string(cap->issued),
 		   ceph_cap_string(cap->implemented));
 	return 0;
@@ -247,7 +247,7 @@ static int caps_show(struct seq_file *s, void *p)
 
 	spin_lock(&mdsc->caps_list_lock);
 	list_for_each_entry(cw, &mdsc->cap_wait_list, list) {
-		seq_printf(s, "%-13d0x%-17lx%-17s%-17s\n", cw->tgid, cw->ino,
+		seq_printf(s, "%-13d0x%-17llx%-17s%-17s\n", cw->tgid, cw->ino,
 				ceph_cap_string(cw->need),
 				ceph_cap_string(cw->want));
 	}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 060bdcc5ce32..d72e4a12bb69 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -259,9 +259,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 			     dentry, dentry, d_inode(dentry));
 			ctx->pos = di->offset;
 			if (!dir_emit(ctx, dentry->d_name.name,
-				      dentry->d_name.len,
-				      ceph_translate_ino(dentry->d_sb,
-							 d_inode(dentry)->i_ino),
+				      dentry->d_name.len, ceph_present_inode(d_inode(dentry)),
 				      d_inode(dentry)->i_mode >> 12)) {
 				dput(dentry);
 				err = 0;
@@ -324,18 +322,21 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	/* always start with . and .. */
 	if (ctx->pos == 0) {
 		dout("readdir off 0 -> '.'\n");
-		if (!dir_emit(ctx, ".", 1, 
-			    ceph_translate_ino(inode->i_sb, inode->i_ino),
+		if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode),
 			    inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 1;
 	}
 	if (ctx->pos == 1) {
-		ino_t ino = parent_ino(file->f_path.dentry);
+		u64 ino;
+		struct dentry *dentry = file->f_path.dentry;
+
+		spin_lock(&dentry->d_lock);
+		ino = ceph_present_inode(dentry->d_parent->d_inode);
+		spin_unlock(&dentry->d_lock);
+
 		dout("readdir off 1 -> '..'\n");
-		if (!dir_emit(ctx, "..", 2,
-			    ceph_translate_ino(inode->i_sb, ino),
-			    inode->i_mode >> 12))
+		if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 2;
 	}
@@ -507,9 +508,6 @@ more:
 	}
 	for (; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
-		struct ceph_vino vino;
-		ino_t ino;
-		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -519,13 +517,10 @@ more:
 		     rde->name_len, rde->name, &rde->inode.in);
 
 		BUG_ON(!rde->inode.in);
-		ftype = le32_to_cpu(rde->inode.in->mode) >> 12;
-		vino.ino = le64_to_cpu(rde->inode.in->ino);
-		vino.snap = le64_to_cpu(rde->inode.in->snapid);
-		ino = ceph_vino_to_ino(vino);
 
 		if (!dir_emit(ctx, rde->name, rde->name_len,
-			      ceph_translate_ino(inode->i_sb, ino), ftype)) {
+			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
+			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
 			dout("filldir stopping us...\n");
 			return 0;
 		}
@@ -1161,7 +1156,7 @@ retry:
 
 	if (try_async && op == CEPH_MDS_OP_UNLINK &&
 	    (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
-		dout("async unlink on %lu/%.*s caps=%s", dir->i_ino,
+		dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
 		     dentry->d_name.len, dentry->d_name.name,
 		     ceph_cap_string(req->r_dir_caps));
 		set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
@@ -1745,7 +1740,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			case -ENOENT:
 				if (d_really_is_negative(dentry))
 					valid = 1;
-				/* Fallthrough */
+				fallthrough;
 			default:
 				break;
 			}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d51c3f2fdca0..3f4c993dfc6f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -252,7 +252,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 	case S_IFREG:
 		ceph_fscache_register_inode_cookie(inode);
 		ceph_fscache_file_set_cookie(inode, file);
-		/* fall through */
+		fallthrough;
 	case S_IFDIR:
 		ret = ceph_init_file_info(inode, file, fmode,
 						S_ISDIR(inode->i_mode));
@@ -630,8 +630,8 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	} else {
 		struct dentry *dn;
 
-		dout("%s d_adding new inode 0x%llx to 0x%lx/%s\n", __func__,
-			vino.ino, dir->i_ino, dentry->d_name.name);
+		dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__,
+			vino.ino, ceph_ino(dir), dentry->d_name.name);
 		ceph_dir_clear_ordered(dir);
 		ceph_init_inode_acls(inode, as_ctx);
 		if (inode->i_state & I_NEW) {
@@ -2507,6 +2507,7 @@ const struct file_operations ceph_file_fops = {
 	.mmap = ceph_mmap,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
+	.setlease = simple_nosetlease,
 	.flock = ceph_flock,
 	.splice_read = generic_file_splice_read,
 	.splice_write = iter_file_splice_write,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 357c937699d5..d163fa96cb40 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -41,8 +41,10 @@ static void ceph_inode_work(struct work_struct *work);
  */
 static int ceph_set_ino_cb(struct inode *inode, void *data)
 {
-	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
-	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ci->i_vino = *(struct ceph_vino *)data;
+	inode->i_ino = ceph_vino_to_ino_t(ci->i_vino);
 	inode_set_iversion_raw(inode, 0);
 	return 0;
 }
@@ -50,17 +52,14 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
 struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
 {
 	struct inode *inode;
-	ino_t t = ceph_vino_to_ino(vino);
 
-	inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
+	inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
+			     ceph_set_ino_cb, &vino);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
-	if (inode->i_state & I_NEW)
-		dout("get_inode created new inode %p %llx.%llx ino %llx\n",
-		     inode, ceph_vinop(inode), (u64)inode->i_ino);
 
-	dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
-	     vino.snap, inode);
+	dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode),
+	     ceph_vinop(inode), inode, !!(inode->i_state & I_NEW));
 	return inode;
 }
 
@@ -2378,7 +2377,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
 	}
 
 	generic_fillattr(inode, stat);
-	stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
+	stat->ino = ceph_present_inode(inode);
 
 	/*
 	 * btime on newly-allocated inodes is 0, so if this is still set to
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index bc9e95937d7c..658800605bfb 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -372,7 +372,7 @@ struct ceph_quotarealm_inode {
 
 struct cap_wait {
 	struct list_head	list;
-	unsigned long		ino;
+	u64			ino;
 	pid_t			tgid;
 	int			need;
 	int			want;
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 198ddde5c1e6..cc2c4d40b022 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -23,12 +23,12 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct super_block *sb = mdsc->fsc->sb;
+	struct inode *root = d_inode(sb->s_root);
 
 	if (atomic64_read(&mdsc->quotarealms_count) > 0)
 		return true;
 	/* if root is the real CephFS root, we don't have quota realms */
-	if (sb->s_root->d_inode &&
-	    (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT))
+	if (root && ceph_ino(root) == CEPH_INO_ROOT)
 		return false;
 	/* otherwise, we can't know for sure */
 	return true;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 4c3c964b1c54..a3995ebe0623 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -457,15 +457,7 @@ ceph_vino(const struct inode *inode)
 	return ceph_inode(inode)->i_vino;
 }
 
-/*
- * ino_t is <64 bits on many architectures, blech.
- *
- *               i_ino (kernel inode)   st_ino (userspace)
- * i386          32                     32
- * x86_64+ino32  64                     32
- * x86_64        64                     64
- */
-static inline u32 ceph_ino_to_ino32(__u64 vino)
+static inline u32 ceph_ino_to_ino32(u64 vino)
 {
 	u32 ino = vino & 0xffffffff;
 	ino ^= vino >> 32;
@@ -475,34 +467,17 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
 }
 
 /*
- * kernel i_ino value
+ * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on
+ * some arches. We generally do not use this value inside the ceph driver, but
+ * we do want to set it to something, so that generic vfs code has an
+ * appropriate value for tracepoints and the like.
  */
-static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino)
 {
-#if BITS_PER_LONG == 32
-	return ceph_ino_to_ino32(vino.ino);
-#else
+	if (sizeof(ino_t) == sizeof(u32))
+		return ceph_ino_to_ino32(vino.ino);
 	return (ino_t)vino.ino;
-#endif
-}
-
-/*
- * user-visible ino (stat, filldir)
- */
-#if BITS_PER_LONG == 32
-static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
-{
-	return ino;
-}
-#else
-static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
-{
-	if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))
-		ino = ceph_ino_to_ino32(ino);
-	return ino;
 }
-#endif
-
 
 /* for printf-style formatting */
 #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
@@ -511,11 +486,34 @@ static inline u64 ceph_ino(struct inode *inode)
 {
 	return ceph_inode(inode)->i_vino.ino;
 }
+
 static inline u64 ceph_snap(struct inode *inode)
 {
 	return ceph_inode(inode)->i_vino.snap;
 }
 
+/**
+ * ceph_present_ino - format an inode number for presentation to userland
+ * @sb: superblock where the inode lives
+ * @ino: inode number to (possibly) convert
+ *
+ * If the user mounted with the ino32 option, then the 64-bit value needs
+ * to be converted to something that can fit inside 32 bits. Note that
+ * internal kernel code never uses this value, so this is entirely for
+ * userland consumption.
+ */
+static inline u64 ceph_present_ino(struct super_block *sb, u64 ino)
+{
+	if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)))
+		return ceph_ino_to_ino32(ino);
+	return ino;
+}
+
+static inline u64 ceph_present_inode(struct inode *inode)
+{
+	return ceph_present_ino(inode->i_sb, ceph_ino(inode));
+}
+
 static inline int ceph_ino_compare(struct inode *inode, void *data)
 {
 	struct ceph_vino *pvino = (struct ceph_vino *)data;
@@ -524,11 +522,16 @@ static inline int ceph_ino_compare(struct inode *inode, void *data)
 		ci->i_vino.snap == pvino->snap;
 }
 
+
 static inline struct inode *ceph_find_inode(struct super_block *sb,
 					    struct ceph_vino vino)
 {
-	ino_t t = ceph_vino_to_ino(vino);
-	return ilookup5(sb, t, ceph_ino_compare, &vino);
+	/*
+	 * NB: The hashval will be run through the fs/inode.c hash function
+	 * anyway, so there is no need to squash the inode number down to
+	 * 32-bits first. Just use low-order bits on arches with 32-bit long.
+	 */
+	return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino);
 }
 
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b296964b8afa..b565d83ba89e 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -2031,4 +2031,19 @@ static inline bool is_smb1_server(struct TCP_Server_Info *server)
 	return strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0;
 }
 
+static inline bool is_tcon_dfs(struct cifs_tcon *tcon)
+{
+	/*
+	 * For SMB1, see MS-CIFS 2.4.55 SMB_COM_TREE_CONNECT_ANDX (0x75) and MS-CIFS 3.3.4.4 DFS
+	 * Subsystem Notifies That a Share Is a DFS Share.
+	 *
+	 * For SMB2+, see MS-SMB2 2.2.10 SMB2 TREE_CONNECT Response and MS-SMB2 3.3.4.14 Server
+	 * Application Updates a Share.
+	 */
+	if (!tcon || !tcon->ses || !tcon->ses->server)
+		return false;
+	return is_smb1_server(tcon->ses->server) ? tcon->Flags & SMB_SHARE_IS_IN_DFS :
+		tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT);
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 0e763d2dcf16..0496934feecb 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -581,7 +581,7 @@ should_set_ext_sec_flag(enum securityEnum sectype)
 		if (global_secflags &
 		    (CIFSSEC_MAY_KRB5 | CIFSSEC_MAY_NTLMSSP))
 			return true;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a275ee399dce..a5731dd6e656 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1378,25 +1378,25 @@ static int cifs_parse_security_flavors(char *value,
 		return 1;
 	case Opt_sec_krb5i:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_krb5:
 		vol->sectype = Kerberos;
 		break;
 	case Opt_sec_ntlmsspi:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_ntlmssp:
 		vol->sectype = RawNTLMSSP;
 		break;
 	case Opt_sec_ntlmi:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_ntlm:
 		vol->sectype = NTLM;
 		break;
 	case Opt_sec_ntlmv2i:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_ntlmv2:
 		vol->sectype = NTLMv2;
 		break;
@@ -2187,7 +2187,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				vol->password = NULL;
 				break;
 			}
-			/* Fallthrough - to Opt_pass below.*/
+			fallthrough;	/* to Opt_pass below */
 		case Opt_pass:
 			/* Obtain the value string */
 			value = strchr(data, '=');
@@ -4909,7 +4909,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
 		if (!tcon)
 			continue;
 		/* Make sure that requests go through new root servers */
-		if (tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT)) {
+		if (is_tcon_dfs(tcon)) {
 			put_root_ses(root_ses);
 			set_root_ses(cifs_sb, ses, &root_ses);
 		}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3989d08396ac..1f75b25e559a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1017,6 +1017,8 @@ handle_mnt_opt:
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) {
 		rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, true,
 				       full_path, fid);
+		if (rc == -EREMOTE)
+			rc = 0;
 		if (rc) {
 			cifs_dbg(FYI, "%s: Get mode from SID failed. rc=%d\n",
 				 __func__, rc);
@@ -1025,6 +1027,8 @@ handle_mnt_opt:
 	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
 		rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, false,
 				       full_path, fid);
+		if (rc == -EREMOTE)
+			rc = 0;
 		if (rc) {
 			cifs_dbg(FYI, "%s: Getting ACL failed with error: %d\n",
 				 __func__, rc);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 69cd5856621b..de564368a887 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -798,7 +798,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 			if ((server->sec_kerberos || server->sec_mskerberos) &&
 			    (global_secflags & CIFSSEC_MAY_KRB5))
 				return Kerberos;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return Unspecified;
 		}
@@ -815,7 +815,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		default:
 			break;
 		}
-		/* Fallthrough - to attempt LANMAN authentication next */
+		fallthrough;	/* to attempt LANMAN authentication next */
 	case CIFS_NEGFLAVOR_LANMAN:
 		switch (requested) {
 		case LANMAN:
@@ -823,7 +823,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		case Unspecified:
 			if (global_secflags & CIFSSEC_MAY_LANMAN)
 				return LANMAN;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return Unspecified;
 		}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 667d70aa335f..96c172d94fba 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1101,7 +1101,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		if ((server->sec_kerberos || server->sec_mskerberos) &&
 			(global_secflags & CIFSSEC_MAY_KRB5))
 			return Kerberos;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		return Unspecified;
 	}
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cb733652ecca..ca2273727225 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1688,11 +1688,11 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
-			/* fall through */
+			fallthrough;
 		case 0:
 			if (offset >= 0)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
diff --git a/fs/dax.c b/fs/dax.c
index 95341af1a966..994ab66a9907 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1367,7 +1367,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			ret = dax_load_hole(&xas, mapping, &entry, vmf);
 			goto finish_iomap;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		WARN_ON_ONCE(1);
 		error = -EIO;
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index b167d2d02148..a768a09430c3 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -177,7 +177,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		goto out;
 
 	if (!fops_get(real_fops)) {
-#ifdef MODULE
+#ifdef CONFIG_MODULES
 		if (real_fops->owner &&
 		    real_fops->owner->state == MODULE_STATE_GOING)
 			goto out;
@@ -312,7 +312,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		goto out;
 
 	if (!fops_get(real_fops)) {
-#ifdef MODULE
+#ifdef CONFIG_MODULES
 		if (real_fops->owner &&
 		    real_fops->owner->state == MODULE_STATE_GOING)
 			goto out;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 18d81599522f..002123efc6b0 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -5817,7 +5817,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 		break;
 	case -EAGAIN:
 		error = 0;
-		/* fall through */
+		fallthrough;
 	default:
 		__put_lkb(ls, lkb);
 		goto out;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7d40d78ea864..ae325541884e 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -359,7 +359,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 		return z_erofs_extent_lookback(m, m->delta[0]);
 	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
 		map->m_flags &= ~EROFS_MAP_ZIPPED;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
 		map->m_la = (lcn << lclusterbits) | m->clusterofs;
 		break;
@@ -416,7 +416,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
 		if (endoff >= m.clusterofs)
 			map->m_flags &= ~EROFS_MAP_ZIPPED;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
 		if (endoff >= m.clusterofs) {
 			map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
@@ -433,7 +433,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 		end = (m.lcn << lclusterbits) | m.clusterofs;
 		map->m_flags |= EROFS_MAP_FULL_MAPPED;
 		m.delta[0] = 1;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
 		/* get the correspoinding first chunk */
 		err = z_erofs_extent_lookback(&m, m.delta[0]);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 12eebcdea9c8..8107e06d7f6f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1994,9 +1994,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 			 * not already there, and calling reverse_path_check()
 			 * during ep_insert().
 			 */
-			if (list_empty(&epi->ffd.file->f_tfile_llink))
-				list_add(&epi->ffd.file->f_tfile_llink,
-					 &tfile_check_list);
+			if (list_empty(&epi->ffd.file->f_tfile_llink)) {
+				if (get_file_rcu(epi->ffd.file))
+					list_add(&epi->ffd.file->f_tfile_llink,
+						 &tfile_check_list);
+			}
 		}
 	}
 	mutex_unlock(&ep->mtx);
@@ -2040,6 +2042,7 @@ static void clear_tfile_check_list(void)
 		file = list_first_entry(&tfile_check_list, struct file,
 					f_tfile_llink);
 		list_del_init(&file->f_tfile_llink);
+		fput(file);
 	}
 	INIT_LIST_HEAD(&tfile_check_list);
 }
@@ -2200,25 +2203,22 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 			full_check = 1;
 			if (is_file_epoll(tf.file)) {
 				error = -ELOOP;
-				if (ep_loop_check(ep, tf.file) != 0) {
-					clear_tfile_check_list();
+				if (ep_loop_check(ep, tf.file) != 0)
 					goto error_tgt_fput;
-				}
-			} else
+			} else {
+				get_file(tf.file);
 				list_add(&tf.file->f_tfile_llink,
 							&tfile_check_list);
+			}
 			error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
-			if (error) {
-out_del:
-				list_del(&tf.file->f_tfile_llink);
+			if (error)
 				goto error_tgt_fput;
-			}
 			if (is_file_epoll(tf.file)) {
 				tep = tf.file->private_data;
 				error = epoll_mutex_lock(&tep->mtx, 1, nonblock);
 				if (error) {
 					mutex_unlock(&ep->mtx);
-					goto out_del;
+					goto error_tgt_fput;
 				}
 			}
 		}
@@ -2239,8 +2239,6 @@ out_del:
 			error = ep_insert(ep, epds, tf.file, fd, full_check);
 		} else
 			error = -EEXIST;
-		if (full_check)
-			clear_tfile_check_list();
 		break;
 	case EPOLL_CTL_DEL:
 		if (epi)
@@ -2263,8 +2261,10 @@ out_del:
 	mutex_unlock(&ep->mtx);
 
 error_tgt_fput:
-	if (full_check)
+	if (full_check) {
+		clear_tfile_check_list();
 		mutex_unlock(&epmutex);
+	}
 
 	fdput(tf);
 error_fput:
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 60378ddf1424..96044f5dbc0e 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -93,8 +93,10 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	vm_fault_t ret;
+	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
+		(vmf->vma->vm_flags & VM_SHARED);
 
-	if (vmf->flags & FAULT_FLAG_WRITE) {
+	if (write) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vmf->vma->vm_file);
 	}
@@ -103,7 +105,7 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, NULL, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
-	if (vmf->flags & FAULT_FLAG_WRITE)
+	if (write)
 		sb_end_pagefault(inode->i_sb);
 	return ret;
 }
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 80662e1f7889..415c21f0e750 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1241,7 +1241,7 @@ do_indirects:
 				mark_inode_dirty(inode);
 				ext2_free_branches(inode, &nr, &nr+1, 1);
 			}
-			/* fall through */
+			fallthrough;
 		case EXT2_IND_BLOCK:
 			nr = i_data[EXT2_DIND_BLOCK];
 			if (nr) {
@@ -1249,7 +1249,7 @@ do_indirects:
 				mark_inode_dirty(inode);
 				ext2_free_branches(inode, &nr, &nr+1, 2);
 			}
-			/* fall through */
+			fallthrough;
 		case EXT2_DIND_BLOCK:
 			nr = i_data[EXT2_TIND_BLOCK];
 			if (nr) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index dda860562ca3..7fab2b3b5b39 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -587,7 +587,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_xip:
 			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
 			set_opt(opts->s_mount_opt, XIP);
-			/* Fall through */
+			fallthrough;
 		case Opt_dax:
 #ifdef CONFIG_FS_DAX
 			ext2_msg(sb, KERN_WARNING,
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 1afa5a4bcb5f..619dd35ddd48 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -110,7 +110,7 @@ config EXT4_KUNIT_TESTS
 	  This builds the ext4 KUnit tests.
 
 	  KUnit tests run during boot and output the results to the debug log
-	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
 	  running KUnit test harness and are not for inclusion into a production
 	  build.
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1ba46d87cdf1..48c3df47748d 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -413,7 +413,8 @@ verified:
  * Return buffer_head on success or an ERR_PTR in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
+			      bool ignore_locked)
 {
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -441,6 +442,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (ignore_locked && buffer_locked(bh)) {
+		/* buffer under IO already, return if called for prefetching */
+		put_bh(bh);
+		return NULL;
+	}
+
 	if (bitmap_uptodate(bh))
 		goto verify;
 
@@ -487,10 +494,11 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	 * submit the buffer_head for reading
 	 */
 	set_buffer_new(bh);
-	trace_ext4_read_block_bitmap_load(sb, block_group);
+	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO |
+		  (ignore_locked ? REQ_RAHEAD : 0), bh);
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -534,7 +542,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct buffer_head *bh;
 	int err;
 
-	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group, false);
 	if (IS_ERR(bh))
 		return bh;
 	err = ext4_wait_block_bitmap(sb, block_group, bh);
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 16e9b2fda03a..c54ba52f2dd4 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -24,6 +24,7 @@ struct ext4_system_zone {
 	struct rb_node	node;
 	ext4_fsblk_t	start_blk;
 	unsigned int	count;
+	u32		ino;
 };
 
 static struct kmem_cache *ext4_system_zone_cachep;
@@ -45,7 +46,8 @@ void ext4_exit_system_zone(void)
 static inline int can_merge(struct ext4_system_zone *entry1,
 		     struct ext4_system_zone *entry2)
 {
-	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
 		return 1;
 	return 0;
 }
@@ -66,9 +68,9 @@ static void release_system_zone(struct ext4_system_blocks *system_blks)
  */
 static int add_system_zone(struct ext4_system_blocks *system_blks,
 			   ext4_fsblk_t start_blk,
-			   unsigned int count)
+			   unsigned int count, u32 ino)
 {
-	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &system_blks->root.rb_node, *node;
 	struct rb_node *parent = NULL, *new_node = NULL;
 
@@ -79,30 +81,21 @@ static int add_system_zone(struct ext4_system_blocks *system_blks,
 			n = &(*n)->rb_left;
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
-		else {
-			if (start_blk + count > (entry->start_blk +
-						 entry->count))
-				entry->count = (start_blk + count -
-						entry->start_blk);
-			new_node = *n;
-			new_entry = rb_entry(new_node, struct ext4_system_zone,
-					     node);
-			break;
-		}
+		else	/* Unexpected overlap of system zones. */
+			return -EFSCORRUPTED;
 	}
 
-	if (!new_entry) {
-		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
-					     GFP_KERNEL);
-		if (!new_entry)
-			return -ENOMEM;
-		new_entry->start_blk = start_blk;
-		new_entry->count = count;
-		new_node = &new_entry->node;
-
-		rb_link_node(new_node, parent, n);
-		rb_insert_color(new_node, &system_blks->root);
-	}
+	new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+				     GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+	new_entry->start_blk = start_blk;
+	new_entry->count = count;
+	new_entry->ino = ino;
+	new_node = &new_entry->node;
+
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &system_blks->root);
 
 	/* Can we merge to the left? */
 	node = rb_prev(new_node);
@@ -151,40 +144,6 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
 	printk(KERN_CONT "\n");
 }
 
-/*
- * Returns 1 if the passed-in block region (start_blk,
- * start_blk+count) is valid; 0 if some part of the block region
- * overlaps with filesystem metadata blocks.
- */
-static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi,
-				     struct ext4_system_blocks *system_blks,
-				     ext4_fsblk_t start_blk,
-				     unsigned int count)
-{
-	struct ext4_system_zone *entry;
-	struct rb_node *n;
-
-	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
-	    (start_blk + count < start_blk) ||
-	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
-		return 0;
-
-	if (system_blks == NULL)
-		return 1;
-
-	n = system_blks->root.rb_node;
-	while (n) {
-		entry = rb_entry(n, struct ext4_system_zone, node);
-		if (start_blk + count - 1 < entry->start_blk)
-			n = n->rb_left;
-		else if (start_blk >= (entry->start_blk + entry->count))
-			n = n->rb_right;
-		else
-			return 0;
-	}
-	return 1;
-}
-
 static int ext4_protect_reserved_inode(struct super_block *sb,
 				       struct ext4_system_blocks *system_blks,
 				       u32 ino)
@@ -214,19 +173,18 @@ static int ext4_protect_reserved_inode(struct super_block *sb,
 		if (n == 0) {
 			i++;
 		} else {
-			if (!ext4_data_block_valid_rcu(sbi, system_blks,
-						map.m_pblk, n)) {
-				err = -EFSCORRUPTED;
-				__ext4_error(sb, __func__, __LINE__, -err,
-					     map.m_pblk, "blocks %llu-%llu "
-					     "from inode %u overlap system zone",
-					     map.m_pblk,
-					     map.m_pblk + map.m_len - 1, ino);
+			err = add_system_zone(system_blks, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					__ext4_error(sb, __func__, __LINE__,
+						     -err, map.m_pblk,
+						     "blocks %llu-%llu from inode %u overlap system zone",
+						     map.m_pblk,
+						     map.m_pblk + map.m_len - 1,
+						     ino);
+				}
 				break;
 			}
-			err = add_system_zone(system_blks, map.m_pblk, n);
-			if (err < 0)
-				break;
 			i += n;
 		}
 	}
@@ -262,14 +220,6 @@ int ext4_setup_system_zone(struct super_block *sb)
 	int flex_size = ext4_flex_bg_size(sbi);
 	int ret;
 
-	if (!test_opt(sb, BLOCK_VALIDITY)) {
-		if (sbi->system_blks)
-			ext4_release_system_zone(sb);
-		return 0;
-	}
-	if (sbi->system_blks)
-		return 0;
-
 	system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL);
 	if (!system_blks)
 		return -ENOMEM;
@@ -277,22 +227,25 @@ int ext4_setup_system_zone(struct super_block *sb)
 	for (i=0; i < ngroups; i++) {
 		cond_resched();
 		if (ext4_bg_has_super(sb, i) &&
-		    ((i < 5) || ((i % flex_size) == 0)))
-			add_system_zone(system_blks,
+		    ((i < 5) || ((i % flex_size) == 0))) {
+			ret = add_system_zone(system_blks,
 					ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1);
+					ext4_bg_num_gdb(sb, i) + 1, 0);
+			if (ret)
+				goto err;
+		}
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		ret = add_system_zone(system_blks,
-				ext4_block_bitmap(sb, gdp), 1);
+				ext4_block_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
-				ext4_inode_bitmap(sb, gdp), 1);
+				ext4_inode_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
 				ext4_inode_table(sb, gdp),
-				sbi->s_itb_per_group);
+				sbi->s_itb_per_group, 0);
 		if (ret)
 			goto err;
 	}
@@ -341,11 +294,24 @@ void ext4_release_system_zone(struct super_block *sb)
 		call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
 }
 
-int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 			  unsigned int count)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_system_blocks *system_blks;
-	int ret;
+	struct ext4_system_zone *entry;
+	struct rb_node *n;
+	int ret = 1;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+		return 0;
 
 	/*
 	 * Lock the system zone to prevent it being released concurrently
@@ -354,8 +320,22 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
 	 */
 	rcu_read_lock();
 	system_blks = rcu_dereference(sbi->system_blks);
-	ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk,
-					count);
+	if (system_blks == NULL)
+		goto out_rcu;
+
+	n = system_blks->root.rb_node;
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else {
+			ret = (entry->ino == inode->i_ino);
+			break;
+		}
+	}
+out_rcu:
 	rcu_read_unlock();
 	return ret;
 }
@@ -374,8 +354,7 @@ int ext4_check_blockref(const char *function, unsigned int line,
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
 		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						    blk, 1))) {
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");
 			return -EFSCORRUPTED;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 42f5060f3cdf..523e00d7b392 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -434,10 +434,36 @@ struct flex_groups {
 #define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x725BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x624BC0FF /* User modifiable flags */
-
-/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
+/* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE		(EXT4_SECRM_FL | \
+					 EXT4_UNRM_FL | \
+					 EXT4_COMPR_FL | \
+					 EXT4_SYNC_FL | \
+					 EXT4_IMMUTABLE_FL | \
+					 EXT4_APPEND_FL | \
+					 EXT4_NODUMP_FL | \
+					 EXT4_NOATIME_FL | \
+					 EXT4_JOURNAL_DATA_FL | \
+					 EXT4_NOTAIL_FL | \
+					 EXT4_DIRSYNC_FL | \
+					 EXT4_TOPDIR_FL | \
+					 EXT4_EXTENTS_FL | \
+					 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \
+					 EXT4_DAX_FL | \
+					 EXT4_PROJINHERIT_FL | \
+					 EXT4_CASEFOLD_FL)
+
+/* User visible flags */
+#define EXT4_FL_USER_VISIBLE		(EXT4_FL_USER_MODIFIABLE | \
+					 EXT4_DIRTY_FL | \
+					 EXT4_COMPRBLK_FL | \
+					 EXT4_NOCOMPR_FL | \
+					 EXT4_ENCRYPT_FL | \
+					 EXT4_INDEX_FL | \
+					 EXT4_VERITY_FL | \
+					 EXT4_INLINE_DATA_FL)
+
+/* Flags we can manipulate with through FS_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
 					 EXT4_IMMUTABLE_FL | \
 					 EXT4_APPEND_FL | \
@@ -669,8 +695,6 @@ enum {
 /*
  * ioctl commands
  */
-#define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
-#define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
 #define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
 #define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
 #define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
@@ -687,17 +711,11 @@ enum {
 #define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
 #define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
 #define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
-#define EXT4_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
-#define EXT4_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
-#define EXT4_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
 /* ioctl codes 19--39 are reserved for fscrypt */
 #define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
 #define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
 #define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
 
-#define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
-#define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
-
 #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
 
 /*
@@ -722,8 +740,6 @@ enum {
 /*
  * ioctl commands in 32 bit emulation
  */
-#define EXT4_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
-#define EXT4_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
 #define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
 #define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
 #define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
@@ -1054,6 +1070,7 @@ struct ext4_inode_info {
 	struct timespec64 i_crtime;
 
 	/* mballoc */
+	atomic_t i_prealloc_active;
 	struct list_head i_prealloc_list;
 	spinlock_t i_prealloc_lock;
 
@@ -1172,6 +1189,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
+#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
@@ -1501,10 +1519,13 @@ struct ext4_sb_info {
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
+	unsigned int s_mb_max_inode_prealloc;
 	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
+	unsigned int s_mb_prefetch;
+	unsigned int s_mb_prefetch_limit;
 
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
@@ -1572,6 +1593,8 @@ struct ext4_sb_info {
 	struct ratelimit_state s_err_ratelimit_state;
 	struct ratelimit_state s_warning_ratelimit_state;
 	struct ratelimit_state s_msg_ratelimit_state;
+	atomic_t s_warning_count;
+	atomic_t s_msg_count;
 
 	/* Encryption context for '-o test_dummy_encryption' */
 	struct fscrypt_dummy_context s_dummy_enc_ctx;
@@ -1585,6 +1608,9 @@ struct ext4_sb_info {
 #ifdef CONFIG_EXT4_DEBUG
 	unsigned long s_simulate_fail;
 #endif
+	/* Record the errseq of the backing block device */
+	errseq_t s_bdev_wb_err;
+	spinlock_t s_bdev_wb_lock;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2313,9 +2339,15 @@ struct ext4_lazy_init {
 	struct mutex		li_list_mtx;
 };
 
+enum ext4_li_mode {
+	EXT4_LI_MODE_PREFETCH_BBITMAP,
+	EXT4_LI_MODE_ITABLE,
+};
+
 struct ext4_li_request {
 	struct super_block	*lr_super;
-	struct ext4_sb_info	*lr_sbi;
+	enum ext4_li_mode	lr_mode;
+	ext4_group_t		lr_first_not_zeroed;
 	ext4_group_t		lr_next_group;
 	struct list_head	lr_request;
 	unsigned long		lr_next_sched;
@@ -2446,7 +2478,8 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
-						ext4_group_t block_group);
+						ext4_group_t block_group,
+						bool ignore_locked);
 extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  ext4_group_t block_group,
 				  struct buffer_head *bh);
@@ -2651,9 +2684,15 @@ extern int ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
 extern int ext4_mb_reserve_blocks(struct super_block *, int);
-extern void ext4_discard_preallocations(struct inode *);
+extern void ext4_discard_preallocations(struct inode *, unsigned int);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
+extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
+				     ext4_group_t group,
+				     unsigned int nr, int *cnt);
+extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+				  unsigned int nr);
+
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     struct buffer_head *bh, ext4_fsblk_t block,
 			     unsigned long count, int flags);
@@ -2765,8 +2804,7 @@ extern int ext4_search_dir(struct buffer_head *bh,
 			   struct ext4_filename *fname,
 			   unsigned int offset,
 			   struct ext4_dir_entry_2 **res_dir);
-extern int ext4_generic_delete_entry(handle_t *handle,
-				     struct inode *dir,
+extern int ext4_generic_delete_entry(struct inode *dir,
 				     struct ext4_dir_entry_2 *de_del,
 				     struct buffer_head *bh,
 				     void *entry_buf,
@@ -2924,12 +2962,6 @@ do {									\
 
 #endif
 
-extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
-					__u32 compat);
-extern int ext4_update_rocompat_feature(handle_t *handle,
-					struct super_block *sb,	__u32 rocompat);
-extern int ext4_update_incompat_feature(handle_t *handle,
-					struct super_block *sb,	__u32 incompat);
 extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 				      struct ext4_group_desc *bg);
 extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
@@ -3145,6 +3177,7 @@ struct ext4_group_info {
 	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
 	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
@@ -3159,6 +3192,8 @@ struct ext4_group_info {
 	(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
 #define EXT4_MB_GRP_CLEAR_TRIMMED(grp)	\
 	(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
+	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
 
 #define EXT4_MAX_CONTENTION		8
 #define EXT4_CONTENTION_THRESHOLD	2
@@ -3363,9 +3398,9 @@ extern void ext4_release_system_zone(struct super_block *sb);
 extern int ext4_setup_system_zone(struct super_block *sb);
 extern int __init ext4_init_system_zone(void);
 extern void ext4_exit_system_zone(void);
-extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
-				 ext4_fsblk_t start_blk,
-				 unsigned int count);
+extern int ext4_inode_block_valid(struct inode *inode,
+				  ext4_fsblk_t start_blk,
+				  unsigned int count);
 extern int ext4_check_blockref(const char *, unsigned int,
 			       struct inode *, __le32 *, unsigned int);
 
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 0c76cdd44d90..760b9ee49dc0 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -195,6 +195,28 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line,
 	jbd2_journal_abort_handle(handle);
 }
 
+static void ext4_check_bdev_write_error(struct super_block *sb)
+{
+	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	/*
+	 * If the block device has write error flag, it may have failed to
+	 * async write out metadata buffers in the background. In this case,
+	 * we could read old data from disk and write it out again, which
+	 * may lead to on-disk filesystem inconsistency.
+	 */
+	if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
+		spin_lock(&sbi->s_bdev_wb_lock);
+		err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
+		spin_unlock(&sbi->s_bdev_wb_lock);
+		if (err)
+			ext4_error_err(sb, -err,
+				       "Error while async write back metadata");
+	}
+}
+
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh)
 {
@@ -202,6 +224,9 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 
 	might_sleep();
 
+	if (bh->b_bdev->bd_super)
+		ext4_check_bdev_write_error(bh->b_bdev->bd_super);
+
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 221f240eae60..a0481582187a 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
 	 * i_mutex. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
@@ -340,7 +340,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	 */
 	if (lblock + len <= lblock)
 		return 0;
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+	return ext4_inode_block_valid(inode, block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,
@@ -348,7 +348,7 @@ static int ext4_valid_extent_idx(struct inode *inode,
 {
 	ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
 
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+	return ext4_inode_block_valid(inode, block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,
@@ -507,14 +507,10 @@ __read_extent_tree_block(const char *function, unsigned int line,
 	}
 	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
 		return bh;
-	if (!ext4_has_feature_journal(inode->i_sb) ||
-	    (inode->i_ino !=
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
-		err = __ext4_ext_check(function, line, inode,
-				       ext_block_hdr(bh), depth, pblk);
-		if (err)
-			goto errout;
-	}
+	err = __ext4_ext_check(function, line, inode,
+			       ext_block_hdr(bh), depth, pblk);
+	if (err)
+		goto errout;
 	set_buffer_verified(bh);
 	/*
 	 * If this is a leaf block, cache all of its entries
@@ -693,10 +689,8 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path)
 		return;
 	depth = path->p_depth;
 	for (i = 0; i <= depth; i++, path++) {
-		if (path->p_bh) {
-			brelse(path->p_bh);
-			path->p_bh = NULL;
-		}
+		brelse(path->p_bh);
+		path->p_bh = NULL;
 	}
 }
 
@@ -1915,7 +1909,7 @@ out:
 
 /*
  * ext4_ext_insert_extent:
- * tries to merge requsted extent into the existing extent or
+ * tries to merge requested extent into the existing extent or
  * inserts requested extent as new one into the tree,
  * creating new leaf in the no-space case.
  */
@@ -3125,7 +3119,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
  *
  *
  * Splits extent [a, b] into two extents [a, @split) and [@split, b], states
- * of which are deterimined by split_flag.
+ * of which are determined by split_flag.
  *
  * There are two cases:
  *  a> the extent are splitted into two extent.
@@ -3650,7 +3644,7 @@ static int ext4_split_convert_extents(handle_t *handle,
 		eof_block = map->m_lblk + map->m_len;
 	/*
 	 * It is safe to convert extent to initialized via explicit
-	 * zeroout only if extent is fully insde i_size or new_size.
+	 * zeroout only if extent is fully inside i_size or new_size.
 	 */
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
@@ -4272,7 +4266,7 @@ got_allocated_blocks:
 			 * not a good idea to call discard here directly,
 			 * but otherwise we'd need to call it every free().
 			 */
-			ext4_discard_preallocations(inode);
+			ext4_discard_preallocations(inode, 0);
 			if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 				fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
 			ext4_free_blocks(handle, inode, NULL, newblock,
@@ -4495,7 +4489,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	/*
-	 * Round up offset. This is not fallocate, we neet to zero out
+	 * Round up offset. This is not fallocate, we need to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
 	 * range.
@@ -5299,7 +5293,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	ret = ext4_es_remove_extent(inode, punch_start,
 				    EXT_MAX_BLOCKS - punch_start);
@@ -5313,7 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		up_write(&EXT4_I(inode)->i_data_sem);
 		goto out_stop;
 	}
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
 				     punch_stop - punch_start, SHIFT_LEFT);
@@ -5445,7 +5439,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
@@ -5579,7 +5573,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1,
 		}
 		ex1 = path1[path1->p_depth].p_ext;
 		ex2 = path2[path2->p_depth].p_ext;
-		/* Do we have somthing to swap ? */
+		/* Do we have something to swap ? */
 		if (unlikely(!ex2 || !ex1))
 			goto finish;
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 129cc1dd6b79..7d61069531d3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -145,10 +145,9 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	/* if we are the last writer on the inode, drop the block reservation */
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1) &&
-		        !EXT4_I(inode)->i_reserved_data_blocks)
-	{
+			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
@@ -428,6 +427,10 @@ restart:
 	 */
 	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
 	     !ext4_overwrite_io(inode, offset, count))) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
 		inode_unlock_shared(inode);
 		*ilock_shared = false;
 		inode_lock(inode);
@@ -812,7 +815,7 @@ out:
 	return err;
 }
 
-static int ext4_file_open(struct inode * inode, struct file * filp)
+static int ext4_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 3e133793a5a3..2924261226e0 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -233,7 +233,7 @@ static int __ext4fs_dirhash(const char *name, int len,
 		break;
 	case DX_HASH_HALF_MD4_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
-		/* fall through */
+		fallthrough;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
@@ -247,7 +247,7 @@ static int __ext4fs_dirhash(const char *name, int len,
 		break;
 	case DX_HASH_TEA_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
-		/* fall through */
+		fallthrough;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index be2b66eb65f7..80c9f33800be 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
 	 * i_mutex. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
@@ -858,8 +858,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
 
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
-				   count)) {
+	if (!ext4_inode_block_valid(inode, block_to_free, count)) {
 		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
 				 "blocks %llu len %lu",
 				 (unsigned long long) block_to_free, count);
@@ -1004,8 +1003,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 			if (!nr)
 				continue;		/* A hole */
 
-			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						   nr, 1)) {
+			if (!ext4_inode_block_valid(inode, nr, 1)) {
 				EXT4_ERROR_INODE(inode,
 						 "invalid indirect mapped "
 						 "block %lu (level %d)",
@@ -1182,21 +1180,21 @@ do_indirects:
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_IND_BLOCK:
 		nr = i_data[EXT4_DIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
 			i_data[EXT4_DIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_DIND_BLOCK:
 		nr = i_data[EXT4_TIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
 			i_data[EXT4_TIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_TIND_BLOCK:
 		;
 	}
@@ -1436,7 +1434,7 @@ do_indirects:
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_IND_BLOCK:
 		if (++n >= n2)
 			break;
@@ -1445,7 +1443,7 @@ do_indirects:
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
 			i_data[EXT4_DIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_DIND_BLOCK:
 		if (++n >= n2)
 			break;
@@ -1454,7 +1452,7 @@ do_indirects:
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
 			i_data[EXT4_TIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_TIND_BLOCK:
 		;
 	}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index c3a1ad2db122..75c97bca0815 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -276,7 +276,7 @@ static int ext4_create_inline_data(handle_t *handle,
 		len = 0;
 	}
 
-	/* Insert the the xttr entry. */
+	/* Insert the xttr entry. */
 	i.value = value;
 	i.value_len = len;
 
@@ -1706,7 +1706,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		goto out;
 
-	err = ext4_generic_delete_entry(handle, dir, de_del, bh,
+	err = ext4_generic_delete_entry(dir, de_del, bh,
 					inline_start, inline_size, 0);
 	if (err)
 		goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 44bad4bb8831..bf596467c234 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -383,7 +383,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
 	    !inode_is_open_for_write(inode))
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 }
 
 static int __check_block_validity(struct inode *inode, const char *func,
@@ -394,8 +394,7 @@ static int __check_block_validity(struct inode *inode, const char *func,
 	    (inode->i_ino ==
 	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
 		return 0;
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
-				   map->m_len)) {
+	if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
 				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,
@@ -3288,7 +3287,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 	if (PageChecked(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page, wait);
+		return jbd2_journal_try_to_free_buffers(journal, page);
 	else
 		return try_to_free_buffers(page);
 }
@@ -4056,7 +4055,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (stop_block > first_block) {
 
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 
 		ret = ext4_es_remove_extent(inode, first_block,
 					    stop_block - first_block);
@@ -4163,7 +4162,7 @@ int ext4_truncate(struct inode *inode)
 	trace_ext4_truncate_enter(inode);
 
 	if (!ext4_can_truncate(inode))
-		return 0;
+		goto out_trace;
 
 	if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
 		ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
@@ -4172,16 +4171,14 @@ int ext4_truncate(struct inode *inode)
 		int has_inline = 1;
 
 		err = ext4_inline_data_truncate(inode, &has_inline);
-		if (err)
-			return err;
-		if (has_inline)
-			return 0;
+		if (err || has_inline)
+			goto out_trace;
 	}
 
 	/* If we zero-out tail of the page, we have to create jinode for jbd2 */
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
 		if (ext4_inode_attach_jinode(inode) < 0)
-			return 0;
+			goto out_trace;
 	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
@@ -4190,8 +4187,10 @@ int ext4_truncate(struct inode *inode)
 		credits = ext4_blocks_for_truncate(inode);
 
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto out_trace;
+	}
 
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1))
 		ext4_block_truncate_page(handle, mapping, inode->i_size);
@@ -4211,7 +4210,7 @@ int ext4_truncate(struct inode *inode)
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		err = ext4_ext_truncate(handle, inode);
@@ -4242,6 +4241,7 @@ out_stop:
 		err = err2;
 	ext4_journal_stop(handle);
 
+out_trace:
 	trace_ext4_truncate_exit(inode);
 	return err;
 }
@@ -4760,7 +4760,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+	    !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: bad extended attribute block %llu",
 				 ei->i_file_acl);
@@ -4901,7 +4901,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb,
 	    (inode->i_state & I_DIRTY_TIME)) {
 		struct ext4_inode_info	*ei = EXT4_I(inode);
 
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 
 		spin_lock(&ei->i_raw_lock);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 999cf6add39c..36eca3bc036a 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -202,7 +202,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	reset_inode_seed(inode);
 	reset_inode_seed(inode_bl);
 
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
@@ -819,12 +819,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	switch (cmd) {
 	case FS_IOC_GETFSMAP:
 		return ext4_ioc_getfsmap(sb, (void __user *)arg);
-	case EXT4_IOC_GETFLAGS:
+	case FS_IOC_GETFLAGS:
 		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 		if (S_ISREG(inode->i_mode))
 			flags &= ~EXT4_PROJINHERIT_FL;
 		return put_user(flags, (int __user *) arg);
-	case EXT4_IOC_SETFLAGS: {
+	case FS_IOC_SETFLAGS: {
 		int err;
 
 		if (!inode_owner_or_capable(inode))
@@ -1129,12 +1129,12 @@ resizefs_out:
 	case EXT4_IOC_PRECACHE_EXTENTS:
 		return ext4_ext_precache(inode);
 
-	case EXT4_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_SET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
 		return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
 
-	case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+	case FS_IOC_GET_ENCRYPTION_PWSALT: {
 #ifdef CONFIG_FS_ENCRYPTION
 		int err, err2;
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1174,7 +1174,7 @@ resizefs_out:
 		return -EOPNOTSUPP;
 #endif
 	}
-	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
 		return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
@@ -1236,7 +1236,7 @@ resizefs_out:
 	case EXT4_IOC_GET_ES_CACHE:
 		return ext4_ioctl_get_es_cache(filp, arg);
 
-	case EXT4_IOC_FSGETXATTR:
+	case FS_IOC_FSGETXATTR:
 	{
 		struct fsxattr fa;
 
@@ -1247,7 +1247,7 @@ resizefs_out:
 			return -EFAULT;
 		return 0;
 	}
-	case EXT4_IOC_FSSETXATTR:
+	case FS_IOC_FSSETXATTR:
 	{
 		struct fsxattr fa, old_fa;
 		int err;
@@ -1313,11 +1313,11 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
-	case EXT4_IOC32_GETFLAGS:
-		cmd = EXT4_IOC_GETFLAGS;
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
 		break;
-	case EXT4_IOC32_SETFLAGS:
-		cmd = EXT4_IOC_SETFLAGS;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
 		break;
 	case EXT4_IOC32_GETVERSION:
 		cmd = EXT4_IOC_GETVERSION;
@@ -1361,9 +1361,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_RESIZE_FS:
 	case FITRIM:
 	case EXT4_IOC_PRECACHE_EXTENTS:
-	case EXT4_IOC_SET_ENCRYPTION_POLICY:
-	case EXT4_IOC_GET_ENCRYPTION_PWSALT:
-	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_PWSALT:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
 	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
 	case FS_IOC_ADD_ENCRYPTION_KEY:
 	case FS_IOC_REMOVE_ENCRYPTION_KEY:
@@ -1377,8 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_CLEAR_ES_CACHE:
 	case EXT4_IOC_GETSTATE:
 	case EXT4_IOC_GET_ES_CACHE:
-	case EXT4_IOC_FSGETXATTR:
-	case EXT4_IOC_FSSETXATTR:
+	case FS_IOC_FSGETXATTR:
+	case FS_IOC_FSSETXATTR:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c0a331e2feb0..132c118d12e1 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -922,7 +922,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 			bh[i] = NULL;
 			continue;
 		}
-		bh[i] = ext4_read_block_bitmap_nowait(sb, group);
+		bh[i] = ext4_read_block_bitmap_nowait(sb, group, false);
 		if (IS_ERR(bh[i])) {
 			err = PTR_ERR(bh[i]);
 			bh[i] = NULL;
@@ -1279,9 +1279,6 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 	e4b->bd_buddy_page = page;
 	e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
 
-	BUG_ON(e4b->bd_bitmap_page == NULL);
-	BUG_ON(e4b->bd_buddy_page == NULL);
-
 	return 0;
 
 err:
@@ -1743,10 +1740,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
 
 }
 
-/*
- * regular allocator, for general purposes allocation
- */
-
 static void ext4_mb_check_limits(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b,
 					int finish_group)
@@ -2119,13 +2112,11 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac,
 
 	BUG_ON(cr < 0 || cr >= 4);
 
-	free = grp->bb_free;
-	if (free == 0)
-		return false;
-	if (cr <= 2 && free < ac->ac_g_ex.fe_len)
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
 		return false;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+	free = grp->bb_free;
+	if (free == 0)
 		return false;
 
 	fragments = grp->bb_fragments;
@@ -2142,8 +2133,10 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac,
 		    ((group % flex_size) == 0))
 			return false;
 
-		if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) ||
-		    (free / fragments) >= ac->ac_g_ex.fe_len)
+		if (free < ac->ac_g_ex.fe_len)
+			return false;
+
+		if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1)
 			return true;
 
 		if (grp->bb_largest_free_order < ac->ac_2order)
@@ -2177,6 +2170,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 {
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 	struct super_block *sb = ac->ac_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK;
 	ext4_grpblk_t free;
 	int ret = 0;
@@ -2195,7 +2189,25 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
+		struct ext4_group_desc *gdp =
+			ext4_get_group_desc(sb, group, NULL);
+		int ret;
+
+		/* cr=0/1 is a very optimistic search to find large
+		 * good chunks almost for free.  If buddy data is not
+		 * ready, then this optimization makes no sense.  But
+		 * we never skip the first block group in a flex_bg,
+		 * since this gets used for metadata block allocation,
+		 * and we want to make sure we locate metadata blocks
+		 * in the first block group in the flex_bg if possible.
+		 */
+		if (cr < 2 &&
+		    (!sbi->s_log_groups_per_flex ||
+		     ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))))
+			return 0;
+		ret = ext4_mb_init_group(sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -2209,15 +2221,95 @@ out:
 	return ret;
 }
 
+/*
+ * Start prefetching @nr block bitmaps starting at @group.
+ * Return the next group which needs to be prefetched.
+ */
+ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
+			      unsigned int nr, int *cnt)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct buffer_head *bh;
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		/*
+		 * Prefetch block groups with free blocks; but don't
+		 * bother if it is marked uninitialized on disk, since
+		 * it won't require I/O to read.  Also only try to
+		 * prefetch once, so we avoid getblk() call, which can
+		 * be expensive.
+		 */
+		if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) &&
+		    EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			bh = ext4_read_block_bitmap_nowait(sb, group, true);
+			if (bh && !IS_ERR(bh)) {
+				if (!buffer_uptodate(bh) && cnt)
+					(*cnt)++;
+				brelse(bh);
+			}
+		}
+		if (++group >= ngroups)
+			group = 0;
+	}
+	blk_finish_plug(&plug);
+	return group;
+}
+
+/*
+ * Prefetching reads the block bitmap into the buffer cache; but we
+ * need to make sure that the buddy bitmap in the page cache has been
+ * initialized.  Note that ext4_mb_init_group() will block if the I/O
+ * is not yet completed, or indeed if it was not initiated by
+ * ext4_mb_prefetch did not start the I/O.
+ *
+ * TODO: We should actually kick off the buddy bitmap setup in a work
+ * queue when the buffer I/O is completed, so that we don't block
+ * waiting for the block allocation bitmap read to finish when
+ * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator().
+ */
+void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+			   unsigned int nr)
+{
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		if (!group)
+			group = ext4_get_groups_count(sb);
+		group--;
+		grp = ext4_get_group_info(sb, group);
+
+		if (EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			if (ext4_mb_init_group(sb, group, GFP_NOFS))
+				break;
+		}
+	}
+}
+
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
-	ext4_group_t ngroups, group, i;
+	ext4_group_t prefetch_grp = 0, ngroups, group, i;
 	int cr = -1;
 	int err = 0, first_err = 0;
+	unsigned int nr = 0, prefetch_ios = 0;
 	struct ext4_sb_info *sbi;
 	struct super_block *sb;
 	struct ext4_buddy e4b;
+	int lost;
 
 	sb = ac->ac_sb;
 	sbi = EXT4_SB(sb);
@@ -2237,8 +2329,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		goto out;
 
 	/*
-	 * ac->ac2_order is set only if the fe_len is a power of 2
-	 * if ac2_order is set we also set criteria to 0 so that we
+	 * ac->ac_2order is set only if the fe_len is a power of 2
+	 * if ac->ac_2order is set we also set criteria to 0 so that we
 	 * try exact allocation using buddy.
 	 */
 	i = fls(ac->ac_g_ex.fe_len);
@@ -2282,6 +2374,7 @@ repeat:
 		 * from the goal value specified
 		 */
 		group = ac->ac_g_ex.fe_group;
+		prefetch_grp = group;
 
 		for (i = 0; i < ngroups; group++, i++) {
 			int ret = 0;
@@ -2293,6 +2386,29 @@ repeat:
 			if (group >= ngroups)
 				group = 0;
 
+			/*
+			 * Batch reads of the block allocation bitmaps
+			 * to get multiple READs in flight; limit
+			 * prefetching at cr=0/1, otherwise mballoc can
+			 * spend a lot of time loading imperfect groups
+			 */
+			if ((prefetch_grp == group) &&
+			    (cr > 1 ||
+			     prefetch_ios < sbi->s_mb_prefetch_limit)) {
+				unsigned int curr_ios = prefetch_ios;
+
+				nr = sbi->s_mb_prefetch;
+				if (ext4_has_feature_flex_bg(sb)) {
+					nr = (group / sbi->s_mb_prefetch) *
+						sbi->s_mb_prefetch;
+					nr = nr + sbi->s_mb_prefetch - group;
+				}
+				prefetch_grp = ext4_mb_prefetch(sb, group,
+							nr, &prefetch_ios);
+				if (prefetch_ios == curr_ios)
+					nr = 0;
+			}
+
 			/* This now checks without needing the buddy page */
 			ret = ext4_mb_good_group_nolock(ac, group, cr);
 			if (ret <= 0) {
@@ -2341,22 +2457,24 @@ repeat:
 		 * We've been searching too long. Let's try to allocate
 		 * the best chunk we've found so far
 		 */
-
 		ext4_mb_try_best_found(ac, &e4b);
 		if (ac->ac_status != AC_STATUS_FOUND) {
 			/*
 			 * Someone more lucky has already allocated it.
 			 * The only thing we can do is just take first
 			 * found block(s)
-			printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n");
 			 */
+			lost = atomic_inc_return(&sbi->s_mb_lost_chunks);
+			mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n",
+				 ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start,
+				 ac->ac_b_ex.fe_len, lost);
+
 			ac->ac_b_ex.fe_group = 0;
 			ac->ac_b_ex.fe_start = 0;
 			ac->ac_b_ex.fe_len = 0;
 			ac->ac_status = AC_STATUS_CONTINUE;
 			ac->ac_flags |= EXT4_MB_HINT_FIRST;
 			cr = 3;
-			atomic_inc(&sbi->s_mb_lost_chunks);
 			goto repeat;
 		}
 	}
@@ -2367,6 +2485,10 @@ out:
 	mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n",
 		 ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status,
 		 ac->ac_flags, cr, err);
+
+	if (nr)
+		ext4_mb_prefetch_fini(sb, prefetch_grp, nr);
+
 	return err;
 }
 
@@ -2439,7 +2561,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	for (i = 0; i <= 13; i++)
 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
 				sg.info.bb_counters[i] : 0);
-	seq_printf(seq, " ]\n");
+	seq_puts(seq, " ]\n");
 
 	return 0;
 }
@@ -2613,6 +2735,26 @@ static int ext4_mb_init_backend(struct super_block *sb)
 			goto err_freebuddy;
 	}
 
+	if (ext4_has_feature_flex_bg(sb)) {
+		/* a single flex group is supposed to be read by a single IO */
+		sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
+	} else {
+		sbi->s_mb_prefetch = 32;
+	}
+	if (sbi->s_mb_prefetch > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch = ext4_get_groups_count(sb);
+	/* now many real IOs to prefetch within a single allocation at cr=0
+	 * given cr=0 is an CPU-related optimization we shouldn't try to
+	 * load too many groups, at some point we should start to use what
+	 * we've got in memory.
+	 * with an average random access time 5ms, it'd take a second to get
+	 * 200 groups (* N with flex_bg), so let's make this limit 4
+	 */
+	sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4;
+	if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb);
+
 	return 0;
 
 err_freebuddy:
@@ -2736,6 +2878,7 @@ int ext4_mb_init(struct super_block *sb)
 	sbi->s_mb_stats = MB_DEFAULT_STATS;
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
+	sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC;
 	/*
 	 * The default group preallocation is 512, which for 4k block
 	 * sizes translates to 2 megabytes.  However for bigalloc file
@@ -3090,7 +3233,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 
 	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-	if (!ext4_data_block_valid(sbi, block, len)) {
+	if (!ext4_inode_block_valid(ac->ac_inode, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error
@@ -3674,6 +3817,26 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 	mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);
 }
 
+static void ext4_mb_mark_pa_deleted(struct super_block *sb,
+				    struct ext4_prealloc_space *pa)
+{
+	struct ext4_inode_info *ei;
+
+	if (pa->pa_deleted) {
+		ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n",
+			     pa->pa_type, pa->pa_pstart, pa->pa_lstart,
+			     pa->pa_len);
+		return;
+	}
+
+	pa->pa_deleted = 1;
+
+	if (pa->pa_type == MB_INODE_PA) {
+		ei = EXT4_I(pa->pa_inode);
+		atomic_dec(&ei->i_prealloc_active);
+	}
+}
+
 static void ext4_mb_pa_callback(struct rcu_head *head)
 {
 	struct ext4_prealloc_space *pa;
@@ -3706,7 +3869,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 		return;
 	}
 
-	pa->pa_deleted = 1;
+	ext4_mb_mark_pa_deleted(sb, pa);
 	spin_unlock(&pa->pa_lock);
 
 	grp_blk = pa->pa_pstart;
@@ -3830,6 +3993,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	spin_lock(pa->pa_obj_lock);
 	list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list);
 	spin_unlock(pa->pa_obj_lock);
+	atomic_inc(&ei->i_prealloc_active);
 }
 
 /*
@@ -4040,7 +4204,7 @@ repeat:
 		}
 
 		/* seems this one can be freed ... */
-		pa->pa_deleted = 1;
+		ext4_mb_mark_pa_deleted(sb, pa);
 
 		/* we can trust pa_free ... */
 		free += pa->pa_free;
@@ -4103,7 +4267,7 @@ out_dbg:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode)
+void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -4121,15 +4285,19 @@ void ext4_discard_preallocations(struct inode *inode)
 
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
-	trace_ext4_discard_preallocations(inode);
+	trace_ext4_discard_preallocations(inode,
+			atomic_read(&ei->i_prealloc_active), needed);
 
 	INIT_LIST_HEAD(&list);
 
+	if (needed == 0)
+		needed = UINT_MAX;
+
 repeat:
 	/* first, collect all pa's in the inode */
 	spin_lock(&ei->i_prealloc_lock);
-	while (!list_empty(&ei->i_prealloc_list)) {
-		pa = list_entry(ei->i_prealloc_list.next,
+	while (!list_empty(&ei->i_prealloc_list) && needed) {
+		pa = list_entry(ei->i_prealloc_list.prev,
 				struct ext4_prealloc_space, pa_inode_list);
 		BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock);
 		spin_lock(&pa->pa_lock);
@@ -4146,10 +4314,11 @@ repeat:
 
 		}
 		if (pa->pa_deleted == 0) {
-			pa->pa_deleted = 1;
+			ext4_mb_mark_pa_deleted(sb, pa);
 			spin_unlock(&pa->pa_lock);
 			list_del_rcu(&pa->pa_inode_list);
 			list_add(&pa->u.pa_tmp_list, &list);
+			needed--;
 			continue;
 		}
 
@@ -4399,7 +4568,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ac->ac_g_ex = ac->ac_o_ex;
 	ac->ac_flags = ar->flags;
 
-	/* we have to define context: we'll we work with a file or
+	/* we have to define context: we'll work with a file or
 	 * locality group. this is a policy, actually */
 	ext4_mb_group_or_file(ac);
 
@@ -4450,7 +4619,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 		BUG_ON(pa->pa_type != MB_GROUP_PA);
 
 		/* seems this one can be freed ... */
-		pa->pa_deleted = 1;
+		ext4_mb_mark_pa_deleted(sb, pa);
 		spin_unlock(&pa->pa_lock);
 
 		list_del_rcu(&pa->pa_inode_list);
@@ -4549,10 +4718,29 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 }
 
 /*
+ * if per-inode prealloc list is too long, trim some PA
+ */
+static void ext4_mb_trim_inode_pa(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int count, delta;
+
+	count = atomic_read(&ei->i_prealloc_active);
+	delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1;
+	if (count > sbi->s_mb_max_inode_prealloc + delta) {
+		count -= sbi->s_mb_max_inode_prealloc;
+		ext4_discard_preallocations(inode, count);
+	}
+}
+
+/*
  * release all resource we used in allocation
  */
 static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
+	struct inode *inode = ac->ac_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
 	if (pa) {
@@ -4564,21 +4752,31 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			pa->pa_free -= ac->ac_b_ex.fe_len;
 			pa->pa_len -= ac->ac_b_ex.fe_len;
 			spin_unlock(&pa->pa_lock);
+
+			/*
+			 * We want to add the pa to the right bucket.
+			 * Remove it from the list and while adding
+			 * make sure the list to which we are adding
+			 * doesn't grow big.
+			 */
+			if (likely(pa->pa_free)) {
+				spin_lock(pa->pa_obj_lock);
+				list_del_rcu(&pa->pa_inode_list);
+				spin_unlock(pa->pa_obj_lock);
+				ext4_mb_add_n_trim(ac);
+			}
 		}
-	}
-	if (pa) {
-		/*
-		 * We want to add the pa to the right bucket.
-		 * Remove it from the list and while adding
-		 * make sure the list to which we are adding
-		 * doesn't grow big.
-		 */
-		if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) {
+
+		if (pa->pa_type == MB_INODE_PA) {
+			/*
+			 * treat per-inode prealloc list as a lru list, then try
+			 * to trim the least recently used PA.
+			 */
 			spin_lock(pa->pa_obj_lock);
-			list_del_rcu(&pa->pa_inode_list);
+			list_move(&pa->pa_inode_list, &ei->i_prealloc_list);
 			spin_unlock(pa->pa_obj_lock);
-			ext4_mb_add_n_trim(ac);
 		}
+
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->ac_bitmap_page)
@@ -4588,6 +4786,7 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
+	ext4_mb_trim_inode_pa(inode);
 	return 0;
 }
 
@@ -4915,7 +5114,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
-	    !ext4_data_block_valid(sbi, block, count)) {
+	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
 			   "block = %llu, count = %lu", block, count);
 		goto error_return;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 6b4d17c2935d..e75b4749aa1c 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -73,6 +73,10 @@
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
+/*
+ * maximum length of inode prealloc list
+ */
+#define MB_DEFAULT_MAX_INODE_PREALLOC	512
 
 struct ext4_free_data {
 	/* this links the free block information from sb_info */
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 1ed86fb6c302..0d601b822875 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 
 out:
 	if (*moved_len) {
-		ext4_discard_preallocations(orig_inode);
-		ext4_discard_preallocations(donor_inode);
+		ext4_discard_preallocations(orig_inode, 0);
+		ext4_discard_preallocations(donor_inode, 0);
 	}
 
 	ext4_ext_drop_refs(path);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 56738b538ddf..153a9fbe1dd0 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1396,8 +1396,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    ext4_match(dir, fname, de)) {
 			/* found a match - just to be sure, do
 			 * a full check */
-			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
-						 bh->b_size, offset))
+			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
+						 buf_size, offset))
 				return -1;
 			*res_dir = de;
 			return 1;
@@ -1858,7 +1858,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 			     blocksize, hinfo, map);
 	map -= count;
 	dx_sort_map(map, count);
-	/* Split the existing block in the middle, size-wise */
+	/* Ensure that neither split block is over half full */
 	size = 0;
 	move = 0;
 	for (i = count-1; i >= 0; i--) {
@@ -1868,8 +1868,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		size += map[i].size;
 		move++;
 	}
-	/* map index at which we will split */
-	split = count - move;
+	/*
+	 * map index at which we will split
+	 *
+	 * If the sum of active entries didn't exceed half the block size, just
+	 * split it in half by count; each resulting block will have at least
+	 * half the space free.
+	 */
+	if (i > 0)
+		split = count - move;
+	else
+		split = count/2;
+
 	hash2 = map[split].hash;
 	continued = hash2 == map[split - 1].hash;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
@@ -2455,8 +2465,7 @@ cleanup:
  * ext4_generic_delete_entry deletes a directory entry by merging it
  * with the previous entry
  */
-int ext4_generic_delete_entry(handle_t *handle,
-			      struct inode *dir,
+int ext4_generic_delete_entry(struct inode *dir,
 			      struct ext4_dir_entry_2 *de_del,
 			      struct buffer_head *bh,
 			      void *entry_buf,
@@ -2472,7 +2481,7 @@ int ext4_generic_delete_entry(handle_t *handle,
 	de = (struct ext4_dir_entry_2 *)entry_buf;
 	while (i < buf_size - csum_size) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
-					 bh->b_data, bh->b_size, i))
+					 entry_buf, buf_size, i))
 			return -EFSCORRUPTED;
 		if (de == de_del)  {
 			if (pde)
@@ -2517,8 +2526,7 @@ static int ext4_delete_entry(handle_t *handle,
 	if (unlikely(err))
 		goto out;
 
-	err = ext4_generic_delete_entry(handle, dir, de_del,
-					bh, bh->b_data,
+	err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data,
 					dir->i_sb->s_blocksize, csum_size);
 	if (err)
 		goto out;
@@ -3193,30 +3201,33 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	 * in separate transaction */
 	retval = dquot_initialize(dir);
 	if (retval)
-		return retval;
+		goto out_trace;
 	retval = dquot_initialize(d_inode(dentry));
 	if (retval)
-		return retval;
+		goto out_trace;
 
-	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
-	if (IS_ERR(bh))
-		return PTR_ERR(bh);
-	if (!bh)
-		goto end_unlink;
+	if (IS_ERR(bh)) {
+		retval = PTR_ERR(bh);
+		goto out_trace;
+	}
+	if (!bh) {
+		retval = -ENOENT;
+		goto out_trace;
+	}
 
 	inode = d_inode(dentry);
 
-	retval = -EFSCORRUPTED;
-	if (le32_to_cpu(de->inode) != inode->i_ino)
-		goto end_unlink;
+	if (le32_to_cpu(de->inode) != inode->i_ino) {
+		retval = -EFSCORRUPTED;
+		goto out_bh;
+	}
 
 	handle = ext4_journal_start(dir, EXT4_HT_DIR,
 				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		handle = NULL;
-		goto end_unlink;
+		goto out_bh;
 	}
 
 	if (IS_DIRSYNC(dir))
@@ -3224,12 +3235,12 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 
 	retval = ext4_delete_entry(handle, dir, de, bh);
 	if (retval)
-		goto end_unlink;
+		goto out_handle;
 	dir->i_ctime = dir->i_mtime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	retval = ext4_mark_inode_dirty(handle, dir);
 	if (retval)
-		goto end_unlink;
+		goto out_handle;
 	if (inode->i_nlink == 0)
 		ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
 				   dentry->d_name.len, dentry->d_name.name);
@@ -3251,10 +3262,11 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 		d_invalidate(dentry);
 #endif
 
-end_unlink:
+out_handle:
+	ext4_journal_stop(handle);
+out_bh:
 	brelse(bh);
-	if (handle)
-		ext4_journal_stop(handle);
+out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
 	return retval;
 }
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index f2df2db0786c..f014c5e473a9 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -140,7 +140,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
 			return;
 		}
 		ctx->cur_step++;
-		/* fall-through */
+		fallthrough;
 	case STEP_VERITY:
 		if (ctx->enabled_steps & (1 << STEP_VERITY)) {
 			INIT_WORK(&ctx->work, verity_work);
@@ -148,7 +148,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
 			return;
 		}
 		ctx->cur_step++;
-		/* fall-through */
+		fallthrough;
 	default:
 		__read_end_io(ctx->bio);
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0907f907c47d..ea425b49b345 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
 static int ext4_show_options(struct seq_file *seq, struct dentry *root);
 static int ext4_commit_super(struct super_block *sb, int sync);
-static void ext4_mark_recovery_complete(struct super_block *sb,
+static int ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
-static void ext4_clear_journal_err(struct super_block *sb,
-				   struct ext4_super_block *es);
+static int ext4_clear_journal_err(struct super_block *sb,
+				  struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
@@ -744,6 +744,7 @@ void __ext4_msg(struct super_block *sb,
 	struct va_format vaf;
 	va_list args;
 
+	atomic_inc(&EXT4_SB(sb)->s_msg_count);
 	if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
 		return;
 
@@ -754,9 +755,12 @@ void __ext4_msg(struct super_block *sb,
 	va_end(args);
 }
 
-#define ext4_warning_ratelimit(sb)					\
-		___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),	\
-			     "EXT4-fs warning")
+static int ext4_warning_ratelimit(struct super_block *sb)
+{
+	atomic_inc(&EXT4_SB(sb)->s_warning_count);
+	return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+			    "EXT4-fs warning");
+}
 
 void __ext4_warning(struct super_block *sb, const char *function,
 		    unsigned int line, const char *fmt, ...)
@@ -1123,6 +1127,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	inode_set_iversion(&ei->vfs_inode, 1);
 	spin_lock_init(&ei->i_raw_lock);
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
+	atomic_set(&ei->i_prealloc_active, 0);
 	spin_lock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
@@ -1216,7 +1221,7 @@ void ext4_clear_inode(struct inode *inode)
 {
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
@@ -1288,8 +1293,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 	if (!page_has_buffers(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page,
-						wait & ~__GFP_DIRECT_RECLAIM);
+		return jbd2_journal_try_to_free_buffers(journal, page);
+
 	return try_to_free_buffers(page);
 }
 
@@ -1522,6 +1527,7 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
+	Opt_prefetch_block_bitmaps,
 };
 
 static const match_table_t tokens = {
@@ -1614,6 +1620,7 @@ static const match_table_t tokens = {
 	{Opt_inlinecrypt, "inlinecrypt"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
+	{Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1831,6 +1838,8 @@ static const struct mount_opts {
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_STRING},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
+	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+	 MOPT_SET},
 	{Opt_err, 0, 0}
 };
 
@@ -3213,15 +3222,34 @@ static void print_daily_error_info(struct timer_list *t)
 static int ext4_run_li_request(struct ext4_li_request *elr)
 {
 	struct ext4_group_desc *gdp = NULL;
-	ext4_group_t group, ngroups;
-	struct super_block *sb;
+	struct super_block *sb = elr->lr_super;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t group = elr->lr_next_group;
 	unsigned long timeout = 0;
+	unsigned int prefetch_ios = 0;
 	int ret = 0;
 
-	sb = elr->lr_super;
-	ngroups = EXT4_SB(sb)->s_groups_count;
+	if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) {
+		elr->lr_next_group = ext4_mb_prefetch(sb, group,
+				EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios);
+		if (prefetch_ios)
+			ext4_mb_prefetch_fini(sb, elr->lr_next_group,
+					      prefetch_ios);
+		trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group,
+					    prefetch_ios);
+		if (group >= elr->lr_next_group) {
+			ret = 1;
+			if (elr->lr_first_not_zeroed != ngroups &&
+			    !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) {
+				elr->lr_next_group = elr->lr_first_not_zeroed;
+				elr->lr_mode = EXT4_LI_MODE_ITABLE;
+				ret = 0;
+			}
+		}
+		return ret;
+	}
 
-	for (group = elr->lr_next_group; group < ngroups; group++) {
+	for (; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp) {
 			ret = 1;
@@ -3239,9 +3267,10 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		timeout = jiffies;
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
+		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
 			timeout = (jiffies - timeout) *
-				  elr->lr_sbi->s_li_wait_mult;
+				EXT4_SB(elr->lr_super)->s_li_wait_mult;
 			elr->lr_timeout = timeout;
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3256,15 +3285,11 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
  */
 static void ext4_remove_li_request(struct ext4_li_request *elr)
 {
-	struct ext4_sb_info *sbi;
-
 	if (!elr)
 		return;
 
-	sbi = elr->lr_sbi;
-
 	list_del(&elr->lr_request);
-	sbi->s_li_request = NULL;
+	EXT4_SB(elr->lr_super)->s_li_request = NULL;
 	kfree(elr);
 }
 
@@ -3473,7 +3498,6 @@ static int ext4_li_info_new(void)
 static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 					    ext4_group_t start)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_li_request *elr;
 
 	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
@@ -3481,8 +3505,13 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 		return NULL;
 
 	elr->lr_super = sb;
-	elr->lr_sbi = sbi;
-	elr->lr_next_group = start;
+	elr->lr_first_not_zeroed = start;
+	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
+		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
+	else {
+		elr->lr_mode = EXT4_LI_MODE_ITABLE;
+		elr->lr_next_group = start;
+	}
 
