Orangefs: merge to v4.5

Merge tag 'v4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into current

Linux 4.5

401 files changed, 17095 insertions, 4220 deletions

diff --git a/Documentation/ABI/testing/configfs-iio b/Documentation/ABI/testing/configfs-iio
new file mode 100644
index 000000000000..2483756fccf5
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-iio
@@ -0,0 +1,21 @@
+What:		/config/iio
+Date:		October 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This represents Industrial IO configuration entry point
+		directory. It contains sub-groups corresponding to IIO
+		objects.
+
+What:		/config/iio/triggers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		Industrial IO software triggers directory.
+
+What:		/config/iio/triggers/hrtimers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		High resolution timers directory. Creating a directory here
+		will result in creating a hrtimer trigger in the IIO subsystem.
diff --git a/Documentation/ABI/testing/configfs-rdma_cm b/Documentation/ABI/testing/configfs-rdma_cm
new file mode 100644
index 000000000000..5c389aaf5291
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-rdma_cm
@@ -0,0 +1,22 @@
+What: 		/config/rdma_cm
+Date: 		November 29, 2015
+KernelVersion:  4.4.0
+Description: 	Interface is used to configure RDMA-cable HCAs in respect to
+		RDMA-CM attributes.
+
+		Attributes are visible only when configfs is mounted. To mount
+		configfs in /config directory use:
+		# mount -t configfs none /config/
+
+		In order to set parameters related to a specific HCA, a directory
+		for this HCA has to be created:
+		mkdir -p /config/rdma_cm/<hca>
+
+
+What: 		/config/rdma_cm/<hca>/ports/<port-num>/default_roce_mode
+Date: 		November 29, 2015
+KernelVersion:  4.4.0
+Description: 	RDMA-CM based connections from HCA <hca> at port <port-num>
+		will be initiated with this RoCE type as default.
+		The possible RoCE types are either "IB/RoCE v1" or "RoCE v2".
+		This parameter has RW access.
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
index bc7ff731aa0c..f56335af2d88 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
+++ b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
@@ -10,3 +10,5 @@ Description:
 		isoc_mult	- 0..2 (hs/ss only)
 		isoc_maxburst	- 0..15 (ss only)
 		buflen		- buffer length
+		bulk_qlen	- depth of queue for bulk
+		iso_qlen	- depth of queue for iso
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-tcm b/Documentation/ABI/testing/configfs-usb-gadget-tcm
new file mode 100644
index 000000000000..a29ed2dd6173
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-usb-gadget-tcm
@@ -0,0 +1,6 @@
+What:		/config/usb-gadget/gadget/functions/tcm.name
+Date:		Dec 2015
+KernelVersion:	4.5
+Description:
+		There are no attributes because all the configuration
+		is performed in the "target" subsystem of configfs.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-ina2xx-adc b/Documentation/ABI/testing/sysfs-bus-iio-ina2xx-adc
new file mode 100644
index 000000000000..8916f7ec6507
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-iio-ina2xx-adc
@@ -0,0 +1,24 @@
+What:		/sys/bus/iio/devices/iio:deviceX/in_allow_async_readout
+Date:		December 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		By default (value '0'), the capture thread checks for the Conversion
+		Ready Flag to being set prior to committing a new value to the sample
+		buffer. This synchronizes the in-chip conversion rate with the
+		in-driver readout rate at the cost of an additional register read.
+
+		Writing '1' will remove the polling for the Conversion Ready Flags to
+		save the additional i2c transaction, which will improve the bandwidth
+		available for reading data. However, samples can be occasionally skipped
+		or repeated, depending on the beat between the capture and conversion
+		rates.
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_shunt_resistor
+Date:		December 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		The value of the shunt resistor may be known only at runtime fom an
+		eeprom content read by a client application. This attribute allows to
+		set its value in ohms.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 3a4abfc44f5e..0bd731cbb50c 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -134,19 +134,21 @@ Description:
 		enabled for the device. Developer can write y/Y/1 or n/N/0 to
 		the file to enable/disable the feature.
 
-What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm
-Date:		June 2015
+What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1
+		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2
+Date:		November 2015
 Contact:	Kevin Strasser <kevin.strasser@linux.intel.com>
+		Lu Baolu <baolu.lu@linux.intel.com>
 Description:
 		If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged
 		in to a xHCI host which supports link PM, it will check if U1
 		and U2 exit latencies have been set in the BOS descriptor; if
-		the check is is passed and the host supports USB3 hardware LPM,
+		the check is passed and the host supports USB3 hardware LPM,
 		USB3 hardware LPM will be enabled for the device and the USB
-		device directory will contain a file named
-		power/usb3_hardware_lpm. The file holds a string value (enable
-		or disable) indicating whether or not USB3 hardware LPM is
-		enabled for the device.
+		device directory will contain two files named
+		power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These
+		files hold a string value (enable or disable) indicating whether
+		or not USB3 hardware LPM U1 or U2 is enabled for the device.
 
 What:		/sys/bus/usb/devices/.../removable
 Date:		February 2012
@@ -187,6 +189,17 @@ Description:
 		The file will read "hotplug", "wired" and "not used" if the
 		information is available, and "unknown" otherwise.
 
+What:		/sys/bus/usb/devices/.../(hub interface)/portX/usb3_lpm_permit
+Date:		November 2015
+Contact:	Lu Baolu <baolu.lu@linux.intel.com>
+Description:
+		Some USB3.0 devices are not friendly to USB3 LPM.  usb3_lpm_permit
+		attribute allows enabling/disabling usb3 lpm of a port. It takes
+		effect both before and after a usb device is enumerated. Supported
+		values are "0" if both u1 and u2 are NOT permitted, "u1" if only u1
+		is permitted, "u2" if only u2 is permitted, "u1_u2" if both u1 and
+		u2 are permitted.
+
 What:		/sys/bus/usb/devices/.../power/usb2_lpm_l1_timeout
 Date:		May 2013
 Contact:	Mathias Nyman <mathias.nyman@linux.intel.com>
diff --git a/Documentation/ABI/testing/sysfs-class-infiniband b/Documentation/ABI/testing/sysfs-class-infiniband
new file mode 100644
index 000000000000..a86abe66a316
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-infiniband
@@ -0,0 +1,16 @@
+What:		/sys/class/infiniband/<hca>/ports/<port-number>/gid_attrs/ndevs/<gid-index>
+Date:		November 29, 2015
+KernelVersion:	4.4.0
+Contact:	linux-rdma@vger.kernel.org
+Description: 	The net-device's name associated with the GID resides
+		at index <gid-index>.
+
+What:		/sys/class/infiniband/<hca>/ports/<port-number>/gid_attrs/types/<gid-index>
+Date:		November 29, 2015
+KernelVersion:	4.4.0
+Contact:	linux-rdma@vger.kernel.org
+Description: 	The RoCE type of the associated GID resides at index <gid-index>.
+		This could either be "IB/RoCE v1" for IB and RoCE v1 based GODs
+		or "RoCE v2" for RoCE v2 based GIDs.
+
+
diff --git a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
index 5cedf72df358..f7be0e88b139 100644
--- a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
+++ b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
@@ -19,6 +19,25 @@ Description:
 		Set to 0 to pad all frames. Set greater than tx_max to
 		disable all padding.
 
+What:		/sys/class/net/<iface>/cdc_ncm/ndp_to_end
+Date:		Dec 2015
+KernelVersion:	4.5
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean attribute showing the status of the "NDP to
+		end" quirk.  Defaults to 'N', except for devices
+		already known to need it enabled.
+
+		The "NDP to end" quirk makes the driver place the NDP
+		(the packet index table) after the payload.  The NCM
+		specification does not mandate this, but some devices
+		are known to be more restrictive. Write 'Y' to this
+		attribute for temporary testing of a suspect device
+		failing to work with the default driver settings.
+
+		A device entry should be added to the driver if this
+		quirk is found to be required.
+
 What:		/sys/class/net/<iface>/cdc_ncm/rx_max
 Date:		May 2014
 KernelVersion:	3.16
diff --git a/Documentation/ABI/testing/sysfs-class-net-mesh b/Documentation/ABI/testing/sysfs-class-net-mesh
index c46406296631..c2b956d44a95 100644
--- a/Documentation/ABI/testing/sysfs-class-net-mesh
+++ b/Documentation/ABI/testing/sysfs-class-net-mesh
@@ -8,7 +8,7 @@ Description:
 
 What:           /sys/class/net/<mesh_iface>/mesh/<vlan_subdir>/ap_isolation
 Date:           May 2011
-Contact:        Antonio Quartulli <antonio@meshcoding.com>
+Contact:        Antonio Quartulli <a@unstable.cc>
 Description:
                 Indicates whether the data traffic going from a
                 wireless client to another wireless client will be
@@ -70,7 +70,7 @@ Description:
 
 What:		/sys/class/net/<mesh_iface>/mesh/isolation_mark
 Date:		Nov 2013
-Contact:	Antonio Quartulli <antonio@meshcoding.com>
+Contact:	Antonio Quartulli <a@unstable.cc>
 Description:
 		Defines the isolation mark (and its bitmask) which
 		is used to classify clients as "isolated" by the
diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi
new file mode 100644
index 000000000000..fa5a00bb1143
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-qmi
@@ -0,0 +1,23 @@
+What:		/sys/class/net/<iface>/qmi/raw_ip
+Date:		Dec 2015
+KernelVersion:	4.4
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean.  Default: 'N'
+
+		Set this to 'Y' to change the network device link
+		framing from '802.3' to 'raw-ip'.
+
+		The netdev will change to reflect the link framing
+		mode.  The netdev is an ordinary ethernet device in
+		'802.3' mode, and the driver expects to exchange
+		frames with an ethernet header over the USB link. The
+		netdev is a headerless p-t-p device in 'raw-ip' mode,
+		and the driver expects to echange IPv4 or IPv6 packets
+		without any L2 header over the USB link.
+
+		Userspace is in full control of firmware configuration
+		through the delegation of the QMI protocol. Userspace
+		is responsible for coordination of driver and firmware
+		link framing mode, changing this setting to 'Y' if the
+		firmware is configured for 'raw-ip' mode.
diff --git a/Documentation/ABI/testing/sysfs-class-watchdog b/Documentation/ABI/testing/sysfs-class-watchdog
new file mode 100644
index 000000000000..736046b33040
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-watchdog
@@ -0,0 +1,51 @@
+What:		/sys/class/watchdog/watchdogn/bootstatus
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains status of the watchdog
+		device at boot. It is equivalent to WDIOC_GETBOOTSTATUS of
+		ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/identity
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains identity string of
+		watchdog device.
+
+What:		/sys/class/watchdog/watchdogn/nowayout
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. While reading, it gives '1' if that
+		device supports nowayout feature else, it gives '0'.
+
+What:		/sys/class/watchdog/watchdogn/state
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It gives active/inactive status of
+		watchdog device.
+
+What:		/sys/class/watchdog/watchdogn/status
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains watchdog device's
+		internal status bits. It is equivalent to WDIOC_GETSTATUS
+		of ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/timeleft
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains value of time left for
+		reset generation. It is equivalent to WDIOC_GETTIMELEFT of
+		ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/timeout
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It is read to know about current
+		value of timeout programmed.
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 0345f2d1c727..e5200f354abf 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -87,6 +87,12 @@ Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls the checkpoint timing.
 
+What:		/sys/fs/f2fs/<disk>/idle_interval
+Date:		January 2016
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the idle timing.
+
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>
diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch
index 5bf42a840b22..da87f43aec58 100644
--- a/Documentation/ABI/testing/sysfs-kernel-livepatch
+++ b/Documentation/ABI/testing/sysfs-kernel-livepatch
@@ -33,7 +33,7 @@ Description:
 		The object directory contains subdirectories for each function
 		that is patched within the object.
 
-What:		/sys/kernel/livepatch/<patch>/<object>/<function>
+What:		/sys/kernel/livepatch/<patch>/<object>/<function,sympos>
 Date:		Nov 2014
 KernelVersion:	3.19.0
 Contact:	live-patching@vger.kernel.org
@@ -41,4 +41,8 @@ Description:
 		The function directory contains attributes regarding the
 		properties and state of the patched function.
 
+		The directory name contains the patched function name and a
+		sympos number corresponding to the nth occurrence of the symbol
+		name in kallsyms for the patched object.
+
 		There are currently no such attributes.
diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp
index 44806a678f12..a17f817a9309 100644
--- a/Documentation/ABI/testing/sysfs-ptp
+++ b/Documentation/ABI/testing/sysfs-ptp
@@ -74,7 +74,7 @@ Description:
 		assignment may be changed by two writing numbers into
 		the file.
 
-What:		/sys/class/ptp/ptpN/pps_avaiable
+What:		/sys/class/ptp/ptpN/pps_available
 Date:		September 2010
 Contact:	Richard Cochran <richardcochran@gmail.com>
 Description:
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index c06f817b3091..db653774c0b7 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -430,7 +430,7 @@ The rationale for using gotos is:
 		return result;
 	}
 
-A common type of bug to be aware of it "one err bugs" which look like this:
+A common type of bug to be aware of is "one err bugs" which look like this:
 
 	err:
 		kfree(foo->bar);
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index d69b3fc64e14..781024ef9050 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -951,16 +951,6 @@ to "Closing".
    alignment constraints (e.g. the alignment constraints about 64-bit
    objects).
 
-3) Supporting multiple types of IOMMUs
-
-   If your architecture needs to support multiple types of IOMMUs, you
-   can use include/linux/asm-generic/dma-mapping-common.h. It's a
-   library to support the DMA API with multiple types of IOMMUs. Lots
-   of architectures (x86, powerpc, sh, alpha, ia64, microblaze and
-   sparc) use it. Choose one to see how it can be used. If you need to
-   support multiple types of IOMMUs in a single system, the example of
-   x86 or powerpc helps.
-
 			   Closing
 
 This document, and the API itself, would not be in its current
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 1e98a7e6bccc..45ef3f279c3b 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -236,7 +236,7 @@ are guaranteed also to be cache line boundaries).
 