 	/*
 	 * Randomize first schedule time of the request to
@@ -3512,8 +3541,9 @@ int ext4_register_li_request(struct super_block *sb,
 		goto out;
 	}
 
-	if (first_not_zeroed == ngroups || sb_rdonly(sb) ||
-	    !test_opt(sb, INIT_INODE_TABLE))
+	if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) &&
+	    (first_not_zeroed == ngroups || sb_rdonly(sb) ||
+	     !test_opt(sb, INIT_INODE_TABLE)))
 		goto out;
 
 	elr = ext4_li_request_new(sb, first_not_zeroed);
@@ -4710,11 +4740,13 @@ no_journal:
 
 	ext4_set_resv_clusters(sb);
 
-	err = ext4_setup_system_zone(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize system "
-			 "zone (%d)", err);
-		goto failed_mount4a;
+	if (test_opt(sb, BLOCK_VALIDITY)) {
+		err = ext4_setup_system_zone(sb);
+		if (err) {
+			ext4_msg(sb, KERN_ERR, "failed to initialize system "
+				 "zone (%d)", err);
+			goto failed_mount4a;
+		}
 	}
 
 	ext4_ext_init(sb);
@@ -4777,12 +4809,23 @@ no_journal:
 	}
 #endif  /* CONFIG_QUOTA */
 
+	/*
+	 * Save the original bdev mapping's wb_err value which could be
+	 * used to detect the metadata async write error.
+	 */
+	spin_lock_init(&sbi->s_bdev_wb_lock);
+	if (!sb_rdonly(sb))
+		errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+					 &sbi->s_bdev_wb_err);
+	sb->s_bdev->bd_super = sb;
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
 	if (needs_recovery) {
 		ext4_msg(sb, KERN_INFO, "recovery complete");
-		ext4_mark_recovery_complete(sb, es);
+		err = ext4_mark_recovery_complete(sb, es);
+		if (err)
+			goto failed_mount8;
 	}
 	if (EXT4_SB(sb)->s_journal) {
 		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -4816,6 +4859,8 @@ no_journal:
 	ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+	atomic_set(&sbi->s_warning_count, 0);
+	atomic_set(&sbi->s_msg_count, 0);
 
 	kfree(orig_data);
 	return 0;
@@ -4825,10 +4870,8 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
-#ifdef CONFIG_QUOTA
 failed_mount8:
 	ext4_unregister_sysfs(sb);
-#endif
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
@@ -4968,7 +5011,8 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 	struct inode *journal_inode;
 	journal_t *journal;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	journal_inode = ext4_get_journal_inode(sb, journal_inum);
 	if (!journal_inode)
@@ -4998,7 +5042,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	struct ext4_super_block *es;
 	struct block_device *bdev;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	bdev = ext4_blkdev_get(j_dev, sb);
 	if (bdev == NULL)
@@ -5089,8 +5134,10 @@ static int ext4_load_journal(struct super_block *sb,
 	dev_t journal_dev;
 	int err = 0;
 	int really_read_only;
+	int journal_dev_ro;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return -EFSCORRUPTED;
 
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -5100,7 +5147,31 @@ static int ext4_load_journal(struct super_block *sb,
 	} else
 		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
 
-	really_read_only = bdev_read_only(sb->s_bdev);
+	if (journal_inum && journal_dev) {
+		ext4_msg(sb, KERN_ERR,
+			 "filesystem has both journal inode and journal device!");
+		return -EINVAL;
+	}
+
+	if (journal_inum) {
+		journal = ext4_get_journal(sb, journal_inum);
+		if (!journal)
+			return -EINVAL;
+	} else {
+		journal = ext4_get_dev_journal(sb, journal_dev);
+		if (!journal)
+			return -EINVAL;
+	}
+
+	journal_dev_ro = bdev_read_only(journal->j_dev);
+	really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro;
+
+	if (journal_dev_ro && !sb_rdonly(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "journal device read-only, try mounting with '-o ro'");
+		err = -EROFS;
+		goto err_out;
+	}
 
 	/*
 	 * Are we loading a blank journal or performing recovery after a
@@ -5115,27 +5186,14 @@ static int ext4_load_journal(struct super_block *sb,
 				ext4_msg(sb, KERN_ERR, "write access "
 					"unavailable, cannot proceed "
 					"(try mounting with noload)");
-				return -EROFS;
+				err = -EROFS;
+				goto err_out;
 			}
 			ext4_msg(sb, KERN_INFO, "write access will "
 			       "be enabled during recovery");
 		}
 	}
 
-	if (journal_inum && journal_dev) {
-		ext4_msg(sb, KERN_ERR, "filesystem has both journal "
-		       "and inode journals!");
-		return -EINVAL;
-	}
-
-	if (journal_inum) {
-		if (!(journal = ext4_get_journal(sb, journal_inum)))
-			return -EINVAL;
-	} else {
-		if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
-			return -EINVAL;
-	}
-
 	if (!(journal->j_flags & JBD2_BARRIER))
 		ext4_msg(sb, KERN_INFO, "barriers disabled");
 
@@ -5155,12 +5213,16 @@ static int ext4_load_journal(struct super_block *sb,
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "error loading journal");
-		jbd2_journal_destroy(journal);
-		return err;
+		goto err_out;
 	}
 
 	EXT4_SB(sb)->s_journal = journal;
-	ext4_clear_journal_err(sb, es);
+	err = ext4_clear_journal_err(sb, es);
+	if (err) {
+		EXT4_SB(sb)->s_journal = NULL;
+		jbd2_journal_destroy(journal);
+		return err;
+	}
 
 	if (!really_read_only && journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -5171,6 +5233,10 @@ static int ext4_load_journal(struct super_block *sb,
 	}
 
 	return 0;
+
+err_out:
+	jbd2_journal_destroy(journal);
+	return err;
 }
 
 static int ext4_commit_super(struct super_block *sb, int sync)
@@ -5183,13 +5249,6 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		return error;
 
 	/*
-	 * The superblock bh should be mapped, but it might not be if the
-	 * device was hot-removed. Not much we can do but fail the I/O.
-	 */
-	if (!buffer_mapped(sbh))
-		return error;
-
-	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
 	 * write time when we are mounting the root file system
@@ -5256,26 +5315,32 @@ static int ext4_commit_super(struct super_block *sb, int sync)
  * remounting) the filesystem readonly, then we will end up with a
  * consistent fs on disk.  Record that fact.
  */
-static void ext4_mark_recovery_complete(struct super_block *sb,
-					struct ext4_super_block *es)
+static int ext4_mark_recovery_complete(struct super_block *sb,
+				       struct ext4_super_block *es)
 {
+	int err;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
 	if (!ext4_has_feature_journal(sb)) {
-		BUG_ON(journal != NULL);
-		return;
+		if (journal != NULL) {
+			ext4_error(sb, "Journal got removed while the fs was "
+				   "mounted!");
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	if (jbd2_journal_flush(journal) < 0)
+	err = jbd2_journal_flush(journal);
+	if (err < 0)
 		goto out;
 
 	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		ext4_commit_super(sb, 1);
 	}
-
 out:
 	jbd2_journal_unlock_updates(journal);
+	return err;
 }
 
 /*
@@ -5283,14 +5348,17 @@ out:
  * has recorded an error from a previous lifetime, move that error to the
  * main filesystem now.
  */
-static void ext4_clear_journal_err(struct super_block *sb,
+static int ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es)
 {
 	journal_t *journal;
 	int j_errno;
 	const char *errstr;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (!ext4_has_feature_journal(sb)) {
+		ext4_error(sb, "Journal got removed while the fs was mounted!");
+		return -EFSCORRUPTED;
+	}
 
 	journal = EXT4_SB(sb)->s_journal;
 
@@ -5315,6 +5383,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);
 	}
+	return 0;
 }
 
 /*
@@ -5457,7 +5526,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	unsigned long old_sb_flags;
+	unsigned long old_sb_flags, vfs_flags;
 	struct ext4_mount_options old_opts;
 	int enable_quota = 0;
 	ext4_group_t g;
@@ -5500,6 +5569,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
 		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
 
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from *flags to s_flags
+	 */
+	vfs_flags = SB_LAZYTIME | SB_I_VERSION;
+	sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags);
+
 	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
 		err = -EINVAL;
 		goto restore_opts;
@@ -5553,9 +5630,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 	}
 
-	if (*flags & SB_LAZYTIME)
-		sb->s_flags |= SB_LAZYTIME;
-
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
 		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
 			err = -EROFS;
@@ -5585,8 +5659,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			    (sbi->s_mount_state & EXT4_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			if (sbi->s_journal)
+			if (sbi->s_journal) {
+				/*
+				 * We let remount-ro finish even if marking fs
+				 * as clean failed...
+				 */
 				ext4_mark_recovery_complete(sb, es);
+			}
 			if (sbi->s_mmp_tsk)
 				kthread_stop(sbi->s_mmp_tsk);
 		} else {
@@ -5629,13 +5708,24 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			}
 
 			/*
+			 * Update the original bdev mapping's wb_err value
+			 * which could be used to detect the metadata async
+			 * write error.
+			 */
+			errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+						 &sbi->s_bdev_wb_err);
+
+			/*
 			 * Mounting a RDONLY partition read-write, so reread
 			 * and store the current valid flag.  (It may have
 			 * been changed by e2fsck since we originally mounted
 			 * the partition.)
 			 */
-			if (sbi->s_journal)
-				ext4_clear_journal_err(sb, es);
+			if (sbi->s_journal) {
+				err = ext4_clear_journal_err(sb, es);
+				if (err)
+					goto restore_opts;
+			}
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
 
 			err = ext4_setup_super(sb, es, 0);
@@ -5665,7 +5755,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		ext4_register_li_request(sb, first_not_zeroed);
 	}
 
-	ext4_setup_system_zone(sb);
+	/*
+	 * Handle creation of system zone data early because it can fail.
+	 * Releasing of existing data is done when we are sure remount will
+	 * succeed.
+	 */
+	if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) {
+		err = ext4_setup_system_zone(sb);
+		if (err)
+			goto restore_opts;
+	}
+
 	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
 		err = ext4_commit_super(sb, 1);
 		if (err)
@@ -5686,8 +5786,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 #endif
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+		ext4_release_system_zone(sb);
+
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from s_flags to *flags
+	 */
+	*flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags);
 
-	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;
@@ -5701,6 +5809,8 @@ restore_opts:
 	sbi->s_commit_interval = old_opts.s_commit_interval;
 	sbi->s_min_batch_time = old_opts.s_min_batch_time;
 	sbi->s_max_batch_time = old_opts.s_max_batch_time;
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+		ext4_release_system_zone(sb);
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
 	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 6c9fc9e21c13..bfabb799fa45 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -189,6 +189,9 @@ static struct ext4_attr ext4_attr_##_name = {			\
 #define EXT4_RW_ATTR_SBI_UL(_name,_elname)	\
 	EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
 
+#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname)
+
 #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
 static struct ext4_attr ext4_attr_##_name = {			\
 	.attr = {.name = __stringify(_name), .mode = _mode },	\
@@ -215,6 +218,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
 EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
@@ -226,6 +230,8 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
 #ifdef CONFIG_EXT4_DEBUG
 EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
 #endif
+EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count);
+EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
 EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
 EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
@@ -240,6 +246,8 @@ EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32);
 EXT4_ATTR(first_error_time, 0444, first_error_time);
 EXT4_ATTR(last_error_time, 0444, last_error_time);
 EXT4_ATTR(journal_task, 0444, journal_task);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -257,6 +265,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(mb_order2_req),
 	ATTR_LIST(mb_stream_req),
 	ATTR_LIST(mb_group_prealloc),
+	ATTR_LIST(mb_max_inode_prealloc),
 	ATTR_LIST(max_writeback_mb_bump),
 	ATTR_LIST(extent_max_zeroout_kb),
 	ATTR_LIST(trigger_fs_error),
@@ -267,6 +276,8 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(msg_ratelimit_interval_ms),
 	ATTR_LIST(msg_ratelimit_burst),
 	ATTR_LIST(errors_count),
+	ATTR_LIST(warning_count),
+	ATTR_LIST(msg_count),
 	ATTR_LIST(first_error_ino),
 	ATTR_LIST(last_error_ino),
 	ATTR_LIST(first_error_block),
@@ -283,6 +294,8 @@ static struct attribute *ext4_attrs[] = {
 #ifdef CONFIG_EXT4_DEBUG
 	ATTR_LIST(simulate_fail),
 #endif
+	ATTR_LIST(mb_prefetch),
+	ATTR_LIST(mb_prefetch_limit),
 	NULL,
 };
 ATTRIBUTE_GROUPS(ext4);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 7d2f6576d954..cba4b877c606 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1356,8 +1356,7 @@ retry:
 
 	block = 0;
 	while (wsize < bufsize) {
-		if (bh != NULL)
-			brelse(bh);
+		brelse(bh);
 		csize = (bufsize - wsize) > blocksize ? blocksize :
 								bufsize - wsize;
 		bh = ext4_getblk(handle, ea_inode, block, 0);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ed2bca0fce92..73683e58a08d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3550,6 +3550,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 	unsigned long align = offset | iov_iter_alignment(iter);
 	struct block_device *bdev = inode->i_sb->s_bdev;
 
+	if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
+		return 1;
+
 	if (align & blocksize_mask) {
 		if (bdev)
 			blkbits = blksize_bits(bdev_logical_block_size(bdev));
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 16322ea5b463..d9e52a7f3702 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2646,7 +2646,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
 	case FI_NEW_INODE:
 		if (set)
 			return;
-		/* fall through */
+		fallthrough;
 	case FI_DATA_EXIST:
 	case FI_INLINE_DOTS:
 	case FI_PIN_FILE:
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9bbaa2614679..cb1b5b61a1da 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -618,10 +618,10 @@ pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
 	switch (dn->max_level) {
 	case 3:
 		base += 2 * indirect_blks;
-		/* fall through */
+		fallthrough;
 	case 2:
 		base += 2 * direct_blks;
-		/* fall through */
+		fallthrough;
 	case 1:
 		base += direct_index;
 		break;
@@ -2373,6 +2373,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 	if (unlikely(nid >= nm_i->max_nid))
 		nid = 0;
 
+	if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+		nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
 	/* Enough entries */
 	if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
 		return 0;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a65d357f89a9..e247a5ef3713 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -799,7 +799,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 
 		if (__is_large_section(sbi)) {
 			unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
-			unsigned short valid_blocks =
+			block_t valid_blocks =
 				get_valid_blocks(sbi, segno, true);
 
 			f2fs_bug_on(sbi, unlikely(!valid_blocks ||
@@ -815,7 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		enum dirty_type dirty_type)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	unsigned short valid_blocks;
+	block_t valid_blocks;
 
 	if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
 		dirty_i->nr_dirty[dirty_type]--;
@@ -4316,8 +4316,8 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int segno = 0, offset = 0, secno;
-	unsigned short valid_blocks;
-	unsigned short blks_per_sec = BLKS_PER_SEC(sbi);
+	block_t valid_blocks;
+	block_t blks_per_sec = BLKS_PER_SEC(sbi);
 
 	while (1) {
 		/* find dirty segment based on free segmap */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 2e4c0fa2074b..19ac5baad50f 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -362,7 +362,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_OFD_SETLK:
 	case F_OFD_SETLKW:
 #endif
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLK:
 	case F_SETLKW:
 		if (copy_from_user(&flock, argp, sizeof(flock)))
@@ -771,7 +771,7 @@ static void send_sigio_to_task(struct task_struct *p,
 			if (!do_send_sig_info(signum, &si, p, type))
 				break;
 		}
-		/* fall-through - fall back on the old plain SIGIO signal */
+			fallthrough;	/* fall back on the old plain SIGIO signal */
 		case 0:
 			do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type);
 	}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a605c3dddabc..149227160ff0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -42,7 +42,6 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
@@ -144,7 +143,9 @@ static void inode_io_list_del_locked(struct inode *inode,
 				     struct bdi_writeback *wb)
 {
 	assert_spin_locked(&wb->list_lock);
+	assert_spin_locked(&inode->i_lock);
 
+	inode->i_state &= ~I_SYNC_QUEUED;
 	list_del_init(&inode->i_io_list);
 	wb_io_lists_depopulated(wb);
 }
@@ -1122,7 +1123,9 @@ void inode_io_list_del(struct inode *inode)
 	struct bdi_writeback *wb;
 
 	wb = inode_to_wb_and_lock_list(inode);
+	spin_lock(&inode->i_lock);
 	inode_io_list_del_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
 }
 EXPORT_SYMBOL(inode_io_list_del);
@@ -1172,8 +1175,10 @@ void sb_clear_inode_writeback(struct inode *inode)
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
-static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb)
 {
+	assert_spin_locked(&inode->i_lock);
+
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -1182,6 +1187,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 			inode->dirtied_when = jiffies;
 	}
 	inode_io_list_move_locked(inode, wb, &wb->b_dirty);
+	inode->i_state &= ~I_SYNC_QUEUED;
+}
+
+static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+{
+	spin_lock(&inode->i_lock);
+	redirty_tail_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 }
 
 /*
@@ -1220,16 +1233,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 #define EXPIRE_DIRTY_ATIME 0x0001
 
 /*
- * Move expired (dirtied before work->older_than_this) dirty inodes from
+ * Move expired (dirtied before dirtied_before) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       int flags,
-			       struct wb_writeback_work *work)
+			       unsigned long dirtied_before)
 {
-	unsigned long *older_than_this = NULL;
-	unsigned long expire_time;
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
@@ -1237,21 +1247,15 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
-		older_than_this = work->older_than_this;
-	else if (!work->for_sync) {
-		expire_time = jiffies - (dirtytime_expire_interval * HZ);
-		older_than_this = &expire_time;
-	}
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (older_than_this &&
-		    inode_dirtied_after(inode, *older_than_this))
+		if (inode_dirtied_after(inode, dirtied_before))
 			break;
 		list_move(&inode->i_io_list, &tmp);
 		moved++;
-		if (flags & EXPIRE_DIRTY_ATIME)
-			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_SYNC_QUEUED;
+		spin_unlock(&inode->i_lock);
 		if (sb_is_blkdev_sb(inode->i_sb))
 			continue;
 		if (sb && sb != inode->i_sb)
@@ -1289,18 +1293,22 @@ out:
  *                                           |
  *                                           +--> dequeue for IO
  */
-static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
+		     unsigned long dirtied_before)
 {
 	int moved;
+	unsigned long time_expire_jif = dirtied_before;
 
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before);
+	if (!work->for_sync)
+		time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
 	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
-				     EXPIRE_DIRTY_ATIME, work);
+				     time_expire_jif);
 	if (moved)
 		wb_io_lists_populated(wb);
-	trace_writeback_queue_io(wb, work, moved);
+	trace_writeback_queue_io(wb, work, dirtied_before, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -1394,7 +1402,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * writeback is not making progress due to locked
 		 * buffers. Skip this inode for now.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 		return;
 	}
 
@@ -1414,7 +1422,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 			 * retrying writeback of the dirty page/inode
 			 * that cannot be performed immediately.
 			 */
-			redirty_tail(inode, wb);
+			redirty_tail_locked(inode, wb);
 		}
 	} else if (inode->i_state & I_DIRTY) {
 		/*
@@ -1422,10 +1430,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * such as delayed allocation during submission or metadata
 		 * updates after data IO completion.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
 		inode->dirtied_when = jiffies;
 		inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
+		inode->i_state &= ~I_SYNC_QUEUED;
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
 		inode_io_list_del_locked(inode, wb);
@@ -1472,18 +1481,14 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	if (inode->i_state & I_DIRTY_TIME) {
-		if ((dirty & I_DIRTY_INODE) ||
-		    wbc->sync_mode == WB_SYNC_ALL ||
-		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
-		    unlikely(time_after(jiffies,
-					(inode->dirtied_time_when +
-					 dirtytime_expire_interval * HZ)))) {
-			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
-			trace_writeback_lazytime(inode);
-		}
-	} else
-		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
+	if ((inode->i_state & I_DIRTY_TIME) &&
+	    ((dirty & I_DIRTY_INODE) ||
+	     wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+	     time_after(jiffies, inode->dirtied_time_when +
+			dirtytime_expire_interval * HZ))) {
+		dirty |= I_DIRTY_TIME;
+		trace_writeback_lazytime(inode);
+	}
 	inode->i_state &= ~dirty;
 
 	/*
@@ -1669,8 +1674,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 */
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			redirty_tail_locked(inode, wb);
 			spin_unlock(&inode->i_lock);
-			redirty_tail(inode, wb);
 			continue;
 		}
 		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
@@ -1811,7 +1816,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, &work);
+		queue_io(wb, &work, jiffies);
 	__writeback_inodes_wb(wb, &work);
 	spin_unlock(&wb->list_lock);
 	blk_finish_plug(&plug);
@@ -1831,7 +1836,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
  * takes longer than a dirty_writeback_interval interval, then leave a
  * one-second gap.
  *
- * older_than_this takes precedence over nr_to_write.  So we'll only write back
+ * dirtied_before takes precedence over nr_to_write.  So we'll only write back
  * all dirty pages if they are all attached to "old" mappings.
  */
 static long wb_writeback(struct bdi_writeback *wb,
@@ -1839,14 +1844,11 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
-	unsigned long oldest_jif;
+	unsigned long dirtied_before = jiffies;
 	struct inode *inode;
 	long progress;
 	struct blk_plug plug;
 
-	oldest_jif = jiffies;
-	work->older_than_this = &oldest_jif;
-
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -1880,14 +1882,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			oldest_jif = jiffies -
+			dirtied_before = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			oldest_jif = jiffies;
+			dirtied_before = jiffies;
 
 		trace_writeback_start(wb, work);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, work);
+			queue_io(wb, work, dirtied_before);
 		if (work->sb)
 			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
@@ -2289,11 +2291,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		inode->i_state |= flags;
 
 		/*
-		 * If the inode is being synced, just update its dirty state.
-		 * The unlocker will place the inode on the appropriate
-		 * superblock list, based upon its state.
+		 * If the inode is queued for writeback by flush worker, just
+		 * update its dirty state. Once the flush worker is done with
+		 * the inode it will place it on the appropriate superblock
+		 * list, based upon its state.
 		 */
-		if (inode->i_state & I_SYNC)
+		if (inode->i_state & I_SYNC_QUEUED)
 			goto out_unlock_inode;
 
 		/*
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 7d5c5dd2b1d5..2834d1afa6e8 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -521,7 +521,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	switch (param->type) {
 	case fs_value_is_string:
 		len = 1 + param->size;
-		/* Fall through */
+		fallthrough;
 	case fs_value_is_flag:
 		len += strlen(param->key);
 		break;
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 2fa3f241b762..27a890aa493a 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -412,7 +412,7 @@ SYSCALL_DEFINE5(fsconfig,
 		break;
 	case FSCONFIG_SET_PATH_EMPTY:
 		lookup_flags = LOOKUP_EMPTY;
-		/* fallthru */
+		fallthrough;
 	case FSCONFIG_SET_PATH:
 		param.type = fs_value_is_filename;
 		param.name = getname_flags(_value, lookup_flags, NULL);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 770f3a720db9..0f69fbd4af66 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -746,7 +746,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 			}
 			if (n == 0)
 				break;
-		/* fall through - To branching from existing tree */
+			fallthrough;	/* To branching from existing tree */
 		case ALLOC_GROW_DEPTH:
 			if (i > 1 && i < mp->mp_fheight)
 				gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
@@ -757,7 +757,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 				state = ALLOC_DATA;
 			if (n == 0)
 				break;
-		/* fall through - To tree complete, adding data blocks */
+			fallthrough;	/* To tree complete, adding data blocks */
 		case ALLOC_DATA:
 			BUG_ON(n > dblks);
 			BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a58333e3980d..3763c9ff1406 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -902,6 +902,36 @@ static void empty_ail1_list(struct gfs2_sbd *sdp)
 }
 
 /**
+ * drain_bd - drain the buf and databuf queue for a failed transaction
+ * @tr: the transaction to drain
+ *
+ * When this is called, we're taking an error exit for a log write that failed
+ * but since we bypassed the after_commit functions, we need to remove the
+ * items from the buf and databuf queue.
+ */
+static void trans_drain(struct gfs2_trans *tr)
+{
+	struct gfs2_bufdata *bd;
+	struct list_head *head;
+
+	if (!tr)
+		return;
+
+	head = &tr->tr_buf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+	head = &tr->tr_databuf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+}
+
+/**
  * gfs2_log_flush - flush incore transaction(s)
  * @sdp: the filesystem
  * @gl: The glock structure to flush.  If NULL, flush the whole incore log
@@ -1005,6 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 out:
 	if (gfs2_withdrawn(sdp)) {
+		trans_drain(tr);
 		/**
 		 * If the tr_list is empty, we're withdrawing during a log
 		 * flush that targets a transaction, but the transaction was
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 4b67d47a7e00..6e173ae378c4 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1599,7 +1599,7 @@ static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state)
 	case GFS2_QUOTA_ON:
 		state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED;
 		state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED;
-		/*FALLTHRU*/
+		fallthrough;
 	case GFS2_QUOTA_ACCOUNT:
 		state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED |
 						  QCI_SYSFILE;
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index e1c7eb6eb00a..6d4bf7ea7b3b 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -67,6 +67,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 		tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
+	INIT_LIST_HEAD(&tr->tr_list);
 	INIT_LIST_HEAD(&tr->tr_ail1_list);
 	INIT_LIST_HEAD(&tr->tr_ail2_list);
 
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 61eec628805d..0350dc7821bf 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -195,7 +195,7 @@ reread:
 	switch (sbi->s_vhdr->signature) {
 	case cpu_to_be16(HFSPLUS_VOLHEAD_SIGX):
 		set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
-		/*FALLTHRU*/
+		fallthrough;
 	case cpu_to_be16(HFSPLUS_VOLHEAD_SIG):
 		break;
 	case cpu_to_be16(HFSP_WRAP_MAGIC):
diff --git a/fs/io-wq.c b/fs/io-wq.c
index e92c4724480c..414beb543883 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -925,6 +925,24 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 	return match->nr_running && !match->cancel_all;
 }
 
+static inline void io_wqe_remove_pending(struct io_wqe *wqe,
+					 struct io_wq_work *work,
+					 struct io_wq_work_node *prev)
+{
+	unsigned int hash = io_get_work_hash(work);
+	struct io_wq_work *prev_work = NULL;
+
+	if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) {
+		if (prev)
+			prev_work = container_of(prev, struct io_wq_work, list);
+		if (prev_work && io_get_work_hash(prev_work) == hash)
+			wqe->hash_tail[hash] = prev_work;
+		else
+			wqe->hash_tail[hash] = NULL;
+	}
+	wq_list_del(&wqe->work_list, &work->list, prev);
+}
+
 static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
 				       struct io_cb_cancel_data *match)
 {
@@ -938,8 +956,7 @@ retry:
 		work = container_of(node, struct io_wq_work, list);
 		if (!match->fn(work, match->data))
 			continue;
-
-		wq_list_del(&wqe->work_list, node, prev);
+		io_wqe_remove_pending(wqe, work, prev);
 		spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
 		match->nr_pending++;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index dc506b75659c..3790c7fe9fee 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -540,7 +540,6 @@ enum {
 	REQ_F_ISREG_BIT,
 	REQ_F_COMP_LOCKED_BIT,
 	REQ_F_NEED_CLEANUP_BIT,
-	REQ_F_OVERFLOW_BIT,
 	REQ_F_POLLED_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
 	REQ_F_NO_FILE_TABLE_BIT,
@@ -583,8 +582,6 @@ enum {
 	REQ_F_COMP_LOCKED	= BIT(REQ_F_COMP_LOCKED_BIT),
 	/* needs cleanup */
 	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
-	/* in overflow list */
-	REQ_F_OVERFLOW		= BIT(REQ_F_OVERFLOW_BIT),
 	/* already went through poll handler */
 	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
 	/* buffer already selected */
@@ -946,7 +943,8 @@ static void io_get_req_task(struct io_kiocb *req)
 
 static inline void io_clean_op(struct io_kiocb *req)
 {
-	if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED))
+	if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED |
+			  REQ_F_INFLIGHT))
 		__io_clean_op(req);
 }
 
@@ -1152,7 +1150,7 @@ static void io_prep_async_work(struct io_kiocb *req)
 	io_req_init_async(req);
 
 	if (req->flags & REQ_F_ISREG) {
-		if (def->hash_reg_file)
+		if (def->hash_reg_file || (req->ctx->flags & IORING_SETUP_IOPOLL))
 			io_wq_hash_work(&req->work, file_inode(req->file));
 	} else {
 		if (def->unbound_nonreg_file)
@@ -1366,7 +1364,6 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 		req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
 						compl.list);
 		list_move(&req->compl.list, &list);
-		req->flags &= ~REQ_F_OVERFLOW;
 		if (cqe) {
 			WRITE_ONCE(cqe->user_data, req->user_data);
 			WRITE_ONCE(cqe->res, req->result);
@@ -1419,7 +1416,6 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 			ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
 		}
 		io_clean_op(req);
-		req->flags |= REQ_F_OVERFLOW;
 		req->result = res;
 		req->compl.cflags = cflags;
 		refcount_inc(&req->refs);
@@ -1563,17 +1559,6 @@ static bool io_dismantle_req(struct io_kiocb *req)
 	if (req->file)
 		io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
 
-	if (req->flags & REQ_F_INFLIGHT) {
-		struct io_ring_ctx *ctx = req->ctx;
-		unsigned long flags;
-
-		spin_lock_irqsave(&ctx->inflight_lock, flags);
-		list_del(&req->inflight_entry);
-		if (waitqueue_active(&ctx->inflight_wait))
-			wake_up(&ctx->inflight_wait);
-		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
-	}
-
 	return io_req_clean_work(req);
 }
 
@@ -1761,7 +1746,8 @@ static struct io_kiocb *io_req_find_next(struct io_kiocb *req)
 	return __io_req_find_next(req);
 }
 
-static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
+static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb,
+				bool twa_signal_ok)
 {
 	struct task_struct *tsk = req->task;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -1774,7 +1760,7 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
 	 * will do the job.
 	 */
 	notify = 0;
-	if (!(ctx->flags & IORING_SETUP_SQPOLL))
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok)
 		notify = TWA_SIGNAL;
 
 	ret = task_work_add(tsk, cb, notify);
@@ -1834,7 +1820,7 @@ static void io_req_task_queue(struct io_kiocb *req)
 	init_task_work(&req->task_work, io_req_task_submit);
 	percpu_ref_get(&req->ctx->refs);
 
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, true);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -2063,6 +2049,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 
 		req = list_first_entry(done, struct io_kiocb, inflight_entry);
 		if (READ_ONCE(req->result) == -EAGAIN) {
+			req->result = 0;
 			req->iopoll_completed = 0;
 			list_move_tail(&req->inflight_entry, &again);
 			continue;
@@ -2308,38 +2295,27 @@ end_req:
 	io_req_complete(req, ret);
 	return false;
 }
-
-static void io_rw_resubmit(struct callback_head *cb)
-{
-	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
-	struct io_ring_ctx *ctx = req->ctx;
-	int err;
-
-	err = io_sq_thread_acquire_mm(ctx, req);
-
-	if (io_resubmit_prep(req, err)) {
-		refcount_inc(&req->refs);
-		io_queue_async_work(req);
-	}
-
-	percpu_ref_put(&ctx->refs);
-}
 #endif
 
 static bool io_rw_reissue(struct io_kiocb *req, long res)
 {
 #ifdef CONFIG_BLOCK
+	umode_t mode = file_inode(req->file)->i_mode;
 	int ret;
 
+	if (!S_ISBLK(mode) && !S_ISREG(mode))
+		return false;
 	if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker())
 		return false;
 
-	init_task_work(&req->task_work, io_rw_resubmit);
-	percpu_ref_get(&req->ctx->refs);
+	ret = io_sq_thread_acquire_mm(req->ctx, req);
 
-	ret = io_req_task_work_add(req, &req->task_work);
-	if (!ret)
+	if (io_resubmit_prep(req, ret)) {
+		refcount_inc(&req->refs);
+		io_queue_async_work(req);
 		return true;
+	}
+
 #endif
 	return false;
 }
@@ -2578,7 +2554,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 		 * IO with EINTR.
 		 */
 		ret = -EINTR;
-		/* fall through */
+		fallthrough;
 	default:
 		kiocb->ki_complete(kiocb, ret, 0);
 	}
@@ -2819,22 +2795,15 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
 	return __io_iov_buffer_select(req, iov, needs_lock);
 }
 
-static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
-			       struct iovec **iovec, struct iov_iter *iter,
-			       bool needs_lock)
+static ssize_t __io_import_iovec(int rw, struct io_kiocb *req,
+				 struct iovec **iovec, struct iov_iter *iter,
+				 bool needs_lock)
 {
 	void __user *buf = u64_to_user_ptr(req->rw.addr);
 	size_t sqe_len = req->rw.len;
 	ssize_t ret;
 	u8 opcode;
 
-	if (req->io) {
-		struct io_async_rw *iorw = &req->io->rw;
-
-		*iovec = NULL;
-		return iov_iter_count(&iorw->iter);
-	}
-
 	opcode = req->opcode;
 	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
 		*iovec = NULL;
@@ -2848,10 +2817,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
 		if (req->flags & REQ_F_BUFFER_SELECT) {
 			buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
-			if (IS_ERR(buf)) {
-				*iovec = NULL;
+			if (IS_ERR(buf))
 				return PTR_ERR(buf);
-			}
 			req->rw.len = sqe_len;
 		}
 
@@ -2879,6 +2846,21 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
 }
 
+static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
+			       struct iovec **iovec, struct iov_iter *iter,
+			       bool needs_lock)
+{
+	if (!req->io)
+		return __io_import_iovec(rw, req, iovec, iter, needs_lock);
+	*iovec = NULL;
+	return iov_iter_count(&req->io->rw.iter);
+}
+
+static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
+{
+	return kiocb->ki_filp->f_mode & FMODE_STREAM ? NULL : &kiocb->ki_pos;
+}
+
 /*
  * For files that don't have ->read_iter() and ->write_iter(), handle them
  * by looping over ->read() or ->write() manually.
@@ -2914,10 +2896,10 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
 
 		if (rw == READ) {
 			nr = file->f_op->read(file, iovec.iov_base,
-					      iovec.iov_len, &kiocb->ki_pos);
+					      iovec.iov_len, io_kiocb_ppos(kiocb));
 		} else {
 			nr = file->f_op->write(file, iovec.iov_base,
-					       iovec.iov_len, &kiocb->ki_pos);
+					       iovec.iov_len, io_kiocb_ppos(kiocb));
 		}
 
 		if (iov_iter_is_bvec(iter))
@@ -2998,17 +2980,15 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw,
 				   bool force_nonblock)
 {
 	struct io_async_rw *iorw = &req->io->rw;
+	struct iovec *iov;
 	ssize_t ret;
 
-	iorw->iter.iov = iorw->fast_iov;
-	/* reset ->io around the iovec import, we don't want to use it */
-	req->io = NULL;
-	ret = io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov,
-				&iorw->iter, !force_nonblock);
-	req->io = container_of(iorw, struct io_async_ctx, rw);
+	iorw->iter.iov = iov = iorw->fast_iov;
+	ret = __io_import_iovec(rw, req, &iov, &iorw->iter, !force_nonblock);
 	if (unlikely(ret < 0))
 		return ret;
 
+	iorw->iter.iov = iov;
 	io_req_map_rw(req, iorw->iter.iov, iorw->fast_iov, &iorw->iter);
 	return 0;
 }
@@ -3061,7 +3041,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 
 	/* submit ref gets dropped, acquire a new one */
 	refcount_inc(&req->refs);
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, true);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -3074,27 +3054,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 	return 1;
 }
 
-static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb,
-					     struct wait_page_queue *wait,
-					     wait_queue_func_t func,
-					     void *data)
-{
-	/* Can't support async wakeup with polled IO */
-	if (kiocb->ki_flags & IOCB_HIPRI)
-		return -EINVAL;
-	if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) {
-		wait->wait.func = func;
-		wait->wait.private = data;
-		wait->wait.flags = 0;
-		INIT_LIST_HEAD(&wait->wait.entry);
-		kiocb->ki_flags |= IOCB_WAITQ;
-		kiocb->ki_waitq = wait;
-		return 0;
-	}
-
-	return -EOPNOTSUPP;
-}
-
 /*
  * This controls whether a given IO request should be armed for async page
  * based retry. If we return false here, the request is handed to the async
@@ -3109,16 +3068,17 @@ static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb,
  */
 static bool io_rw_should_retry(struct io_kiocb *req)
 {
+	struct wait_page_queue *wait = &req->io->rw.wpq;
 	struct kiocb *kiocb = &req->rw.kiocb;
-	int ret;
 
 	/* never retry for NOWAIT, we just complete with -EAGAIN */
 	if (req->flags & REQ_F_NOWAIT)
 		return false;
 
 	/* Only for buffered IO */
-	if (kiocb->ki_flags & IOCB_DIRECT)
+	if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
 		return false;
+
 	/*
 	 * just use poll if we can, and don't attempt if the fs doesn't
 	 * support callback based unlocks
@@ -3126,14 +3086,15 @@ static bool io_rw_should_retry(struct io_kiocb *req)
 	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
 		return false;
 
-	ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq,
-						io_async_buf_func, req);
-	if (!ret) {
-		io_get_req_task(req);
-		return true;
-	}
+	wait->wait.func = io_async_buf_func;
+	wait->wait.private = req;
+	wait->wait.flags = 0;
+	INIT_LIST_HEAD(&wait->wait.entry);
+	kiocb->ki_flags |= IOCB_WAITQ;
+	kiocb->ki_waitq = wait;
 
-	return false;
+	io_get_req_task(req);
+	return true;
 }
 
 static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
@@ -3161,6 +3122,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
+	iov_count = iov_iter_count(iter);
 	io_size = ret;
 	req->result = io_size;
 	ret = 0;
@@ -3173,8 +3135,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	if (force_nonblock && !io_file_supports_async(req->file, READ))
 		goto copy_iov;
 
-	iov_count = iov_iter_count(iter);
-	ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count);
+	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count);
 	if (unlikely(ret))
 		goto out_free;
 
@@ -3186,14 +3147,21 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 		ret = 0;
 		goto out_free;
 	} else if (ret == -EAGAIN) {
-		if (!force_nonblock)
+		/* IOPOLL retry should happen for io-wq threads */
+		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto done;
+		/* no retry on NONBLOCK marked file */
+		if (req->file->f_flags & O_NONBLOCK)
+			goto done;
+		/* some cases will consume bytes even on error returns */
+		iov_iter_revert(iter, iov_count - iov_iter_count(iter));
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
 		if (ret)
 			goto out_free;
 		return -EAGAIN;
 	} else if (ret < 0) {
-		goto out_free;
+		/* make sure -ERESTARTSYS -> -EINTR is done */
+		goto done;
 	}
 
 	/* read it all, or we did blocking attempt. no retry. */
@@ -3238,6 +3206,7 @@ done:
 	kiocb_done(kiocb, ret, cs);
 	ret = 0;
 out_free:
+	/* it's reportedly faster than delegating the null check to kfree() */
 	if (iovec)
 		kfree(iovec);
 	return ret;
@@ -3276,6 +3245,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
+	iov_count = iov_iter_count(iter);
 	io_size = ret;
 	req->result = io_size;
 
@@ -3292,8 +3262,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	    (req->flags & REQ_F_ISREG))
 		goto copy_iov;
 
-	iov_count = iov_iter_count(iter);
-	ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count);
+	ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), iov_count);
 	if (unlikely(ret))
 		goto out_free;
 
@@ -3325,15 +3294,25 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	 */
 	if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
 		ret2 = -EAGAIN;
+	/* no retry on NONBLOCK marked file */
+	if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK))
+		goto done;
 	if (!force_nonblock || ret2 != -EAGAIN) {
+		/* IOPOLL retry should happen for io-wq threads */
+		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
+			goto copy_iov;
+done:
 		kiocb_done(kiocb, ret2, cs);
 	} else {
 copy_iov:
+		/* some cases will consume bytes even on error returns */
+		iov_iter_revert(iter, iov_count - iov_iter_count(iter));
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
 		if (!ret)
 			return -EAGAIN;
 	}
 out_free:
+	/* it's reportedly faster than delegating the null check to kfree() */
 	if (iovec)
 		kfree(iovec);
 	return ret;
@@ -4600,6 +4579,7 @@ struct io_poll_table {
 static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 			   __poll_t mask, task_work_func_t func)
 {
+	bool twa_signal_ok;
 	int ret;
 
 	/* for instances that support it check for an event match first: */
@@ -4615,12 +4595,20 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	percpu_ref_get(&req->ctx->refs);
 
 	/*
+	 * If we using the signalfd wait_queue_head for this wakeup, then
+	 * it's not safe to use TWA_SIGNAL as we could be recursing on the
+	 * tsk->sighand->siglock on doing the wakeup. Should not be needed
+	 * either, as the normal wakeup will suffice.
+	 */
+	twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh);
+
+	/*
 	 * If this fails, then the task is exiting. When a task exits, the
 	 * work gets canceled, so just cancel this request as well instead
 	 * of executing it. We can't safely execute it anyway, as we may not
 	 * have the needed state needed for it anyway.
 	 */
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, twa_signal_ok);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -4909,12 +4897,20 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 	struct async_poll *apoll;
 	struct io_poll_table ipt;
 	__poll_t mask, ret;
+	int rw;
 
 	if (!req->file || !file_can_poll(req->file))
 		return false;
 	if (req->flags & REQ_F_POLLED)
 		return false;
-	if (!def->pollin && !def->pollout)
+	if (def->pollin)
+		rw = READ;
+	else if (def->pollout)
+		rw = WRITE;
+	else
+		return false;
+	/* if we can't nonblock try, then no point in arming a poll handler */
+	if (!io_file_supports_async(req->file, rw))
 		return false;
 
 	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
@@ -5653,6 +5649,18 @@ static void __io_clean_op(struct io_kiocb *req)
 		}
 		req->flags &= ~REQ_F_NEED_CLEANUP;
 	}
+
+	if (req->flags & REQ_F_INFLIGHT) {
+		struct io_ring_ctx *ctx = req->ctx;
+		unsigned long flags;
+
+		spin_lock_irqsave(&ctx->inflight_lock, flags);
+		list_del(&req->inflight_entry);
+		if (waitqueue_active(&ctx->inflight_wait))
+			wake_up(&ctx->inflight_wait);
+		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+		req->flags &= ~REQ_F_INFLIGHT;
+	}
 }
 
 static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -7327,7 +7335,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 		table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
 		index = i & IORING_FILE_TABLE_MASK;
 		if (table->files[index]) {
-			file = io_file_from_index(ctx, index);
+			file = table->files[index];
 			err = io_queue_file_removal(data, file);
 			if (err)
 				break;
@@ -7356,6 +7364,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 			table->files[index] = file;
 			err = io_sqe_file_register(ctx, file, i);
 			if (err) {
+				table->files[index] = NULL;
 				fput(file);
 				break;
 			}
@@ -7455,9 +7464,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 {
 	int ret;
 
-	mmgrab(current->mm);
-	ctx->sqo_mm = current->mm;
-
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		ret = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
@@ -7502,10 +7508,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 	return 0;
 err:
 	io_finish_async(ctx);
-	if (ctx->sqo_mm) {
-		mmdrop(ctx->sqo_mm);
-		ctx->sqo_mm = NULL;
-	}
 	return ret;
 }
 
@@ -7979,7 +7981,13 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 			 ACCT_LOCKED);
 
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
-	queue_work(system_wq, &ctx->exit_work);
+	/*
+	 * Use system_unbound_wq to avoid spawning tons of event kworkers
+	 * if we're exiting a ton of rings at the same time. It just adds
+	 * noise and overhead, there's no discernable change in runtime
+	 * over using system_wq.
+	 */
+	queue_work(system_unbound_wq, &ctx->exit_work);
 }
 
 static int io_uring_release(struct inode *inode, struct file *file)
@@ -8016,6 +8024,28 @@ static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req)
 	return false;
 }
 
+static inline bool io_match_files(struct io_kiocb *req,
+				       struct files_struct *files)
+{
+	return (req->flags & REQ_F_WORK_INITIALIZED) && req->work.files == files;
+}
+
+static bool io_match_link_files(struct io_kiocb *req,
+				struct files_struct *files)
+{
+	struct io_kiocb *link;
+
+	if (io_match_files(req, files))
+		return true;
+	if (req->flags & REQ_F_LINK_HEAD) {
+		list_for_each_entry(link, &req->link_list, link_list) {
+			if (io_match_files(link, files))
+				return true;
+		}
+	}
+	return false;
+}
+
 /*
  * We're looking to cancel 'req' because it's holding on to our files, but
  * 'req' could be a link to another request. See if it is, and cancel that
@@ -8063,12 +8093,65 @@ static bool io_timeout_remove_link(struct io_ring_ctx *ctx,
 	return found;
 }
 
+static bool io_cancel_link_cb(struct io_wq_work *work, void *data)
+{
+	return io_match_link(container_of(work, struct io_kiocb, work), data);
+}
+
+static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
+{
+	enum io_wq_cancel cret;
+
+	/* cancel this particular work, if it's running */
+	cret = io_wq_cancel_work(ctx->io_wq, &req->work);
+	if (cret != IO_WQ_CANCEL_NOTFOUND)
+		return;
+
+	/* find links that hold this pending, cancel those */
+	cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_link_cb, req, true);
+	if (cret != IO_WQ_CANCEL_NOTFOUND)
+		return;
+
+	/* if we have a poll link holding this pending, cancel that */
+	if (io_poll_remove_link(ctx, req))
+		return;
+
+	/* final option, timeout link is holding this req pending */
+	io_timeout_remove_link(ctx, req);
+}
+
+static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+				  struct files_struct *files)
+{
+	struct io_defer_entry *de = NULL;
+	LIST_HEAD(list);
+
+	spin_lock_irq(&ctx->completion_lock);
+	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
+		if (io_match_link_files(de->req, files)) {
+			list_cut_position(&list, &ctx->defer_list, &de->list);
+			break;
+		}
+	}
+	spin_unlock_irq(&ctx->completion_lock);
+
+	while (!list_empty(&list)) {
+		de = list_first_entry(&list, struct io_defer_entry, list);
+		list_del_init(&de->list);
+		req_set_fail_links(de->req);
+		io_put_req(de->req);
+		io_req_complete(de->req, -ECANCELED);
+		kfree(de);
+	}
+}
+
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
 	if (list_empty_careful(&ctx->inflight_list))
 		return;
 
+	io_cancel_defer_files(ctx, files);
 	/* cancel all at once, should be faster than doing it one by one*/
 	io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
 
@@ -8094,35 +8177,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		/* We need to keep going until we don't find a matching req */
 		if (!cancel_req)
 			break;
-
-		if (cancel_req->flags & REQ_F_OVERFLOW) {
-			spin_lock_irq(&ctx->completion_lock);
-			list_del(&cancel_req->compl.list);
-			cancel_req->flags &= ~REQ_F_OVERFLOW;
-
-			io_cqring_mark_overflow(ctx);
-			WRITE_ONCE(ctx->rings->cq_overflow,
-				atomic_inc_return(&ctx->cached_cq_overflow));
-			io_commit_cqring(ctx);
-			spin_unlock_irq(&ctx->completion_lock);
-
-			/*
-			 * Put inflight ref and overflow ref. If that's
-			 * all we had, then we're done with this request.
-			 */
-			if (refcount_sub_and_test(2, &cancel_req->refs)) {
-				io_free_req(cancel_req);
-				finish_wait(&ctx->inflight_wait, &wait);
-				continue;
-			}
-		} else {
-			io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
-			/* could be a link, check and remove if it is */
-			if (!io_poll_remove_link(ctx, cancel_req))
-				io_timeout_remove_link(ctx, cancel_req);
-			io_put_req(cancel_req);
-		}
-
+		/* cancel this request, or head link requests */
+		io_attempt_cancel(ctx, cancel_req);
+		io_put_req(cancel_req);
 		schedule();
 		finish_wait(&ctx->inflight_wait, &wait);
 	}
@@ -8548,6 +8605,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	ctx->user = user;
 	ctx->creds = get_current_cred();
 
+	mmgrab(current->mm);
+	ctx->sqo_mm = current->mm;
+
 	/*
 	 * Account memory _before_ installing the file descriptor. Once
 	 * the descriptor is installed, it can get closed at any time. Also
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index 89f61d93c0bc..107ee80c3568 100644
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -127,7 +127,7 @@ iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
 						   SEEK_HOLE);
 		if (offset < 0)
 			return length;
-		/* fall through */
+		fallthrough;
 	case IOMAP_HOLE:
 		*(loff_t *)data = offset;
 		return 0;
@@ -175,7 +175,7 @@ iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
 						   SEEK_DATA);
 		if (offset < 0)
 			return length;
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		*(loff_t *)data = offset;
 		return 0;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e4944436e733..17fdc482f554 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1285,7 +1285,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode)
  * superblock as being NULL to prevent the journal destroy from writing
  * back a bogus superblock.
  */
-static void journal_fail_superblock (journal_t *journal)
+static void journal_fail_superblock(journal_t *journal)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	brelse(bh);
@@ -1367,8 +1367,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	int ret;
 
 	/* Buffer got discarded which means block device got invalidated */
-	if (!buffer_mapped(bh))
+	if (!buffer_mapped(bh)) {
+		unlock_buffer(bh);
 		return -EIO;
+	}
 
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
@@ -1815,7 +1817,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 
 /**
- *int jbd2_journal_check_used_features () - Check if features specified are used.
+ *int jbd2_journal_check_used_features() - Check if features specified are used.
  * @journal: Journal to check.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -1825,7 +1827,7 @@ int jbd2_journal_destroy(journal_t *journal)
  * features.  Return true (non-zero) if it does.
  **/
 
-int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat,
 				 unsigned long ro, unsigned long incompat)
 {
 	journal_superblock_t *sb;
@@ -1860,7 +1862,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
  * all of a given set of features on this journal.  Return true
  * (non-zero) if it can. */
 
-int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat,
 				      unsigned long ro, unsigned long incompat)
 {
 	if (!compat && !ro && !incompat)
@@ -1882,7 +1884,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com
 }
 
 /**
- * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
+ * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -1893,7 +1895,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com
  *
  */
 
-int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 			  unsigned long ro, unsigned long incompat)
 {
 #define INCOMPAT_FEATURE_ON(f) \
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 2ed278f0dced..faa97d748474 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -690,14 +690,11 @@ static int do_one_pass(journal_t *journal,
 			 * number. */
 			if (pass == PASS_SCAN &&
 			    jbd2_has_feature_checksum(journal)) {
-				int chksum_err, chksum_seen;
 				struct commit_header *cbh =
 					(struct commit_header *)bh->b_data;
 				unsigned found_chksum =
 					be32_to_cpu(cbh->h_chksum[0]);
 
-				chksum_err = chksum_seen = 0;
-
 				if (info->end_transaction) {
 					journal->j_failed_commit =
 						info->end_transaction;
@@ -705,42 +702,23 @@ static int do_one_pass(journal_t *journal,
 					break;
 				}
 
-				if (crc32_sum == found_chksum &&
-				    cbh->h_chksum_type == JBD2_CRC32_CHKSUM &&
-				    cbh->h_chksum_size ==
-						JBD2_CRC32_CHKSUM_SIZE)
-				       chksum_seen = 1;
-				else if (!(cbh->h_chksum_type == 0 &&
-					     cbh->h_chksum_size == 0 &&
-					     found_chksum == 0 &&
-					     !chksum_seen))
-				/*
-				 * If fs is mounted using an old kernel and then
-				 * kernel with journal_chksum is used then we
-				 * get a situation where the journal flag has
-				 * checksum flag set but checksums are not
-				 * present i.e chksum = 0, in the individual
-				 * commit blocks.
-				 * Hence to avoid checksum failures, in this
-				 * situation, this extra check is added.
-				 */
-						chksum_err = 1;
-
-				if (chksum_err) {
-					info->end_transaction = next_commit_ID;
-
-					if (!jbd2_has_feature_async_commit(journal)) {
-						journal->j_failed_commit =
-							next_commit_ID;
-						brelse(bh);
-						break;
-					}
-				}
+				/* Neither checksum match nor unused? */
+				if (!((crc32_sum == found_chksum &&
+				       cbh->h_chksum_type ==
+						JBD2_CRC32_CHKSUM &&
+				       cbh->h_chksum_size ==
+						JBD2_CRC32_CHKSUM_SIZE) ||
+				      (cbh->h_chksum_type == 0 &&
+				       cbh->h_chksum_size == 0 &&
+				       found_chksum == 0)))
+					goto chksum_error;
+
 				crc32_sum = ~0;
 			}
 			if (pass == PASS_SCAN &&
 			    !jbd2_commit_block_csum_verify(journal,
 							   bh->b_data)) {
+			chksum_error:
 				info->end_transaction = next_commit_ID;
 
 				if (!jbd2_has_feature_async_commit(journal)) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e91aad3637a2..43985738aa86 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2026,6 +2026,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
  */
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
 }
@@ -2078,10 +2081,6 @@ out:
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
- * code to release the buffers.
- *
  *
  * For all the buffers on this page,
  * if they are fully written out ordered data, move them onto BUF_CLEAN
@@ -2112,11 +2111,11 @@ out:
  *
  * Return 0 on failure, 1 on success
  */
-int jbd2_journal_try_to_free_buffers(journal_t *journal,
-				struct page *page, gfp_t gfp_mask)
+int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
+	bool has_write_io_error = false;
 	int ret = 0;
 
 	J_ASSERT(PageLocked(page));
@@ -2141,11 +2140,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 		jbd2_journal_put_journal_head(jh);
 		if (buffer_jbd(bh))
 			goto busy;
+
+		/*
+		 * If we free a metadata buffer which has been failed to
+		 * write out, the jbd2 checkpoint procedure will not detect
+		 * this failure and may lead to filesystem inconsistency
+		 * after cleanup journal tail.
+		 */
+		if (buffer_write_io_error(bh)) {
+			pr_err("JBD2: Error while async write back metadata bh %llu.",
+			       (unsigned long long)bh->b_blocknr);
+			has_write_io_error = true;
+		}
 	} while ((bh = bh->b_this_page) != head);
 
 	ret = try_to_free_buffers(page);
 
 busy:
+	if (has_write_io_error)
+		jbd2_journal_abort(journal, -EIO);
+
 	return ret;
 }
 
@@ -2572,6 +2586,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh)
 
 	was_dirty = test_clear_buffer_jbddirty(bh);
 	__jbd2_journal_temp_unlink_buffer(jh);
+
+	/*
+	 * b_transaction must be set, otherwise the new b_transaction won't
+	 * be holding jh reference
+	 */
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+
 	/*
 	 * We set b_transaction here because b_next_transaction will inherit
 	 * our jh reference and thus __jbd2_journal_file_buffer() must not
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index ab8cdd9e9325..78858f6e9583 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -341,7 +341,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 			rdev = old_decode_dev(je16_to_cpu(jdev.old_id));
 		else
 			rdev = new_decode_dev(je32_to_cpu(jdev.new_id));
-		/* fall through */
+		fallthrough;
 
 	case S_IFSOCK:
 	case S_IFIFO:
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index bccfc40b3a74..2f6f0b140c05 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -1273,7 +1273,7 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c,
 			dbg_readinode("symlink's target '%s' cached\n", f->target);
 		}
 
-		/* fall through... */
+		fallthrough;
 
 	case S_IFBLK:
 	case S_IFCHR:
diff --git a/fs/libfs.c b/fs/libfs.c
index 4d08edf19c78..e0d42e977d9a 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -137,11 +137,11 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
-			/* fall through */
+			fallthrough;
 		case 0:
 			if (offset >= 0)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
diff --git a/fs/locks.c b/fs/locks.c
index 8fc0542f5132..1f84a03601fe 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1499,7 +1499,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 	switch (arg) {
 	case F_UNLCK:
 		fl->fl_flags &= ~FL_UNLOCK_PENDING;
-		/* fall through */
+		fallthrough;
 	case F_RDLCK:
 		fl->fl_flags &= ~FL_DOWNGRADE_PENDING;
 	}
@@ -2525,7 +2525,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		cmd = F_SETLKW;
 		file_lock->fl_flags |= FL_OFDLCK;
 		file_lock->fl_owner = filp;
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLKW:
 		file_lock->fl_flags |= FL_SLEEP;
 	}
@@ -2656,7 +2656,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		cmd = F_SETLKW64;
 		file_lock->fl_flags |= FL_OFDLCK;
 		file_lock->fl_owner = filp;
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLKW64:
 		file_lock->fl_flags |= FL_SLEEP;
 	}
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index d1a0e2c8b1b4..08108b6d2fa1 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -753,7 +753,7 @@ out:
 	case -ENODEV:
 		/* Our extent block devices are unavailable */
 		set_bit(NFS_LSEG_UNAVAILABLE, &lseg->pls_flags);
-		/* Fall through */
+		fallthrough;
 	case 0:
 		return lseg;
 	default:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a12f42e7d8c7..e732580fe47b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1181,7 +1181,7 @@ int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
 			/* A NFSv4 OPEN will revalidate later */
 			if (server->caps & NFS_CAP_ATOMIC_OPEN)
 				goto out;
-			/* Fallthrough */
+			fallthrough;
 		case S_IFDIR:
 			if (server->flags & NFS_MOUNT_NOCTO)
 				break;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index a13e69009f19..7f5aa0403e16 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -187,7 +187,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		pnfs_error_mark_layout_for_return(inode, lseg);
 		pnfs_set_lo_fail(lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		/* fall through */
+		fallthrough;
 	default:
 reset:
 		dprintk("%s Retry through MDS. Error %d\n", __func__,
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 965145592750..ff8965d1a4d4 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1133,7 +1133,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		/* fall through */
+		fallthrough;
 	default:
 		if (ff_layout_avoid_mds_available_ds(lseg))
 			return -NFS4ERR_RESET_TO_PNFS;
@@ -1260,7 +1260,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		 */
 		if (opnum == OP_READ)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
 						  lseg);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 66949da0e827..524812984e2d 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -651,21 +651,21 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) {
 		case Opt_xprt_udp6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_udp:
 			ctx->flags &= ~NFS_MOUNT_TCP;
 			ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP;
 			break;
 		case Opt_xprt_tcp6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_tcp:
 			ctx->flags |= NFS_MOUNT_TCP;
 			ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 			break;
 		case Opt_xprt_rdma6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_rdma:
 			/* vector side protocols to TCP */
 			ctx->flags |= NFS_MOUNT_TCP;
@@ -684,13 +684,13 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) {
 		case Opt_xprt_udp6:
 			mountfamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_udp:
 			ctx->mount_server.protocol = XPRT_TRANSPORT_UDP;
 			break;
 		case Opt_xprt_tcp6:
 			mountfamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_tcp:
 			ctx->mount_server.protocol = XPRT_TRANSPORT_TCP;
 			break;
@@ -899,9 +899,11 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 	ctx->version = NFS_DEFAULT_VERSION;
 	switch (data->version) {
 	case 1:
-		data->namlen = 0; /* fall through */
+		data->namlen = 0;
+		fallthrough;
 	case 2:
-		data->bsize = 0; /* fall through */
+		data->bsize = 0;
+		fallthrough;
 	case 3:
 		if (data->flags & NFS_MOUNT_VER3)
 			goto out_no_v3;
@@ -909,14 +911,14 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
 		/* Turn off security negotiation */
 		extra_flags |= NFS_MOUNT_SECFLAVOUR;
-		/* fall through */
+		fallthrough;
 	case 4:
 		if (data->flags & NFS_MOUNT_SECFLAVOUR)
 			goto out_no_sec;
-		/* fall through */
+		fallthrough;
 	case 5:
 		memset(data->context, 0, sizeof(data->context));
-		/* fall through */
+		fallthrough;
 	case 6:
 		if (data->flags & NFS_MOUNT_VER3) {
 			if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 26c94b32d6f4..c6c863382f37 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -108,7 +108,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
 		case -EPROTONOSUPPORT:
 			dprintk("NFS_V3_ACL extension not supported; disabling\n");
 			server->caps &= ~NFS_CAP_ACLS;
-			/* fall through */
+			fallthrough;
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
 		default:
@@ -228,7 +228,7 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 			dprintk("NFS_V3_ACL SETACL RPC not supported"
 					"(will not retry)\n");
 			server->caps &= ~NFS_CAP_ACLS;
-			/* fall through */
+			fallthrough;
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
 	}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a33970765467..fdfc77486ace 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -211,7 +211,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 		ret = nfs42_proc_llseek(filep, offset, whence);
 		if (ret != -ENOTSUPP)
 			return ret;
-		/* Fall through */
+		fallthrough;
 	default:
 		return nfs_file_llseek(filep, offset, whence);
 	}
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 1e7296395d71..62e6eea5c516 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -520,7 +520,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
 	switch (token) {
 	case Opt_find_uid:
 		im->im_type = IDMAP_TYPE_USER;
-		/* Fall through */
+		fallthrough;
 	case Opt_find_gid:
 		im->im_conv = IDMAP_CONV_NAMETOID;
 		ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ);
@@ -528,7 +528,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
 
 	case Opt_find_user:
 		im->im_type = IDMAP_TYPE_USER;
-		/* Fall through */
+		fallthrough;
 	case Opt_find_group:
 		im->im_conv = IDMAP_CONV_IDTONAME;
 		ret = match_int(&substr, &im->im_id);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index dbd01548335b..6e95c85fe395 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -483,7 +483,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 						stateid);
 				goto wait_on_recovery;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_OPENMODE:
 			if (inode) {
 				int err;
@@ -534,10 +534,10 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 				ret = -EBUSY;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
@@ -1505,7 +1505,7 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
 	case NFS4_OPEN_CLAIM_PREVIOUS:
 		if (!test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags))
 			break;
-		/* Fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -2439,7 +2439,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 	case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
 		data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
-		/* Fall through */
+		fallthrough;
 	case NFS4_OPEN_CLAIM_FH:
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
 	}
@@ -3293,8 +3293,10 @@ static int _nfs4_do_setattr(struct inode *inode,
 
 	/* Servers should only apply open mode checks for file size changes */
 	truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
-	if (!truncate)
+	if (!truncate) {
+		nfs4_inode_make_writeable(inode);
 		goto zero_stateid;
+	}
 
 	if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
 		/* Use that stateid */
@@ -3545,11 +3547,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			nfs4_free_revoked_stateid(server,
 					&calldata->arg.stateid,
 					task->tk_msg.rpc_cred);
-			/* Fallthrough */
+			fallthrough;
 		case -NFS4ERR_BAD_STATEID:
 			if (calldata->arg.fmode == 0)
 				break;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			task->tk_status = nfs4_async_handle_exception(task,
 					server, task->tk_status, &exception);
@@ -6294,7 +6296,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		nfs4_free_revoked_stateid(data->res.server,
 				data->args.stateid,
 				task->tk_msg.rpc_cred);
-		/* Fallthrough */
+		fallthrough;
 	case -NFS4ERR_BAD_STATEID:
 	case -NFS4ERR_STALE_STATEID:
 	case -ETIMEDOUT:
@@ -6314,7 +6316,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 			data->res.fattr = NULL;
 			goto out_restart;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		task->tk_status = nfs4_async_handle_exception(task,
 				data->res.server, task->tk_status,
@@ -6622,13 +6624,13 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			if (nfs4_update_lock_stateid(calldata->lsp,
 					&calldata->res.stateid))
 				break;
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_EXPIRED:
 			nfs4_free_revoked_stateid(calldata->server,
 					&calldata->arg.stateid,
 					task->tk_msg.rpc_cred);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_STALE_STATEID:
 			if (nfs4_sync_lock_stateid(&calldata->arg.stateid,
@@ -7298,7 +7300,12 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 	err = nfs4_set_lock_state(state, fl);
 	if (err != 0)
 		return err;
-	err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+	do {
+		err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		ssleep(1);
+	} while (err == -NFS4ERR_DELAY);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
 }
 
@@ -8665,7 +8672,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
 		dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status);
 		rpc_delay(task, NFS4_POLL_RETRY_MIN);
 		task->tk_status = 0;
-		/* fall through */
+		fallthrough;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		rpc_restart_call_prepare(task);
 		return;
@@ -9113,13 +9120,13 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 	switch(task->tk_status) {
 	case 0:
 		wake_up_all(&clp->cl_lock_waitq);
-		/* Fallthrough */
+		fallthrough;
 	case -NFS4ERR_COMPLETE_ALREADY:
 	case -NFS4ERR_WRONG_CRED: /* What to do here? */
 		break;
 	case -NFS4ERR_DELAY:
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
-		/* fall through */
+		fallthrough;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		return -EAGAIN;
 	case -NFS4ERR_BADSESSION:
@@ -9434,10 +9441,10 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 					&lrp->args.range,
 					lrp->args.inode))
 			goto out_restart;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		task->tk_status = 0;
-		/* Fallthrough */
+		fallthrough;
 	case 0:
 		break;
 	case -NFS4ERR_DELAY:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b1dba24918f8..4bf10792cb5b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1530,7 +1530,7 @@ restart:
 		default:
 			pr_err("NFS: %s: unhandled error %d\n",
 					__func__, status);
-			/* Fall through */
+			fallthrough;
 		case -ENOMEM:
 		case -NFS4ERR_DENIED:
 		case -NFS4ERR_RECLAIM_BAD:
@@ -1667,7 +1667,7 @@ restart:
 				break;
 			}
 			printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
-			/* Fall through */
+			fallthrough;
 		case -ENOENT:
 		case -ENOMEM:
 		case -EACCES:
@@ -1683,7 +1683,7 @@ restart:
 				set_bit(ops->state_flag_bit, &state->flags);
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
@@ -1695,7 +1695,7 @@ restart:
 		case -NFS4ERR_EXPIRED:
 		case -NFS4ERR_NO_GRACE:
 			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -2273,11 +2273,11 @@ again:
 	case -ETIMEDOUT:
 		if (clnt->cl_softrtry)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_DELAY:
 	case -EAGAIN:
 		ssleep(1);
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_STALE_CLIENTID:
 		dprintk("NFS: %s after status %d, retrying\n",
 			__func__, status);
@@ -2289,7 +2289,7 @@ again:
 		}
 		if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_WRONGSEC:
 		/* No point in retrying if we already used RPC_AUTH_UNIX */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6ea4cac41e46..6985cacf4700 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -711,7 +711,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
 	case FLUSH_COND_STABLE:
 		if (nfs_reqs_to_commit(cinfo))
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		hdr->args.stable = NFS_FILE_SYNC;
 	}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 40332c758d84..71f7741126b6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1541,7 +1541,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	case 0:
 		if (res->lrs_present)
 			res_stateid = &res->stateid;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		arg_stateid = &args->stateid;
 	}
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 8ceb6425e01a..d056ad2fdefd 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -237,7 +237,7 @@ posix_acl_from_nfsacl(struct posix_acl *acl)
 				break;
 			case ACL_MASK:
 				mask = pa;
-				/* fall through */
+				fallthrough;
 			case ACL_OTHER:
 				break;
 		}
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 9bbaa671c079..311e5ce80cfc 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -83,13 +83,13 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 			bex->soff = iomap.addr;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_HOLE:
 		if (seg->iomode == IOMODE_READ) {
 			bex->es = PNFS_BLOCK_NONE_DATA;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_DELALLOC:
 	default:
 		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7fbe9840a03e..052be5bf9ef5 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1119,7 +1119,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		break;
 	case -ESERVERFAULT:
 		++session->se_cb_seq_nr;
-		/* Fall through */
+		fallthrough;
 	case 1:
 	case -NFS4ERR_BADSESSION:
 		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index e12409eca7cc..a97873f2d22b 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -681,7 +681,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 			rpc_delay(task, HZ/100); /* 10 mili-seconds */
 			return 0;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a527da3d8052..eaf50eafa935 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -428,7 +428,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				goto out;
 			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 			reclaim = true;
-			/* fall through */
+			fallthrough;
 		case NFS4_OPEN_CLAIM_FH:
 		case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 			status = do_open_fhandle(rqstp, cstate, open);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 81ed8e8bab3f..c09a2a4281ec 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3117,7 +3117,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		break;
 	default:				/* checked by xdr code */
 		WARN_ON_ONCE(1);
-		/* fall through */
+		fallthrough;
 	case SP4_SSV:
 		status = nfserr_encr_alg_unsupp;
 		goto out_nolock;
@@ -4532,7 +4532,7 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
 			rpc_delay(task, 2 * HZ);
 			return 0;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		return 1;
 	}
@@ -4597,6 +4597,8 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl)
 	if (!i_am_nfsd())
 		return NULL;
 	rqst = kthread_data(current);
+	if (!rqst->rq_lease_breaker)
+		return NULL;
 	clp = *(rqst->rq_lease_breaker);
 	return dl->dl_stid.sc_client == clp;
 }
@@ -5652,7 +5654,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 		break;
 	default:
 		printk("unknown stateid type %x\n", s->sc_type);
-		/* Fallthrough */
+		fallthrough;
 	case NFS4_CLOSED_STID:
 	case NFS4_CLOSED_DELEG_STID:
 		status = nfserr_bad_stateid;
@@ -6742,7 +6744,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		case NFS4_READW_LT:
 			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
-			/* Fallthrough */
+			fallthrough;
 		case NFS4_READ_LT:
 			spin_lock(&fp->fi_lock);
 			nf = find_readable_file_locked(fp);
@@ -6754,7 +6756,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		case NFS4_WRITEW_LT:
 			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
-			/* Fallthrough */
+			fallthrough;
 		case NFS4_WRITE_LT:
 			spin_lock(&fp->fi_lock);
 			nf = find_writeable_file_locked(fp);
@@ -6816,7 +6818,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		break;
 	case FILE_LOCK_DEFERRED:
 		nbl = NULL;
-		/* Fallthrough */
+		fallthrough;
 	case -EAGAIN:		/* conflock holds conflicting lock */
 		status = nfserr_denied;
 		dprintk("NFSD: nfsd4_lock: conflicting lock found!\n");
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 37bc8f5f4514..c81dbbad8792 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -459,7 +459,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	case FSID_DEV:
 		if (!old_valid_dev(exp_sb(exp)->s_dev))
 			return false;
-		/* FALL THROUGH */
+		fallthrough;
 	case FSID_MAJOR_MINOR:
 	case FSID_ENCODE_DEV:
 		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
@@ -469,7 +469,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	case FSID_UUID16:
 		if (!is_root_export(exp))
 			return false;
-		/* fall through */
+		fallthrough;
 	case FSID_UUID4_INUM:
 	case FSID_UUID16_INUM:
 		return exp->ex_uuid != NULL;
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 543bbe0a556e..6e0b066480c5 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -314,7 +314,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 					rdev = inode->i_rdev;
 					attr->ia_valid |= ATTR_SIZE;
 
-					/* FALLTHROUGH */
+					fallthrough;
 				case S_IFIFO:
 					/* this is probably a permission check..
 					 * at least IRIX implements perm checking on
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index b603dfcdd361..f7f6473578af 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -221,7 +221,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change)
 	case NFSD_TEST:
 		if (nn->nfsd_versions)
 			return nn->nfsd_versions[vers];
-		/* Fallthrough */
+		fallthrough;
 	case NFSD_AVAIL:
 		return nfsd_support_version(vers);
 	}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7d2933b85b65..aba5af9df328 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1456,7 +1456,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS4_CREATE_EXCLUSIVE4_1:
 			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
 			    && d_inode(dchild)->i_atime.tv_sec == v_atime
@@ -1465,7 +1465,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				goto set_attr;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
 		}
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index fb5a9a8a13cf..e516ae389ca5 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -519,7 +519,7 @@ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode)
 		break;
 	case NILFS_IFILE_INO:
 		lockdep_set_class(&bmap->b_sem, &nilfs_bmap_mdt_lock_key);
-		/* Fall through */
+		fallthrough;
 	default:
 		bmap->b_ptr_type = NILFS_BMAP_PTR_VM;
 		bmap->b_last_allocated_key = 0;
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0b453ef8fae5..2217f904a7cf 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -626,7 +626,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 			    !(flags & NILFS_SS_SYNDT))
 				goto try_next_pseg;
 			state = RF_DSYNC_ST;
-			/* Fall through */
+			fallthrough;
 		case RF_DSYNC_ST:
 			if (!(flags & NILFS_SS_SYNDT))
 				goto confused;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a651e821c2de..e3726aca28ed 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1138,7 +1138,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			nilfs_sc_cstage_set(sci, NILFS_ST_DAT);
 			goto dat_stage;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_GC:
 		if (nilfs_doing_gc()) {
 			head = &sci->sc_gc_inodes;
@@ -1159,7 +1160,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			}
 			sci->sc_stage.gc_inode_ptr = NULL;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_FILE:
 		head = &sci->sc_dirty_files;
 		ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head,
@@ -1186,7 +1188,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		}
 		nilfs_sc_cstage_inc(sci);
 		sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED;
-		/* Fall through */
+		fallthrough;
 	case NILFS_ST_IFILE:
 		err = nilfs_segctor_scan_file(sci, sci->sc_root->ifile,
 					      &nilfs_sc_file_ops);
@@ -1197,13 +1199,14 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		err = nilfs_segctor_create_checkpoint(sci);
 		if (unlikely(err))
 			break;
-		/* Fall through */
+		fallthrough;
 	case NILFS_ST_CPFILE:
 		err = nilfs_segctor_scan_file(sci, nilfs->ns_cpfile,
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_SUFILE:
 		err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs,
 					 sci->sc_nfreesegs, &ndone);
@@ -1219,7 +1222,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_DAT:
  dat_stage:
 		err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
@@ -1230,7 +1234,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 			return 0;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_SR:
 		if (mode == SC_LSEG_SR) {
 			/* Appending a super root */
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 559de311deca..3e01d8f2ab90 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1147,7 +1147,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
-	case FAN_MARK_ADD:		/* fallthrough */
+	case FAN_MARK_ADD:
 	case FAN_MARK_REMOVE:
 		if (!mask)
 			return -EINVAL;
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 1ef24574f481..cea739be77c4 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -67,7 +67,7 @@ static void o2quo_fence_self(void)
 	default:
 		WARN_ON(o2nm_single_cluster->cl_fence_method >=
 			O2NM_FENCE_METHODS);
-		/* fall through */
+		fallthrough;
 	case O2NM_FENCE_RESET:
 		printk(KERN_ERR "*** ocfs2 is very sorry to be fencing this "
 		       "system by restarting ***\n");
diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c
index 819428dfa32f..3ce89216670c 100644
--- a/fs/pstore/zone.c
+++ b/fs/pstore/zone.c
@@ -1081,7 +1081,6 @@ next_zone:
 		readop = psz_ftrace_read;
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		fallthrough;
 	case PSTORE_TYPE_PMSG:
 		readop = psz_record_read;
 		break;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 5444d3c4d93f..47f9e151988b 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -38,7 +38,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 		if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) ||
 		    (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id))))
 			break;
-		/*FALLTHROUGH*/
+		fallthrough;
 	default:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c
index 6b2b4362089e..b57b3ffcbc32 100644
--- a/fs/romfs/storage.c
+++ b/fs/romfs/storage.c
@@ -217,10 +217,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos,
 	size_t limit;
 
 	limit = romfs_maxsize(sb);
-	if (pos >= limit)
+	if (pos >= limit || buflen > limit - pos)
 		return -EIO;
-	if (buflen > limit - pos)
-		buflen = limit - pos;
 
 #ifdef CONFIG_ROMFS_ON_MTD
 	if (sb->s_mtd)
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4e6239f33c06..31219c1db17d 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -295,7 +295,7 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 	case SEEK_CUR:
 		offset += file->f_pos;
-		/* fall through */
+		fallthrough;
 	case SEEK_SET:
 		if (offset < 0)
 			break;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 5b78719be445..456046e15873 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -176,7 +176,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info
 		if (!nonblock)
 			break;
 		ret = -EAGAIN;
-		/* fall through */
+		fallthrough;
 	default:
 		spin_unlock_irq(&current->sighand->siglock);
 		return ret;
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 76bb1c846845..8a19773b5a0b 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -87,7 +87,11 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length,
 	int error, i;
 	struct bio *bio;
 
-	bio = bio_alloc(GFP_NOIO, page_count);
+	if (page_count <= BIO_MAX_PAGES)
+		bio = bio_alloc(GFP_NOIO, page_count);
+	else
+		bio = bio_kmalloc(GFP_NOIO, page_count);
+
 	if (!bio)
 		return -ENOMEM;
 
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 22bfda158f7f..6d6cd85c2b4c 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -269,7 +269,7 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
 			break;
 		/* No more room on heap so make it un-categorized */
 		cat = LPROPS_UNCAT;
-		/* Fall through */
+		fallthrough;
 	case LPROPS_UNCAT:
 		list_add(&lprops->list, &c->uncat_list);
 		break;
@@ -313,7 +313,7 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
 	case LPROPS_FREEABLE:
 		c->freeable_cnt -= 1;
 		ubifs_assert(c, c->freeable_cnt >= 0);
-		/* Fall through */
+		fallthrough;
 	case LPROPS_UNCAT:
 	case LPROPS_EMPTY:
 	case LPROPS_FRDI_IDX:
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 6023c97c6da2..25ff91c7e94a 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -52,7 +52,7 @@ static int udf_pc_to_char(struct super_block *sb, unsigned char *from,
 				elen += pc->lengthComponentIdent;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case 2:
 			if (tolen == 0)
 				return -ENAMETOOLONG;
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index e1f1b2e868a7..4931bec1a01c 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -42,7 +42,7 @@ ufs_get_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1,
 	case UFS_ST_SUNOS:
 		if (fs32_to_cpu(sb, usb3->fs_postblformat) == UFS_42POSTBLFMT)
 			return fs32_to_cpu(sb, usb1->fs_u0.fs_sun.fs_state);
-		/* Fall Through - to UFS_ST_SUN */
+		fallthrough;	/* to UFS_ST_SUN */
 	case UFS_ST_SUN:
 		return fs32_to_cpu(sb, usb3->fs_un2.fs_sun.fs_state);
 	case UFS_ST_SUNx86:
@@ -63,7 +63,7 @@ ufs_set_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1,
 			usb1->fs_u0.fs_sun.fs_state = cpu_to_fs32(sb, value);
 			break;
 		}
-		/* Fall Through - to UFS_ST_SUN */
+		fallthrough;	/* to UFS_ST_SUN */
 	case UFS_ST_SUN:
 		usb3->fs_un2.fs_sun.fs_state = cpu_to_fs32(sb, value);
 		break;
@@ -197,7 +197,7 @@ ufs_get_inode_uid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_EFT:
 		if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_uid);
-		/* Fall through */
+		fallthrough;
 	default:
 		return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_suid);
 	}
@@ -215,7 +215,7 @@ ufs_set_inode_uid(struct super_block *sb, struct ufs_inode *inode, u32 value)
 		inode->ui_u3.ui_sun.ui_uid = cpu_to_fs32(sb, value);
 		if (value > 0xFFFF)
 			value = 0xFFFF;
-		/* Fall through */
+		fallthrough;
 	default:
 		inode->ui_u1.oldids.ui_suid = cpu_to_fs16(sb, value);
 		break;
@@ -231,7 +231,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_EFT:
 		if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
-		/* Fall through */
+		fallthrough;
 	default:
 		return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_sgid);
 	}
@@ -249,7 +249,7 @@ ufs_set_inode_gid(struct super_block *sb, struct ufs_inode *inode, u32 value)
 		inode->ui_u3.ui_sun.ui_gid = cpu_to_fs32(sb, value);
 		if (value > 0xFFFF)
 			value = 0xFFFF;
-		/* Fall through */
+		fallthrough;
 	default:
 		inode->ui_u1.oldids.ui_sgid =  cpu_to_fs16(sb, value);
 		break;
diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c
index 96bd160da48b..018057546067 100644
--- a/fs/vboxsf/utils.c
+++ b/fs/vboxsf/utils.c
@@ -226,7 +226,7 @@ int vboxsf_getattr(const struct path *path, struct kstat *kstat,
 		break;
 	case AT_STATX_FORCE_SYNC:
 		sf_i->force_restat = 1;
-		/* fall-through */
+		fallthrough;
 	default:
 		err = vboxsf_inode_revalidate(dentry);
 	}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 8623c815164a..305d4bc07337 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -653,8 +653,8 @@ xfs_attr_shortform_create(
 		ASSERT(ifp->if_flags & XFS_IFINLINE);
 	}
 	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data;
-	hdr->count = 0;
+	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 }
@@ -1036,8 +1036,10 @@ xfs_attr_shortform_verify(
 		 * struct xfs_attr_sf_entry has a variable length.
 		 * Check the fixed-offset parts of the structure are
 		 * within the data buffer.
+		 * xfs_attr_sf_entry is defined with a 1-byte variable
+		 * array at the end, so we must subtract that off.
 		 */
-		if (((char *)sfep + sizeof(*sfep)) >= endp)
+		if (((char *)sfep + sizeof(*sfep) - 1) >= endp)
 			return __this_address;
 
 		/* Don't allow names with known bad length. */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 9c40d5971035..1b0a01b06a05 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6226,7 +6226,7 @@ xfs_bmap_validate_extent(
 
 	isrt = XFS_IS_REALTIME_INODE(ip);
 	endfsb = irec->br_startblock + irec->br_blockcount - 1;
-	if (isrt) {
+	if (isrt && whichfork == XFS_DATA_FORK) {
 		if (!xfs_verify_rtbno(mp, irec->br_startblock))
 			return __this_address;
 		if (!xfs_verify_rtbno(mp, endfsb))
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f742a96a2fe1..a6b37db55169 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -688,7 +688,7 @@ xfs_ialloc_ag_alloc(
 		args.minalignslop = igeo->cluster_align - 1;
 
 		/* Allow space for the inode btree to split. */
-		args.minleft = igeo->inobt_maxlevels - 1;
+		args.minleft = igeo->inobt_maxlevels;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 
@@ -736,7 +736,7 @@ xfs_ialloc_ag_alloc(
 		/*
 		 * Allow space for the inode btree to split.
 		 */
-		args.minleft = igeo->inobt_maxlevels - 1;
+		args.minleft = igeo->inobt_maxlevels;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 	}
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index e15129647e00..b7e222befb08 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -110,9 +110,9 @@ xfs_trans_log_inode(
 	 * to log the timestamps, or will clear already cleared fields in the
 	 * worst case.
 	 */
-	if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) {
+	if (inode->i_state & I_DIRTY_TIME) {
 		spin_lock(&inode->i_lock);
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index c6df01a2a158..7ad3659c5d2a 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -58,7 +58,7 @@
 #define	XFS_IALLOC_SPACE_RES(mp)	\
 	(M_IGEO(mp)->ialloc_blks + \
 	 ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \
-	  (M_IGEO(mp)->inobt_maxlevels - 1)))
+	  M_IGEO(mp)->inobt_maxlevels))
 
 /*
  * Space reservation values for various transactions.
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 73cafc843cd7..5123f82f2477 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1165,7 +1165,7 @@ xfs_insert_file_space(
 		goto out_trans_cancel;
 
 	do {
-		error = xfs_trans_roll_inode(&tp, ip);
+		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_trans_cancel;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index c31cd3be9fb2..a29f78a663ca 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1223,6 +1223,14 @@ __xfs_filemap_fault(
 	return ret;
 }
 
+static inline bool
+xfs_is_write_fault(
+	struct vm_fault		*vmf)
+{
+	return (vmf->flags & FAULT_FLAG_WRITE) &&
+	       (vmf->vma->vm_flags & VM_SHARED);
+}
+
 static vm_fault_t
 xfs_filemap_fault(
 	struct vm_fault		*vmf)
@@ -1230,7 +1238,7 @@ xfs_filemap_fault(
 	/* DAX can shortcut the normal fault path on write faults! */
 	return __xfs_filemap_fault(vmf, PE_SIZE_PTE,
 			IS_DAX(file_inode(vmf->vma->vm_file)) &&
-			(vmf->flags & FAULT_FLAG_WRITE));
+			xfs_is_write_fault(vmf));
 }
 
 static vm_fault_t
@@ -1243,7 +1251,7 @@ xfs_filemap_huge_fault(
 
 	/* DAX can shortcut the normal fault path on write faults! */
 	return __xfs_filemap_fault(vmf, pe_size,
-			(vmf->flags & FAULT_FLAG_WRITE));
+			xfs_is_write_fault(vmf));
 }
 
 static vm_fault_t
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 5c2819924862..85513eeb2196 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1607,12 +1607,18 @@ static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux,
 	return drm_dp_dpcd_write(aux, offset, &value, 1);
 }
 
+int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux,
+			  u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+
 int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux,
 				 u8 status[DP_LINK_STATUS_SIZE]);
 
 bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux,
 				    u8 real_edid_checksum);
 
+int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]);
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4]);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
@@ -1628,6 +1634,12 @@ void drm_dp_set_subconnector_property(struct drm_connector *connector,
 				      const u8 *dpcd,
 				      const u8 port_cap[4]);
 
+struct drm_dp_desc;
+bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				const struct drm_dp_desc *desc);
+int drm_dp_read_sink_count(struct drm_dp_aux *aux);
+
 void drm_dp_remote_aux_init(struct drm_dp_aux *aux);
 void drm_dp_aux_init(struct drm_dp_aux *aux);
 int drm_dp_aux_register(struct drm_dp_aux *aux);
@@ -1686,7 +1698,8 @@ enum drm_dp_quirk {
 	 * @DP_DPCD_QUIRK_NO_SINK_COUNT:
 	 *
 	 * The device does not set SINK_COUNT to a non-zero value.
-	 * The driver should ignore SINK_COUNT during detection.
+	 * The driver should ignore SINK_COUNT during detection. Note that
+	 * drm_dp_read_sink_count_cap() automatically checks for this quirk.
 	 */
 	DP_DPCD_QUIRK_NO_SINK_COUNT,
 	/**
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 8b9eb4db3381..6ae5860d8644 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -728,10 +728,9 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr,
 
 void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr);
 
-
+bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state);
 
-
 int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled);
 
 
diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h
index c6bab4986a65..fe58dbb46962 100644
--- a/include/drm/drm_hdcp.h
+++ b/include/drm/drm_hdcp.h
@@ -29,6 +29,9 @@
 /* Slave address for the HDCP registers in the receiver */
 #define DRM_HDCP_DDC_ADDR			0x3A
 
+/* Value to use at the end of the SHA-1 bytestream used for repeaters */
+#define DRM_HDCP_SHA1_TERMINATOR		0x80
+
 /* HDCP register offsets for HDMI/DVI devices */
 #define DRM_HDCP_DDC_BKSV			0x00
 #define DRM_HDCP_DDC_RI_PRIME			0x08
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index 4fc9a43ac45a..aafd07388eb7 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -164,6 +164,8 @@ int drm_modeset_lock_all_ctx(struct drm_device *dev,
  * is 0, so no error checking is necessary
  */
 #define DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, flags, ret)		\
+	if (!drm_drv_uses_atomic_modeset(dev))				\
+		mutex_lock(&dev->mode_config.mutex);			\
 	drm_modeset_acquire_init(&ctx, flags);				\
 modeset_lock_retry:							\
 	ret = drm_modeset_lock_all_ctx(dev, &ctx);			\
@@ -172,6 +174,7 @@ modeset_lock_retry:							\
 
 /**
  * DRM_MODESET_LOCK_ALL_END - Helper to release and cleanup modeset locks
+ * @dev: drm device
  * @ctx: local modeset acquire context, will be dereferenced
  * @ret: local ret/err/etc variable to track error status
  *
@@ -188,7 +191,7 @@ modeset_lock_retry:							\
  * to that failure. In both of these cases the code between BEGIN/END will not
  * be run, so the failure will reflect the inability to grab the locks.
  */
-#define DRM_MODESET_LOCK_ALL_END(ctx, ret)				\
+#define DRM_MODESET_LOCK_ALL_END(dev, ctx, ret)				\
 modeset_lock_fail:							\
 	if (ret == -EDEADLK) {						\
 		ret = drm_modeset_backoff(&ctx);			\
@@ -196,6 +199,8 @@ modeset_lock_fail:							\
 			goto modeset_lock_retry;			\
 	}								\
 	drm_modeset_drop_locks(&ctx);					\
-	drm_modeset_acquire_fini(&ctx);
+	drm_modeset_acquire_fini(&ctx);					\
+	if (!drm_drv_uses_atomic_modeset(dev))				\
+		mutex_unlock(&dev->mode_config.mutex);
 
 #endif /* DRM_MODESET_LOCK_H_ */
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index b9780ae9dd26..92436553fd6a 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -33,15 +33,16 @@
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
+/* These are often used as an (initial) index
+ * to an array, and as such should start at 0.
+ */
 enum drm_sched_priority {
 	DRM_SCHED_PRIORITY_MIN,
-	DRM_SCHED_PRIORITY_LOW = DRM_SCHED_PRIORITY_MIN,
 	DRM_SCHED_PRIORITY_NORMAL,
-	DRM_SCHED_PRIORITY_HIGH_SW,
-	DRM_SCHED_PRIORITY_HIGH_HW,
+	DRM_SCHED_PRIORITY_HIGH,
 	DRM_SCHED_PRIORITY_KERNEL,
-	DRM_SCHED_PRIORITY_MAX,
-	DRM_SCHED_PRIORITY_INVALID = -1,
+
+	DRM_SCHED_PRIORITY_COUNT,
 	DRM_SCHED_PRIORITY_UNSET = -2
 };
 
@@ -274,7 +275,7 @@ struct drm_gpu_scheduler {
 	uint32_t			hw_submission_limit;
 	long				timeout;
 	const char			*name;
-	struct drm_sched_rq		sched_rq[DRM_SCHED_PRIORITY_MAX];
+	struct drm_sched_rq		sched_rq[DRM_SCHED_PRIORITY_COUNT];
 	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
 	atomic_t			hw_rq_count;
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 96e408b4bdc9..8e7ae30ebcbb 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -258,9 +258,7 @@
 	INTEL_VGA_DEVICE(0x0f30, info), \
 	INTEL_VGA_DEVICE(0x0f31, info), \
 	INTEL_VGA_DEVICE(0x0f32, info), \
-	INTEL_VGA_DEVICE(0x0f33, info), \
-	INTEL_VGA_DEVICE(0x0157, info), \
-	INTEL_VGA_DEVICE(0x0155, info)
+	INTEL_VGA_DEVICE(0x0f33, info)
 
 #define INTEL_BDW_ULT_GT1_IDS(info) \
 	INTEL_VGA_DEVICE(0x1606, info), /* GT1 ULT */ \
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ac0c7299d5b8..dd74503f7e5e 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -117,11 +117,18 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 	return true;
 }
 
+static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter)
+{
+	iter->bi_bvec_done = 0;
+	iter->bi_idx++;
+}
+
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
-	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
+	     (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter),	\
+		     (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter)))
 
 /* for iterating one bio from start to end */
 #define BVEC_ITER_ALL_INIT (struct bvec_iter)				\
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index fcd84e8d88f4..999636d53cf2 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -11,14 +11,14 @@
 #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL
 
 #define DEFINE_CEPH_FEATURE(bit, incarnation, name)			\
-	static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit);		\
-	static const uint64_t CEPH_FEATUREMASK_##name =			\
+	static const uint64_t __maybe_unused CEPH_FEATURE_##name = (1ULL<<bit);		\
+	static const uint64_t __maybe_unused CEPH_FEATUREMASK_##name =			\
 		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
 
 /* this bit is ignored but still advertised by release *when* */
 #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \
-	static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \
-	static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name =		\
+	static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit);	\
+	static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATUREMASK_##name =		\
 		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
 
 /*
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..b354ce58966e 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -429,11 +429,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set,
 	compat_sigset_t v;
 	switch (_NSIG_WORDS) {
 	case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3];
-		/* fall through */
+		fallthrough;
 	case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2];
-		/* fall through */
+		fallthrough;
 	case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1];
-		/* fall through */
+		fallthrough;
 	case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0];
 	}
 	return copy_to_user(compat, &v, size) ? -EFAULT : 0;
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 6122efdad6ad..ea7b756b1c8f 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -22,14 +22,8 @@
 
 /*
  * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute
+ * In the meantime, to support gcc < 5, we implement __has_attribute
  * by hand.
- *
- * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__
- * depending on the compiler used to build it; however, these attributes have
- * no semantic effects for sparse, so it does not matter. Also note that,
- * in order to avoid sparse's warnings, even the unsupported ones must be
- * defined to 0.
  */
 #ifndef __has_attribute
 # define __has_attribute(x) __GCC4_has_attribute_##x
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 4b33cb385f96..6e390d58a9f8 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -11,8 +11,8 @@
 # define __iomem	__attribute__((noderef, address_space(__iomem)))
 # define __percpu	__attribute__((noderef, address_space(__percpu)))
 # define __rcu		__attribute__((noderef, address_space(__rcu)))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
+static inline void __chk_user_ptr(const volatile void __user *ptr) { }
+static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 /* context/locking */
 # define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 8f141d4c859c..a911e5d06845 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	case CPUFREQ_RELATION_C:
 		return cpufreq_table_find_index_c(policy, target_freq);
 	default:
-		pr_err("%s: Invalid relation: %d\n", __func__, relation);
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		return 0;
 	}
 }
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index a2710e654b64..3215023d4852 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -132,6 +132,7 @@ enum cpuhp_state {
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
+	CPUHP_AP_CLINT_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
 	CPUHP_AP_HYPERV_TIMER_STARTING,
 	CPUHP_AP_KVM_STARTING,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index b65909ae4e20..75895e6363b8 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -75,12 +75,13 @@ struct cpuidle_state {
 };
 
 /* Idle State Flags */
-#define CPUIDLE_FLAG_NONE       (0x00)
-#define CPUIDLE_FLAG_POLLING	BIT(0) /* polling state */
-#define CPUIDLE_FLAG_COUPLED	BIT(1) /* state applies to multiple cpus */
-#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */
-#define CPUIDLE_FLAG_UNUSABLE	BIT(3) /* avoid using this state */
-#define CPUIDLE_FLAG_OFF	BIT(4) /* disable this state by default */
+#define CPUIDLE_FLAG_NONE       	(0x00)
+#define CPUIDLE_FLAG_POLLING		BIT(0) /* polling state */
+#define CPUIDLE_FLAG_COUPLED		BIT(1) /* state applies to multiple cpus */
+#define CPUIDLE_FLAG_TIMER_STOP 	BIT(2) /* timer is stopped on this state */
+#define CPUIDLE_FLAG_UNUSABLE		BIT(3) /* avoid using this state */
+#define CPUIDLE_FLAG_OFF		BIT(4) /* disable this state by default */
+#define CPUIDLE_FLAG_TLB_FLUSHED	BIT(5) /* idle-state flushes TLBs */
 
 struct cpuidle_device_kobj;
 struct cpuidle_state_kobj;
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..9e6ea8931a52 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -454,6 +454,7 @@ struct dev_links_info {
  * @pm_domain:	Provide callbacks that are executed during system suspend,
  * 		hibernation, system resume and during runtime PM transitions
  * 		along with subsystem-level and driver-level callbacks.
+ * @em_pd:	device's energy model performance domain
  * @pins:	For device pin management.
  *		See Documentation/driver-api/pinctl.rst for details.
  * @msi_list:	Hosts MSI descriptors
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 5a3ce2a24794..6e87225600ae 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 }
 
 u64 dma_direct_get_required_mask(struct device *dev);
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-				  u64 *phys_mask);
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 016b96b384bd..52635e91143b 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 			pgprot_t prot, const void *caller);
 void dma_common_free_remap(void *cpu_addr, size_t size);
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags);
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
 bool dma_free_from_pool(struct device *dev, void *start, size_t size);
 
 int
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index aa9ff9e1c0b3..8aa0c7c2608c 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -49,6 +49,10 @@ struct _ddebug {
 
 
 #if defined(CONFIG_DYNAMIC_DEBUG_CORE)
+
+/* exported for module authors to exercise >control */
+int dynamic_debug_exec_queries(const char *query, const char *modname);
+
 int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 				const char *modname);
 extern int ddebug_remove_module(const char *mod_name);
@@ -105,7 +109,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	static_branch_unlikely(&descriptor.key.dd_key_false)
 #endif
 
-#else /* !HAVE_JUMP_LABEL */
+#else /* !CONFIG_JUMP_LABEL */
 
 #define _DPRINTK_KEY_INIT
 
@@ -117,7 +121,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)
 #endif
 
-#endif
+#endif /* CONFIG_JUMP_LABEL */
 
 #define __dynamic_func_call(id, fmt, func, ...) do {	\
 	DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt);		\
@@ -172,10 +176,11 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 				   KERN_DEBUG, prefix_str, prefix_type,	\
 				   rowsize, groupsize, buf, len, ascii)
 
-#else
+#else /* !CONFIG_DYNAMIC_DEBUG_CORE */
 
 #include <linux/string.h>
 #include <linux/errno.h>
+#include <linux/printk.h>
 
 static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 				    const char *modname)
@@ -210,6 +215,13 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val,
 		print_hex_dump(KERN_DEBUG, prefix_str, prefix_type,	\
 				rowsize, groupsize, buf, len, ascii);	\
 	} while (0)
-#endif
+
+static inline int dynamic_debug_exec_queries(const char *query, const char *modname)
+{
+	pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n");
+	return 0;
+}
+
+#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */
 
 #endif
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 57eac5241303..a97a12bb2c9e 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -8,8 +8,8 @@
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
 /*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they are in this header for use by lib/test_firmware.c only!
+ * This struct is private to the efi-embedded fw implementation.
+ * They are in this header for use by lib/test_firmware.c only!
  */
 struct efi_embedded_fw {
 	struct list_head list;
@@ -18,8 +18,6 @@ struct efi_embedded_fw {
 	size_t length;
 };
 
-extern struct list_head efi_embedded_fw_list;
-
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..159c7476b11b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -110,15 +110,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
 #endif
 
 /**
- * syscall_enter_from_user_mode - Check and handle work before invoking
- *				 a syscall
+ * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
  * @regs:	Pointer to currents pt_regs
- * @syscall:	The syscall number
  *
  * Invoked from architecture specific syscall entry code with interrupts
  * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and the subsequent functions can be
- * instrumented.
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This handles lockdep, RCU (context tracking) and tracing state.
+ *
+ * This is invoked when there is extra architecture specific functionality
+ * to be done between establishing state and handling user mode entry work.
+ */
+void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
+
+/**
+ * syscall_enter_from_user_mode_work - Check and handle work before invoking
+ *				       a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * enabled after invoking syscall_enter_from_user_mode_prepare() and extra
+ * architecture specific work.
  *
  * Returns: The original or a modified syscall number
  *
@@ -127,12 +142,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
  * syscall_set_return_value() first.  If neither of those are called and -1
  * is returned, then the syscall will fail with ENOSYS.
  *
- * The following functionality is handled here:
+ * It handles the following work items:
  *
- *  1) Establish state (lockdep, RCU (context tracking), tracing)
- *  2) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
+ *  1) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
  *     __secure_computing(), trace_sys_enter()
- *  3) Invocation of audit_syscall_entry()
+ *  2) Invocation of audit_syscall_entry()
+ */
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+
+/**
+ * syscall_enter_from_user_mode - Establish state and check and handle work
+ *				  before invoking a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This is combination of syscall_enter_from_user_mode_prepare() and
+ * syscall_enter_from_user_mode_work().
+ *
+ * Returns: The original or a modified syscall number. See
+ * syscall_enter_from_user_mode_work() for further explanation.
  */
 long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0a355b005bf4..ebfb7cfb65f1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1200,7 +1200,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
 		BPF_ANCILLARY(RANDOM);
 		BPF_ANCILLARY(VLAN_TPID);
 		}
-		/* Fallthrough. */
+		fallthrough;
 	default:
 		return ftest->code;
 	}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..7519ae003a08 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2132,6 +2132,10 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
  *
  * I_DONTCACHE		Evict inode as soon as it is not used anymore.
  *
+ * I_SYNC_QUEUED	Inode is queued in b_io or b_more_io writeback lists.
+ *			Used to detect that mark_inode_dirty() should not move
+ * 			inode between dirty lists.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2149,12 +2153,11 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
 #define I_LINKABLE		(1 << 10)
 #define I_DIRTY_TIME		(1 << 11)
-#define __I_DIRTY_TIME_EXPIRED	12
-#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 #define I_WB_SWITCH		(1 << 13)
 #define I_OVL_INUSE		(1 << 14)
 #define I_CREATING		(1 << 15)
 #define I_DONTCACHE		(1 << 16)
+#define I_SYNC_QUEUED		(1 << 17)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 875f71132b14..c7044a14200e 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -959,34 +959,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) {
  * @max: maximal valid usage->code to consider later (out parameter)
  * @type: input event type (EV_KEY, EV_REL, ...)
  * @c: code which corresponds to this usage and type
+ *
+ * The value pointed to by @bit will be set to NULL if either @type is
+ * an unhandled event type, or if @c is out of range for @type. This
+ * can be used as an error condition.
  */
 static inline void hid_map_usage(struct hid_input *hidinput,
 		struct hid_usage *usage, unsigned long **bit, int *max,
-		__u8 type, __u16 c)
+		__u8 type, unsigned int c)
 {
 	struct input_dev *input = hidinput->input;
-
-	usage->type = type;
-	usage->code = c;
+	unsigned long *bmap = NULL;
+	unsigned int limit = 0;
 
 	switch (type) {
 	case EV_ABS:
-		*bit = input->absbit;
-		*max = ABS_MAX;
+		bmap = input->absbit;
+		limit = ABS_MAX;
 		break;
 	case EV_REL:
-		*bit = input->relbit;
-		*max = REL_MAX;
+		bmap = input->relbit;
+		limit = REL_MAX;
 		break;
 	case EV_KEY:
-		*bit = input->keybit;
-		*max = KEY_MAX;
+		bmap = input->keybit;
+		limit = KEY_MAX;
 		break;
 	case EV_LED:
-		*bit = input->ledbit;
-		*max = LED_MAX;
+		bmap = input->ledbit;
+		limit = LED_MAX;
 		break;
 	}
+
+	if (unlikely(c > limit || !bmap)) {
+		pr_warn_ratelimited("%s: Invalid code %d type %d\n",
+				    input->name, c, type);
+		*bit = NULL;
+		return;
+	}
+
+	usage->type = type;
+	usage->code = c;
+	*max = limit;
+	*bit = bmap;
 }
 
 /**
@@ -1000,7 +1015,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput,
 		__u8 type, __u16 c)
 {
 	hid_map_usage(hidinput, usage, bit, max, type, c);
-	clear_bit(c, *bit);
+	if (*bit)
+		clear_bit(usage->code, *bit);
 }
 
 /**
diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h
index d03071732db4..7c522fdd9ea7 100644
--- a/include/linux/i2c-algo-pca.h
+++ b/include/linux/i2c-algo-pca.h
@@ -53,6 +53,20 @@
 #define I2C_PCA_CON_SI		0x08 /* Serial Interrupt */
 #define I2C_PCA_CON_CR		0x07 /* Clock Rate (MASK) */
 
+/**
+ * struct pca_i2c_bus_settings - The configured PCA i2c bus settings
+ * @mode: Configured i2c bus mode
+ * @tlow: Configured SCL LOW period
+ * @thi: Configured SCL HIGH period
+ * @clock_freq: The configured clock frequency
+ */
+struct pca_i2c_bus_settings {
+	int mode;
+	int tlow;
+	int thi;
+	int clock_freq;
+};
+
 struct i2c_algo_pca_data {
 	void 				*data;	/* private low level data */
 	void (*write_byte)		(void *data, int reg, int val);
@@ -64,6 +78,7 @@ struct i2c_algo_pca_data {
 	 * For PCA9665, use the frequency you want here. */
 	unsigned int			i2c_clock;
 	unsigned int			chip;
+	struct pca_i2c_bus_settings		bus_settings;
 };
 
 int i2c_pca_add_bus(struct i2c_adapter *);
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index bd5c55755447..3ed4e8771b64 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -49,17 +49,18 @@ struct irqtrace_events {
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
-  extern void trace_hardirqs_on_prepare(void);
-  extern void trace_hardirqs_off_finish(void);
-  extern void trace_hardirqs_on(void);
-  extern void trace_hardirqs_off(void);
-# define lockdep_hardirq_context()	(this_cpu_read(hardirq_context))
+extern void trace_hardirqs_on_prepare(void);
+extern void trace_hardirqs_off_finish(void);
+extern void trace_hardirqs_on(void);
+extern void trace_hardirqs_off(void);
+
+# define lockdep_hardirq_context()	(raw_cpu_read(hardirq_context))
 # define lockdep_softirq_context(p)	((p)->softirq_context)
 # define lockdep_hardirqs_enabled()	(this_cpu_read(hardirqs_enabled))
 # define lockdep_softirqs_enabled(p)	((p)->softirqs_enabled)
 # define lockdep_hardirq_enter()			\
 do {							\
-	if (this_cpu_inc_return(hardirq_context) == 1)	\
+	if (__this_cpu_inc_return(hardirq_context) == 1)\
 		current->hardirq_threaded = 0;		\
 } while (0)
 # define lockdep_hardirq_threaded()		\
@@ -68,7 +69,7 @@ do {						\
 } while (0)
 # define lockdep_hardirq_exit()			\
 do {						\
-	this_cpu_dec(hardirq_context);		\
+	__this_cpu_dec(hardirq_context);	\
 } while (0)
 # define lockdep_softirq_enter()		\
 do {						\
@@ -120,17 +121,17 @@ do {						\
 #else
 # define trace_hardirqs_on_prepare()		do { } while (0)
 # define trace_hardirqs_off_finish()		do { } while (0)
-# define trace_hardirqs_on()		do { } while (0)
-# define trace_hardirqs_off()		do { } while (0)
-# define lockdep_hardirq_context()	0
-# define lockdep_softirq_context(p)	0
-# define lockdep_hardirqs_enabled()	0
-# define lockdep_softirqs_enabled(p)	0
-# define lockdep_hardirq_enter()	do { } while (0)
-# define lockdep_hardirq_threaded()	do { } while (0)
-# define lockdep_hardirq_exit()		do { } while (0)
-# define lockdep_softirq_enter()	do { } while (0)
-# define lockdep_softirq_exit()		do { } while (0)
+# define trace_hardirqs_on()			do { } while (0)
+# define trace_hardirqs_off()			do { } while (0)
+# define lockdep_hardirq_context()		0
+# define lockdep_softirq_context(p)		0
+# define lockdep_hardirqs_enabled()		0
+# define lockdep_softirqs_enabled(p)		0
+# define lockdep_hardirq_enter()		do { } while (0)
+# define lockdep_hardirq_threaded()		do { } while (0)
+# define lockdep_hardirq_exit()			do { } while (0)
+# define lockdep_softirq_enter()		do { } while (0)
+# define lockdep_softirq_exit()			do { } while (0)
 # define lockdep_hrtimer_enter(__hrtimer)	false
 # define lockdep_hrtimer_exit(__context)	do { } while (0)
 # define lockdep_posixtimer_enter()		do { } while (0)
@@ -181,26 +182,33 @@ do {						\
  * if !TRACE_IRQFLAGS.
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-#define local_irq_enable() \
-	do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0)
-#define local_irq_disable() \
-	do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0)
+
+#define local_irq_enable()				\
+	do {						\
+		trace_hardirqs_on();			\
+		raw_local_irq_enable();			\
+	} while (0)
+
+#define local_irq_disable()				\
+	do {						\
+		bool was_disabled = raw_irqs_disabled();\
+		raw_local_irq_disable();		\
+		if (!was_disabled)			\
+			trace_hardirqs_off();		\
+	} while (0)
+
 #define local_irq_save(flags)				\
 	do {						\
 		raw_local_irq_save(flags);		\
-		trace_hardirqs_off();			\
+		if (!raw_irqs_disabled_flags(flags))	\
+			trace_hardirqs_off();		\
 	} while (0)
 
-
 #define local_irq_restore(flags)			\
 	do {						\
-		if (raw_irqs_disabled_flags(flags)) {	\
-			raw_local_irq_restore(flags);	\
-			trace_hardirqs_off();		\
-		} else {				\
+		if (!raw_irqs_disabled_flags(flags))	\
 			trace_hardirqs_on();		\
-			raw_local_irq_restore(flags);	\
-		}					\
+		raw_local_irq_restore(flags);		\
 	} while (0)
 
 #define safe_halt()				\
@@ -214,10 +222,7 @@ do {						\
 
 #define local_irq_enable()	do { raw_local_irq_enable(); } while (0)
 #define local_irq_disable()	do { raw_local_irq_disable(); } while (0)
-#define local_irq_save(flags)					\
-	do {							\
-		raw_local_irq_save(flags);			\
-	} while (0)
+#define local_irq_save(flags)	do { raw_local_irq_save(flags); } while (0)
 #define local_irq_restore(flags) do { raw_local_irq_restore(flags); } while (0)
 #define safe_halt()		do { raw_safe_halt(); } while (0)
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 4aaa29772bb0..08f904943ab2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1381,7 +1381,7 @@ extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned int, unsigned int);
-extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
+extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
 extern int	 jbd2_journal_stop(handle_t *);
 extern int	 jbd2_journal_flush (journal_t *);
 extern void	 jbd2_journal_lock_updates (journal_t *);
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index 19ddd43aee68..cfb62e9f37be 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -86,17 +86,17 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 	}
 	/* Last block: affect all 32 bits of (c) */
 	switch (length) {
-	case 12: c += (u32)k[11]<<24;	/* fall through */
-	case 11: c += (u32)k[10]<<16;	/* fall through */
-	case 10: c += (u32)k[9]<<8;	/* fall through */
-	case 9:  c += k[8];		/* fall through */
-	case 8:  b += (u32)k[7]<<24;	/* fall through */
-	case 7:  b += (u32)k[6]<<16;	/* fall through */
-	case 6:  b += (u32)k[5]<<8;	/* fall through */
-	case 5:  b += k[4];		/* fall through */
-	case 4:  a += (u32)k[3]<<24;	/* fall through */
-	case 3:  a += (u32)k[2]<<16;	/* fall through */
-	case 2:  a += (u32)k[1]<<8;	/* fall through */
+	case 12: c += (u32)k[11]<<24;	fallthrough;
+	case 11: c += (u32)k[10]<<16;	fallthrough;
+	case 10: c += (u32)k[9]<<8;	fallthrough;
+	case 9:  c += k[8];		fallthrough;
+	case 8:  b += (u32)k[7]<<24;	fallthrough;
+	case 7:  b += (u32)k[6]<<16;	fallthrough;
+	case 6:  b += (u32)k[5]<<8;	fallthrough;
+	case 5:  b += k[4];		fallthrough;
+	case 4:  a += (u32)k[3]<<24;	fallthrough;
+	case 3:  a += (u32)k[2]<<16;	fallthrough;
+	case 2:  a += (u32)k[1]<<8;	fallthrough;
 	case 1:  a += k[0];
 		 __jhash_final(a, b, c);
 	case 0: /* Nothing left to add */
@@ -132,8 +132,8 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval)
 
 	/* Handle the last 3 u32's */
 	switch (length) {
-	case 3: c += k[2];	/* fall through */
-	case 2: b += k[1];	/* fall through */
+	case 3: c += k[2];	fallthrough;
+	case 2: b += k[1];	fallthrough;
 	case 1: a += k[0];
 		__jhash_final(a, b, c);
 	case 0:	/* Nothing left to add */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 500def620d8f..c25b8e41c0ea 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -186,7 +186,7 @@
  * lower_32_bits - return bits 0-31 of a number
  * @n: the number we're accessing
  */
-#define lower_32_bits(n) ((u32)(n))
+#define lower_32_bits(n) ((u32)((n) & 0xffffffff))
 
 struct completion;
 struct pt_regs;
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index e48b1e453ff5..161e8164abcf 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -53,8 +53,6 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
-bool reuse_ksm_page(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
 
 #else  /* !CONFIG_KSM */
 
@@ -88,11 +86,6 @@ static inline void rmap_walk_ksm(struct page *page,
 static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
 }
-static inline bool reuse_ksm_page(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
-{
-	return false;
-}
 #endif /* CONFIG_MMU */
 #endif /* !CONFIG_KSM */
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a23076765b4c..05e3c2fb3ef7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -749,25 +749,46 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
 
-#define __kvm_put_guest(kvm, gfn, offset, value, type)			\
+#define __kvm_get_guest(kvm, gfn, offset, v)				\
 ({									\
 	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
-	type __user *__uaddr = (type __user *)(__addr + offset);	\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
 	int __ret = -EFAULT;						\
 									\
 	if (!kvm_is_error_hva(__addr))					\
-		__ret = put_user(value, __uaddr);			\
+		__ret = get_user(v, __uaddr);				\
+	__ret;								\
+})
+
+#define kvm_get_guest(kvm, gpa, v)					\
+({									\
+	gpa_t __gpa = gpa;						\
+	struct kvm *__kvm = kvm;					\
+									\
+	__kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT,			\
+			offset_in_page(__gpa), v);			\
+})
+
+#define __kvm_put_guest(kvm, gfn, offset, v)				\
+({									\
+	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
+	int __ret = -EFAULT;						\
+									\
+	if (!kvm_is_error_hva(__addr))					\
+		__ret = put_user(v, __uaddr);				\
 	if (!__ret)							\
 		mark_page_dirty(kvm, gfn);				\
 	__ret;								\
 })
 
-#define kvm_put_guest(kvm, gpa, value, type)				\
+#define kvm_put_guest(kvm, gpa, v)					\
 ({									\
 	gpa_t __gpa = gpa;						\
 	struct kvm *__kvm = kvm;					\
+									\
 	__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT,			\
-			offset_in_page(__gpa), (value), type);		\
+			offset_in_page(__gpa), v);			\
 })
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 77ccf040a128..5f550eb27f81 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -421,6 +421,7 @@ enum {
 	ATA_HORKAGE_NO_DMA_LOG	= (1 << 23),	/* don't use DMA for log read */
 	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
 	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
+	ATA_HORKAGE_MAX_TRIM_128M = (1 << 26),	/* Limit max trim size to 128M */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 62a382d1845b..6a584b3e5c74 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -535,19 +535,27 @@ do {									\
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
+/*
+ * The below lockdep_assert_*() macros use raw_cpu_read() to access the above
+ * per-cpu variables. This is required because this_cpu_read() will potentially
+ * call into preempt/irq-disable and that obviously isn't right. This is also
+ * correct because when IRQs are enabled, it doesn't matter if we accidentally
+ * read the value from our previous CPU.
+ */
+
 #define lockdep_assert_irqs_enabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled));	\
 } while (0)
 
 #define lockdep_assert_irqs_disabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled));	\
 } while (0)
 
 #define lockdep_assert_in_irq()						\
 do {									\
-	WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context));	\
+	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context));	\
 } while (0)
 
 #define lockdep_assert_preemption_enabled()				\
@@ -555,7 +563,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     debug_locks			&&		\
 		     (preempt_count() != 0		||		\
-		      !this_cpu_read(hardirqs_enabled)));		\
+		      !raw_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
 #define lockdep_assert_preemption_disabled()				\
@@ -563,7 +571,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     debug_locks			&&		\
 		     (preempt_count() == 0		&&		\
-		      this_cpu_read(hardirqs_enabled)));		\
+		      raw_cpu_read(hardirqs_enabled)));			\
 } while (0)
 
 #else
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 83a4a3ca3e8a..c619ec6eff4a 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -173,7 +173,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define roundup_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 1 :			\
+		((n) == 1) ? 1 :		\
 		(1UL << (ilog2((n) - 1) + 1))	\
 				   ) :		\
 	__roundup_pow_of_two(n)			\
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 5f5b2df06e61..e5862746751b 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -46,11 +46,10 @@ struct vmem_altmap {
  * wakeup is used to coordinate physical address space management (ex:
  * fs truncate/hole punch) vs pinned pages (ex: device dma).
  *
- * MEMORY_DEVICE_DEVDAX:
+ * MEMORY_DEVICE_GENERIC:
  * Host memory that has similar access semantics as System RAM i.e. DMA
- * coherent and supports page pinning. In contrast to
- * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax
- * character device.
+ * coherent and supports page pinning. This is for example used by DAX devices
+ * that expose memory using a character device.
  *
  * MEMORY_DEVICE_PCI_P2PDMA:
  * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
@@ -60,7 +59,7 @@ enum memory_type {
 	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_FS_DAX,
-	MEMORY_DEVICE_DEVDAX,
+	MEMORY_DEVICE_GENERIC,
 	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1983e08f5906..ca6e6a81576b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -157,11 +157,14 @@ static inline void __mm_zero_struct_page(struct page *page)
 
 	switch (sizeof(struct page)) {
 	case 80:
-		_pp[9] = 0;	/* fallthrough */
+		_pp[9] = 0;
+		fallthrough;
 	case 72:
-		_pp[8] = 0;	/* fallthrough */
+		_pp[8] = 0;
+		fallthrough;
 	case 64:
-		_pp[7] = 0;	/* fallthrough */
+		_pp[7] = 0;
+		fallthrough;
 	case 56:
 		_pp[6] = 0;
 		_pp[5] = 0;
@@ -321,6 +324,8 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+#elif defined(CONFIG_PPC)
+# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
 # define VM_GROWSUP	VM_ARCH_1
 #elif defined(CONFIG_IA64)
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index c51a84132d7c..03dee12d2b61 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -3,10 +3,15 @@
 #define _LINUX_MMU_CONTEXT_H
 
 #include <asm/mmu_context.h>
+#include <asm/mmu.h>
 
 /* Architectures that care about IRQ state in switch_mm can override this. */
 #ifndef switch_mm_irqs_off
 # define switch_mm_irqs_off switch_mm
 #endif
 
+#ifndef leave_mm
+static inline void leave_mm(int cpu) { }
+#endif
+
 #endif
diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h
index 9a33f171aa82..625f491b95de 100644
--- a/include/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/linux/netfilter/nf_conntrack_sctp.h
@@ -9,6 +9,8 @@ struct ip_ct_sctp {
 	enum sctp_conntrack state;
 
 	__be32 vtag[IP_CT_DIR_MAX];
+	u8 last_dir;
+	u8 flags;
 };
 
 #endif /* _NF_CONNTRACK_SCTP_H */
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 851425c3178f..89016d08f6a2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -43,8 +43,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group);
 int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
 		   unsigned int group, int echo, gfp_t flags);
 int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
-int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
-		      int flags);
+int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid);
 
 static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type)
 {
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index aac42c28fe62..9b67394471e1 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -58,7 +58,6 @@ struct nf_ipv6_ops {
 			int (*output)(struct net *, struct sock *, struct sk_buff *));
 	int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry);
 #if IS_MODULE(CONFIG_IPV6)
-	int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user);
 	int (*br_fragment)(struct net *net, struct sock *sk,
 			   struct sk_buff *skb,
 			   struct nf_bridge_frag_data *data,
@@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst,
 
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 
-static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb,
-				    u32 user)
-{
-#if IS_MODULE(CONFIG_IPV6)
-	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
-	if (!v6_ops)
-		return 1;
-
-	return v6_ops->br_defrag(net, skb, user);
-#elif IS_BUILTIN(CONFIG_IPV6)
-	return nf_ct_frag6_gather(net, skb, user);
-#else
-	return 1;
-#endif
-}
-
 int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		    struct nf_bridge_frag_data *data,
 		    int (*output)(struct net *, struct sock *sk,
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index a124c21e3204..e8cbc2e795d5 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address)
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
  */
+#ifndef pgd_offset_k
 #define pgd_offset_k(address)		pgd_offset(&init_mm, (address))
+#endif
 
 /*
  * In many cases it is known that a virtual address is mapped at PMD or PTE
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index a8e876317e25..c36fb41a7d90 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs,
  * For most 10GBASE-R, there is no advertisement.
  */
 int pcs_config(struct phylink_pcs *pcs, unsigned int mode,
-	       phy_interface_t interface, const unsigned long *advertising);
+	       phy_interface_t interface, const unsigned long *advertising,
+	       bool permit_pause_to_mac);
 
 /**
  * pcs_an_restart() - restart 802.3z BaseX autonegotiation
diff --git a/include/linux/powercap.h b/include/linux/powercap.h
index 4537f57f9e42..3d557bbcd2c7 100644
--- a/include/linux/powercap.h
+++ b/include/linux/powercap.h
@@ -44,19 +44,18 @@ struct powercap_control_type_ops {
 };
 
 /**
- * struct powercap_control_type- Defines a powercap control_type
- * @name:		name of control_type
+ * struct powercap_control_type - Defines a powercap control_type
  * @dev:		device for this control_type
  * @idr:		idr to have unique id for its child
- * @root_node:		Root holding power zones for this control_type
+ * @nr_zones:		counter for number of zones of this type
  * @ops:		Pointer to callback struct
- * @node_lock:		mutex for control type
+ * @lock:		mutex for control type
  * @allocated:		This is possible that client owns the memory
  *			used by this structure. In this case
  *			this flag is set to false by framework to
  *			prevent deallocation during release process.
  *			Otherwise this flag is set to true.
- * @ctrl_inst:		link to the control_type list
+ * @node:		linked-list node
  *
  * Defines powercap control_type. This acts as a container for power
  * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc.
@@ -129,7 +128,7 @@ struct powercap_zone_ops {
  *			this flag is set to false by framework to
  *			prevent deallocation during release process.
  *			Otherwise this flag is set to true.
- * @constraint_ptr:	List of constraints for this zone.
+ * @constraints:	List of constraints for this zone.
  *
  * This defines a power zone instance. The fields of this structure are
  * private, and should not be used by client drivers.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 93ecd930efd3..afe01e232935 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1666,7 +1666,7 @@ extern struct task_struct *idle_task(int cpu);
  *
  * Return: 1 if @p is an idle task. 0 otherwise.
  */
-static inline bool is_idle_task(const struct task_struct *p)
+static __always_inline bool is_idle_task(const struct task_struct *p)
 {
 	return !!(p->flags & PF_IDLE);
 }
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 917d88edb7b9..a8ec3b6093fc 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -36,6 +36,9 @@ struct user_struct {
     defined(CONFIG_NET) || defined(CONFIG_IO_URING)
 	atomic_long_t locked_vm;
 #endif
+#ifdef CONFIG_WATCH_QUEUE
+	atomic_t nr_watches;	/* The number of watches this user currently has */
+#endif
 
 	/* Miscellaneous per-user rate limit */
 	struct ratelimit_state ratelimit;
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 6bb1a3f0258c..7bbc0e9cf084 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -137,11 +137,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \
 		b3 = b->sig[3]; b2 = b->sig[2];				\
 		r->sig[3] = op(a3, b3);					\
 		r->sig[2] = op(a2, b2);					\
-		/* fall through */					\
+		fallthrough;						\
 	case 2:								\
 		a1 = a->sig[1]; b1 = b->sig[1];				\
 		r->sig[1] = op(a1, b1);					\
-		/* fall through */					\
+		fallthrough;						\
 	case 1:								\
 		a0 = a->sig[0]; b0 = b->sig[0];				\
 		r->sig[0] = op(a0, b0);					\
@@ -171,9 +171,9 @@ static inline void name(sigset_t *set)					\
 	switch (_NSIG_WORDS) {						\
 	case 4:	set->sig[3] = op(set->sig[3]);				\
 		set->sig[2] = op(set->sig[2]);				\
-		/* fall through */					\
+		fallthrough;						\
 	case 2:	set->sig[1] = op(set->sig[1]);				\
-		/* fall through */					\
+		fallthrough;						\
 	case 1:	set->sig[0] = op(set->sig[0]);				\
 		    break;						\
 	default:							\
@@ -194,7 +194,7 @@ static inline void sigemptyset(sigset_t *set)
 		memset(set, 0, sizeof(sigset_t));
 		break;
 	case 2: set->sig[1] = 0;
-		/* fall through */
+		fallthrough;
 	case 1:	set->sig[0] = 0;
 		break;
 	}
@@ -207,7 +207,7 @@ static inline void sigfillset(sigset_t *set)
 		memset(set, -1, sizeof(sigset_t));
 		break;
 	case 2: set->sig[1] = -1;
-		/* fall through */
+		fallthrough;
 	case 1:	set->sig[0] = -1;
 		break;
 	}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 46881d902124..ed9bea924dc3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -71,7 +71,7 @@
  *	NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain
  *			  TCP or UDP packets over IPv6. These are specifically
  *			  unencapsulated packets of the form IPv6|TCP or
- *			  IPv4|UDP where the Next Header field in the IPv6
+ *			  IPv6|UDP where the Next Header field in the IPv6
  *			  header is either TCP or UDP. IPv6 extension headers
  *			  are not supported with this feature. This feature
  *			  cannot be set in features for a device with
@@ -1056,7 +1056,16 @@ void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt);
 void skb_tx_error(struct sk_buff *skb);
+
+#ifdef CONFIG_TRACEPOINTS
 void consume_skb(struct sk_buff *skb);
+#else
+static inline void consume_skb(struct sk_buff *skb)
+{
+	return kfree_skb(skb);
+}
+#endif
+
 void __consume_stateless_skb(struct sk_buff *skb);
 void  __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
@@ -2658,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
  *
  * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS)
  * to reduce average number of cache lines per packet.
- * get_rps_cpus() for example only access one 64 bytes aligned block :
+ * get_rps_cpu() for example only access one 64 bytes aligned block :
  * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8)
  */
 #ifndef NET_SKB_PAD
@@ -3745,19 +3754,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 #define __it(x, op) (x -= sizeof(u##op))
 #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
 	case 32: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case 24: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case 16: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case  8: diffs |= __it_diff(a, b, 64);
 		break;
 	case 28: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case 20: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case 12: diffs |= __it_diff(a, b, 64);
-		 /* fall through */
+		fallthrough;
 	case  4: diffs |= __it_diff(a, b, 32);
 		break;
 	}
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 49c5d29cd33c..cf27b080e148 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -220,6 +220,9 @@ struct ti_sci_rm_core_ops {
 				    u16 *range_start, u16 *range_num);
 };
 
+#define TI_SCI_RESASG_SUBTYPE_IR_OUTPUT		0
+#define TI_SCI_RESASG_SUBTYPE_IA_VINT		0xa
+#define TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT	0xd
 /**
  * struct ti_sci_rm_irq_ops: IRQ management operations
  * @set_irq:		Set an IRQ route between the requested source
@@ -556,6 +559,9 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res);
 struct ti_sci_resource *
 devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle,
 			    struct device *dev, u32 dev_id, char *of_prop);
+struct ti_sci_resource *
+devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev,
+			 u32 dev_id, u32 sub_type);
 
 #else	/* CONFIG_TI_SCI_PROTOCOL */
 
@@ -609,6 +615,13 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle,
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline struct ti_sci_resource *
+devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev,
+			 u32 dev_id, u32 sub_type);
+{
+	return ERR_PTR(-EINVAL);
+}
 #endif	/* CONFIG_TI_SCI_PROTOCOL */
 
 #endif	/* __TISCI_PROTOCOL_H */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 2e6ca53b9bbd..18e75974d4e3 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
 		PGREFILL,
+		PGREUSE,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
 		PGSCAN_KSWAPD,
diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index adcc6a97db61..143568d64b20 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -308,7 +308,7 @@ do {									     \
 									     \
   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):			     \
     R##_e = X##_e;							     \
-	  /* Fall through */						     \
+	fallthrough;							     \
   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):			     \
   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):				     \
   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):				     \
@@ -319,7 +319,7 @@ do {									     \
 									     \
   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):			     \
     R##_e = Y##_e;							     \
-	  /* Fall through */						     \
+	fallthrough;							     \
   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):			     \
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):				     \
   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):				     \
@@ -417,7 +417,7 @@ do {							\
   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):		\
   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):		\
     R##_s = X##_s;					\
-	/* Fall through */				\
+	  fallthrough;					\
 							\
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):		\
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\
@@ -431,7 +431,7 @@ do {							\
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):		\
   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):		\
     R##_s = Y##_s;					\
-	/* Fall through */				\
+	  fallthrough;					\
 							\
   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):	\
   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\
@@ -497,7 +497,7 @@ do {							\
 							\
   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\
     FP_SET_EXCEPTION(FP_EX_DIVZERO);			\
-	  /* Fall through */				\
+	fallthrough;					\
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):		\
   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\
     R##_c = FP_CLS_INF;					\
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index ba3f6c15ad2b..18f783dcd55f 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -97,7 +97,8 @@ bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
 
 int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev);
 
-struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr);
+struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr,
+				 struct net_device *dev);
 
 struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net,
 				     const struct in6_addr *addr,
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 91eacbdcf33d..f6abcc0bbd6e 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
-u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *);
+bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 9205a76d967a..38e4094960ce 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -494,7 +494,7 @@ int igmp6_event_report(struct sk_buff *skb);
 
 #ifdef CONFIG_SYSCTL
 int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write,
-			       void __user *buffer, size_t *lenp, loff_t *ppos);
+			       void *buffer, size_t *lenp, loff_t *ppos);
 int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl,
 				 void __user *oldval, size_t __user *oldlenp,
 				 void __user *newval, size_t newlen);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index bf9491b77d16..224d194ad29d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -143,6 +143,8 @@ static inline u64 nft_reg_load64(const u32 *sreg)
 static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
 				 unsigned int len)
 {
+	if (len % NFT_REG32_SIZE)
+		dst[len / NFT_REG32_SIZE] = 0;
 	memcpy(dst, src, len);
 }
 
diff --git a/include/soc/nps/common.h b/include/soc/nps/common.h
index 9b1d43d671a3..8c18dc6d3fde 100644
--- a/include/soc/nps/common.h
+++ b/include/soc/nps/common.h
@@ -45,6 +45,12 @@
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST	0x5B60
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM	0x00010422
 
+#ifndef AUX_IENABLE
+#define AUX_IENABLE				0x40c
+#endif
+
+#define CTOP_AUX_IACK				(0xFFFFF800 + 0x088)
+
 #ifndef __ASSEMBLY__
 
 /* In order to increase compilation test coverage */
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index cc41d692ae8e..4c8b99ec8606 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -746,24 +746,29 @@ TRACE_EVENT(ext4_mb_release_group_pa,
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
 
-	TP_ARGS(inode),
+	TP_ARGS(inode, len, needed),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	unsigned int,	len		)
+		__field(	unsigned int,	needed		)
 
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
+		__entry->len	= len;
+		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %d,%d ino %lu",
+	TP_printk("dev %d,%d ino %lu len: %u needed %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino)
+		  (unsigned long) __entry->ino, __entry->len,
+		  __entry->needed)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
@@ -1312,18 +1317,34 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load,
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load,
+DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
 
 	TP_PROTO(struct super_block *sb, unsigned long group),
 
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
+TRACE_EVENT(ext4_read_block_bitmap_load,
+	TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch),
 
-	TP_PROTO(struct super_block *sb, unsigned long group),
+	TP_ARGS(sb, group, prefetch),
 
-	TP_ARGS(sb, group)
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	bool,	prefetch		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->prefetch = prefetch;
+	),
+
+	TP_printk("dev %d,%d group %u prefetch %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->prefetch)
 );
 
 TRACE_EVENT(ext4_direct_IO_enter,
@@ -2726,6 +2747,50 @@ TRACE_EVENT(ext4_error,
 		  __entry->function, __entry->line)
 );
 
+TRACE_EVENT(ext4_prefetch_bitmaps,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group,
+		     ext4_group_t next, unsigned int prefetch_ios),
+
+	TP_ARGS(sb, group, next, prefetch_ios),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	__u32,	next			)
+		__field(	__u32,	ios			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->next	= next;
+		__entry->ios	= prefetch_ios;
+	),
+
+	TP_printk("dev %d,%d group %u next %u ios %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->next, __entry->ios)
+);
+
+TRACE_EVENT(ext4_lazy_itable_init,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group),
+
+	TP_ARGS(sb, group),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %d,%d group %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 939092dbcb8b..5fb752034386 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -114,6 +114,8 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 
 #if defined(CONFIG_X86)
 #define __VM_ARCH_SPECIFIC_1 {VM_PAT,     "pat"           }
+#elif defined(CONFIG_PPC)
+#define __VM_ARCH_SPECIFIC_1 {VM_SAO,     "sao"           }
 #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64)
 #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP,	"growsup"	}
 #elif !defined(CONFIG_MMU)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 059b6e45a028..c33079b986e8 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -138,11 +138,16 @@ enum rxrpc_recvmsg_trace {
 };
 
 enum rxrpc_rtt_tx_trace {
+	rxrpc_rtt_tx_cancel,
 	rxrpc_rtt_tx_data,
+	rxrpc_rtt_tx_no_slot,
 	rxrpc_rtt_tx_ping,
 };
 
 enum rxrpc_rtt_rx_trace {
+	rxrpc_rtt_rx_cancel,
+	rxrpc_rtt_rx_lost,
+	rxrpc_rtt_rx_obsolete,
 	rxrpc_rtt_rx_ping_response,
 	rxrpc_rtt_rx_requested_ack,
 };
@@ -339,10 +344,15 @@ enum rxrpc_tx_point {
 	E_(rxrpc_recvmsg_wait,			"WAIT")
 
 #define rxrpc_rtt_tx_traces \
+	EM(rxrpc_rtt_tx_cancel,			"CNCE") \
 	EM(rxrpc_rtt_tx_data,			"DATA") \
+	EM(rxrpc_rtt_tx_no_slot,		"FULL") \
 	E_(rxrpc_rtt_tx_ping,			"PING")
 
 #define rxrpc_rtt_rx_traces \
+	EM(rxrpc_rtt_rx_cancel,			"CNCL") \
+	EM(rxrpc_rtt_rx_obsolete,		"OBSL") \
+	EM(rxrpc_rtt_rx_lost,			"LOST") \
 	EM(rxrpc_rtt_rx_ping_response,		"PONG") \
 	E_(rxrpc_rtt_rx_requested_ack,		"RACK")
 
@@ -1087,38 +1097,43 @@ TRACE_EVENT(rxrpc_recvmsg,
 
 TRACE_EVENT(rxrpc_rtt_tx,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_tx_trace why,
-		     rxrpc_serial_t send_serial),
+		     int slot, rxrpc_serial_t send_serial),
 
-	    TP_ARGS(call, why, send_serial),
+	    TP_ARGS(call, why, slot, send_serial),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_tx_trace,	why		)
+		    __field(int,			slot		)
 		    __field(rxrpc_serial_t,		send_serial	)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call = call->debug_id;
 		    __entry->why = why;
+		    __entry->slot = slot;
 		    __entry->send_serial = send_serial;
 			   ),
 
-	    TP_printk("c=%08x %s sr=%08x",
+	    TP_printk("c=%08x [%d] %s sr=%08x",
 		      __entry->call,
+		      __entry->slot,
 		      __print_symbolic(__entry->why, rxrpc_rtt_tx_traces),
 		      __entry->send_serial)
 	    );
 
 TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+		     int slot,
 		     rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
 		     u32 rtt, u32 rto),
 
-	    TP_ARGS(call, why, send_serial, resp_serial, rtt, rto),
+	    TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_rx_trace,	why		)
+		    __field(int,			slot		)
 		    __field(rxrpc_serial_t,		send_serial	)
 		    __field(rxrpc_serial_t,		resp_serial	)
 		    __field(u32,			rtt		)
@@ -1128,14 +1143,16 @@ TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_fast_assign(
 		    __entry->call = call->debug_id;
 		    __entry->why = why;
+		    __entry->slot = slot;
 		    __entry->send_serial = send_serial;
 		    __entry->resp_serial = resp_serial;
 		    __entry->rtt = rtt;
 		    __entry->rto = rto;
 			   ),
 
-	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u",
+	    TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u",
 		      __entry->call,
+		      __entry->slot,
 		      __print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
 		      __entry->send_serial,
 		      __entry->resp_serial,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 10f5d1fa7347..e7cbccc7c14c 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -20,7 +20,6 @@
 		{I_CLEAR,		"I_CLEAR"},		\
 		{I_SYNC,		"I_SYNC"},		\
 		{I_DIRTY_TIME,		"I_DIRTY_TIME"},	\
-		{I_DIRTY_TIME_EXPIRED,	"I_DIRTY_TIME_EXPIRED"}, \
 		{I_REFERENCED,		"I_REFERENCED"}		\
 	)
 
@@ -498,8 +497,9 @@ DEFINE_WBC_EVENT(wbc_writepage);
 TRACE_EVENT(writeback_queue_io,
 	TP_PROTO(struct bdi_writeback *wb,
 		 struct wb_writeback_work *work,
+		 unsigned long dirtied_before,
 		 int moved),
-	TP_ARGS(wb, work, moved),
+	TP_ARGS(wb, work, dirtied_before, moved),
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
 		__field(unsigned long,	older)
@@ -509,19 +509,17 @@ TRACE_EVENT(writeback_queue_io,
 		__field(ino_t,		cgroup_ino)
 	),
 	TP_fast_assign(
-		unsigned long *older_than_this = work->older_than_this;
 		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
-		__entry->older	= older_than_this ?  *older_than_this : 0;
-		__entry->age	= older_than_this ?
-				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->older	= dirtied_before;
+		__entry->age	= (jiffies - dirtied_before) * 1000 / HZ;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu",
 		__entry->name,
-		__entry->older,	/* older_than_this in jiffies */
-		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->older,	/* dirtied_before in jiffies */
+		__entry->age,	/* dirtied_before in relative milliseconds */
 		__entry->moved,
 		__print_symbolic(__entry->reason, WB_WORK_REASON),
 		(unsigned long)__entry->cgroup_ino
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 3218576e109d..c5ff2b275fcd 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -673,6 +673,7 @@ struct drm_amdgpu_cs_chunk_data {
  */
 #define AMDGPU_IDS_FLAGS_FUSION         0x1
 #define AMDGPU_IDS_FLAGS_PREEMPTION     0x2
+#define AMDGPU_IDS_FLAGS_TMZ            0x4
 
 /* indicate if acceleration can be working */
 #define AMDGPU_INFO_ACCEL_WORKING		0x00
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 00546062e023..fa1f3d62f9a6 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_PERF_REVISION	54
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1046,6 +1052,38 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+	struct i915_user_extension base;
+
+	/**
+	 * Number of element in the handles_ptr & value_ptr arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
+	 * fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * Pointer to an array of u64 values of length fence_count. Values
+	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 */
+	__u64 values_ptr;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -1062,8 +1100,14 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 num_cliprects;
 	/**
 	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
-	 * struct drm_i915_gem_exec_fence *fences.
+	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+	 * of the array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single struct i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (0x3f)
@@ -1181,7 +1225,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_SUBMIT		(1 << 20)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0480f893facd..b6238b2209b7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 3d0d8231dc19..7d6687618d80 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -135,7 +135,7 @@ struct in_addr {
  * this socket to prevent accepting spoofed ones.
  */
 #define IP_PMTUDISC_INTERFACE		4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
  * fragmented if they exeed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index f738c3b53f4e..695b606da4b1 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -449,8 +449,15 @@ struct kfd_ioctl_import_dmabuf_args {
 /*
  * KFD SMI(System Management Interface) events
  */
-/* Event type (defined by bitmask) */
-#define KFD_SMI_EVENT_VMFAULT     0x0000000000000001
+enum kfd_smi_event {
+	KFD_SMI_EVENT_NONE = 0, /* not used */
+	KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
+	KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
+	KFD_SMI_EVENT_GPU_POST_RESET = 4,
+};
+
+#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6d86033c4fa..7d8eced6f459 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 42f351c1f5c5..2b8e12f7a4a6 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -133,7 +133,7 @@ enum nf_tables_msg_types {
  * @NFTA_LIST_ELEM: list element (NLA_NESTED)
  */
 enum nft_list_attributes {
-	NFTA_LIST_UNPEC,
+	NFTA_LIST_UNSPEC,
 	NFTA_LIST_ELEM,
 	__NFTA_LIST_MAX
 };
diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h
index d7f6af50e200..39df751d0dc4 100644
--- a/include/xen/arm/page.h
+++ b/include/xen/arm/page.h
@@ -76,7 +76,11 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn)
 #define bfn_to_local_pfn(bfn)	bfn_to_pfn(bfn)
 
 /* VIRT <-> GUEST conversion */
-#define virt_to_gfn(v)		(pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT))
+#define virt_to_gfn(v)                                                         \
+	({                                                                     \
+		WARN_ON_ONCE(!virt_addr_valid(v));                              \
+		pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT);                 \
+	})
 #define gfn_to_virt(m)		(__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT))
 
 /* Only used in PV code. But ARM guests are always HVM. */
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index 6fb95aa19405..6dbdb0b3fd03 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -2,6 +2,8 @@
 /******************************************************************************
  * Xen balloon functionality
  */
+#ifndef _XEN_BALLOON_H
+#define _XEN_BALLOON_H
 
 #define RETRY_UNLIMITED	0
 
@@ -34,3 +36,5 @@ static inline void xen_balloon_init(void)
 {
 }
 #endif
+
+#endif	/* _XEN_BALLOON_H */
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 19a72f591e2b..43efba045acc 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -52,4 +52,13 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 extern u64 xen_saved_max_mem_size;
 #endif
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+#else
+#define xen_alloc_unpopulated_pages alloc_xenballooned_pages
+#define xen_free_unpopulated_pages free_xenballooned_pages
+#include <xen/balloon.h>
+#endif
+
 #endif	/* _XEN_XEN_H */
diff --git a/init/initramfs.c b/init/initramfs.c
index e6dbfb767057..1f97c0328a7a 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -297,7 +297,7 @@ static void __init clean_path(char *path, umode_t fmode)
 {
 	struct kstat st;
 
-	if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
+	if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
 	    (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
 			init_rmdir(path);
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index d1b8644bfb88..3f312bf2b116 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -85,7 +85,7 @@ static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 }
 
 static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
+	void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, semmni;
 	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
diff --git a/ipc/sem.c b/ipc/sem.c
index 8c0244e0365e..f6c30a85dadf 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1691,7 +1691,7 @@ static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int v
 	case IPC_SET:
 		if (copy_semid_from_user(&semid64, p, version))
 			return -EFAULT;
-		/* fall through */
+		fallthrough;
 	case IPC_RMID:
 		return semctl_down(ns, semid, cmd, &semid64);
 	default:
@@ -1805,7 +1805,7 @@ static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int vers
 	case IPC_SET:
 		if (copy_compat_semid_from_user(&semid64, p, version))
 			return -EFAULT;
-		/* fallthru */
+		fallthrough;
 	case IPC_RMID:
 		return semctl_down(ns, semid, cmd, &semid64);
 	default:
diff --git a/ipc/shm.c b/ipc/shm.c
index f1ed36e3ac9f..e25c7c6106bc 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1179,7 +1179,7 @@ static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int ver
 	case IPC_SET:
 		if (copy_shmid_from_user(&sem64, buf, version))
 			return -EFAULT;
-		/* fallthru */
+		fallthrough;
 	case IPC_RMID:
 		return shmctl_down(ns, shmid, cmd, &sem64);
 	case SHM_LOCK:
@@ -1374,7 +1374,7 @@ static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int versio
 	case IPC_SET:
 		if (copy_compat_shmid_from_user(&sem64, uptr, version))
 			return -EFAULT;
-		/* fallthru */
+		fallthrough;
 	case IPC_RMID:
 		return shmctl_down(ns, shmid, cmd, &sem64);
 	case SHM_LOCK:
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a10e2997aa6c..333b3bcfc545 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -681,7 +681,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 				data->values[i] = AUDIT_UID_UNSET;
 				break;
 			}
-			/* fall through - if set */
+			fallthrough;	/* if set */
 		default:
 			data->values[i] = f->val;
 		}
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index b6715964b685..8faa2ce89396 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq)
 	iter_priv->done_stop = true;
 }
 
+/* maximum visited objects before bailing out */
+#define MAX_ITER_OBJECTS	1000000
+
 /* bpf_seq_read, a customized and simpler version for bpf iterator.
  * no_llseek is assumed for this file.
  * The following are differences from seq_read():
@@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 {
 	struct seq_file *seq = file->private_data;
 	size_t n, offs, copied = 0;
-	int err = 0;
+	int err = 0, num_objs = 0;
 	void *p;
 
 	mutex_lock(&seq->lock);
@@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 	while (1) {
 		loff_t pos = seq->index;
 
+		num_objs++;
 		offs = seq->count;
 		p = seq->op->next(seq, p, &seq->index);
 		if (pos == seq->index) {
@@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 		if (seq->count >= size)
 			break;
 
+		if (num_objs >= MAX_ITER_OBJECTS) {
+			if (offs == 0) {
+				err = -EAGAIN;
+				seq->op->stop(seq, p);
+				goto done;
+			}
+			break;
+		}
+
 		err = seq->op->show(seq, p);
 		if (err > 0) {
 			bpf_iter_dec_seq_num(seq);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 83ff127ef7ae..e21de4f1754c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1794,7 +1794,7 @@ static bool cg_sockopt_is_valid_access(int off, int size,
 			return prog->expected_attach_type ==
 				BPF_CGROUP_GETSOCKOPT;
 		case offsetof(struct bpf_sockopt, optname):
-			/* fallthrough */
+			fallthrough;
 		case offsetof(struct bpf_sockopt, level):
 			if (size != size_default)
 				return false;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index f1c46529929b..6386b7bb98f2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -279,7 +279,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 			break;
 		default:
 			bpf_warn_invalid_xdp_action(act);
-			/* fallthrough */
+			fallthrough;
 		case XDP_DROP:
 			xdp_return_frame(xdpf);
 			stats->drop++;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 4fd830a62be2..cfed0ac44d38 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr,
 
 	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 
@@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr,
 
 	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 86299a292214..b999e7ff2583 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2029,7 +2029,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -2634,7 +2634,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 	u32 ulen = info->raw_tracepoint.tp_name_len;
 	size_t tp_len = strlen(tp_name);
 
-	if (ulen && !ubuf)
+	if (!ulen ^ !ubuf)
 		return -EINVAL;
 
 	info->raw_tracepoint.tp_name_len = tp_len + 1;
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 232df29793e9..99af4cea1102 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
 
 	rcu_read_lock();
 retry:
-	pid = idr_get_next(&ns->idr, tid);
+	pid = find_ge_pid(*tid, ns);
 	if (pid) {
+		*tid = pid_nr_ns(pid, ns);
 		task = get_pid_task(pid, PIDTYPE_PID);
 		if (!task) {
 			++*tid;
@@ -178,10 +179,11 @@ again:
 		f = fcheck_files(curr_files, curr_fd);
 		if (!f)
 			continue;
+		if (!get_file_rcu(f))
+			continue;
 