 DMA_TO_DEVICE synchronisation must be done after the last modification
 of the memory region by the software and before it is handed off to
-the driver.  Once this primitive is used, memory covered by this
+the device.  Once this primitive is used, memory covered by this
 primitive should be treated as read-only by the device.  If the device
 may write to it at any point, it should be DMA_BIDIRECTIONAL (see
 below).
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 91f6d89bb19f..d70f9b68174e 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -50,8 +50,7 @@ pdfdocs: $(PDF)
 
 HTML := $(sort $(patsubst %.xml, %.html, $(BOOKS)))
 htmldocs: $(HTML)
-	$(call build_main_index)
-	$(call build_images)
+	$(call cmd,build_main_index)
 	$(call install_media_images)
 
 MAN := $(patsubst %.xml, %.9, $(BOOKS))
@@ -139,7 +138,8 @@ quiet_cmd_db2pdf = PDF     $@
 
 index = index.html
 main_idx = $(obj)/$(index)
-build_main_index = rm -rf $(main_idx); \
+quiet_cmd_build_main_index = HTML    $(main_idx)
+      cmd_build_main_index = rm -rf $(main_idx); \
 		   echo '<h1>Linux Kernel HTML Documentation</h1>' >> $(main_idx) && \
 		   echo '<h2>Kernel Version: $(KERNELVERSION)</h2>' >> $(main_idx) && \
 		   cat $(HTML) >> $(main_idx)
@@ -227,6 +227,10 @@ dochelp:
 	@echo  '  mandocs         - man pages'
 	@echo  '  installmandocs  - install man pages generated by mandocs'
 	@echo  '  cleandocs       - clean all generated DocBook files'
+	@echo
+	@echo  'make DOCBOOKS="s1.xml s2.xml" [target] Generate only docs s1.xml s2.xml'
+	@echo  '  valid values for DOCBOOKS are: $(DOCBOOKS)'
+
 
 ###
 # Temporary files left by various tools
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 42a2d8593e39..cdd8b24db68d 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -238,83 +238,32 @@ X!Isound/sound_firmware.c
 !Iinclude/media/videobuf2-memops.h
      </sect1>
      <sect1><title>Digital TV (DVB) devices</title>
-!Idrivers/media/dvb-core/dvb_ca_en50221.h
-!Idrivers/media/dvb-core/dvb_frontend.h
+	<sect1><title>Digital TV Common functions</title>
 !Idrivers/media/dvb-core/dvb_math.h
 !Idrivers/media/dvb-core/dvb_ringbuffer.h
 !Idrivers/media/dvb-core/dvbdev.h
-	<sect1><title>Digital TV Demux API</title>
-	    <para>The kernel demux API defines a driver-internal interface for
-	    registering low-level, hardware specific driver to a hardware
-	    independent demux layer. It is only of interest for Digital TV
-	    device driver writers. The header file for this API is named
-	    <constant>demux.h</constant> and located in
-	    <constant>drivers/media/dvb-core</constant>.</para>
-
-	<para>The demux API should be implemented for each demux in the
-	system. It is used to select the TS source of a demux and to manage
-	the demux resources. When the demux client allocates a resource via
-	the demux API, it receives a pointer to the API of that
-	resource.</para>
-	<para>Each demux receives its TS input from a DVB front-end or from
-	memory, as set via this demux API. In a system with more than one
-	front-end, the API can be used to select one of the DVB front-ends
-	as a TS source for a demux, unless this is fixed in the HW platform.
-	The demux API only controls front-ends regarding to their connections
-	with demuxes; the APIs used to set the other front-end parameters,
-	such as tuning, are not defined in this document.</para>
-	<para>The functions that implement the abstract interface demux should
-	be defined static or module private and registered to the Demux
-	core for external access. It is not necessary to implement every
-	function in the struct <constant>dmx_demux</constant>. For example,
-	a demux interface might support Section filtering, but not PES
-	filtering. The API client is expected to check the value of any
-	function pointer before calling the function: the value of NULL means
-	that the &#8220;function is not available&#8221;.</para>
-	<para>Whenever the functions of the demux API modify shared data,
-	the possibilities of lost update and race condition problems should
-	be addressed, e.g. by protecting parts of code with mutexes.</para>
-	<para>Note that functions called from a bottom half context must not
-	sleep. Even a simple memory allocation without using GFP_ATOMIC can
-	result in a kernel thread being put to sleep if swapping is needed.
-	For example, the Linux kernel calls the functions of a network device
-	interface from a bottom half context. Thus, if a demux API function
-	is called from network device code, the function must not sleep.
-	</para>
-    </sect1>
-
-    <section id="demux_callback_api">
-	<title>Demux Callback API</title>
-	<para>This kernel-space API comprises the callback functions that
-	deliver filtered data to the demux client. Unlike the other DVB
-	kABIs, these functions are provided by the client and called from
-	the demux code.</para>
-	<para>The function pointers of this abstract interface are not
-	packed into a structure as in the other demux APIs, because the
-	callback functions are registered and used independent of each
-	other. As an example, it is possible for the API client to provide
-	several callback functions for receiving TS packets and no
-	callbacks for PES packets or sections.</para>
-	<para>The functions that implement the callback API need not be
-	re-entrant: when a demux driver calls one of these functions,
-	the driver is not allowed to call the function again before
-	the original call returns. If a callback is triggered by a
-	hardware interrupt, it is recommended to use the Linux
-	&#8220;bottom half&#8221; mechanism or start a tasklet instead of
-	making the callback function call directly from a hardware
-	interrupt.</para>
-	<para>This mechanism is implemented by
-	<link linkend='API-dmx-ts-cb'>dmx_ts_cb()</link> and
-	<link linkend='API-dmx-section-cb'>dmx_section_cb()</link>.</para>
-    </section>
-
+	</sect1>
+	<sect1><title>Digital TV Frontend kABI</title>
+!Pdrivers/media/dvb-core/dvb_frontend.h Digital TV Frontend
+!Idrivers/media/dvb-core/dvb_frontend.h
+	</sect1>
+	<sect1><title>Digital TV Demux kABI</title>
+!Pdrivers/media/dvb-core/demux.h Digital TV Demux
+	<sect1><title>Demux Callback API</title>
+!Pdrivers/media/dvb-core/demux.h Demux Callback
+	</sect1>
 !Idrivers/media/dvb-core/demux.h
-    </sect1>
+	</sect1>
+	<sect1><title>Digital TV Conditional Access kABI</title>
+!Idrivers/media/dvb-core/dvb_ca_en50221.h
+	</sect1>
+     </sect1>
     <sect1><title>Remote Controller devices</title>
 !Iinclude/media/rc-core.h
 !Iinclude/media/lirc_dev.h
     </sect1>
     <sect1><title>Media Controller devices</title>
+!Pinclude/media/media-device.h Media Controller
 !Iinclude/media/media-device.h
 !Iinclude/media/media-devnode.h
 !Iinclude/media/media-entity.h
diff --git a/Documentation/DocBook/gpu.tmpl b/Documentation/DocBook/gpu.tmpl
index 201dcd3c2e9d..a8669330b456 100644
--- a/Documentation/DocBook/gpu.tmpl
+++ b/Documentation/DocBook/gpu.tmpl
@@ -124,6 +124,43 @@
     <para>
       [Insert diagram of typical DRM stack here]
     </para>
+  <sect1>
+    <title>Style Guidelines</title>
+    <para>
+      For consistency this documentation uses American English. Abbreviations
+      are written as all-uppercase, for example: DRM, KMS, IOCTL, CRTC, and so
+      on. To aid in reading, documentations make full use of the markup
+      characters kerneldoc provides: @parameter for function parameters, @member
+      for structure members, &amp;structure to reference structures and
+      function() for functions. These all get automatically hyperlinked if
+      kerneldoc for the referenced objects exists. When referencing entries in
+      function vtables please use -&gt;vfunc(). Note that kerneldoc does
+      not support referencing struct members directly, so please add a reference
+      to the vtable struct somewhere in the same paragraph or at least section.
+    </para>
+    <para>
+      Except in special situations (to separate locked from unlocked variants)
+      locking requirements for functions aren't documented in the kerneldoc.
+      Instead locking should be check at runtime using e.g.
+      <code>WARN_ON(!mutex_is_locked(...));</code>. Since it's much easier to
+      ignore documentation than runtime noise this provides more value. And on
+      top of that runtime checks do need to be updated when the locking rules
+      change, increasing the chances that they're correct. Within the
+      documentation the locking rules should be explained in the relevant
+      structures: Either in the comment for the lock explaining what it
+      protects, or data fields need a note about which lock protects them, or
+      both.
+    </para>
+    <para>
+      Functions which have a non-<code>void</code> return value should have a
+      section called "Returns" explaining the expected return values in
+      different cases and their meanings. Currently there's no consensus whether
+      that section name should be all upper-case or not, and whether it should
+      end in a colon or not. Go with the file-local style. Other common section
+      names are "Notes" with information for dangerous or tricky corner cases,
+      and "FIXME" where the interface could be cleaned up.
+    </para>
+  </sect1>
   </chapter>
 