 		/* set info->fd */
 		info->fd = curr_fd;
-		get_file(f);
 		rcu_read_unlock();
 		return f;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ef938f17b944..47e74f09fa37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5236,7 +5236,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 				off_reg == dst_reg ? dst : src);
 			return -EACCES;
 		}
-		/* fall-through */
+		fallthrough;
 	default:
 		break;
 	}
@@ -10988,7 +10988,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	default:
 		if (!prog_extension)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
 	case BPF_MODIFY_RETURN:
 	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
diff --git a/kernel/capability.c b/kernel/capability.c
index 1444f3954d75..7c59b096c98a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -93,7 +93,7 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
 		break;
 	case _LINUX_CAPABILITY_VERSION_2:
 		warn_deprecated_v2();
-		/* fall through - v3 is otherwise equivalent to v2. */
+		fallthrough;	/* v3 is otherwise equivalent to v2 */
 	case _LINUX_CAPABILITY_VERSION_3:
 		*tocopy = _LINUX_CAPABILITY_U32S_3;
 		break;
diff --git a/kernel/compat.c b/kernel/compat.c
index b8d2800bb4b7..05adfd6fa8bf 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -255,11 +255,11 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat)
 		return -EFAULT;
 	switch (_NSIG_WORDS) {
 	case 4: set->sig[3] = v.sig[6] | (((long)v.sig[7]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 3: set->sig[2] = v.sig[4] | (((long)v.sig[5]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 2: set->sig[1] = v.sig[2] | (((long)v.sig[3]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 1: set->sig[0] = v.sig[0] | (((long)v.sig[1]) << 32 );
 	}
 #else
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index a790026e42d0..cc3c43dfec44 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -1046,14 +1046,14 @@ int gdb_serial_stub(struct kgdb_state *ks)
 				return DBG_PASS_EVENT;
 			}
 #endif
-			/* Fall through */
+			fallthrough;
 		case 'C': /* Exception passing */
 			tmp = gdb_cmd_exception_pass(ks);
 			if (tmp > 0)
 				goto default_handle;
 			if (tmp == 0)
 				break;
-			/* Fall through - on tmp < 0 */
+			fallthrough;	/* on tmp < 0 */
 		case 'c': /* Continue packet */
 		case 's': /* Single step packet */
 			if (kgdb_contthread && kgdb_contthread != current) {
@@ -1062,7 +1062,7 @@ int gdb_serial_stub(struct kgdb_state *ks)
 				break;
 			}
 			dbg_activate_sw_breakpoints();
-			/* Fall through - to default processing */
+			fallthrough;	/* to default processing */
 		default:
 default_handle:
 			error = kgdb_arch_handle_exception(ks->ex_vector,
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index 750497b0003a..f877a0a0d7cf 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -173,11 +173,11 @@ int kdb_get_kbd_char(void)
 	case KT_LATIN:
 		if (isprint(keychar))
 			break;		/* printable characters */
-		/* fall through */
+		fallthrough;
 	case KT_SPEC:
 		if (keychar == K_ENTER)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		return -1;	/* ignore unprintables */
 	}
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 004c5b6c87f8..6226502ce049 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
@@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getword: bad width %ld\n", (long) size);
@@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size)
 			diag = kdb_putarea(addr, w8);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_putword: bad width %ld\n", (long) size);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index bb0041e99659..db6ef07aec3b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
 
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 				  u64 *phys_limit)
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
@@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
@@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
-		ret = dma_alloc_from_pool(dev, size, &page, gfp);
-		if (!ret)
+		u64 phys_mask;
+
+		gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+				&phys_mask);
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
 			return NULL;
 		goto done;
 	}
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 6bc74a2d5127..1281c0f0442b 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -3,7 +3,9 @@
  * Copyright (C) 2012 ARM Ltd.
  * Copyright (C) 2020 Google LLC
  */
+#include <linux/cma.h>
 #include <linux/debugfs.h>
+#include <linux/dma-contiguous.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/init.h>
@@ -55,11 +57,34 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
 		pool_size_kernel += size;
 }
 
+static bool cma_in_zone(gfp_t gfp)
+{
+	unsigned long size;
+	phys_addr_t end;
+	struct cma *cma;
+
+	cma = dev_get_cma_area(NULL);
+	if (!cma)
+		return false;
+
+	size = cma_get_size(cma);
+	if (!size)
+		return false;
+
+	/* CMA can't cross zone boundaries, see cma_activate_area() */
+	end = cma_get_base(cma) + size - 1;
+	if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+		return end <= DMA_BIT_MASK(zone_dma_bits);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+		return end <= DMA_BIT_MASK(32);
+	return true;
+}
+
 static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 			      gfp_t gfp)
 {
 	unsigned int order;
-	struct page *page;
+	struct page *page = NULL;
 	void *addr;
 	int ret = -ENOMEM;
 
@@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
-		page = alloc_pages(gfp, order);
+		if (cma_in_zone(gfp))
+			page = dma_alloc_from_contiguous(NULL, 1 << order,
+							 order, false);
+		if (!page)
+			page = alloc_pages(gfp, order);
 	} while (!page && order-- > 0);
 	if (!page)
 		goto out;
@@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void)
 }
 postcore_initcall(dma_atomic_pool_init);
 
-static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev)
+static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
 {
-	u64 phys_mask;
-	gfp_t gfp;
-
-	gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-					  &phys_mask);
-	if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA)
+	if (prev == NULL) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+			return atomic_pool_dma32;
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+			return atomic_pool_dma;
+		return atomic_pool_kernel;
+	}
+	if (prev == atomic_pool_kernel)
+		return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
+	if (prev == atomic_pool_dma32)
 		return atomic_pool_dma;
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32)
-		return atomic_pool_dma32;
-	return atomic_pool_kernel;
+	return NULL;
 }
 
-static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool)
+static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
+		struct gen_pool *pool, void **cpu_addr,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
-	if (bad_pool == atomic_pool_kernel)
-		return atomic_pool_dma32 ? : atomic_pool_dma;
+	unsigned long addr;
+	phys_addr_t phys;
 
-	if (bad_pool == atomic_pool_dma32)
-		return atomic_pool_dma;
+	addr = gen_pool_alloc(pool, size);
+	if (!addr)
+		return NULL;
 
-	return NULL;
-}
+	phys = gen_pool_virt_to_phys(pool, addr);
+	if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) {
+		gen_pool_free(pool, addr, size);
+		return NULL;
+	}
 
-static inline struct gen_pool *dma_guess_pool(struct device *dev,
-					      struct gen_pool *bad_pool)
-{
-	if (bad_pool)
-		return dma_get_safer_pool(bad_pool);
+	if (gen_pool_avail(pool) < atomic_pool_size)
+		schedule_work(&atomic_pool_work);
 
-	return dma_guess_pool_from_device(dev);
+	*cpu_addr = (void *)addr;
+	memset(*cpu_addr, 0, size);
+	return pfn_to_page(__phys_to_pfn(phys));
 }
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags)
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t gfp,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
 	struct gen_pool *pool = NULL;
-	unsigned long val = 0;
-	void *ptr = NULL;
-	phys_addr_t phys;
-
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool) {
-			WARN(1, "Failed to get suitable pool for %s\n",
-			     dev_name(dev));
-			break;
-		}
-
-		val = gen_pool_alloc(pool, size);
-		if (!val)
-			continue;
-
-		phys = gen_pool_virt_to_phys(pool, val);
-		if (dma_coherent_ok(dev, phys, size))
-			break;
-
-		gen_pool_free(pool, val, size);
-		val = 0;
-	}
-
-
-	if (val) {
-		*ret_page = pfn_to_page(__phys_to_pfn(phys));
-		ptr = (void *)val;
-		memset(ptr, 0, size);
+	struct page *page;
 
-		if (gen_pool_avail(pool) < atomic_pool_size)
-			schedule_work(&atomic_pool_work);
+	while ((pool = dma_guess_pool(pool, gfp))) {
+		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+					     phys_addr_ok);
+		if (page)
+			return page;
 	}
 
-	return ptr;
+	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	return NULL;
 }
 
 bool dma_free_from_pool(struct device *dev, void *start, size_t size)
 {
 	struct gen_pool *pool = NULL;
 
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool)
-			return false;
-
-		if (gen_pool_has_addr(pool, (unsigned long)start, size)) {
-			gen_pool_free(pool, (unsigned long)start, size);
-			return true;
-		}
+	while ((pool = dma_guess_pool(pool, 0))) {
+		if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+			continue;
+		gen_pool_free(pool, (unsigned long)start, size);
+		return true;
 	}
+
+	return false;
 }
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 9852e0d62d95..18683598edbc 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -65,25 +65,49 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 
 	syscall_enter_audit(regs, syscall);
 
-	return ret ? : syscall;
+	/* The above might have changed the syscall number */
+	return ret ? : syscall_get_nr(current, regs);
 }
 
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+static __always_inline long
+__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
 	unsigned long ti_work;
 
-	enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	local_irq_enable();
 	ti_work = READ_ONCE(current_thread_info()->flags);
 	if (ti_work & SYSCALL_ENTER_WORK)
 		syscall = syscall_trace_enter(regs, syscall, ti_work);
-	instrumentation_end();
 
 	return syscall;
 }
 
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	return __syscall_enter_from_user_work(regs, syscall);
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = __syscall_enter_from_user_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
+}
+
 /**
  * exit_to_user_mode - Fixup state when exiting to user mode
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5bfe8e3c6e44..7ed5248f0445 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10034,7 +10034,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 		case IF_SRC_KERNELADDR:
 		case IF_SRC_KERNEL:
 			kernel = 1;
-			/* fall through */
+			fallthrough;
 
 		case IF_SRC_FILEADDR:
 		case IF_SRC_FILE:
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 649fd53dc9ad..0e18aaf23a7b 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 		try_to_free_swap(old_page);
 	page_vma_mapped_walk_done(&pvmw);
 
-	if (vma->vm_flags & VM_LOCKED)
+	if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page))
 		munlock_vma_page(old_page);
 	put_page(old_page);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 4d32190861bd..49677d668de4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3014,7 +3014,7 @@ int unshare_files(struct files_struct **displaced)
 }
 
 int sysctl_max_threads(struct ctl_table *table, int write,
-		       void __user *buffer, size_t *lenp, loff_t *ppos)
+		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int ret;
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 908fdf5098c3..53c67c87f141 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -19,7 +19,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if (__GNUC__ >= 7)
+#if (__GNUC__ >= 10)
+#define GCOV_COUNTERS			8
+#elif (__GNUC__ >= 7)
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a8e14c80b405..762a928e18f9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -173,7 +173,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
 
 			__irq_wake_thread(desc, action);
 
-			/* Fall through - to add to randomness */
+			fallthrough;	/* to add to randomness */
 		case IRQ_HANDLED:
 			*flags |= action->flags;
 			break;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 52ac5391dcc6..5df903fccb60 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -271,7 +271,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(desc->irq_common_data.affinity, mask);
-		/* fall through */
+		fallthrough;
 	case IRQ_SET_MASK_OK_NOCOPY:
 		irq_validate_effective_affinity(data);
 		irq_set_thread_affinity(desc);
@@ -868,7 +868,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
 	case IRQ_SET_MASK_OK_DONE:
 		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
 		irqd_set(&desc->irq_data, flags);
-		/* fall through */
+		fallthrough;
 
 	case IRQ_SET_MASK_OK_NOCOPY:
 		flags = irqd_get_trigger_type(&desc->irq_data);
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 30cc217b8631..651a4ad6d711 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -380,6 +380,13 @@ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
 	unsigned int cpu, bit;
 	struct cpumap *cm;
 
+	/*
+	 * Not required in theory, but matrix_find_best_cpu() uses
+	 * for_each_cpu() which ignores the cpumask on UP .
+	 */
+	if (cpumask_empty(msk))
+		return -EINVAL;
+
 	cpu = matrix_find_best_cpu(m, msk);
 	if (cpu == UINT_MAX)
 		return -ENOSPC;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 95cb74f73292..4fb15fa96734 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -684,12 +684,12 @@ bool kallsyms_show_value(const struct cred *cred)
 	case 0:
 		if (kallsyms_for_perf())
 			return true;
-	/* fallthrough */
+		fallthrough;
 	case 1:
 		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
 				     CAP_OPT_NOAUDIT) == 0)
 			return true;
-	/* fallthrough */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 2fad21d345b0..54b74fabf40c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3756,7 +3756,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 
 skip_checks:
 	/* we'll do an OFF -> ON transition: */
-	this_cpu_write(hardirqs_enabled, 1);
+	__this_cpu_write(hardirqs_enabled, 1);
 	trace->hardirq_enable_ip = ip;
 	trace->hardirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(hardirqs_on_events);
@@ -3795,7 +3795,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		this_cpu_write(hardirqs_enabled, 0);
+		__this_cpu_write(hardirqs_enabled, 0);
 		trace->hardirq_disable_ip = ip;
 		trace->hardirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
@@ -4977,6 +4977,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
 	if (unlikely(current->lockdep_recursion)) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
@@ -5001,7 +5003,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	check_flags(flags);
 
 	current->lockdep_recursion++;
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -5013,13 +5014,15 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_release(lock, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
+
 	current->lockdep_recursion++;
-	trace_lock_release(lock, ip);
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -5205,8 +5208,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip);
-
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -5225,6 +5226,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_acquired(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -5234,7 +5237,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion++;
-	trace_lock_contended(lock, ip);
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5245,6 +5247,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_contended(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
diff --git a/kernel/padata.c b/kernel/padata.c
index 16cb894dc272..d4d3ba6e1728 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -215,12 +215,13 @@ int padata_do_parallel(struct padata_shell *ps,
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
-	rcu_read_unlock_bh();
-
 	spin_lock(&padata_works_lock);
 	padata->seq_nr = ++pd->seq_nr;
 	pw = padata_work_alloc();
 	spin_unlock(&padata_works_lock);
+
+	rcu_read_unlock_bh();
+
 	if (pw) {
 		padata_work_init(pw, padata_parallel_worker, padata, 0);
 		queue_work(pinst->parallel_wq, &pw->pw_work);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f33769f97aca..e7aa57fb2fdc 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -659,7 +659,7 @@ static void power_down(void)
 		break;
 	case HIBERNATION_PLATFORM:
 		hibernation_platform_enter();
-		/* Fall through */
+		fallthrough;
 	case HIBERNATION_SHUTDOWN:
 		if (pm_power_off)
 			kernel_power_off();
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index db0bed2cae26..ec7e1e85923e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -119,7 +119,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 		 * and add, then see if the aggregate has changed.
 		 */
 		plist_del(node, &c->list);
-		/* fall through */
+		fallthrough;
 	case PM_QOS_ADD_REQ:
 		plist_node_init(node, new_value);
 		plist_add(node, &c->list);
@@ -188,7 +188,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 		break;
 	case PM_QOS_UPDATE_REQ:
 		pm_qos_flags_remove_req(pqf, req);
-		/* fall through */
+		fallthrough;
 	case PM_QOS_ADD_REQ:
 		req->flags = val;
 		INIT_LIST_HEAD(&req->node);
diff --git a/kernel/relay.c b/kernel/relay.c
index 72fe443ea78f..fb4e0c530c08 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -197,6 +197,7 @@ free_buf:
 static void relay_destroy_channel(struct kref *kref)
 {
 	struct rchan *chan = container_of(kref, struct rchan, kref);
+	free_percpu(chan->buf);
 	kfree(chan);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8471a0f7eb32..2d95dc3f4644 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2320,7 +2320,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 				state = possible;
 				break;
 			}
-			/* Fall-through */
+			fallthrough;
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6bf34986f45c..f324dc36fc43 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -54,17 +54,18 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static noinline int __cpuidle cpu_idle_poll(void)
 {
+	trace_cpu_idle(0, smp_processor_id());
+	stop_critical_timings();
 	rcu_idle_enter();
-	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	stop_critical_timings();
 
 	while (!tif_need_resched() &&
-		(cpu_idle_force_poll || tick_check_broadcast_expired()))
+	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
-	start_critical_timings();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+
 	rcu_idle_exit();
+	start_critical_timings();
+	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 
 	return 1;
 }
@@ -90,9 +91,14 @@ void __cpuidle default_idle_call(void)
 	if (current_clr_polling_and_test()) {
 		local_irq_enable();
 	} else {
+
+		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
+		rcu_idle_enter();
 		arch_cpu_idle();
+		rcu_idle_exit();
 		start_critical_timings();
+		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 	}
 }
 
@@ -158,7 +164,6 @@ static void cpuidle_idle_call(void)
 
 	if (cpuidle_not_available(drv, dev)) {
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		default_idle_call();
 		goto exit_idle;
@@ -178,21 +183,17 @@ static void cpuidle_idle_call(void)
 		u64 max_latency_ns;
 
 		if (idle_should_enter_s2idle()) {
-			rcu_idle_enter();
 
 			entered_state = call_cpuidle_s2idle(drv, dev);
 			if (entered_state > 0)
 				goto exit_idle;
 
-			rcu_idle_exit();
-
 			max_latency_ns = U64_MAX;
 		} else {
 			max_latency_ns = dev->forced_idle_latency_limit_ns;
 		}
 
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
@@ -209,8 +210,6 @@ static void cpuidle_idle_call(void)
 		else
 			tick_nohz_idle_retain_tick();
 
-		rcu_idle_enter();
-
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
 		 * Give the governor an opportunity to reflect on the outcome
@@ -226,8 +225,6 @@ exit_idle:
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
-
-	rcu_idle_exit();
 }
 
 /*
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 007b0a6b0152..1bd7e3af904f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1219,13 +1219,13 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 	case sa_rootdomain:
 		if (!atomic_read(&d->rd->refcount))
 			free_rootdomain(&d->rd->rcu);
-		/* Fall through */
+		fallthrough;
 	case sa_sd:
 		free_percpu(d->sd);
-		/* Fall through */
+		fallthrough;
 	case sa_sd_storage:
 		__sdt_free(cpu_map);
-		/* Fall through */
+		fallthrough;
 	case sa_none:
 		break;
 	}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 3ee59ce0a323..676d4af62103 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1109,13 +1109,18 @@ out:
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
-static int seccomp_notify_release(struct inode *inode, struct file *file)
+static void seccomp_notify_free(struct seccomp_filter *filter)
+{
+	kfree(filter->notif);
+	filter->notif = NULL;
+}
+
+static void seccomp_notify_detach(struct seccomp_filter *filter)
 {
-	struct seccomp_filter *filter = file->private_data;
 	struct seccomp_knotif *knotif;
 
 	if (!filter)
-		return 0;
+		return;
 
 	mutex_lock(&filter->notify_lock);
 
@@ -1139,9 +1144,15 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		complete(&knotif->ready);
 	}
 
-	kfree(filter->notif);
-	filter->notif = NULL;
+	seccomp_notify_free(filter);
 	mutex_unlock(&filter->notify_lock);
+}
+
+static int seccomp_notify_release(struct inode *inode, struct file *file)
+{
+	struct seccomp_filter *filter = file->private_data;
+
+	seccomp_notify_detach(filter);
 	__put_seccomp_filter(filter);
 	return 0;
 }
@@ -1488,7 +1499,7 @@ static struct file *init_listener(struct seccomp_filter *filter)
 
 out_notif:
 	if (IS_ERR(ret))
-		kfree(filter->notif);
+		seccomp_notify_free(filter);
 out:
 	return ret;
 }
@@ -1581,6 +1592,7 @@ out_put_fd:
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
+			seccomp_notify_detach(prepared);
 		} else {
 			fd_install(listener, listener_f);
 			ret = listener;
diff --git a/kernel/signal.c b/kernel/signal.c
index 42b67d2cea37..a38b3edc6851 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -851,7 +851,7 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 			 */
 			if (!sid || sid == task_session(current))
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EPERM;
 		}
diff --git a/kernel/sys.c b/kernel/sys.c
index ca11af9d815d..ab6c409b1159 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1753,7 +1753,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 
 		if (who == RUSAGE_CHILDREN)
 			break;
-		/* fall through */
+		fallthrough;
 
 	case RUSAGE_SELF:
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 287862f91717..09e70ee2332e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -204,8 +204,7 @@ static int max_extfrag_threshold = 1000;
 
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
 static int bpf_stats_handler(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp,
-			     loff_t *ppos)
+			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct static_key *key = (struct static_key *)table->data;
 	static int saved_val;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c4038511d5c9..95b6a708b040 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -377,7 +377,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
 	switch (state) {
 	case ODEBUG_STATE_ACTIVE:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 07709ac30439..bf540f5a4115 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -439,12 +439,12 @@ static struct pid *good_sigevent(sigevent_t * event)
 		rtn = pid_task(pid, PIDTYPE_PID);
 		if (!rtn || !same_thread_group(rtn, current))
 			return NULL;
-		/* FALLTHRU */
+		fallthrough;
 	case SIGEV_SIGNAL:
 	case SIGEV_THREAD:
 		if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
 			return NULL;
-		/* FALLTHRU */
+		fallthrough;
 	case SIGEV_NONE:
 		return pid;
 	default:
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e51778c312f1..36d7464c8962 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -381,7 +381,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 	switch (mode) {
 	case TICK_BROADCAST_FORCE:
 		tick_broadcast_forced = 1;
-		/* fall through */
+		fallthrough;
 	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a16764b0116e..a50364df1054 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -666,7 +666,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 
 	case ODEBUG_STATE_ACTIVE:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7ba62d68885a..4b3a42fc3b24 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -745,7 +745,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 #endif
 	case BLKTRACESTART:
 		start = 1;
-		/* fall through */
+		fallthrough;
 	case BLKTRACESTOP:
 		ret = __blk_trace_startstop(q, start);
 		break;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index bf44f6bbd0c3..78a678eeb140 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -499,7 +499,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
 					ptr++;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				parse_error(pe, FILT_ERR_TOO_MANY_PREDS,
 					    next - str);
@@ -1273,7 +1273,7 @@ static int parse_pred(const char *str, void *data,
 		switch (op) {
 		case OP_NE:
 			pred->not = 1;
-			/* Fall through */
+			fallthrough;
 		case OP_GLOB:
 		case OP_EQ:
 			break;
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index f74020f6bd9d..0ef8f65bd2d7 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu)
 	struct watch *watch = container_of(rcu, struct watch, rcu);
 
 	put_watch_queue(rcu_access_pointer(watch->queue));
+	atomic_dec(&watch->cred->user->nr_watches);
 	put_cred(watch->cred);
 }
 
@@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
 	watch->cred = get_current_cred();
 	rcu_assign_pointer(watch->watch_list, wlist);
 
+	if (atomic_inc_return(&watch->cred->user->nr_watches) >
+	    task_rlimit(current, RLIMIT_NOFILE)) {
+		atomic_dec(&watch->cred->user->nr_watches);
+		put_cred(watch->cred);
+		return -EAGAIN;
+	}
+
 	spin_lock_bh(&wqueue->lock);
 	kref_get(&wqueue->usage);
 	kref_get(&watch->usage);
diff --git a/lib/Makefile b/lib/Makefile
index e290fc5707ea..a4a4c6864f51 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -15,11 +15,16 @@ KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 KCOV_INSTRUMENT_fault-inject.o := n
 
+# string.o implements standard library functions like memset/memcpy etc.
+# Use -ffreestanding to ensure that the compiler does not try to "optimize"
+# them into calls to themselves.
+CFLAGS_string.o := -ffreestanding
+
 # Early boot use of cmdline, don't instrument it
 ifdef CONFIG_AMD_MEM_ENCRYPT
 KASAN_SANITIZE_string.o := n
 
-CFLAGS_string.o := -fno-stack-protector
+CFLAGS_string.o += -fno-stack-protector
 endif
 
 # Used by KCSAN while enabled, avoid recursion.
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index a5f701161f6b..2c905a91d4eb 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -817,7 +817,7 @@ int __init xbc_init(char *buf, const char **emsg, int *epos)
 							q - 2);
 				break;
 			}
-			/* Fall through */
+			/* fall through */
 		case '=':
 			ret = xbc_parse_kv(&p, q, c);
 			break;
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 1d012e597cc3..2d4dfd44b0fa 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -353,8 +353,7 @@ static int check_set(const char **dest, char *src, char *name)
 
 /*
  * Parse words[] as a ddebug query specification, which is a series
- * of (keyword, value) pairs or combined keyword=value terms,
- * chosen from these possibilities:
+ * of (keyword, value) pairs chosen from these possibilities:
  *
  * func <function-name>
  * file <full-pathname>
@@ -373,34 +372,22 @@ static int ddebug_parse_query(char *words[], int nwords,
 	unsigned int i;
 	int rc = 0;
 	char *fline;
-	char *keyword, *arg;
+
+	/* check we have an even number of words */
+	if (nwords % 2 != 0) {
+		pr_err("expecting pairs of match-spec <value>\n");
+		return -EINVAL;
+	}
 
 	if (modname)
 		/* support $modname.dyndbg=<multiple queries> */
 		query->module = modname;
 
-	for (i = 0; i < nwords; i++) {
-		/* accept keyword=arg */
-		vpr_info("%d w:%s\n", i, words[i]);
-
-		keyword = words[i];
-		arg = strchr(keyword, '=');
-		if (arg) {
-			*arg++ = '\0';
-		} else {
-			i++; /* next word is arg */
-			if (!(i < nwords)) {
-				pr_err("missing arg to keyword: %s\n", keyword);
-				return -EINVAL;
-			}
-			arg = words[i];
-		}
-		vpr_info("%d key:%s arg:%s\n", i, keyword, arg);
-
-		if (!strcmp(keyword, "func")) {
-			rc = check_set(&query->function, arg, "func");
-		} else if (!strcmp(keyword, "file")) {
-			if (check_set(&query->filename, arg, "file"))
+	for (i = 0; i < nwords; i += 2) {
+		if (!strcmp(words[i], "func")) {
+			rc = check_set(&query->function, words[i+1], "func");
+		} else if (!strcmp(words[i], "file")) {
+			if (check_set(&query->filename, words[i+1], "file"))
 				return -EINVAL;
 
 			/* tail :$info is function or line-range */
@@ -416,18 +403,18 @@ static int ddebug_parse_query(char *words[], int nwords,
 				if (parse_linerange(query, fline))
 					return -EINVAL;
 			}
-		} else if (!strcmp(keyword, "module")) {
-			rc = check_set(&query->module, arg, "module");
-		} else if (!strcmp(keyword, "format")) {
-			string_unescape_inplace(arg, UNESCAPE_SPACE |
+		} else if (!strcmp(words[i], "module")) {
+			rc = check_set(&query->module, words[i+1], "module");
+		} else if (!strcmp(words[i], "format")) {
+			string_unescape_inplace(words[i+1], UNESCAPE_SPACE |
 							    UNESCAPE_OCTAL |
 							    UNESCAPE_SPECIAL);
-			rc = check_set(&query->format, arg, "format");
-		} else if (!strcmp(keyword, "line")) {
-			if (parse_linerange(query, arg))
+			rc = check_set(&query->format, words[i+1], "format");
+		} else if (!strcmp(words[i], "line")) {
+			if (parse_linerange(query, words[i+1]))
 				return -EINVAL;
 		} else {
-			pr_err("unknown keyword \"%s\"\n", keyword);
+			pr_err("unknown keyword \"%s\"\n", words[i]);
 			return -EINVAL;
 		}
 		if (rc)
@@ -525,7 +512,7 @@ static int ddebug_exec_query(char *query_string, const char *modname)
    last error or number of matching callsites.  Module name is either
    in param (for boot arg) or perhaps in query string.
 */
-int ddebug_exec_queries(char *query, const char *modname)
+static int ddebug_exec_queries(char *query, const char *modname)
 {
 	char *split;
 	int i, errs = 0, exitcode = 0, rc, nfound = 0;
@@ -557,7 +544,30 @@ int ddebug_exec_queries(char *query, const char *modname)
 		return exitcode;
 	return nfound;
 }
-EXPORT_SYMBOL_GPL(ddebug_exec_queries);
+
+/**
+ * dynamic_debug_exec_queries - select and change dynamic-debug prints
+ * @query: query-string described in admin-guide/dynamic-debug-howto
+ * @modname: string containing module name, usually &module.mod_name
+ *
+ * This uses the >/proc/dynamic_debug/control reader, allowing module
+ * authors to modify their dynamic-debug callsites. The modname is
+ * canonically struct module.mod_name, but can also be null or a
+ * module-wildcard, for example: "drm*".
+ */
+int dynamic_debug_exec_queries(const char *query, const char *modname)
+{
+	int rc;
+	char *qry = kstrndup(query, PAGE_SIZE, GFP_KERNEL);
+
+	if (!query)
+		return -ENOMEM;
+
+	rc = ddebug_exec_queries(qry, modname);
+	kfree(qry);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dynamic_debug_exec_queries);
 
 #define PREFIX_SIZE 64
 
@@ -947,7 +957,7 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	list_add(&dt->link, &ddebug_tables);
 	mutex_unlock(&ddebug_lock);
 
-	v2pr_info("%u debug prints in module %s\n", n, dt->mod_name);
+	v2pr_info("%3u debug prints in module %s\n", n, dt->mod_name);
 	return 0;
 }
 
diff --git a/lib/glob.c b/lib/glob.c
index 0ba3ea86b546..52e3ed7e4a9b 100644
--- a/lib/glob.c
+++ b/lib/glob.c
@@ -102,7 +102,7 @@ bool __pure glob_match(char const *pat, char const *str)
 			break;
 		case '\\':
 			d = *pat++;
-			/*FALLTHROUGH*/
+			/* fall through */
 		default:	/* Literal character */
 literal:
 			if (c == d) {
diff --git a/lib/kobject.c b/lib/kobject.c
index 3afb939f2a1c..ea53b30cf483 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -604,9 +604,6 @@ static void __kobject_del(struct kobject *kobj)
 	struct kernfs_node *sd;
 	const struct kobj_type *ktype;
 
-	if (!kobj)
-		return;
-
 	sd = kobj->sd;
 	ktype = get_ktype(kobj);
 
@@ -637,8 +634,12 @@ static void __kobject_del(struct kobject *kobj)
  */
 void kobject_del(struct kobject *kobj)
 {
-	struct kobject *parent = kobj->parent;
+	struct kobject *parent;
+
+	if (!kobj)
+		return;
 
+	parent = kobj->parent;
 	__kobject_del(kobj);
 	kobject_put(parent);
 }
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 9fee2b93a8d1..06c955057756 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -26,6 +26,8 @@
 #include <linux/vmalloc.h>
 #include <linux/efi_embedded_fw.h>
 
+MODULE_IMPORT_NS(TEST_FIRMWARE);
+
 #define TEST_FIRMWARE_NAME	"test-firmware.bin"
 #define TEST_FIRMWARE_NUM_REQS	4
 #define TEST_FIRMWARE_BUF_SIZE	SZ_1K
@@ -489,6 +491,9 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -501,6 +506,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -513,6 +519,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -530,6 +538,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index c155769559ab..afb9521ddf91 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1681,7 +1681,8 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 
 	switch (*(++fmt)) {
 	case 'L':
-		uc = true;		/* fall-through */
+		uc = true;
+		/* fall through */
 	case 'l':
 		index = guid_index;
 		break;
@@ -2218,7 +2219,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	case 'S':
 	case 's':
 		ptr = dereference_symbol_descriptor(ptr);
-		/* Fallthrough */
+		/* fall through */
 	case 'B':
 		return symbol_string(buf, end, ptr, spec, fmt);
 	case 'R':
@@ -2467,7 +2468,7 @@ qualifier:
 		 * utility, treat it as any other invalid or
 		 * unsupported format specifier.
 		 */
-		/* Fall-through */
+		/* fall through */
 
 	default:
 		WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt);
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 9f336bc07ed6..65a1aad8c223 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -1043,7 +1043,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
 
 			s->lzma2.sequence = SEQ_LZMA_PREPARE;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_LZMA_PREPARE:
 			if (s->lzma2.compressed < RC_INIT_BYTES)
@@ -1055,7 +1055,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
 			s->lzma2.compressed -= RC_INIT_BYTES;
 			s->lzma2.sequence = SEQ_LZMA_RUN;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_LZMA_RUN:
 			/*
diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c
index bd1d182419d7..32ab2a08b7cb 100644
--- a/lib/xz/xz_dec_stream.c
+++ b/lib/xz/xz_dec_stream.c
@@ -583,7 +583,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			if (ret != XZ_OK)
 				return ret;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_START:
 			/* We need one byte of input to continue. */
@@ -608,7 +608,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			s->temp.pos = 0;
 			s->sequence = SEQ_BLOCK_HEADER;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_HEADER:
 			if (!fill_temp(s, b))
@@ -620,7 +620,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_UNCOMPRESS;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_UNCOMPRESS:
 			ret = dec_block(s, b);
@@ -629,7 +629,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_PADDING;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_PADDING:
 			/*
@@ -651,7 +651,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_CHECK;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_CHECK:
 			if (s->check_type == XZ_CHECK_CRC32) {
@@ -675,7 +675,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_INDEX_PADDING;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_INDEX_PADDING:
 			while ((s->index.size + (b->in_pos - s->in_start))
@@ -699,7 +699,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_INDEX_CRC32;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_INDEX_CRC32:
 			ret = crc32_validate(s, b);
@@ -709,7 +709,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			s->temp.size = STREAM_HEADER_SIZE;
 			s->sequence = SEQ_STREAM_FOOTER;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_STREAM_FOOTER:
 			if (!fill_temp(s, b))
diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
index 269ee9a796c1..db6761ea4deb 100644
--- a/lib/zstd/decompress.c
+++ b/lib/zstd/decompress.c
@@ -442,7 +442,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize
 		case set_repeat:
 			if (dctx->litEntropy == 0)
 				return ERROR(dictionary_corrupted);
-		/* fall-through */
+			/* fall through */
 		case set_compressed:
 			if (srcSize < 5)
 				return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
@@ -2309,7 +2309,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 		switch (zds->stage) {
 		case zdss_init:
 			ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
-						/* fall-through */
+			/* fall through */
 
 		case zdss_loadHeader: {
 			size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
@@ -2376,7 +2376,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			}
 			zds->stage = zdss_read;
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_read: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2405,7 +2405,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			zds->stage = zdss_load;
 			/* pass-through */
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_load: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2438,7 +2438,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 				/* pass-through */
 			}
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_flush: {
 			size_t const toFlushSize = zds->outEnd - zds->outStart;
diff --git a/mm/gup.c b/mm/gup.c
index ae096ea7583f..e5739a1974d5 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -381,22 +381,13 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pte's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
 {
-	return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte));
-}
-
-/*
- * A (separate) COW fault might break the page the other way and
- * get_user_pages() would return the page from what is now the wrong
- * VM. So we need to force a COW break at GUP time even for reads.
- */
-static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags)
-{
-	return is_cow_mapping(vma->vm_flags) && (flags & (FOLL_GET | FOLL_PIN));
+	return pte_write(pte) ||
+		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -843,7 +834,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 			goto unmap;
 		*page = pte_page(*pte);
 	}
-	if (unlikely(!try_get_page(*page))) {
+	if (unlikely(!try_grab_page(*page, gup_flags))) {
 		ret = -ENOMEM;
 		goto unmap;
 	}
@@ -1067,11 +1058,9 @@ static long __get_user_pages(struct mm_struct *mm,
 				goto out;
 			}
 			if (is_vm_hugetlb_page(vma)) {
-				if (should_force_cow_break(vma, foll_flags))
-					foll_flags |= FOLL_WRITE;
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
-						foll_flags, locked);
+						gup_flags, locked);
 				if (locked && *locked == 0) {
 					/*
 					 * We've got a VM_FAULT_RETRY
@@ -1085,10 +1074,6 @@ static long __get_user_pages(struct mm_struct *mm,
 				continue;
 			}
 		}
-
-		if (should_force_cow_break(vma, foll_flags))
-			foll_flags |= FOLL_WRITE;
-
 retry:
 		/*
 		 * If we have a pending SIGKILL, don't keep faulting pages and
@@ -2689,19 +2674,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 		return -EFAULT;
 
 	/*
-	 * The FAST_GUP case requires FOLL_WRITE even for pure reads,
-	 * because get_user_pages() may need to cause an early COW in
-	 * order to avoid confusing the normal COW routines. So only
-	 * targets that are already writable are safe to do by just
-	 * looking at the page tables.
-	 *
-	 * NOTE! With FOLL_FAST_ONLY we allow read-only gup_fast() here,
-	 * because there is no slow path to fall back on. But you'd
-	 * better be careful about possible COW pages - you'll get _a_
-	 * COW page, but not necessarily the one you intended to get
-	 * depending on what COW event happens after this. COW may break
-	 * the page copy in a random direction.
-	 *
 	 * Disable interrupts. The nested form is used, in order to allow
 	 * full, general purpose use of this routine.
 	 *
@@ -2714,8 +2686,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 	 */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) {
 		unsigned long fast_flags = gup_flags;
-		if (!(gup_flags & FOLL_FAST_ONLY))
-			fast_flags |= FOLL_WRITE;
 
 		local_irq_save(flags);
 		gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2ccff8472cd4..7ff29cc3d55c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1291,12 +1291,13 @@ fallback:
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
 {
-	return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..67fc6383995b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1250,21 +1250,32 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
 #ifdef CONFIG_CMA
 	{
 		struct page *page;
 		int node;
 
-		for_each_node_mask(node, *nodemask) {
-			if (!hugetlb_cma[node])
-				continue;
-
-			page = cma_alloc(hugetlb_cma[node], nr_pages,
-					 huge_page_order(h), true);
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
 			if (page)
 				return page;
 		}
+
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
+
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
 	}
 #endif
 
@@ -3454,6 +3465,22 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void *buffer, size_t *length, loff_t *ppos)
@@ -3465,9 +3492,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3510,9 +3536,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index aabf65d4d91b..1f87aec9ab5c 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -655,7 +655,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx)
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf);
 	cft->private = MEMFILE_PRIVATE(idx, 0);
 	cft->seq_show = hugetlb_events_show;
-	cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]),
+	cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]);
 	cft->flags = CFTYPE_NOT_ON_ROOT;
 
 	/* Add the events.local file */
@@ -664,7 +664,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx)
 	cft->private = MEMFILE_PRIVATE(idx, 0);
 	cft->seq_show = hugetlb_events_local_show;
 	cft->file_offset = offsetof(struct hugetlb_cgroup,
-				    events_local_file[idx]),
+				    events_local_file[idx]);
 	cft->flags = CFTYPE_NOT_ON_ROOT;
 
 	/* NULL terminate the last cft */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 15a9af791014..cfa0dba5fd3b 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -466,7 +466,7 @@ int __khugepaged_enter(struct mm_struct *mm)
 		return -ENOMEM;
 
 	/* __khugepaged_exit() must not run from under us */
-	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
+	VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm);
 	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
 		free_mm_slot(mm_slot);
 		return 0;
@@ -1709,7 +1709,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				page_cache_sync_readahead(mapping, &file->f_ra,
 							  file, index,
-							  PAGE_SIZE);
+							  end - index);
 				/* drain pagevecs to help isolate_lru_page() */
 				lru_add_drain();
 				page = find_lock_page(mapping, index);
diff --git a/mm/ksm.c b/mm/ksm.c
index 0aa2247bddd7..235f55d01541 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2453,6 +2453,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (vma_is_dax(vma))
 			return 0;
 
+#ifdef VM_SAO
+		if (*vm_flags & VM_SAO)
+			return 0;
+#endif
 #ifdef VM_SPARC_ADI
 		if (*vm_flags & VM_SPARC_ADI)
 			return 0;
@@ -2657,31 +2661,6 @@ again:
 		goto again;
 }
 
-bool reuse_ksm_page(struct page *page,
-		    struct vm_area_struct *vma,
-		    unsigned long address)
-{
-#ifdef CONFIG_DEBUG_VM
-	if (WARN_ON(is_zero_pfn(page_to_pfn(page))) ||
-			WARN_ON(!page_mapped(page)) ||
-			WARN_ON(!PageLocked(page))) {
-		dump_page(page, "reuse_ksm_page");
-		return false;
-	}
-#endif
-
-	if (PageSwapCache(page) || !page_stable_node(page))
-		return false;
-	/* Prohibit parallel get_ksm_page() */
-	if (!page_ref_freeze(page, 1))
-		return false;
-
-	page_move_anon_rmap(page, vma);
-	page->index = linear_page_index(vma, address);
-	page_ref_unfreeze(page, 1);
-
-	return true;
-}
 #ifdef CONFIG_MIGRATION
 void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index dd1d43cf026d..d4aa5f776543 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -289,9 +289,9 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
-	mmap_read_unlock(current->mm);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	mmap_read_unlock(current->mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
 	mmap_read_lock(current->mm);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..cfa6cbad21d5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6774,6 +6774,9 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
+
+	/* drop reference from uncharge_page */
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6797,6 +6800,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 			uncharge_gather_clear(ug);
 		}
 		ug->memcg = page->mem_cgroup;
+
+		/* pairs with css_put in uncharge_batch */
+		css_get(&ug->memcg->css);
 	}
 
 	nr_pages = compound_nr(page);
diff --git a/mm/memory.c b/mm/memory.c
index 3a7779d9891d..469af373ae76 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -73,6 +73,7 @@
 #include <linux/numa.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
+#include <linux/vmalloc.h>
 
 #include <trace/events/kmem.h>
 
@@ -83,6 +84,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+#include "pgalloc-track.h"
 #include "internal.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
@@ -2206,7 +2208,8 @@ EXPORT_SYMBOL(vm_iomap_memory);
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
 	int err = 0;
@@ -2214,7 +2217,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 	if (create) {
 		pte = (mm == &init_mm) ?
-			pte_alloc_kernel(pmd, addr) :
+			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
@@ -2235,6 +2238,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				break;
 		}
 	} while (addr += PAGE_SIZE, addr != end);
+	*mask |= PGTBL_PTE_MODIFIED;
 
 	arch_leave_lazy_mmu_mode();
 
@@ -2245,7 +2249,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -2254,7 +2259,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	BUG_ON(pud_huge(*pud));
 
 	if (create) {
-		pmd = pmd_alloc(mm, pud, addr);
+		pmd = pmd_alloc_track(mm, pud, addr, mask);
 		if (!pmd)
 			return -ENOMEM;
 	} else {
@@ -2264,7 +2269,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (create || !pmd_none_or_clear_bad(pmd)) {
 			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2274,14 +2279,15 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		pud = pud_alloc(mm, p4d, addr);
+		pud = pud_alloc_track(mm, p4d, addr, mask);
 		if (!pud)
 			return -ENOMEM;
 	} else {
@@ -2291,7 +2297,7 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		next = pud_addr_end(addr, end);
 		if (create || !pud_none_or_clear_bad(pud)) {
 			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2301,14 +2307,15 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	p4d_t *p4d;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		p4d = p4d_alloc(mm, pgd, addr);
+		p4d = p4d_alloc_track(mm, pgd, addr, mask);
 		if (!p4d)
 			return -ENOMEM;
 	} else {
@@ -2318,7 +2325,7 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		next = p4d_addr_end(addr, end);
 		if (create || !p4d_none_or_clear_bad(p4d)) {
 			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2331,8 +2338,9 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 				 void *data, bool create)
 {
 	pgd_t *pgd;
-	unsigned long next;
+	unsigned long start = addr, next;
 	unsigned long end = addr + size;
+	pgtbl_mod_mask mask = 0;
 	int err = 0;
 
 	if (WARN_ON(addr >= end))
@@ -2343,11 +2351,14 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (!create && pgd_none_or_clear_bad(pgd))
 			continue;
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, start + size);
+
 	return err;
 }
 
@@ -2622,6 +2633,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	count_vm_event(PGREUSE);
 }
 
 /*
@@ -2927,50 +2939,25 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	 * not dirty accountable.
 	 */
 	if (PageAnon(vmf->page)) {
-		int total_map_swapcount;
-		if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
-					   page_count(vmf->page) != 1))
+		struct page *page = vmf->page;
+
+		/* PageKsm() doesn't necessarily raise the page refcount */
+		if (PageKsm(page) || page_count(page) != 1)
+			goto copy;
+		if (!trylock_page(page))
+			goto copy;
+		if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) {
+			unlock_page(page);
 			goto copy;
-		if (!trylock_page(vmf->page)) {
-			get_page(vmf->page);
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			lock_page(vmf->page);
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
-			if (!pte_same(*vmf->pte, vmf->orig_pte)) {
-				update_mmu_tlb(vma, vmf->address, vmf->pte);
-				unlock_page(vmf->page);
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
-				put_page(vmf->page);
-				return 0;
-			}
-			put_page(vmf->page);
-		}
-		if (PageKsm(vmf->page)) {
-			bool reused = reuse_ksm_page(vmf->page, vmf->vma,
-						     vmf->address);
-			unlock_page(vmf->page);
-			if (!reused)
-				goto copy;
-			wp_page_reuse(vmf);
-			return VM_FAULT_WRITE;
-		}
-		if (reuse_swap_page(vmf->page, &total_map_swapcount)) {
-			if (total_map_swapcount == 1) {
-				/*
-				 * The page is all ours. Move it to
-				 * our anon_vma so the rmap code will
-				 * not search our parent or siblings.
-				 * Protected against the rmap code by
-				 * the page lock.
-				 */
-				page_move_anon_rmap(vmf->page, vma);
-			}
-			unlock_page(vmf->page);
-			wp_page_reuse(vmf);
-			return VM_FAULT_WRITE;
 		}
-		unlock_page(vmf->page);
+		/*
+		 * Ok, we've got the only map reference, and the only
+		 * page count reference, and the page is locked,
+		 * it's dark out, and we're wearing sunglasses. Hit it.
+		 */
+		wp_page_reuse(vmf);
+		unlock_page(page);
+		return VM_FAULT_WRITE;
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
@@ -4247,6 +4234,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 				vmf->flags & FAULT_FLAG_WRITE)) {
 		update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
 	} else {
+		/* Skip spurious TLB flush for retried page fault */
+		if (vmf->flags & FAULT_FLAG_TRIED)
+			goto unlock;
 		/*
 		 * This is needed only for protection faults but the arch code
 		 * is not yet telling us if this is a protection fault or not.
diff --git a/mm/memremap.c b/mm/memremap.c
index 03e38b7a38f1..006dace60b1a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -216,7 +216,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(-EINVAL);
 		}
 		break;
-	case MEMORY_DEVICE_DEVDAX:
+	case MEMORY_DEVICE_GENERIC:
 		need_devmap_managed = false;
 		break;
 	case MEMORY_DEVICE_PCI_P2PDMA:
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..941b89383cf3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -246,13 +246,13 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
-		if (unlikely(is_zone_device_page(new))) {
-			if (is_device_private_page(new)) {
-				entry = make_device_private_entry(new, pte_write(pte));
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_uffd_wp(*pvmw.pte))
-					pte = pte_mkuffd_wp(pte);
-			}
+		if (unlikely(is_device_private_page(new))) {
+			entry = make_device_private_entry(new, pte_write(pte));
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*pvmw.pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*pvmw.pte))
+				pte = pte_swp_mkuffd_wp(pte);
 		}
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -2427,10 +2427,17 @@ again:
 			entry = make_migration_entry(page, mpfn &
 						     MIGRATE_PFN_WRITE);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pte))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pte))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			if (pte_present(pte)) {
+				if (pte_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			} else {
+				if (pte_swp_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_swp_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			}
 			set_pte_at(mm, addr, ptep, swp_pte);
 
 			/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0e2bab486fea..fab5e97dc9ca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1302,6 +1302,11 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	struct page *page, *tmp;
 	LIST_HEAD(head);
 
+	/*
+	 * Ensure proper count is passed which otherwise would stuck in the
+	 * below while (list_empty(list)) loop.
+	 */
+	count = min(pcp->count, count);
 	while (count) {
 		struct list_head *list;
 
@@ -7888,7 +7893,7 @@ int __meminit init_per_zone_wmark_min(void)
 
 	return 0;
 }
-core_initcall(init_per_zone_wmark_min)
+postcore_initcall(init_per_zone_wmark_min)
 
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
diff --git a/mm/rmap.c b/mm/rmap.c
index 83cc459edc40..9425260774a1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1511,9 +1511,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 */
 			entry = make_migration_entry(page, 0);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
+
+			/*
+			 * pteval maps a zone device page and is therefore
+			 * a swap pte.
+			 */
+			if (pte_swp_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pteval))
+			if (pte_swp_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 			/*
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index 2a99df7beeb3..2613371945b7 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -7,6 +7,7 @@
  */
 #define pr_fmt(fmt) "rodata_test: " fmt
 
+#include <linux/rodata_test.h>
 #include <linux/uaccess.h>
 #include <asm/sections.h>
 
diff --git a/mm/slub.c b/mm/slub.c
index 68c02b2eecd9..d4177aecedf6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -672,12 +672,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
-	    !check_valid_pointer(s, page, nextfree)) {
-		object_err(s, page, freelist, "Freechain corrupt");
-		freelist = NULL;
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
 		slab_fix(s, "Isolate corrupted freechain");
 		return true;
 	}
@@ -1494,7 +1494,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	return false;
 }
@@ -2184,7 +2184,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		 * 'freelist' is already corrupted.  So isolate all objects
 		 * starting at 'freelist'.
 		 */
-		if (freelist_corrupted(s, page, freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist, nextfree))
 			break;
 
 		do {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b482d240f9a2..be4724b916b3 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -104,6 +104,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		vunmap_pte_range(pmd, addr, next, mask);
+
+		cond_resched();
 	} while (pmd++, addr = next, addr != end);
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 99e1796eb833..9727dd8e2581 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2615,6 +2615,14 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
+		/*
+		 * This loop can become CPU-bound when target memcgs
+		 * aren't eligible for reclaim - either because they
+		 * don't have any reclaimable pages, or because their
+		 * memory is explicitly protected. Avoid soft lockups.
+		 */
+		cond_resched();
+
 		mem_cgroup_calculate_protection(target_memcg, memcg);
 
 		if (mem_cgroup_below_min(memcg)) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e670f910cd2f..4f7b4ee6aa12 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1241,6 +1241,7 @@ const char * const vmstat_text[] = {
 	"pglazyfreed",
 
 	"pgrefill",
+	"pgreuse",
 	"pgsteal_kswapd",
 	"pgsteal_direct",
 	"pgscan_kswapd",
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 3dd7c972677b..ec8408d1638f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -367,7 +367,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (!net_eq(dev_net(dev), &init_net))
 			break;
-		/* fall through */
+		fallthrough;
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 3debad93be1a..bc8807d9281f 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -520,7 +520,7 @@ static void xen_9pfs_front_changed(struct xenbus_device *dev,
 	case XenbusStateClosed:
 		if (dev->state == XenbusStateClosed)
 			break;
-		/* fall through - Missed the backend's CLOSING state */
+		fallthrough;	/* Missed the backend's CLOSING state */
 	case XenbusStateClosing:
 		xenbus_frontend_closed(dev);
 		break;
diff --git a/net/atm/common.c b/net/atm/common.c
index 84367b844b14..1cfa9bf1d187 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -297,7 +297,7 @@ static int adjust_tp(struct atm_trafprm *tp, unsigned char aal)
 		break;
 	default:
 		pr_warn("AAL problems ... (%d)\n", aal);
-		/* fall through */
+		fallthrough;
 	case ATM_AAL5:
 		max_sdu = ATM_MAX_AAL5_PDU;
 	}
@@ -417,7 +417,7 @@ static int __vcc_connect(struct atm_vcc *vcc, struct atm_dev *dev, short vpi,
 	case ATM_NO_AAL:
 		/* ATM_AAL5 is also used in the "0 for default" case */
 		vcc->qos.aal = ATM_AAL5;
-		/* fall through */
+		fallthrough;
 	case ATM_AAL5:
 		error = atm_init_aal5(vcc);
 		vcc->stats = &dev->stats.aal5;
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 875fc0bc1780..b570ef919c28 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -380,7 +380,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
 
 		if (mesg->content.normal.no_source_le_narp)
 			break;
-		/* FALL THROUGH */
+		fallthrough;
 	case l_arp_update:
 		lec_arp_update(priv, mesg->content.normal.mac_addr,
 			       mesg->content.normal.atm_addr,
diff --git a/net/atm/resources.c b/net/atm/resources.c
index 94bdc6527ee8..53236986dfe0 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -266,7 +266,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len,
 				goto done;
 			}
 	}
-	/* fall through */
+		fallthrough;
 	case ATM_SETESIF:
 	{
 		unsigned char esi[ESI_LEN];
@@ -288,7 +288,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len,
 			error = -EPERM;
 			goto done;
 		}
-		/* fall through */
+		fallthrough;
 	case ATM_GETSTAT:
 		size = sizeof(struct atm_dev_stats);
 		error = fetch_stats(dev, buf, cmd == ATM_GETSTATZ);
@@ -361,7 +361,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len,
 			error = -EINVAL;
 			goto done;
 		}
-		/* fall through */
+		fallthrough;
 	case ATM_SETCIRANGE:
 	case SONET_GETSTATZ:
 	case SONET_SETDIAG:
@@ -371,7 +371,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len,
 			error = -EPERM;
 			goto done;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		if (IS_ENABLED(CONFIG_COMPAT) && compat) {
 #ifdef CONFIG_COMPAT
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 0f8495b9eeb1..717fe657561d 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -881,6 +881,12 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 		   ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl,
 		   ogm_packet->version, ntohs(ogm_packet->tvlv_len));
 
+	if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) {
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: originator packet from ourself\n");
+		return;
+	}
+
 	/* If the throughput metric is 0, immediately drop the packet. No need
 	 * to create orig_node / neigh_node for an unusable route.
 	 */
@@ -1008,11 +1014,6 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
 		goto free_skb;
 
-	ogm_packet = (struct batadv_ogm2_packet *)skb->data;
-
-	if (batadv_is_my_mac(bat_priv, ogm_packet->orig))
-		goto free_skb;
-
 	batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX);
 	batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES,
 			   skb->len + ETH_HLEN);
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 91a04ca373dc..8500f56cbd10 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -437,7 +437,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 	batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES,
 			   skb->len + ETH_HLEN);
 
-	netif_rx(skb);
+	if (in_interrupt())
+		netif_rx(skb);
+	else
+		netif_rx_ni(skb);
 out:
 	if (primary_if)
 		batadv_hardif_put(primary_if);
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index a18dcc686dc3..ef3f85b576c4 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -703,8 +703,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
 
 	chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET;
 	/* store the client address if the message is going to a client */
-	if (ret == BATADV_DHCP_TO_CLIENT &&
-	    pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) {
+	if (ret == BATADV_DHCP_TO_CLIENT) {
+		if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN))
+			return BATADV_DHCP_NO;
+
 		/* check if the DHCP packet carries an Ethernet DHCP */
 		p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET;
 		if (*p != BATADV_DHCP_HTYPE_ETHERNET)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 99eb8c6c0fbc..a66f211726e7 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -425,7 +425,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
 		is_l2 = true;
-		/* fall through */
+		fallthrough;
 	case BPF_PROG_TYPE_LWT_IN:
 	case BPF_PROG_TYPE_LWT_OUT:
 	case BPF_PROG_TYPE_LWT_XMIT:
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 1641f414d1ba..ebe33b60efd6 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2238,6 +2238,10 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd,
 	struct ebt_table *t;
 	struct net *net = sock_net(sk);
 
+	if ((cmd == EBT_SO_GET_INFO || cmd == EBT_SO_GET_INIT_INFO) &&
+	    *len != sizeof(struct compat_ebt_replace))
+		return -EINVAL;
+
 	if (copy_from_user(&tmp, user, sizeof(tmp)))
 		return -EFAULT;
 
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 809673222382..8d033a75a766 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb,
 static unsigned int nf_ct_br_defrag6(struct sk_buff *skb,
 				     const struct nf_hook_state *state)
 {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 	enum ip_conntrack_info ctinfo;
 	struct br_input_skb_cb cb;
@@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb,
 
 	br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm));
 
-	err = nf_ipv6_br_defrag(state->net, skb,
-				IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
+	err = nf_ct_frag6_gather(state->net, skb,
+				 IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
 	/* queued */
 	if (err == -EINPROGRESS)
 		return NF_STOLEN;
 
 	br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size);
 	return err == 0 ? NF_ACCEPT : NF_DROP;
+#else
+	return NF_ACCEPT;
+#endif
 }
 
 static int nf_ct_br_ip_check(const struct sk_buff *skb)
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index ce2767e9cec6..7b0af33bdb97 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -116,7 +116,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt)
 	if (segmented) {
 		if (rfml->incomplete_frm == NULL) {
 			/* Initial Segment */
-			if (cfpkt_peek_head(pkt, rfml->seghead, 6) < 0)
+			if (cfpkt_peek_head(pkt, rfml->seghead, 6) != 0)
 				goto out;
 
 			rfml->pdu_size = get_unaligned_le16(rfml->seghead+4);
@@ -233,7 +233,7 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt)
 	if (cfpkt_getlen(pkt) > rfml->fragment_size + RFM_HEAD_SIZE)
 		err = cfpkt_peek_head(pkt, head, 6);
 
-	if (err < 0)
+	if (err != 0)
 		goto out;
 
 	while (cfpkt_getlen(frontpkt) > rfml->fragment_size + RFM_HEAD_SIZE) {
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 78ff9b3f1d40..1be4c898b2fa 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -398,6 +398,7 @@ static int j1939_sk_init(struct sock *sk)
 	spin_lock_init(&jsk->sk_session_queue_lock);
 	INIT_LIST_HEAD(&jsk->sk_session_queue);
 	sk->sk_destruct = j1939_sk_sock_destruct;
+	sk->sk_protocol = CAN_J1939;
 
 	return 0;
 }
@@ -466,6 +467,14 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			goto out_release_sock;
 		}
 
+		if (!ndev->ml_priv) {
+			netdev_warn_once(ndev,
+					 "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n");
+			dev_put(ndev);
+			ret = -ENODEV;
+			goto out_release_sock;
+		}
+
 		priv = j1939_netdev_start(ndev);
 		dev_put(ndev);
 		if (IS_ERR(priv)) {
@@ -553,6 +562,11 @@ static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr,
 static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr,
 				       const struct j1939_sock *jsk, int peer)
 {
+	/* There are two holes (2 bytes and 3 bytes) to clear to avoid
+	 * leaking kernel information to user space.
+	 */
+	memset(addr, 0, J1939_MIN_NAMELEN);
+
 	addr->can_family = AF_CAN;
 	addr->can_ifindex = jsk->ifindex;
 	addr->can_addr.j1939.pgn = jsk->addr.pgn;
@@ -1072,7 +1086,7 @@ static int j1939_sk_send_loop(struct j1939_priv *priv,  struct sock *sk,
 		break;
 	case -ERESTARTSYS:
 		ret = -EINTR;
-		/* fall through */
+		fallthrough;
 	case -EAGAIN: /* OK */
 		if (todo_size != size)
 			ret = size - todo_size;
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 9f99af5b0b11..0cec4152f979 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -352,17 +352,16 @@ void j1939_session_skb_queue(struct j1939_session *session,
 	skb_queue_tail(&session->skb_queue, skb);
 }
 
-static struct sk_buff *j1939_session_skb_find(struct j1939_session *session)
+static struct
+sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session,
+					  unsigned int offset_start)
 {
 	struct j1939_priv *priv = session->priv;
+	struct j1939_sk_buff_cb *do_skcb;
 	struct sk_buff *skb = NULL;
 	struct sk_buff *do_skb;
-	struct j1939_sk_buff_cb *do_skcb;
-	unsigned int offset_start;
 	unsigned long flags;
 
-	offset_start = session->pkt.dpo * 7;
-
 	spin_lock_irqsave(&session->skb_queue.lock, flags);
 	skb_queue_walk(&session->skb_queue, do_skb) {
 		do_skcb = j1939_skb_to_cb(do_skb);
@@ -382,6 +381,14 @@ static struct sk_buff *j1939_session_skb_find(struct j1939_session *session)
 	return skb;
 }
 
+static struct sk_buff *j1939_session_skb_find(struct j1939_session *session)
+{
+	unsigned int offset_start;
+
+	offset_start = session->pkt.dpo * 7;
+	return j1939_session_skb_find_by_offset(session, offset_start);
+}
+
 /* see if we are receiver
  * returns 0 for broadcasts, although we will receive them
  */
@@ -716,10 +723,12 @@ static int j1939_session_tx_rts(struct j1939_session *session)
 		return ret;
 
 	session->last_txcmd = dat[0];
-	if (dat[0] == J1939_TP_CMD_BAM)
+	if (dat[0] == J1939_TP_CMD_BAM) {
 		j1939_tp_schedule_txtimer(session, 50);
-
-	j1939_tp_set_rxtimeout(session, 1250);
+		j1939_tp_set_rxtimeout(session, 250);
+	} else {
+		j1939_tp_set_rxtimeout(session, 1250);
+	}
 
 	netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session);
 
@@ -766,7 +775,7 @@ static int j1939_session_tx_dat(struct j1939_session *session)
 	int ret = 0;
 	u8 dat[8];
 
-	se_skb = j1939_session_skb_find(session);
+	se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7);
 	if (!se_skb)
 		return -ENOBUFS;
 
@@ -787,6 +796,18 @@ static int j1939_session_tx_dat(struct j1939_session *session)
 		if (len > 7)
 			len = 7;
 
+		if (offset + len > se_skb->len) {
+			netdev_err_once(priv->ndev,
+					"%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n",
+					__func__, session, skcb->offset, se_skb->len , session->pkt.tx);
+			return -EOVERFLOW;
+		}
+
+		if (!len) {
+			ret = -ENOBUFS;
+			break;
+		}
+
 		memcpy(&dat[1], &tpdat[offset], len);
 		ret = j1939_tp_tx_dat(session, dat, len + 1);
 		if (ret < 0) {
@@ -839,7 +860,7 @@ static int j1939_xtp_txnext_transmiter(struct j1939_session *session)
 				return ret;
 		}
 
-		/* fall through */
+		fallthrough;
 	case J1939_TP_CMD_CTS:
 	case 0xff: /* did some data */
 	case J1939_ETP_CMD_DPO:
@@ -1055,9 +1076,9 @@ static void __j1939_session_cancel(struct j1939_session *session,
 	lockdep_assert_held(&session->priv->active_session_list_lock);
 
 	session->err = j1939_xtp_abort_to_errno(priv, err);
+	session->state = J1939_SESSION_WAITING_ABORT;
 	/* do not send aborts on incoming broadcasts */
 	if (!j1939_cb_is_broadcast(&session->skcb)) {
-		session->state = J1939_SESSION_WAITING_ABORT;
 		j1939_xtp_tx_abort(priv, &session->skcb,
 				   !session->transmission,
 				   err, session->skcb.addr.pgn);
@@ -1120,6 +1141,9 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer)
 		 * cleanup including propagation of the error to user space.
 		 */
 		break;
+	case -EOVERFLOW:
+		j1939_session_cancel(session, J1939_XTP_ABORT_ECTS_TOO_BIG);
+		break;
 	case 0:
 		session->tx_retry = 0;
 		break;
@@ -1651,8 +1675,12 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb,
 			return;
 		}
 		session = j1939_xtp_rx_rts_session_new(priv, skb);
-		if (!session)
+		if (!session) {
+			if (cmd == J1939_TP_CMD_BAM && j1939_sk_recv_match(priv, skcb))
+				netdev_info(priv->ndev, "%s: failed to create TP BAM session\n",
+					    __func__);
 			return;
+		}
 	} else {
 		if (j1939_xtp_rx_rts_session_active(session, skb)) {
 			j1939_session_put(session);
@@ -1661,11 +1689,15 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb,
 	}
 	session->last_cmd = cmd;
 
-	j1939_tp_set_rxtimeout(session, 1250);
-
-	if (cmd != J1939_TP_CMD_BAM && !session->transmission) {
-		j1939_session_txtimer_cancel(session);
-		j1939_tp_schedule_txtimer(session, 0);
+	if (cmd == J1939_TP_CMD_BAM) {
+		if (!session->transmission)
+			j1939_tp_set_rxtimeout(session, 750);
+	} else {
+		if (!session->transmission) {
+			j1939_session_txtimer_cancel(session);
+			j1939_tp_schedule_txtimer(session, 0);
+		}
+		j1939_tp_set_rxtimeout(session, 1250);
 	}
 
 	j1939_session_put(session);
@@ -1716,6 +1748,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 	int offset;
 	int nbytes;
 	bool final = false;
+	bool remain = false;
 	bool do_cts_eoma = false;
 	int packet;
 
@@ -1731,12 +1764,12 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 	case J1939_ETP_CMD_DPO:
 		if (skcb->addr.type == J1939_ETP)
 			break;
-		/* fall through */
-	case J1939_TP_CMD_BAM: /* fall through */
+		fallthrough;
+	case J1939_TP_CMD_BAM:
 	case J1939_TP_CMD_CTS: /* fall through */
 		if (skcb->addr.type != J1939_ETP)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		netdev_info(priv->ndev, "%s: 0x%p: last %02x\n", __func__,
 			    session, session->last_cmd);
@@ -1750,7 +1783,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 			    __func__, session);
 		goto out_session_cancel;
 	}
-	se_skb = j1939_session_skb_find(session);
+
+	se_skb = j1939_session_skb_find_by_offset(session, packet * 7);
 	if (!se_skb) {
 		netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__,
 			    session);
@@ -1769,7 +1803,20 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 	}
 
 	tpdat = se_skb->data;
-	memcpy(&tpdat[offset], &dat[1], nbytes);
+	if (!session->transmission) {
+		memcpy(&tpdat[offset], &dat[1], nbytes);
+	} else {
+		int err;
+
+		err = memcmp(&tpdat[offset], &dat[1], nbytes);
+		if (err)
+			netdev_err_once(priv->ndev,
+					"%s: 0x%p: Data of RX-looped back packet (%*ph) doesn't match TX data (%*ph)!\n",
+					__func__, session,
+					nbytes, &dat[1],
+					nbytes, &tpdat[offset]);
+	}
+
 	if (packet == session->pkt.rx)
 		session->pkt.rx++;
 
@@ -1777,6 +1824,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 	    j1939_cb_is_broadcast(&session->skcb)) {
 		if (session->pkt.rx >= session->pkt.total)
 			final = true;
+		else
+			remain = true;
 	} else {
 		/* never final, an EOMA must follow */
 		if (session->pkt.rx >= session->pkt.last)
@@ -1784,7 +1833,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 	}
 
 	if (final) {
+		j1939_session_timers_cancel(session);
 		j1939_session_completed(session);
+	} else if (remain) {
+		if (!session->transmission)
+			j1939_tp_set_rxtimeout(session, 750);
 	} else if (do_cts_eoma) {
 		j1939_tp_set_rxtimeout(session, 1250);
 		if (!session->transmission)
@@ -1829,6 +1882,13 @@ static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb)
 		else
 			j1939_xtp_rx_dat_one(session, skb);
 	}
+
+	if (j1939_cb_is_broadcast(skcb)) {
+		session = j1939_session_get_by_addr(priv, &skcb->addr, false,
+						    false);
+		if (session)
+			j1939_xtp_rx_dat_one(session, skb);
+	}
 }
 
 /* j1939 main intf */
@@ -1905,8 +1965,8 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb)
 	switch (cmd) {
 	case J1939_ETP_CMD_RTS:
 		extd = J1939_ETP;
-		/* fall through */
-	case J1939_TP_CMD_BAM: /* fall through */
+		fallthrough;
+	case J1939_TP_CMD_BAM:
 	case J1939_TP_CMD_RTS: /* fall through */
 		if (skcb->addr.type != extd)
 			return;
@@ -1920,14 +1980,14 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb)
 		if (j1939_tp_im_transmitter(skcb))
 			j1939_xtp_rx_rts(priv, skb, true);
 
-		if (j1939_tp_im_receiver(skcb))
+		if (j1939_tp_im_receiver(skcb) || j1939_cb_is_broadcast(skcb))
 			j1939_xtp_rx_rts(priv, skb, false);
 
 		break;
 
 	case J1939_ETP_CMD_CTS:
 		extd = J1939_ETP;
-		/* fall through */
+		fallthrough;
 	case J1939_TP_CMD_CTS:
 		if (skcb->addr.type != extd)
 			return;
@@ -1954,7 +2014,7 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb)
 
 	case J1939_ETP_CMD_EOMA:
 		extd = J1939_ETP;
-		/* fall through */
+		fallthrough;
 	case J1939_TP_CMD_EOMA:
 		if (skcb->addr.type != extd)
 			return;
@@ -1984,20 +2044,20 @@ int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb)
 {
 	struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb);
 
-	if (!j1939_tp_im_involved_anydir(skcb))
+	if (!j1939_tp_im_involved_anydir(skcb) && !j1939_cb_is_broadcast(skcb))
 		return 0;
 
 	switch (skcb->addr.pgn) {
 	case J1939_ETP_PGN_DAT:
 		skcb->addr.type = J1939_ETP;
-		/* fall through */
+		fallthrough;
 	case J1939_TP_PGN_DAT:
 		j1939_xtp_rx_dat(priv, skb);
 		break;
 
 	case J1939_ETP_PGN_CTL:
 		skcb->addr.type = J1939_ETP;
-		/* fall through */
+		fallthrough;
 	case J1939_TP_PGN_CTL:
 		if (skb->len < 8)
 			return 0; /* Don't care. Nothing to extract here */
@@ -2017,6 +2077,10 @@ void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb)
 	if (!skb->sk)
 		return;
 
+	if (skb->sk->sk_family != AF_CAN ||
+	    skb->sk->sk_protocol != CAN_J1939)
+		return;
+
 	j1939_session_list_lock(priv);
 	session = j1939_session_get_simple(priv, skb);
 	j1939_session_list_unlock(priv);
diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
index 81e1e006c540..16a47c0eef37 100644
--- a/net/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -50,35 +50,35 @@ unsigned int ceph_str_hash_rjenkins(const char *str, unsigned int length)
 	switch (len) {
 	case 11:
 		c = c + ((__u32)k[10] << 24);
-		/* fall through */
+		fallthrough;
 	case 10:
 		c = c + ((__u32)k[9] << 16);
-		/* fall through */
+		fallthrough;
 	case 9:
 		c = c + ((__u32)k[8] << 8);
 		/* the first byte of c is reserved for the length */
-		/* fall through */
+		fallthrough;
 	case 8:
 		b = b + ((__u32)k[7] << 24);
-		/* fall through */
+		fallthrough;
 	case 7:
 		b = b + ((__u32)k[6] << 16);
-		/* fall through */
+		fallthrough;
 	case 6:
 		b = b + ((__u32)k[5] << 8);
-		/* fall through */
+		fallthrough;
 	case 5:
 		b = b + k[4];
-		/* fall through */
+		fallthrough;
 	case 4:
 		a = a + ((__u32)k[3] << 24);
-		/* fall through */
+		fallthrough;
 	case 3:
 		a = a + ((__u32)k[2] << 16);
-		/* fall through */
+		fallthrough;
 	case 2:
 		a = a + ((__u32)k[1] << 8);
-		/* fall through */
+		fallthrough;
 	case 1:
 		a = a + k[0];
 		/* case 0: nothing left to add */
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 07e5614eb3f1..7057f8db4f99 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -987,7 +987,7 @@ int crush_do_rule(const struct crush_map *map,
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
 		case CRUSH_RULE_CHOOSE_FIRSTN:
 			firstn = 1;
-			/* fall through */
+			fallthrough;
 		case CRUSH_RULE_CHOOSELEAF_INDEP:
 		case CRUSH_RULE_CHOOSE_INDEP:
 			if (wsize == 0)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 27d6ab11f9ee..bdfd66ba3843 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -412,7 +412,7 @@ static void ceph_sock_state_change(struct sock *sk)
 	switch (sk->sk_state) {
 	case TCP_CLOSE:
 		dout("%s TCP_CLOSE\n", __func__);
-		/* fall through */
+		fallthrough;
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
 		con_sock_state_closing(con);
@@ -2751,7 +2751,7 @@ more:
 			switch (ret) {
 			case -EBADMSG:
 				con->error_msg = "bad crc/signature";
-				/* fall through */
+				fallthrough;
 			case -EBADE:
 				ret = -EIO;
 				break;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 3d8c8015e976..d633a0aeaa55 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1307,7 +1307,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 		 * request had a non-zero tid.  Work around this weirdness
 		 * by allocating a new message.
 		 */
-		/* fall through */
+		fallthrough;
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index e4fbcad6e7d8..7901ab6c79fd 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3854,7 +3854,7 @@ static void scan_requests(struct ceph_osd *osd,
 			if (!force_resend && !force_resend_writes)
 				break;
 
-			/* fall through */
+			fallthrough;
 		case CALC_TARGET_NEED_RESEND:
 			cancel_linger_map_check(lreq);
 			/*
@@ -3891,7 +3891,7 @@ static void scan_requests(struct ceph_osd *osd,
 			     !force_resend_writes))
 				break;
 
-			/* fall through */
+			fallthrough;
 		case CALC_TARGET_NEED_RESEND:
 			cancel_map_check(req);
 			unlink_request(osd, req);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7df6c9617321..4086d335978c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4690,10 +4690,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(skb->dev, xdp_prog, act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 	do_drop:
 		kfree_skb(skb);
@@ -6612,12 +6612,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		netdev_err_once(dev, "%s() called with weight %d\n", __func__,
 				weight);
 	napi->weight = weight;
-	list_add(&napi->dev_list, &dev->napi_list);
 	napi->dev = dev;
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
 	set_bit(NAPI_STATE_SCHED, &napi->state);
+	set_bit(NAPI_STATE_NPSVC, &napi->state);
+	list_add_rcu(&napi->dev_list, &dev->napi_list);
 	napi_hash_add(napi);
 }
 EXPORT_SYMBOL(netif_napi_add);
@@ -8742,13 +8743,15 @@ struct bpf_xdp_link {
 	int flags;
 };
 
-static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
+static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags)
 {
 	if (flags & XDP_FLAGS_HW_MODE)
 		return XDP_MODE_HW;
 	if (flags & XDP_FLAGS_DRV_MODE)
 		return XDP_MODE_DRV;
-	return XDP_MODE_SKB;
+	if (flags & XDP_FLAGS_SKB_MODE)
+		return XDP_MODE_SKB;
+	return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB;
 }
 
 static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
@@ -8896,7 +8899,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EINVAL;
 	}
 
-	mode = dev_xdp_mode(flags);
+	mode = dev_xdp_mode(dev, flags);
 	/* can't replace attached link */
 	if (dev_xdp_link(dev, mode)) {
 		NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
@@ -8913,10 +8916,6 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		NL_SET_ERR_MSG(extack, "Active program does not match expected");
 		return -EEXIST;
 	}
-	if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
-		NL_SET_ERR_MSG(extack, "XDP program already attached");
-		return -EBUSY;
-	}
 
 	/* put effective new program into new_prog */
 	if (link)
@@ -8927,6 +8926,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
 					       ? XDP_MODE_DRV : XDP_MODE_SKB;
 
+		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
+			NL_SET_ERR_MSG(extack, "XDP program already attached");
+			return -EBUSY;
+		}
 		if (!offload && dev_xdp_prog(dev, other_mode)) {
 			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;
@@ -8984,7 +8987,7 @@ static int dev_xdp_detach_link(struct net_device *dev,
 
 	ASSERT_RTNL();
 
-	mode = dev_xdp_mode(link->flags);
+	mode = dev_xdp_mode(dev, link->flags);
 	if (dev_xdp_link(dev, mode) != link)
 		return -EINVAL;
 
@@ -9080,7 +9083,7 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 		goto out_unlock;
 	}
 
-	mode = dev_xdp_mode(xdp_link->flags);
+	mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags);
 	bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode);
 	err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL,
 			      xdp_link->flags, new_prog);
@@ -9164,7 +9167,7 @@ out_put_dev:
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags)
 {
-	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
+	enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags);
 	struct bpf_prog *new_prog = NULL, *old_prog = NULL;
 	int err;
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index b2cf9b7bb7b8..205e92e604ef 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -322,7 +322,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		err = net_hwtstamp_validate(ifr);
 		if (err)
 			return err;
-		/* fall through */
+		fallthrough;
 
 	/*
 	 *	Unknown or private ioctl
@@ -478,7 +478,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c
 	case SIOCSIFTXQLEN:
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-		/* fall through */
+		fallthrough;
 	/*
 	 *	These ioctl calls:
 	 *	- require local superuser power.
@@ -503,7 +503,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c
 	case SIOCSHWTSTAMP:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
-		/* fall through */
+		fallthrough;
 	case SIOCBONDSLAVEINFOQUERY:
 	case SIOCBONDINFOQUERY:
 		dev_load(net, ifr->ifr_name);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e674f0f46dc2..80ec1cd81c64 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4063,7 +4063,7 @@ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id)
 {
 	lockdep_assert_held(&devlink->lock);
 
-	if (WARN_ON(xa_load(&devlink->snapshot_ids, id)))
+	if (xa_load(&devlink->snapshot_ids, id))
 		return -EEXIST;
 
 	return xa_err(xa_store(&devlink->snapshot_ids, id, xa_mk_value(0),
@@ -6196,8 +6196,8 @@ devlink_trap_action_get_from_info(struct genl_info *info,
 
 	val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]);
 	switch (val) {
-	case DEVLINK_TRAP_ACTION_DROP: /* fall-through */
-	case DEVLINK_TRAP_ACTION_TRAP: /* fall-through */
+	case DEVLINK_TRAP_ACTION_DROP:
+	case DEVLINK_TRAP_ACTION_TRAP:
 	case DEVLINK_TRAP_ACTION_MIRROR:
 		*p_trap_action = val;
 		break;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b09bebeadf0b..9704522b0872 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1189,7 +1189,7 @@ static int net_dm_alert_mode_get_from_info(struct genl_info *info,
 	val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]);
 
 	switch (val) {
-	case NET_DM_ALERT_MODE_SUMMARY: /* fall-through */
+	case NET_DM_ALERT_MODE_SUMMARY:
 	case NET_DM_ALERT_MODE_PACKET:
 		*p_alert_mode = val;
 		break;
diff --git a/net/core/filter.c b/net/core/filter.c
index 7124f0fe6974..1f647ab986b6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8317,15 +8317,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 /* Helper macro for adding read access to tcp_sock or sock fields. */
 #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
 	do {								      \
+		int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2;     \
 		BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) >		      \
 			     sizeof_field(struct bpf_sock_ops, BPF_FIELD));   \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == si->src_reg) {			      \
+			*insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg,	      \
+					  offsetof(struct bpf_sock_ops_kern,  \
+					  temp));			      \
+			fullsock_reg = reg;				      \
+			jmp += 2;					      \
+		}							      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
 						is_fullsock),		      \
-				      si->dst_reg, si->src_reg,		      \
+				      fullsock_reg, si->src_reg,	      \
 				      offsetof(struct bpf_sock_ops_kern,      \
 					       is_fullsock));		      \
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2);	      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
+		if (si->dst_reg == si->src_reg)				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern, sk),\
 				      si->dst_reg, si->src_reg,		      \
@@ -8334,6 +8350,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 						       OBJ_FIELD),	      \
 				      si->dst_reg, si->dst_reg,		      \
 				      offsetof(OBJ, OBJ_FIELD));	      \
+		if (si->dst_reg == si->src_reg)	{			      \
+			*insn++ = BPF_JMP_A(1);				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		}							      \
+	} while (0)
+
+#define SOCK_OPS_GET_SK()							      \
+	do {								      \
+		int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1;     \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == si->src_reg) {			      \
+			*insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg,	      \
+					  offsetof(struct bpf_sock_ops_kern,  \
+					  temp));			      \
+			fullsock_reg = reg;				      \
+			jmp += 2;					      \
+		}							      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern,     \
+						is_fullsock),		      \
+				      fullsock_reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       is_fullsock));		      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
+		if (si->dst_reg == si->src_reg)				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern, sk),\
+				      si->dst_reg, si->src_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern, sk));\
+		if (si->dst_reg == si->src_reg)	{			      \
+			*insn++ = BPF_JMP_A(1);				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		}							      \
 	} while (0)
 
 #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \
@@ -8620,17 +8679,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked);
 		break;
 	case offsetof(struct bpf_sock_ops, sk):
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
-						struct bpf_sock_ops_kern,
-						is_fullsock),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct bpf_sock_ops_kern,
-					       is_fullsock));
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
-						struct bpf_sock_ops_kern, sk),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct bpf_sock_ops_kern, sk));
+		SOCK_OPS_GET_SK();
 		break;
 	}
 	return insn - insn_buf;
@@ -9174,7 +9223,7 @@ sk_reuseport_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
 			return false;
-		/* fall through */
+		fallthrough;
 	case bpf_ctx_range(struct sk_reuseport_md, ip_protocol):
 	case bpf_ctx_range(struct sk_reuseport_md, bind_inany):
 	case bpf_ctx_range(struct sk_reuseport_md, len):
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 093e90e52bc2..2338753e936b 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -162,7 +162,7 @@ static void poll_napi(struct net_device *dev)
 	struct napi_struct *napi;
 	int cpu = smp_processor_id();
 
-	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+	list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
 		if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) {
 			poll_one_napi(napi);
 			smp_store_release(&napi->poll_owner, -1);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b53b6d38c4df..44fdbb9c6e53 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3430,7 +3430,7 @@ xmit_more:
 		net_info_ratelimited("%s xmit error: %d\n",
 				     pkt_dev->odevname, ret);
 		pkt_dev->errors++;
-		/* fall through */
+		fallthrough;
 	case NETDEV_TX_BUSY:
 		/* Retry it next time */
 		refcount_dec(&(pkt_dev->skb->users));
@@ -3699,7 +3699,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 				   cpu_to_node(cpu),
 				   "kpktgend_%d", cpu);
 	if (IS_ERR(p)) {
-		pr_err("kernel_thread() failed for cpu %d\n", t->cpu);
+		pr_err("kthread_create_on_node() failed for cpu %d\n", t->cpu);
 		list_del(&t->th_list);
 		kfree(t);
 		return PTR_ERR(p);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7e2e502ef519..6faf73d6a0f7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -820,6 +820,7 @@ void skb_tx_error(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(skb_tx_error);
 
+#ifdef CONFIG_TRACEPOINTS
 /**
  *	consume_skb - free an skbuff
  *	@skb: buffer to free
@@ -837,6 +838,7 @@ void consume_skb(struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 EXPORT_SYMBOL(consume_skb);
+#endif
 
 /**
  *	consume_stateless_skb - free an skbuff, assuming it is stateless
@@ -5418,8 +5420,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		goto err_free;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+	/* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short))))
 		goto err_free;
 
 	vhdr = (struct vlan_hdr *)skb->data;
@@ -5987,9 +5989,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 	if (skb_has_frag_list(skb))
 		skb_clone_fraglist(skb);
 
-	if (k == 0) {
-		/* split line is in frag list */
-		pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask);
+	/* split line is in frag list */
+	if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) {
+		/* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */
+		if (skb_has_frag_list(skb))
+			kfree_skb_list(skb_shinfo(skb)->frag_list);
+		kfree(data);
+		return -ENOMEM;
 	}
 	skb_release_data(skb);
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6a32a1fd34f8..649583158983 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -772,7 +772,6 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_DROP:
-		/* fall-through */
 	default:
 out_free:
 		kfree_skb(skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index e4f40b175acb..6c5c6b18eff4 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1008,7 +1008,7 @@ set_sndbuf:
 		break;
 	case SO_TIMESTAMPING_NEW:
 		sock_set_flag(sk, SOCK_TSTAMP_NEW);
-		/* fall through */
+		fallthrough;
 	case SO_TIMESTAMPING_OLD:
 		if (val & ~SOF_TIMESTAMPING_MASK) {
 			ret = -EINVAL;
@@ -3254,7 +3254,7 @@ void sk_common_release(struct sock *sk)
 		sk->sk_prot->destroy(sk);
 
 	/*
-	 * Observation: when sock_common_release is called, processes have
+	 * Observation: when sk_common_release is called, processes have
 	 * no access to socket. But net still has.
 	 * Step one, detach it from networking:
 	 *
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index aef72f6a2829..b9ee1a4a8955 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -608,7 +608,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 		 */
 		if (hc->rx_x_recv > 0)
 			break;
-		/* fall through */
+		fallthrough;
 	case CCID3_FBACK_PERIODIC:
 		delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
 		if (delta <= 0)
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index afc071ea1271..788dd629c420 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1407,7 +1407,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 	 *	Negotiation during connection setup
 	 */
 	case DCCP_LISTEN:
-		server = true;			/* fall through */
+		server = true;
+		fallthrough;
 	case DCCP_REQUESTING:
 		switch (opt) {
 		case DCCPO_CHANGE_L:
diff --git a/net/dccp/input.c b/net/dccp/input.c
index bd9cfdb67436..2cbb757a894f 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -64,7 +64,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
 		 */
 		if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT)
 			break;
-		/* fall through */
+		fallthrough;
 	case DCCP_REQUESTING:
 	case DCCP_ACTIVE_CLOSEREQ:
 		dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
@@ -76,7 +76,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
 		queued = 1;
 		dccp_fin(sk, skb);
 		dccp_set_state(sk, DCCP_PASSIVE_CLOSE);
-		/* fall through */
+		fallthrough;
 	case DCCP_PASSIVE_CLOSE:
 		/*
 		 * Retransmitted Close: we have already enqueued the first one.
@@ -113,7 +113,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
 		queued = 1;
 		dccp_fin(sk, skb);
 		dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ);
-		/* fall through */
+		fallthrough;
 	case DCCP_PASSIVE_CLOSEREQ:
 		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
 	}
@@ -530,7 +530,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
 	case DCCP_PKT_DATA:
 		if (sk->sk_state == DCCP_RESPOND)
 			break;
-		/* fall through */
+		fallthrough;
 	case DCCP_PKT_DATAACK:
 	case DCCP_PKT_ACK:
 		/*
@@ -684,7 +684,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Step 8: if using Ack Vectors, mark packet acknowledgeable */
 		dccp_handle_ackvec_processing(sk, skb);
 		dccp_deliver_input_to_ccids(sk, skb);
-		/* fall through */
+		fallthrough;
 	case DCCP_RESPOND:
 		queued = dccp_rcv_respond_partopen_state_process(sk, skb,
 								 dh, len);
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 51aaba7a5d45..d24cad05001e 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -225,7 +225,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 			 * interested. The RX CCID need not parse Ack Vectors,
 			 * since it is only interested in clearing old state.
 			 */
-			/* fall through */
+			fallthrough;
 		case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
 			if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
 						     pkt_type, opt, value, len))
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 6433187a5cc4..50e6d5699bb2 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -62,7 +62,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 		switch (dcb->dccpd_type) {
 		case DCCP_PKT_DATA:
 			set_ack = 0;
-			/* fall through */
+			fallthrough;
 		case DCCP_PKT_DATAACK:
 		case DCCP_PKT_RESET:
 			break;
@@ -72,12 +72,12 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 			/* Use ISS on the first (non-retransmitted) Request. */
 			if (icsk->icsk_retransmits == 0)
 				dcb->dccpd_seq = dp->dccps_iss;
-			/* fall through */
+			fallthrough;
 
 		case DCCP_PKT_SYNC:
 		case DCCP_PKT_SYNCACK:
 			ackno = dcb->dccpd_ack_seq;
-			/* fall through */
+			fallthrough;
 		default:
 			/*
 			 * Set owner/destructor: some skbs are allocated via
@@ -481,7 +481,7 @@ struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb)
 	case DCCP_RESET_CODE_PACKET_ERROR:
 		dhr->dccph_reset_data[0] = rxdh->dccph_type;
 		break;
-	case DCCP_RESET_CODE_OPTION_ERROR:	/* fall through */
+	case DCCP_RESET_CODE_OPTION_ERROR:
 	case DCCP_RESET_CODE_MANDATORY_ERROR:
 		memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3);
 		break;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index d148ab1530e5..6d705d90c614 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -101,7 +101,7 @@ void dccp_set_state(struct sock *sk, const int state)
 		if (inet_csk(sk)->icsk_bind_hash != NULL &&
 		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
 			inet_put_port(sk);
-		/* fall through */
+		fallthrough;
 	default:
 		if (oldstate == DCCP_OPEN)
 			DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
@@ -834,7 +834,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		case DCCP_PKT_CLOSEREQ:
 			if (!(flags & MSG_PEEK))
 				dccp_finish_passive_close(sk);
-			/* fall through */
+			fallthrough;
 		case DCCP_PKT_RESET:
 			dccp_pr_debug("found fin (%s) ok!\n",
 				      dccp_packet_name(dh->dccph_type));
@@ -960,7 +960,7 @@ static void dccp_terminate_connection(struct sock *sk)
 	case DCCP_PARTOPEN:
 		dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk);
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
-		/* fall through */
+		fallthrough;
 	case DCCP_OPEN:
 		dccp_send_close(sk, 1);
 
@@ -969,7 +969,7 @@ static void dccp_terminate_connection(struct sock *sk)
 			next_state = DCCP_ACTIVE_CLOSEREQ;
 		else
 			next_state = DCCP_CLOSING;
-		/* fall through */
+		fallthrough;
 	default:
 		dccp_set_state(sk, next_state);
 	}
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 3b53d766789d..5dbd45dc35ad 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -623,12 +623,12 @@ static void dn_destroy_sock(struct sock *sk)
 		goto disc_reject;
 	case DN_RUN:
 		scp->state = DN_DI;
-		/* fall through */
+		fallthrough;
 	case DN_DI:
 	case DN_DR:
 disc_reject:
 		dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation);
-		/* fall through */
+		fallthrough;
 	case DN_NC:
 	case DN_NR:
 	case DN_RJ:
@@ -642,7 +642,7 @@ disc_reject:
 		break;
 	default:
 		printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n");
-		/* fall through */
+		fallthrough;
 	case DN_O:
 		dn_stop_slow_timer(sk);
 
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index c68503a18025..c97bdca5ec30 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -483,7 +483,7 @@ static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb)
 		break;
 	case DN_RUN:
 		sk->sk_shutdown |= SHUTDOWN_MASK;
-		/* fall through */
+		fallthrough;
 	case DN_CC:
 		scp->state = DN_CN;
 	}
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 33fefb0aebca..4086f9c746af 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -156,7 +156,7 @@ static void dn_rehash_zone(struct dn_zone *dz)
 	default:
 		printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n",
 		       old_divisor);
-		/* fall through */
+		fallthrough;
 	case 256:
 		new_divisor = 1024;
 		new_hashmask = 0x3FF;
diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c
index deae519bdeec..67b5ab2657b7 100644
--- a/net/decnet/sysctl_net_decnet.c
+++ b/net/decnet/sysctl_net_decnet.c
@@ -75,7 +75,7 @@ static void strip_it(char *str)
 		case '\r':
 		case ':':
 			*str = 0;
-			/* Fallthrough */
+			fallthrough;
 		case 0:
 			return;
 		}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 41d60eeefdbd..9af1a2d0cec4 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -2009,7 +2009,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused,
 	switchdev_work->event = event;
 
 	switch (event) {
-	case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr))
 			goto err_fdb_work_init;
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 4e632dc987d8..495635f152ba 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT);
 	struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1];
@@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 
 	rtnl_lock();
 	ethnl_features_to_bitmap(old_active, dev->features);
+	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
@@ -261,17 +264,15 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 		goto out_rtnl;
 	}
 
-	/* set req_wanted bits not in req_mask from old_active */
+	/* set req_wanted bits not in req_mask from old_wanted */
 	bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT);
-	if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) {
-		ret = 0;
-		goto out_rtnl;
+	bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT);
+	bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT);
+	if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
+		dev->wanted_features &= ~dev->hw_features;
+		dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
+		__netdev_update_features(dev);
 	}
-
-	dev->wanted_features = ethnl_bitmap_to_features(req_wanted);
-	__netdev_update_features(dev);
 	ethnl_features_to_bitmap(new_active, dev->features);
 	mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT);
 
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index bbe9b3b2d395..be6f06adefe0 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -195,7 +195,7 @@ static int lowpan_frag_rx_handlers_result(struct sk_buff *skb,
 		net_warn_ratelimited("%s: received unknown dispatch\n",
 				     __func__);
 
-		/* fall-through */
+		fallthrough;
 	default:
 		/* all others failure */
 		return NET_RX_DROP;
diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c
index b34d050c9687..517e6493f5d1 100644
--- a/net/ieee802154/6lowpan/rx.c
+++ b/net/ieee802154/6lowpan/rx.c
@@ -35,11 +35,11 @@ static int lowpan_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res)
 		net_warn_ratelimited("%s: received unknown dispatch\n",
 				     __func__);
 
-		/* fall-through */
+		fallthrough;
 	case RX_DROP_UNUSABLE:
 		kfree_skb(skb);
 
-		/* fall-through */
+		fallthrough;
 	case RX_DROP:
 		return NET_RX_DROP;
 	case RX_QUEUED:
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 60db5a6487cc..87983e70f03f 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -661,13 +661,13 @@ config TCP_CONG_BBR
 
 	  BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
 	  maximize network utilization and minimize queues. It builds an explicit
-	  model of the the bottleneck delivery rate and path round-trip
-	  propagation delay. It tolerates packet loss and delay unrelated to
-	  congestion. It can operate over LAN, WAN, cellular, wifi, or cable
-	  modem links. It can coexist with flows that use loss-based congestion
-	  control, and can operate with shallow buffers, deep buffers,
-	  bufferbloat, policers, or AQM schemes that do not provide a delay
-	  signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+	  model of the bottleneck delivery rate and path round-trip propagation
+	  delay. It tolerates packet loss and delay unrelated to congestion. It
+	  can operate over LAN, WAN, cellular, wifi, or cable modem links. It can
+	  coexist with flows that use loss-based congestion control, and can
+	  operate with shallow buffers, deep buffers, bufferbloat, policers, or
+	  AQM schemes that do not provide a delay signal. It requires the fq
+	  ("Fair Queue") pacing packet scheduler.
 
 choice
 	prompt "Default TCP congestion control"
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index c89b46fec153..ffc5332f1390 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2121,7 +2121,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info)
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
 		struct fib_table *tb;
 
-		hlist_for_each_entry_rcu(tb, head, tb_hlist)
+		hlist_for_each_entry_rcu(tb, head, tb_hlist,
+					 lockdep_rtnl_is_held())
 			__fib_info_notify_update(net, tb, info);
 	}
 }
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 7afde8828b4c..3f248a19faa3 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -3,7 +3,7 @@
  * nf_nat_pptp.c
  *
  * NAT support for PPTP (Point to Point Tunneling Protocol).
- * PPTP is a a protocol for creating virtual private networks.
+ * PPTP is a protocol for creating virtual private networks.
  * It is a specification defined by Microsoft and some vendors
  * working with Microsoft.  PPTP is built on top of a modified
  * version of the Internet Generic Routing Encapsulation Protocol.
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index cc8049b100b2..134e92382275 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -446,7 +446,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	unsigned int i, j;
 	u8 nhg_fdb = 0;
 
-	if (len & (sizeof(struct nexthop_grp) - 1)) {
+	if (!len || len & (sizeof(struct nexthop_grp) - 1)) {
 		NL_SET_ERR_MSG(extack,
 			       "Invalid length for nexthop group attribute");
 		return -EINVAL;
@@ -1187,6 +1187,9 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	struct nexthop *nh;
 	int i;
 
+	if (WARN_ON(!num_nh))
+		return ERR_PTR(-EINVAL);
+
 	nh = nexthop_alloc();
 	if (!nh)
 		return ERR_PTR(-ENOMEM);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6fd4330287c2..407956be7deb 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	} else if (!ipc.oif) {
 		ipc.oif = inet->uc_index;
 	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
-		/* oif is set, packet is to local broadcast and
+		/* oif is set, packet is to local broadcast
 		 * and uc_index is set. oif is most likely set
 		 * by sk_bound_dev_if. If uc_index != oif check if the
 		 * oif is an L3 master and uc_index is an L3 slave.
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8e761b8c47c6..01146b66d666 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1893,12 +1893,13 @@ EXPORT_SYMBOL(ipv6_chk_addr);
  *   2. does the address exist on the specific device
  *      (skip_dev_check = false)
  */
-int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
-			    const struct net_device *dev, bool skip_dev_check,
-			    int strict, u32 banned_flags)
+static struct net_device *
+__ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			  const struct net_device *dev, bool skip_dev_check,
+			  int strict, u32 banned_flags)
 {
 	unsigned int hash = inet6_addr_hash(net, addr);
-	const struct net_device *l3mdev;
+	struct net_device *l3mdev, *ndev;
 	struct inet6_ifaddr *ifp;
 	u32 ifp_flags;
 
@@ -1909,10 +1910,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 		dev = NULL;
 
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
-		if (!net_eq(dev_net(ifp->idev->dev), net))
+		ndev = ifp->idev->dev;
+		if (!net_eq(dev_net(ndev), net))
 			continue;
 
-		if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev)
+		if (l3mdev_master_dev_rcu(ndev) != l3mdev)
 			continue;
 
 		/* Decouple optimistic from tentative for evaluation here.
@@ -1923,15 +1925,23 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 			    : ifp->flags;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
 		    !(ifp_flags&banned_flags) &&
-		    (!dev || ifp->idev->dev == dev ||
+		    (!dev || ndev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
 			rcu_read_unlock();
-			return 1;
+			return ndev;
 		}
 	}
 
 	rcu_read_unlock();
-	return 0;
+	return NULL;
+}
+
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			    const struct net_device *dev, bool skip_dev_check,
+			    int strict, u32 banned_flags)
+{
+	return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check,
+					 strict, banned_flags) ? 1 : 0;
 }
 EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
@@ -1990,35 +2000,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
  *
  * The caller should be protected by RCU, or RTNL.
  */
-struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr)
+struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr,
+				 struct net_device *dev)
 {
-	unsigned int hash = inet6_addr_hash(net, addr);
-	struct inet6_ifaddr *ifp, *result = NULL;
-	struct net_device *dev = NULL;
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
-		if (net_eq(dev_net(ifp->idev->dev), net) &&
-		    ipv6_addr_equal(&ifp->addr, addr)) {
-			result = ifp;
-			break;
-		}
-	}
-
-	if (!result) {
-		struct rt6_info *rt;
-
-		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
-		if (rt) {
-			dev = rt->dst.dev;
-			ip6_rt_put(rt);
-		}
-	} else {
-		dev = result->idev->dev;
-	}
-	rcu_read_unlock();
-
-	return dev;
+	return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1,
+					 IFA_F_TENTATIVE);
 }
 EXPORT_SYMBOL(ipv6_dev_find);
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f635914f42ec..a0217e5bf3bc 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -915,7 +915,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
 		struct metadata_dst *tun_dst,
 		bool log_ecn_err)
 {
-	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
+	int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+				    const struct ipv6hdr *ipv6h,
+				    struct sk_buff *skb);
+
+	dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate;
+	if (tpi->proto == htons(ETH_P_IP))
+		dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate;
+
+	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 			     log_ecn_err);
 }
 EXPORT_SYMBOL(ip6_tnl_rcv);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 409e79b84a83..6d0e942d082d 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = {
 	.route_input		= ip6_route_input,
 	.fragment		= ip6_fragment,
 	.reroute		= nf_ip6_reroute,
-#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-	.br_defrag		= nf_ct_frag6_gather,
-#endif
 #if IS_MODULE(CONFIG_IPV6)
 	.br_fragment		= br_ip6_fragment,
 #endif
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index fac2135aa47b..5b60a4bdd36a 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -21,6 +21,7 @@
 #include <net/calipso.h>
 #endif
 
+static int two = 2;
 static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_min;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
@@ -150,7 +151,7 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler   = proc_rt6_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "seg6_flowlabel",
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 6ee9851ac7c6..a95af62acb52 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -418,7 +418,7 @@ static void iucv_sock_close(struct sock *sk)
 			sk->sk_state = IUCV_DISCONN;
 			sk->sk_state_change(sk);
 		}
-		/* fall through */
+		fallthrough;
 
 	case IUCV_DISCONN:
 		sk->sk_state = IUCV_CLOSING;
@@ -433,7 +433,7 @@ static void iucv_sock_close(struct sock *sk)
 					iucv_sock_in_state(sk, IUCV_CLOSED, 0),
 					timeo);
 		}
-		/* fall through */
+		fallthrough;
 
 	case IUCV_CLOSING:
 		sk->sk_state = IUCV_CLOSED;
@@ -444,7 +444,7 @@ static void iucv_sock_close(struct sock *sk)
 
 		skb_queue_purge(&iucv->send_skb_q);
 		skb_queue_purge(&iucv->backlog_skb_q);
-		/* fall through */
+		fallthrough;
 
 	default:
 		iucv_sever_path(sk, 1);
@@ -2111,10 +2111,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev,
 			kfree_skb(skb);
 			break;
 		}
-		/* fall through - and receive non-zero length data */
+		fallthrough;	/* and receive non-zero length data */
 	case (AF_IUCV_FLAG_SHT):
 		/* shutdown request */
-		/* fall through - and receive zero length data */
+		fallthrough;	/* and receive zero length data */
 	case 0:
 		/* plain data frame */
 		IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class;
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index e71ca5aec684..864326f150e2 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
 EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu);
 
 /**
- *	l3mdev_fib_table - get FIB table id associated with an L3
+ *	l3mdev_fib_table_rcu - get FIB table id associated with an L3
  *                             master interface
  *	@dev: targeted interface
  */
diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c
index 366f76c9003d..314973033d03 100644
--- a/net/mac80211/airtime.c
+++ b/net/mac80211/airtime.c
@@ -405,18 +405,14 @@ ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre,
 	return duration;
 }
 
-u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
-			      struct ieee80211_rx_status *status,
-			      int len)
+static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw,
+				       struct ieee80211_rx_status *status,
+				       u32 *overhead)
 {
-	struct ieee80211_supported_band *sband;
-	const struct ieee80211_rate *rate;
 	bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI;
-	bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE;
 	int bw, streams;
 	int group, idx;
 	u32 duration;
-	bool cck;
 
 	switch (status->bw) {
 	case RATE_INFO_BW_20:
@@ -437,20 +433,6 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
 	}
 
 	switch (status->encoding) {
-	case RX_ENC_LEGACY:
-		if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ))
-			return 0;
-
-		sband = hw->wiphy->bands[status->band];
-		if (!sband || status->rate_idx >= sband->n_bitrates)
-			return 0;
-
-		rate = &sband->bitrates[status->rate_idx];
-		cck = rate->flags & IEEE80211_RATE_MANDATORY_B;
-
-		return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp,
-							   cck, len);
-
 	case RX_ENC_VHT:
 		streams = status->nss;
 		idx = status->rate_idx;
@@ -477,51 +459,144 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
 
 	duration = airtime_mcs_groups[group].duration[idx];
 	duration <<= airtime_mcs_groups[group].shift;
+	*overhead = 36 + (streams << 2);
+
+	return duration;
+}
+
+
+u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
+			      struct ieee80211_rx_status *status,
+			      int len)
+{
+	struct ieee80211_supported_band *sband;
+	u32 duration, overhead = 0;
+
+	if (status->encoding == RX_ENC_LEGACY) {
+		const struct ieee80211_rate *rate;
+		bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE;
+		bool cck;
+
+		if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ))
+			return 0;
+
+		sband = hw->wiphy->bands[status->band];
+		if (!sband || status->rate_idx >= sband->n_bitrates)
+			return 0;
+
+		rate = &sband->bitrates[status->rate_idx];
+		cck = rate->flags & IEEE80211_RATE_MANDATORY_B;
+
+		return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp,
+							   cck, len);
+	}
+
+	duration = ieee80211_get_rate_duration(hw, status, &overhead);
+	if (!duration)
+		return 0;
+
 	duration *= len;
 	duration /= AVG_PKT_SIZE;
 	duration /= 1024;
 
-	duration += 36 + (streams << 2);
-
-	return duration;
+	return duration + overhead;
 }
 EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime);
 
-static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw,
-					  struct ieee80211_tx_rate *rate,
-					  u8 band, int len)
+static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw,
+				     struct ieee80211_rx_status *stat, u8 band,
+				     struct rate_info *ri)
 {
-	struct ieee80211_rx_status stat = {
-		.band = band,
-	};
+	struct ieee80211_supported_band *sband = hw->wiphy->bands[band];
+	int i;
 
-	if (rate->idx < 0 || !rate->count)
+	if (!ri || !sband)
+	    return false;
+
+	stat->bw = ri->bw;
+	stat->nss = ri->nss;
+	stat->rate_idx = ri->mcs;
+
+	if (ri->flags & RATE_INFO_FLAGS_HE_MCS)
+		stat->encoding = RX_ENC_HE;
+	else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS)
+		stat->encoding = RX_ENC_VHT;
+	else if (ri->flags & RATE_INFO_FLAGS_MCS)
+		stat->encoding = RX_ENC_HT;
+	else
+		stat->encoding = RX_ENC_LEGACY;
+
+	if (ri->flags & RATE_INFO_FLAGS_SHORT_GI)
+		stat->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	stat->he_gi = ri->he_gi;
+
+	if (stat->encoding != RX_ENC_LEGACY)
+		return true;
+
+	stat->rate_idx = 0;
+	for (i = 0; i < sband->n_bitrates; i++) {
+		if (ri->legacy != sband->bitrates[i].bitrate)
+			continue;
+
+		stat->rate_idx = i;
+		return true;
+	}
+
+	return false;
+}
+
+static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat,
+				    struct ieee80211_hw *hw,
+				    struct ieee80211_tx_rate *rate,
+				    struct rate_info *ri, u8 band, int len)
+{
+	memset(stat, 0, sizeof(*stat));
+	stat->band = band;
+
+	if (ieee80211_fill_rate_info(hw, stat, band, ri))
 		return 0;
 
+	if (rate->idx < 0 || !rate->count)
+		return -1;
+
 	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-		stat.bw = RATE_INFO_BW_80;
+		stat->bw = RATE_INFO_BW_80;
 	else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-		stat.bw = RATE_INFO_BW_40;
+		stat->bw = RATE_INFO_BW_40;
 	else
-		stat.bw = RATE_INFO_BW_20;
+		stat->bw = RATE_INFO_BW_20;
 
-	stat.enc_flags = 0;
+	stat->enc_flags = 0;
 	if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
-		stat.enc_flags |= RX_ENC_FLAG_SHORTPRE;
+		stat->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-		stat.enc_flags |= RX_ENC_FLAG_SHORT_GI;
+		stat->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
-	stat.rate_idx = rate->idx;
+	stat->rate_idx = rate->idx;
 	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
-		stat.encoding = RX_ENC_VHT;
-		stat.rate_idx = ieee80211_rate_get_vht_mcs(rate);
-		stat.nss = ieee80211_rate_get_vht_nss(rate);
+		stat->encoding = RX_ENC_VHT;
+		stat->rate_idx = ieee80211_rate_get_vht_mcs(rate);
+		stat->nss = ieee80211_rate_get_vht_nss(rate);
 	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		stat.encoding = RX_ENC_HT;
+		stat->encoding = RX_ENC_HT;
 	} else {
-		stat.encoding = RX_ENC_LEGACY;
+		stat->encoding = RX_ENC_LEGACY;
 	}
 
+	return 0;
+}
+
+static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw,
+					  struct ieee80211_tx_rate *rate,
+					  struct rate_info *ri,
+					  u8 band, int len)
+{
+	struct ieee80211_rx_status stat;
+
+	if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len))
+		return 0;
+
 	return ieee80211_calc_rx_airtime(hw, &stat, len);
 }
 
@@ -536,7 +611,7 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
 		struct ieee80211_tx_rate *rate = &info->status.rates[i];
 		u32 cur_duration;
 
-		cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate,
+		cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, NULL,
 							      info->band, len);
 		if (!cur_duration)
 			break;
@@ -572,26 +647,41 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
 	if (pubsta) {
 		struct sta_info *sta = container_of(pubsta, struct sta_info,
 						    sta);
+		struct ieee80211_rx_status stat;
 		struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate;
-		u32 airtime;
+		struct rate_info *ri = &sta->tx_stats.last_rate_info;
+		u32 duration, overhead;
+		u8 agg_shift;
 
-		if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS |
-				     IEEE80211_TX_RC_MCS)))
-			ampdu = false;
+		if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len))
+			return 0;
 
+		if (stat.encoding == RX_ENC_LEGACY || !ampdu)
+			return ieee80211_calc_rx_airtime(hw, &stat, len);
+
+		duration = ieee80211_get_rate_duration(hw, &stat, &overhead);
 		/*
 		 * Assume that HT/VHT transmission on any AC except VO will
 		 * use aggregation. Since we don't have reliable reporting
-		 * of aggregation length, assume an average of 16.
+		 * of aggregation length, assume an average size based on the
+		 * tx rate.
 		 * This will not be very accurate, but much better than simply
-		 * assuming un-aggregated tx.
+		 * assuming un-aggregated tx in all cases.
 		 */
-		airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band,
-							 ampdu ? len * 16 : len);
-		if (ampdu)
-			airtime /= 16;
-
-		return airtime;
+		if (duration > 400) /* <= VHT20 MCS2 1S */
+			agg_shift = 1;
+		else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */
+			agg_shift = 2;
+		else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */
+			agg_shift = 3;
+		else
+			agg_shift = 4;
+
+		duration *= len;
+		duration /= AVG_PKT_SIZE;
+		duration /= 1024;
+
+		return duration + (overhead >> agg_shift);
 	}
 
 	if (!conf)
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 9d398c9daa4c..d5010116cf4d 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -524,7 +524,7 @@ struct ieee80211_sta_rx_stats {
  * @status_stats.retry_failed: # of frames that failed after retry
  * @status_stats.retry_count: # of retries attempted
  * @status_stats.lost_packets: # of lost packets
- * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet
+ * @status_stats.last_pkt_time: timestamp of last ACKed packet
  * @status_stats.msdu_retries: # of MSDU retries
  * @status_stats.msdu_failed: # of failed MSDUs
  * @status_stats.last_ack: last ack timestamp (jiffies)
@@ -597,7 +597,7 @@ struct sta_info {
 		unsigned long filtered;
 		unsigned long retry_failed, retry_count;
 		unsigned int lost_packets;
-		unsigned long last_tdls_pkt_time;
+		unsigned long last_pkt_time;
 		u64 msdu_retries[IEEE80211_NUM_TIDS + 1];
 		u64 msdu_failed[IEEE80211_NUM_TIDS + 1];
 		unsigned long last_ack;
@@ -611,6 +611,7 @@ struct sta_info {
 		u64 packets[IEEE80211_NUM_ACS];
 		u64 bytes[IEEE80211_NUM_ACS];
 		struct ieee80211_tx_rate last_rate;
+		struct rate_info last_rate_info;
 		u64 msdu[IEEE80211_NUM_TIDS + 1];
 	} tx_stats;
 	u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1];
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index adb1d30ce06e..0794396a7988 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -755,12 +755,16 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
  *  - current throughput (higher value for higher tpt)?
  */
 #define STA_LOST_PKT_THRESHOLD	50
+#define STA_LOST_PKT_TIME	HZ		/* 1 sec since last ACK */
 #define STA_LOST_TDLS_PKT_THRESHOLD	10
 #define STA_LOST_TDLS_PKT_TIME		(10*HZ) /* 10secs since last ACK */
 
 static void ieee80211_lost_packet(struct sta_info *sta,
 				  struct ieee80211_tx_info *info)
 {
+	unsigned long pkt_time = STA_LOST_PKT_TIME;
+	unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD;
+
 	/* If driver relies on its own algorithm for station kickout, skip
 	 * mac80211 packet loss mechanism.
 	 */
@@ -773,21 +777,20 @@ static void ieee80211_lost_packet(struct sta_info *sta,
 		return;
 
 	sta->status_stats.lost_packets++;
-	if (!sta->sta.tdls &&
-	    sta->status_stats.lost_packets < STA_LOST_PKT_THRESHOLD)
-		return;
+	if (sta->sta.tdls) {
+		pkt_time = STA_LOST_TDLS_PKT_TIME;
+		pkt_thr = STA_LOST_PKT_THRESHOLD;
+	}
 
 	/*
 	 * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD
 	 * of the last packets were lost, and that no ACK was received in the
 	 * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss
 	 * mechanism.
+	 * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME
 	 */
-	if (sta->sta.tdls &&
-	    (sta->status_stats.lost_packets < STA_LOST_TDLS_PKT_THRESHOLD ||
-	     time_before(jiffies,
-			 sta->status_stats.last_tdls_pkt_time +
-			 STA_LOST_TDLS_PKT_TIME)))
+	if (sta->status_stats.lost_packets < pkt_thr ||
+	    !time_after(jiffies, sta->status_stats.last_pkt_time + pkt_time))
 		return;
 
 	cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr,
@@ -1033,9 +1036,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 					sta->status_stats.lost_packets = 0;
 
 				/* Track when last TDLS packet was ACKed */
-				if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
-					sta->status_stats.last_tdls_pkt_time =
-						jiffies;
+				sta->status_stats.last_pkt_time = jiffies;
 			} else if (noack_success) {
 				/* nothing to do here, do not account as lost */
 			} else {
@@ -1137,9 +1138,17 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	struct ieee80211_tx_info *info = status->info;
 	struct ieee80211_sta *pubsta = status->sta;
 	struct ieee80211_supported_band *sband;
+	struct sta_info *sta;
 	int retry_count;
 	bool acked, noack_success;
 
+	if (pubsta) {
+		sta = container_of(pubsta, struct sta_info, sta);
+
+		if (status->rate)
+			sta->tx_stats.last_rate_info = *status->rate;
+	}
+
 	if (status->skb)
 		return __ieee80211_tx_status(hw, status);
 
@@ -1154,10 +1163,6 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
 
 	if (pubsta) {
-		struct sta_info *sta;
-
-		sta = container_of(pubsta, struct sta_info, sta);
-
 		if (!acked && !noack_success)
 			sta->status_stats.retry_failed++;
 		sta->status_stats.retry_count += retry_count;
@@ -1168,9 +1173,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 			if (sta->status_stats.lost_packets)
 				sta->status_stats.lost_packets = 0;
 
-			/* Track when last TDLS packet was ACKed */
-			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
-				sta->status_stats.last_tdls_pkt_time = jiffies;
+			/* Track when last packet was ACKed */
+			sta->status_stats.last_pkt_time = jiffies;
 		} else if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
 			return;
 		} else if (noack_success) {
@@ -1259,8 +1263,7 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw,
 			if (sta->status_stats.lost_packets)
 				sta->status_stats.lost_packets = 0;
 
-			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
-				sta->status_stats.last_tdls_pkt_time = jiffies;
+			sta->status_stats.last_pkt_time = jiffies;
 		} else {
 			ieee80211_lost_packet(sta, info);
 		}
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 6fdd0c9f865a..f2868a8a50c3 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1516,7 +1516,7 @@ static void mpls_ifdown(struct net_device *dev, int event)
 			case NETDEV_DOWN:
 			case NETDEV_UNREGISTER:
 				nh_flags |= RTNH_F_DEAD;
-				/* fall through */
+				fallthrough;
 			case NETDEV_CHANGE:
 				nh_flags |= RTNH_F_LINKDOWN;
 				break;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 8c1d1a595701..365ba96c84b0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -193,7 +193,6 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
 			sk->sk_state_change(sk);
 			break;
 		case TCP_CLOSING:
-			fallthrough;
 		case TCP_LAST_ACK:
 			inet_sk_state_store(sk, TCP_CLOSE);
 			sk->sk_state_change(sk);
@@ -725,8 +724,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		if (!psize)
 			return -EINVAL;
 
-		if (!sk_wmem_schedule(sk, psize + dfrag->overhead))
+		if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
+			iov_iter_revert(&msg->msg_iter, psize);
 			return -ENOMEM;
+		}
 	} else {
 		offset = dfrag->offset;
 		psize = min_t(size_t, dfrag->data_len, avail_size);
@@ -737,8 +738,11 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	 */
 	ret = do_tcp_sendpages(ssk, page, offset, psize,
 			       msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
-	if (ret <= 0)
+	if (ret <= 0) {
+		if (!retransmission)
+			iov_iter_revert(&msg->msg_iter, psize);
 		return ret;
+	}
 
 	frag_truesize += ret;
 	if (!retransmission) {
@@ -887,7 +891,6 @@ restart:
 		goto out;
 	}
 
-wait_for_sndbuf:
 	__mptcp_flush_join_list(msk);
 	ssk = mptcp_subflow_get_send(msk);
 	while (!sk_stream_memory_free(sk) ||
@@ -977,7 +980,7 @@ wait_for_sndbuf:
 				 */
 				mptcp_set_timeout(sk, ssk);
 				release_sock(ssk);
-				goto wait_for_sndbuf;
+				goto restart;
 			}
 		}
 	}
@@ -1388,7 +1391,9 @@ static void mptcp_worker(struct work_struct *work)
 	struct mptcp_data_frag *dfrag;
 	u64 orig_write_seq;
 	size_t copied = 0;
-	struct msghdr msg;
+	struct msghdr msg = {
+		.msg_flags = MSG_DONTWAIT,
+	};
 	long timeo = 0;
 
 	lock_sock(sk);
@@ -1421,7 +1426,6 @@ static void mptcp_worker(struct work_struct *work)
 
 	lock_sock(ssk);
 
-	msg.msg_flags = MSG_DONTWAIT;
 	orig_len = dfrag->data_len;
 	orig_offset = dfrag->offset;
 	orig_write_seq = dfrag->data_seq;
@@ -1535,7 +1539,7 @@ static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 	case TCP_LISTEN:
 		if (!(how & RCV_SHUTDOWN))
 			break;
-		/* fall through */
+		fallthrough;
 	case TCP_SYN_SENT:
 		tcp_disconnect(ssk, O_NONBLOCK);
 		break;
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 1f387be7827b..f1be3e3f6425 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -474,7 +474,7 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 	switch (nd->state) {
 	case ncsi_dev_state_suspend:
 		nd->state = ncsi_dev_state_suspend_select;
-		/* Fall through */
+		fallthrough;
 	case ncsi_dev_state_suspend_select:
 		ndp->pending_req_num = 1;
 
@@ -1302,7 +1302,7 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 	switch (nd->state) {
 	case ncsi_dev_state_probe:
 		nd->state = ncsi_dev_state_probe_deselect;
-		/* Fall through */
+		fallthrough;
 	case ncsi_dev_state_probe_deselect:
 		ndp->pending_req_num = 8;
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 32b028853a7c..dc2e7da2742a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -315,7 +315,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
 		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
-		/* fall through */
+		fallthrough;
 	case CHECKSUM_COMPLETE:
 #ifdef CONFIG_IP_VS_IPV6
 		if (af == AF_INET6) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 153d89647c87..68260d91c988 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -318,7 +318,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 		case CHECKSUM_NONE:
 			skb->csum = skb_checksum(skb, udphoff,
 						 skb->len - udphoff, 0);
-			/* fall through */
+			fallthrough;
 		case CHECKSUM_COMPLETE:
 #ifdef CONFIG_IP_VS_IPV6
 			if (af == AF_INET6) {
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 1f44d523b512..5105d4250012 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Connection tracking support for PPTP (Point to Point Tunneling Protocol).
- * PPTP is a a protocol for creating virtual private networks.
+ * PPTP is a protocol for creating virtual private networks.
  * It is a specification defined by Microsoft and some vendors
  * working with Microsoft.  PPTP is built on top of a modified
  * version of the Internet Generic Routing Encapsulation Protocol.
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 4f897b14b606..810cca24b399 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -62,6 +62,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
 	[SCTP_CONNTRACK_HEARTBEAT_ACKED]	= 210 SECS,
 };
 
+#define	SCTP_FLAG_HEARTBEAT_VTAG_FAILED	1
+
 #define sNO SCTP_CONNTRACK_NONE
 #define	sCL SCTP_CONNTRACK_CLOSED
 #define	sCW SCTP_CONNTRACK_COOKIE_WAIT
@@ -369,6 +371,7 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 	u_int32_t offset, count;
 	unsigned int *timeouts;
 	unsigned long map[256 / sizeof(unsigned long)] = { 0 };
+	bool ignore = false;
 
 	if (sctp_error(skb, dataoff, state))
 		return -NF_ACCEPT;
@@ -427,15 +430,39 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 			/* Sec 8.5.1 (D) */
 			if (sh->vtag != ct->proto.sctp.vtag[dir])
 				goto out_unlock;
-		} else if (sch->type == SCTP_CID_HEARTBEAT ||
-			   sch->type == SCTP_CID_HEARTBEAT_ACK) {
+		} else if (sch->type == SCTP_CID_HEARTBEAT) {
+			if (ct->proto.sctp.vtag[dir] == 0) {
+				pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir);
+				ct->proto.sctp.vtag[dir] = sh->vtag;
+			} else if (sh->vtag != ct->proto.sctp.vtag[dir]) {
+				if (test_bit(SCTP_CID_DATA, map) || ignore)
+					goto out_unlock;
+
+				ct->proto.sctp.flags |= SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
+				ct->proto.sctp.last_dir = dir;
+				ignore = true;
+				continue;
+			} else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) {
+				ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
+			}
+		} else if (sch->type == SCTP_CID_HEARTBEAT_ACK) {
 			if (ct->proto.sctp.vtag[dir] == 0) {
 				pr_debug("Setting vtag %x for dir %d\n",
 					 sh->vtag, dir);
 				ct->proto.sctp.vtag[dir] = sh->vtag;
 			} else if (sh->vtag != ct->proto.sctp.vtag[dir]) {
-				pr_debug("Verification tag check failed\n");
-				goto out_unlock;
+				if (test_bit(SCTP_CID_DATA, map) || ignore)
+					goto out_unlock;
+
+				if ((ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) == 0 ||
+				    ct->proto.sctp.last_dir == dir)
+					goto out_unlock;
+
+				ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
+				ct->proto.sctp.vtag[dir] = sh->vtag;
+				ct->proto.sctp.vtag[!dir] = 0;
+			} else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) {
+				ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
 			}
 		}
 
@@ -470,6 +497,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 	}
 	spin_unlock_bh(&ct->lock);
 
+	/* allow but do not refresh timeout */
+	if (ignore)
+		return NF_ACCEPT;
+
 	timeouts = nf_ct_timeout_lookup(ct);
 	if (!timeouts)
 		timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 6892e497781c..e8c86ee4c1c4 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1152,7 +1152,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
 		   && (old_state == TCP_CONNTRACK_SYN_RECV
 		       || old_state == TCP_CONNTRACK_ESTABLISHED)
 		   && new_state == TCP_CONNTRACK_ESTABLISHED) {
-		/* Set ASSURED if we see see valid ack in ESTABLISHED
+		/* Set ASSURED if we see valid ack in ESTABLISHED
 		   after SYN_RECV or a valid answer for a picked up
 		   connection. */
 		set_bit(IPS_ASSURED_BIT, &ct->status);
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 760ca2422816..af402f458ee0 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -81,18 +81,6 @@ static bool udp_error(struct sk_buff *skb,
 	return false;
 }
 
-static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct,
-					       struct sk_buff *skb,
-					       enum ip_conntrack_info ctinfo,
-					       u32 extra_jiffies)
-{
-	if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY &&
-		     ct->status & IPS_NAT_CLASH))
-		nf_ct_kill(ct);
-	else
-		nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies);
-}
-
 /* Returns verdict for packet, and may modify conntracktype */
 int nf_conntrack_udp_packet(struct nf_conn *ct,
 			    struct sk_buff *skb,
@@ -124,12 +112,15 @@ int nf_conntrack_udp_packet(struct nf_conn *ct,
 
 		nf_ct_refresh_acct(ct, ctinfo, skb, extra);
 
+		/* never set ASSURED for IPS_NAT_CLASH, they time out soon */
+		if (unlikely((ct->status & IPS_NAT_CLASH)))
+			return NF_ACCEPT;
+
 		/* Also, more likely to be important, and not a probe */
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
-						   timeouts[UDP_CT_UNREPLIED]);
+		nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }
@@ -206,12 +197,15 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct,
 	if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
 		nf_ct_refresh_acct(ct, ctinfo, skb,
 				   timeouts[UDP_CT_REPLIED]);
+
+		if (unlikely((ct->status & IPS_NAT_CLASH)))
+			return NF_ACCEPT;
+
 		/* Also, more likely to be important, and not a probe */
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
-						   timeouts[UDP_CT_UNREPLIED]);
+		nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d878e34e3354..b7dc1cbf40ea 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -815,11 +815,11 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk,
 					nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0,
 					family, table);
 	if (err < 0)
-		goto err;
+		goto err_fill_table_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 
-err:
+err_fill_table_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -1563,11 +1563,11 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
 					nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0,
 					family, table, chain);
 	if (err < 0)
-		goto err;
+		goto err_fill_chain_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 
-err:
+err_fill_chain_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -2018,8 +2018,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	if (nla[NFTA_CHAIN_NAME]) {
 		chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
 	} else {
-		if (!(flags & NFT_CHAIN_BINDING))
-			return -EINVAL;
+		if (!(flags & NFT_CHAIN_BINDING)) {
+			err = -EINVAL;
+			goto err1;
+		}
 
 		snprintf(name, sizeof(name), "__chain%llu", ++chain_id);
 		chain->name = kstrdup(name, GFP_KERNEL);
@@ -3006,11 +3008,11 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 				       nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
 				       family, table, chain, rule, NULL);
 	if (err < 0)
-		goto err;
+		goto err_fill_rule_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 
-err:
+err_fill_rule_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -3768,7 +3770,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
-	if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
+	if (set->udata &&
+	    nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
 		goto nla_put_failure;
 
 	nest = nla_nest_start_noflag(skb, NFTA_SET_DESC);
@@ -3965,11 +3968,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
 
 	err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0);
 	if (err < 0)
-		goto err;
+		goto err_fill_set_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 
-err:
+err_fill_set_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -4857,24 +4860,18 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	err = -ENOMEM;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (skb == NULL)
-		goto err1;
+		return err;
 
 	err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid,
 					  NFT_MSG_NEWSETELEM, 0, set, &elem);
 	if (err < 0)
-		goto err2;
+		goto err_fill_setelem;
 
-	err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT);
-	/* This avoids a loop in nfnetlink. */
-	if (err < 0)
-		goto err1;
+	return nfnetlink_unicast(skb, ctx->net, ctx->portid);
 
-	return 0;
-err2:
+err_fill_setelem:
 	kfree_skb(skb);
-err1:
-	/* this avoids a loop in nfnetlink. */
-	return err == -EAGAIN ? -ENOBUFS : err;
+	return err;
 }
 
 /* called with rcu_read_lock held */
@@ -6179,10 +6176,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 				      nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
 				      family, table, obj, reset);
 	if (err < 0)
-		goto err;
+		goto err_fill_obj_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
-err:
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
+
+err_fill_obj_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -7042,10 +7040,11 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
 					    NFT_MSG_NEWFLOWTABLE, 0, family,
 					    flowtable, &flowtable->hook_list);
 	if (err < 0)
-		goto err;
+		goto err_fill_flowtable_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
-err:
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
+
+err_fill_flowtable_info:
 	kfree_skb(skb2);
 	return err;
 }
@@ -7231,10 +7230,11 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk,
 	err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid,
 				      nlh->nlmsg_seq);
 	if (err < 0)
-		goto err;
+		goto err_fill_gen_info;
 
-	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
-err:
+	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
+
+err_fill_gen_info:
 	kfree_skb(skb2);
 	return err;
 }
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 5f24edf95830..3a2e64e13b22 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -149,10 +149,15 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error)
 }
 EXPORT_SYMBOL_GPL(nfnetlink_set_err);
 
-int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
-		      int flags)
+int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid)
 {
-	return netlink_unicast(net->nfnl, skb, portid, flags);
+	int err;
+
+	err = nlmsg_unicast(net->nfnl, skb, portid);
+	if (err == -EAGAIN)
+		err = -ENOBUFS;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(nfnetlink_unicast);
 
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index f02992419850..b35e8d9a5b37 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -356,8 +356,7 @@ __nfulnl_send(struct nfulnl_instance *inst)
 			goto out;
 		}
 	}
-	nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
-			  MSG_DONTWAIT);
+	nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid);
 out:
 	inst->qlen = 0;
 	inst->skb = NULL;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index dadfc06245a3..d1d8bca03b4f 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -681,7 +681,7 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue,
 	*packet_id_ptr = htonl(entry->id);
 
 	/* nfnetlink_unicast will either free the nskb or add it to a socket */
-	err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT);
+	err = nfnetlink_unicast(nskb, net, queue->peer_portid);
 	if (err < 0) {
 		if (queue->flags & NFQA_CFG_F_FAIL_OPEN) {
 			failopen = 1;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 6428856ccbec..8e56f353ff35 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -27,8 +27,6 @@ struct nft_xt_match_priv {
 	void *info;
 };
 
-static refcount_t nft_compat_pending_destroy = REFCOUNT_INIT(1);
-
 static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx,
 						const char *tablename)
 {
@@ -215,6 +213,17 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	return 0;
 }
 
+static void nft_compat_wait_for_destructors(void)
+{
+	/* xtables matches or targets can have side effects, e.g.
+	 * creation/destruction of /proc files.
+	 * The xt ->destroy functions are run asynchronously from
+	 * work queue.  If we have pending invocations we thus
+	 * need to wait for those to finish.
+	 */
+	nf_tables_trans_destroy_flush_work();
+}
+
 static int
 nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		const struct nlattr * const tb[])
@@ -238,14 +247,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
 
-	/* xtables matches or targets can have side effects, e.g.
-	 * creation/destruction of /proc files.
-	 * The xt ->destroy functions are run asynchronously from
-	 * work queue.  If we have pending invocations we thus
-	 * need to wait for those to finish.
-	 */
-	if (refcount_read(&nft_compat_pending_destroy) > 1)
-		nf_tables_trans_destroy_flush_work();
+	nft_compat_wait_for_destructors();
 
 	ret = xt_check_target(&par, size, proto, inv);
 	if (ret < 0)
@@ -260,7 +262,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr)
 {
-	refcount_dec(&nft_compat_pending_destroy);
 	module_put(me);
 	kfree(expr->ops);
 }
@@ -468,6 +469,8 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
 
+	nft_compat_wait_for_destructors();
+
 	return xt_check_match(&par, size, proto, inv);
 }
 
@@ -716,14 +719,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
 
 static struct nft_expr_type nft_match_type;
 
-static void nft_mt_tg_deactivate(const struct nft_ctx *ctx,
-				 const struct nft_expr *expr,
-				 enum nft_trans_phase phase)
-{
-	if (phase == NFT_TRANS_COMMIT)
-		refcount_inc(&nft_compat_pending_destroy);
-}
-
 static const struct nft_expr_ops *
 nft_match_select_ops(const struct nft_ctx *ctx,
 		     const struct nlattr * const tb[])
@@ -762,7 +757,6 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	ops->type = &nft_match_type;
 	ops->eval = nft_match_eval;
 	ops->init = nft_match_init;
-	ops->deactivate = nft_mt_tg_deactivate,
 	ops->destroy = nft_match_destroy;
 	ops->dump = nft_match_dump;
 	ops->validate = nft_match_validate;
@@ -853,7 +847,6 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
 	ops->init = nft_target_init;
 	ops->destroy = nft_target_destroy;
-	ops->deactivate = nft_mt_tg_deactivate,
 	ops->dump = nft_target_dump;
 	ops->validate = nft_target_validate;
 	ops->data = target;
@@ -917,8 +910,6 @@ static void __exit nft_compat_module_exit(void)
 	nfnetlink_subsys_unregister(&nfnl_compat_subsys);
 	nft_unregister_expr(&nft_target_type);
 	nft_unregister_expr(&nft_match_type);
-
-	WARN_ON_ONCE(refcount_read(&nft_compat_pending_destroy) != 1);
 }
 
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 07782836fad6..3c48cdc8935d 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 
 	err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
 	if (priv->flags & NFT_EXTHDR_F_PRESENT) {
-		*dest = (err >= 0);
+		nft_reg_store8(dest, err >= 0);
 		return;
 	} else if (err < 0) {
 		goto err;
@@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr,
 
 	err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type);
 	if (priv->flags & NFT_EXTHDR_F_PRESENT) {
-		*dest = (err >= 0);
+		nft_reg_store8(dest, err >= 0);
 		return;
 	} else if (err < 0) {
 		goto err;
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 3b9b97aa4b32..3a6c84fb2c90 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -102,7 +102,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	}
 
 	if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
-	    ct->status & IPS_SEQ_ADJUST)
+	    ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH))
 		goto out;
 
 	if (!nf_ct_is_confirmed(ct))
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index ed7cb9f747f6..7a2e59638499 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -87,7 +87,9 @@ void nft_payload_eval(const struct nft_expr *expr,
 	u32 *dest = &regs->data[priv->dreg];
 	int offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
+	if (priv->len % NFT_REG32_SIZE)
+		dest[priv->len / NFT_REG32_SIZE] = 0;
+
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
 		if (!skb_mac_header_was_set(skb))
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 4b2834fd17b2..217ab3644c25 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -218,11 +218,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			       struct nft_rbtree_elem *new,
 			       struct nft_set_ext **ext)
 {
+	bool overlap = false, dup_end_left = false, dup_end_right = false;
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_next(net);
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *parent, **p;
-	bool overlap = false;
 	int d;
 
 	/* Detect overlaps as we descend the tree. Set the flag in these cases:
@@ -238,24 +238,44 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	 *
 	 * b1. _ _ __>|  !_ _ __|  (insert end before existing start)
 	 * b2. _ _ ___|  !_ _ _>|  (insert end after existing start)
-	 * b3. _ _ ___! >|_ _ __|  (insert start after existing end)
+	 * b3. _ _ ___! >|_ _ __|  (insert start after existing end, as a leaf)
+	 *            '--' no nodes falling in this range
+	 * b4.          >|_ _   !  (insert start before existing start)
 	 *
 	 * Case a3. resolves to b3.:
 	 * - if the inserted start element is the leftmost, because the '0'
 	 *   element in the tree serves as end element
-	 * - otherwise, if an existing end is found. Note that end elements are
-	 *   always inserted after corresponding start elements.
+	 * - otherwise, if an existing end is found immediately to the left. If
+	 *   there are existing nodes in between, we need to further descend the
+	 *   tree before we can conclude the new start isn't causing an overlap
+	 *
+	 * or to b4., which, preceded by a3., means we already traversed one or
+	 * more existing intervals entirely, from the right.
 	 *
 	 * For a new, rightmost pair of elements, we'll hit cases b3. and b2.,
 	 * in that order.
 	 *
 	 * The flag is also cleared in two special cases:
 	 *
-	 * b4. |__ _ _!|<_ _ _   (insert start right before existing end)
-	 * b5. |__ _ >|!__ _ _   (insert end right after existing start)
+	 * b5. |__ _ _!|<_ _ _   (insert start right before existing end)
+	 * b6. |__ _ >|!__ _ _   (insert end right after existing start)
 	 *
 	 * which always happen as last step and imply that no further
 	 * overlapping is possible.
+	 *
+	 * Another special case comes from the fact that start elements matching
+	 * an already existing start element are allowed: insertion is not
+	 * performed but we return -EEXIST in that case, and the error will be
+	 * cleared by the caller if NLM_F_EXCL is not present in the request.
+	 * This way, request for insertion of an exact overlap isn't reported as
+	 * error to userspace if not desired.
+	 *
+	 * However, if the existing start matches a pre-existing start, but the
+	 * end element doesn't match the corresponding pre-existing end element,
+	 * we need to report a partial overlap. This is a local condition that
+	 * can be noticed without need for a tracking flag, by checking for a
+	 * local duplicated end for a corresponding start, from left and right,
+	 * separately.
 	 */
 
 	parent = NULL;
@@ -272,26 +292,41 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			if (nft_rbtree_interval_start(new)) {
 				if (nft_rbtree_interval_end(rbe) &&
 				    nft_set_elem_active(&rbe->ext, genmask) &&
-				    !nft_set_elem_expired(&rbe->ext))
+				    !nft_set_elem_expired(&rbe->ext) && !*p)
 					overlap = false;
 			} else {
+				if (dup_end_left && !*p)
+					return -ENOTEMPTY;
+
 				overlap = nft_rbtree_interval_end(rbe) &&
 					  nft_set_elem_active(&rbe->ext,
 							      genmask) &&
 					  !nft_set_elem_expired(&rbe->ext);
+
+				if (overlap) {
+					dup_end_right = true;
+					continue;
+				}
 			}
 		} else if (d > 0) {
 			p = &parent->rb_right;
 
 			if (nft_rbtree_interval_end(new)) {
+				if (dup_end_right && !*p)
+					return -ENOTEMPTY;
+
 				overlap = nft_rbtree_interval_end(rbe) &&
 					  nft_set_elem_active(&rbe->ext,
 							      genmask) &&
 					  !nft_set_elem_expired(&rbe->ext);
-			} else if (nft_rbtree_interval_end(rbe) &&
-				   nft_set_elem_active(&rbe->ext, genmask) &&
+
+				if (overlap) {
+					dup_end_left = true;
+					continue;
+				}
+			} else if (nft_set_elem_active(&rbe->ext, genmask) &&
 				   !nft_set_elem_expired(&rbe->ext)) {
-				overlap = true;
+				overlap = nft_rbtree_interval_end(rbe);
 			}
 		} else {
 			if (nft_rbtree_interval_end(rbe) &&
@@ -316,6 +351,8 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 				p = &parent->rb_left;
 			}
 		}
+
+		dup_end_left = dup_end_right = false;
 	}
 
 	if (overlap)
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 19bef176145e..606411869698 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -640,7 +640,7 @@ static void __net_exit recent_proc_net_exit(struct net *net)
 	struct recent_table *t;
 
 	/* recent_net_exit() is called before recent_mt_destroy(). Make sure
-	 * that the parent xt_recent proc entry is is empty before trying to
+	 * that the parent xt_recent proc entry is empty before trying to
 	 * remove it.
 	 */
 	spin_lock_bh(&recent_lock);
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index d07de2c0fbc7..f73a8382c275 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -85,6 +85,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry)
 			kfree(netlbl_domhsh_addr6_entry(iter6));
 		}
 #endif /* IPv6 */
+		kfree(ptr->def.addrsel);
 	}
 	kfree(ptr->domain);
 	kfree(ptr);
@@ -537,6 +538,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 				goto add_return;
 		}
 #endif /* IPv6 */
+		/* cleanup the new entry since we've moved everything over */
+		netlbl_domhsh_free_entry(&entry->rcu);
 	} else
 		ret_val = -EINVAL;
 
@@ -580,6 +583,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 {
 	int ret_val = 0;
 	struct audit_buffer *audit_buf;
+	struct netlbl_af4list *iter4;
+	struct netlbl_domaddr4_map *map4;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct netlbl_af6list *iter6;
+	struct netlbl_domaddr6_map *map6;
+#endif /* IPv6 */
 
 	if (entry == NULL)
 		return -ENOENT;
@@ -597,6 +606,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 		ret_val = -ENOENT;
 	spin_unlock(&netlbl_domhsh_lock);
 
+	if (ret_val)
+		return ret_val;
+
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info);
 	if (audit_buf != NULL) {
 		audit_log_format(audit_buf,
@@ -606,40 +618,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 		audit_log_end(audit_buf);
 	}
 
-	if (ret_val == 0) {
-		struct netlbl_af4list *iter4;
-		struct netlbl_domaddr4_map *map4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct netlbl_af6list *iter6;
-		struct netlbl_domaddr6_map *map6;
-#endif /* IPv6 */
-
-		switch (entry->def.type) {
-		case NETLBL_NLTYPE_ADDRSELECT:
-			netlbl_af4list_foreach_rcu(iter4,
-					     &entry->def.addrsel->list4) {
-				map4 = netlbl_domhsh_addr4_entry(iter4);
-				cipso_v4_doi_putdef(map4->def.cipso);
-			}
+	switch (entry->def.type) {
+	case NETLBL_NLTYPE_ADDRSELECT:
+		netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) {
+			map4 = netlbl_domhsh_addr4_entry(iter4);
+			cipso_v4_doi_putdef(map4->def.cipso);
+		}
 #if IS_ENABLED(CONFIG_IPV6)
-			netlbl_af6list_foreach_rcu(iter6,
-					     &entry->def.addrsel->list6) {
-				map6 = netlbl_domhsh_addr6_entry(iter6);
-				calipso_doi_putdef(map6->def.calipso);
-			}
+		netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) {
+			map6 = netlbl_domhsh_addr6_entry(iter6);
+			calipso_doi_putdef(map6->def.calipso);
+		}
 #endif /* IPv6 */
-			break;
-		case NETLBL_NLTYPE_CIPSOV4:
-			cipso_v4_doi_putdef(entry->def.cipso);
-			break;
+		break;
+	case NETLBL_NLTYPE_CIPSOV4:
+		cipso_v4_doi_putdef(entry->def.cipso);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
-		case NETLBL_NLTYPE_CALIPSO:
-			calipso_doi_putdef(entry->def.calipso);
-			break;
+	case NETLBL_NLTYPE_CALIPSO:
+		calipso_doi_putdef(entry->def.calipso);
+		break;
 #endif /* IPv6 */
-		}
-		call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
 	}
+	call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
 
 	return ret_val;
 }
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b5f30d7d30d0..d2d1448274f5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -353,7 +353,7 @@ static void netlink_rcv_wake(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
-	if (skb_queue_empty(&sk->sk_receive_queue))
+	if (skb_queue_empty_lockless(&sk->sk_receive_queue))
 		clear_bit(NETLINK_S_CONGESTED, &nlk->state);
 	if (!test_bit(NETLINK_S_CONGESTED, &nlk->state))
 		wake_up_interruptible(&nlk->wait);
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index f6491853c797..641ffbdd977a 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -51,6 +51,9 @@ static int add_policy(struct nl_policy_dump **statep,
 	if (!state)
 		return -ENOMEM;
 
+	memset(&state->policies[state->n_alloc], 0,
+	       flex_array_size(state, policies, n_alloc - state->n_alloc));
+
 	state->policies[state->n_alloc].policy = policy;
 	state->policies[state->n_alloc].maxtype = maxtype;
 	state->n_alloc = n_alloc;
@@ -185,7 +188,7 @@ send_attribute:
 		goto next;
 	case NLA_NESTED:
 		type = NL_ATTR_TYPE_NESTED;
-		/* fall through */
+		fallthrough;
 	case NLA_NESTED_ARRAY:
 		if (pt->type == NLA_NESTED_ARRAY)
 			type = NL_ATTR_TYPE_NESTED_ARRAY;
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 2bef3779f893..69e58906c32b 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -122,7 +122,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
 
 	case NR_DISCREQ:
 		nr_write_internal(sk, NR_DISCACK);
-		/* fall through */
+		fallthrough;
 	case NR_DISCACK:
 		nr_disconnect(sk, 0);
 		break;
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 0891ee02ca4f..78da5eab252a 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -263,7 +263,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 	case 3:
 		re_sort_routes(nr_node, 0, 1);
 		re_sort_routes(nr_node, 1, 2);
-		/* fall through */
+		fallthrough;
 	case 2:
 		re_sort_routes(nr_node, 0, 1);
 	case 1:
@@ -356,7 +356,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n
 				switch (i) {
 				case 0:
 					nr_node->routes[0] = nr_node->routes[1];
-					/* fall through */
+					fallthrough;
 				case 1:
 					nr_node->routes[1] = nr_node->routes[2];
 				case 2:
@@ -479,7 +479,7 @@ static int nr_dec_obs(void)
 				switch (i) {
 				case 0:
 					s->routes[0] = s->routes[1];
-					/* Fallthrough */
+					fallthrough;
 				case 1:
 					s->routes[1] = s->routes[2];
 				case 2:
@@ -526,7 +526,7 @@ void nr_rt_device_down(struct net_device *dev)
 						switch (i) {
 						case 0:
 							t->routes[0] = t->routes[1];
-							/* fall through */
+							fallthrough;
 						case 1:
 							t->routes[1] = t->routes[2];
 						case 2:
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 98d393e70de3..a3f1204f1ed2 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -778,7 +778,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			}
 		}
 		/* Non-ICMP, fall thru to initialize if needed. */
-		/* fall through */
+		fallthrough;
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
@@ -1540,7 +1540,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 		switch (type) {
 		case OVS_CT_ATTR_FORCE_COMMIT:
 			info->force = true;
-			/* fall through. */
+			fallthrough;
 		case OVS_CT_ATTR_COMMIT:
 			info->commit = true;
 			break;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 03942c30d83e..b03d142ec82e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -675,7 +675,7 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
 			case -EINVAL:
 				memset(&key->ip, 0, sizeof(key->ip));
 				memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
-				/* fall-through */
+				fallthrough;
 			case -EPROTO:
 				skb->transport_header = skb->network_header;
 				error = 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 479c257ded73..2b33e977a905 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2170,7 +2170,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
 	unsigned long status = TP_STATUS_USER;
-	unsigned short macoff, netoff, hdrlen;
+	unsigned short macoff, hdrlen;
+	unsigned int netoff;
 	struct sk_buff *copy_skb = NULL;
 	struct timespec64 ts;
 	__u32 ts_status;
@@ -2239,6 +2240,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 		macoff = netoff - maclen;
 	}
+	if (netoff > USHRT_MAX) {
+		atomic_inc(&po->tp_drops);
+		goto drop_n_restore;
+	}
 	if (po->tp_version <= TPACKET_V2) {
 		if (macoff + snaplen > po->rx_ring.frame_size) {
 			if (po->copy_thresh &&
@@ -4061,7 +4066,7 @@ static int packet_notifier(struct notifier_block *this,
 		case NETDEV_UNREGISTER:
 			if (po->mclist)
 				packet_dev_mclist_delete(dev, &po->mclist);
-			/* fallthrough */
+			fallthrough;
 
 		case NETDEV_DOWN:
 			if (dev->ifindex == po->ifindex) {
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e47d09aca4af..a1525916885a 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -368,7 +368,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 			err = -EINVAL;
 			goto out;
 		}
-		/* fall through */
+		fallthrough;
 	case PNS_PEP_DISABLE_REQ:
 		atomic_set(&pn->tx_credits, 0);
 		pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC);
@@ -385,7 +385,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 	case PNS_PIPE_ALIGNED_DATA:
 		__skb_pull(skb, 1);
-		/* fall through */
+		fallthrough;
 	case PNS_PIPE_DATA:
 		__skb_pull(skb, 3); /* Pipe data header */
 		if (!pn_flow_safe(pn->rx_fc)) {
@@ -417,11 +417,11 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 		err = pipe_rcv_created(sk, skb);
 		if (err)
 			break;
-		/* fall through */
+		fallthrough;
 	case PNS_PIPE_RESET_IND:
 		if (!pn->init_enable)
 			break;
-		/* fall through */
+		fallthrough;
 	case PNS_PIPE_ENABLED_IND:
 		if (!pn_flow_safe(pn->tx_fc)) {
 			atomic_set(&pn->tx_credits, 1);
@@ -555,7 +555,7 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
 	switch (hdr->message_id) {
 	case PNS_PIPE_ALIGNED_DATA:
 		__skb_pull(skb, 1);
-		/* fall through */
+		fallthrough;
 	case PNS_PIPE_DATA:
 		__skb_pull(skb, 3); /* Pipe data header */
 		if (!pn_flow_safe(pn->rx_fc)) {
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b4c0db0b7d31..90c558f89d46 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
  */
 static int qrtr_port_assign(struct qrtr_sock *ipc, int *port)
 {
+	u32 min_port;
 	int rc;
 
 	mutex_lock(&qrtr_port_lock);
 	if (!*port) {
-		rc = idr_alloc(&qrtr_ports, ipc,
-			       QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1,
-			       GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = QRTR_MIN_EPH_SOCKET;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	} else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) {
 		rc = -EACCES;
 	} else if (*port == QRTR_PORT_CTRL) {
-		rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC);
+		min_port = 0;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC);
 	} else {
-		rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = *port;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	}
 	mutex_unlock(&qrtr_port_lock);
 
diff --git a/net/rds/send.c b/net/rds/send.c
index 9a529a01cdc6..985d0b7713ac 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -934,7 +934,7 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs,
 
 		case RDS_CMSG_ZCOPY_COOKIE:
 			zcopy_cookie = true;
-			/* fall through */
+			fallthrough;
 
 		case RDS_CMSG_RDMA_DEST:
 		case RDS_CMSG_RDMA_MAP:
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 0d4fab2be82b..6af786d66b03 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -216,7 +216,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety
 	switch (frametype) {
 	case ROSE_RESET_REQUEST:
 		rose_write_internal(sk, ROSE_RESET_CONFIRMATION);
-		/* fall through */
+		fallthrough;
 	case ROSE_RESET_CONFIRMATION:
 		rose_stop_timer(sk);
 		rose_start_idletimer(sk);
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 5277631fa14c..6e35703ff353 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -343,7 +343,7 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 				case 0:
 					rose_node->neighbour[0] =
 						rose_node->neighbour[1];
-					/* fall through */
+					fallthrough;
 				case 1:
 					rose_node->neighbour[1] =
 						rose_node->neighbour[2];
@@ -505,7 +505,7 @@ void rose_rt_device_down(struct net_device *dev)
 				switch (i) {
 				case 0:
 					t->neighbour[0] = t->neighbour[1];
-					/* fall through */
+					fallthrough;
 				case 1:
 					t->neighbour[1] = t->neighbour[2];
 				case 2:
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index e6725a6de015..186c8a889b16 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -246,7 +246,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 			ret = 0;
 			break;
 		}
-		/* Fall through */
+		fallthrough;
 	default:
 		ret = -EBUSY;
 		break;
@@ -545,7 +545,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 
 		rx->local = local;
 		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
-		/* Fall through */
+		fallthrough;
 
 	case RXRPC_CLIENT_BOUND:
 		if (!m->msg_name &&
@@ -553,7 +553,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 			m->msg_name = &rx->connect_srx;
 			m->msg_namelen = sizeof(rx->connect_srx);
 		}
-		/* Fall through */
+		fallthrough;
 	case RXRPC_SERVER_BOUND:
 	case RXRPC_SERVER_LISTENING:
 		ret = rxrpc_do_sendmsg(rx, m, len);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 6d29a3603a3e..884cff7bb169 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -488,7 +488,6 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_LAST,		/* Received the last packet (at rxtx_top) */
 	RXRPC_CALL_TX_LAST,		/* Last packet in Tx buffer (at rxtx_top) */
 	RXRPC_CALL_SEND_PING,		/* A ping will need to be sent */
-	RXRPC_CALL_PINGING,		/* Ping in process */
 	RXRPC_CALL_RETRANS_TIMEOUT,	/* Retransmission due to timeout occurred */
 	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
@@ -673,9 +672,13 @@ struct rxrpc_call {
 	rxrpc_seq_t		ackr_consumed;	/* Highest packet shown consumed */
 	rxrpc_seq_t		ackr_seen;	/* Highest packet shown seen */
 