   <!-- Internals -->
@@ -615,18 +652,6 @@ char *date;</synopsis>
           <function>drm_gem_object_init</function>. Storage for private GEM
           objects must be managed by drivers.
         </para>
-        <para>
-          Drivers that do not need to extend GEM objects with private information
-          can call the <function>drm_gem_object_alloc</function> function to
-          allocate and initialize a struct <structname>drm_gem_object</structname>
-          instance. The GEM core will call the optional driver
-          <methodname>gem_init_object</methodname> operation after initializing
-          the GEM object with <function>drm_gem_object_init</function>.
-          <synopsis>int (*gem_init_object) (struct drm_gem_object *obj);</synopsis>
-        </para>
-        <para>
-          No alloc-and-init function exists for private GEM objects.
-        </para>
       </sect3>
       <sect3>
         <title>GEM Objects Lifetime</title>
@@ -635,10 +660,10 @@ char *date;</synopsis>
           acquired and release by <function>calling drm_gem_object_reference</function>
           and <function>drm_gem_object_unreference</function> respectively. The
           caller must hold the <structname>drm_device</structname>
-          <structfield>struct_mutex</structfield> lock. As a convenience, GEM
-          provides the <function>drm_gem_object_reference_unlocked</function> and
-          <function>drm_gem_object_unreference_unlocked</function> functions that
-          can be called without holding the lock.
+	  <structfield>struct_mutex</structfield> lock when calling
+	  <function>drm_gem_object_reference</function>. As a convenience, GEM
+	  provides <function>drm_gem_object_unreference_unlocked</function>
+	  functions that can be called without holding the lock.
         </para>
         <para>
           When the last reference to a GEM object is released the GEM core calls
@@ -649,15 +674,9 @@ char *date;</synopsis>
         </para>
         <para>
           <synopsis>void (*gem_free_object) (struct drm_gem_object *obj);</synopsis>
-          Drivers are responsible for freeing all GEM object resources, including
-          the resources created by the GEM core. If an mmap offset has been
-          created for the object (in which case
-          <structname>drm_gem_object</structname>::<structfield>map_list</structfield>::<structfield>map</structfield>
-          is not NULL) it must be freed by a call to
-          <function>drm_gem_free_mmap_offset</function>. The shmfs backing store
-          must be released by calling <function>drm_gem_object_release</function>
-          (that function can safely be called if no shmfs backing store has been
-          created).
+          Drivers are responsible for freeing all GEM object resources. This includes
+          the resources created by the GEM core, which need to be released with
+          <function>drm_gem_object_release</function>.
         </para>
       </sect3>
       <sect3>
@@ -740,17 +759,10 @@ char *date;</synopsis>
           DRM identifies the GEM object to be mapped by a fake offset passed
           through the mmap offset argument. Prior to being mapped, a GEM object
           must thus be associated with a fake offset. To do so, drivers must call
-          <function>drm_gem_create_mmap_offset</function> on the object. The
-          function allocates a fake offset range from a pool and stores the
-          offset divided by PAGE_SIZE in
-          <literal>obj-&gt;map_list.hash.key</literal>. Care must be taken not to
-          call <function>drm_gem_create_mmap_offset</function> if a fake offset
-          has already been allocated for the object. This can be tested by
-          <literal>obj-&gt;map_list.map</literal> being non-NULL.
+          <function>drm_gem_create_mmap_offset</function> on the object.
         </para>
         <para>
           Once allocated, the fake offset value
-          (<literal>obj-&gt;map_list.hash.key &lt;&lt; PAGE_SHIFT</literal>)
           must be passed to the application in a driver-specific way and can then
           be used as the mmap offset argument.
         </para>
@@ -836,10 +848,11 @@ char *date;</synopsis>
           abstracted from the client in libdrm.
         </para>
       </sect3>
-      <sect3>
-        <title>GEM Function Reference</title>
+    </sect2>
+    <sect2>
+      <title>GEM Function Reference</title>
 !Edrivers/gpu/drm/drm_gem.c
-      </sect3>
+!Iinclude/drm/drm_gem.h
     </sect2>
     <sect2>
       <title>VMA Offset Manager</title>
@@ -970,12 +983,10 @@ int max_width, max_height;</synopsis>
     <sect2>
       <title>Atomic Mode Setting Function Reference</title>
 !Edrivers/gpu/drm/drm_atomic.c
+!Idrivers/gpu/drm/drm_atomic.c
     </sect2>
     <sect2>
-      <title>Frame Buffer Creation</title>
-      <synopsis>struct drm_framebuffer *(*fb_create)(struct drm_device *dev,
-				     struct drm_file *file_priv,
-				     struct drm_mode_fb_cmd2 *mode_cmd);</synopsis>
+      <title>Frame Buffer Abstraction</title>
       <para>
         Frame buffers are abstract memory objects that provide a source of
         pixels to scanout to a CRTC. Applications explicitly request the
@@ -994,73 +1005,6 @@ int max_width, max_height;</synopsis>
 	and so expects TTM handles in the create ioctl and not GEM handles.
       </para>
       <para>
-        Drivers must first validate the requested frame buffer parameters passed
-        through the mode_cmd argument. In particular this is where invalid
-        sizes, pixel formats or pitches can be caught.
-      </para>
-      <para>
-        If the parameters are deemed valid, drivers then create, initialize and
-        return an instance of struct <structname>drm_framebuffer</structname>.
-        If desired the instance can be embedded in a larger driver-specific
-	structure. Drivers must fill its <structfield>width</structfield>,
-	<structfield>height</structfield>, <structfield>pitches</structfield>,
-        <structfield>offsets</structfield>, <structfield>depth</structfield>,
-        <structfield>bits_per_pixel</structfield> and
-        <structfield>pixel_format</structfield> fields from the values passed
-        through the <parameter>drm_mode_fb_cmd2</parameter> argument. They
-        should call the <function>drm_helper_mode_fill_fb_struct</function>
-        helper function to do so.
-      </para>
-
-      <para>
-	The initialization of the new framebuffer instance is finalized with a
-	call to <function>drm_framebuffer_init</function> which takes a pointer
-	to DRM frame buffer operations (struct
-	<structname>drm_framebuffer_funcs</structname>). Note that this function
-	publishes the framebuffer and so from this point on it can be accessed
-	concurrently from other threads. Hence it must be the last step in the
-	driver's framebuffer initialization sequence. Frame buffer operations
-	are
-        <itemizedlist>
-          <listitem>
-            <synopsis>int (*create_handle)(struct drm_framebuffer *fb,
-		     struct drm_file *file_priv, unsigned int *handle);</synopsis>
-            <para>
-              Create a handle to the frame buffer underlying memory object. If
-              the frame buffer uses a multi-plane format, the handle will
-              reference the memory object associated with the first plane.
-            </para>
-            <para>
-              Drivers call <function>drm_gem_handle_create</function> to create
-              the handle.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_framebuffer *framebuffer);</synopsis>
-            <para>
-              Destroy the frame buffer object and frees all associated
-              resources. Drivers must call
-              <function>drm_framebuffer_cleanup</function> to free resources
-              allocated by the DRM core for the frame buffer object, and must
-              make sure to unreference all memory objects associated with the
-              frame buffer. Handles created by the
-              <methodname>create_handle</methodname> operation are released by
-              the DRM core.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*dirty)(struct drm_framebuffer *framebuffer,
-	     struct drm_file *file_priv, unsigned flags, unsigned color,
-	     struct drm_clip_rect *clips, unsigned num_clips);</synopsis>
-            <para>
-              This optional operation notifies the driver that a region of the
-              frame buffer has changed in response to a DRM_IOCTL_MODE_DIRTYFB
-              ioctl call.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </para>
-      <para>
 	The lifetime of a drm framebuffer is controlled with a reference count,
 	drivers can grab additional references with
 	<function>drm_framebuffer_reference</function>and drop them
@@ -1197,137 +1141,6 @@ int max_width, max_height;</synopsis>
           pointer to CRTC functions.
         </para>
       </sect3>
-      <sect3 id="drm-kms-crtcops">
-        <title>CRTC Operations</title>
-        <sect4>
-          <title>Set Configuration</title>
-          <synopsis>int (*set_config)(struct drm_mode_set *set);</synopsis>
-          <para>
-            Apply a new CRTC configuration to the device. The configuration
-            specifies a CRTC, a frame buffer to scan out from, a (x,y) position in
-            the frame buffer, a display mode and an array of connectors to drive
-            with the CRTC if possible.
-          </para>
-          <para>
-            If the frame buffer specified in the configuration is NULL, the driver
-            must detach all encoders connected to the CRTC and all connectors
-            attached to those encoders and disable them.
-          </para>
-          <para>
-            This operation is called with the mode config lock held.
-          </para>
-          <note><para>
-	    Note that the drm core has no notion of restoring the mode setting
-	    state after resume, since all resume handling is in the full
-	    responsibility of the driver. The common mode setting helper library
-	    though provides a helper which can be used for this:
-	    <function>drm_helper_resume_force_mode</function>.
-          </para></note>
-        </sect4>
-        <sect4>
-          <title>Page Flipping</title>
-          <synopsis>int (*page_flip)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-                   struct drm_pending_vblank_event *event);</synopsis>
-          <para>
-            Schedule a page flip to the given frame buffer for the CRTC. This
-            operation is called with the mode config mutex held.
-          </para>
-          <para>
-            Page flipping is a synchronization mechanism that replaces the frame
-            buffer being scanned out by the CRTC with a new frame buffer during
-            vertical blanking, avoiding tearing. When an application requests a page
-            flip the DRM core verifies that the new frame buffer is large enough to
-            be scanned out by  the CRTC in the currently configured mode and then
-            calls the CRTC <methodname>page_flip</methodname> operation with a
-            pointer to the new frame buffer.
-          </para>
-          <para>
-            The <methodname>page_flip</methodname> operation schedules a page flip.
-            Once any pending rendering targeting the new frame buffer has
-            completed, the CRTC will be reprogrammed to display that frame buffer
-            after the next vertical refresh. The operation must return immediately
-            without waiting for rendering or page flip to complete and must block
-            any new rendering to the frame buffer until the page flip completes.
-          </para>
-          <para>
-            If a page flip can be successfully scheduled the driver must set the
-            <code>drm_crtc-&gt;fb</code> field to the new framebuffer pointed to
-            by <code>fb</code>. This is important so that the reference counting
-            on framebuffers stays balanced.
-          </para>
-          <para>
-            If a page flip is already pending, the
-            <methodname>page_flip</methodname> operation must return
-            -<errorname>EBUSY</errorname>.
-          </para>
-          <para>
-            To synchronize page flip to vertical blanking the driver will likely
-            need to enable vertical blanking interrupts. It should call
-            <function>drm_vblank_get</function> for that purpose, and call
-            <function>drm_vblank_put</function> after the page flip completes.
-          </para>
-          <para>
-            If the application has requested to be notified when page flip completes
-            the <methodname>page_flip</methodname> operation will be called with a
-            non-NULL <parameter>event</parameter> argument pointing to a
-            <structname>drm_pending_vblank_event</structname> instance. Upon page
-            flip completion the driver must call <methodname>drm_send_vblank_event</methodname>
-            to fill in the event and send to wake up any waiting processes.
-            This can be performed with
-            <programlisting><![CDATA[
-            spin_lock_irqsave(&dev->event_lock, flags);
-            ...
-            drm_send_vblank_event(dev, pipe, event);
-            spin_unlock_irqrestore(&dev->event_lock, flags);
-            ]]></programlisting>
-          </para>
-          <note><para>
-            FIXME: Could drivers that don't need to wait for rendering to complete
-            just add the event to <literal>dev-&gt;vblank_event_list</literal> and
-            let the DRM core handle everything, as for "normal" vertical blanking
-            events?
-          </para></note>
-          <para>
-            While waiting for the page flip to complete, the
-            <literal>event-&gt;base.link</literal> list head can be used freely by
-            the driver to store the pending event in a driver-specific list.
-          </para>
-          <para>
-            If the file handle is closed before the event is signaled, drivers must
-            take care to destroy the event in their
-            <methodname>preclose</methodname> operation (and, if needed, call
-            <function>drm_vblank_put</function>).
-          </para>
-        </sect4>
-        <sect4>
-          <title>Miscellaneous</title>
-          <itemizedlist>
-            <listitem>
-              <synopsis>void (*set_property)(struct drm_crtc *crtc,
-                     struct drm_property *property, uint64_t value);</synopsis>
-              <para>
-                Set the value of the given CRTC property to
-                <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-                for more information about properties.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*gamma_set)(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-                        uint32_t start, uint32_t size);</synopsis>
-              <para>
-                Apply a gamma table to the device. The operation is optional.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*destroy)(struct drm_crtc *crtc);</synopsis>
-              <para>
-                Destroy the CRTC when not needed anymore. See
-                <xref linkend="drm-kms-init"/>.
-              </para>
-            </listitem>
-          </itemizedlist>
-        </sect4>
-      </sect3>
     </sect2>
     <sect2>
       <title>Planes (struct <structname>drm_plane</structname>)</title>
@@ -1344,7 +1157,7 @@ int max_width, max_height;</synopsis>
         <listitem>
         DRM_PLANE_TYPE_PRIMARY represents a "main" plane for a CRTC.  Primary
         planes are the planes operated upon by CRTC modesetting and flipping
-        operations described in <xref linkend="drm-kms-crtcops"/>.
+	operations described in the page_flip hook in <structname>drm_crtc_funcs</structname>.
         </listitem>
         <listitem>
         DRM_PLANE_TYPE_CURSOR represents a "cursor" plane for a CRTC.  Cursor
@@ -1381,52 +1194,6 @@ int max_width, max_height;</synopsis>
           primary plane with standard capabilities.
         </para>
       </sect3>
-      <sect3>
-        <title>Plane Operations</title>
-        <itemizedlist>
-          <listitem>
-            <synopsis>int (*update_plane)(struct drm_plane *plane, struct drm_crtc *crtc,
-                        struct drm_framebuffer *fb, int crtc_x, int crtc_y,
-                        unsigned int crtc_w, unsigned int crtc_h,
-                        uint32_t src_x, uint32_t src_y,
-                        uint32_t src_w, uint32_t src_h);</synopsis>
-            <para>
-              Enable and configure the plane to use the given CRTC and frame buffer.
-            </para>
-            <para>
-              The source rectangle in frame buffer memory coordinates is given by
-              the <parameter>src_x</parameter>, <parameter>src_y</parameter>,
-              <parameter>src_w</parameter> and <parameter>src_h</parameter>
-              parameters (as 16.16 fixed point values). Devices that don't support
-              subpixel plane coordinates can ignore the fractional part.
-            </para>
-            <para>
-              The destination rectangle in CRTC coordinates is given by the
-              <parameter>crtc_x</parameter>, <parameter>crtc_y</parameter>,
-              <parameter>crtc_w</parameter> and <parameter>crtc_h</parameter>
-              parameters (as integer values). Devices scale the source rectangle to
-              the destination rectangle. If scaling is not supported, and the source
-              rectangle size doesn't match the destination rectangle size, the
-              driver must return a -<errorname>EINVAL</errorname> error.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*disable_plane)(struct drm_plane *plane);</synopsis>
-            <para>
-              Disable the plane. The DRM core calls this method in response to a
-              DRM_IOCTL_MODE_SETPLANE ioctl call with the frame buffer ID set to 0.
-              Disabled planes must not be processed by the CRTC.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_plane *plane);</synopsis>
-            <para>
-              Destroy the plane when not needed anymore. See
-              <xref linkend="drm-kms-init"/>.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </sect3>
     </sect2>
     <sect2>
       <title>Encoders (struct <structname>drm_encoder</structname>)</title>
@@ -1483,27 +1250,6 @@ int max_width, max_height;</synopsis>
           encoders they want to use to a CRTC.
         </para>
       </sect3>
-      <sect3>
-        <title>Encoder Operations</title>
-        <itemizedlist>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_encoder *encoder);</synopsis>
-            <para>
-              Called to destroy the encoder when not needed anymore. See
-              <xref linkend="drm-kms-init"/>.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*set_property)(struct drm_plane *plane,
-                     struct drm_property *property, uint64_t value);</synopsis>
-            <para>
-              Set the value of the given plane property to
-              <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-              for more information about properties.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </sect3>
     </sect2>
     <sect2>
       <title>Connectors (struct <structname>drm_connector</structname>)</title>
@@ -1707,27 +1453,6 @@ int max_width, max_height;</synopsis>
             connector_status_unknown.
           </para>
         </sect4>
-        <sect4>
-          <title>Miscellaneous</title>
-          <itemizedlist>
-            <listitem>
-              <synopsis>void (*set_property)(struct drm_connector *connector,
-                     struct drm_property *property, uint64_t value);</synopsis>
-              <para>
-                Set the value of the given connector property to
-                <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-                for more information about properties.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*destroy)(struct drm_connector *connector);</synopsis>
-              <para>
-                Destroy the connector when not needed anymore. See
-                <xref linkend="drm-kms-init"/>.
-              </para>
-            </listitem>
-          </itemizedlist>
-        </sect4>
       </sect3>
     </sect2>
     <sect2>
@@ -1854,462 +1579,6 @@ void intel_crt_init(struct drm_device *dev)
       entities.
     </para>
     <sect2>
-      <title>Helper Functions</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>int drm_crtc_helper_set_config(struct drm_mode_set *set);</synopsis>
-          <para>
-            The <function>drm_crtc_helper_set_config</function> helper function
-            is a CRTC <methodname>set_config</methodname> implementation. It
-            first tries to locate the best encoder for each connector by calling
-            the connector <methodname>best_encoder</methodname> helper
-            operation.
-          </para>
-          <para>
-            After locating the appropriate encoders, the helper function will
-            call the <methodname>mode_fixup</methodname> encoder and CRTC helper
-            operations to adjust the requested mode, or reject it completely in
-            which case an error will be returned to the application. If the new
-            configuration after mode adjustment is identical to the current
-            configuration the helper function will return without performing any
-            other operation.
-          </para>
-          <para>
-            If the adjusted mode is identical to the current mode but changes to
-            the frame buffer need to be applied, the
-            <function>drm_crtc_helper_set_config</function> function will call
-            the CRTC <methodname>mode_set_base</methodname> helper operation. If
-            the adjusted mode differs from the current mode, or if the
-            <methodname>mode_set_base</methodname> helper operation is not
-            provided, the helper function performs a full mode set sequence by
-            calling the <methodname>prepare</methodname>,
-            <methodname>mode_set</methodname> and
-            <methodname>commit</methodname> CRTC and encoder helper operations,
-            in that order.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void drm_helper_connector_dpms(struct drm_connector *connector, int mode);</synopsis>
-          <para>
-            The <function>drm_helper_connector_dpms</function> helper function
-            is a connector <methodname>dpms</methodname> implementation that
-            tracks power state of connectors. To use the function, drivers must
-            provide <methodname>dpms</methodname> helper operations for CRTCs
-            and encoders to apply the DPMS state to the device.
-          </para>
-          <para>
-            The mid-layer doesn't track the power state of CRTCs and encoders.
-            The <methodname>dpms</methodname> helper operations can thus be
-            called with a mode identical to the currently active mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
-                                            uint32_t maxX, uint32_t maxY);</synopsis>
-          <para>
-            The <function>drm_helper_probe_single_connector_modes</function> helper
-            function is a connector <methodname>fill_modes</methodname>
-            implementation that updates the connection status for the connector
-            and then retrieves a list of modes by calling the connector
-            <methodname>get_modes</methodname> helper operation.
-          </para>
-         <para>
-            If the helper operation returns no mode, and if the connector status
-            is connector_status_connected, standard VESA DMT modes up to
-            1024x768 are automatically added to the modes list by a call to
-            <function>drm_add_modes_noedid</function>.
-          </para>
-          <para>
-            The function then filters out modes larger than
-            <parameter>max_width</parameter> and <parameter>max_height</parameter>
-            if specified. It finally calls the optional connector
-            <methodname>mode_valid</methodname> helper operation for each mode in
-            the probed list to check whether the mode is valid for the connector.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>CRTC Helper Operations</title>
-      <itemizedlist>
-        <listitem id="drm-helper-crtc-mode-fixup">
-          <synopsis>bool (*mode_fixup)(struct drm_crtc *crtc,
-                       const struct drm_display_mode *mode,
-                       struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Let CRTCs adjust the requested mode or reject it completely. This
-            operation returns true if the mode is accepted (possibly after being
-            adjusted) or false if it is rejected.
-          </para>
-          <para>
-            The <methodname>mode_fixup</methodname> operation should reject the
-            mode if it can't reasonably use it. The definition of "reasonable"
-            is currently fuzzy in this context. One possible behaviour would be
-            to set the adjusted mode to the panel timings when a fixed-mode
-            panel is used with hardware capable of scaling. Another behaviour
-            would be to accept any input mode and adjust it to the closest mode
-            supported by the hardware (FIXME: This needs to be clarified).
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_set_base)(struct drm_crtc *crtc, int x, int y,
-                     struct drm_framebuffer *old_fb)</synopsis>
-          <para>
-            Move the CRTC on the current frame buffer (stored in
-            <literal>crtc-&gt;fb</literal>) to position (x,y). Any of the frame
-            buffer, x position or y position may have been modified.
-          </para>
-          <para>
-            This helper operation is optional. If not provided, the
-            <function>drm_crtc_helper_set_config</function> function will fall
-            back to the <methodname>mode_set</methodname> helper operation.
-          </para>
-          <note><para>
-            FIXME: Why are x and y passed as arguments, as they can be accessed
-            through <literal>crtc-&gt;x</literal> and
-            <literal>crtc-&gt;y</literal>?
-          </para></note>
-        </listitem>
-        <listitem>
-          <synopsis>void (*prepare)(struct drm_crtc *crtc);</synopsis>
-          <para>
-            Prepare the CRTC for mode setting. This operation is called after
-            validating the requested mode. Drivers use it to perform
-            device-specific operations required before setting the new mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_set)(struct drm_crtc *crtc, struct drm_display_mode *mode,
-                struct drm_display_mode *adjusted_mode, int x, int y,
-                struct drm_framebuffer *old_fb);</synopsis>
-          <para>
-            Set a new mode, position and frame buffer. Depending on the device
-            requirements, the mode can be stored internally by the driver and
-            applied in the <methodname>commit</methodname> operation, or
-            programmed to the hardware immediately.
-          </para>
-          <para>
-            The <methodname>mode_set</methodname> operation returns 0 on success
-	    or a negative error code if an error occurs.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*commit)(struct drm_crtc *crtc);</synopsis>
-          <para>
-            Commit a mode. This operation is called after setting the new mode.
-            Upon return the device must use the new mode and be fully
-            operational.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>Encoder Helper Operations</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>bool (*mode_fixup)(struct drm_encoder *encoder,
-                       const struct drm_display_mode *mode,
-                       struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Let encoders adjust the requested mode or reject it completely. This
-            operation returns true if the mode is accepted (possibly after being
-            adjusted) or false if it is rejected. See the
-            <link linkend="drm-helper-crtc-mode-fixup">mode_fixup CRTC helper
-            operation</link> for an explanation of the allowed adjustments.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*prepare)(struct drm_encoder *encoder);</synopsis>
-          <para>
-            Prepare the encoder for mode setting. This operation is called after
-            validating the requested mode. Drivers use it to perform
-            device-specific operations required before setting the new mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*mode_set)(struct drm_encoder *encoder,
-                 struct drm_display_mode *mode,
-                 struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Set a new mode. Depending on the device requirements, the mode can
-            be stored internally by the driver and applied in the
-            <methodname>commit</methodname> operation, or programmed to the
-            hardware immediately.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*commit)(struct drm_encoder *encoder);</synopsis>
-          <para>
-            Commit a mode. This operation is called after setting the new mode.
-            Upon return the device must use the new mode and be fully
-            operational.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>Connector Helper Operations</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>struct drm_encoder *(*best_encoder)(struct drm_connector *connector);</synopsis>
-          <para>
-            Return a pointer to the best encoder for the connecter. Device that
-            map connectors to encoders 1:1 simply return the pointer to the
-            associated encoder. This operation is mandatory.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*get_modes)(struct drm_connector *connector);</synopsis>
-          <para>
-            Fill the connector's <structfield>probed_modes</structfield> list
-            by parsing EDID data with <function>drm_add_edid_modes</function>,
-            adding standard VESA DMT modes with <function>drm_add_modes_noedid</function>,
-            or calling <function>drm_mode_probed_add</function> directly for every
-            supported mode and return the number of modes it has detected. This
-            operation is mandatory.
-          </para>
-          <para>
-            Note that the caller function will automatically add standard VESA
-            DMT modes up to 1024x768 if the <methodname>get_modes</methodname>
-            helper operation returns no mode and if the connector status is
-            connector_status_connected. There is no need to call
-            <function>drm_add_edid_modes</function> manually in that case.
-          </para>
-          <para>
-            When adding modes manually the driver creates each mode with a call to
-            <function>drm_mode_create</function> and must fill the following fields.
-            <itemizedlist>
-              <listitem>
-                <synopsis>__u32 type;</synopsis>
-                <para>
-                  Mode type bitmask, a combination of
-                  <variablelist>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_BUILTIN</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_CLOCK_C</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_CRTC_C</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>
-        DRM_MODE_TYPE_PREFERRED - The preferred mode for the connector
-                      </term>
-                      <listitem>
-                        <para>not used?</para>
-                      </listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_DEFAULT</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_USERDEF</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_DRIVER</term>
-                      <listitem>
-                        <para>
-                          The mode has been created by the driver (as opposed to
-                          to user-created modes).
-                        </para>
-                      </listitem>
-                    </varlistentry>
-                  </variablelist>
-                  Drivers must set the DRM_MODE_TYPE_DRIVER bit for all modes they
-                  create, and set the DRM_MODE_TYPE_PREFERRED bit for the preferred
-                  mode.
-                </para>
-              </listitem>
-              <listitem>
-                <synopsis>__u32 clock;</synopsis>
-                <para>Pixel clock frequency in kHz unit</para>
-              </listitem>
-              <listitem>
-                <synopsis>__u16 hdisplay, hsync_start, hsync_end, htotal;
-    __u16 vdisplay, vsync_start, vsync_end, vtotal;</synopsis>
-                <para>Horizontal and vertical timing information</para>
-                <screen><![CDATA[
-             Active                 Front           Sync           Back
-             Region                 Porch                          Porch
-    <-----------------------><----------------><-------------><-------------->
-
-      //////////////////////|
-     ////////////////////// |
-    //////////////////////  |..................               ................
-                                               _______________
-
-    <----- [hv]display ----->
-    <------------- [hv]sync_start ------------>
-    <--------------------- [hv]sync_end --------------------->
-    <-------------------------------- [hv]total ----------------------------->
-]]></screen>
-              </listitem>
-              <listitem>
-                <synopsis>__u16 hskew;
-    __u16 vscan;</synopsis>
-                <para>Unknown</para>
-              </listitem>
-              <listitem>
-                <synopsis>__u32 flags;</synopsis>
-                <para>
-                  Mode flags, a combination of
-                  <variablelist>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PHSYNC</term>
-                      <listitem><para>
-                        Horizontal sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NHSYNC</term>
-                      <listitem><para>
-                        Horizontal sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PVSYNC</term>
-                      <listitem><para>
-                        Vertical sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NVSYNC</term>
-                      <listitem><para>
-                        Vertical sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_INTERLACE</term>
-                      <listitem><para>
-                        Mode is interlaced
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_DBLSCAN</term>
-                      <listitem><para>
-                        Mode uses doublescan
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_CSYNC</term>
-                      <listitem><para>
-                        Mode uses composite sync
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PCSYNC</term>
-                      <listitem><para>
-                        Composite sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NCSYNC</term>
-                      <listitem><para>
-                        Composite sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_HSKEW</term>
-                      <listitem><para>
-                        hskew provided (not used?)
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_BCAST</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PIXMUX</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_DBLCLK</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_CLKDIV2</term>
-                      <listitem><para>
-                        ?
-                      </para></listitem>
-                    </varlistentry>
-                  </variablelist>
-                </para>
-                <para>
-                  Note that modes marked with the INTERLACE or DBLSCAN flags will be
-                  filtered out by
-                  <function>drm_helper_probe_single_connector_modes</function> if
-                  the connector's <structfield>interlace_allowed</structfield> or
-                  <structfield>doublescan_allowed</structfield> field is set to 0.
-                </para>
-              </listitem>
-              <listitem>
-                <synopsis>char name[DRM_DISPLAY_MODE_LEN];</synopsis>
-                <para>
-                  Mode name. The driver must call
-                  <function>drm_mode_set_name</function> to fill the mode name from
-                  <structfield>hdisplay</structfield>,
-                  <structfield>vdisplay</structfield> and interlace flag after
-                  filling the corresponding fields.
-                </para>
-              </listitem>
-            </itemizedlist>
-          </para>
-          <para>
-            The <structfield>vrefresh</structfield> value is computed by
-            <function>drm_helper_probe_single_connector_modes</function>.
-          </para>
-          <para>
-            When parsing EDID data, <function>drm_add_edid_modes</function> fills the
-            connector <structfield>display_info</structfield>
-            <structfield>width_mm</structfield> and
-            <structfield>height_mm</structfield> fields. When creating modes
-            manually the <methodname>get_modes</methodname> helper operation must
-            set the <structfield>display_info</structfield>
-            <structfield>width_mm</structfield> and
-            <structfield>height_mm</structfield> fields if they haven't been set
-            already (for instance at initialization time when a fixed-size panel is
-            attached to the connector). The mode <structfield>width_mm</structfield>
-            and <structfield>height_mm</structfield> fields are only used internally
-            during EDID parsing and should not be set when creating modes manually.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_valid)(struct drm_connector *connector,
-		  struct drm_display_mode *mode);</synopsis>
-          <para>
-            Verify whether a mode is valid for the connector. Return MODE_OK for
-            supported modes and one of the enum drm_mode_status values (MODE_*)
-            for unsupported modes. This operation is optional.
-          </para>
-          <para>
-            As the mode rejection reason is currently not used beside for
-            immediately removing the unsupported mode, an implementation can
-            return MODE_BAD regardless of the exact reason why the mode is not
-            valid.
-          </para>
-          <note><para>
-            Note that the <methodname>mode_valid</methodname> helper operation is
-            only called for modes detected by the device, and
-            <emphasis>not</emphasis> for modes set by the user through the CRTC
-            <methodname>set_config</methodname> operation.
-          </para></note>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
       <title>Atomic Modeset Helper Functions Reference</title>
       <sect3>
 	<title>Overview</title>
@@ -2327,8 +1596,12 @@ void intel_crt_init(struct drm_device *dev)
 !Edrivers/gpu/drm/drm_atomic_helper.c
     </sect2>
     <sect2>
-      <title>Modeset Helper Functions Reference</title>
-!Iinclude/drm/drm_crtc_helper.h
+      <title>Modeset Helper Reference for Common Vtables</title>
+!Iinclude/drm/drm_modeset_helper_vtables.h
+!Pinclude/drm/drm_modeset_helper_vtables.h overview
+    </sect2>
+    <sect2>
+      <title>Legacy CRTC/Modeset Helper Functions Reference</title>
 !Edrivers/gpu/drm/drm_crtc_helper.c
 !Pdrivers/gpu/drm/drm_crtc_helper.c overview
     </sect2>
@@ -4039,92 +3312,6 @@ int num_ioctls;</synopsis>
       <sect2>
         <title>DPIO</title>
 !Pdrivers/gpu/drm/i915/i915_reg.h DPIO
-	<table id="dpiox2">
-	  <title>Dual channel PHY (VLV/CHV/BXT)</title>
-	  <tgroup cols="8">
-	    <colspec colname="c0" />
-	    <colspec colname="c1" />
-	    <colspec colname="c2" />
-	    <colspec colname="c3" />
-	    <colspec colname="c4" />
-	    <colspec colname="c5" />
-	    <colspec colname="c6" />
-	    <colspec colname="c7" />
-	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
-	    <spanspec spanname="ch1" namest="c4" nameend="c7" />
-	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
-	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
-	    <spanspec spanname="ch1pcs01" namest="c4" nameend="c5" />
-	    <spanspec spanname="ch1pcs23" namest="c6" nameend="c7" />
-	    <thead>
-	      <row>
-		<entry spanname="ch0">CH0</entry>
-		<entry spanname="ch1">CH1</entry>
-	      </row>
-	    </thead>
-	    <tbody valign="top" align="center">
-	      <row>
-		<entry spanname="ch0">CMN/PLL/REF</entry>
-		<entry spanname="ch1">CMN/PLL/REF</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0pcs01">PCS01</entry>
-		<entry spanname="ch0pcs23">PCS23</entry>
-		<entry spanname="ch1pcs01">PCS01</entry>
-		<entry spanname="ch1pcs23">PCS23</entry>
-	      </row>
-	      <row>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0">DDI0</entry>
-		<entry spanname="ch1">DDI1</entry>
-	      </row>
-	    </tbody>
-	  </tgroup>
-	</table>
-	<table id="dpiox1">
-	  <title>Single channel PHY (CHV/BXT)</title>
-	  <tgroup cols="4">
-	    <colspec colname="c0" />
-	    <colspec colname="c1" />
-	    <colspec colname="c2" />
-	    <colspec colname="c3" />
-	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
-	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
-	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
-	    <thead>
-	      <row>
-		<entry spanname="ch0">CH0</entry>
-	      </row>
-	    </thead>
-	    <tbody valign="top" align="center">
-	      <row>
-		<entry spanname="ch0">CMN/PLL/REF</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0pcs01">PCS01</entry>
-		<entry spanname="ch0pcs23">PCS23</entry>
-	      </row>
-	      <row>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0">DDI2</entry>
-	      </row>
-	    </tbody>
-	  </tgroup>
-	</table>
       </sect2>
 
       <sect2>
@@ -4201,17 +3388,21 @@ int num_ioctls;</synopsis>
       </sect2>
     </sect1>
     <sect1>
-      <title>GuC-based Command Submission</title>
+      <title>GuC</title>
       <sect2>
-        <title>GuC</title>
+        <title>GuC-specific firmware loader</title>
 !Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader
 !Idrivers/gpu/drm/i915/intel_guc_loader.c
       </sect2>
       <sect2>
-        <title>GuC Client</title>
-!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submissison
+        <title>GuC-based command submission</title>
+!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submission
 !Idrivers/gpu/drm/i915/i915_guc_submission.c
       </sect2>
+      <sect2>
+        <title>GuC Firmware Layout</title>
+!Pdrivers/gpu/drm/i915/intel_guc_fwif.h GuC Firmware Layout
+      </sect2>
     </sect1>
 
     <sect1>
@@ -4246,41 +3437,63 @@ int num_ioctls;</synopsis>
 
   <chapter id="modes_of_use">
     <title>Modes of Use</title>
-  <sect1>
-    <title>Manual switching and manual power control</title>
+    <sect1>
+      <title>Manual switching and manual power control</title>
 !Pdrivers/gpu/vga/vga_switcheroo.c Manual switching and manual power control
-  </sect1>
-  <sect1>
-    <title>Driver power control</title>
+    </sect1>
+    <sect1>
+      <title>Driver power control</title>
 !Pdrivers/gpu/vga/vga_switcheroo.c Driver power control
-  </sect1>
+    </sect1>
   </chapter>
 
-  <chapter id="pubfunctions">
-    <title>Public functions</title>
+  <chapter id="api">
+    <title>API</title>
+    <sect1>
+      <title>Public functions</title>
 !Edrivers/gpu/vga/vga_switcheroo.c
-  </chapter>
-
-  <chapter id="pubstructures">
-    <title>Public structures</title>
+    </sect1>
+    <sect1>
+      <title>Public structures</title>
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_handler
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_client_ops
-  </chapter>
-
-  <chapter id="pubconstants">
-    <title>Public constants</title>
+    </sect1>
+    <sect1>
+      <title>Public constants</title>
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_client_id
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_state
-  </chapter>
-
-  <chapter id="privstructures">
-    <title>Private structures</title>
+    </sect1>
+    <sect1>
+      <title>Private structures</title>
 !Fdrivers/gpu/vga/vga_switcheroo.c vgasr_priv
 !Fdrivers/gpu/vga/vga_switcheroo.c vga_switcheroo_client
+    </sect1>
+  </chapter>
+
+  <chapter id="handlers">
+    <title>Handlers</title>
+    <sect1>
+      <title>apple-gmux Handler</title>
+!Pdrivers/platform/x86/apple-gmux.c Overview
+!Pdrivers/platform/x86/apple-gmux.c Interrupt
+      <sect2>
+        <title>Graphics mux</title>
+!Pdrivers/platform/x86/apple-gmux.c Graphics mux
+      </sect2>
+      <sect2>
+        <title>Power control</title>
+!Pdrivers/platform/x86/apple-gmux.c Power control
+      </sect2>
+      <sect2>
+        <title>Backlight control</title>
+!Pdrivers/platform/x86/apple-gmux.c Backlight control
+      </sect2>
+    </sect1>
   </chapter>
 
 !Cdrivers/gpu/vga/vga_switcheroo.c
 !Cinclude/linux/vga_switcheroo.h
+!Cdrivers/platform/x86/apple-gmux.c
 </part>
 
 </book>
diff --git a/Documentation/DocBook/iio.tmpl b/Documentation/DocBook/iio.tmpl
index 98be322673da..f525bf56d1dd 100644
--- a/Documentation/DocBook/iio.tmpl
+++ b/Documentation/DocBook/iio.tmpl
@@ -458,7 +458,7 @@
             .scan_type = {
               .sign = 's',
               .realbits = 12,
-              .storgebits = 16,
+              .storagebits = 16,
               .shift = 4,
               .endianness = IIO_LE,
             },
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 08527e7ea4d0..2840ff483d5a 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -199,8 +199,10 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)-mkdir $(MEDIA_OBJ_DIR)/media_api; \
-	cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)if [ "x$(findstring media_api.xml,$(DOCBOOKS))" != "x" ]; then \
+		mkdir -p $(MEDIA_OBJ_DIR)/media_api; \
+		cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api; \
+	fi
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/DocBook/media/dvb/dvbproperty.xml b/Documentation/DocBook/media/dvb/dvbproperty.xml
index 08227d4e9150..e579ae5088ae 100644
--- a/Documentation/DocBook/media/dvb/dvbproperty.xml
+++ b/Documentation/DocBook/media/dvb/dvbproperty.xml
@@ -76,7 +76,7 @@ int main(void)
 
 <para>NOTE: While it is possible to directly call the Kernel code like the
     above example, it is strongly recommended to use
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
     as it provides abstraction to work with the supported digital TV standards
     and provides methods for usual operations like program scanning and to
     read/write channel descriptor files.</para>
diff --git a/Documentation/DocBook/media/dvb/examples.xml b/Documentation/DocBook/media/dvb/examples.xml
index c9f68c7183cc..837fb3b64b72 100644
--- a/Documentation/DocBook/media/dvb/examples.xml
+++ b/Documentation/DocBook/media/dvb/examples.xml
@@ -3,7 +3,7 @@
 </para>
 <para>NOTE: This section is out of date, and the code below won't even
     compile. Please refer to the
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
     for updated/recommended examples.
 </para>
 
diff --git a/Documentation/DocBook/media/dvb/intro.xml b/Documentation/DocBook/media/dvb/intro.xml
index 51db15648099..b5b701f5d8c2 100644
--- a/Documentation/DocBook/media/dvb/intro.xml
+++ b/Documentation/DocBook/media/dvb/intro.xml
@@ -32,7 +32,7 @@ and filtering several section and PES data streams at the same time.
 new standard Linux DVB API. As a commitment to the development of
 terminals based on open standards, Nokia and Convergence made it
 available to all Linux developers and published it on
-<ulink url="http://www.linuxtv.org/" /> in September 2000.
+<ulink url="https://linuxtv.org" /> in September 2000.
 Convergence is the maintainer of the Linux DVB API. Together with the
 LinuxTV community (i.e. you, the reader of this document), the Linux DVB
 API will be constantly reviewed and improved. With the Linux driver for
diff --git a/Documentation/DocBook/media/v4l/capture.c.xml b/Documentation/DocBook/media/v4l/capture.c.xml
index 1c5c49a2de59..22126a991b34 100644
--- a/Documentation/DocBook/media/v4l/capture.c.xml
+++ b/Documentation/DocBook/media/v4l/capture.c.xml
@@ -5,7 +5,7 @@
  *  This program can be used and distributed without restrictions.
  *
  *      This program is provided with the V4L2 API
- * see http://linuxtv.org/docs.php for more information
+ * see https://linuxtv.org/docs.php for more information
  */
 