-	/* ping management */
-	rxrpc_serial_t		ping_serial;	/* Last ping sent */
-	ktime_t			ping_time;	/* Time last ping sent */
+	/* RTT management */
+	rxrpc_serial_t		rtt_serial[4];	/* Serial number of DATA or PING sent */
+	ktime_t			rtt_sent_at[4];	/* Time packet sent */
+	unsigned long		rtt_avail;	/* Mask of available slots in bits 0-3,
+						 * Mask of pending samples in 8-11 */
+#define RXRPC_CALL_RTT_AVAIL_MASK	0xf
+#define RXRPC_CALL_RTT_PEND_SHIFT	8
 
 	/* transmission-phase ACK management */
 	ktime_t			acks_latest_ts;	/* Timestamp of latest ACK received */
@@ -1037,7 +1040,7 @@ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
 /*
  * rtt.c
  */
-void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
+void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int,
 			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
 unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool);
 void rxrpc_peer_init_rtt(struct rxrpc_peer *);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 032ed76c0166..ef160566aa9a 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -622,7 +622,7 @@ int rxrpc_reject_call(struct rxrpc_sock *rx)
 	case RXRPC_CALL_SERVER_ACCEPTING:
 		__rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED);
 		abort = true;
-		/* fall through */
+		fallthrough;
 	case RXRPC_CALL_COMPLETE:
 		ret = call->error;
 		goto out_discard;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 38a46167523f..a40fae013942 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -153,6 +153,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
 	call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1;
 
 	call->rxnet = rxnet;
+	call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK;
 	atomic_inc(&rxnet->nr_calls);
 	return call;
 
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index f2a1a5dbb5a7..159e3eda7914 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -881,7 +881,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 			conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE;
 			rxrpc_activate_channels_locked(conn);
 		}
-		/* fall through */
+		fallthrough;
 	case RXRPC_CONN_CLIENT_ACTIVE:
 		if (list_empty(&conn->waiting_calls)) {
 			rxrpc_deactivate_one_channel(conn, channel);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 767579328a06..667c44aa5a63 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -608,36 +608,57 @@ unlock:
 }
 
 /*
- * Process a requested ACK.
+ * See if there's a cached RTT probe to complete.
  */
-static void rxrpc_input_requested_ack(struct rxrpc_call *call,
-				      ktime_t resp_time,
-				      rxrpc_serial_t orig_serial,
-				      rxrpc_serial_t ack_serial)
+static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
+				     ktime_t resp_time,
+				     rxrpc_serial_t acked_serial,
+				     rxrpc_serial_t ack_serial,
+				     enum rxrpc_rtt_rx_trace type)
 {
-	struct rxrpc_skb_priv *sp;
-	struct sk_buff *skb;
+	rxrpc_serial_t orig_serial;
+	unsigned long avail;
 	ktime_t sent_at;
-	int ix;
+	bool matched = false;
+	int i;
 
-	for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) {
-		skb = call->rxtx_buffer[ix];
-		if (!skb)
-			continue;
+	avail = READ_ONCE(call->rtt_avail);
+	smp_rmb(); /* Read avail bits before accessing data. */
 
-		sent_at = skb->tstamp;
-		smp_rmb(); /* Read timestamp before serial. */
-		sp = rxrpc_skb(skb);
-		if (sp->hdr.serial != orig_serial)
+	for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) {
+		if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail))
 			continue;
-		goto found;
-	}
 
-	return;
+		sent_at = call->rtt_sent_at[i];
+		orig_serial = call->rtt_serial[i];
+
+		if (orig_serial == acked_serial) {
+			clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
+			smp_mb(); /* Read data before setting avail bit */
+			set_bit(i, &call->rtt_avail);
+			if (type != rxrpc_rtt_rx_cancel)
+				rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
+						   sent_at, resp_time);
+			else
+				trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i,
+						   orig_serial, acked_serial, 0, 0);
+			matched = true;
+		}
+
+		/* If a later serial is being acked, then mark this slot as
+		 * being available.
+		 */
+		if (after(acked_serial, orig_serial)) {
+			trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i,
+					   orig_serial, acked_serial, 0, 0);
+			clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
+			smp_wmb();
+			set_bit(i, &call->rtt_avail);
+		}
+	}
 
-found:
-	rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack,
-			   orig_serial, ack_serial, sent_at, resp_time);
+	if (!matched)
+		trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0);
 }
 
 /*
@@ -682,27 +703,11 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call)
  */
 static void rxrpc_input_ping_response(struct rxrpc_call *call,
 				      ktime_t resp_time,
-				      rxrpc_serial_t orig_serial,
+				      rxrpc_serial_t acked_serial,
 				      rxrpc_serial_t ack_serial)
 {
-	rxrpc_serial_t ping_serial;
-	ktime_t ping_time;
-
-	ping_time = call->ping_time;
-	smp_rmb();
-	ping_serial = READ_ONCE(call->ping_serial);
-
-	if (orig_serial == call->acks_lost_ping)
+	if (acked_serial == call->acks_lost_ping)
 		rxrpc_input_check_for_lost_ack(call);
-
-	if (before(orig_serial, ping_serial) ||
-	    !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags))
-		return;
-	if (after(orig_serial, ping_serial))
-		return;
-
-	rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response,
-			   orig_serial, ack_serial, ping_time, resp_time);
 }
 
 /*
@@ -843,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 		struct rxrpc_ackinfo info;
 		u8 acks[RXRPC_MAXACKS];
 	} buf;
-	rxrpc_serial_t acked_serial;
+	rxrpc_serial_t ack_serial, acked_serial;
 	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
 	int nr_acks, offset, ioffset;
 
@@ -856,6 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	}
 	offset += sizeof(buf.ack);
 
+	ack_serial = sp->hdr.serial;
 	acked_serial = ntohl(buf.ack.serial);
 	first_soft_ack = ntohl(buf.ack.firstPacket);
 	prev_pkt = ntohl(buf.ack.previousPacket);
@@ -864,31 +870,42 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
 			      buf.ack.reason : RXRPC_ACK__INVALID);
 
-	trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
+	trace_rxrpc_rx_ack(call, ack_serial, acked_serial,
 			   first_soft_ack, prev_pkt,
 			   summary.ack_reason, nr_acks);
 
-	if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
+	switch (buf.ack.reason) {
+	case RXRPC_ACK_PING_RESPONSE:
 		rxrpc_input_ping_response(call, skb->tstamp, acked_serial,
-					  sp->hdr.serial);
-	if (buf.ack.reason == RXRPC_ACK_REQUESTED)
-		rxrpc_input_requested_ack(call, skb->tstamp, acked_serial,
-					  sp->hdr.serial);
+					  ack_serial);
+		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+					 rxrpc_rtt_rx_ping_response);
+		break;
+	case RXRPC_ACK_REQUESTED:
+		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+					 rxrpc_rtt_rx_requested_ack);
+		break;
+	default:
+		if (acked_serial != 0)
+			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+						 rxrpc_rtt_rx_cancel);
+		break;
+	}
 
 	if (buf.ack.reason == RXRPC_ACK_PING) {
-		_proto("Rx ACK %%%u PING Request", sp->hdr.serial);
+		_proto("Rx ACK %%%u PING Request", ack_serial);
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
-				  sp->hdr.serial, true, true,
+				  ack_serial, true, true,
 				  rxrpc_propose_ack_respond_to_ping);
 	} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
 		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
-				  sp->hdr.serial, true, true,
+				  ack_serial, true, true,
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
 	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
-		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+		trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
 					   first_soft_ack, call->ackr_first_seq,
 					   prev_pkt, call->ackr_prev_seq);
 		return;
@@ -904,7 +921,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 
 	/* Discard any out-of-order or duplicate ACKs (inside lock). */
 	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
-		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+		trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
 					   first_soft_ack, call->ackr_first_seq,
 					   prev_pkt, call->ackr_prev_seq);
 		goto out;
@@ -964,7 +981,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    RXRPC_TX_ANNO_LAST &&
 	    summary.nr_acks == call->tx_top - hard_ack &&
 	    rxrpc_is_client_call(call))
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial,
 				  false, true,
 				  rxrpc_propose_ack_ping_for_lost_reply);
 
@@ -1084,7 +1101,7 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx,
 	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		rxrpc_call_completed(call);
-		/* Fall through */
+		fallthrough;
 	case RXRPC_CALL_COMPLETE:
 		break;
 	default:
@@ -1243,12 +1260,12 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 	case RXRPC_PACKET_TYPE_BUSY:
 		if (rxrpc_to_server(sp))
 			goto discard;
-		/* Fall through */
+		fallthrough;
 	case RXRPC_PACKET_TYPE_ACK:
 	case RXRPC_PACKET_TYPE_ACKALL:
 		if (sp->hdr.callNumber == 0)
 			goto bad_message;
-		/* Fall through */
+		fallthrough;
 	case RXRPC_PACKET_TYPE_ABORT:
 		break;
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index c8b2097f499c..ede058f9cc15 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -162,7 +162,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		/* Fall through and set IPv4 options too otherwise we don't get
 		 * errors from IPv4 packets sent through the IPv6 socket.
 		 */
-		/* Fall through */
+		fallthrough;
 	case AF_INET:
 		/* we want to receive ICMP errors */
 		ip_sock_set_recverr(local->socket->sk);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 1ba43c3df4ad..3cfff7922ba8 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -124,6 +124,49 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 }
 
 /*
+ * Record the beginning of an RTT probe.
+ */
+static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial,
+				 enum rxrpc_rtt_tx_trace why)
+{
+	unsigned long avail = call->rtt_avail;
+	int rtt_slot = 9;
+
+	if (!(avail & RXRPC_CALL_RTT_AVAIL_MASK))
+		goto no_slot;
+
+	rtt_slot = __ffs(avail & RXRPC_CALL_RTT_AVAIL_MASK);
+	if (!test_and_clear_bit(rtt_slot, &call->rtt_avail))
+		goto no_slot;
+
+	call->rtt_serial[rtt_slot] = serial;
+	call->rtt_sent_at[rtt_slot] = ktime_get_real();
+	smp_wmb(); /* Write data before avail bit */
+	set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
+
+	trace_rxrpc_rtt_tx(call, why, rtt_slot, serial);
+	return rtt_slot;
+
+no_slot:
+	trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial);
+	return -1;
+}
+
+/*
+ * Cancel an RTT probe.
+ */
+static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call,
+				   rxrpc_serial_t serial, int rtt_slot)
+{
+	if (rtt_slot != -1) {
+		clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
+		smp_wmb(); /* Clear pending bit before setting slot */
+		set_bit(rtt_slot, &call->rtt_avail);
+		trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial);
+	}
+}
+
+/*
  * Send an ACK call packet.
  */
 int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
@@ -136,7 +179,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	rxrpc_serial_t serial;
 	rxrpc_seq_t hard_ack, top;
 	size_t len, n;
-	int ret;
+	int ret, rtt_slot = -1;
 	u8 reason;
 
 	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
@@ -196,18 +239,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	if (_serial)
 		*_serial = serial;
 
-	if (ping) {
-		call->ping_serial = serial;
-		smp_wmb();
-		/* We need to stick a time in before we send the packet in case
-		 * the reply gets back before kernel_sendmsg() completes - but
-		 * asking UDP to send the packet can take a relatively long
-		 * time.
-		 */
-		call->ping_time = ktime_get_real();
-		set_bit(RXRPC_CALL_PINGING, &call->flags);
-		trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial);
-	}
+	if (ping)
+		rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping);
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	conn->params.peer->last_tx_at = ktime_get_seconds();
@@ -221,8 +254,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
-			if (ping)
-				clear_bit(RXRPC_CALL_PINGING, &call->flags);
+			rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
 			rxrpc_propose_ACK(call, pkt->ack.reason,
 					  ntohl(pkt->ack.serial),
 					  false, true,
@@ -321,7 +353,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	struct kvec iov[2];
 	rxrpc_serial_t serial;
 	size_t len;
-	int ret;
+	int ret, rtt_slot = -1;
 
 	_enter(",{%d}", skb->len);
 
@@ -397,6 +429,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	sp->hdr.serial = serial;
 	smp_wmb(); /* Set serial before timestamp */
 	skb->tstamp = ktime_get_real();
+	if (whdr.flags & RXRPC_REQUEST_ACK)
+		rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data);
 
 	/* send the packet by UDP
 	 * - returns -EMSGSIZE if UDP would have to fragment the packet
@@ -408,12 +442,15 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	up_read(&conn->params.local->defrag_sem);
-	if (ret < 0)
+	if (ret < 0) {
+		rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_point_call_data_nofrag);
-	else
+	} else {
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_nofrag);
+	}
+
 	rxrpc_tx_backoff(call, ret);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
@@ -422,7 +459,6 @@ done:
 	if (ret >= 0) {
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
 			call->peer->rtt_last_req = skb->tstamp;
-			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
 			if (call->peer->rtt_count > 1) {
 				unsigned long nowj = jiffies, ack_lost_at;
 
@@ -469,6 +505,8 @@ send_fragmentable:
 	sp->hdr.serial = serial;
 	smp_wmb(); /* Set serial before timestamp */
 	skb->tstamp = ktime_get_real();
+	if (whdr.flags & RXRPC_REQUEST_ACK)
+		rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data);
 
 	switch (conn->params.local->srx.transport.family) {
 	case AF_INET6:
@@ -487,12 +525,14 @@ send_fragmentable:
 		BUG();
 	}
 
-	if (ret < 0)
+	if (ret < 0) {
+		rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_point_call_data_frag);
-	else
+	} else {
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_frag);
+	}
 	rxrpc_tx_backoff(call, ret);
 
 	up_write(&conn->params.local->defrag_sem);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index a852f46d5234..be032850ae8c 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -273,7 +273,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
 	case SO_EE_ORIGIN_ICMP6:
 		if (err == EACCES)
 			err = EHOSTUNREACH;
-		/* Fall through */
+		fallthrough;
 	default:
 		_proto("Rx Received error report { orig=%u }", ee->ee_origin);
 		break;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index ca29976bb193..68396d052052 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -502,11 +502,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer);
  * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
  * @sock: The socket on which the call is in progress.
  * @call: The call to query
+ * @_srtt: Where to store the SRTT value.
  *
- * Get the call's peer smoothed RTT.
+ * Get the call's peer smoothed RTT in uS.
  */
-u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call)
+bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call,
+			   u32 *_srtt)
 {
-	return call->peer->srtt_us >> 3;
+	struct rxrpc_peer *peer = call->peer;
+
+	if (peer->rtt_count == 0) {
+		*_srtt = 1000000; /* 1S */
+		return false;
+	}
+
+	*_srtt = call->peer->srtt_us >> 3;
+	return true;
 }
 EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index efecc5a8f67d..c4684dde1f16 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -776,7 +776,7 @@ out:
 	case RXRPC_ACK_DELAY:
 		if (ret != -EAGAIN)
 			break;
-		/* Fall through */
+		fallthrough;
 	default:
 		rxrpc_send_ack_packet(call, false, NULL);
 	}
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
index 928d8b34a3ee..1221b0637a7e 100644
--- a/net/rxrpc/rtt.c
+++ b/net/rxrpc/rtt.c
@@ -146,6 +146,7 @@ static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
  * exclusive access to the peer RTT data.
  */
 void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+			int rtt_slot,
 			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
 			ktime_t send_time, ktime_t resp_time)
 {
@@ -162,7 +163,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 		peer->rtt_count++;
 	spin_unlock(&peer->rtt_input_lock);
 
-	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+	trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial,
 			   peer->srtt_us >> 3, peer->rto_j);
 }
 
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 52a24d4ef5d8..e08130e5746b 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1137,7 +1137,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	ret = -ENOMEM;
 	ticket = kmalloc(ticket_len, GFP_NOFS);
 	if (!ticket)
-		goto temporary_error;
+		goto temporary_error_free_resp;
 
 	eproto = tracepoint_string("rxkad_tkt_short");
 	abort_code = RXKADPACKETSHORT;
@@ -1230,6 +1230,7 @@ protocol_error:
 
 temporary_error_free_ticket:
 	kfree(ticket);
+temporary_error_free_resp:
 	kfree(response);
 temporary_error:
 	/* Ignore the response packet if we got a temporary error such as
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index f3f6da6e4ad2..0824e103d037 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -241,7 +241,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 			trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
 			if (!last)
 				break;
-			/* Fall through */
+			fallthrough;
 		case RXRPC_CALL_SERVER_SEND_REPLY:
 			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
 			rxrpc_notify_end_tx(rx, call, notify_end_tx);
@@ -721,13 +721,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (p.call.timeouts.normal > 0 && j == 0)
 			j = 1;
 		WRITE_ONCE(call->next_rx_timo, j);
-		/* Fall through */
+		fallthrough;
 	case 2:
 		j = msecs_to_jiffies(p.call.timeouts.idle);
 		if (p.call.timeouts.idle > 0 && j == 0)
 			j = 1;
 		WRITE_ONCE(call->next_req_timo, j);
-		/* Fall through */
+		fallthrough;
 	case 1:
 		if (p.call.timeouts.hard > 0) {
 			j = msecs_to_jiffies(p.call.timeouts.hard);
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index e6ad42b11835..2c3619165680 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -704,7 +704,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		err = ip_defrag(net, skb, user);
 		local_bh_enable();
 		if (err && err != -EINPROGRESS)
-			goto out_free;
+			return err;
 
 		if (!err) {
 			*defrag = true;
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 0618b63f87c4..7d37638ee1c7 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1670,7 +1670,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return 0;
 		}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index deac82f3ad7b..e89fab6ccb34 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -353,23 +353,11 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 			      FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP,
 			      tb[TCA_RED_EARLY_DROP_BLOCK], extack);
 	if (err)
-		goto err_early_drop_init;
-
-	err = tcf_qevent_init(&q->qe_mark, sch,
-			      FLOW_BLOCK_BINDER_TYPE_RED_MARK,
-			      tb[TCA_RED_MARK_BLOCK], extack);
-	if (err)
-		goto err_mark_init;
-
-	return 0;
+		return err;
 
-err_mark_init:
-	tcf_qevent_destroy(&q->qe_early_drop, sch);
-err_early_drop_init:
-	del_timer_sync(&q->adapt_timer);
-	red_offload(sch, false);
-	qdisc_put(q->qdisc);
-	return err;
+	return tcf_qevent_init(&q->qe_mark, sch,
+			       FLOW_BLOCK_BINDER_TYPE_RED_MARK,
+			       tb[TCA_RED_MARK_BLOCK], extack);
 }
 
 static int red_change(struct Qdisc *sch, struct nlattr *opt,
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e981992634dd..fe53c1e38c7d 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1176,9 +1176,27 @@ static void taprio_offload_config_changed(struct taprio_sched *q)
 	spin_unlock(&q->current_entry_lock);
 }
 
-static void taprio_sched_to_offload(struct taprio_sched *q,
+static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask)
+{
+	u32 i, queue_mask = 0;
+
+	for (i = 0; i < dev->num_tc; i++) {
+		u32 offset, count;
+
+		if (!(tc_mask & BIT(i)))
+			continue;
+
+		offset = dev->tc_to_txq[i].offset;
+		count = dev->tc_to_txq[i].count;
+
+		queue_mask |= GENMASK(offset + count - 1, offset);
+	}
+
+	return queue_mask;
+}
+
+static void taprio_sched_to_offload(struct net_device *dev,
 				    struct sched_gate_list *sched,
-				    const struct tc_mqprio_qopt *mqprio,
 				    struct tc_taprio_qopt_offload *offload)
 {
 	struct sched_entry *entry;
@@ -1193,7 +1211,8 @@ static void taprio_sched_to_offload(struct taprio_sched *q,
 
 		e->command = entry->command;
 		e->interval = entry->interval;
-		e->gate_mask = entry->gate_mask;
+		e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask);
+
 		i++;
 	}
 
@@ -1201,7 +1220,6 @@ static void taprio_sched_to_offload(struct taprio_sched *q,
 }
 
 static int taprio_enable_offload(struct net_device *dev,
-				 struct tc_mqprio_qopt *mqprio,
 				 struct taprio_sched *q,
 				 struct sched_gate_list *sched,
 				 struct netlink_ext_ack *extack)
@@ -1223,7 +1241,7 @@ static int taprio_enable_offload(struct net_device *dev,
 		return -ENOMEM;
 	}
 	offload->enable = 1;
-	taprio_sched_to_offload(q, sched, mqprio, offload);
+	taprio_sched_to_offload(dev, sched, offload);
 
 	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload);
 	if (err < 0) {
@@ -1485,7 +1503,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
-		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
+		err = taprio_enable_offload(dev, q, new_admin, extack);
 	else
 		err = taprio_disable_offload(dev, q, extack);
 	if (err)
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index aea2a982984d..8a58f42d6d19 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -875,7 +875,7 @@ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp)
 	case AF_INET:
 		if (!__ipv6_only_sock(sctp_opt2sk(sp)))
 			return 1;
-		/* fallthru */
+		fallthrough;
 	default:
 		return 0;
 	}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 577e3bc4ee6f..3fd06a27105d 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -912,7 +912,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 		case SCTP_CID_ABORT:
 			if (sctp_test_T_bit(chunk))
 				ctx->packet->vtag = ctx->asoc->c.my_vtag;
-			/* fallthru */
+			fallthrough;
 
 		/* The following chunks are "response" chunks, i.e.
 		 * they are generated in response to something we
@@ -927,7 +927,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 		case SCTP_CID_ECN_CWR:
 		case SCTP_CID_ASCONF_ACK:
 			one_packet = 1;
-			/* Fall through */
+			fallthrough;
 
 		case SCTP_CID_SACK:
 		case SCTP_CID_HEARTBEAT:
@@ -1030,7 +1030,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
 		if (!ctx->packet || !ctx->packet->has_cookie_echo)
 			return;
 
-		/* fall through */
+		fallthrough;
 	case SCTP_STATE_ESTABLISHED:
 	case SCTP_STATE_SHUTDOWN_PENDING:
 	case SCTP_STATE_SHUTDOWN_RECEIVED:
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 47910470e532..c11c24524652 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2077,7 +2077,7 @@ static enum sctp_ierror sctp_process_unk_param(
 		break;
 	case SCTP_PARAM_ACTION_DISCARD_ERR:
 		retval =  SCTP_IERROR_ERROR;
-		/* Fall through */
+		fallthrough;
 	case SCTP_PARAM_ACTION_SKIP_ERR:
 		/* Make an ERROR chunk, preparing enough room for
 		 * returning multiple unknown parameters.
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 9f36fe911d08..aa821e71f05e 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1516,7 +1516,7 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 
 			if (timer_pending(timer))
 				break;
-			/* fall through */
+			fallthrough;
 
 		case SCTP_CMD_TIMER_START:
 			timer = &asoc->timers[cmd->obj.to];
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e86620fbd90f..c669f8bd1eab 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4315,7 +4315,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(err_chunk));
 		}
-		/* Fall Through */
+		fallthrough;
 	case SCTP_IERROR_AUTH_BAD_KEYID:
 	case SCTP_IERROR_BAD_SIG:
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ec1fba1fbe71..836615f71a7d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -8060,8 +8060,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 
 	pr_debug("%s: begins, snum:%d\n", __func__, snum);
 
-	local_bh_disable();
-
 	if (snum == 0) {
 		/* Search for an available port. */
 		int low, high, remaining, index;
@@ -8079,20 +8077,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 				continue;
 			index = sctp_phashfn(net, rover);
 			head = &sctp_port_hashtable[index];
-			spin_lock(&head->lock);
+			spin_lock_bh(&head->lock);
 			sctp_for_each_hentry(pp, &head->chain)
 				if ((pp->port == rover) &&
 				    net_eq(net, pp->net))
 					goto next;
 			break;
 		next:
-			spin_unlock(&head->lock);
+			spin_unlock_bh(&head->lock);
+			cond_resched();
 		} while (--remaining > 0);
 
 		/* Exhausted local port range during search? */
 		ret = 1;
 		if (remaining <= 0)
-			goto fail;
+			return ret;
 
 		/* OK, here is the one we will use.  HEAD (the port
 		 * hash table list entry) is non-NULL and we hold it's
@@ -8107,7 +8106,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		 * port iterator, pp being NULL.
 		 */
 		head = &sctp_port_hashtable[sctp_phashfn(net, snum)];
-		spin_lock(&head->lock);
+		spin_lock_bh(&head->lock);
 		sctp_for_each_hentry(pp, &head->chain) {
 			if ((pp->port == snum) && net_eq(pp->net, net))
 				goto pp_found;
@@ -8207,10 +8206,7 @@ success:
 	ret = 0;
 
 fail_unlock:
-	spin_unlock(&head->lock);
-
-fail:
-	local_bh_enable();
+	spin_unlock_bh(&head->lock);
 	return ret;
 }
 
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index bda2536dd740..6dc95dcc0ff4 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 	int ret;
 
 	if (outcnt <= stream->outcnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->out, outcnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->outcnt = outcnt;
 	return 0;
 }
@@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 	int ret;
 
 	if (incnt <= stream->incnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->in, incnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->incnt = incnt;
 	return 0;
 }
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 290270c821ca..0e7409e469c0 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -116,7 +116,6 @@ static void smc_close_cancel_work(struct smc_sock *smc)
 	cancel_work_sync(&smc->conn.close_work);
 	cancel_delayed_work_sync(&smc->conn.tx_work);
 	lock_sock(sk);
-	sk->sk_state = SMC_CLOSED;
 }
 
 /* terminate smc socket abnormally - active abort
@@ -134,22 +133,22 @@ void smc_close_active_abort(struct smc_sock *smc)
 	}
 	switch (sk->sk_state) {
 	case SMC_ACTIVE:
-		sk->sk_state = SMC_PEERABORTWAIT;
-		smc_close_cancel_work(smc);
-		sk->sk_state = SMC_CLOSED;
-		sock_put(sk); /* passive closing */
-		break;
 	case SMC_APPCLOSEWAIT1:
 	case SMC_APPCLOSEWAIT2:
+		sk->sk_state = SMC_PEERABORTWAIT;
 		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
 		sk->sk_state = SMC_CLOSED;
-		sock_put(sk); /* postponed passive closing */
+		sock_put(sk); /* (postponed) passive closing */
 		break;
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
 	case SMC_PEERFINCLOSEWAIT:
 		sk->sk_state = SMC_PEERABORTWAIT;
 		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
 		sk->sk_state = SMC_CLOSED;
 		smc_conn_free(&smc->conn);
 		release_clcsock = true;
@@ -159,6 +158,8 @@ void smc_close_active_abort(struct smc_sock *smc)
 	case SMC_APPFINCLOSEWAIT:
 		sk->sk_state = SMC_PEERABORTWAIT;
 		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
 		sk->sk_state = SMC_CLOSED;
 		smc_conn_free(&smc->conn);
 		release_clcsock = true;
@@ -372,7 +373,7 @@ static void smc_close_passive_work(struct work_struct *work)
 	case SMC_PEERCLOSEWAIT1:
 		if (rxflags->peer_done_writing)
 			sk->sk_state = SMC_PEERCLOSEWAIT2;
-		/* fall through */
+		fallthrough;
 		/* to check for closing */
 	case SMC_PEERCLOSEWAIT2:
 		if (!smc_cdc_rxed_any_close(conn))
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index b42fa3b00d00..a406627b1d55 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1356,6 +1356,8 @@ create:
 	if (ini->is_smcd) {
 		conn->rx_off = sizeof(struct smcd_cdc_msg);
 		smcd_cdc_rx_init(conn); /* init tasklet for this conn */
+	} else {
+		conn->rx_off = 0;
 	}
 #ifndef KERNEL_HAS_ATOMIC64
 	spin_lock_init(&conn->acurs_lock);
@@ -1777,6 +1779,7 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
 		list_del(&smc->conn.sndbuf_desc->list);
 		mutex_unlock(&smc->conn.lgr->sndbufs_lock);
 		smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
+		smc->conn.sndbuf_desc = NULL;
 	}
 	return rc;
 }
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index e1f64f4ba236..da9ba6d1679b 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_connection *conn = &smc->conn;
-		struct smcd_diag_dmbinfo dinfo = {
-			.linkid = *((u32 *)conn->lgr->id),
-			.peer_gid = conn->lgr->peer_gid,
-			.my_gid = conn->lgr->smcd->local_gid,
-			.token = conn->rmb_desc->token,
-			.peer_token = conn->peer_token
-		};
+		struct smcd_diag_dmbinfo dinfo;
+
+		memset(&dinfo, 0, sizeof(dinfo));
+
+		dinfo.linkid = *((u32 *)conn->lgr->id);
+		dinfo.peer_gid = conn->lgr->peer_gid;
+		dinfo.my_gid = conn->lgr->smcd->local_gid;
+		dinfo.token = conn->rmb_desc->token;
+		dinfo.peer_token = conn->peer_token;
 
 		if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
 			goto errout;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index df5b0a6ea848..3ea33466ebe9 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -841,6 +841,9 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
 	struct smc_init_info ini;
 	int lnk_idx, rc = 0;
 
+	if (!llc->qp_mtu)
+		goto out_reject;
+
 	ini.vlan_id = lgr->vlan_id;
 	smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev);
 	if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) &&
@@ -917,10 +920,20 @@ out:
 	kfree(qentry);
 }
 
+static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(llc->raw.data); i++)
+		if (llc->raw.data[i])
+			return false;
+	return true;
+}
+
 static bool smc_llc_is_local_add_link(union smc_llc_msg *llc)
 {
 	if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK &&
-	    !llc->add_link.qp_mtu && !llc->add_link.link_num)
+	    smc_llc_is_empty_llc_message(llc))
 		return true;
 	return false;
 }
diff --git a/net/socket.c b/net/socket.c
index dbbe8ea7d395..0c0144604f81 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3610,7 +3610,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
 EXPORT_SYMBOL(kernel_getsockname);
 
 /**
- *	kernel_peername - get the address which the socket is connected (kernel space)
+ *	kernel_getpeername - get the address which the socket is connected (kernel space)
  *	@sock: socket
  *	@addr: address holder
  *
@@ -3671,7 +3671,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
 EXPORT_SYMBOL(kernel_sendpage_locked);
 
 /**
- *	kernel_shutdown - shut down part of a full-duplex connection (kernel space)
+ *	kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space)
  *	@sock: socket
  *	@how: connection part
  *
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 90b8329fef82..8b300b74a722 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -137,7 +137,7 @@ gss_krb5_make_confounder(char *p, u32 conflen)
 	switch (conflen) {
 	case 16:
 		*q++ = i++;
-		/* fall through */
+		fallthrough;
 	case 8:
 		*q++ = i++;
 		break;
diff --git a/net/sunrpc/auth_gss/trace.c b/net/sunrpc/auth_gss/trace.c
index d26036a57443..76685abba60f 100644
--- a/net/sunrpc/auth_gss/trace.c
+++ b/net/sunrpc/auth_gss/trace.c
@@ -9,7 +9,6 @@
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/auth_gss.h>
 #include <linux/sunrpc/gss_err.h>
-#include <linux/sunrpc/auth_gss.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/rpcgss.h>
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index a91d1cdad9d7..62e0b6c1e8cf 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1702,7 +1702,7 @@ call_reserveresult(struct rpc_task *task)
 	switch (status) {
 	case -ENOMEM:
 		rpc_delay(task, HZ >> 2);
-		/* fall through */
+		fallthrough;
 	case -EAGAIN:	/* woken up; retry */
 		task->tk_action = call_retry_reserve;
 		return;
@@ -1759,13 +1759,13 @@ call_refreshresult(struct rpc_task *task)
 		/* Use rate-limiting and a max number of retries if refresh
 		 * had status 0 but failed to update the cred.
 		 */
-		/* fall through */
+		fallthrough;
 	case -ETIMEDOUT:
 		rpc_delay(task, 3*HZ);
-		/* fall through */
+		fallthrough;
 	case -EAGAIN:
 		status = -EACCES;
-		/* fall through */
+		fallthrough;
 	case -EKEYEXPIRED:
 		if (!task->tk_cred_retry)
 			break;
@@ -2132,7 +2132,7 @@ call_connect_status(struct rpc_task *task)
 			rpc_force_rebind(clnt);
 			goto out_retry;
 		}
-		/* fall through */
+		fallthrough;
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENETDOWN:
@@ -2146,7 +2146,7 @@ call_connect_status(struct rpc_task *task)
 			break;
 		/* retry with existing socket, after a delay */
 		rpc_delay(task, 3*HZ);
-		/* fall through */
+		fallthrough;
 	case -EADDRINUSE:
 	case -ENOTCONN:
 	case -EAGAIN:
@@ -2228,7 +2228,7 @@ call_transmit_status(struct rpc_task *task)
 		 */
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
-		/* fall through */
+		fallthrough;
 	case -EBADSLT:
 	case -EAGAIN:
 		task->tk_action = call_transmit;
@@ -2247,7 +2247,7 @@ call_transmit_status(struct rpc_task *task)
 			rpc_call_rpcerror(task, task->tk_status);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -EADDRINUSE:
@@ -2313,7 +2313,7 @@ call_bc_transmit_status(struct rpc_task *task)
 		break;
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
-		/* fall through */
+		fallthrough;
 	case -EBADSLT:
 	case -EAGAIN:
 		task->tk_status = 0;
@@ -2380,7 +2380,7 @@ call_status(struct rpc_task *task)
 		 * were a timeout.
 		 */
 		rpc_delay(task, 3*HZ);
-		/* fall through */
+		fallthrough;
 	case -ETIMEDOUT:
 		break;
 	case -ECONNREFUSED:
@@ -2391,7 +2391,7 @@ call_status(struct rpc_task *task)
 		break;
 	case -EADDRINUSE:
 		rpc_delay(task, 3*HZ);
-		/* fall through */
+		fallthrough;
 	case -EPIPE:
 	case -EAGAIN:
 		break;
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index c27123e6ba80..4a67685c83eb 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -982,8 +982,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, len);
 	if (unlikely(p == NULL))
 		goto out_fail;
-	dprintk("RPC: %5u RPCB_%s reply: %s\n", req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name, (char *)p);
+	dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid,
+			req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p);
 
 	if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len,
 				sap, sizeof(address)) == 0)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 6ba9d5842629..5a8e47bbfb9f 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1623,7 +1623,7 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 	case -EAGAIN:
 		xprt_add_backlog(xprt, task);
 		dprintk("RPC:       waiting for request slot\n");
-		/* fall through */
+		fallthrough;
 	default:
 		task->tk_status = -EAGAIN;
 	}
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 75c646743df3..ad6e2e4994ce 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -268,7 +268,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
 		pr_info("rpcrdma: removing device %s for %pISpc\n",
 			ep->re_id->device->name, sap);
-		/* fall through */
+		fallthrough;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
 		ep->re_connect_status = -ENODEV;
 		goto disconnected;
@@ -933,6 +933,8 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req)
 
 	rpcrdma_regbuf_dma_unmap(req->rl_sendbuf);
 	rpcrdma_regbuf_dma_unmap(req->rl_recvbuf);
+
+	frwr_reset(req);
 }
 
 /* ASSUMPTION: the rb_allreqs list is stable for the duration,
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c57aef829403..554e1bb4c1c7 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -885,7 +885,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
 	default:
 		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
 			-status);
-		/* fall through */
+		fallthrough;
 	case -EPIPE:
 		xs_close(xprt);
 		status = -ENOTCONN;
@@ -1436,7 +1436,7 @@ static void xs_tcp_state_change(struct sock *sk)
 		xprt->connect_cookie++;
 		clear_bit(XPRT_CONNECTED, &xprt->state);
 		xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT);
-		/* fall through */
+		fallthrough;
 	case TCP_CLOSING:
 		/*
 		 * If the server closed down the connection, make sure that
@@ -2202,7 +2202,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 	switch (ret) {
 	case 0:
 		xs_set_srcport(transport, sock);
-		/* fall through */
+		fallthrough;
 	case -EINPROGRESS:
 		/* SYN_SENT! */
 		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
@@ -2255,7 +2255,7 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	default:
 		printk("%s: connect returned unhandled error %d\n",
 			__func__, status);
-		/* fall through */
+		fallthrough;
 	case -EADDRNOTAVAIL:
 		/* We're probably in TIME_WAIT. Get rid of existing socket,
 		 * and retry
diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig
index 9dd780215eef..be1c4003d67d 100644
--- a/net/tipc/Kconfig
+++ b/net/tipc/Kconfig
@@ -6,6 +6,7 @@
 menuconfig TIPC
 	tristate "The TIPC Protocol"
 	depends on INET
+	depends on IPV6 || IPV6=n
 	help
 	  The Transparent Inter Process Communication (TIPC) protocol is
 	  specially designed for intra cluster communication. This protocol
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 808b147df7d5..650414110452 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -652,7 +652,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 			test_and_set_bit_lock(0, &b->up);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case NETDEV_GOING_DOWN:
 		clear_bit_unlock(0, &b->up);
 		tipc_reset_bearer(net, b);
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 001bcb0f2480..7c523dc81575 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -326,7 +326,8 @@ static void tipc_aead_free(struct rcu_head *rp)
 	if (aead->cloned) {
 		tipc_aead_put(aead->cloned);
 	} else {
-		head = *this_cpu_ptr(aead->tfm_entry);
+		head = *get_cpu_ptr(aead->tfm_entry);
+		put_cpu_ptr(aead->tfm_entry);
 		list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) {
 			crypto_free_aead(tfm_entry->tfm);
 			list_del(&tfm_entry->list);
@@ -399,10 +400,15 @@ static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val)
  */
 static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead)
 {
-	struct tipc_tfm **tfm_entry = this_cpu_ptr(aead->tfm_entry);
+	struct tipc_tfm **tfm_entry;
+	struct crypto_aead *tfm;
 
+	tfm_entry = get_cpu_ptr(aead->tfm_entry);
 	*tfm_entry = list_next_entry(*tfm_entry, list);
-	return (*tfm_entry)->tfm;
+	tfm = (*tfm_entry)->tfm;
+	put_cpu_ptr(tfm_entry);
+
+	return tfm;
 }
 
 /**
@@ -757,10 +763,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err)
 	switch (err) {
 	case 0:
 		this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]);
+		rcu_read_lock();
 		if (likely(test_bit(0, &b->up)))
 			b->media->send_msg(net, skb, b, &tx_ctx->dst);
 		else
 			kfree_skb(skb);
+		rcu_read_unlock();
 		break;
 	case -EINPROGRESS:
 		return;
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 89257e2a980d..588c2d2b0c69 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -536,7 +536,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
 				update = true;
 				deliver = false;
 			}
-			/* Fall thru */
+			fallthrough;
 		case TIPC_GRP_BCAST_MSG:
 			m->bc_rcv_nxt++;
 			ack = msg_grp_bc_ack_req(hdr);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 107578122973..b7362556da95 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1239,7 +1239,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 			skb_queue_tail(mc_inputq, skb);
 			return true;
 		}
-		/* fall through */
+		fallthrough;
 	case CONN_MANAGER:
 		skb_queue_tail(inputq, skb);
 		return true;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 217516357ef2..90e3c70a91ad 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -275,8 +275,9 @@ err_out:
 static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 				 struct tipc_nl_compat_msg *msg)
 {
-	int err;
+	struct nlmsghdr *nlh;
 	struct sk_buff *arg;
+	int err;
 
 	if (msg->req_type && (!msg->req_size ||
 			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
@@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 		return -ENOMEM;
 	}
 
+	nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI);
+	if (!nlh) {
+		kfree_skb(arg);
+		kfree_skb(msg->rep);
+		msg->rep = NULL;
+		return -EMSGSIZE;
+	}
+	nlmsg_end(arg, nlh);
+
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
 	if (err) {
 		kfree_skb(msg->rep);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 07419f36116a..ebd280e767bd 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -783,7 +783,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 	case TIPC_ESTABLISHED:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
 			revents |= EPOLLOUT;
-		/* fall through */
+		fallthrough;
 	case TIPC_LISTEN:
 	case TIPC_CONNECTING:
 		if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
@@ -2597,7 +2597,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 		 * case is EINPROGRESS, rather than EALREADY.
 		 */
 		res = -EINPROGRESS;
-		/* fall through */
+		fallthrough;
 	case TIPC_CONNECTING:
 		if (!timeout) {
 			if (previous == TIPC_CONNECTING)
@@ -2771,18 +2771,21 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 	trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
-	sk->sk_shutdown = SEND_SHUTDOWN;
+	if (tipc_sk_type_connectionless(sk))
+		sk->sk_shutdown = SHUTDOWN_MASK;
+	else
+		sk->sk_shutdown = SEND_SHUTDOWN;
 
 	if (sk->sk_state == TIPC_DISCONNECTING) {
 		/* Discard any unreceived messages */
 		__skb_queue_purge(&sk->sk_receive_queue);
 
-		/* Wake up anyone sleeping in poll */
-		sk->sk_state_change(sk);
 		res = 0;
 	} else {
 		res = -ENOTCONN;
 	}
+	/* Wake up anyone sleeping in poll. */
+	sk->sk_state_change(sk);
 
 	release_sock(sk);
 	return res;
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 53f0de0676b7..911d13cd2e67 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -660,6 +660,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	struct udp_tunnel_sock_cfg tuncfg = {NULL};
 	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
 	u8 node_id[NODE_ID_LEN] = {0,};
+	struct net_device *dev;
 	int rmcast = 0;
 
 	ub = kzalloc(sizeof(*ub), GFP_ATOMIC);
@@ -714,8 +715,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	rcu_assign_pointer(ub->bearer, b);
 	tipc_udp_media_addr_set(&b->addr, &local);
 	if (local.proto == htons(ETH_P_IP)) {
-		struct net_device *dev;
-
 		dev = __ip_dev_find(net, local.ipv4.s_addr, false);
 		if (!dev) {
 			err = -ENODEV;
@@ -738,9 +737,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		b->mtu = b->media->mtu;
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (local.proto == htons(ETH_P_IPV6)) {
-		struct net_device *dev;
-
-		dev = ipv6_dev_find(net, &local.ipv6);
+		dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL;
+		dev = ipv6_dev_find(net, &local.ipv6, dev);
 		if (!dev) {
 			err = -ENODEV;
 			goto err;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 181ea6fb56a6..92784e51ee7d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -837,7 +837,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		 */
 	case SOCK_RAW:
 		sock->type = SOCK_DGRAM;
-		/* fall through */
+		fallthrough;
 	case SOCK_DGRAM:
 		sock->ops = &unix_dgram_ops;
 		break;
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 90f0f82cd9ca..6a6f2f214c10 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/bitfield.h>
 #include <net/cfg80211.h>
 #include "core.h"
 #include "rdev-ops.h"
@@ -912,6 +913,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 	struct ieee80211_sta_vht_cap *vht_cap;
 	struct ieee80211_edmg *edmg_cap;
 	u32 width, control_freq, cap;
+	bool support_80_80 = false;
 
 	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
 		return false;
@@ -957,7 +959,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 		if (!ht_cap->ht_supported &&
 		    chandef->chan->band != NL80211_BAND_6GHZ)
 			return false;
-		/* fall through */
+		fallthrough;
 	case NL80211_CHAN_WIDTH_20_NOHT:
 		prohibited_flags |= IEEE80211_CHAN_NO_20MHZ;
 		width = 20;
@@ -979,11 +981,15 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 			return false;
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
-		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
-		if (chandef->chan->band != NL80211_BAND_6GHZ &&
-		    cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
+		cap = vht_cap->cap;
+		support_80_80 =
+			(cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) ||
+			(cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+			 cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) ||
+			u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1;
+		if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80)
 			return false;
-		/* fall through */
+		fallthrough;
 	case NL80211_CHAN_WIDTH_80:
 		prohibited_flags |= IEEE80211_CHAN_NO_80MHZ;
 		width = 80;
@@ -1001,7 +1007,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 			return false;
 		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
 		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
-		    cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
+		    cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ &&
+		    !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK))
 			return false;
 		break;
 	default:
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index a6c61a2e6569..db7333e20dd7 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -941,7 +941,7 @@ void cfg80211_cac_event(struct net_device *netdev,
 		       sizeof(struct cfg80211_chan_def));
 		queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk);
 		cfg80211_sched_dfs_chan_update(rdev);
-		/* fall through */
+		fallthrough;
 	case NL80211_RADAR_CAC_ABORTED:
 		wdev->cac_started = false;
 		break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c04fc6cf6583..2c9e9a2d1688 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2107,7 +2107,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 1:
 		if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES,
 			    sizeof(u32) * rdev->wiphy.n_cipher_suites,
@@ -2154,7 +2154,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES,
 					rdev->wiphy.interface_modes))
@@ -2162,7 +2162,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 3:
 		nl_bands = nla_nest_start_noflag(msg,
 						 NL80211_ATTR_WIPHY_BANDS);
@@ -2189,7 +2189,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 				state->chan_start++;
 				if (state->split)
 					break;
-				/* fall through */
+				fallthrough;
 			default:
 				/* add frequencies */
 				nl_freqs = nla_nest_start_noflag(msg,
@@ -2244,7 +2244,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 4:
 		nl_cmds = nla_nest_start_noflag(msg,
 						NL80211_ATTR_SUPPORTED_COMMANDS);
@@ -2273,7 +2273,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 5:
 		if (rdev->ops->remain_on_channel &&
 		    (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
@@ -2291,7 +2291,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 6:
 #ifdef CONFIG_PM
 		if (nl80211_send_wowlan(msg, rdev, state->split))
@@ -2302,7 +2302,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 #else
 		state->split_start++;
 #endif
-		/* fall through */
+		fallthrough;
 	case 7:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES,
 					rdev->wiphy.software_iftypes))
@@ -2315,7 +2315,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
-		/* fall through */
+		fallthrough;
 	case 8:
 		if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
 		    nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME,
@@ -5207,7 +5207,7 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr)
 		break;
 	default:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	case RATE_INFO_BW_20:
 		rate_flg = 0;
 		break;
@@ -6011,7 +6011,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY])
 		params.he_6ghz_capa =
-			nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+			nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]);
 
 	if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT])
 		params.airtime_weight =
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 35b8847a2f6d..d8a90d397423 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2946,6 +2946,9 @@ int regulatory_hint_user(const char *alpha2,
 	if (WARN_ON(!alpha2))
 		return -EINVAL;
 
+	if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2))
+		return -EINVAL;
+
 	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
 	if (!request)
 		return -ENOMEM;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index e67a74488bbe..04f2d198c215 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1433,7 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	switch (ftype) {
 	case CFG80211_BSS_FTYPE_BEACON:
 		ies->from_beacon = true;
-		/* fall through */
+		fallthrough;
 	case CFG80211_BSS_FTYPE_UNKNOWN:
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 		break;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 985f3c23f054..079ce320dc1e 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -205,7 +205,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev,
 		return err;
 	case CFG80211_CONN_ASSOC_FAILED_TIMEOUT:
 		*treason = NL80211_TIMEOUT_ASSOC;
-		/* fall through */
+		fallthrough;
 	case CFG80211_CONN_ASSOC_FAILED:
 		cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid,
 				     NULL, 0,
@@ -215,7 +215,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev,
 		cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid,
 				     NULL, 0,
 				     WLAN_REASON_DEAUTH_LEAVING, false);
-		/* fall through */
+		fallthrough;
 	case CFG80211_CONN_ABANDON:
 		/* free directly, disconnected event already sent */
 		cfg80211_sme_free(wdev);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index dfad1c0f57ad..4a9ff9ef513f 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -123,11 +123,13 @@ int ieee80211_freq_khz_to_channel(u32 freq)
 		return (freq - 2407) / 5;
 	else if (freq >= 4910 && freq <= 4980)
 		return (freq - 4000) / 5;
-	else if (freq < 5945)
+	else if (freq < 5925)
 		return (freq - 5000) / 5;
+	else if (freq == 5935)
+		return 2;
 	else if (freq <= 45000) /* DMG band lower limit */
-		/* see 802.11ax D4.1 27.3.22.2 */
-		return (freq - 5940) / 5;
+		/* see 802.11ax D6.1 27.3.22.2 */
+		return (freq - 5950) / 5;
 	else if (freq >= 58320 && freq <= 70200)
 		return (freq - 56160) / 2160;
 	else
@@ -198,7 +200,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband)
 				sband->bitrates[i].flags |=
 					IEEE80211_RATE_MANDATORY_G;
 				want--;
-				/* fall through */
+				fallthrough;
 			default:
 				sband->bitrates[i].flags |=
 					IEEE80211_RATE_ERP_G;
@@ -1008,7 +1010,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 		case NL80211_IFTYPE_STATION:
 			if (dev->ieee80211_ptr->use_4addr)
 				break;
-			/* fall through */
+			fallthrough;
 		case NL80211_IFTYPE_OCB:
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_ADHOC:
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index aa918d7ff6bd..4d2160c989a3 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -1334,7 +1334,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 			wstats.qual.qual = sig + 110;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case CFG80211_SIGNAL_TYPE_UNSPEC:
 		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) {
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
@@ -1343,7 +1343,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 			wstats.qual.qual = sinfo.signal;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		wstats.qual.updated |= IW_QUAL_LEVEL_INVALID;
 		wstats.qual.updated |= IW_QUAL_QUAL_INVALID;
diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7fb327632272..8e1a49b0c0dc 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -98,7 +98,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities,
 					*vc_fac_mask |= X25_MASK_REVERSE;
 					break;
 				}
-				/*fall through */
+				fallthrough;
 			case X25_FAC_THROUGHPUT:
 				facilities->throughput = p[1];
 				*vc_fac_mask |= X25_MASK_THROUGHPUT;
diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index 4d3bb46aaae0..e1c4197af468 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -349,7 +349,7 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp
 
 		case X25_RESET_REQUEST:
 			x25_write_internal(sk, X25_RESET_CONFIRMATION);
-			/* fall through */
+			fallthrough;
 		case X25_RESET_CONFIRMATION: {
 			x25_stop_timer(sk);
 			x25->condition = 0x00;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d5280fd6f9c1..d622c2548d22 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3410,7 +3410,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 		switch (nexthdr) {
 		case NEXTHDR_FRAGMENT:
 			onlyproto = 1;
-			/* fall through */
+			fallthrough;
 		case NEXTHDR_ROUTING:
 		case NEXTHDR_HOP:
 		case NEXTHDR_DEST:
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index 7d7153777678..4b22ace52f80 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -483,7 +483,7 @@ int main(int argc, char **argv)
 					"Option -%c requires an argument.\n\n",
 					optopt);
 		case 'h':
-			// fallthrough
+			fallthrough;
 		default:
 			Usage();
 			return 0;
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 62c275685b75..95e4cdb94fe9 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -66,7 +66,6 @@ KBUILD_CFLAGS += -Wnested-externs
 KBUILD_CFLAGS += -Wshadow
 KBUILD_CFLAGS += $(call cc-option, -Wlogical-op)
 KBUILD_CFLAGS += -Wmissing-field-initializers
-KBUILD_CFLAGS += -Wsign-compare
 KBUILD_CFLAGS += -Wtype-limits
 KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized)
 KBUILD_CFLAGS += $(call cc-option, -Wunused-macros)
@@ -87,6 +86,7 @@ KBUILD_CFLAGS += -Wpacked
 KBUILD_CFLAGS += -Wpadded
 KBUILD_CFLAGS += -Wpointer-arith
 KBUILD_CFLAGS += -Wredundant-decls
+KBUILD_CFLAGS += -Wsign-compare
 KBUILD_CFLAGS += -Wswitch-default
 KBUILD_CFLAGS += $(call cc-option, -Wpacked-bitfield-compat)
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 60d4a79674b6..504d2e431c60 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2639,8 +2639,8 @@ sub process {
 
 # Check if the commit log has what seems like a diff which can confuse patch
 		if ($in_commit_log && !$commit_log_has_diff &&
-		    (($line =~ m@^\s+diff\b.*a/[\w/]+@ &&
-		      $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) ||
+		    (($line =~ m@^\s+diff\b.*a/([\w/]+)@ &&
+		      $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) ||
 		     $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ ||
 		     $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) {
 			ERROR("DIFF_IN_COMMIT_MSG",
diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c
index b071bf476fea..3bc48c726c41 100644
--- a/scripts/extract-cert.c
+++ b/scripts/extract-cert.c
@@ -71,7 +71,7 @@ static void drain_openssl_errors(void)
 static const char *key_pass;
 static BIO *wb;
 static char *cert_dst;
-int kbuild_verbose;
+static int kbuild_verbose;
 
 static void write_cert(X509 *x509)
 {
diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c
index 7a85c4e21175..057c6cabad1d 100644
--- a/scripts/genksyms/keywords.c
+++ b/scripts/genksyms/keywords.c
@@ -25,9 +25,9 @@ static struct resword {
 	{ "__int128_t", BUILTIN_INT_KEYW },
 	{ "__uint128_t", BUILTIN_INT_KEYW },
 
-	// According to rth, c99 defines "_Bool", __restrict", __restrict__", "restrict".  KAO
+	// According to rth, c99 defines "_Bool", "__restrict", "__restrict__", "restrict".  KAO
 	{ "_Bool", BOOL_KEYW },
-	{ "_restrict", RESTRICT_KEYW },
+	{ "__restrict", RESTRICT_KEYW },
 	{ "__restrict__", RESTRICT_KEYW },
 	{ "restrict", RESTRICT_KEYW },
 	{ "asm", ASM_KEYW },
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index daf1c1506ec4..e0f965529166 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -755,7 +755,6 @@ static void build_conf(struct menu *menu)
 			switch (ptype) {
 			case P_MENU:
 				child_count++;
-				prompt = prompt;
 				if (single_menu_mode) {
 					item_make(menu, 'm',
 						"%s%*c%s",
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index bc390df49f1f..8638785328a7 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -885,7 +885,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 		connect(action, SIGNAL(toggled(bool)),
 			parent(), SLOT(setShowName(bool)));
 		connect(parent(), SIGNAL(showNameChanged(bool)),
-			action, SLOT(setOn(bool)));
+			action, SLOT(setChecked(bool)));
 		action->setChecked(showName);
 		headerPopup->addAction(action);
 
@@ -894,7 +894,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 		connect(action, SIGNAL(toggled(bool)),
 			parent(), SLOT(setShowRange(bool)));
 		connect(parent(), SIGNAL(showRangeChanged(bool)),
-			action, SLOT(setOn(bool)));
+			action, SLOT(setChecked(bool)));
 		action->setChecked(showRange);
 		headerPopup->addAction(action);
 
@@ -903,7 +903,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 		connect(action, SIGNAL(toggled(bool)),
 			parent(), SLOT(setShowData(bool)));
 		connect(parent(), SIGNAL(showDataChanged(bool)),
-			action, SLOT(setOn(bool)));
+			action, SLOT(setChecked(bool)));
 		action->setChecked(showData);
 		headerPopup->addAction(action);
 	}
@@ -1012,6 +1012,16 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name)
 		configSettings->endGroup();
 		connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings()));
 	}
+
+	contextMenu = createStandardContextMenu();
+	QAction *action = new QAction("Show Debug Info", contextMenu);
+
+	action->setCheckable(true);
+	connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
+	connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setChecked(bool)));
+	action->setChecked(showDebug());
+	contextMenu->addSeparator();
+	contextMenu->addAction(action);
 }
 
 void ConfigInfoView::saveSettings(void)
@@ -1066,80 +1076,80 @@ void ConfigInfoView::symbolInfo(void)
 void ConfigInfoView::menuInfo(void)
 {
 	struct symbol* sym;
-	QString head, debug, help;
+	QString info;
+	QTextStream stream(&info);
 
 	sym = _menu->sym;
 	if (sym) {
 		if (_menu->prompt) {
-			head += "<big><b>";
-			head += print_filter(_menu->prompt->text);
-			head += "</b></big>";
+			stream << "<big><b>";
+			stream << print_filter(_menu->prompt->text);
+			stream << "</b></big>";
 			if (sym->name) {
-				head += " (";
+				stream << " (";
 				if (showDebug())
-					head += QString().sprintf("<a href=\"s%s\">", sym->name);
-				head += print_filter(sym->name);
+					stream << "<a href=\"s" << sym->name << "\">";
+				stream << print_filter(sym->name);
 				if (showDebug())
-					head += "</a>";
-				head += ")";
+					stream << "</a>";
+				stream << ")";
 			}
 		} else if (sym->name) {
-			head += "<big><b>";
+			stream << "<big><b>";
 			if (showDebug())
-				head += QString().sprintf("<a href=\"s%s\">", sym->name);
-			head += print_filter(sym->name);
+				stream << "<a href=\"s" << sym->name << "\">";
+			stream << print_filter(sym->name);
 			if (showDebug())
-				head += "</a>";
-			head += "</b></big>";
+				stream << "</a>";
+			stream << "</b></big>";
 		}
-		head += "<br><br>";
+		stream << "<br><br>";
 
 		if (showDebug())
-			debug = debug_info(sym);
+			stream << debug_info(sym);
 
-		struct gstr help_gstr = str_new();
-		menu_get_ext_help(_menu, &help_gstr);
-		help = print_filter(str_get(&help_gstr));
-		str_free(&help_gstr);
 	} else if (_menu->prompt) {
-		head += "<big><b>";
-		head += print_filter(_menu->prompt->text);
-		head += "</b></big><br><br>";
+		stream << "<big><b>";
+		stream << print_filter(_menu->prompt->text);
+		stream << "</b></big><br><br>";
 		if (showDebug()) {
 			if (_menu->prompt->visible.expr) {
-				debug += "&nbsp;&nbsp;dep: ";
-				expr_print(_menu->prompt->visible.expr, expr_print_help, &debug, E_NONE);
-				debug += "<br><br>";
+				stream << "&nbsp;&nbsp;dep: ";
+				expr_print(_menu->prompt->visible.expr,
+					   expr_print_help, &stream, E_NONE);
+				stream << "<br><br>";
 			}
 		}
 	}
 	if (showDebug())
-		debug += QString().sprintf("defined at %s:%d<br><br>", _menu->file->name, _menu->lineno);
+		stream << "defined at " << _menu->file->name << ":"
+		       << _menu->lineno << "<br><br>";
 
-	setText(head + debug + help);
+	setText(info);
 }
 
 QString ConfigInfoView::debug_info(struct symbol *sym)
 {
 	QString debug;
+	QTextStream stream(&debug);
 
-	debug += "type: ";
-	debug += print_filter(sym_type_name(sym->type));
+	stream << "type: ";
+	stream << print_filter(sym_type_name(sym->type));
 	if (sym_is_choice(sym))
-		debug += " (choice)";
+		stream << " (choice)";
 	debug += "<br>";
 	if (sym->rev_dep.expr) {
-		debug += "reverse dep: ";
-		expr_print(sym->rev_dep.expr, expr_print_help, &debug, E_NONE);
-		debug += "<br>";
+		stream << "reverse dep: ";
+		expr_print(sym->rev_dep.expr, expr_print_help, &stream, E_NONE);
+		stream << "<br>";
 	}
 	for (struct property *prop = sym->prop; prop; prop = prop->next) {
 		switch (prop->type) {
 		case P_PROMPT:
 		case P_MENU:
-			debug += QString().sprintf("prompt: <a href=\"m%s\">", sym->name);
-			debug += print_filter(prop->text);
-			debug += "</a><br>";
+			stream << "prompt: <a href=\"m" << sym->name << "\">";
+			stream << print_filter(prop->text);
+			stream << "</a><br>";
 			break;
 		case P_DEFAULT:
 		case P_SELECT:
@@ -1147,30 +1157,33 @@ QString ConfigInfoView::debug_info(struct symbol *sym)
 		case P_COMMENT:
 		case P_IMPLY:
 		case P_SYMBOL:
-			debug += prop_get_type_name(prop->type);
-			debug += ": ";
-			expr_print(prop->expr, expr_print_help, &debug, E_NONE);
-			debug += "<br>";
+			stream << prop_get_type_name(prop->type);
+			stream << ": ";
+			expr_print(prop->expr, expr_print_help,
+				   &stream, E_NONE);
+			stream << "<br>";
 			break;
 		case P_CHOICE:
 			if (sym_is_choice(sym)) {
-				debug += "choice: ";
-				expr_print(prop->expr, expr_print_help, &debug, E_NONE);
-				debug += "<br>";
+				stream << "choice: ";
+				expr_print(prop->expr, expr_print_help,
+					   &stream, E_NONE);
+				stream << "<br>";
 			}
 			break;
 		default:
-			debug += "unknown property: ";
-			debug += prop_get_type_name(prop->type);
-			debug += "<br>";
+			stream << "unknown property: ";
+			stream << prop_get_type_name(prop->type);
+			stream << "<br>";
 		}
 		if (prop->visible.expr) {
-			debug += "&nbsp;&nbsp;&nbsp;&nbsp;dep: ";
-			expr_print(prop->visible.expr, expr_print_help, &debug, E_NONE);
-			debug += "<br>";
+			stream << "&nbsp;&nbsp;&nbsp;&nbsp;dep: ";
+			expr_print(prop->visible.expr, expr_print_help,
+				   &stream, E_NONE);
+			stream << "<br>";
 		}
 	}
-	debug += "<br>";
+	stream << "<br>";
 
 	return debug;
 }
@@ -1208,15 +1221,15 @@ QString ConfigInfoView::print_filter(const QString &str)
 
 void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char *str)
 {
-	QString* text = reinterpret_cast<QString*>(data);
-	QString str2 = print_filter(str);
+	QTextStream *stream = reinterpret_cast<QTextStream *>(data);
 
 	if (sym && sym->name && !(sym->flags & SYMBOL_CONST)) {
-		*text += QString().sprintf("<a href=\"s%s\">", sym->name);
-		*text += str2;
-		*text += "</a>";
-	} else
-		*text += str2;
+		*stream << "<a href=\"s" << sym->name << "\">";
+		*stream << print_filter(str);
+		*stream << "</a>";
+	} else {
+		*stream << print_filter(str);
+	}
 }
 
 void ConfigInfoView::clicked(const QUrl &url)
@@ -1228,7 +1241,6 @@ void ConfigInfoView::clicked(const QUrl &url)
 	struct menu *m = NULL;
 
 	if (count < 1) {
-		qInfo() << "Clicked link is empty";
 		delete[] data;
 		return;
 	}
@@ -1241,7 +1253,6 @@ void ConfigInfoView::clicked(const QUrl &url)
 	strcat(data, "$");
 	result = sym_re_search(data);
 	if (!result) {
-		qInfo() << "Clicked symbol is invalid:" << data;
 		delete[] data;
 		return;
 	}
@@ -1268,23 +1279,10 @@ void ConfigInfoView::clicked(const QUrl &url)
 	delete data;
 }
 
-QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos)
-{
-	QMenu* popup = Parent::createStandardContextMenu(pos);
-	QAction* action = new QAction("Show Debug Info", popup);
-
-	action->setCheckable(true);
-	connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
-	connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool)));
-	action->setChecked(showDebug());
-	popup->addSeparator();
-	popup->addAction(action);
-	return popup;
-}
-
-void ConfigInfoView::contextMenuEvent(QContextMenuEvent *e)
+void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event)
 {
-	Parent::contextMenuEvent(e);
+	contextMenu->popup(event->globalPos());
+	event->accept();
 }
 
 ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent)
diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h
index 461df6419f15..f97376a8123f 100644
--- a/scripts/kconfig/qconf.h
+++ b/scripts/kconfig/qconf.h
@@ -30,7 +30,7 @@ public:
 };
 
 enum colIdx {
-	promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx, colNr
+	promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx
 };
 enum listMode {
 	singleMode, menuMode, symbolMode, fullMode, listMode
@@ -215,6 +215,7 @@ public:
 class ConfigInfoView : public QTextBrowser {
 	Q_OBJECT
 	typedef class QTextBrowser Parent;
+	QMenu *contextMenu;
 public:
 	ConfigInfoView(QWidget* parent, const char *name = 0);
 	bool showDebug(void) const { return _showDebug; }
@@ -235,8 +236,7 @@ protected:
 	QString debug_info(struct symbol *sym);
 	static QString print_filter(const QString &str);
 	static void expr_print_help(void *data, struct symbol *sym, const char *str);
-	QMenu *createStandardContextMenu(const QPoint & pos);
-	void contextMenuEvent(QContextMenuEvent *e);
+	void contextMenuEvent(QContextMenuEvent *event);
 
 	struct symbol *sym;
 	struct menu *_menu;
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 19857d18d814..1c78ba49ca99 100755
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -593,7 +593,10 @@ while ($repeat) {
 }
 
 my %setconfigs;
-my @preserved_kconfigs = split(/:/,$ENV{LMC_KEEP});
+my @preserved_kconfigs;
+if (defined($ENV{'LMC_KEEP'})) {
+	@preserved_kconfigs = split(/:/,$ENV{LMC_KEEP});
+}
 
 sub in_preserved_kconfigs {
     my $kconfig = $config2kfile{$_[0]};
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 32d3f53af10b..850f4ccb6afc 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -26,7 +26,11 @@ else
 fi
 
 # ignore userspace tools
-ignore="$ignore ( -path ${tree}tools ) -prune -o"
+if [ -n "$COMPILED_SOURCE" ]; then
+	ignore="$ignore ( -path ./tools ) -prune -o"
+else
+	ignore="$ignore ( -path ${tree}tools ) -prune -o"
+fi
 
 # Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH
 if [ "${ALLSOURCE_ARCHS}" = "" ]; then
@@ -92,7 +96,7 @@ all_sources()
 all_compiled_sources()
 {
 	realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) \
-		include/generated/autoconf.h $(find -name "*.cmd" -exec \
+		include/generated/autoconf.h $(find $ignore -name "*.cmd" -exec \
 		grep -Poh '(?(?=^source_.* \K).*|(?=^  \K\S).*(?= \\))' {} \+ |
 		awk '!a[$0]++') | sort -u
 }
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 7b0e13ce7dc7..f919ebd042fd 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -577,7 +577,7 @@ static struct aa_label *x_to_label(struct aa_profile *profile,
 			stack = NULL;
 			break;
 		}
-		/* fall through - to X_NAME */
+		fallthrough;	/* to X_NAME */
 	case AA_X_NAME:
 		if (xindex & AA_X_CHILD)
 			/* released by caller */
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 30c246a9d440..fa49b81eb54c 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -292,13 +292,13 @@ void aa_apply_modes_to_perms(struct aa_profile *profile, struct aa_perms *perms)
 	switch (AUDIT_MODE(profile)) {
 	case AUDIT_ALL:
 		perms->audit = ALL_PERMS_MASK;
-		/* fall through */
+		fallthrough;
 	case AUDIT_NOQUIET:
 		perms->quiet = 0;
 		break;
 	case AUDIT_QUIET:
 		perms->audit = 0;
-		/* fall through */
+		fallthrough;
 	case AUDIT_QUIET_DENIED:
 		perms->quiet = ALL_PERMS_MASK;
 		break;
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 372d16382960..b8848f53c8cc 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -223,7 +223,7 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint,
 	case IMA_XATTR_DIGEST_NG:
 		/* first byte contains algorithm id */
 		hash_start = 1;
-		/* fall through */
+		fallthrough;
 	case IMA_XATTR_DIGEST:
 		if (iint->flags & IMA_DIGSIG_REQUIRED) {
 			*cause = "IMA-signature-required";
@@ -395,7 +395,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 		/* It's fine not to have xattrs when using a modsig. */
 		if (try_modsig)
 			break;
-		/* fall through */
+		fallthrough;
 	case INTEGRITY_NOLABEL:		/* No security.evm xattr. */
 		cause = "missing-HMAC";
 		goto out;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 07f033634b27..b4de33074b37 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -1279,12 +1279,12 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 		case Opt_uid_gt:
 		case Opt_euid_gt:
 			entry->uid_op = &uid_gt;
-			/* fall through */
+			fallthrough;
 		case Opt_uid_lt:
 		case Opt_euid_lt:
 			if ((token == Opt_uid_lt) || (token == Opt_euid_lt))
 				entry->uid_op = &uid_lt;
-			/* fall through */
+			fallthrough;
 		case Opt_uid_eq:
 		case Opt_euid_eq:
 			uid_token = (token == Opt_uid_eq) ||
@@ -1313,11 +1313,11 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			break;
 		case Opt_fowner_gt:
 			entry->fowner_op = &uid_gt;
-			/* fall through */
+			fallthrough;
 		case Opt_fowner_lt:
 			if (token == Opt_fowner_lt)
 				entry->fowner_op = &uid_lt;
-			/* fall through */
+			fallthrough;
 		case Opt_fowner_eq:
 			ima_log_string_op(ab, "fowner", args[0].from,
 					  entry->fowner_op);
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 41a5f435b793..c022ee9e2a4e 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -77,7 +77,7 @@ static void ima_show_template_data_ascii(struct seq_file *m,
 		/* skip ':' and '\0' */
 		buf_ptr += 2;
 		buflen -= buf_ptr - field_data->data;
-		/* fall through */
+		fallthrough;
 	case DATA_FMT_DIGEST:
 	case DATA_FMT_HEX:
 		if (!buflen)
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 7e0232db1707..1fe8b934f656 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -465,7 +465,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx)
 		case -EAGAIN: /* no key */
 			if (ret)
 				break;
-			/* fall through */
+			fallthrough;
 		case -ENOKEY: /* negative key */
 			ret = key_ref;
 			break;
@@ -487,7 +487,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx)
 		case -EAGAIN: /* no key */
 			if (ret)
 				break;
-			/* fall through */
+			fallthrough;
 		case -ENOKEY: /* negative key */
 			ret = key_ref;
 			break;
@@ -509,7 +509,7 @@ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx)
 		case -EAGAIN: /* no key */
 			if (ret)
 				break;
-			/* fall through */
+			fallthrough;
 		case -ENOKEY: /* negative key */
 			ret = key_ref;
 			break;
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index e1b9f1a80676..2da4404276f0 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -295,26 +295,26 @@ static int construct_get_dest_keyring(struct key **_dest_keyring)
 				}
 			}
 
-			/* fall through */
+			fallthrough;
 		case KEY_REQKEY_DEFL_THREAD_KEYRING:
 			dest_keyring = key_get(cred->thread_keyring);
 			if (dest_keyring)
 				break;
 
-			/* fall through */
+			fallthrough;
 		case KEY_REQKEY_DEFL_PROCESS_KEYRING:
 			dest_keyring = key_get(cred->process_keyring);
 			if (dest_keyring)
 				break;
 
-			/* fall through */
+			fallthrough;
 		case KEY_REQKEY_DEFL_SESSION_KEYRING:
 			dest_keyring = key_get(cred->session_keyring);
 
 			if (dest_keyring)
 				break;
 
-			/* fall through */
+			fallthrough;
 		case KEY_REQKEY_DEFL_USER_SESSION_KEYRING:
 			ret = look_up_user_keyrings(NULL, &dest_keyring);
 			if (ret < 0)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index ca901025802a..a340986aa92e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3606,26 +3606,20 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case FIONREAD:
-	/* fall through */
 	case FIBMAP:
-	/* fall through */
 	case FIGETBSZ:
-	/* fall through */
 	case FS_IOC_GETFLAGS:
-	/* fall through */
 	case FS_IOC_GETVERSION:
 		error = file_has_perm(cred, file, FILE__GETATTR);
 		break;
 
 	case FS_IOC_SETFLAGS:
-	/* fall through */
 	case FS_IOC_SETVERSION:
 		error = file_has_perm(cred, file, FILE__SETATTR);
 		break;
 
 	/* sys_ioctl() checks */
 	case FIONBIO:
-	/* fall through */
 	case FIOASYNC:
 		error = file_has_perm(cred, file, 0);
 		break;
@@ -3783,7 +3777,7 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd,
 			err = file_has_perm(cred, file, FILE__WRITE);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case F_SETOWN:
 	case F_SETSIG:
 	case F_GETFL:
diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c
index 408d306895f8..d338962fb0c4 100644
--- a/security/selinux/ss/mls.c
+++ b/security/selinux/ss/mls.c
@@ -535,7 +535,7 @@ int mls_compute_sid(struct policydb *p,
 						  scontext, tcontext);
 		}
 
-		/* Fallthrough */
+		fallthrough;
 	case AVTAB_CHANGE:
 		if ((tclass == p->process_class) || sock)
 			/* Use the process MLS attributes. */
@@ -546,8 +546,6 @@ int mls_compute_sid(struct policydb *p,
 	case AVTAB_MEMBER:
 		/* Use the process effective MLS attributes. */
 		return mls_context_cpy_low(newcontext, scontext);
-
-	/* fall through */
 	}
 	return -EINVAL;
 }
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 8ffbf951b7ed..8c0893eb5aa8 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3365,7 +3365,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 * to set mount options simulate setting the
 		 * superblock default.
 		 */
-		/* Fall through */
+		fallthrough;
 	default:
 		/*
 		 * This isn't an understood special case.
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index c16b8c1b03e7..4bee32bfe16d 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -1240,7 +1240,7 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head,
 			tomoyo_set_space(head);
 			tomoyo_set_string(head, cond->transit->name);
 		}
-		/* fall through */
+		fallthrough;
 	case 1:
 		{
 			const u16 condc = cond->condc;
@@ -1345,12 +1345,12 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head,
 			}
 		}
 		head->r.cond_step++;
-		/* fall through */
+		fallthrough;
 	case 2:
 		if (!tomoyo_flush(head))
 			break;
 		head->r.cond_step++;
-		/* fall through */
+		fallthrough;
 	case 3:
 		if (cond->grant_log != TOMOYO_GRANTLOG_AUTO)
 			tomoyo_io_printf(head, " grant_log=%s",
@@ -1639,7 +1639,7 @@ static void tomoyo_read_domain(struct tomoyo_io_buffer *head)
 					tomoyo_set_string(head, tomoyo_dif[i]);
 			head->r.index = 0;
 			head->r.step++;
-			/* fall through */
+			fallthrough;
 		case 1:
 			while (head->r.index < TOMOYO_MAX_ACL_GROUPS) {
 				i = head->r.index++;
@@ -1652,14 +1652,14 @@ static void tomoyo_read_domain(struct tomoyo_io_buffer *head)
 			head->r.index = 0;
 			head->r.step++;
 			tomoyo_set_lf(head);
-			/* fall through */
+			fallthrough;
 		case 2:
 			if (!tomoyo_read_domain2(head, &domain->acl_info_list))
 				return;
 			head->r.step++;
 			if (!tomoyo_set_lf(head))
 				return;
-			/* fall through */
+			fallthrough;
 		case 3:
 			head->r.step = 0;
 			if (head->r.print_this_domain_only)
@@ -2088,7 +2088,7 @@ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...)
 		/* Check max_learning_entry parameter. */
 		if (tomoyo_domain_quota_is_ok(r))
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -2710,13 +2710,13 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
 		case TOMOYO_DOMAINPOLICY:
 			if (tomoyo_select_domain(head, cp0))
 				continue;
-			/* fall through */
+			fallthrough;
 		case TOMOYO_EXCEPTIONPOLICY:
 			if (!strcmp(cp0, "select transition_only")) {
 				head->r.print_transition_related_only = true;
 				continue;
 			}
-			/* fall through */
+			fallthrough;
 		default:
 			if (!tomoyo_manager()) {
 				error = -EPERM;
diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c
index 86f7d1b90212..051f7297877c 100644
--- a/security/tomoyo/file.c
+++ b/security/tomoyo/file.c
@@ -927,7 +927,7 @@ int tomoyo_path2_perm(const u8 operation, const struct path *path1,
 	case TOMOYO_TYPE_LINK:
 		if (!d_is_dir(path1->dentry))
 			break;
-		/* fall through */
+		fallthrough;
 	case TOMOYO_TYPE_PIVOT_ROOT:
 		tomoyo_add_slash(&buf1);
 		tomoyo_add_slash(&buf2);
diff --git a/sound/core/oss/mulaw.c b/sound/core/oss/mulaw.c
index 3788906421a7..fe27034f2846 100644
--- a/sound/core/oss/mulaw.c
+++ b/sound/core/oss/mulaw.c
@@ -329,8 +329,8 @@ int snd_pcm_plugin_build_mulaw(struct snd_pcm_substream *plug,
 		snd_BUG();
 		return -EINVAL;
 	}
-	if (snd_BUG_ON(!snd_pcm_format_linear(format->format)))
-		return -ENXIO;
+	if (!snd_pcm_format_linear(format->format))
+		return -EINVAL;
 
 	err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion",
 				   src_format, dst_format,
diff --git a/sound/core/timer.c b/sound/core/timer.c
index d9f85f2d66a3..6e27d87b18ed 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -816,9 +816,9 @@ static void snd_timer_clear_callbacks(struct snd_timer *timer,
  * timer tasklet
  *
  */
-static void snd_timer_tasklet(unsigned long arg)
+static void snd_timer_tasklet(struct tasklet_struct *t)
 {
-	struct snd_timer *timer = (struct snd_timer *) arg;
+	struct snd_timer *timer = from_tasklet(timer, t, task_queue);
 	unsigned long flags;
 
 	if (timer->card && timer->card->shutdown) {
@@ -967,8 +967,7 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 	INIT_LIST_HEAD(&timer->ack_list_head);
 	INIT_LIST_HEAD(&timer->sack_list_head);
 	spin_lock_init(&timer->lock);
-	tasklet_init(&timer->task_queue, snd_timer_tasklet,
-		     (unsigned long)timer);
+	tasklet_setup(&timer->task_queue, snd_timer_tasklet);
 	timer->max_instances = 1000; /* default limit per timer */
 	if (card != NULL) {
 		timer->module = card->module;
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index f8586f75441d..ee1c428b1fd3 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -64,7 +64,7 @@
 #define IT_PKT_HEADER_SIZE_CIP		8 // For 2 CIP header.
 #define IT_PKT_HEADER_SIZE_NO_CIP	0 // Nothing.
 
-static void pcm_period_tasklet(unsigned long data);
+static void pcm_period_tasklet(struct tasklet_struct *t);
 
 /**
  * amdtp_stream_init - initialize an AMDTP stream structure
@@ -94,7 +94,7 @@ int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
 	s->flags = flags;
 	s->context = ERR_PTR(-1);
 	mutex_init(&s->mutex);
-	tasklet_init(&s->period_tasklet, pcm_period_tasklet, (unsigned long)s);
+	tasklet_setup(&s->period_tasklet, pcm_period_tasklet);
 	s->packet_index = 0;
 
 	init_waitqueue_head(&s->callback_wait);
@@ -441,9 +441,9 @@ static void update_pcm_pointers(struct amdtp_stream *s,
 	}
 }
 
-static void pcm_period_tasklet(unsigned long data)
+static void pcm_period_tasklet(struct tasklet_struct *t)
 {
-	struct amdtp_stream *s = (void *)data;
+	struct amdtp_stream *s = from_tasklet(s, t, period_tasklet);
 	struct snd_pcm_substream *pcm = READ_ONCE(s->pcm);
 
 	if (pcm)
diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c
index c84b913a9fe0..ab8408966ec3 100644
--- a/sound/firewire/digi00x/digi00x.c
+++ b/sound/firewire/digi00x/digi00x.c
@@ -14,6 +14,7 @@ MODULE_LICENSE("GPL v2");
 #define VENDOR_DIGIDESIGN	0x00a07e
 #define MODEL_CONSOLE		0x000001
 #define MODEL_RACK		0x000002
+#define SPEC_VERSION		0x000001
 
 static int name_card(struct snd_dg00x *dg00x)
 {
@@ -175,14 +176,18 @@ static const struct ieee1394_device_id snd_dg00x_id_table[] = {
 	/* Both of 002/003 use the same ID. */
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_CONSOLE,
 	},
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_RACK,
 	},
 	{}
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index 5dac0d9fc58e..75f2edd8e78f 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -39,9 +39,6 @@ static const struct snd_tscm_spec model_specs[] = {
 		.midi_capture_ports = 2,
 		.midi_playback_ports = 4,
 	},
-	// This kernel module doesn't support FE-8 because the most of features
-	// can be implemented in userspace without any specific support of this
-	// module.
 };
 
 static int identify_model(struct snd_tscm *tscm)
@@ -211,11 +208,39 @@ static void snd_tscm_remove(struct fw_unit *unit)
 }
 
 static const struct ieee1394_device_id snd_tscm_id_table[] = {
+	// Tascam, FW-1884.
+	{
+		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
+		.vendor_id = 0x00022e,
+		.specifier_id = 0x00022e,
+		.version = 0x800000,
+	},
+	// Tascam, FE-8 (.version = 0x800001)
+	// This kernel module doesn't support FE-8 because the most of features
+	// can be implemented in userspace without any specific support of this
+	// module.
+	//
+	// .version = 0x800002 is unknown.
+	//
+	// Tascam, FW-1082.
+	{
+		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
+		.vendor_id = 0x00022e,
+		.specifier_id = 0x00022e,
+		.version = 0x800003,
+	},
+	// Tascam, FW-1804.
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
-			       IEEE1394_MATCH_SPECIFIER_ID,
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
 		.vendor_id = 0x00022e,
 		.specifier_id = 0x00022e,
+		.version = 0x800004,
 	},
 	{}
 };
diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c
index 09ddab5f5cae..9766f6af8743 100644
--- a/sound/hda/hdac_bus.c
+++ b/sound/hda/hdac_bus.c
@@ -46,6 +46,18 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev,
 	INIT_LIST_HEAD(&bus->hlink_list);
 	init_waitqueue_head(&bus->rirb_wq);
 	bus->irq = -1;
+
+	/*
+	 * Default value of '8' is as per the HD audio specification (Rev 1.0a).
+	 * Following relation is used to derive STRIPE control value.
+	 *  For sample rate <= 48K:
+	 *   { ((num_channels * bits_per_sample) / number of SDOs) >= 8 }
+	 *  For sample rate > 48K:
+	 *   { ((num_channels * bits_per_sample * rate/48000) /
+	 *	number of SDOs) >= 8 }
+	 */
+	bus->sdo_limit = 8;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_bus_init);
diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c
index 011b17cc1efa..b98449fd92f3 100644
--- a/sound/hda/hdac_controller.c
+++ b/sound/hda/hdac_controller.c
@@ -529,17 +529,6 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset)
 
 	bus->chip_init = true;
 
-	/*
-	 * Default value of '8' is as per the HD audio specification (Rev 1.0a).
-	 * Following relation is used to derive STRIPE control value.
-	 *  For sample rate <= 48K:
-	 *   { ((num_channels * bits_per_sample) / number of SDOs) >= 8 }
-	 *  For sample rate > 48K:
-	 *   { ((num_channels * bits_per_sample * rate/48000) /
-	 *	number of SDOs) >= 8 }
-	 */
-	bus->sdo_limit = 8;
-
 	return true;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_bus_init_chip);
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 333220f0f8af..3e9e9ac804f6 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -127,6 +127,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_device_init);
 void snd_hdac_device_exit(struct hdac_device *codec)
 {
 	pm_runtime_put_noidle(&codec->dev);
+	/* keep balance of runtime PM child_count in parent device */
+	pm_runtime_set_suspended(&codec->dev);
 	snd_hdac_bus_remove_device(codec->bus, codec);
 	kfree(codec->vendor_name);
 	kfree(codec->chip_name);
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index 99aec7349167..1c5114dedda9 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -54,7 +54,7 @@ static const struct config_entry config_table[] = {
 #endif
 /*
  * Apollolake (Broxton-P)
- * the legacy HDaudio driver is used except on Up Squared (SOF) and
+ * the legacy HDAudio driver is used except on Up Squared (SOF) and
  * Chromebooks (SST)
  */
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
@@ -89,7 +89,7 @@ static const struct config_entry config_table[] = {
 	},
 #endif
 /*
- * Skylake and Kabylake use legacy HDaudio driver except for Google
+ * Skylake and Kabylake use legacy HDAudio driver except for Google
  * Chromebooks (SST)
  */
 
@@ -135,7 +135,7 @@ static const struct config_entry config_table[] = {
 #endif
 
 /*
- * Geminilake uses legacy HDaudio driver except for Google
+ * Geminilake uses legacy HDAudio driver except for Google
  * Chromebooks
  */
 /* Geminilake */
@@ -157,7 +157,7 @@ static const struct config_entry config_table[] = {
 
 /*
  * CoffeeLake, CannonLake, CometLake, IceLake, TigerLake use legacy
- * HDaudio driver except for Google Chromebooks and when DMICs are
+ * HDAudio driver except for Google Chromebooks and when DMICs are
  * present. Two cases are required since Coreboot does not expose NHLT
  * tables.
  *
@@ -391,7 +391,7 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci)
 	if (pci->class == 0x040300)
 		return SND_INTEL_DSP_DRIVER_LEGACY;
 	if (pci->class != 0x040100 && pci->class != 0x040380) {
-		dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, selecting HDA legacy driver\n", pci->class);
+		dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, selecting HDAudio legacy driver\n", pci->class);
 		return SND_INTEL_DSP_DRIVER_LEGACY;
 	}
 
diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c
index 5363d88cc4b9..2e5a5c5279e8 100644
--- a/sound/isa/sscape.c
+++ b/sound/isa/sscape.c
@@ -308,7 +308,7 @@ static inline int verify_mpu401(const struct snd_mpu401 *mpu)
 }
 
 /*
- * This is apparently the standard way to initailise an MPU-401
+ * This is apparently the standard way to initialise an MPU-401
  */
 static inline void initialise_mpu401(const struct snd_mpu401 *mpu)
 {
@@ -339,7 +339,7 @@ static void soundscape_free(struct snd_card *c)
 }
 
 /*
- * Tell the SoundScape to begin a DMA tranfer using the given channel.
+ * Tell the SoundScape to begin a DMA transfer using the given channel.
  * All locking issues are left to the caller.
  */
 static void sscape_start_dma_unsafe(unsigned io_base, enum GA_REG reg)
@@ -803,7 +803,7 @@ static int mpu401_open(struct snd_mpu401 *mpu)
 }
 
 /*
- * Initialse an MPU-401 subdevice for MIDI support on the SoundScape.
+ * Initialise an MPU-401 subdevice for MIDI support on the SoundScape.
  */
 static int create_mpu401(struct snd_card *card, int devnum,
 			 unsigned long port, int irq)
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 023c35a2a951..35e76480306e 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -921,10 +921,10 @@ static void snd_card_asihpi_timer_function(struct timer_list *t)
 		add_timer(&dpcm->timer);
 }
 
-static void snd_card_asihpi_int_task(unsigned long data)
+static void snd_card_asihpi_int_task(struct tasklet_struct *t)
 {
-	struct hpi_adapter *a = (struct hpi_adapter *)data;
-	struct snd_card_asihpi *asihpi;
+	struct snd_card_asihpi *asihpi = from_tasklet(asihpi, t, t);
+	struct hpi_adapter *a = asihpi->hpi;
 
 	WARN_ON(!a || !a->snd_card || !a->snd_card->private_data);
 	asihpi = (struct snd_card_asihpi *)a->snd_card->private_data;
@@ -2871,8 +2871,7 @@ static int snd_asihpi_probe(struct pci_dev *pci_dev,
 	if (hpi->interrupt_mode) {
 		asihpi->pcm_start = snd_card_asihpi_pcm_int_start;
 		asihpi->pcm_stop = snd_card_asihpi_pcm_int_stop;
-		tasklet_init(&asihpi->t, snd_card_asihpi_int_task,
-			(unsigned long)hpi);
+		tasklet_setup(&asihpi->t, snd_card_asihpi_int_task);
 		hpi->interrupt_callback = snd_card_asihpi_isr;
 	} else {
 		asihpi->pcm_start = snd_card_asihpi_pcm_timer_start;
diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c
index 70d775ff967e..c189f70c82cb 100644
--- a/sound/pci/ca0106/ca0106_main.c
+++ b/sound/pci/ca0106/ca0106_main.c
@@ -537,7 +537,8 @@ static int snd_ca0106_pcm_power_dac(struct snd_ca0106 *chip, int channel_id,
 		else
 			/* Power down */
 			chip->spi_dac_reg[reg] |= bit;
-		return snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]);
+		if (snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]) != 0)
+			return -ENXIO;
 	}
 	return 0;
 }
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e34a4d5d047c..36a9dbc33aa0 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2127,9 +2127,10 @@ static int azx_probe(struct pci_dev *pci,
 	 */
 	if (dmic_detect) {
 		err = snd_intel_dsp_driver_probe(pci);
-		if (err != SND_INTEL_DSP_DRIVER_ANY &&
-		    err != SND_INTEL_DSP_DRIVER_LEGACY)
+		if (err != SND_INTEL_DSP_DRIVER_ANY && err != SND_INTEL_DSP_DRIVER_LEGACY) {
+			dev_dbg(&pci->dev, "HDAudio driver not selected, aborting probe\n");
 			return -ENODEV;
+		}
 	} else {
 		dev_warn(&pci->dev, "dmic_detect option is deprecated, pass snd-intel-dspcfg.dsp_driver=1 option instead\n");
 	}
@@ -2745,8 +2746,6 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI },
 	/* Zhaoxin */
 	{ PCI_DEVICE(0x1d17, 0x3288), .driver_data = AZX_DRIVER_ZHAOXIN },
-	/* Loongson */
-	{ PCI_DEVICE(0x0014, 0x7a07), .driver_data = AZX_DRIVER_GENERIC },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, azx_ids);
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index c94553bcca88..70164d1428d4 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -179,6 +179,10 @@ static int __maybe_unused hda_tegra_runtime_suspend(struct device *dev)
 	struct hda_tegra *hda = container_of(chip, struct hda_tegra, chip);
 
 	if (chip && chip->running) {
+		/* enable controller wake up event */
+		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
+			   STATESTS_INT_MASK);
+
 		azx_stop_chip(chip);
 		azx_enter_link_reset(chip);
 	}
@@ -200,6 +204,9 @@ static int __maybe_unused hda_tegra_runtime_resume(struct device *dev)
 	if (chip && chip->running) {
 		hda_tegra_init(hda);
 		azx_init_chip(chip, 1);
+		/* disable controller wake up event*/
+		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
+			   ~STATESTS_INT_MASK);
 	}
 
 	return 0;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index b8c8490e568b..402050088090 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2794,6 +2794,7 @@ static void i915_pin_cvt_fixup(struct hda_codec *codec,
 			       hda_nid_t cvt_nid)
 {
 	if (per_pin) {
+		haswell_verify_D0(codec, per_pin->cvt_nid, per_pin->pin_nid);
 		snd_hda_set_dev_select(codec, per_pin->pin_nid,
 			       per_pin->dev_id);
 		intel_verify_pin_cvt_connect(codec, per_pin);
@@ -3734,6 +3735,7 @@ static int tegra_hdmi_build_pcms(struct hda_codec *codec)
 
 static int patch_tegra_hdmi(struct hda_codec *codec)
 {
+	struct hdmi_spec *spec;
 	int err;
 
 	err = patch_generic_hdmi(codec);
@@ -3741,6 +3743,10 @@ static int patch_tegra_hdmi(struct hda_codec *codec)
 		return err;
 
 	codec->patch_ops.build_pcms = tegra_hdmi_build_pcms;
+	spec = codec->spec;
+	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
+		nvhdmi_chmap_cea_alloc_validate_get_type;
+	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
 
 	return 0;
 }
@@ -4263,6 +4269,7 @@ HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI",	patch_i915_tgl_hdmi),
+HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI",	patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7f9d35273734..c521a1f17096 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2475,6 +2475,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
+	SND_PCI_QUIRK(0x1462, 0x9c37, "MSI X570-A PRO", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
@@ -5867,6 +5868,39 @@ static void alc275_fixup_gpio4_off(struct hda_codec *codec,
 	}
 }
 
+/* Quirk for Thinkpad X1 7th and 8th Gen
+ * The following fixed routing needed
+ * DAC1 (NID 0x02) -> Speaker (NID 0x14); some eq applied secretly
+ * DAC2 (NID 0x03) -> Bass (NID 0x17) & Headphone (NID 0x21); sharing a DAC
+ * DAC3 (NID 0x06) -> Unused, due to the lack of volume amp
+ */
+static void alc285_fixup_thinkpad_x1_gen7(struct hda_codec *codec,
+					  const struct hda_fixup *fix, int action)
+{
+	static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x14, 0x02, 0x17, 0x03, 0x21, 0x03, 0
+	};
+	struct alc_spec *spec = codec->spec;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+		spec->gen.preferred_dacs = preferred_pairs;
+		break;
+	case HDA_FIXUP_ACT_BUILD:
+		/* The generic parser creates somewhat unintuitive volume ctls
+		 * with the fixed routing above, and the shared DAC2 may be
+		 * confusing for PA.
+		 * Rename those to unique names so that PA doesn't touch them
+		 * and use only Master volume.
+		 */
+		rename_ctl(codec, "Front Playback Volume", "DAC1 Playback Volume");
+		rename_ctl(codec, "Bass Speaker Playback Volume", "DAC2 Playback Volume");
+		break;
+	}
+}
+
 static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec,
 					 const struct hda_fixup *fix,
 					 int action)
@@ -6135,6 +6169,7 @@ enum {
 	ALC289_FIXUP_DUAL_SPK,
 	ALC294_FIXUP_SPK2_TO_DAC1,
 	ALC294_FIXUP_ASUS_DUAL_SPK,
+	ALC285_FIXUP_THINKPAD_X1_GEN7,
 	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	ALC294_FIXUP_ASUS_HPE,
 	ALC294_FIXUP_ASUS_COEF_1B,
@@ -7280,11 +7315,17 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC294_FIXUP_SPK2_TO_DAC1
 	},
+	[ALC285_FIXUP_THINKPAD_X1_GEN7] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_thinkpad_x1_gen7,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_THINKPAD_ACPI
+	},
 	[ALC285_FIXUP_THINKPAD_HEADSET_JACK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_jack,
 		.chained = true,
-		.chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1
+		.chain_id = ALC285_FIXUP_THINKPAD_X1_GEN7
 	},
 	[ALC294_FIXUP_ASUS_HPE] = {
 		.type = HDA_FIXUP_VERBS,
@@ -7694,6 +7735,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
 	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
@@ -7955,6 +7999,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"},
 	{.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"},
 	{.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"},
+	{.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index b4f300281822..098c69b3b7aa 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -1070,9 +1070,9 @@ getmixer(struct cmdif *cif, short num, unsigned short *rval,
 	return 0;
 }
 
-static void riptide_handleirq(unsigned long dev_id)
+static void riptide_handleirq(struct tasklet_struct *t)
 {
-	struct snd_riptide *chip = (void *)dev_id;
+	struct snd_riptide *chip = from_tasklet(chip, t, riptide_tq);
 	struct cmdif *cif = chip->cif;
 	struct snd_pcm_substream *substream[PLAYBACK_SUBSTREAMS + 1];
 	struct snd_pcm_runtime *runtime;
@@ -1843,7 +1843,7 @@ snd_riptide_create(struct snd_card *card, struct pci_dev *pci,
 	chip->received_irqs = 0;
 	chip->handled_irqs = 0;
 	chip->cif = NULL;
-	tasklet_init(&chip->riptide_tq, riptide_handleirq, (unsigned long)chip);
+	tasklet_setup(&chip->riptide_tq, riptide_handleirq);
 
 	if ((chip->res_port =
 	     request_region(chip->port, 64, "RIPTIDE")) == NULL) {
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 227aece17e39..dda56ecfd33b 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -3791,9 +3791,9 @@ static int snd_hdsp_set_defaults(struct hdsp *hdsp)
 	return 0;
 }
 
-static void hdsp_midi_tasklet(unsigned long arg)
+static void hdsp_midi_tasklet(struct tasklet_struct *t)
 {
-	struct hdsp *hdsp = (struct hdsp *)arg;
+	struct hdsp *hdsp = from_tasklet(hdsp, t, midi_tasklet);
 
 	if (hdsp->midi[0].pending)
 		snd_hdsp_midi_input_read (&hdsp->midi[0]);
@@ -5182,7 +5182,7 @@ static int snd_hdsp_create(struct snd_card *card,
 
 	spin_lock_init(&hdsp->lock);
 
-	tasklet_init(&hdsp->midi_tasklet, hdsp_midi_tasklet, (unsigned long)hdsp);
+	tasklet_setup(&hdsp->midi_tasklet, hdsp_midi_tasklet);
 
 	pci_read_config_word(hdsp->pci, PCI_CLASS_REVISION, &hdsp->firmware_rev);
 	hdsp->firmware_rev &= 0xff;
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 0fa49f4d15cf..572350aaf18d 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -2169,9 +2169,9 @@ static int snd_hdspm_create_midi(struct snd_card *card,
 }
 
 
-static void hdspm_midi_tasklet(unsigned long arg)
+static void hdspm_midi_tasklet(struct tasklet_struct *t)
 {
-	struct hdspm *hdspm = (struct hdspm *)arg;
+	struct hdspm *hdspm = from_tasklet(hdspm, t, midi_tasklet);
 	int i = 0;
 
 	while (i < hdspm->midiPorts) {
@@ -6836,8 +6836,7 @@ static int snd_hdspm_create(struct snd_card *card,
 
 	}
 
-	tasklet_init(&hdspm->midi_tasklet,
-			hdspm_midi_tasklet, (unsigned long) hdspm);
+	tasklet_setup(&hdspm->midi_tasklet, hdspm_midi_tasklet);
 
 
 	if (hdspm->io_type != MADIface) {
diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
index b8161a08f2ca..58bb49fff184 100644
--- a/sound/ppc/snd_ps3.c
+++ b/sound/ppc/snd_ps3.c
@@ -227,14 +227,14 @@ static int snd_ps3_program_dma(struct snd_ps3_card_info *card,
 	switch (filltype) {
 	case SND_PS3_DMA_FILLTYPE_SILENT_FIRSTFILL:
 		silent = 1;
-		/* intentionally fall thru */
+		fallthrough;
 	case SND_PS3_DMA_FILLTYPE_FIRSTFILL:
 		ch0_kick_event = PS3_AUDIO_KICK_EVENT_ALWAYS;
 		break;
 
 	case SND_PS3_DMA_FILLTYPE_SILENT_RUNNING:
 		silent = 1;
-		/* intentionally fall thru */
+		fallthrough;
 	case SND_PS3_DMA_FILLTYPE_RUNNING:
 		ch0_kick_event = PS3_AUDIO_KICK_EVENT_SERIALOUT0_EMPTY;
 		break;
diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c
index 55815fdaa1aa..406526e79af3 100644
--- a/sound/soc/amd/acp3x-rt5682-max9836.c
+++ b/sound/soc/amd/acp3x-rt5682-max9836.c
@@ -138,7 +138,7 @@ static int acp3x_1015_hw_params(struct snd_pcm_substream *substream,
 	srate = params_rate(params);
 
 	for_each_rtd_codec_dais(rtd, i, codec_dai) {
-		if (strcmp(codec_dai->component->name, "rt1015-aif"))
+		if (strcmp(codec_dai->name, "rt1015-aif"))
 			continue;
 		ret = snd_soc_dai_set_bclk_ratio(codec_dai, 64);
 		if (ret < 0)
diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c
index 623dfd3ea705..7b14d9a81b97 100644
--- a/sound/soc/amd/renoir/acp3x-pdm-dma.c
+++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c
@@ -314,40 +314,30 @@ static int acp_pdm_dma_close(struct snd_soc_component *component,
 	return 0;
 }
 
-static int acp_pdm_dai_hw_params(struct snd_pcm_substream *substream,
-				 struct snd_pcm_hw_params *params,
-				 struct snd_soc_dai *dai)
+static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream,
+			       int cmd, struct snd_soc_dai *dai)
 {
 	struct pdm_stream_instance *rtd;
+	int ret;
+	bool pdm_status;
 	unsigned int ch_mask;
 
 	rtd = substream->runtime->private_data;
-	switch (params_channels(params)) {
+	ret = 0;
+	switch (substream->runtime->channels) {
 	case TWO_CH:
 		ch_mask = 0x00;
 		break;
 	default:
 		return -EINVAL;
 	}
-	rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS);
-	rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base +
-		  ACP_WOV_PDM_DECIMATION_FACTOR);
-	return 0;
-}
-
-static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream,
-			       int cmd, struct snd_soc_dai *dai)
-{
-	struct pdm_stream_instance *rtd;
-	int ret;
-	bool pdm_status;
-
-	rtd = substream->runtime->private_data;
-	ret = 0;
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS);
+		rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base +
+			  ACP_WOV_PDM_DECIMATION_FACTOR);
 		rtd->bytescount = acp_pdm_get_byte_count(rtd,
 							 substream->stream);
 		pdm_status = check_pdm_dma_status(rtd->acp_base);
@@ -369,7 +359,6 @@ static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream,
 }
 
 static struct snd_soc_dai_ops acp_pdm_dai_ops = {
-	.hw_params = acp_pdm_dai_hw_params,
 	.trigger   = acp_pdm_dai_trigger,
 };
 
diff --git a/sound/soc/atmel/mchp-i2s-mcc.c b/sound/soc/atmel/mchp-i2s-mcc.c
index 3cb63886195f..04acc18f2d72 100644
--- a/sound/soc/atmel/mchp-i2s-mcc.c
+++ b/sound/soc/atmel/mchp-i2s-mcc.c
@@ -536,7 +536,7 @@ static int mchp_i2s_mcc_hw_params(struct snd_pcm_substream *substream,
 		/* cpu is BCLK master */
 		mrb |= MCHP_I2SMCC_MRB_CLKSEL_INT;
 		set_divs = 1;
-		/* fall through */
+		fallthrough;
 	case SND_SOC_DAIFMT_CBM_CFM:
 		/* cpu is slave */
 		mra |= MCHP_I2SMCC_MRA_MODE_SLAVE;
diff --git a/sound/soc/codecs/jz4770.c b/sound/soc/codecs/jz4770.c
index c0a28f06b09a..298689a07168 100644
--- a/sound/soc/codecs/jz4770.c
+++ b/sound/soc/codecs/jz4770.c
@@ -202,7 +202,7 @@ static int jz4770_codec_set_bias_level(struct snd_soc_component *codec,
 				   REG_CR_VIC_SB_SLEEP, REG_CR_VIC_SB_SLEEP);
 		regmap_update_bits(regmap, JZ4770_CODEC_REG_CR_VIC,
 				   REG_CR_VIC_SB, REG_CR_VIC_SB);
-	/* fall-through */
+		fallthrough;
 	default:
 		break;
 	}
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 4428c62e25cf..3ddd822240e3 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -19,8 +19,8 @@
 
 #define CDC_D_REVISION1			(0xf000)
 #define CDC_D_PERPH_SUBTYPE		(0xf005)
-#define CDC_D_INT_EN_SET		(0x015)
-#define CDC_D_INT_EN_CLR		(0x016)
+#define CDC_D_INT_EN_SET		(0xf015)
+#define CDC_D_INT_EN_CLR		(0xf016)
 #define MBHC_SWITCH_INT			BIT(7)
 #define MBHC_MIC_ELECTRICAL_INS_REM_DET	BIT(6)
 #define MBHC_BUTTON_PRESS_DET		BIT(5)
diff --git a/sound/soc/codecs/pcm186x.c b/sound/soc/codecs/pcm186x.c
index f0da55901dcb..b8845f45549e 100644
--- a/sound/soc/codecs/pcm186x.c
+++ b/sound/soc/codecs/pcm186x.c
@@ -401,7 +401,7 @@ static int pcm186x_set_fmt(struct snd_soc_dai *dai, unsigned int format)
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
 		priv->tdm_offset += 1;
-		/* fall through */
+		fallthrough;
 		/* DSP_A uses the same basic config as DSP_B
 		 * except we need to shift the TDM output by one BCK cycle
 		 */
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index 68a3b48e6b31..3bce9a14f0f3 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -412,8 +412,12 @@ int wm8958_aif_ev(struct snd_soc_dapm_widget *w,
 		  struct snd_kcontrol *kcontrol, int event)
 {
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct wm8994 *control = dev_get_drvdata(component->dev->parent);
 	int i;
 
+	if (control->type != WM8958)
+		return 0;
+
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
 	case SND_SOC_DAPM_PRE_PMU:
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 317916cb4e27..0623a2251084 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -151,7 +151,6 @@ static const struct reg_default wm8962_reg[] = {
 	{ 40, 0x0000 },   /* R40    - SPKOUTL volume */
 	{ 41, 0x0000 },   /* R41    - SPKOUTR volume */
 
-	{ 48, 0x0000 },   /* R48    - Additional control(4) */
 	{ 49, 0x0010 },   /* R49    - Class D Control 1 */
 	{ 51, 0x0003 },   /* R51    - Class D Control 2 */
 
@@ -842,6 +841,7 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg)
 	case WM8962_SPKOUTL_VOLUME:
 	case WM8962_SPKOUTR_VOLUME:
 	case WM8962_THERMAL_SHUTDOWN_STATUS:
+	case WM8962_ADDITIONAL_CONTROL_4:
 	case WM8962_CLASS_D_CONTROL_1:
 	case WM8962_CLASS_D_CONTROL_2:
 	case WM8962_CLOCKING_4:
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index a84ae879d37e..038be667c1a6 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -43,10 +43,12 @@
 #define WM8994_NUM_DRC 3
 #define WM8994_NUM_EQ  3
 
-static struct {
+struct wm8994_reg_mask {
 	unsigned int reg;
 	unsigned int mask;
-} wm8994_vu_bits[] = {
+};
+
+static struct wm8994_reg_mask wm8994_vu_bits[] = {
 	{ WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
 	{ WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
 	{ WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU },
@@ -60,14 +62,10 @@ static struct {
 
 	{ WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU },
 	{ WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU },
-	{ WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU },
-	{ WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU },
 	{ WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU },
 	{ WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU },
 	{ WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU },
 	{ WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU },
-	{ WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU },
-	{ WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
 	{ WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU },
 	{ WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
 	{ WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU },
@@ -76,6 +74,14 @@ static struct {
 	{ WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU },
 };
 
+/* VU bitfields for ADC2, DAC2 not available on WM1811 */
+static struct wm8994_reg_mask wm8994_adc2_dac2_vu_bits[] = {
+	{ WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU },
+	{ WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU },
+	{ WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU },
+	{ WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
+};
+
 static int wm8994_drc_base[] = {
 	WM8994_AIF1_DRC1_1,
 	WM8994_AIF1_DRC2_1,
@@ -1030,6 +1036,26 @@ static bool wm8994_check_class_w_digital(struct snd_soc_component *component)
 	return true;
 }
 
+static void wm8994_update_vu_bits(struct snd_soc_component *component)
+{
+	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
+	struct wm8994 *control = wm8994->wm8994;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+		snd_soc_component_write(component, wm8994_vu_bits[i].reg,
+					snd_soc_component_read(component,
+						       wm8994_vu_bits[i].reg));
+	if (control->type == WM1811)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++)
+		snd_soc_component_write(component,
+				wm8994_adc2_dac2_vu_bits[i].reg,
+				snd_soc_component_read(component,
+					wm8994_adc2_dac2_vu_bits[i].reg));
+}
+
 static int aif_mclk_set(struct snd_soc_component *component, int aif, bool enable)
 {
 	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
@@ -1076,7 +1102,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
 	struct wm8994 *control = wm8994->wm8994;
 	int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA;
-	int ret, i;
+	int ret;
 	int dac;
 	int adc;
 	int val;
@@ -1144,10 +1170,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 		break;
 
 	case SND_SOC_DAPM_POST_PMU:
-		for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
-			snd_soc_component_write(component, wm8994_vu_bits[i].reg,
-				      snd_soc_component_read(component,
-						   wm8994_vu_bits[i].reg));
+		wm8994_update_vu_bits(component);
 		break;
 
 	case SND_SOC_DAPM_PRE_PMD:
@@ -1181,7 +1204,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w,
 		      struct snd_kcontrol *kcontrol, int event)
 {
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	int ret, i;
+	int ret;
 	int dac;
 	int adc;
 	int val;
@@ -1237,10 +1260,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w,
 		break;
 
 	case SND_SOC_DAPM_POST_PMU:
-		for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
-			snd_soc_component_write(component, wm8994_vu_bits[i].reg,
-				      snd_soc_component_read(component,
-						   wm8994_vu_bits[i].reg));
+		wm8994_update_vu_bits(component);
 		break;
 
 	case SND_SOC_DAPM_PRE_PMD:
@@ -4346,6 +4366,14 @@ static int wm8994_component_probe(struct snd_soc_component *component)
 				    wm8994_vu_bits[i].mask,
 				    wm8994_vu_bits[i].mask);
 
+	if (control->type != WM1811) {
+		for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++)
+			snd_soc_component_update_bits(component,
+					wm8994_adc2_dac2_vu_bits[i].reg,
+					wm8994_adc2_dac2_vu_bits[i].mask,
+					wm8994_adc2_dac2_vu_bits[i].mask);
+	}
+
 	/* Set the low bit of the 3D stereo depth so TLV matches */
 	snd_soc_component_update_bits(component, WM8994_AIF1_DAC1_FILTERS_2,
 			    1 << WM8994_AIF1DAC1_3D_GAIN_SHIFT,
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index de136c0a497d..52adedc03245 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -73,6 +73,7 @@ struct cpu_priv {
  * @codec_priv: CODEC private data
  * @cpu_priv: CPU private data
  * @card: ASoC card structure
+ * @streams: Mask of current active streams
  * @sample_rate: Current sample rate
  * @sample_format: Current sample format
  * @asrc_rate: ASRC sample rate used by Back-Ends
@@ -89,6 +90,7 @@ struct fsl_asoc_card_priv {
 	struct codec_priv codec_priv;
 	struct cpu_priv cpu_priv;
 	struct snd_soc_card card;
+	u8 streams;
 	u32 sample_rate;
 	snd_pcm_format_t sample_format;
 	u32 asrc_rate;
@@ -151,21 +153,17 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
 	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card);
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
+	struct codec_priv *codec_priv = &priv->codec_priv;
 	struct cpu_priv *cpu_priv = &priv->cpu_priv;
 	struct device *dev = rtd->card->dev;
+	unsigned int pll_out;
 	int ret;
 
 	priv->sample_rate = params_rate(params);
 	priv->sample_format = params_format(params);
+	priv->streams |= BIT(substream->stream);
 
-	/*
-	 * If codec-dai is DAI Master and all configurations are already in the
-	 * set_bias_level(), bypass the remaining settings in hw_params().
-	 * Note: (dai_fmt & CBM_CFM) includes CBM_CFM and CBM_CFS.
-	 */
-	if ((priv->card.set_bias_level &&
-	     priv->dai_fmt & SND_SOC_DAIFMT_CBM_CFM) ||
-	    fsl_asoc_card_is_ac97(priv))
+	if (fsl_asoc_card_is_ac97(priv))
 		return 0;
 
 	/* Specific configurations of DAIs starts from here */
@@ -174,7 +172,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream,
 				     cpu_priv->sysclk_dir[tx]);
 	if (ret && ret != -ENOTSUPP) {
 		dev_err(dev, "failed to set sysclk for cpu dai\n");
-		return ret;
+		goto fail;
 	}
 
 	if (cpu_priv->slot_width) {
@@ -182,6 +180,68 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream,
 					       cpu_priv->slot_width);
 		if (ret && ret != -ENOTSUPP) {
 			dev_err(dev, "failed to set TDM slot for cpu dai\n");
+			goto fail;
+		}
+	}
+
+	/* Specific configuration for PLL */
+	if (codec_priv->pll_id && codec_priv->fll_id) {
+		if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE)
+			pll_out = priv->sample_rate * 384;
+		else
+			pll_out = priv->sample_rate * 256;
+
+		ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0),
+					  codec_priv->pll_id,
+					  codec_priv->mclk_id,
+					  codec_priv->mclk_freq, pll_out);
+		if (ret) {
+			dev_err(dev, "failed to start FLL: %d\n", ret);
+			goto fail;
+		}
+
+		ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0),
+					     codec_priv->fll_id,
+					     pll_out, SND_SOC_CLOCK_IN);
+
+		if (ret && ret != -ENOTSUPP) {
+			dev_err(dev, "failed to set SYSCLK: %d\n", ret);
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	priv->streams &= ~BIT(substream->stream);
+	return ret;
+}
+
+static int fsl_asoc_card_hw_free(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct codec_priv *codec_priv = &priv->codec_priv;
+	struct device *dev = rtd->card->dev;
+	int ret;
+
+	priv->streams &= ~BIT(substream->stream);
+
+	if (!priv->streams && codec_priv->pll_id && codec_priv->fll_id) {
+		/* Force freq to be 0 to avoid error message in codec */
+		ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0),
+					     codec_priv->mclk_id,
+					     0,
+					     SND_SOC_CLOCK_IN);
+		if (ret) {
+			dev_err(dev, "failed to switch away from FLL: %d\n", ret);
+			return ret;
+		}
+
+		ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0),
+					  codec_priv->pll_id, 0, 0, 0);
+		if (ret && ret != -ENOTSUPP) {
+			dev_err(dev, "failed to stop FLL: %d\n", ret);
 			return ret;
 		}
 	}
@@ -191,6 +251,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream,
 
 static const struct snd_soc_ops fsl_asoc_card_ops = {
 	.hw_params = fsl_asoc_card_hw_params,
+	.hw_free = fsl_asoc_card_hw_free,
 };
 
 static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
@@ -254,75 +315,6 @@ static struct snd_soc_dai_link fsl_asoc_card_dai[] = {
 	},
 };
 
-static int fsl_asoc_card_set_bias_level(struct snd_soc_card *card,
-					struct snd_soc_dapm_context *dapm,
-					enum snd_soc_bias_level level)
-{
-	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card);
-	struct snd_soc_pcm_runtime *rtd;
-	struct snd_soc_dai *codec_dai;
-	struct codec_priv *codec_priv = &priv->codec_priv;
-	struct device *dev = card->dev;
-	unsigned int pll_out;
-	int ret;
-
-	rtd = snd_soc_get_pcm_runtime(card, &card->dai_link[0]);
-	codec_dai = asoc_rtd_to_codec(rtd, 0);
-	if (dapm->dev != codec_dai->dev)
-		return 0;
-
-	switch (level) {
-	case SND_SOC_BIAS_PREPARE:
-		if (dapm->bias_level != SND_SOC_BIAS_STANDBY)
-			break;
-
-		if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE)
-			pll_out = priv->sample_rate * 384;
-		else
-			pll_out = priv->sample_rate * 256;
-
-		ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id,
-					  codec_priv->mclk_id,
-					  codec_priv->mclk_freq, pll_out);
-		if (ret) {
-			dev_err(dev, "failed to start FLL: %d\n", ret);
-			return ret;
-		}
-
-		ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->fll_id,
-					     pll_out, SND_SOC_CLOCK_IN);
-		if (ret && ret != -ENOTSUPP) {
-			dev_err(dev, "failed to set SYSCLK: %d\n", ret);
-			return ret;
-		}
-		break;
-
-	case SND_SOC_BIAS_STANDBY:
-		if (dapm->bias_level != SND_SOC_BIAS_PREPARE)
-			break;
-
-		ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id,
-					     codec_priv->mclk_freq,
-					     SND_SOC_CLOCK_IN);
-		if (ret && ret != -ENOTSUPP) {
-			dev_err(dev, "failed to switch away from FLL: %d\n", ret);
-			return ret;
-		}
-
-		ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, 0, 0, 0);
-		if (ret) {
-			dev_err(dev, "failed to stop FLL: %d\n", ret);
-			return ret;
-		}
-		break;
-
-	default:
-		break;
-	}
-
-	return 0;
-}
-
 static int fsl_asoc_card_audmux_init(struct device_node *np,
 				     struct fsl_asoc_card_priv *priv)
 {
@@ -611,7 +603,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 	/* Diversify the card configurations */
 	if (of_device_is_compatible(np, "fsl,imx-audio-cs42888")) {
 		codec_dai_name = "cs42888";
-		priv->card.set_bias_level = NULL;
 		priv->cpu_priv.sysclk_freq[TX] = priv->codec_priv.mclk_freq;
 		priv->cpu_priv.sysclk_freq[RX] = priv->codec_priv.mclk_freq;
 		priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT;
@@ -628,26 +619,22 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
 	} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) {
 		codec_dai_name = "wm8962";
-		priv->card.set_bias_level = fsl_asoc_card_set_bias_level;
 		priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK;
 		priv->codec_priv.fll_id = WM8962_SYSCLK_FLL;
 		priv->codec_priv.pll_id = WM8962_FLL;
 		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
 	} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) {
 		codec_dai_name = "wm8960-hifi";
-		priv->card.set_bias_level = fsl_asoc_card_set_bias_level;
 		priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO;
 		priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO;
 		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
 	} else if (of_device_is_compatible(np, "fsl,imx-audio-ac97")) {
 		codec_dai_name = "ac97-hifi";
-		priv->card.set_bias_level = NULL;
 		priv->dai_fmt = SND_SOC_DAIFMT_AC97;
 		priv->card.dapm_routes = audio_map_ac97;
 		priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_ac97);
 	} else if (of_device_is_compatible(np, "fsl,imx-audio-mqs")) {
 		codec_dai_name = "fsl-mqs-dai";
-		priv->card.set_bias_level = NULL;
 		priv->dai_fmt = SND_SOC_DAIFMT_LEFT_J |
 				SND_SOC_DAIFMT_CBS_CFS |
 				SND_SOC_DAIFMT_NB_NF;
@@ -657,7 +644,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 		priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_tx);
 	} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8524")) {
 		codec_dai_name = "wm8524-hifi";
-		priv->card.set_bias_level = NULL;
 		priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
 		priv->dai_link[1].dpcm_capture = 0;
 		priv->dai_link[2].dpcm_capture = 0;
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 4ae36099ae82..79b861afd986 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -708,9 +708,9 @@ static void fsl_esai_trigger_stop(struct fsl_esai *esai_priv, bool tx)
 			   ESAI_xFCR_xFR, 0);
 }
 
-static void fsl_esai_hw_reset(unsigned long arg)
+static void fsl_esai_hw_reset(struct tasklet_struct *t)
 {
-	struct fsl_esai *esai_priv = (struct fsl_esai *)arg;
+	struct fsl_esai *esai_priv = from_tasklet(esai_priv, t, task);
 	bool tx = true, rx = false, enabled[2];
 	unsigned long lock_flags;
 	u32 tfcr, rfcr;
@@ -1070,8 +1070,7 @@ static int fsl_esai_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	tasklet_init(&esai_priv->task, fsl_esai_hw_reset,
-		     (unsigned long)esai_priv);
+	tasklet_setup(&esai_priv->task, fsl_esai_hw_reset);
 
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index d8b9c6547142..404be27c15fe 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -898,7 +898,7 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi, unsigned int fmt)
 					"missing baudclk for master mode\n");
 				return -EINVAL;
 			}
-			/* fall through */
+			fallthrough;
 		case SND_SOC_DAIFMT_CBM_CFS:
 			ssi->i2s_net |= SSI_SCR_I2S_MODE_MASTER;
 			break;
diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c
index 9e4f66b6b92b..231984882176 100644
--- a/sound/soc/fsl/mpc5200_dma.c
+++ b/sound/soc/fsl/mpc5200_dma.c
@@ -339,7 +339,6 @@ static int psc_dma_new(struct snd_soc_component *component,
 static void psc_dma_free(struct snd_soc_component *component,
 			 struct snd_pcm *pcm)
 {
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
 	struct snd_pcm_substream *substream;
 	int stream;
 
diff --git a/sound/soc/hisilicon/hi6210-i2s.c b/sound/soc/hisilicon/hi6210-i2s.c
index fd5dcd6b9f85..907f5f1f7b44 100644
--- a/sound/soc/hisilicon/hi6210-i2s.c
+++ b/sound/soc/hisilicon/hi6210-i2s.c
@@ -261,13 +261,13 @@ static int hi6210_i2s_hw_params(struct snd_pcm_substream *substream,
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_U16_LE:
 		signed_data = HII2S_I2S_CFG__S2_CODEC_DATA_FORMAT;
-		/* fall through */
+		fallthrough;
 	case SNDRV_PCM_FORMAT_S16_LE:
 		bits = HII2S_BITS_16;
 		break;
 	case SNDRV_PCM_FORMAT_U24_LE:
 		signed_data = HII2S_I2S_CFG__S2_CODEC_DATA_FORMAT;
-		/* fall through */
+		fallthrough;
 	case SNDRV_PCM_FORMAT_S24_LE:
 		bits = HII2S_BITS_24;
 		break;
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 49b9f18472bc..b1cac7abdc0a 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -331,7 +331,7 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 
 	ret_val = power_up_sst(stream);
 	if (ret_val < 0)
-		return ret_val;
+		goto out_power_up;
 
 	/* Make sure, that the period size is always even */
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
@@ -340,8 +340,9 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 	return snd_pcm_hw_constraint_integer(runtime,
 			 SNDRV_PCM_HW_PARAM_PERIODS);
 out_ops:
-	kfree(stream);
 	mutex_unlock(&sst_lock);
+out_power_up:
+	kfree(stream);
 	return ret_val;
 }
 
diff --git a/sound/soc/intel/baytrail/sst-baytrail-pcm.c b/sound/soc/intel/baytrail/sst-baytrail-pcm.c
index 54a66cc6db89..d2cda33b65d5 100644
--- a/sound/soc/intel/baytrail/sst-baytrail-pcm.c
+++ b/sound/soc/intel/baytrail/sst-baytrail-pcm.c
@@ -181,7 +181,7 @@ static int sst_byt_pcm_trigger(struct snd_soc_component *component,
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 		pdata->restore_stream = false;
-		/* fallthrough */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		sst_byt_stream_pause(byt, pcm_data->stream);
 		break;
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 414ae4bb5224..7ae34b49815c 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -573,7 +573,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 			break;
 		default:
 			dev_err(dev, "get speaker GPIO failed: %d\n", ret);
-			/* fall through */
+			fallthrough;
 		case -EPROBE_DEFER:
 			return ret;
 		}
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 4e2897596cea..688b5e0a49e3 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -1009,7 +1009,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 			default:
 				dev_err(&pdev->dev, "Failed to get ext-amp-enable GPIO: %d\n",
 					ret_val);
-				/* fall through */
+				fallthrough;
 			case -EPROBE_DEFER:
 				put_device(codec_dev);
 				return ret_val;
@@ -1029,7 +1029,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 			default:
 				dev_err(&pdev->dev, "Failed to get hp-detect GPIO: %d\n",
 					ret_val);
-				/* fall through */
+				fallthrough;
 			case -EPROBE_DEFER:
 				put_device(codec_dev);
 				return ret_val;
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 5dee55e9546b..bbe8d782e0af 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -488,7 +488,7 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 							stream->lpib);
 			snd_hdac_ext_stream_set_lpib(stream, stream->lpib);
 		}
-		/* fall through */
+		fallthrough;
 
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
index 36df30915378..c8664ab80d45 100644
--- a/sound/soc/meson/axg-tdm-interface.c
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -58,17 +58,17 @@ int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask,
 	switch (slot_width) {
 	case 0:
 		slot_width = 32;
-		/* Fall-through */
+		fallthrough;
 	case 32:
 		fmt |= SNDRV_PCM_FMTBIT_S32_LE;
-		/* Fall-through */
+		fallthrough;
 	case 24:
 		fmt |= SNDRV_PCM_FMTBIT_S24_LE;
 		fmt |= SNDRV_PCM_FMTBIT_S20_LE;
-		/* Fall-through */
+		fallthrough;
 	case 16:
 		fmt |= SNDRV_PCM_FMTBIT_S16_LE;
-		/* Fall-through */
+		fallthrough;
 	case 8:
 		fmt |= SNDRV_PCM_FMTBIT_S8;
 		break;
@@ -133,7 +133,7 @@ static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	case SND_SOC_DAIFMT_CBS_CFM:
 	case SND_SOC_DAIFMT_CBM_CFS:
 		dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n");
-		/* Fall-through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index d1e09ade0190..c4e7307a4437 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -488,7 +488,7 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 
 	case SND_SOC_DAIFMT_DSP_A:
 		sspsp |= SSPSP_FSRT;
-		/* fall through */
+		fallthrough;
 	case SND_SOC_DAIFMT_DSP_B:
 		sscr0 |= SSCR0_MOD | SSCR0_PSP;
 		sscr1 |= SSCR1_TRAIL | SSCR1_RWOT;
diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 2a5302f1db98..0168af849272 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -1150,206 +1150,206 @@ static int q6afe_of_xlate_dai_name(struct snd_soc_component *component,
 }
 
 static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = {
-	SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_MI2S_RX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_TX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_MI2S_RX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_MI2S_TX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_MI2S_TX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX_SD1",
 			"Secondary MI2S Playback SD1",
-			0, 0, 0, 0),
+			0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRI_MI2S_RX", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRI_MI2S_TX", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_0", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_1", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_2", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_3", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_4", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_5", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_6", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_7", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_0", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_1", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_2", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_3", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_4", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_5", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_6", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_7", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_0", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_1", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_2", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_3", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_4", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_5", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_6", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_7", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_0", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_1", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_2", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_3", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_4", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_5", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_6", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_7", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_0", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_1", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_2", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_3", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_4", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_5", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_6", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_7", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_0", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_1", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_2", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_3", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_4", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_5", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_6", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_7", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_0", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_1", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_2", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_3", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_4", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_5", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_6", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_7", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_0", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_1", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_2", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_3", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_4", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_5", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_6", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_7", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_0", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_1", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_2", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_3", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_4", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_5", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_6", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_7", NULL,
-			     0, 0, 0, 0),
+			     0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_0", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_1", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_2", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_3", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_4", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_5", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_6", NULL,
-						0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_7", NULL,
-						0, 0, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, 0, 0, 0),
+						0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, SND_SOC_NOPM, 0, 0),
 };
 
 static const struct snd_soc_component_driver q6afe_dai_component = {
diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index eaa95b5a7b66..25d23e0266c7 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -973,6 +973,20 @@ static int msm_routing_probe(struct snd_soc_component *c)
 	return 0;
 }
 
+static unsigned int q6routing_reg_read(struct snd_soc_component *component,
+				       unsigned int reg)
+{
+	/* default value */
+	return 0;
+}
+
+static int q6routing_reg_write(struct snd_soc_component *component,
+			       unsigned int reg, unsigned int val)
+{
+	/* dummy */
+	return 0;
+}
+
 static const struct snd_soc_component_driver msm_soc_routing_component = {
 	.probe = msm_routing_probe,
 	.name = DRV_NAME,
@@ -981,6 +995,8 @@ static const struct snd_soc_component_driver msm_soc_routing_component = {
 	.num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets),
 	.dapm_routes = intercon,
 	.num_dapm_routes = ARRAY_SIZE(intercon),
+	.read = q6routing_reg_read,
+	.write = q6routing_reg_write,
 };
 
 static int q6pcm_routing_probe(struct platform_device *pdev)
diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c
index 1707414cfa92..5adb293d0435 100644
--- a/sound/soc/rockchip/rockchip_pdm.c
+++ b/sound/soc/rockchip/rockchip_pdm.c
@@ -229,13 +229,13 @@ static int rockchip_pdm_hw_params(struct snd_pcm_substream *substream,
 	switch (params_channels(params)) {
 	case 8:
 		val |= PDM_PATH3_EN;
-		/* fallthrough */
+		fallthrough;
 	case 6:
 		val |= PDM_PATH2_EN;
-		/* fallthrough */
+		fallthrough;
 	case 4:
 		val |= PDM_PATH1_EN;
-		/* fallthrough */
+		fallthrough;
 	case 2:
 		val |= PDM_PATH0_EN;
 		break;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 80ecb5c7fed0..df53d4ea808f 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -733,7 +733,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 	switch (params_channels(params)) {
 	case 6:
 		val |= MOD_DC2_EN;
-		/* Fall through */
+		fallthrough;
 	case 4:
 		val |= MOD_DC1_EN;
 		break;
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index bd9de77c35f3..50fc7810723e 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -198,9 +198,9 @@ static int siu_pcm_rd_set(struct siu_port *port_info,
 	return 0;
 }
 
-static void siu_io_tasklet(unsigned long data)
+static void siu_io_tasklet(struct tasklet_struct *t)
 {
-	struct siu_stream *siu_stream = (struct siu_stream *)data;
+	struct siu_stream *siu_stream = from_tasklet(siu_stream, t, tasklet);
 	struct snd_pcm_substream *substream = siu_stream->substream;
 	struct device *dev = substream->pcm->card->dev;
 	struct snd_pcm_runtime *rt = substream->runtime;
@@ -520,10 +520,8 @@ static int siu_pcm_new(struct snd_soc_component *component,
 		(*port_info)->pcm = pcm;
 
 		/* IO tasklets */
-		tasklet_init(&(*port_info)->playback.tasklet, siu_io_tasklet,
-			     (unsigned long)&(*port_info)->playback);
-		tasklet_init(&(*port_info)->capture.tasklet, siu_io_tasklet,
-			     (unsigned long)&(*port_info)->capture);
+		tasklet_setup(&(*port_info)->playback.tasklet, siu_io_tasklet);
+		tasklet_setup(&(*port_info)->capture.tasklet, siu_io_tasklet);
 	}
 
 	dev_info(card->dev, "SuperH SIU driver initialized.\n");
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index f0b4f4bc44a4..5504b92946e3 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -406,7 +406,7 @@ static unsigned int soc_component_read_no_lock(
 		ret = -EIO;
 
 	if (ret < 0)
-		soc_component_ret(component, ret);
+		return soc_component_ret(component, ret);
 
 	return val;
 }
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 2fe1b2ec7c8f..663e3839f251 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -618,7 +618,7 @@ int snd_soc_suspend(struct device *dev)
 						"ASoC: idle_bias_off CODEC on over suspend\n");
 					break;
 				}
-				/* fall through */
+				fallthrough;
 
 			case SND_SOC_BIAS_OFF:
 				snd_soc_component_suspend(component);
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index cee998671318..5b60379237bf 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1057,7 +1057,7 @@ static int soc_tplg_denum_create(struct soc_tplg *tplg, unsigned int count,
 					ec->hdr.name);
 				goto err_denum;
 			}
-			/* fall through */
+			fallthrough;
 		case SND_SOC_TPLG_CTL_ENUM:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT:
@@ -1445,7 +1445,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
 					ec->hdr.name);
 				goto err_se;
 			}
-			/* fall through */
+			fallthrough;
 		case SND_SOC_TPLG_CTL_ENUM:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT:
diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c
index df1c6997cb4e..c6cb8c212eca 100644
--- a/sound/soc/sof/intel/hda-dai.c
+++ b/sound/soc/sof/intel/hda-dai.c
@@ -310,7 +310,7 @@ static int hda_link_pcm_trigger(struct snd_pcm_substream *substream,
 			return ret;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		snd_hdac_ext_link_stream_start(link_dev);
@@ -333,7 +333,7 @@ static int hda_link_pcm_trigger(struct snd_pcm_substream *substream,
 
 		link_dev->link_prepared = 0;
 
-		/* fallthrough */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		snd_hdac_ext_link_stream_clear(link_dev);
 		break;
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index d730e437e4ba..71c3f29057a7 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -361,7 +361,7 @@ static int sof_pcm_trigger(struct snd_soc_component *component,
 			return ret;
 		}
 
-		/* fallthrough */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_START:
 		if (spcm->stream[substream->stream].suspend_ignored) {
 			/*
@@ -386,7 +386,7 @@ static int sof_pcm_trigger(struct snd_soc_component *component,
 			spcm->stream[substream->stream].suspend_ignored = true;
 			return 0;
 		}
-		/* fallthrough */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_STOP:
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_STOP;
 		ipc_first = true;
diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c
index fe7117171a0e..0cbe31e2c7e9 100644
--- a/sound/soc/tegra/tegra186_dspk.c
+++ b/sound/soc/tegra/tegra186_dspk.c
@@ -71,7 +71,7 @@ static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-static int tegra186_dspk_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev)
 {
 	struct tegra186_dspk *dspk = dev_get_drvdata(dev);
 
@@ -83,7 +83,7 @@ static int tegra186_dspk_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra186_dspk_runtime_resume(struct device *dev)
+static int __maybe_unused tegra186_dspk_runtime_resume(struct device *dev)
 {
 	struct tegra186_dspk *dspk = dev_get_drvdata(dev);
 	int err;
diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c
index 4894e8e6ee7f..1268046b345d 100644
--- a/sound/soc/tegra/tegra210_admaif.c
+++ b/sound/soc/tegra/tegra210_admaif.c
@@ -219,7 +219,7 @@ static const struct regmap_config tegra186_admaif_regmap_config = {
 	.cache_type		= REGCACHE_FLAT,
 };
 
-static int tegra_admaif_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra_admaif_runtime_suspend(struct device *dev)
 {
 	struct tegra_admaif *admaif = dev_get_drvdata(dev);
 
@@ -229,7 +229,7 @@ static int tegra_admaif_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra_admaif_runtime_resume(struct device *dev)
+static int __maybe_unused tegra_admaif_runtime_resume(struct device *dev)
 {
 	struct tegra_admaif *admaif = dev_get_drvdata(dev);
 
diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c
index 5123a96fdde8..66287a7c9865 100644
--- a/sound/soc/tegra/tegra210_ahub.c
+++ b/sound/soc/tegra/tegra210_ahub.c
@@ -564,7 +564,7 @@ static const struct of_device_id tegra_ahub_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, tegra_ahub_of_match);
 
-static int tegra_ahub_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra_ahub_runtime_suspend(struct device *dev)
 {
 	struct tegra_ahub *ahub = dev_get_drvdata(dev);
 
@@ -576,7 +576,7 @@ static int tegra_ahub_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra_ahub_runtime_resume(struct device *dev)
+static int __maybe_unused tegra_ahub_runtime_resume(struct device *dev)
 {
 	struct tegra_ahub *ahub = dev_get_drvdata(dev);
 	int err;
diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c
index d682414ad90d..a661f40bc41c 100644
--- a/sound/soc/tegra/tegra210_dmic.c
+++ b/sound/soc/tegra/tegra210_dmic.c
@@ -40,7 +40,7 @@ static const struct reg_default tegra210_dmic_reg_defaults[] = {
 	{ TEGRA210_DMIC_LP_BIQUAD_1_COEF_4, 0x0 },
 };
 
-static int tegra210_dmic_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra210_dmic_runtime_suspend(struct device *dev)
 {
 	struct tegra210_dmic *dmic = dev_get_drvdata(dev);
 
@@ -52,7 +52,7 @@ static int tegra210_dmic_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra210_dmic_runtime_resume(struct device *dev)
+static int __maybe_unused tegra210_dmic_runtime_resume(struct device *dev)
 {
 	struct tegra210_dmic *dmic = dev_get_drvdata(dev);
 	int err;
diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c
index 722092181583..a383bd5c51cd 100644
--- a/sound/soc/tegra/tegra210_i2s.c
+++ b/sound/soc/tegra/tegra210_i2s.c
@@ -164,7 +164,7 @@ static int tegra210_i2s_init(struct snd_soc_dapm_widget *w,
 	return tegra210_i2s_sw_reset(compnt, is_playback);
 }
 
-static int tegra210_i2s_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra210_i2s_runtime_suspend(struct device *dev)
 {
 	struct tegra210_i2s *i2s = dev_get_drvdata(dev);
 
@@ -176,7 +176,7 @@ static int tegra210_i2s_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra210_i2s_runtime_resume(struct device *dev)
+static int __maybe_unused tegra210_i2s_runtime_resume(struct device *dev)
 {
 	struct tegra210_i2s *i2s = dev_get_drvdata(dev);
 	int err;
diff --git a/sound/soc/ti/davinci-i2s.c b/sound/soc/ti/davinci-i2s.c
index d89b5c928c4d..dd34504c09ba 100644
--- a/sound/soc/ti/davinci-i2s.c
+++ b/sound/soc/ti/davinci-i2s.c
@@ -289,7 +289,7 @@ static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		 * rate is lowered.
 		 */
 		inv_fs = true;
-		/* fall through */
+		fallthrough;
 	case SND_SOC_DAIFMT_DSP_A:
 		dev->mode = MOD_DSP_A;
 		break;
diff --git a/sound/soc/ti/n810.c b/sound/soc/ti/n810.c
index 2802a33b9c5f..ed217b34f846 100644
--- a/sound/soc/ti/n810.c
+++ b/sound/soc/ti/n810.c
@@ -46,7 +46,7 @@ static void n810_ext_control(struct snd_soc_dapm_context *dapm)
 	switch (n810_jack_func) {
 	case N810_JACK_HS:
 		line1l = 1;
-		/* fall through */
+		fallthrough;
 	case N810_JACK_HP:
 		hp = 1;
 		break;
diff --git a/sound/soc/ti/omap-dmic.c b/sound/soc/ti/omap-dmic.c
index 01abf1be5d78..a26588e9c3bc 100644
--- a/sound/soc/ti/omap-dmic.c
+++ b/sound/soc/ti/omap-dmic.c
@@ -203,10 +203,10 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream,
 	switch (channels) {
 	case 6:
 		dmic->ch_enabled |= OMAP_DMIC_UP3_ENABLE;
-		/* fall through */
+		fallthrough;
 	case 4:
 		dmic->ch_enabled |= OMAP_DMIC_UP2_ENABLE;
-		/* fall through */
+		fallthrough;
 	case 2:
 		dmic->ch_enabled |= OMAP_DMIC_UP1_ENABLE;
 		break;
diff --git a/sound/soc/ti/omap-mcpdm.c b/sound/soc/ti/omap-mcpdm.c
index d482b62f314a..fafb2998ad0d 100644
--- a/sound/soc/ti/omap-mcpdm.c
+++ b/sound/soc/ti/omap-mcpdm.c
@@ -309,19 +309,19 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 4;
-		/* fall through */
+		fallthrough;
 	case 4:
 		if (stream == SNDRV_PCM_STREAM_CAPTURE)
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 3;
-		/* fall through */
+		fallthrough;
 	case 3:
 		link_mask |= 1 << 2;
-		/* fall through */
+		fallthrough;
 	case 2:
 		link_mask |= 1 << 1;
-		/* fall through */
+		fallthrough;
 	case 1:
 		link_mask |= 1 << 0;
 		break;
diff --git a/sound/soc/ti/rx51.c b/sound/soc/ti/rx51.c
index 2176a95201bf..a2629ccc1dc8 100644
--- a/sound/soc/ti/rx51.c
+++ b/sound/soc/ti/rx51.c
@@ -55,7 +55,7 @@ static void rx51_ext_control(struct snd_soc_dapm_context *dapm)
 		break;
 	case RX51_JACK_HS:
 		hs = 1;
-		/* fall through */
+		fallthrough;
 	case RX51_JACK_HP:
 		hp = 1;
 		break;
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index 4b1cd4da3e36..939b33ec39f5 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -134,9 +134,9 @@ txx9aclc_dma_submit(struct txx9aclc_dmadata *dmadata, dma_addr_t buf_dma_addr)
 
 #define NR_DMA_CHAIN		2
 
-static void txx9aclc_dma_tasklet(unsigned long data)
+static void txx9aclc_dma_tasklet(struct tasklet_struct *t)
 {
-	struct txx9aclc_dmadata *dmadata = (struct txx9aclc_dmadata *)data;
+	struct txx9aclc_dmadata *dmadata = from_tasklet(dmadata, t, tasklet);
 	struct dma_chan *chan = dmadata->dma_chan;
 	struct dma_async_tx_descriptor *desc;
 	struct snd_pcm_substream *substream = dmadata->substream;
@@ -352,8 +352,7 @@ static int txx9aclc_dma_init(struct txx9aclc_soc_device *dev,
 			"playback" : "capture");
 		return -EBUSY;
 	}
-	tasklet_init(&dmadata->tasklet, txx9aclc_dma_tasklet,
-		     (unsigned long)dmadata);
+	tasklet_setup(&dmadata->tasklet, txx9aclc_dma_tasklet);
 	return 0;
 }
 
diff --git a/sound/soc/zte/zx-i2s.c b/sound/soc/zte/zx-i2s.c
index 568cde64ff8b..1c1a44e08a67 100644
--- a/sound/soc/zte/zx-i2s.c
+++ b/sound/soc/zte/zx-i2s.c
@@ -294,7 +294,7 @@ static int zx_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
 			zx_i2s_rx_dma_en(zx_i2s->reg_base, true);
 		else
 			zx_i2s_tx_dma_en(zx_i2s->reg_base, true);
-	/* fall thru */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		if (capture)
@@ -308,7 +308,7 @@ static int zx_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
 			zx_i2s_rx_dma_en(zx_i2s->reg_base, false);
 		else
 			zx_i2s_tx_dma_en(zx_i2s->reg_base, false);
-	/* fall thru */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		if (capture)
diff --git a/sound/soc/zte/zx-spdif.c b/sound/soc/zte/zx-spdif.c
index a3a07c0730e6..b4168bd532b7 100644
--- a/sound/soc/zte/zx-spdif.c
+++ b/sound/soc/zte/zx-spdif.c
@@ -218,7 +218,7 @@ static int zx_spdif_trigger(struct snd_pcm_substream *substream, int cmd,
 		val = readl_relaxed(zx_spdif->reg_base + ZX_FIFOCTRL);
 		val |= ZX_FIFOCTRL_TX_FIFO_RST;
 		writel_relaxed(val, zx_spdif->reg_base + ZX_FIFOCTRL);
-	/* fall thru */
+		fallthrough;
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		zx_spdif_cfg_tx(zx_spdif->reg_base, true);
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index df639fe03118..e8287a05e36b 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -344,10 +344,9 @@ static void snd_usbmidi_do_output(struct snd_usb_midi_out_endpoint *ep)
 	spin_unlock_irqrestore(&ep->buffer_lock, flags);
 }
 
-static void snd_usbmidi_out_tasklet(unsigned long data)
+static void snd_usbmidi_out_tasklet(struct tasklet_struct *t)
 {
-	struct snd_usb_midi_out_endpoint *ep =
-		(struct snd_usb_midi_out_endpoint *) data;
+	struct snd_usb_midi_out_endpoint *ep = from_tasklet(ep, t, tasklet);
 
 	snd_usbmidi_do_output(ep);
 }
@@ -1441,7 +1440,7 @@ static int snd_usbmidi_out_endpoint_create(struct snd_usb_midi *umidi,
 	}
 
 	spin_lock_init(&ep->buffer_lock);
-	tasklet_init(&ep->tasklet, snd_usbmidi_out_tasklet, (unsigned long)ep);
+	tasklet_setup(&ep->tasklet, snd_usbmidi_out_tasklet);
 	init_waitqueue_head(&ep->drain_wait);
 
 	for (i = 0; i < 0x10; ++i)
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 884e740a785c..3b2dce1043f5 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -247,9 +247,9 @@ static inline void add_with_wraparound(struct ua101 *ua,
 		*value -= ua->playback.queue_length;
 }
 
-static void playback_tasklet(unsigned long data)
+static void playback_tasklet(struct tasklet_struct *t)
 {
-	struct ua101 *ua = (void *)data;
+	struct ua101 *ua = from_tasklet(ua, t, playback_tasklet);
 	unsigned long flags;
 	unsigned int frames;
 	struct ua101_urb *urb;
@@ -1218,8 +1218,7 @@ static int ua101_probe(struct usb_interface *interface,
 	spin_lock_init(&ua->lock);
 	mutex_init(&ua->mutex);
 	INIT_LIST_HEAD(&ua->ready_playback_urbs);
-	tasklet_init(&ua->playback_tasklet,
-		     playback_tasklet, (unsigned long)ua);
+	tasklet_setup(&ua->playback_tasklet, playback_tasklet);
 	init_waitqueue_head(&ua->alsa_capture_wait);
 	init_waitqueue_head(&ua->rate_feedback_wait);
 	init_waitqueue_head(&ua->alsa_playback_wait);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 6b0f3a8469ef..81e987eaf063 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2371,7 +2371,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 	int num_ins;
 	struct usb_mixer_elem_info *cval;
 	struct snd_kcontrol *kctl;
-	int i, err, nameid, type, len;
+	int i, err, nameid, type, len, val;
 	const struct procunit_info *info;
 	const struct procunit_value_info *valinfo;
 	const struct usbmix_name_map *map;
@@ -2474,6 +2474,12 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 			break;
 		}
 