 #include &lt;stdio.h&gt;
diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml
index 5701a08ed792..5399e8904715 100644
--- a/Documentation/DocBook/media/v4l/compat.xml
+++ b/Documentation/DocBook/media/v4l/compat.xml
@@ -2666,7 +2666,7 @@ is useful to display images captured with V4L2 devices.</para>
         <para>V4L2 does not support digital terrestrial, cable or
 satellite broadcast. A separate project aiming at digital receivers
 exists. You can find its homepage at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>. The Linux DVB API
+url="https://linuxtv.org">https://linuxtv.org</ulink>. The Linux DVB API
 has no connection to the V4L2 API except that drivers for hybrid
 hardware may support both.</para>
       </section>
diff --git a/Documentation/DocBook/media/v4l/io.xml b/Documentation/DocBook/media/v4l/io.xml
index da654031ef3f..144158b3a5ac 100644
--- a/Documentation/DocBook/media/v4l/io.xml
+++ b/Documentation/DocBook/media/v4l/io.xml
@@ -699,7 +699,7 @@ linkend="v4l2-buf-type" /></entry>
 buffer. It depends on the negotiated data format and may change with
 each buffer for compressed variable size data like JPEG images.
 Drivers must set this field when <structfield>type</structfield>
-refers to an input stream, applications when it refers to an output stream.
+refers to a capture stream, applications when it refers to an output stream.
 If the application sets this to 0 for an output stream, then
 <structfield>bytesused</structfield> will be set to the size of the
 buffer (see the <structfield>length</structfield> field of this struct) by
@@ -720,14 +720,14 @@ linkend="buffer-flags" />.</entry>
 	    <entry>Indicates the field order of the image in the
 buffer, see <xref linkend="v4l2-field" />. This field is not used when
 the buffer contains VBI data. Drivers must set it when
-<structfield>type</structfield> refers to an input stream,
+<structfield>type</structfield> refers to a capture stream,
 applications when it refers to an output stream.</entry>
 	  </row>
 	  <row>
 	    <entry>struct timeval</entry>
 	    <entry><structfield>timestamp</structfield></entry>
 	    <entry></entry>
-	    <entry><para>For input streams this is time when the first data
+	    <entry><para>For capture streams this is time when the first data
 	    byte was captured, as returned by the
 	    <function>clock_gettime()</function> function for the relevant
 	    clock id; see <constant>V4L2_BUF_FLAG_TIMESTAMP_*</constant> in
@@ -866,7 +866,7 @@ must set this to 0.</entry>
 	    <entry></entry>
 	    <entry>The number of bytes occupied by data in the plane
 	      (its payload). Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      If the application sets this to 0 for an output stream, then
 	      <structfield>bytesused</structfield> will be set to the size of the
 	      plane (see the <structfield>length</structfield> field of this struct)
@@ -919,7 +919,7 @@ must set this to 0.</entry>
 	    <entry></entry>
 	    <entry>Offset in bytes to video data in the plane.
 	      Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      Note that data_offset is included in <structfield>bytesused</structfield>.
 	      So the size of the image in the plane is
 	      <structfield>bytesused</structfield>-<structfield>data_offset</structfield> at
diff --git a/Documentation/DocBook/media/v4l/media-controller.xml b/Documentation/DocBook/media/v4l/media-controller.xml
index 873ac3a621f0..5f2fc07a93d7 100644
--- a/Documentation/DocBook/media/v4l/media-controller.xml
+++ b/Documentation/DocBook/media/v4l/media-controller.xml
@@ -58,21 +58,36 @@
     <title>Media device model</title>
     <para>Discovering a device internal topology, and configuring it at runtime,
     is one of the goals of the media controller API. To achieve this, hardware
-    devices are modelled as an oriented graph of building blocks called entities
-    connected through pads.</para>
-    <para>An entity is a basic media hardware or software building block. It can
-    correspond to a large variety of logical blocks such as physical hardware
-    devices (CMOS sensor for instance), logical hardware devices (a building
-    block in a System-on-Chip image processing pipeline), DMA channels or
-    physical connectors.</para>
-    <para>A pad is a connection endpoint through which an entity can interact
-    with other entities. Data (not restricted to video) produced by an entity
-    flows from the entity's output to one or more entity inputs. Pads should not
-    be confused with physical pins at chip boundaries.</para>
-    <para>A link is a point-to-point oriented connection between two pads,
-    either on the same entity or on different entities. Data flows from a source
-    pad to a sink pad.</para>
+    devices and Linux Kernel interfaces are modelled as graph objects on
+    an oriented graph. The object types that constitute the graph are:</para>
+    <itemizedlist>
+    <listitem><para>An <emphasis role="bold">entity</emphasis>
+    is a basic media hardware or software building block. It can correspond to
+    a large variety of logical blocks such as physical hardware devices
+    (CMOS sensor for instance), logical hardware devices (a building block in
+    a System-on-Chip image processing pipeline), DMA channels or physical
+    connectors.</para></listitem>
+    <listitem><para>An <emphasis role="bold">interface</emphasis>
+    is a graph representation of a Linux Kernel userspace API interface,
+    like a device node or a sysfs file that controls one or more entities
+    in the graph.</para></listitem>
+    <listitem><para>A <emphasis role="bold">pad</emphasis>
+    is a data connection endpoint through which an entity can interact with
+    other entities. Data (not restricted to video) produced by an entity
+    flows from the entity's output to one or more entity inputs. Pads should
+    not be confused with physical pins at chip boundaries.</para></listitem>
+    <listitem><para>A <emphasis role="bold">data link</emphasis>
+    is a point-to-point oriented connection between two pads, either on the
+    same entity or on different entities. Data flows from a source pad to a
+    sink pad.</para></listitem>
+    <listitem><para>An <emphasis role="bold">interface link</emphasis>
+    is a point-to-point bidirectional control connection between a Linux
+    Kernel interface and an entity.m</para></listitem>
+    </itemizedlist>
   </section>
+
+  <!-- All non-ioctl specific data types go here. -->
+  &sub-media-types;
 </chapter>
 
 <appendix id="media-user-func">
@@ -83,6 +98,7 @@
   &sub-media-func-ioctl;
   <!-- All ioctls go here. -->
   &sub-media-ioc-device-info;
+  &sub-media-ioc-g-topology;
   &sub-media-ioc-enum-entities;
   &sub-media-ioc-enum-links;
   &sub-media-ioc-setup-link;
diff --git a/Documentation/DocBook/media/v4l/media-ioc-enum-entities.xml b/Documentation/DocBook/media/v4l/media-ioc-enum-entities.xml
index 5872f8bbf774..0c4f96bfc2de 100644
--- a/Documentation/DocBook/media/v4l/media-ioc-enum-entities.xml
+++ b/Documentation/DocBook/media/v4l/media-ioc-enum-entities.xml
@@ -59,15 +59,6 @@
     <para>Entity IDs can be non-contiguous. Applications must
     <emphasis>not</emphasis> try to enumerate entities by calling
     MEDIA_IOC_ENUM_ENTITIES with increasing id's until they get an error.</para>
-    <para>Two or more entities that share a common non-zero
-    <structfield>group_id</structfield> value are considered as logically
-    grouped. Groups are used to report
-    <itemizedlist>
-      <listitem><para>ALSA, VBI and video nodes that carry the same media
-      stream</para></listitem>
-      <listitem><para>lens and flash controllers associated with a sensor</para></listitem>
-    </itemizedlist>
-    </para>
 
     <table pgwide="1" frame="none" id="media-entity-desc">
       <title>struct <structname>media_entity_desc</structname></title>
@@ -106,7 +97,7 @@
 	    <entry><structfield>revision</structfield></entry>
 	    <entry></entry>
 	    <entry></entry>
-	    <entry>Entity revision in a driver/hardware specific format.</entry>
+	    <entry>Entity revision. Always zero (obsolete)</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
@@ -120,7 +111,7 @@
 	    <entry><structfield>group_id</structfield></entry>
 	    <entry></entry>
 	    <entry></entry>
-	    <entry>Entity group ID</entry>
+	    <entry>Entity group ID. Always zero (obsolete)</entry>
 	  </row>
 	  <row>
 	    <entry>__u16</entry>
@@ -171,97 +162,6 @@
 	</tbody>
       </tgroup>
     </table>
-
-    <table frame="none" pgwide="1" id="media-entity-type">
-      <title>Media entity types</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE</constant></entry>
-	    <entry>Unknown device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_V4L</constant></entry>
-	    <entry>V4L video, radio or vbi device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_FB</constant></entry>
-	    <entry>Frame buffer device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_ALSA</constant></entry>
-	    <entry>ALSA card</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_FE</constant></entry>
-	    <entry>DVB frontend devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_DEMUX</constant></entry>
-	    <entry>DVB demux devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_DVR</constant></entry>
-	    <entry>DVB DVR devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_CA</constant></entry>
-	    <entry>DVB CAM devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_NET</constant></entry>
-	    <entry>DVB network devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV</constant></entry>
-	    <entry>Unknown V4L sub-device</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_SENSOR</constant></entry>
-	    <entry>Video sensor</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_FLASH</constant></entry>
-	    <entry>Flash controller</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_LENS</constant></entry>
-	    <entry>Lens controller</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_DECODER</constant></entry>
-	    <entry>Video decoder, the basic function of the video decoder is to
-	    accept analogue video from a wide variety of sources such as
-	    broadcast, DVD players, cameras and video cassette recorders, in
-	    either NTSC, PAL or HD format and still occasionally SECAM, separate
-	    it into its component parts, luminance and chrominance, and output
-	    it in some digital video standard, with appropriate embedded timing
-	    signals.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_TUNER</constant></entry>
-	    <entry>TV and/or radio tuner</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
-    <table frame="none" pgwide="1" id="media-entity-flag">
-      <title>Media entity flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_ENT_FL_DEFAULT</constant></entry>
-	    <entry>Default entity for its type. Used to discover the default
-	    audio, VBI and video devices, the default camera sensor, ...</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
   </refsect1>
 
   <refsect1>
diff --git a/Documentation/DocBook/media/v4l/media-ioc-enum-links.xml b/Documentation/DocBook/media/v4l/media-ioc-enum-links.xml
index 74fb394ec667..2bbeea9f3e18 100644
--- a/Documentation/DocBook/media/v4l/media-ioc-enum-links.xml
+++ b/Documentation/DocBook/media/v4l/media-ioc-enum-links.xml
@@ -118,35 +118,6 @@
       </tgroup>
     </table>
 
-    <table frame="none" pgwide="1" id="media-pad-flag">
-      <title>Media pad flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_SINK</constant></entry>
-	    <entry>Input pad, relative to the entity. Input pads sink data and
-	    are targets of links.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_SOURCE</constant></entry>
-	    <entry>Output pad, relative to the entity. Output pads source data
-	    and are origins of links.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_MUST_CONNECT</constant></entry>
-	    <entry>If this flag is set and the pad is linked to any other
-	    pad, then at least one of those links must be enabled for the
-	    entity to be able to stream. There could be temporary reasons
-	    (e.g. device configuration dependent) for the pad to need
-	    enabled links even when this flag isn't set; the absence of the
-	    flag doesn't imply there is none.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
     <table pgwide="1" frame="none" id="media-link-desc">
       <title>struct <structname>media_link_desc</structname></title>
       <tgroup cols="3">
@@ -171,33 +142,6 @@
       </tgroup>
     </table>
 
-    <table frame="none" pgwide="1" id="media-link-flag">
-      <title>Media link flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_ENABLED</constant></entry>
-	    <entry>The link is enabled and can be used to transfer media data.
-	    When two or more links target a sink pad, only one of them can be
-	    enabled at a time.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_IMMUTABLE</constant></entry>
-	    <entry>The link enabled state can't be modified at runtime. An
-	    immutable link is always enabled.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_DYNAMIC</constant></entry>
-	    <entry>The link enabled state can be modified during streaming. This
-	    flag is set by drivers and is read-only for applications.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-    <para>One and only one of <constant>MEDIA_PAD_FL_SINK</constant> and
-    <constant>MEDIA_PAD_FL_SOURCE</constant> must be set for every pad.</para>
   </refsect1>
 