+		err = get_cur_ctl_value(cval, cval->control << 8, &val);
+		if (err < 0) {
+			usb_mixer_elem_info_free(cval);
+			return -EINVAL;
+		}
+
 		kctl = snd_ctl_new1(&mixer_procunit_ctl, cval);
 		if (!kctl) {
 			usb_mixer_elem_info_free(cval);
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 5600751803cf..b401ee894e1b 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -369,11 +369,13 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
 	case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */
 	case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */
+	case USB_ID(0x0499, 0x172f): /* Steinberg UR22C */
 	case USB_ID(0x0d9a, 0x00df): /* RTX6001 */
 		ep = 0x81;
 		ifnum = 2;
 		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x2b73, 0x000a): /* Pioneer DJ DJM-900NXS2 */
+	case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */
 		ep = 0x82;
 		ifnum = 0;
 		goto add_sync_ep_from_ifnum;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index d79e3ddc5690..23eafd50126f 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2680,6 +2680,10 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.data = (const struct snd_usb_audio_quirk[]) {
 			{
 				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
+			},
+			{
+				.ifnum = 0,
 				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
 				.data = &(const struct audioformat) {
 					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
@@ -2690,6 +2694,32 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 					.attributes = UAC_EP_CS_ATTR_SAMPLE_RATE,
 					.endpoint = 0x01,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC,
+					.datainterval = 1,
+					.maxpacksize = 0x024c,
+					.rates = SNDRV_PCM_RATE_44100 |
+						 SNDRV_PCM_RATE_48000,
+					.rate_min = 44100,
+					.rate_max = 48000,
+					.nr_rates = 2,
+					.rate_table = (unsigned int[]) {
+						44100, 48000
+					}
+				}
+			},
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 2,
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.attributes = 0,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC,
+					.datainterval = 1,
+					.maxpacksize = 0x0126,
 					.rates = SNDRV_PCM_RATE_44100 |
 						 SNDRV_PCM_RATE_48000,
 					.rate_min = 44100,
@@ -2797,14 +2827,24 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 /* Lenovo ThinkStation P620 Rear Line-in, Line-out and Microphone */
 {
 	USB_DEVICE(0x17aa, 0x1046),
-	QUIRK_DEVICE_PROFILE("Lenovo", "ThinkStation P620 Rear",
-			     "Lenovo-ThinkStation-P620-Rear"),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Lenovo",
+		.product_name = "ThinkStation P620 Rear",
+		.profile_name = "Lenovo-ThinkStation-P620-Rear",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_SETUP_DISABLE_AUTOSUSPEND
+	}
 },
 /* Lenovo ThinkStation P620 Internal Speaker + Front Headset */
 {
 	USB_DEVICE(0x17aa, 0x104d),
-	QUIRK_DEVICE_PROFILE("Lenovo", "ThinkStation P620 Main",
-			     "Lenovo-ThinkStation-P620-Main"),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Lenovo",
+		.product_name = "ThinkStation P620 Main",
+		.profile_name = "Lenovo-ThinkStation-P620-Main",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_SETUP_DISABLE_AUTOSUSPEND
+	}
 },
 
 /* Native Instruments MK2 series */
@@ -3519,14 +3559,40 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 {
 	/*
 	 * Pioneer DJ DJM-250MK2
-	 * PCM is 8 channels out @ 48 fixed (endpoints 0x01).
-	 * The output from computer to the mixer is usable.
+	 * PCM is 8 channels out @ 48 fixed (endpoint 0x01)
+	 * and 8 channels in @ 48 fixed (endpoint 0x82).
+	 *
+	 * Both playback and recording is working, even simultaneously.
+	 *
+	 * Playback channels could be mapped to:
+	 *  - CH1
+	 *  - CH2
+	 *  - AUX
 	 *
-	 * The input (phono or line to computer) is not working.
-	 * It should be at endpoint 0x82 and probably also 8 channels,
-	 * but it seems that it works only with Pioneer proprietary software.
-	 * Even on officially supported OS, the Audacity was unable to record
-	 * and Mixxx to recognize the control vinyls.
+	 * Recording channels could be mapped to:
+	 *  - Post CH1 Fader
+	 *  - Post CH2 Fader
+	 *  - Cross Fader A
+	 *  - Cross Fader B
+	 *  - MIC
+	 *  - AUX
+	 *  - REC OUT
+	 *
+	 * There is remaining problem with recording directly from PHONO/LINE.
+	 * If we map a channel to:
+	 *  - CH1 Control Tone PHONO
+	 *  - CH1 Control Tone LINE
+	 *  - CH2 Control Tone PHONO
+	 *  - CH2 Control Tone LINE
+	 * it is silent.
+	 * There is no signal even on other operating systems with official drivers.
+	 * The signal appears only when a supported application is started.
+	 * This needs to be investigated yet...
+	 * (there is quite a lot communication on the USB in both directions)
+	 *
+	 * In current version this mixer could be used for playback
+	 * and for recording from vinyls (through Post CH* Fader)
+	 * but not for DVS (Digital Vinyl Systems) like in Mixxx.
 	 */
 	USB_DEVICE_VENDOR_SPEC(0x2b73, 0x0017),
 	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
@@ -3550,6 +3616,26 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.rate_max = 48000,
 					.nr_rates = 1,
 					.rate_table = (unsigned int[]) { 48000 }
+					}
+			},
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 8, // inputs
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						USB_ENDPOINT_SYNC_ASYNC|
+						USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_48000,
+					.rate_min = 48000,
+					.rate_max = 48000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 48000 }
 				}
 			},
 			{
@@ -3714,8 +3800,8 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */
  * they pretend to be 96kHz mono as a workaround for stereo being broken
  * by that...
  *
- * They also have swapped L-R channels, but that's for userspace to deal
- * with.
+ * They also have an issue with initial stream alignment that causes the
+ * channels to be swapped and out of phase, which is dealt with in quirks.c.
  */
 {
 	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index abf99b814a0f..75bbdc691243 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -518,6 +518,15 @@ static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip,
 	return 1;	/* Continue with creating streams and mixer */
 }
 
+static int setup_disable_autosuspend(struct snd_usb_audio *chip,
+				       struct usb_interface *iface,
+				       struct usb_driver *driver,
+				       const struct snd_usb_audio_quirk *quirk)
+{
+	driver->supports_autosuspend = 0;
+	return 1;	/* Continue with creating streams and mixer */
+}
+
 /*
  * audio-interface quirks
  *
@@ -557,6 +566,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip,
 		[QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk,
 		[QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk,
 		[QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk,
+		[QUIRK_SETUP_DISABLE_AUTOSUSPEND] = setup_disable_autosuspend,
 	};
 
 	if (quirk->type < QUIRK_TYPE_COUNT) {
@@ -1493,6 +1503,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 		set_format_emu_quirk(subs, fmt);
 		break;
 	case USB_ID(0x2b73, 0x000a): /* Pioneer DJ DJM-900NXS2 */
+	case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */
 		pioneer_djm_set_format_quirk(subs);
 		break;
 	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index b91c4c0807ec..6839915a0128 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -102,6 +102,7 @@ enum quirk_type {
 	QUIRK_AUDIO_ALIGN_TRANSFER,
 	QUIRK_AUDIO_STANDARD_MIXER,
 	QUIRK_SETUP_FMT_AFTER_RESUME,
+	QUIRK_SETUP_DISABLE_AUTOSUSPEND,
 
 	QUIRK_TYPE_COUNT
 };
diff --git a/sound/x86/Kconfig b/sound/x86/Kconfig
index 77777192f650..4ffcc5e623c2 100644
--- a/sound/x86/Kconfig
+++ b/sound/x86/Kconfig
@@ -9,7 +9,7 @@ menuconfig SND_X86
 if SND_X86
 
 config HDMI_LPE_AUDIO
-	tristate "HDMI audio without HDaudio on Intel Atom platforms"
+	tristate "HDMI audio without HDAudio on Intel Atom platforms"
 	depends on DRM_I915
 	select SND_PCM
 	help
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index ede162f83eea..0e9310727281 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -67,7 +67,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
 	if (!info->btf_id || !info->nr_func_info ||
 	    btf__get_from_id(info->btf_id, &prog_btf))
 		goto print;
-	finfo = (struct bpf_func_info *)info->func_info;
+	finfo = u64_to_ptr(info->func_info);
 	func_type = btf__type_by_id(prog_btf, finfo->type_id);
 	if (!func_type || !btf_is_func(func_type))
 		goto print;
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 8a4c2b3b0cd6..f61184653633 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -143,6 +143,20 @@ static int codegen_datasec_def(struct bpf_object *obj,
 			      var_name, align);
 			return -EINVAL;
 		}
+		/* Assume 32-bit architectures when generating data section
+		 * struct memory layout. Given bpftool can't know which target
+		 * host architecture it's emitting skeleton for, we need to be
+		 * conservative and assume 32-bit one to ensure enough padding
+		 * bytes are generated for pointer and long types. This will
+		 * still work correctly for 64-bit architectures, because in
+		 * the worst case we'll generate unnecessary padding field,
+		 * which on 64-bit architectures is not strictly necessary and
+		 * would be handled by natural 8-byte alignment. But it still
+		 * will be a correct memory layout, based on recorded offsets
+		 * in BTF.
+		 */
+		if (align > 4)
+			align = 4;
 
 		align_off = (off + align - 1) / align * align;
 		if (align_off != need_off) {
@@ -397,7 +411,7 @@ static int do_skeleton(int argc, char **argv)
 		{							    \n\
 			struct %1$s *obj;				    \n\
 									    \n\
-			obj = (typeof(obj))calloc(1, sizeof(*obj));	    \n\
+			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
 			if (!obj)					    \n\
 				return NULL;				    \n\
 			if (%1$s__create_skeleton(obj))			    \n\
@@ -461,7 +475,7 @@ static int do_skeleton(int argc, char **argv)
 		{							    \n\
 			struct bpf_object_skeleton *s;			    \n\
 									    \n\
-			s = (typeof(s))calloc(1, sizeof(*s));		    \n\
+			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
 			if (!s)						    \n\
 				return -1;				    \n\
 			obj->skeleton = s;				    \n\
@@ -479,7 +493,7 @@ static int do_skeleton(int argc, char **argv)
 				/* maps */				    \n\
 				s->map_cnt = %zu;			    \n\
 				s->map_skel_sz = sizeof(*s->maps);	    \n\
-				s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\
+				s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
 				if (!s->maps)				    \n\
 					goto err;			    \n\
 			",
@@ -515,7 +529,7 @@ static int do_skeleton(int argc, char **argv)
 				/* programs */				    \n\
 				s->prog_cnt = %zu;			    \n\
 				s->prog_skel_sz = sizeof(*s->progs);	    \n\
-				s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\
+				s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
 				if (!s->progs)				    \n\
 					goto err;			    \n\
 			",
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 1b793759170e..a89f09e3c848 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -106,7 +106,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	switch (info->type) {
 	case BPF_LINK_TYPE_RAW_TRACEPOINT:
 		jsonw_string_field(json_wtr, "tp_name",
-				   (const char *)info->raw_tracepoint.tp_name);
+				   u64_to_ptr(info->raw_tracepoint.tp_name));
 		break;
 	case BPF_LINK_TYPE_TRACING:
 		err = get_prog_info(info->prog_id, &prog_info);
@@ -185,7 +185,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	switch (info->type) {
 	case BPF_LINK_TYPE_RAW_TRACEPOINT:
 		printf("\n\ttp '%s'  ",
-		       (const char *)info->raw_tracepoint.tp_name);
+		       (const char *)u64_to_ptr(info->raw_tracepoint.tp_name));
 		break;
 	case BPF_LINK_TYPE_TRACING:
 		err = get_prog_info(info->prog_id, &prog_info);
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index e3a79b5a9960..c46e52137b87 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -21,7 +21,15 @@
 /* Make sure we do not use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
-#define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64)(unsigned long)ptr;
+}
+
+static inline void *u64_to_ptr(__u64 ptr)
+{
+	return (void *)(unsigned long)ptr;
+}
 
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index e3b116325403..df7d8ec76036 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -134,6 +134,8 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 	while (true) {
 		ret = read(fd, buf, sizeof(buf));
 		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
 			err = -errno;
 			p_err("failed to read PID iterator output: %d", err);
 			goto out;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 158995d853b0..d393eb8263a6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -428,14 +428,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 			p_info("no instructions returned");
 			return -1;
 		}
-		buf = (unsigned char *)(info->jited_prog_insns);
+		buf = u64_to_ptr(info->jited_prog_insns);
 		member_len = info->jited_prog_len;
 	} else {	/* DUMP_XLATED */
 		if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) {
 			p_err("error retrieving insn dump: kernel.kptr_restrict set?");
 			return -1;
 		}
-		buf = (unsigned char *)info->xlated_prog_insns;
+		buf = u64_to_ptr(info->xlated_prog_insns);
 		member_len = info->xlated_prog_len;
 	}
 
@@ -444,7 +444,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 		return -1;
 	}
 
-	func_info = (void *)info->func_info;
+	func_info = u64_to_ptr(info->func_info);
 
 	if (info->nr_line_info) {
 		prog_linfo = bpf_prog_linfo__new(info);
@@ -462,7 +462,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 
 		n = write(fd, buf, member_len);
 		close(fd);
-		if (n != member_len) {
+		if (n != (ssize_t)member_len) {
 			p_err("error writing output file: %s",
 			      n < 0 ? strerror(errno) : "short write");
 			return -1;
@@ -492,13 +492,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 			__u32 i;
 			if (info->nr_jited_ksyms) {
 				kernel_syms_load(&dd);
-				ksyms = (__u64 *) info->jited_ksyms;
+				ksyms = u64_to_ptr(info->jited_ksyms);
 			}
 
 			if (json_output)
 				jsonw_start_array(json_wtr);
 
-			lens = (__u32 *) info->jited_func_lens;
+			lens = u64_to_ptr(info->jited_func_lens);
 			for (i = 0; i < info->nr_jited_func_lens; i++) {
 				if (ksyms) {
 					sym = kernel_syms_search(&dd, ksyms[i]);
@@ -559,7 +559,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 	} else {
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info->nr_jited_ksyms;
-		dd.jited_ksyms = (__u64 *) info->jited_ksyms;
+		dd.jited_ksyms = u64_to_ptr(info->jited_ksyms);
 		dd.btf = btf;
 		dd.func_info = func_info;
 		dd.finfo_rec_size = info->func_info_rec_size;
@@ -1681,7 +1681,7 @@ static char *profile_target_name(int tgt_fd)
 		goto out;
 	}
 
-	func_info = (struct bpf_func_info *)(info_linear->info.func_info);
+	func_info = u64_to_ptr(info_linear->info.func_info);
 	t = btf__type_by_id(btf, func_info[0].type_id);
 	if (!t) {
 		p_err("btf %d doesn't have type %d",
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 4d9ecb975862..0def0bb1f783 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -233,6 +233,39 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, false);
 }
 
+/*
+ * The data of compressed section should be aligned to 4
+ * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld
+ * sets sh_addralign to 1, which makes libelf fail with
+ * misaligned section error during the update:
+ *    FAILED elf_update(WRITE): invalid section alignment
+ *
+ * While waiting for ld fix, we fix the compressed sections
+ * sh_addralign value manualy.
+ */
+static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh)
+{
+	int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8;
+
+	if (!(sh->sh_flags & SHF_COMPRESSED))
+		return 0;
+
+	if (sh->sh_addralign == expected)
+		return 0;
+
+	pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n",
+		  sh->sh_addralign, expected);
+
+	sh->sh_addralign = expected;
+
+	if (gelf_update_shdr(scn, sh) == 0) {
+		printf("FAILED cannot update section header: %s\n",
+			elf_errmsg(-1));
+		return -1;
+	}
+	return 0;
+}
+
 static int elf_collect(struct object *obj)
 {
 	Elf_Scn *scn = NULL;
@@ -309,6 +342,9 @@ static int elf_collect(struct object *obj)
 			obj->efile.idlist_shndx = idx;
 			obj->efile.idlist_addr  = sh.sh_addr;
 		}
+
+		if (compressed_section_fix(elf, scn, &sh))
+			return -1;
 	}
 
 	return 0;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0480f893facd..b6238b2209b7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 077e7ee69e3d..3e5dcdd48a49 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@ union perf_mem_data_src {
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	37
+#define PERF_MEM_SNOOPX_SHIFT	38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index bc14db706b88..e9a4ecddb7a5 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -40,7 +40,7 @@
  * Helper macro to manipulate data structures
  */
 #ifndef offsetof
-#define offsetof(TYPE, MEMBER)  __builtin_offsetof(TYPE, MEMBER)
+#define offsetof(TYPE, MEMBER)	((unsigned long)&((TYPE *)0)->MEMBER)
 #endif
 #ifndef container_of
 #define container_of(ptr, type, member)				\
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 4843e44916f7..7dfca7016aaa 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -41,6 +41,7 @@ struct btf {
 	__u32 types_size;
 	__u32 data_size;
 	int fd;
+	int ptr_sz;
 };
 
 static inline __u64 ptr_to_u64(const void *ptr)
@@ -221,6 +222,70 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 	return btf->types[type_id];
 }
 
+static int determine_ptr_size(const struct btf *btf)
+{
+	const struct btf_type *t;
+	const char *name;
+	int i;
+
+	for (i = 1; i <= btf->nr_types; i++) {
+		t = btf__type_by_id(btf, i);
+		if (!btf_is_int(t))
+			continue;
+
+		name = btf__name_by_offset(btf, t->name_off);
+		if (!name)
+			continue;
+
+		if (strcmp(name, "long int") == 0 ||
+		    strcmp(name, "long unsigned int") == 0) {
+			if (t->size != 4 && t->size != 8)
+				continue;
+			return t->size;
+		}
+	}
+
+	return -1;
+}
+
+static size_t btf_ptr_sz(const struct btf *btf)
+{
+	if (!btf->ptr_sz)
+		((struct btf *)btf)->ptr_sz = determine_ptr_size(btf);
+	return btf->ptr_sz < 0 ? sizeof(void *) : btf->ptr_sz;
+}
+
+/* Return pointer size this BTF instance assumes. The size is heuristically
+ * determined by looking for 'long' or 'unsigned long' integer type and
+ * recording its size in bytes. If BTF type information doesn't have any such
+ * type, this function returns 0. In the latter case, native architecture's
+ * pointer size is assumed, so will be either 4 or 8, depending on
+ * architecture that libbpf was compiled for. It's possible to override
+ * guessed value by using btf__set_pointer_size() API.
+ */
+size_t btf__pointer_size(const struct btf *btf)
+{
+	if (!btf->ptr_sz)
+		((struct btf *)btf)->ptr_sz = determine_ptr_size(btf);
+
+	if (btf->ptr_sz < 0)
+		/* not enough BTF type info to guess */
+		return 0;
+
+	return btf->ptr_sz;
+}
+
+/* Override or set pointer size in bytes. Only values of 4 and 8 are
+ * supported.
+ */
+int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
+{
+	if (ptr_sz != 4 && ptr_sz != 8)
+		return -EINVAL;
+	btf->ptr_sz = ptr_sz;
+	return 0;
+}
+
 static bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void || btf_is_fwd(t);
@@ -253,7 +318,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 			size = t->size;
 			goto done;
 		case BTF_KIND_PTR:
-			size = sizeof(void *);
+			size = btf_ptr_sz(btf);
 			goto done;
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_VOLATILE:
@@ -293,9 +358,9 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	switch (kind) {
 	case BTF_KIND_INT:
 	case BTF_KIND_ENUM:
-		return min(sizeof(void *), (size_t)t->size);
+		return min(btf_ptr_sz(btf), (size_t)t->size);
 	case BTF_KIND_PTR:
-		return sizeof(void *);
+		return btf_ptr_sz(btf);
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
@@ -533,6 +598,18 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 	if (IS_ERR(btf))
 		goto done;
 
+	switch (gelf_getclass(elf)) {
+	case ELFCLASS32:
+		btf__set_pointer_size(btf, 4);
+		break;
+	case ELFCLASS64:
+		btf__set_pointer_size(btf, 8);
+		break;
+	default:
+		pr_warn("failed to get ELF class (bitness) for %s\n", path);
+		break;
+	}
+
 	if (btf_ext && btf_ext_data) {
 		*btf_ext = btf_ext__new(btf_ext_data->d_buf,
 					btf_ext_data->d_size);
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index f4a1a1d2b9a3..1ca14448df4c 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -76,6 +76,8 @@ LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
+LIBBPF_API size_t btf__pointer_size(const struct btf *btf);
+LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz);
 LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index cf711168d34a..57c00fa63932 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -13,6 +13,7 @@
 #include <errno.h>
 #include <linux/err.h>
 #include <linux/btf.h>
+#include <linux/kernel.h>
 #include "btf.h"
 #include "hashmap.h"
 #include "libbpf.h"
@@ -60,6 +61,7 @@ struct btf_dump {
 	const struct btf_ext *btf_ext;
 	btf_dump_printf_fn_t printf_fn;
 	struct btf_dump_opts opts;
+	int ptr_sz;
 	bool strip_mods;
 
 	/* per-type auxiliary state */
@@ -138,6 +140,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 	d->btf_ext = btf_ext;
 	d->printf_fn = printf_fn;
 	d->opts.ctx = opts ? opts->ctx : NULL;
+	d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *);
 
 	d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
 	if (IS_ERR(d->type_names)) {
@@ -549,6 +552,9 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	}
 }
 
+static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id,
+					  const struct btf_type *t);
+
 static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
 				     const struct btf_type *t);
 static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id,
@@ -671,6 +677,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 
 	switch (kind) {
 	case BTF_KIND_INT:
+		/* Emit type alias definitions if necessary */
+		btf_dump_emit_missing_aliases(d, id, t);
+
 		tstate->emit_state = EMITTED;
 		break;
 	case BTF_KIND_ENUM:
@@ -797,7 +806,7 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d,
 				      int align, int lvl)
 {
 	int off_diff = m_off - cur_off;
-	int ptr_bits = sizeof(void *) * 8;
+	int ptr_bits = d->ptr_sz * 8;
 
 	if (off_diff <= 0)
 		/* no gap */
@@ -870,7 +879,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 			btf_dump_printf(d, ": %d", m_sz);
 			off = m_off + m_sz;
 		} else {
-			m_sz = max(0, btf__resolve_size(d->btf, m->type));
+			m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
 			off = m_off + m_sz * 8;
 		}
 		btf_dump_printf(d, ";");
@@ -890,6 +899,32 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 		btf_dump_printf(d, " __attribute__((packed))");
 }
 
+static const char *missing_base_types[][2] = {
+	/*
+	 * GCC emits typedefs to its internal __PolyX_t types when compiling Arm
+	 * SIMD intrinsics. Alias them to standard base types.
+	 */
+	{ "__Poly8_t",		"unsigned char" },
+	{ "__Poly16_t",		"unsigned short" },
+	{ "__Poly64_t",		"unsigned long long" },
+	{ "__Poly128_t",	"unsigned __int128" },
+};
+
+static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id,
+					  const struct btf_type *t)
+{
+	const char *name = btf_dump_type_name(d, id);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(missing_base_types); i++) {
+		if (strcmp(name, missing_base_types[i][0]) == 0) {
+			btf_dump_printf(d, "typedef %s %s;\n\n",
+					missing_base_types[i][1], name);
+			break;
+		}
+	}
+}
+
 static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
 				   const struct btf_type *t)
 {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0a06124f7999..0ad0b0491e1f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2264,7 +2264,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		data = elf_getdata(scn, NULL);
 	if (!scn || !data) {
 		pr_warn("failed to get Elf_Data from map section %d (%s)\n",
-			obj->efile.maps_shndx, MAPS_ELF_SEC);
+			obj->efile.btf_maps_shndx, MAPS_ELF_SEC);
 		return -EINVAL;
 	}
 
@@ -2434,6 +2434,8 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 				BTF_ELF_SEC, err);
 			goto out;
 		}
+		/* enforce 8-byte pointers for BPF-targeted BTFs */
+		btf__set_pointer_size(obj->btf, 8);
 		err = 0;
 	}
 	if (btf_ext_data) {
@@ -2542,6 +2544,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		if (IS_ERR(kern_btf))
 			return PTR_ERR(kern_btf);
 
+		/* enforce 8-byte pointers for BPF-targeted BTFs */
+		btf__set_pointer_size(obj->btf, 8);
 		bpf_object__sanitize_btf(obj, kern_btf);
 	}
 
@@ -3478,10 +3482,11 @@ bpf_object__probe_global_data(struct bpf_object *obj)
 
 	map = bpf_create_map_xattr(&map_attr);
 	if (map < 0) {
-		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
 		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
-			__func__, cp, errno);
-		return -errno;
+			__func__, cp, -ret);
+		return ret;
 	}
 
 	insns[0].imm = map;
@@ -5194,7 +5199,8 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 static int bpf_object__collect_map_relos(struct bpf_object *obj,
 					 GElf_Shdr *shdr, Elf_Data *data)
 {
-	int i, j, nrels, new_sz, ptr_sz = sizeof(void *);
+	const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *);
+	int i, j, nrels, new_sz;
 	const struct btf_var_secinfo *vi = NULL;
 	const struct btf_type *sec, *var, *def;
 	const struct btf_member *member;
@@ -5243,7 +5249,7 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 
 			vi = btf_var_secinfos(sec) + map->btf_var_idx;
 			if (vi->offset <= rel.r_offset &&
-			    rel.r_offset + sizeof(void *) <= vi->offset + vi->size)
+			    rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size)
 				break;
 		}
 		if (j == obj->nr_maps) {
@@ -5279,17 +5285,20 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 			return -EINVAL;
 
 		moff = rel.r_offset - vi->offset - moff;
-		if (moff % ptr_sz)
+		/* here we use BPF pointer size, which is always 64 bit, as we
+		 * are parsing ELF that was built for BPF target
+		 */
+		if (moff % bpf_ptr_sz)
 			return -EINVAL;
-		moff /= ptr_sz;
+		moff /= bpf_ptr_sz;
 		if (moff >= map->init_slots_sz) {
 			new_sz = moff + 1;
-			tmp = realloc(map->init_slots, new_sz * ptr_sz);
+			tmp = realloc(map->init_slots, new_sz * host_ptr_sz);
 			if (!tmp)
 				return -ENOMEM;
 			map->init_slots = tmp;
 			memset(map->init_slots + map->init_slots_sz, 0,
-			       (new_sz - map->init_slots_sz) * ptr_sz);
+			       (new_sz - map->init_slots_sz) * host_ptr_sz);
 			map->init_slots_sz = new_sz;
 		}
 		map->init_slots[moff] = targ_map;
@@ -6012,9 +6021,10 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		err = -errno;
+		cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
 		pr_warn("failed to pin program: %s\n", cp);
-		return -errno;
+		return err;
 	}
 	pr_debug("pinned program '%s'\n", path);
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 0c4722bfdd0a..e35bd6cdbdbf 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -295,5 +295,7 @@ LIBBPF_0.1.0 {
 		bpf_program__set_sk_lookup;
 		btf__parse;
 		btf__parse_raw;
+		btf__pointer_size;
 		btf__set_fd;
+		btf__set_pointer_size;
 } LIBBPF_0.0.9;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3ba566de821c..5acc18b32606 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5259,7 +5259,7 @@ static int print_arg_pointer(struct trace_seq *s, const char *format, int plen,
 	default:
 		ret = 0;
 		val = eval_num_arg(data, size, event, arg);
-		trace_seq_printf(s, "%p", (void *)val);
+		trace_seq_printf(s, "%p", (void *)(intptr_t)val);
 		break;
 	}
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3f72d8e261f3..bd50cdff08a8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,6 +33,10 @@ OPTIONS
         - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
 	  'param1', 'param2', etc are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index c9bfefc051fb..db420dd75e43 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -39,6 +39,10 @@ report::
 	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
 	  param1 and param2 are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*
@@ -416,6 +420,9 @@ counts for all hardware threads in a core but show the sum counts per
 hardware thread. This is essentially a replacement for the any bit and
 convenient for post processing.
 
+--summary::
+Print summary for interval mode (-I).
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
index 8d624aea1c5e..b2924e3181dc 100644
--- a/tools/perf/bench/synthesize.c
+++ b/tools/perf/bench/synthesize.c
@@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target,
 	init_stats(&event_stats);
 	for (i = 0; i < multi_iterations; i++) {
 		session = perf_session__new(NULL, false, NULL);
-		if (!session)
-			return -ENOMEM;
+		if (IS_ERR(session))
+			return PTR_ERR(session);
 
 		atomic_set(&event_count, 0);
 		gettimeofday(&start, NULL);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f91352f847c0..772f1057647f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2452,7 +2452,7 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
-	OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
+	OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"),
 	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
 		    "Fail if the specified frequency can't be used"),
 	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ece1cddfcd7c..3c74c9c0f3c3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1332,6 +1332,9 @@ int cmd_report(int argc, const char **argv)
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
 
+	if (dump_trace)
+		report.tool.ordered_events = false;
+
 	if (quiet)
 		perf_quiet_option();
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0c7d599fa555..e6fc297cee91 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2584,7 +2584,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->idle_hist || thread->tid == 0) {
-		timehist_update_runtime_stats(tr, t, tprev);
+		if (!cpu_list || test_bit(sample->cpu, cpu_bitmap))
+			timehist_update_runtime_stats(tr, t, tprev);
 
 		if (sched->idle_hist) {
 			struct idle_thread_runtime *itr = (void *)tr;
@@ -2857,6 +2858,9 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	printf("\nIdle stats:\n");
 	for (i = 0; i < idle_max_cpu; ++i) {
+		if (cpu_list && !test_bit(i, cpu_bitmap))
+			continue;
+
 		t = idle_threads[i];
 		if (!t)
 			continue;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 483a28ef4ec4..fddc97cac984 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs)
 {
 	struct evsel *counter;
 
-	if (!stat_config.summary && (read_affinity_counters(rs) < 0))
+	if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0))
 		return;
 
 	evlist__for_each_entry(evsel_list, counter) {
@@ -897,9 +897,9 @@ try_again_reset:
 	if (stat_config.walltime_run_table)
 		stat_config.walltime_run[run_idx] = t1 - t0;
 
-	if (interval) {
+	if (interval && stat_config.summary) {
 		stat_config.interval = 0;
-		stat_config.summary = true;
+		stat_config.stop_read_counter = true;
 		init_stats(&walltime_nsecs_stats);
 		update_stats(&walltime_nsecs_stats, t1 - t0);
 
@@ -1164,6 +1164,8 @@ static struct option stat_options[] = {
 		    "Use with 'percore' event qualifier to show the event "
 		    "counts of one hardware thread by sum up total hardware "
 		    "threads of same physical core"),
+	OPT_BOOLEAN(0, "summary", &stat_config.summary,
+		       "print summary for interval mode"),
 #ifdef HAVE_LIBPFM
 	OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
 		"libpfm4 event selector. use 'perf list' to list available events",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 994c230027bb..7c64134472c7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1746,6 +1746,7 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+#ifdef HAVE_LIBBPF_SUPPORT
 	if (!top.record_opts.no_bpf_event) {
 		top.sb_evlist = evlist__new();
 
@@ -1759,6 +1760,7 @@ int cmd_top(int argc, const char **argv)
 			goto out_delete_evlist;
 		}
 	}
+#endif
 
 	if (perf_evlist__start_sb_thread(top.sb_evlist, target)) {
 		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index fa86c5f997cc..fc9c158bfa13 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -137,7 +137,7 @@ static char *fixregex(char *s)
 		return s;
 
 	/* allocate space for a new string */
-	fixed = (char *) malloc(len + 1);
+	fixed = (char *) malloc(len + esc_count + 1);
 	if (!fixed)
 		return NULL;
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 5d20bf8397f0..cd77e334e577 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		perf_mmap__read_done(&md->core);
 	}
 
-	if (count != expect) {
+	if (count != expect * evlist->core.nr_entries) {
 		pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
 		goto out_delete_evlist;
 	}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7f9f87a470c3..aae0fd9045c1 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
@@ -842,7 +842,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index fc0838a7abc2..23db8acc492d 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -70,6 +70,9 @@ static struct pmu_event pme_test[] = {
 {
 	.metric_expr	= "1/m3",
 	.metric_name	= "M3",
+},
+{
+	.name	= NULL,
 }
 };
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index be9c4c0549bc..a07626f07208 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -3629,8 +3629,8 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
 {
 	int nr_entries = evlist->core.nr_entries;
 
-single_entry:
 	if (perf_evlist__single_entry(evlist)) {
+single_entry: {
 		struct evsel *first = evlist__first(evlist);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
@@ -3638,6 +3638,7 @@ single_entry:
 						env, warn_lost_event,
 						annotation_opts);
 	}
+	}
 
 	if (symbol_conf.event_group) {
 		struct evsel *pos;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 302a14d0aca9..93e063f22be5 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -182,15 +182,15 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 			if (payload & BIT(EV_TLB_ACCESS))
 				decoder->record.type |= ARM_SPE_TLB_ACCESS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_LLC_MISS)))
 				decoder->record.type |= ARM_SPE_LLC_MISS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_LLC_ACCESS)))
 				decoder->record.type |= ARM_SPE_LLC_ACCESS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_REMOTE_ACCESS)))
 				decoder->record.type |= ARM_SPE_REMOTE_ACCESS;
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index c283223fb31f..a2a369e2fbb6 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1344,8 +1344,15 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
 	}
 
-	if (etm->synth_opts.last_branch)
+	if (etm->synth_opts.last_branch) {
 		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+		/*
+		 * We don't use the hardware index, but the sample generation
+		 * code uses the new format branch_stack with this field,
+		 * so the event attributes must indicate that it's present.
+		 */
+		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+	}
 
 	if (etm->synth_opts.instructions) {
 		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 2a8d245351e7..0af4e81c46e2 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -3017,8 +3017,15 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain)
 		attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
-	if (pt->synth_opts.last_branch)
+	if (pt->synth_opts.last_branch) {
 		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+		/*
+		 * We don't use the hardware index, but the sample generation
+		 * code uses the new format branch_stack with this field,
+		 * so the event attributes must indicate that it's present.
+		 */
+		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+	}
 
 	if (pt->synth_opts.instructions) {
 		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 208b813e00ea..85587de027a5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static int is_bpf_image(const char *name)
-{
-	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
-	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
-}
-
 static int machine__process_ksymbol_register(struct machine *machine,
 					     union perf_event *event,
 					     struct perf_sample *sample __maybe_unused)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 1d7210804639..cc0faf8f1321 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map)
 	return name && (strstr(name, "bpf_prog_") == name);
 }
 
+bool __map__is_bpf_image(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE)
+		return true;
+
+	/*
+	 * If PERF_RECORD_KSYMBOL is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && is_bpf_image(name);
+}
+
 bool __map__is_ool(const struct map *map)
 {
 	return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 9e312ae2d656..c2f5d28fe73a 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
 bool __map__is_bpf_prog(const struct map *map);
+bool __map__is_bpf_image(const struct map *map);
 bool __map__is_ool(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
 	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
-	       !__map__is_bpf_prog(map) && !__map__is_ool(map);
+	       !__map__is_bpf_prog(map) && !__map__is_ool(map) &&
+	       !__map__is_bpf_image(map);
 }
 
 bool map__has_symbols(const struct map *map);
@@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name)
 	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
 }
 
+static inline bool is_bpf_image(const char *name)
+{
+	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
+	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
+}
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9f7260e69113..c4d2394e2b2d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -37,6 +37,7 @@
 #include "util/evsel_config.h"
 #include "util/event.h"
 #include "util/pfm.h"
+#include "perf.h"
 
 #define MAX_NAME_LEN 100
 
@@ -1533,19 +1534,23 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	evsel = __add_event(list, &parse_state->idx, &attr, true,
 			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats, NULL);
-	if (evsel) {
-		evsel->unit = info.unit;
-		evsel->scale = info.scale;
-		evsel->per_pkg = info.per_pkg;
-		evsel->snapshot = info.snapshot;
-		evsel->metric_expr = info.metric_expr;
-		evsel->metric_name = info.metric_name;
-		evsel->pmu_name = name ? strdup(name) : NULL;
-		evsel->use_uncore_alias = use_uncore_alias;
-		evsel->percore = config_term_percore(&evsel->config_terms);
-	}
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->pmu_name = name ? strdup(name) : NULL;
+	evsel->use_uncore_alias = use_uncore_alias;
+	evsel->percore = config_term_percore(&evsel->config_terms);
 
-	return evsel ? 0 : -ENOMEM;
+	if (parse_state->fake_pmu)
+		return 0;
+
+	evsel->unit = info.unit;
+	evsel->scale = info.scale;
+	evsel->per_pkg = info.per_pkg;
+	evsel->snapshot = info.snapshot;
+	evsel->metric_expr = info.metric_expr;
+	evsel->metric_name = info.metric_name;
+	return 0;
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
@@ -1794,6 +1799,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 		if (*str == 'u') {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
+			if (!exclude_GH && !perf_guest)
+				eG = 1;
 			eu = 0;
 		} else if (*str == 'k') {
 			if (!exclude)
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index b9fb91fdc5de..645bf4f1859f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	err = parse_events_add_breakpoint(list, &parse_state->idx,
-					(void *) $2, $6, $4);
+					(void *)(uintptr_t) $2, $6, $4);
 	free($6);
 	if (err) {
 		free(list);
@@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	if (parse_events_add_breakpoint(list, &parse_state->idx,
-						(void *) $2, NULL, $4)) {
+						(void *)(uintptr_t) $2, NULL, $4)) {
 		free(list);
 		YYABORT;
 	}
@@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	err = parse_events_add_breakpoint(list, &parse_state->idx,
-					(void *) $2, $4, 0);
+					(void *)(uintptr_t) $2, $4, 0);
 	free($4);
 	if (err) {
 		free(list);
@@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	if (parse_events_add_breakpoint(list, &parse_state->idx,
-						(void *) $2, NULL, 0)) {
+						(void *)(uintptr_t) $2, NULL, 0)) {
 		free(list);
 		YYABORT;
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ffbc9d35a383..7a5f03764702 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -87,7 +87,7 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 		session->decomp_last = decomp;
 	}
 
-	pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size);
+	pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size);
 
 	return 0;
 }
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 57d0706e1330..493ec372fdec 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -117,7 +117,7 @@ static void aggr_printout(struct perf_stat_config *config,
 				cpu_map__id_to_die(id),
 				config->csv_output ? 0 : -3,
 				cpu_map__id_to_cpu(id), config->csv_sep);
-		} else {
+		} else if (id > -1) {
 			fprintf(config->output, "CPU%*d%s",
 				config->csv_output ? 0 : -7,
 				evsel__cpus(evsel)->map[id],
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index f8778cffd941..aa3bed48511b 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -113,6 +113,7 @@ struct perf_stat_config {
 	bool			 summary;
 	bool			 metric_no_group;
 	bool			 metric_no_merge;
+	bool			 stop_read_counter;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1f5fcb828a21..5151a8c0b791 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -663,6 +663,7 @@ static bool symbol__is_idle(const char *name)
 		"exit_idle",
 		"mwait_idle",
 		"mwait_idle_with_hints",
+		"mwait_idle_with_hints.constprop.0",
 		"poll_idle",
 		"ppc64_runlatch_off",
 		"pseries_dedicated_idle_sleep",
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index d2202392ffdb..48dd2b018c47 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -99,7 +99,7 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
-			pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n",
+			pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n",
 			       src_size, output.size, dst_size, ZSTD_getErrorName(ret));
 			break;
 		}
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 1bb204cee853..9a0946ddb705 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -6,7 +6,6 @@ test_lpm_map
 test_tag
 FEATURE-DUMP.libbpf
 fixdep
-test_align
 test_dev_cgroup
 /test_progs*
 test_tcpbpf_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a83b5827532f..fc946b7ac288 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -32,7 +32,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread
 
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
+	test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 7afa4160416f..284d5921c345 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -159,15 +159,15 @@ void test_bpf_obj_id(void)
 		/* Check getting link info */
 		info_len = sizeof(struct bpf_link_info) * 2;
 		bzero(&link_infos[i], info_len);
-		link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name;
+		link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name);
 		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
 		err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]),
 					     &link_infos[i], &info_len);
 		if (CHECK(err ||
 			  link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
 			  link_infos[i].prog_id != prog_infos[i].id ||
-			  link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name ||
-			  strcmp((char *)link_infos[i].raw_tracepoint.tp_name,
+			  link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) ||
+			  strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
 				 "sys_enter") ||
 			  info_len != sizeof(struct bpf_link_info),
 			  "get-link-info(fd)",
@@ -178,7 +178,7 @@ void test_bpf_obj_id(void)
 			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
 			  link_infos[i].id,
 			  link_infos[i].prog_id, prog_infos[i].id,
-			  (char *)link_infos[i].raw_tracepoint.tp_name,
+			  (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
 			  "sys_enter"))
 			goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index cb33a7ee4e04..39fb81d9daeb 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -12,15 +12,16 @@ void btf_dump_printf(void *ctx, const char *fmt, va_list args)
 static struct btf_dump_test_case {
 	const char *name;
 	const char *file;
+	bool known_ptr_sz;
 	struct btf_dump_opts opts;
 } btf_dump_test_cases[] = {
-	{"btf_dump: syntax", "btf_dump_test_case_syntax", {}},
-	{"btf_dump: ordering", "btf_dump_test_case_ordering", {}},
-	{"btf_dump: padding", "btf_dump_test_case_padding", {}},
-	{"btf_dump: packing", "btf_dump_test_case_packing", {}},
-	{"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}},
-	{"btf_dump: multidim", "btf_dump_test_case_multidim", {}},
-	{"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}},
+	{"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}},
+	{"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}},
+	{"btf_dump: padding", "btf_dump_test_case_padding", true, {}},
+	{"btf_dump: packing", "btf_dump_test_case_packing", true, {}},
+	{"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}},
+	{"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}},
+	{"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}},
 };
 
 static int btf_dump_all_types(const struct btf *btf,
@@ -62,6 +63,18 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 		goto done;
 	}
 
+	/* tests with t->known_ptr_sz have no "long" or "unsigned long" type,
+	 * so it's impossible to determine correct pointer size; but if they
+	 * do, it should be 8 regardless of host architecture, becaues BPF
+	 * target is always 64-bit
+	 */
+	if (!t->known_ptr_sz) {
+		btf__set_pointer_size(btf, 8);
+	} else {
+		CHECK(btf__pointer_size(btf) != 8, "ptr_sz", "exp %d, got %zu\n",
+		      8, btf__pointer_size(btf));
+	}
+
 	snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file);
 	fd = mkstemp(out_file);
 	if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) {
diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c
index b093787e9448..1931a158510e 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_extern.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c
@@ -159,8 +159,8 @@ void test_core_extern(void)
 		exp = (uint64_t *)&t->data;
 		for (j = 0; j < n; j++) {
 			CHECK(got[j] != exp[j], "check_res",
-			      "result #%d: expected %lx, but got %lx\n",
-			       j, exp[j], got[j]);
+			      "result #%d: expected %llx, but got %llx\n",
+			       j, (__u64)exp[j], (__u64)got[j]);
 		}
 cleanup:
 		test_core_extern__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 084ed26a7d78..a54eafc5e4b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -237,8 +237,8 @@
 		.union_sz = sizeof(((type *)0)->union_field),		\
 		.arr_sz = sizeof(((type *)0)->arr_field),		\
 		.arr_elem_sz = sizeof(((type *)0)->arr_field[0]),	\
-		.ptr_sz = sizeof(((type *)0)->ptr_field),		\
-		.enum_sz = sizeof(((type *)0)->enum_field),	\
+		.ptr_sz = 8, /* always 8-byte pointer for BPF */	\
+		.enum_sz = sizeof(((type *)0)->enum_field),		\
 	}
 
 #define SIZE_CASE(name) {						\
@@ -432,20 +432,20 @@ static struct core_reloc_test_case test_cases[] = {
 		.sb4 = -1,
 		.sb20 = -0x17654321,
 		.u32 = 0xBEEF,
-		.s32 = -0x3FEDCBA987654321,
+		.s32 = -0x3FEDCBA987654321LL,
 	}),
 	BITFIELDS_CASE(bitfields___bitfield_vs_int, {
-		.ub1 = 0xFEDCBA9876543210,
+		.ub1 = 0xFEDCBA9876543210LL,
 		.ub2 = 0xA6,
-		.ub7 = -0x7EDCBA987654321,
-		.sb4 = -0x6123456789ABCDE,
-		.sb20 = 0xD00D,
+		.ub7 = -0x7EDCBA987654321LL,
+		.sb4 = -0x6123456789ABCDELL,
+		.sb20 = 0xD00DLL,
 		.u32 = -0x76543,
-		.s32 = 0x0ADEADBEEFBADB0B,
+		.s32 = 0x0ADEADBEEFBADB0BLL,
 	}),
 	BITFIELDS_CASE(bitfields___just_big_enough, {
-		.ub1 = 0xF,
-		.ub2 = 0x0812345678FEDCBA,
+		.ub1 = 0xFLL,
+		.ub2 = 0x0812345678FEDCBALL,
 	}),
 	BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield),
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index a895bfed55db..197d0d217b56 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -16,7 +16,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 	__u32 duration = 0, retval;
 	struct bpf_map *data_map;
 	const int zero = 0;
-	u64 *result = NULL;
+	__u64 *result = NULL;
 
 	err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
 			    &pkt_obj, &pkt_fd);
@@ -29,7 +29,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
+	result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64));
 	if (CHECK(!link || !prog || !result, "alloc_memory",
 		  "failed to alloc memory"))
 		goto close_prog;
@@ -72,7 +72,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 		goto close_prog;
 
 	for (i = 0; i < prog_cnt; i++)
-		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n",
+		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n",
 			  result[i]))
 			goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index f11f187990e9..cd6dc80edf18 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -591,7 +591,7 @@ void test_flow_dissector(void)
 		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
 			   err || tattr.retval != 1,
 			   tests[i].name,
-			   "err %d errno %d retval %d duration %d size %u/%lu\n",
+			   "err %d errno %d retval %d duration %d size %u/%zu\n",
 			   err, errno, tattr.retval, tattr.duration,
 			   tattr.data_size_out, sizeof(flow_keys));
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index e3cb62b0a110..9efa7e50eab2 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -5,7 +5,7 @@
 static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 {
 	int i, err, map_fd;
-	uint64_t num;
+	__u64 num;
 
 	map_fd = bpf_find_map(__func__, obj, "result_number");
 	if (CHECK_FAIL(map_fd < 0))
@@ -14,7 +14,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 	struct {
 		char *name;
 		uint32_t key;
-		uint64_t num;
+		__u64 num;
 	} tests[] = {
 		{ "relocate .bss reference",     0, 0 },
 		{ "relocate .data reference",    1, 42 },
@@ -32,7 +32,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
 		err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num);
 		CHECK(err || num != tests[i].num, tests[i].name,
-		      "err %d result %lx expected %lx\n",
+		      "err %d result %llx expected %llx\n",
 		      err, num, tests[i].num);
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 43d0b5578f46..9c3c5c0f068f 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -21,7 +21,7 @@ void test_mmap(void)
 	const long page_size = sysconf(_SC_PAGE_SIZE);
 	int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd;
 	struct bpf_map *data_map, *bss_map;
-	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
+	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp0, *tmp1, *tmp2;
 	struct test_mmap__bss *bss_data;
 	struct bpf_map_info map_info;
 	__u32 map_info_sz = sizeof(map_info);
@@ -183,16 +183,23 @@ void test_mmap(void)
 
 	/* check some more advanced mmap() manipulations */
 
+	tmp0 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_ANONYMOUS,
+			  -1, 0);
+	if (CHECK(tmp0 == MAP_FAILED, "adv_mmap0", "errno %d\n", errno))
+		goto cleanup;
+
 	/* map all but last page: pages 1-3 mapped */
-	tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED,
+	tmp1 = mmap(tmp0, 3 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
 			  data_map_fd, 0);
-	if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno))
+	if (CHECK(tmp0 != tmp1, "adv_mmap1", "tmp0: %p, tmp1: %p\n", tmp0, tmp1)) {
+		munmap(tmp0, 4 * page_size);
 		goto cleanup;
+	}
 
 	/* unmap second page: pages 1, 3 mapped */
 	err = munmap(tmp1 + page_size, page_size);
 	if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) {
-		munmap(tmp1, map_sz);
+		munmap(tmp1, 4 * page_size);
 		goto cleanup;
 	}
 
@@ -201,7 +208,7 @@ void test_mmap(void)
 		    MAP_SHARED | MAP_FIXED, data_map_fd, 0);
 	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) {
 		munmap(tmp1, page_size);
-		munmap(tmp1 + 2*page_size, page_size);
+		munmap(tmp1 + 2*page_size, 2 * page_size);
 		goto cleanup;
 	}
 	CHECK(tmp1 + page_size != tmp2, "adv_mmap4",
@@ -211,7 +218,7 @@ void test_mmap(void)
 	tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
 		    data_map_fd, 0);
 	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) {
-		munmap(tmp1, 3 * page_size); /* unmap page 1 */
+		munmap(tmp1, 4 * page_size); /* unmap page 1 */
 		goto cleanup;
 	}
 	CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2);
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index dde2b7ae7bc9..935a294f049a 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -28,7 +28,7 @@ void test_prog_run_xattr(void)
 	      "err %d errno %d retval %d\n", err, errno, tattr.retval);
 
 	CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out",
-	      "incorrect output size, want %lu have %u\n",
+	      "incorrect output size, want %zu have %u\n",
 	      sizeof(pkt_v4), tattr.data_size_out);
 
 	CHECK_ATTR(buf[5] != 0, "overflow",
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index c571584c00f5..9ff0412e1fd3 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -309,6 +309,7 @@ static void v4_to_v6(struct sockaddr_storage *ss)
 	v6->sin6_addr.s6_addr[10] = 0xff;
 	v6->sin6_addr.s6_addr[11] = 0xff;
 	memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4);
+	memset(&v6->sin6_addr.s6_addr[0], 0, 10);
 }
 
 static int udp_recv_send(int server_fd)
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index 25de86af2d03..fafeddaad6a9 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -81,7 +81,7 @@ void test_skb_ctx(void)
 
 	CHECK_ATTR(tattr.ctx_size_out != sizeof(skb),
 		   "ctx_size_out",
-		   "incorrect output size, want %lu have %u\n",
+		   "incorrect output size, want %zu have %u\n",
 		   sizeof(skb), tattr.ctx_size_out);
 
 	for (i = 0; i < 5; i++)
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 25b068591e9a..193002b14d7f 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -19,7 +19,7 @@ static int libbpf_debug_print(enum libbpf_print_level level,
 	log_buf = va_arg(args, char *);
 	if (!log_buf)
 		goto out;
-	if (strstr(log_buf, err_str) == 0)
+	if (err_str && strstr(log_buf, err_str) == 0)
 		found = true;
 out:
 	printf(format, log_buf);
diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c
index c75525eab02c..dd324b4933db 100644
--- a/tools/testing/selftests/bpf/prog_tests/varlen.c
+++ b/tools/testing/selftests/bpf/prog_tests/varlen.c
@@ -44,25 +44,25 @@ void test_varlen(void)
 	CHECK_VAL(bss->payload1_len2, size2);
 	CHECK_VAL(bss->total1, size1 + size2);
 	CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check",
-	      "doesn't match!");
+	      "doesn't match!\n");
 
 	CHECK_VAL(data->payload2_len1, size1);
 	CHECK_VAL(data->payload2_len2, size2);
 	CHECK_VAL(data->total2, size1 + size2);
 	CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check",
-	      "doesn't match!");
+	      "doesn't match!\n");
 
 	CHECK_VAL(data->payload3_len1, size1);
 	CHECK_VAL(data->payload3_len2, size2);
 	CHECK_VAL(data->total3, size1 + size2);
 	CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check",
-	      "doesn't match!");
+	      "doesn't match!\n");
 
 	CHECK_VAL(data->payload4_len1, size1);
 	CHECK_VAL(data->payload4_len2, size2);
 	CHECK_VAL(data->total4, size1 + size2);
 	CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check",
-	      "doesn't match!");
+	      "doesn't match!\n");
 cleanup:
 	test_varlen__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 34d84717c946..69139ed66216 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -1,5 +1,10 @@
 #include <stdint.h>
 #include <stdbool.h>
+
+void preserce_ptr_sz_fn(long x) {}
+
+#define __bpf_aligned __attribute__((aligned(8)))
+
 /*
  * KERNEL
  */
@@ -444,51 +449,51 @@ struct core_reloc_primitives {
 	char a;
 	int b;
 	enum core_reloc_primitives_enum c;
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___diff_enum_def {
 	char a;
 	int b;
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 	enum {
 		X = 100,
 		Y = 200,
-	} c; /* inline enum def with differing set of values */
+	} c __bpf_aligned; /* inline enum def with differing set of values */
 };
 
 struct core_reloc_primitives___diff_func_proto {
-	void (*f)(int); /* incompatible function prototype */
-	void *d;
-	enum core_reloc_primitives_enum c;
+	void (*f)(int) __bpf_aligned; /* incompatible function prototype */
+	void *d __bpf_aligned;
+	enum core_reloc_primitives_enum c __bpf_aligned;
 	int b;
 	char a;
 };
 
 struct core_reloc_primitives___diff_ptr_type {
-	const char * const d; /* different pointee type + modifiers */
-	char a;
+	const char * const d __bpf_aligned; /* different pointee type + modifiers */
+	char a __bpf_aligned;
 	int b;
 	enum core_reloc_primitives_enum c;
-	int (*f)(const char *);
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_enum {
 	char a[1];
 	int b;
 	int c; /* int instead of enum */
-	void *d;
-	int (*f)(const char *);
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_int {
 	char a[1];
-	int *b; /* ptr instead of int */
-	enum core_reloc_primitives_enum c;
-	void *d;
-	int (*f)(const char *);
+	int *b __bpf_aligned; /* ptr instead of int */
+	enum core_reloc_primitives_enum c __bpf_aligned;
+	void *d __bpf_aligned;
+	int (*f)(const char *) __bpf_aligned;
 };
 
 struct core_reloc_primitives___err_non_ptr {
@@ -496,7 +501,7 @@ struct core_reloc_primitives___err_non_ptr {
 	int b;
 	enum core_reloc_primitives_enum c;
 	int d; /* int instead of ptr */
-	int (*f)(const char *);
+	int (*f)(const char *) __bpf_aligned;
 };
 
 /*
@@ -507,7 +512,7 @@ struct core_reloc_mods_output {
 };
 
 typedef const int int_t;
-typedef const char *char_ptr_t;
+typedef const char *char_ptr_t __bpf_aligned;
 typedef const int arr_t[7];
 
 struct core_reloc_mods_substruct {
@@ -523,9 +528,9 @@ typedef struct {
 struct core_reloc_mods {
 	int a;
 	int_t b;
-	char *c;
+	char *c __bpf_aligned;
 	char_ptr_t d;
-	int e[3];
+	int e[3] __bpf_aligned;
 	arr_t f;
 	struct core_reloc_mods_substruct g;
 	core_reloc_mods_substruct_t h;
@@ -535,9 +540,9 @@ struct core_reloc_mods {
 struct core_reloc_mods___mod_swap {
 	int b;
 	int_t a;
-	char *d;
+	char *d __bpf_aligned;
 	char_ptr_t c;
-	int f[3];
+	int f[3] __bpf_aligned;
 	arr_t e;
 	struct {
 		int y;
@@ -555,7 +560,7 @@ typedef arr1_t arr2_t;
 typedef arr2_t arr3_t;
 typedef arr3_t arr4_t;
 
-typedef const char * const volatile fancy_char_ptr_t;
+typedef const char * const volatile fancy_char_ptr_t __bpf_aligned;
 
 typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt;
 
@@ -567,7 +572,7 @@ struct core_reloc_mods___typedefs {
 	arr4_t e;
 	fancy_char_ptr_t d;
 	fancy_char_ptr_t c;
-	int3_t b;
+	int3_t b __bpf_aligned;
 	int3_t a;
 };
 
@@ -739,19 +744,19 @@ struct core_reloc_bitfields___bit_sz_change {
 	int8_t		sb4: 1;		/*  4 ->  1 */
 	int32_t		sb20: 30;	/* 20 -> 30 */
 	/* non-bitfields */
-	uint16_t	u32;		/* 32 -> 16 */
-	int64_t		s32;		/* 32 -> 64 */
+	uint16_t	u32;			/* 32 -> 16 */
+	int64_t		s32 __bpf_aligned;	/* 32 -> 64 */
 };
 
 /* turn bitfield into non-bitfield and vice versa */
 struct core_reloc_bitfields___bitfield_vs_int {
 	uint64_t	ub1;		/*  3 -> 64 non-bitfield */
 	uint8_t		ub2;		/* 20 ->  8 non-bitfield */
-	int64_t		ub7;		/*  7 -> 64 non-bitfield signed */
-	int64_t		sb4;		/*  4 -> 64 non-bitfield signed */
-	uint64_t	sb20;		/* 20 -> 16 non-bitfield unsigned */
-	int32_t		u32: 20;	/* 32 non-bitfield -> 20 bitfield */
-	uint64_t	s32: 60;	/* 32 non-bitfield -> 60 bitfield */
+	int64_t		ub7 __bpf_aligned;	/*  7 -> 64 non-bitfield signed */
+	int64_t		sb4 __bpf_aligned;	/*  4 -> 64 non-bitfield signed */
+	uint64_t	sb20 __bpf_aligned;	/* 20 -> 16 non-bitfield unsigned */
+	int32_t		u32: 20;		/* 32 non-bitfield -> 20 bitfield */
+	uint64_t	s32: 60 __bpf_aligned;	/* 32 non-bitfield -> 60 bitfield */
 };
 
 struct core_reloc_bitfields___just_big_enough {
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 1f1966e86e9f..3e6912e4df3d 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -54,6 +54,7 @@ SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
 	char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+	struct bpf_sock_ops *reuse = skops;
 	struct tcphdr *thdr;
 	int good_call_rv = 0;
 	int bad_call_rv = 0;
@@ -62,6 +63,46 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 	int v = 0;
 	int op;
 
+	/* Test reading fields in bpf_sock_ops using single register */
+	asm volatile (
+		"%[reuse] = *(u32 *)(%[reuse] +96)"
+		: [reuse] "+r"(reuse)
+		:);
+
+	asm volatile (
+		"%[op] = *(u32 *)(%[skops] +96)"
+		: [op] "+r"(op)
+		: [skops] "r"(skops)
+		:);
+
+	asm volatile (
+		"r9 = %[skops];\n"
+		"r8 = *(u32 *)(r9 +164);\n"
+		"*(u32 *)(r9 +164) = r8;\n"
+		:: [skops] "r"(skops)
+		: "r9", "r8");
+
+	asm volatile (
+		"r1 = %[skops];\n"
+		"r1 = *(u64 *)(r1 +184);\n"
+		"if r1 == 0 goto +1;\n"
+		"r1 = *(u32 *)(r1 +4);\n"
+		:: [skops] "r"(skops):"r1");
+
+	asm volatile (
+		"r9 = %[skops];\n"
+		"r9 = *(u64 *)(r9 +184);\n"
+		"if r9 == 0 goto +1;\n"
+		"r9 = *(u32 *)(r9 +4);\n"
+		:: [skops] "r"(skops):"r9");
+
+	asm volatile (
+		"r1 = %[skops];\n"
+		"r2 = *(u64 *)(r1 +184);\n"
+		"if r2 == 0 goto +1;\n"
+		"r2 = *(u32 *)(r2 +4);\n"
+		:: [skops] "r"(skops):"r1", "r2");
+
 	op = (int) skops->op;
 
 	update_event_map(op);
diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c
index cd4b72c55dfe..913acdffd90f 100644
--- a/tools/testing/selftests/bpf/progs/test_varlen.c
+++ b/tools/testing/selftests/bpf/progs/test_varlen.c
@@ -15,9 +15,9 @@ int test_pid = 0;
 bool capture = false;
 
 /* .bss */
-long payload1_len1 = 0;
-long payload1_len2 = 0;
-long total1 = 0;
+__u64 payload1_len1 = 0;
+__u64 payload1_len2 = 0;
+__u64 total1 = 0;
 char payload1[MAX_LEN + MAX_LEN] = {};
 
 /* .data */
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 305fae8f80a9..c75fc6447186 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3883,7 +3883,7 @@ static int test_big_btf_info(unsigned int test_num)
 	info_garbage.garbage = 0;
 	err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
 	if (CHECK(err || info_len != sizeof(*info),
-		  "err:%d errno:%d info_len:%u sizeof(*info):%lu",
+		  "err:%d errno:%d info_len:%u sizeof(*info):%zu",
 		  err, errno, info_len, sizeof(*info))) {
 		err = -1;
 		goto done;
@@ -4094,7 +4094,7 @@ static int do_test_get_info(unsigned int test_num)
 	if (CHECK(err || !info.id || info_len != sizeof(info) ||
 		  info.btf_size != raw_btf_size ||
 		  (ret = memcmp(raw_btf, user_btf, expected_nbytes)),
-		  "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
+		  "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%zu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
 		  err, errno, info.id, info_len, sizeof(info),
 		  raw_btf_size, info.btf_size, expected_nbytes, ret)) {
 		err = -1;
@@ -4730,7 +4730,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 
 		nexpected_line = snprintf(expected_line, line_size,
 					  "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
-					  "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
+					  "{%llu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
 					  "%u,0x%x,[[%d,%d],[%d,%d]]}\n",
 					  percpu_map ? "\tcpu" : "",
 					  percpu_map ? cpu : next_key,
@@ -4738,7 +4738,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 					  v->unused_bits2a,
 					  v->bits28,
 					  v->unused_bits2b,
-					  v->ui64,
+					  (__u64)v->ui64,
 					  v->ui8a[0], v->ui8a[1],
 					  v->ui8a[2], v->ui8a[3],
 					  v->ui8a[4], v->ui8a[5],
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 754cf611723e..0d92ebcb335d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1274,6 +1274,8 @@ static void __run_parallel(unsigned int tasks,
 	pid_t pid[tasks];
 	int i;
 
+	fflush(stdout);
+
 	for (i = 0; i < tasks; i++) {
 		pid[i] = fork();
 		if (pid[i] == 0) {
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index b1e4dadacd9b..22943b58d752 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -618,7 +618,9 @@ int cd_flavor_subdir(const char *exec_name)
 	if (!flavor)
 		return 0;
 	flavor++;
-	fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor);
+	if (env.verbosity > VERBOSE_NONE)
+		fprintf(stdout,	"Switching to flavor '%s' subdirectory...\n", flavor);
+
 	return chdir(flavor);
 }
 
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 6e09bf738473..dbb820dde138 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -135,6 +135,11 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
+static inline void *u64_to_ptr(__u64 ptr)
+{
+	return (void *) (unsigned long) ptr;
+}
+
 int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
 int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index 8162c58a1234..b8d14f9db5f9 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -40,11 +40,11 @@ static void guest_code(void)
 
 	/* Single step test, covers 2 basic instructions and 2 emulated */
 	asm volatile("ss_start: "
-		     "xor %%rax,%%rax\n\t"
+		     "xor %%eax,%%eax\n\t"
 		     "cpuid\n\t"
 		     "movl $0x1a0,%%ecx\n\t"
 		     "rdmsr\n\t"
-		     : : : "rax", "ecx");
+		     : : : "eax", "ebx", "ecx", "edx");
 
 	/* DR6.BD test */
 	asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax");
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index 18c5de53558a..bf361f30d6ef 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -180,6 +180,8 @@ setup()
 			;;
 		r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
 		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
+		       ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
+		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
 
 		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
 		       ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index d3e0809ab368..431296c0f91c 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -2,13 +2,18 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 # This tests basic flowtable functionality.
-# Creates following topology:
+# Creates following default topology:
 #
 # Originator (MTU 9000) <-Router1-> MTU 1500 <-Router2-> Responder (MTU 2000)
 # Router1 is the one doing flow offloading, Router2 has no special
 # purpose other than having a link that is smaller than either Originator
 # and responder, i.e. TCPMSS announced values are too large and will still
 # result in fragmentation and/or PMTU discovery.
+#
+# You can check with different Orgininator/Link/Responder MTU eg:
+# nft_flowtable.sh -o8000 -l1500 -r2000
+#
+
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -21,29 +26,17 @@ ns2out=""
 
 log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
 
-nft --version > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without nft tool"
-	exit $ksft_skip
-fi
-
-ip -Version > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without ip tool"
-	exit $ksft_skip
-fi
-
-which nc > /dev/null 2>&1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without nc (netcat)"
-	exit $ksft_skip
-fi
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
 
-ip netns add nsr1
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace"
-	exit $ksft_skip
-fi
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add nsr1" "create net namespace"
 
 ip netns add ns1
 ip netns add ns2
@@ -89,11 +82,41 @@ ip -net nsr2 addr add dead:2::1/64 dev veth1
 # ns2 is going via nsr2 with a smaller mtu, so that TCPMSS announced by both peers
 # is NOT the lowest link mtu.
 
-ip -net nsr1 link set veth0 mtu 9000
-ip -net ns1 link set eth0 mtu 9000
+omtu=9000
+lmtu=1500
+rmtu=2000
+
+usage(){
+	echo "nft_flowtable.sh [OPTIONS]"
+	echo
+	echo "MTU options"
+	echo "   -o originator"
+	echo "   -l link"
+	echo "   -r responder"
+	exit 1
+}
+
+while getopts "o:l:r:" o
+do
+	case $o in
+		o) omtu=$OPTARG;;
+		l) lmtu=$OPTARG;;
+		r) rmtu=$OPTARG;;
+		*) usage;;
+	esac
+done
+
+if ! ip -net nsr1 link set veth0 mtu $omtu; then
+	exit 1
+fi
+
+ip -net ns1 link set eth0 mtu $omtu
+
+if ! ip -net nsr2 link set veth1 mtu $rmtu; then
+	exit 1
+fi
 
-ip -net nsr2 link set veth1 mtu 2000
-ip -net ns2 link set eth0 mtu 2000
+ip -net ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
 # these addresses are not used for connections.
@@ -113,7 +136,10 @@ for i in 1 2; do
   ip -net ns$i route add default via 10.0.$i.1
   ip -net ns$i addr add dead:$i::99/64 dev eth0
   ip -net ns$i route add default via dead:$i::1
-  ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null
+  if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
+	echo "ERROR: Check Originator/Responder values (problem during address addition)"
+	exit 1
+  fi
 
   # don't set ip DF bit for first two tests
   ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
@@ -147,7 +173,7 @@ table inet filter {
       # as PMTUd is off.
       # This rule is deleted for the last test, when we expect PMTUd
       # to kick in and ensure all packets meet mtu requirements.
-      meta length gt 1500 accept comment something-to-grep-for
+      meta length gt $lmtu accept comment something-to-grep-for
 
       # next line blocks connection w.o. working offload.
       # we only do this for reverse dir, because we expect packets to
@@ -171,15 +197,13 @@ if [ $? -ne 0 ]; then
 fi
 
 # test basic connectivity
-ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null
-if [ $? -ne 0 ];then
+if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
   echo "ERROR: ns1 cannot reach ns2" 1>&2
   bash
   exit 1
 fi
 
-ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null
-if [ $? -ne 0 ];then
+if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
   echo "ERROR: ns2 cannot reach ns1" 1>&2
   exit 1
 fi
@@ -196,7 +220,6 @@ ns2out=$(mktemp)
 make_file()
 {
 	name=$1
-	who=$2
 
 	SIZE=$((RANDOM % (1024 * 8)))
 	TSIZE=$((SIZE * 1024))
@@ -215,8 +238,7 @@ check_transfer()
 	out=$2
 	what=$3
 
-	cmp "$in" "$out" > /dev/null 2>&1
-	if [ $? -ne 0 ] ;then
+	if ! cmp "$in" "$out" > /dev/null 2>&1; then
 		echo "FAIL: file mismatch for $what" 1>&2
 		ls -l "$in"
 		ls -l "$out"
@@ -243,17 +265,21 @@ test_tcp_forwarding_ip()
 
 	sleep 3
 
-	kill $lpid
-	kill $cpid
+	if ps -p $lpid > /dev/null;then
+		kill $lpid
+	fi
+
+	if ps -p $cpid > /dev/null;then
+		kill $cpid
+	fi
+
 	wait
 
-	check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"
-	if [ $? -ne 0 ];then
+	if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 	fi
 
-	check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"
-	if [ $? -ne 0 ];then
+	if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 	fi
 
@@ -282,13 +308,12 @@ test_tcp_forwarding_nat()
 	return $lret
 }
 
-make_file "$ns1in" "ns1"
-make_file "$ns2in" "ns2"
+make_file "$ns1in"
+make_file "$ns2in"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
-test_tcp_forwarding ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -319,9 +344,7 @@ table ip nat {
 }
 EOF
 
-test_tcp_forwarding_nat ns1 ns2
-
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding_nat ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
@@ -333,8 +356,7 @@ fi
 # Same as second test, but with PMTU discovery enabled.
 handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
 
-ip netns exec nsr1 nft delete rule inet filter forward $handle
-if [ $? -ne 0 ] ;then
+if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then
 	echo "FAIL: Could not delete large-packet accept rule"
 	exit 1
 fi
@@ -342,8 +364,7 @@ fi
 ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 
-test_tcp_forwarding_nat ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding_nat ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
@@ -389,8 +410,7 @@ ip -net ns2 route del 192.168.10.1 via 10.0.2.1
 ip -net ns2 route add default via 10.0.2.1
 ip -net ns2 route add default via dead:2::1
 
-test_tcp_forwarding ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding ns1 ns2; then
 	echo "PASS: ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 91c775c23c66..aac4a59f9e28 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,6 +2,7 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
+prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 250ce172e0da..defe488d6bf1 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot \
 		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
 
@@ -14,6 +14,8 @@ include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
 
+$(OUTPUT)/prot_sao: ../utils.c
+
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
new file mode 100644
index 000000000000..e0cf8ebbf8cd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2016, Michael Ellerman, IBM Corp.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#include <asm/cputable.h>
+
+#include "utils.h"
+
+#define SIZE (64 * 1024)
+
+int test_prot_sao(void)
+{
+	char *p;
+
+	/* SAO was introduced in 2.06 and removed in 3.1 */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+	/*
+	 * Ensure we can ask for PROT_SAO.
+	 * We can't really verify that it does the right thing, but at least we
+	 * confirm the kernel will accept it.
+	 */
+	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Write to the mapping, to at least cause a fault */
+	memset(p, 0xaa, SIZE);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_prot_sao, "prot-sao");
+}
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 7656c7ce79d9..0e73a16874c4 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 
 TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
 
+TEST_FILES := settings
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/timers/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index c41f24b517f4..65c141ebfbbd 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -462,6 +462,17 @@ static int test_vsys_x(void)
 	return 0;
 }
 
+/*
+ * Debuggers expect ptrace() to be able to peek at the vsyscall page.
+ * Use process_vm_readv() as a proxy for ptrace() to test this.  We
+ * want it to work in the vsyscall=emulate case and to fail in the
+ * vsyscall=xonly case.
+ *
+ * It's worth noting that this ABI is a bit nutty.  write(2) can't
+ * read from the vsyscall page on any kernel version or mode.  The
+ * fact that ptrace() ever worked was a nice courtesy of old kernels,
+ * but the code to support it is fairly gross.
+ */
 static int test_process_vm_readv(void)
 {
 #ifdef __x86_64__
@@ -477,8 +488,12 @@ static int test_process_vm_readv(void)
 	remote.iov_len = 4096;
 	ret = process_vm_readv(getpid(), &local, 1, &remote, 1, 0);
 	if (ret != 4096) {
-		printf("[OK]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", ret, errno);
-		return 0;
+		/*
+		 * We expect process_vm_readv() to work if and only if the
+		 * vsyscall page is readable.
+		 */
+		printf("[%s]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", vsyscall_map_r ? "FAIL" : "OK", ret, errno);
+		return vsyscall_map_r ? 1 : 0;
 	}
 
 	if (vsyscall_map_r) {
@@ -488,6 +503,9 @@ static int test_process_vm_readv(void)
 			printf("[FAIL]\tIt worked but returned incorrect data\n");
 			return 1;
 		}
+	} else {
+		printf("[FAIL]\tprocess_rm_readv() succeeded, but it should have failed in this configuration\n");
+		return 1;
 	}
 #endif
 
diff --git a/tools/usb/Build b/tools/usb/Build
new file mode 100644
index 000000000000..2ad6f9745816
--- /dev/null
+++ b/tools/usb/Build
@@ -0,0 +1,2 @@
+testusb-y += testusb.o
+ffs-test-y += ffs-test.o
diff --git a/tools/usb/Makefile b/tools/usb/Makefile
index 01d758d73b6d..1b128e551b2e 100644
--- a/tools/usb/Makefile
+++ b/tools/usb/Makefile
@@ -1,14 +1,51 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for USB tools
+include ../scripts/Makefile.include
 
-PTHREAD_LIBS = -lpthread
-WARNINGS = -Wall -Wextra
-CFLAGS = $(WARNINGS) -g -I../include
-LDFLAGS = $(PTHREAD_LIBS)
+bindir ?= /usr/bin
 
-all: testusb ffs-test
-%: %.c
-	$(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+override CFLAGS += -O2 -Wall -Wextra -g -D_GNU_SOURCE -I$(OUTPUT)include -I$(srctree)/tools/include
+override LDFLAGS += -lpthread
+
+ALL_TARGETS := testusb ffs-test
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+TESTUSB_IN := $(OUTPUT)testusb-in.o
+$(TESTUSB_IN): FORCE
+	$(Q)$(MAKE) $(build)=testusb
+$(OUTPUT)testusb: $(TESTUSB_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
+
+FFS_TEST_IN := $(OUTPUT)ffs-test-in.o
+$(FFS_TEST_IN): FORCE
+	$(Q)$(MAKE) $(build)=ffs-test
+$(OUTPUT)ffs-test: $(FFS_TEST_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
 
 clean:
-	$(RM) testusb ffs-test
+	rm -f $(ALL_PROGRAMS)
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.o.cmd' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 737666db02de..cf88233b819a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -482,7 +482,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
-	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end);
+	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
+					     range->flags);
 	need_tlb_flush |= kvm->tlbs_dirty;
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
@@ -4331,7 +4332,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			       struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
@@ -4348,17 +4349,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+		       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);