   <refsect1>
diff --git a/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml b/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml
new file mode 100644
index 000000000000..63152ab9efba
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml
@@ -0,0 +1,394 @@
+<refentry id="media-g-topology">
+  <refmeta>
+    <refentrytitle>ioctl MEDIA_IOC_G_TOPOLOGY</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>MEDIA_IOC_G_TOPOLOGY</refname>
+    <refpurpose>Enumerate the graph topology and graph element properties</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct media_v2_topology *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='media-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>MEDIA_IOC_G_TOPOLOGY</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para><emphasis role="bold">NOTE:</emphasis> This new ioctl is programmed to be added on Kernel 4.6. Its definition/arguments may change until its final version.</para>
+
+    <para>The typical usage of this ioctl is to call it twice.
+    On the first call, the structure defined at &media-v2-topology; should
+    be zeroed. At return, if no errors happen, this ioctl will return the
+    <constant>topology_version</constant> and the total number of entities,
+    interfaces, pads and links.</para>
+    <para>Before the second call, the userspace should allocate arrays to
+    store the graph elements that are desired, putting the pointers to them
+    at the ptr_entities, ptr_interfaces, ptr_links and/or ptr_pads, keeping
+    the other values untouched.</para>
+    <para>If the <constant>topology_version</constant> remains the same, the
+    ioctl should fill the desired arrays with the media graph elements.</para>
+
+    <table pgwide="1" frame="none" id="media-v2-topology">
+      <title>struct <structname>media_v2_topology</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>topology_version</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Version of the media graph topology. When the graph is
+		    created, this field starts with zero. Every time a graph
+		    element is added or removed, this field is
+		    incremented.</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_entities</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Number of entities in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_entities</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the entities array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   entities. It will just update
+		   <constant>num_entities</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_interfaces</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Number of interfaces in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_interfaces</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the interfaces array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   interfaces. It will just update
+		   <constant>num_interfaces</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_pads</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Total number of pads in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_pads</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the pads array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   pads. It will just update
+		   <constant>num_pads</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_links</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Total number of data and interface links in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_links</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the links array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   links. It will just update
+		   <constant>num_links</constant></entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-entity">
+      <title>struct <structname>media_v2_entity</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the entity.</entry>
+	  </row>
+	  <row>
+	    <entry>char</entry>
+	    <entry><structfield>name</structfield>[64]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Entity name as an UTF-8 NULL-terminated string.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>function</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Entity main function, see <xref linkend="media-entity-type" /> for details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[12]</entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-interface">
+      <title>struct <structname>media_v2_interface</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the interface.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>intf_type</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Interface type, see <xref linkend="media-intf-type" /> for details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Interface flags. Currently unused.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[9]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	  <row>
+	    <entry>struct media_v2_intf_devnode</entry>
+	    <entry><structfield>devnode</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Used only for device node interfaces. See <xref linkend="media-v2-intf-devnode" /> for details..</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-intf-devnode">
+      <title>struct <structname>media_v2_interface</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>major</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Device node major number.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>minor</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Device node minor number.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-pad">
+      <title>struct <structname>media_v2_pad</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the pad.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>entity_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the entity where this pad belongs.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Pad flags, see <xref linkend="media-pad-flag" /> for more details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[9]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-link">
+      <title>struct <structname>media_v2_pad</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the pad.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>source_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>
+	       <para>On pad to pad links: unique ID for the source pad.</para>
+	       <para>On interface to entity links: unique ID for the interface.</para>
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>sink_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>
+	       <para>On pad to pad links: unique ID for the sink pad.</para>
+	       <para>On interface to entity links: unique ID for the entity.</para>
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Link flags, see <xref linkend="media-link-flag" /> for more details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[5]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>ENOSPC</errorcode></term>
+	<listitem>
+	  <para>This is returned when either one or more of the num_entities,
+	  num_interfaces, num_links or num_pads are non-zero and are smaller
+	  than the actual number of elements inside the graph. This may happen
+	  if the <constant>topology_version</constant> changed when compared
+	  to the last time this ioctl was called. Userspace should usually
+	  free the area for the pointers, zero the struct elements and call
+	  this ioctl again.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml
new file mode 100644
index 000000000000..0ee0f3386cdf
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/media-types.xml
@@ -0,0 +1,236 @@
+<section id="media-controller-types">
+<title>Types and flags used to represent the media graph elements</title>
+
+    <table frame="none" pgwide="1" id="media-entity-type">
+      <title>Media entity types</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_UNKNOWN</constant> and <constant>MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN</constant></entry>
+	    <entry>Unknown entity. That generally indicates that
+	    a driver didn't initialize properly the entity, with is a Kernel bug</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_V4L</constant></entry>
+	    <entry>Data streaming input and/or output entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_VBI</constant></entry>
+	    <entry>V4L VBI streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_SWRADIO</constant></entry>
+	    <entry>V4L Software Digital Radio (SDR) streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_DTV</constant></entry>
+	    <entry>DVB Digital TV streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_DEMOD</constant></entry>
+	    <entry>Digital TV demodulator entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_TS_DEMUX</constant></entry>
+	    <entry>MPEG Transport stream demux entity. Could be implemented on hardware or in Kernelspace by the Linux DVB subsystem.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_CA</constant></entry>
+	    <entry>Digital TV Conditional Access module (CAM) entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_NET_DECAP</constant></entry>
+	    <entry>Digital TV network ULE/MLE desencapsulation entity. Could be implemented on hardware or in Kernelspace</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_RF</constant></entry>
+	    <entry>Connector for a Radio Frequency (RF) signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_SVIDEO</constant></entry>
+	    <entry>Connector for a S-Video signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_COMPOSITE</constant></entry>
+	    <entry>Connector for a RGB composite signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CAM_SENSOR</constant></entry>
+	    <entry>Camera video sensor entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_FLASH</constant></entry>
+	    <entry>Flash controller entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_LENS</constant></entry>
+	    <entry>Lens controller entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_ATV_DECODER</constant></entry>
+	    <entry>Analog video decoder, the basic function of the video decoder
+	    is to accept analogue video from a wide variety of sources such as
+	    broadcast, DVD players, cameras and video cassette recorders, in
+	    either NTSC, PAL, SECAM or HD format, separating the stream
+	    into its component parts, luminance and chrominance, and output
+	    it in some digital video standard, with appropriate timing
+	    signals.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_TUNER</constant></entry>
+	    <entry>Digital TV, analog TV, radio and/or software radio tuner.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-entity-flag">
+      <title>Media entity flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_ENT_FL_DEFAULT</constant></entry>
+	    <entry>Default entity for its type. Used to discover the default
+	    audio, VBI and video devices, the default camera sensor, ...</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_FL_CONNECTOR</constant></entry>
+	    <entry>The entity represents a data conector</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-intf-type">
+      <title>Media interface types</title>
+      <tgroup cols="3">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<colspec colname="c3"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_FE</constant></entry>
+	    <entry>Device node interface for the Digital TV frontend</entry>
+	    <entry>typically, /dev/dvb/adapter?/frontend?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_DEMUX</constant></entry>
+	    <entry>Device node interface for the Digital TV demux</entry>
+	    <entry>typically, /dev/dvb/adapter?/demux?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_DVR</constant></entry>
+	    <entry>Device node interface for the Digital TV DVR</entry>
+	    <entry>typically, /dev/dvb/adapter?/dvr?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_CA</constant></entry>
+	    <entry>Device node interface for the Digital TV Conditional Access</entry>
+	    <entry>typically, /dev/dvb/adapter?/ca?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_FE</constant></entry>
+	    <entry>Device node interface for the Digital TV network control</entry>
+	    <entry>typically, /dev/dvb/adapter?/net?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_VIDEO</constant></entry>
+	    <entry>Device node interface for video (V4L)</entry>
+	    <entry>typically, /dev/video?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_VBI</constant></entry>
+	    <entry>Device node interface for VBI (V4L)</entry>
+	    <entry>typically, /dev/vbi?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_RADIO</constant></entry>
+	    <entry>Device node interface for radio (V4L)</entry>
+	    <entry>typically, /dev/vbi?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_SUBDEV</constant></entry>
+	    <entry>Device node interface for a V4L subdevice</entry>
+	    <entry>typically, /dev/v4l-subdev?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_SWRADIO</constant></entry>
+	    <entry>Device node interface for Software Defined Radio (V4L)</entry>
+	    <entry>typically, /dev/swradio?</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-pad-flag">
+      <title>Media pad flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_SINK</constant></entry>
+	    <entry>Input pad, relative to the entity. Input pads sink data and
+	    are targets of links.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_SOURCE</constant></entry>
+	    <entry>Output pad, relative to the entity. Output pads source data
+	    and are origins of links.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_MUST_CONNECT</constant></entry>
+	    <entry>If this flag is set and the pad is linked to any other
+	    pad, then at least one of those links must be enabled for the
+	    entity to be able to stream. There could be temporary reasons
+	    (e.g. device configuration dependent) for the pad to need
+	    enabled links even when this flag isn't set; the absence of the
+	    flag doesn't imply there is none.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <para>One and only one of <constant>MEDIA_PAD_FL_SINK</constant> and
+    <constant>MEDIA_PAD_FL_SOURCE</constant> must be set for every pad.</para>
+
+    <table frame="none" pgwide="1" id="media-link-flag">
+      <title>Media link flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_ENABLED</constant></entry>
+	    <entry>The link is enabled and can be used to transfer media data.
+	    When two or more links target a sink pad, only one of them can be
+	    enabled at a time.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_IMMUTABLE</constant></entry>
+	    <entry>The link enabled state can't be modified at runtime. An
+	    immutable link is always enabled.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_DYNAMIC</constant></entry>
+	    <entry>The link enabled state can be modified during streaming. This
+	    flag is set by drivers and is read-only for applications.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_LINK_TYPE</constant></entry>
+	    <entry><para>This is a bitmask that defines the type of the link.
+		   Currently, two types of links are supported:</para>
+	    <para><constant>MEDIA_LNK_FL_DATA_LINK</constant>
+	    if the link is between two pads</para>
+	    <para><constant>MEDIA_LNK_FL_INTERFACE_LINK</constant>
+	    if the link is between an interface and an entity</para></entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+</section>
diff --git a/Documentation/DocBook/media/v4l/v4l2.xml b/Documentation/DocBook/media/v4l/v4l2.xml
index 7e61643358de..42e626d6c936 100644
--- a/Documentation/DocBook/media/v4l/v4l2.xml
+++ b/Documentation/DocBook/media/v4l/v4l2.xml
@@ -152,6 +152,16 @@ structs, ioctls) must be noted in more detail in the history chapter
 (compat.xml), along with the possible impact on existing drivers and
 applications. -->
       <revision>
+	<revnumber>4.5</revnumber>
+	<date>2015-10-29</date>
+	<authorinitials>rr</authorinitials>
+	<revremark>Extend vidioc-g-ext-ctrls;. Replace ctrl_class with a new
+union with ctrl_class and which. Which is used to select the current value of
+the control or the default value.
+	</revremark>
+      </revision>
+
+      <revision>
 	<revnumber>4.4</revnumber>
 	<date>2015-05-26</date>
 	<authorinitials>ap</authorinitials>
diff --git a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
index 8ffe74f84af1..d81fa0d4016b 100644
--- a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
@@ -58,7 +58,7 @@
     <para>This ioctl is used to create buffers for <link linkend="mmap">memory
 mapped</link> or <link linkend="userp">user pointer</link> or <link
 linkend="dmabuf">DMA buffer</link> I/O. It can be used as an alternative or in
-addition to the <constant>VIDIOC_REQBUFS</constant> ioctl, when a tighter
+addition to the &VIDIOC-REQBUFS; ioctl, when a tighter
 control over buffers is required. This ioctl can be called multiple times to
 create buffers of different sizes.</para>
 
@@ -71,30 +71,28 @@ zeroed.</para>
 
     <para>The <structfield>format</structfield> field specifies the image format
 that the buffers must be able to handle. The application has to fill in this
-&v4l2-format;. Usually this will be done using the
-<constant>VIDIOC_TRY_FMT</constant> or <constant>VIDIOC_G_FMT</constant> ioctl()
-to ensure that the requested format is supported by the driver. Unsupported
-formats will result in an error.</para>
+&v4l2-format;. Usually this will be done using the &VIDIOC-TRY-FMT; or &VIDIOC-G-FMT; ioctls
+to ensure that the requested format is supported by the driver.
+Based on the format's <structfield>type</structfield> field the requested buffer
+size (for single-planar) or plane sizes (for multi-planar formats) will be
+used for the allocated buffers. The driver may return an error if the size(s)
+are not supported by the hardware (usually because they are too small).</para>
 
     <para>The buffers created by this ioctl will have as minimum size the size
-defined by the <structfield>format.pix.sizeimage</structfield> field. If the
+defined by the <structfield>format.pix.sizeimage</structfield> field (or the
+corresponding fields for other format types). Usually if the
 <structfield>format.pix.sizeimage</structfield> field is less than the minimum
-required for the given format, then <structfield>sizeimage</structfield> will be
-increased by the driver to that minimum to allocate the buffers. If it is
-larger, then the value will be used as-is. The same applies to the
-<structfield>sizeimage</structfield> field of the
-<structname>v4l2_plane_pix_format</structname> structure in the case of
-multiplanar formats.</para>
+required for the given format, then an error will be returned since drivers will
+typically not allow this. If it is larger, then the value will be used as-is.
+In other words, the driver may reject the requested size, but if it is accepted
+the driver will use it unchanged.</para>
 
     <para>When the ioctl is called with a pointer to this structure the driver
 will attempt to allocate up to the requested number of buffers and store the
 actual number allocated and the starting index in the
 <structfield>count</structfield> and the <structfield>index</structfield> fields
 respectively. On return <structfield>count</structfield> can be smaller than
-the number requested. The driver may also increase buffer sizes if required,
-however, it will not update <structfield>sizeimage</structfield> field values.
-The user has to use <constant>VIDIOC_QUERYBUF</constant> to retrieve that
-information.</para>
+the number requested.</para>
 
     <table pgwide="1" frame="none" id="v4l2-create-buffers">
       <title>struct <structname>v4l2_create_buffers</structname></title>
diff --git a/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml b/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
index 4c4603c135fe..f14a3bb1afaa 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
@@ -99,7 +99,7 @@ if the driver supports writing registers to the device.</para>
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling this ioctl directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-register.sgml
diff --git a/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml b/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
index 3d038e75d12b..5877f68a5820 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
@@ -117,7 +117,7 @@ However when a driver supports these ioctls it must also support
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling these ioctls directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-chip-info.sgml
diff --git a/Documentation/DocBook/media/v4l/vidioc-enumstd.xml b/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
index 8065099401d1..f18454e91752 100644
--- a/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
@@ -198,7 +198,7 @@ video4linux-list@redhat.com on 17 Oct 2002
 <constant>V4L2_STD_ATSC_16_VSB</constant> are U.S. terrestrial digital
 TV standards. Presently the V4L2 API does not support digital TV. See
 also the Linux DVB API at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 <para><programlisting>
 #define V4L2_STD_PAL_BG         (V4L2_STD_PAL_B         |\
 				 V4L2_STD_PAL_B1        |\
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
index 842536aae8b4..eb82f7e7d06b 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
@@ -61,7 +61,7 @@ must belong to the same control class.</para>
 
     <para>Applications must always fill in the
 <structfield>count</structfield>,
-<structfield>ctrl_class</structfield>,
+<structfield>which</structfield>,
 <structfield>controls</structfield> and
 <structfield>reserved</structfield> fields of &v4l2-ext-controls;, and
 initialize the &v4l2-ext-control; array pointed to by the
@@ -109,7 +109,7 @@ the driver whether wrong values are automatically adjusted to a valid
 value or if an error is returned.</para>
 
     <para>When the <structfield>id</structfield> or
-<structfield>ctrl_class</structfield> is invalid drivers return an
+<structfield>which</structfield> is invalid drivers return an
 &EINVAL;. When the value is out of bounds drivers can choose to take
 the closest valid value or return an &ERANGE;, whatever seems more
 appropriate. In the first case the new value is set in
@@ -223,7 +223,12 @@ Valid if <constant>V4L2_CTRL_FLAG_HAS_PAYLOAD</constant> is set for this control
       <tgroup cols="3">
 	&cs-str;
 	<tbody valign="top">
+	 <row>
+	    <entry>union</entry>
+	    <entry>(anonymous)</entry>
+	  </row>
 	  <row>
+	    <entry></entry>
 	    <entry>__u32</entry>
 	    <entry><structfield>ctrl_class</structfield></entry>
 	    <entry>The control class to which all controls belong, see
@@ -235,6 +240,23 @@ with a <structfield>count</structfield> of 0. If that succeeds, then the driver
 supports this feature.</entry>
 	  </row>
 	  <row>
+	    <entry></entry>
+	    <entry>__u32</entry>
+	    <entry><structfield>which</structfield></entry>
+	    <entry><para>Which value of the control to get/set/try. <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+will return the current value of the control and <constant>V4L2_CTRL_WHICH_DEF_VAL</constant> will
+return the default value of the control. Please note that you can only get the default value of the
+control, you cannot set or try it.</para>
+<para>For backwards compatibility you can also use a control class here (see
+<xref linkend="ctrl-class" />). In that case all controls have to belong to that
+control class. This usage is deprecated, instead just use <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.
+There are some very old drivers that do not yet support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+and that require a control class here. You can test for such drivers by setting ctrl_class to
+<constant>V4L2_CTRL_WHICH_CUR_VAL</constant> and calling VIDIOC_TRY_EXT_CTRLS with a count of 0.
+If that fails, then the driver does not support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.</para>
+</entry>
+	  </row>
+	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>count</structfield></entry>
 	    <entry>The number of controls in the controls array. May
@@ -390,7 +412,7 @@ These controls are described in <xref linkend="rf-tuner-controls" />.</entry>
 	<listitem>
 	  <para>The &v4l2-ext-control; <structfield>id</structfield>
 is invalid, the &v4l2-ext-controls;
-<structfield>ctrl_class</structfield> is invalid, or the &v4l2-ext-control;
+<structfield>which</structfield> is invalid, or the &v4l2-ext-control;
 <structfield>value</structfield> was inappropriate (e.g. the given menu
 index is not supported by the driver). This error code is
 also returned by the <constant>VIDIOC_S_EXT_CTRLS</constant> and
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 92037033f5eb..7b77e0f7b87d 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -19,10 +19,10 @@
 <!ENTITY cs-def                 "<colspec colname='c1' colwidth='3*' /><colspec colname='c2' colwidth='1*' /><colspec colname='c3' colwidth='4*' /><spanspec spanname='hspan' namest='c1' nameend='c3' />">
 
 <!-- Video for Linux mailing list address. -->
-<!ENTITY v4l-ml                 "<ulink url='http://www.linuxtv.org/lists.php'>http://www.linuxtv.org/lists.php</ulink>">
+<!ENTITY v4l-ml                 "<ulink url='https://linuxtv.org/lists.php'>https://linuxtv.org/lists.php</ulink>">
 
 <!-- LinuxTV v4l-dvb repository. -->
-<!ENTITY v4l-dvb		"<ulink url='http://linuxtv.org/repo/'>http://linuxtv.org/repo/</ulink>">
+<!ENTITY v4l-dvb		"<ulink url='https://linuxtv.org/repo/'>https://linuxtv.org/repo/</ulink>">
 <!ENTITY dash-ent-8             "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-10            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-12            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
@@ -91,7 +91,7 @@
 	      components, like mixers, PCM capture, PCM playback, etc, which
 	      are controlled via ALSA API.</para>
 	<para>For additional information and for the latest development code,
-		see: <ulink url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+		see: <ulink url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 	<para>For discussing improvements, reporting troubles, sending new drivers, etc, please mail to: <ulink url="http://vger.kernel.org/vger-lists.html#linux-media">Linux Media Mailing List (LMML).</ulink>.</para>
 </preface>
 
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index 7da8f0402af5..b442921bca54 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -162,12 +162,15 @@
 	<sect1 id="Basic_defines">
 		<title>Basic defines</title>
 		<para>
-			At least you have to provide a mtd structure and
-			a storage for the ioremap'ed chip address.
-			You can allocate the mtd structure using kmalloc
-			or you can allocate it statically.
-			In case of static allocation you have to allocate
-			a nand_chip structure too.
+			At least you have to provide a nand_chip structure
+			and a storage for the ioremap'ed chip address.
+			You can allocate the nand_chip structure using
+			kmalloc or you can allocate it statically.
+			The NAND chip structure embeds an mtd structure
+			which will be registered to the MTD subsystem.
+			You can extract a pointer to the mtd structure
+			from a nand_chip pointer using the nand_to_mtd()
+			helper.
 		</para>
 		<para>
 			Kmalloc based example
@@ -180,7 +183,6 @@ static void __iomem *baseaddr;
 			Static example
 		</para>
 		<programlisting>
-static struct mtd_info board_mtd;
 static struct nand_chip board_chip;
 static void __iomem *baseaddr;
 		</programlisting>
@@ -235,7 +237,7 @@ static void board_hwcontrol(struct mtd_info *mtd, int cmd)
 		<programlisting>
 static void board_hwcontrol(struct mtd_info *mtd, int cmd)
 {
-	struct nand_chip *this = (struct nand_chip *) mtd->priv;
+	struct nand_chip *this = mtd_to_nand(mtd);
 	switch(cmd){
 		case NAND_CTL_SETCLE: this->IO_ADDR_W |= CLE_ADRR_BIT;  break;
 		case NAND_CTL_CLRCLE: this->IO_ADDR_W &amp;= ~CLE_ADRR_BIT; break;
@@ -274,13 +276,15 @@ static int __init board_init (void)
 	int err = 0;
 
 	/* Allocate memory for MTD device structure and private data */
-	board_mtd = kzalloc(sizeof(struct mtd_info) + sizeof(struct nand_chip), GFP_KERNEL);
-	if (!board_mtd) {
+	this = kzalloc(sizeof(struct nand_chip), GFP_KERNEL);
+	if (!this) {
 		printk ("Unable to allocate NAND MTD device structure.\n");
 		err = -ENOMEM;
 		goto out;
 	}
 
+	board_mtd = nand_to_mtd(this);
+
 	/* map physical address */
 	baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
 	if (!baseaddr) {
@@ -289,11 +293,6 @@ static int __init board_init (void)
 		goto out_mtd;
 	}
 
-	/* Get pointer to private data */
-	this = (struct nand_chip *) ();
-	/* Link the private data with the MTD structure */
-	board_mtd->priv = this;
-
 	/* Set address of NAND IO lines */
 	this->IO_ADDR_R = baseaddr;
 	this->IO_ADDR_W = baseaddr;
@@ -317,7 +316,7 @@ static int __init board_init (void)
 out_ior:
 	iounmap(baseaddr);
 out_mtd:
-	kfree (board_mtd);
+	kfree (this);
 out:
 	return err;
 }
@@ -343,7 +342,7 @@ static void __exit board_cleanup (void)
 	iounmap(baseaddr);
 	
 	/* Free the MTD device structure */
-	kfree (board_mtd);
+	kfree (mtd_to_nand(board_mtd));
 }
 module_exit(board_cleanup);
 #endif
@@ -399,7 +398,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 		<programlisting>
 static void board_select_chip (struct mtd_info *mtd, int chip)
 {
-	struct nand_chip *this = (struct nand_chip *) mtd->priv;
+	struct nand_chip *this = mtd_to_nand(mtd);
 	
 	/* Deselect all chips */
 	this->IO_ADDR_R &amp;= ~BOARD_NAND_ADDR_MASK;
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 21152d397b88..d5a699d5a551 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -209,7 +209,7 @@ tools.  One such tool that is particularly recommended is the Linux
 Cross-Reference project, which is able to present source code in a
 self-referential, indexed webpage format. An excellent up-to-date
 repository of the kernel code may be found at:
-	http://lxr.linux.no/+trees
+	http://lxr.free-electrons.com/
 
 
 The development process
diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt
index 7b57fc087088..49585b6e1ea2 100644
--- a/Documentation/Intel-IOMMU.txt
+++ b/Documentation/Intel-IOMMU.txt
@@ -3,7 +3,7 @@ Linux IOMMU Support
 
 The architecture spec can be obtained from the below location.
 
-http://www.intel.com/technology/virtualization/
+http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
 
 This guide gives a quick cheat sheet for some basic understanding.
 
diff --git a/Documentation/Makefile b/Documentation/Makefile
index bc0548201755..1207d7907650 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,4 +1,4 @@
 subdir-y := accounting auxdisplay blackfin connector \
 	filesystems filesystems ia64 laptops mic misc-devices \
-	networking pcmcia prctl ptp spi timers vDSO video4linux \
+	networking pcmcia prctl ptp timers vDSO video4linux \
 	watchdog
diff --git a/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png
new file mode 100644
index 000000000000..7496a55e4e7b
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png
diff --git a/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg
new file mode 100644
index 000000000000..4b4014fda770
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg
@@ -0,0 +1,374 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="447.99197"
+   height="428.19299"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="GPpartitionReaders1.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.6184291"
+     inkscape:cx="223.99599"
+     inkscape:cy="214.0965"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="979"
+     inkscape:window-height="836"
+     inkscape:window-x="571"
+     inkscape:window-y="335"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-28.441125,-185.60612)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991"></flowPara></flowRoot>    <g
+       id="g4433"
+       transform="translate(2,0)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993"
+         y="-261.66608"
+         x="412.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="412.12299"
+           id="tspan2995"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="m 97.580736,477.4048 183.140664,0"
+           id="path2997"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 281.54942,465.38397 0,22.62742"
+           id="path4397-5"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="268.18076"
+       id="text4429"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431"
+         x="112.04738"
+         y="268.18076">WRITE_ONCE(a, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="439.13766"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="112.04738"
+         y="439.13766">WRITE_ONCE(b, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.60869"
+       y="309.29346"
+       id="text4445"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447"
+         x="255.60869"
+         y="309.29346">r1 = READ_ONCE(a);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.14423"
+       y="520.61786"
+       id="text4449"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451"
+         x="255.14423"
+         y="520.61786">WRITE_ONCE(c, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="384.71124"
+       id="text4453"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455"
+         x="396.10254"
+         y="384.71124">r2 = READ_ONCE(b);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="582.13617"
+       id="text4457"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459"
+         x="396.10254"
+         y="582.13617">r3 = READ_ONCE(c);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.08231"
+       y="213.91006"
+       id="text4461"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463"
+         x="112.08231"
+         y="213.91006">thread0()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="252.34512"
+       y="213.91006"
+       id="text4461-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-0"
+         x="252.34512"
+         y="213.91006">thread1()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.42557"
+       y="213.91006"
+       id="text4461-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2"
+         x="396.42557"
+         y="213.91006">thread2()</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect4495"
+       width="436.28488"
+       height="416.4859"
+       x="34.648232"
+       y="191.10612" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 183.14066,191.10612 0,417.193 -0.70711,0"
+       id="path4497"
+       inkscape:connector-curvature="0" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 325.13867,191.10612 0,417.193 -0.70711,0"
+       id="path4497-5"
+       inkscape:connector-curvature="0" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="251.53981"
+       id="text4429-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9"
+         x="111.75929"
+         y="251.53981">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="367.91556"
+       id="text4429-8-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4"
+         x="396.10254"
+         y="367.91556">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="597.40289"
+       id="text4429-8-9-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4"
+         x="396.10254"
+         y="597.40289">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="453.15311"
+       id="text4429-8-9-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-6"
+         x="111.75929"
+         y="453.15311">rcu_read_unlock();</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+       d="m 33.941125,227.87568 436.284885,0 0,0.7071"
+       id="path4608"
+       inkscape:connector-curvature="0" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="394.94427"
+       y="345.66351"
+       id="text4648"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650"
+         x="394.94427"
+         y="345.66351">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(36.441125,199.60612)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.11968"
+       y="475.77856"
+       id="text4648-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4"
+         x="112.11968"
+         y="475.77856">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-246.38346,329.72117)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-103.65246,202.90878)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="254.85066"
+       y="348.96619"
+       id="text4648-4-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5"
+         x="254.85066"
+         y="348.96619">QS</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/RCUApplicability.svg b/Documentation/RCU/Design/Requirements/RCUApplicability.svg
new file mode 100644
index 000000000000..ebcbeee391ed
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/RCUApplicability.svg
@@ -0,0 +1,237 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5d -->
+
+<!-- CreationDate: Tue Mar  4 18:34:25 2014 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="1089.1382"
+   height="668.21368"
+   viewBox="-2121 -36 14554.634 8876.4061"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="RCUApplicability.svg">
+  <metadata
+     id="metadata40">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <defs
+     id="defs38" />
+  <sodipodi:namedview
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1"
+     objecttolerance="10"
+     gridtolerance="10"
+     guidetolerance="10"
+     inkscape:pageopacity="0"
+     inkscape:pageshadow="2"
+     inkscape:window-width="849"
+     inkscape:window-height="639"
+     id="namedview36"
+     showgrid="false"
+     inkscape:zoom="0.51326165"
+     inkscape:cx="544.56912"
+     inkscape:cy="334.10686"
+     inkscape:window-x="149"
+     inkscape:window-y="448"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="g4"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <g
+     style="fill:none;stroke-width:0.025in"
+     id="g4"
+     transform="translate(-2043.6828,14.791398)">
+    <!-- Line: box -->
+    <rect
+       x="0"
+       y="0"
+       width="14400"
+       height="8775"
+       rx="0"
+       style="fill:#ffa1a1;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect6" />
+    <!-- Line: box -->
+    <rect
+       x="1350"
+       y="0"
+       width="11700"
+       height="6075"
+       rx="0"
+       style="fill:#ffff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect8" />
+    <!-- Line: box -->
+    <rect
+       x="2700"
+       y="0"
+       width="9000"
+       height="4275"
+       rx="0"
+       style="fill:#00ff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect10" />
+    <!-- Line: box -->
+    <rect
+       x="4050"
+       y="0"
+       width="6300"
+       height="2475"
+       rx="0"
+       style="fill:#87cfff;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect12" />
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="900"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text14"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3017">Read-Mostly, Stale &amp;</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="1350"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text16"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3019">Inconsistent Data OK</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="1800"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text18"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3021">(RCU Works Great!!!)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="3825"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text20"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3023">(RCU Works Well)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="3375"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text22"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3025">Read-Mostly, Need Consistent Data</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="5175"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text24"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3027">Read-Write, Need Consistent Data</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="6975"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text26"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">Update-Mostly, Need Consistent Data</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="5625"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text28"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3029">(RCU Might Be OK...)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="7875"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text30"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(1) Provide Existence Guarantees For Update-Friendly Mechanisms</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="8325"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text32"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(2) Provide Wait-Free Read-Side Primitives for Real-Time Use)</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="7425"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text34"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(RCU is Very Unlikely to be the Right Tool For The Job, But it Can:</text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg
new file mode 100644
index 000000000000..48cd1623d4d4
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg
@@ -0,0 +1,639 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="735.25"
+   height="516.21875"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="ReadersPartitionGP1.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="367.26465"
+     inkscape:cy="258.46182"
+     inkscape:document-units="px"
+     inkscape:current-layer="g4433-6"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="438"
+     inkscape:window-y="335"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-29.15625,-185.59375)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <g
+       id="g4433"
+       transform="translate(2,-12)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993"
+         y="-261.66608"
+         x="436.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="436.12299"
+           id="tspan2995"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="M 97.580736,477.4048 327.57913,476.09759"
+           id="path2997"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 328.40703,465.38397 0,22.62742"
+           id="path4397-5"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="268.18076"
+       id="text4429"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431"
+         x="112.04738"
+         y="268.18076">WRITE_ONCE(a, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="487.13766"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="112.04738"
+         y="487.13766">WRITE_ONCE(b, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.60869"
+       y="297.29346"
+       id="text4445"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447"
+         x="255.60869"
+         y="297.29346">r1 = READ_ONCE(a);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.14423"
+       y="554.61786"
+       id="text4449"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451"
+         x="255.14423"
+         y="554.61786">WRITE_ONCE(c, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="370.71124"
+       id="text4453"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455"
+         x="396.10254"
+         y="370.71124">WRITE_ONCE(d, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="572.13617"
+       id="text4457"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459"
+         x="396.10254"
+         y="572.13617">r2 = READ_ONCE(c);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.08231"
+       y="213.91006"
+       id="text4461"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463"
+         x="112.08231"
+         y="213.91006">thread0()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="252.34512"
+       y="213.91006"
+       id="text4461-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-0"
+         x="252.34512"
+         y="213.91006">thread1()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.42557"
+       y="213.91006"
+       id="text4461-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2"
+         x="396.42557"
+         y="213.91006">thread2()</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect4495"
+       width="724.25244"
+       height="505.21201"
+       x="34.648232"
+       y="191.10612" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 183.14066,191.10612 0,504.24243"
+       id="path4497"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 325.13867,191.10612 0,504.24243"
+       id="path4497-5"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="251.53981"
+       id="text4429-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9"
+         x="111.75929"
+         y="251.53981">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="353.91556"
+       id="text4429-8-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4"
+         x="396.10254"
+         y="353.91556">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="587.40289"
+       id="text4429-8-9-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4"
+         x="396.10254"
+         y="587.40289">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="501.15311"
+       id="text4429-8-9-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-6"
+         x="111.75929"
+         y="501.15311">rcu_read_unlock();</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+       d="m 33.941125,227.87568 724.941765,0"
+       id="path4608"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="394.94427"
+       y="331.66351"
+       id="text4648"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650"
+         x="394.94427"
+         y="331.66351">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(36.441125,185.60612)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.11968"
+       y="523.77856"
+       id="text4648-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4"
+         x="112.11968"
+         y="523.77856">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-246.38346,377.72117)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-103.65246,190.90878)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="254.85066"
+       y="336.96619"
+       id="text4648-4-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5"
+         x="254.85066"
+         y="336.96619">QS</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 470.93311,190.39903 0,504.24243"
+       id="path4497-5-6"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 616.22755,190.38323 0,504.24243"
+       id="path4497-5-2"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       id="g4433-6"
+       transform="translate(288.0964,78.32827)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993-7"
+         y="-261.66608"
+         x="440.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="440.12299"
+           id="tspan2995-1"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417-1"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="M 97.580736,477.4048 328.5624,477.07246"
+           id="path2997-2"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397-3"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 329.39039,465.38397 0,22.62742"
+           id="path4397-5-4"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="541.70508"
+       y="387.6217"
+       id="text4445-0"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447-5"
+         x="541.70508"
+         y="387.6217">r3 = READ_ONCE(d);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="541.2406"
+       y="646.94611"
+       id="text4449-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451-6"
+         x="541.2406"
+         y="646.94611">WRITE_ONCE(e, 1);</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7-5"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(182.44393,281.23704)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="540.94702"
+       y="427.29443"
+       id="text4648-4-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5-7"
+         x="540.94702"
+         y="427.29443">QS</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="461.83929"
+       id="text4453-7"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455-1"
+         x="686.27747"
+         y="461.83929">r4 = READ_ONCE(b);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="669.26422"
+       id="text4457-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459-2"
+         x="686.27747"
+         y="669.26422">r5 = READ_ONCE(e);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="445.04358"
+       id="text4429-8-9-33"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-2"
+         x="686.27747"
+         y="445.04358">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="684.53094"
+       id="text4429-8-9-3-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-5"
+         x="686.27747"
+         y="684.53094">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="685.11914"
+       y="422.79153"
+       id="text4648-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-7"
+         x="685.11914"
+         y="422.79153">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-8"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(326.61602,276.73415)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="397.85934"
+       y="609.59003"
+       id="text4648-5"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-77"
+         x="397.85934"
+         y="609.59003">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-80"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(39.356201,463.53264)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="256.75986"
+       y="586.99133"
+       id="text4648-5-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-77-7"
+         x="256.75986"
+         y="586.99133">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-80-5"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-101.74328,440.93395)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="546.22791"
+       y="213.91006"
+       id="text4461-2-5"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2-6"
+         x="546.22791"
+         y="213.91006">thread3()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="684.00067"
+       y="213.91006"
+       id="text4461-2-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2-0"
+         x="684.00067"
+         y="213.91006">thread4()</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
new file mode 100644
index 000000000000..a725f9900ec8
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -0,0 +1,2897 @@
+<!-- DO NOT HAND EDIT. -->
+<!-- Instead, edit Documentation/RCU/Design/Requirements/Requirements.htmlx and run 'sh htmlqqz.sh Documentation/RCU/Design/Requirements/Requirements' -->
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+        <html>
+        <head><title>A Tour Through RCU's Requirements [LWN.net]</title>
+        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
+
+<h1>A Tour Through RCU's Requirements</h1>
+
+<p>Copyright IBM Corporation, 2015</p>
+<p>Author: Paul E.&nbsp;McKenney</p>
+<p><i>The initial version of this document appeared in the
+<a href="https://lwn.net/">LWN</a> articles
+<a href="https://lwn.net/Articles/652156/">here</a>,
+<a href="https://lwn.net/Articles/652677/">here</a>, and
+<a href="https://lwn.net/Articles/653326/">here</a>.</i></p>
+
+<h2>Introduction</h2>
+
+<p>
+Read-copy update (RCU) is a synchronization mechanism that is often
+used as a replacement for reader-writer locking.
+RCU is unusual in that updaters do not block readers,
+which means that RCU's read-side primitives can be exceedingly fast
+and scalable.
+In addition, updaters can make useful forward progress concurrently
+with readers.
+However, all this concurrency between RCU readers and updaters does raise
+the question of exactly what RCU readers are doing, which in turn
+raises the question of exactly what RCU's requirements are.
+
+<p>
+This document therefore summarizes RCU's requirements, and can be thought
+of as an informal, high-level specification for RCU.
+It is important to understand that RCU's specification is primarily
+empirical in nature;
+in fact, I learned about many of these requirements the hard way.
+This situation might cause some consternation, however, not only
+has this learning process been a lot of fun, but it has also been
+a great privilege to work with so many people willing to apply
+technologies in interesting new ways.
+
+<p>
+All that aside, here are the categories of currently known RCU requirements:
+</p>
+
+<ol>
+<li>	<a href="#Fundamental Requirements">
+	Fundamental Requirements</a>
+<li>	<a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a>
+<li>	<a href="#Parallelism Facts of Life">
+	Parallelism Facts of Life</a>
+<li>	<a href="#Quality-of-Implementation Requirements">
+	Quality-of-Implementation Requirements</a>
+<li>	<a href="#Linux Kernel Complications">
+	Linux Kernel Complications</a>
+<li>	<a href="#Software-Engineering Requirements">
+	Software-Engineering Requirements</a>
+<li>	<a href="#Other RCU Flavors">
+	Other RCU Flavors</a>
+<li>	<a href="#Possible Future Changes">
+	Possible Future Changes</a>
+</ol>
+
+<p>
+This is followed by a <a href="#Summary">summary</a>,
+which is in turn followed by the inevitable
+<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
+
+<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2>
+
+<p>
+RCU's fundamental requirements are the closest thing RCU has to hard
+mathematical requirements.
+These are:
+
+<ol>
+<li>	<a href="#Grace-Period Guarantee">
+	Grace-Period Guarantee</a>
+<li>	<a href="#Publish-Subscribe Guarantee">
+	Publish-Subscribe Guarantee</a>
+<li>	<a href="#Memory-Barrier Guarantees">
+	Memory-Barrier Guarantees</a>
+<li>	<a href="#RCU Primitives Guaranteed to Execute Unconditionally">
+	RCU Primitives Guaranteed to Execute Unconditionally</a>
+<li>	<a href="#Guaranteed Read-to-Write Upgrade">
+	Guaranteed Read-to-Write Upgrade</a>
+</ol>
+
+<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3>
+
+<p>
+RCU's grace-period guarantee is unusual in being premeditated:
+Jack Slingwine and I had this guarantee firmly in mind when we started
+work on RCU (then called &ldquo;rclock&rdquo;) in the early 1990s.
+That said, the past two decades of experience with RCU have produced
+a much more detailed understanding of this guarantee.
+
+<p>
+RCU's grace-period guarantee allows updaters to wait for the completion
+of all pre-existing RCU read-side critical sections.
+An RCU read-side critical section
+begins with the marker <tt>rcu_read_lock()</tt> and ends with
+the marker <tt>rcu_read_unlock()</tt>.
+These markers may be nested, and RCU treats a nested set as one
+big RCU read-side critical section.
+Production-quality implementations of <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> are extremely lightweight, and in
+fact have exactly zero overhead in Linux kernels built for production
+use with <tt>CONFIG_PREEMPT=n</tt>.
+
+<p>
+This guarantee allows ordering to be enforced with extremely low
+overhead to readers, for example:
+
+<blockquote>
+<pre>
+ 1 int x, y;
+ 2
+ 3 void thread0(void)
+ 4 {
+ 5   rcu_read_lock();
+ 6   r1 = READ_ONCE(x);
+ 7   r2 = READ_ONCE(y);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   WRITE_ONCE(x, 1);
+14   synchronize_rcu();
+15   WRITE_ONCE(y, 1);
+16 }
+</pre>
+</blockquote>
+
+<p>
+Because the <tt>synchronize_rcu()</tt> on line&nbsp;14 waits for
+all pre-existing readers, any instance of <tt>thread0()</tt> that
+loads a value of zero from <tt>x</tt> must complete before
+<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must
+also load a value of zero from <tt>y</tt>.
+Similarly, any instance of <tt>thread0()</tt> that loads a value of
+one from <tt>y</tt> must have started after the
+<tt>synchronize_rcu()</tt> started, and must therefore also load
+a value of one from <tt>x</tt>.
+Therefore, the outcome:
+<blockquote>
+<pre>
+(r1 == 0 &amp;&amp; r2 == 1)
+</pre>
+</blockquote>
+cannot happen.
+
+<p><a name="Quick Quiz 1"><b>Quick Quiz 1</b>:</a>
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+<br><a href="#qq1answer">Answer</a>
+
+<p>
+This scenario resembles one of the first uses of RCU in
+<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>,
+which managed a distributed lock manager's transition into
+a state suitable for handling recovery from node failure,
+more or less as follows:
+
+<blockquote>
+<pre>
+ 1 #define STATE_NORMAL        0
+ 2 #define STATE_WANT_RECOVERY 1
+ 3 #define STATE_RECOVERING    2
+ 4 #define STATE_WANT_NORMAL   3
+ 5
+ 6 int state = STATE_NORMAL;
+ 7
+ 8 void do_something_dlm(void)
+ 9 {
+10   int state_snap;
+11
+12   rcu_read_lock();
+13   state_snap = READ_ONCE(state);
+14   if (state_snap == STATE_NORMAL)
+15     do_something();
+16   else
+17     do_something_carefully();
+18   rcu_read_unlock();
+19 }
+20
+21 void start_recovery(void)
+22 {
+23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
+24   synchronize_rcu();
+25   WRITE_ONCE(state, STATE_RECOVERING);
+26   recovery();
+27   WRITE_ONCE(state, STATE_WANT_NORMAL);
+28   synchronize_rcu();
+29   WRITE_ONCE(state, STATE_NORMAL);
+30 }
+</pre>
+</blockquote>
+
+<p>
+The RCU read-side critical section in <tt>do_something_dlm()</tt>
+works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt>
+to guarantee that <tt>do_something()</tt> never runs concurrently
+with <tt>recovery()</tt>, but with little or no synchronization
+overhead in <tt>do_something_dlm()</tt>.
+
+<p><a name="Quick Quiz 2"><b>Quick Quiz 2</b>:</a>
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+<br><a href="#qq2answer">Answer</a>
+
+<p>
+In order to avoid fatal problems such as deadlocks,
+an RCU read-side critical section must not contain calls to
+<tt>synchronize_rcu()</tt>.
+Similarly, an RCU read-side critical section must not
+contain anything that waits, directly or indirectly, on completion of
+an invocation of <tt>synchronize_rcu()</tt>.
+
+<p>
+Although RCU's grace-period guarantee is useful in and of itself, with
+<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>,
+it would be good to be able to use RCU to coordinate read-side
+access to linked data structures.
+For this, the grace-period guarantee is not sufficient, as can
+be seen in function <tt>add_gp_buggy()</tt> below.
+We will look at the reader's code later, but in the meantime, just think of
+the reader as locklessly picking up the <tt>gp</tt> pointer,
+and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the
+<tt>-&gt;a</tt> and <tt>-&gt;b</tt> fields.
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   gp = p; /* ORDERING BUG */
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The problem is that both the compiler and weakly ordered CPUs are within
+their rights to reorder this code as follows:
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy_optimized(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+<b>11   gp = p; /* ORDERING BUG */
+12   p-&gt;a = a;
+13   p-&gt;b = a;</b>
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+If an RCU reader fetches <tt>gp</tt> just after
+<tt>add_gp_buggy_optimized</tt> executes line&nbsp;11,
+it will see garbage in the <tt>-&gt;a</tt> and <tt>-&gt;b</tt>
+fields.
+And this is but one of many ways in which compiler and hardware optimizations
+could cause trouble.
+Therefore, we clearly need some way to prevent the compiler and the CPU from
+reordering in this manner, which brings us to the publish-subscribe
+guarantee discussed in the next section.
+
+<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3>
+
+<p>
+RCU's publish-subscribe guarantee allows data to be inserted
+into a linked data structure without disrupting RCU readers.
+The updater uses <tt>rcu_assign_pointer()</tt> to insert the
+new data, and readers use <tt>rcu_dereference()</tt> to
+access data, whether new or old.
+The following shows an example of insertion:
+
+<blockquote>
+<pre>
+ 1 bool add_gp(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   rcu_assign_pointer(gp, p);
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_assign_pointer()</tt> on line&nbsp;13 is conceptually
+equivalent to a simple assignment statement, but also guarantees
+that its assignment will
+happen after the two assignments in lines&nbsp;11 and&nbsp;12,
+similar to the C11 <tt>memory_order_release</tt> store operation.
+It also prevents any number of &ldquo;interesting&rdquo; compiler
+optimizations, for example, the use of <tt>gp</tt> as a scratch
+location immediately preceding the assignment.
+
+<p><a name="Quick Quiz 3"><b>Quick Quiz 3</b>:</a>
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+<br><a href="#qq3answer">Answer</a>
+
+<p>
+It is tempting to assume that the reader need not do anything special
+to control its accesses to the RCU-protected data,
+as shown in <tt>do_something_gp_buggy()</tt> below:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+However, this temptation must be resisted because there are a
+surprisingly large number of ways that the compiler
+(to say nothing of
+<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>)
+can trip this code up.
+For but one example, if the compiler were short of registers, it
+might choose to refetch from <tt>gp</tt> rather than keeping
+a separate copy in <tt>p</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy_optimized(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
+<b> 5     do_something(gp-&gt;a, gp-&gt;b);</b>
+ 6     rcu_read_unlock();
+ 7     return true;
+ 8   }
+ 9   rcu_read_unlock();
+10   return false;
+11 }
+</pre>
+</blockquote>
+
+<p>
+If this function ran concurrently with a series of updates that
+replaced the current structure with a new one,
+the fetches of <tt>gp-&gt;a</tt>
+and <tt>gp-&gt;b</tt> might well come from two different structures,
+which could cause serious confusion.
+To prevent this (and much else besides), <tt>do_something_gp()</tt> uses
+<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = rcu_dereference(gp);
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha)
+memory barriers in the Linux kernel.
+Should a
+<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a>
+ever appear, then <tt>rcu_dereference()</tt> could be implemented
+as a <tt>memory_order_consume</tt> load.
+Regardless of the exact implementation, a pointer fetched by
+<tt>rcu_dereference()</tt> may not be used outside of the
+outermost RCU read-side critical section containing that
+<tt>rcu_dereference()</tt>, unless protection of
+the corresponding data element has been passed from RCU to some
+other synchronization mechanism, most commonly locking or
+<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>.
+
+<p>
+In short, updaters use <tt>rcu_assign_pointer()</tt> and readers
+use <tt>rcu_dereference()</tt>, and these two RCU API elements
+work together to ensure that readers have a consistent view of
+newly added data elements.
+
+<p>
+Of course, it is also necessary to remove elements from RCU-protected
+data structures, for example, using the following process:
+
+<ol>
+<li>	Remove the data element from the enclosing structure.
+<li>	Wait for all pre-existing RCU read-side critical sections
+	to complete (because only pre-existing readers can possibly have
+	a reference to the newly removed data element).
+<li>	At this point, only the updater has a reference to the
+	newly removed data element, so it can safely reclaim
+	the data element, for example, by passing it to <tt>kfree()</tt>.
+</ol>
+
+This process is implemented by <tt>remove_gp_synchronous()</tt>:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_synchronous(void)
+ 2 {
+ 3   struct foo *p;
+ 4
+ 5   spin_lock(&amp;gp_lock);
+ 6   p = rcu_access_pointer(gp);
+ 7   if (!p) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   rcu_assign_pointer(gp, NULL);
+12   spin_unlock(&amp;gp_lock);
+13   synchronize_rcu();
+14   kfree(p);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+This function is straightforward, with line&nbsp;13 waiting for a grace
+period before line&nbsp;14 frees the old data element.
+This waiting ensures that readers will reach line&nbsp;7 of
+<tt>do_something_gp()</tt> before the data element referenced by
+<tt>p</tt> is freed.
+The <tt>rcu_access_pointer()</tt> on line&nbsp;6 is similar to
+<tt>rcu_dereference()</tt>, except that:
+
+<ol>
+<li>	The value returned by <tt>rcu_access_pointer()</tt>
+	cannot be dereferenced.
+	If you want to access the value pointed to as well as
+	the pointer itself, use <tt>rcu_dereference()</tt>
+	instead of <tt>rcu_access_pointer()</tt>.
+<li>	The call to <tt>rcu_access_pointer()</tt> need not be
+	protected.
+	In contrast, <tt>rcu_dereference()</tt> must either be
+	within an RCU read-side critical section or in a code
+	segment where the pointer cannot change, for example, in
+	code protected by the corresponding update-side lock.
+</ol>
+
+<p><a name="Quick Quiz 4"><b>Quick Quiz 4</b>:</a>
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+<br><a href="#qq4answer">Answer</a>
+
+<p>
+In short, RCU's publish-subscribe guarantee is provided by the combination
+of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>.
+This guarantee allows data elements to be safely added to RCU-protected
+linked data structures without disrupting RCU readers.
+This guarantee can be used in combination with the grace-period
+guarantee to also allow data elements to be removed from RCU-protected
+linked data structures, again without disrupting RCU readers.
+
+<p>
+This guarantee was only partially premeditated.
+DYNIX/ptx used an explicit memory barrier for publication, but had nothing
+resembling <tt>rcu_dereference()</tt> for subscription, nor did it
+have anything resembling the <tt>smp_read_barrier_depends()</tt>
+that was later subsumed into <tt>rcu_dereference()</tt>.
+The need for these operations made itself known quite suddenly at a
+late-1990s meeting with the DEC Alpha architects, back in the days when
+DEC was still a free-standing company.
+It took the Alpha architects a good hour to convince me that any sort
+of barrier would ever be needed, and it then took me a good <i>two</i> hours
+to convince them that their documentation did not make this point clear.
+More recent work with the C and C++ standards committees have provided
+much education on tricks and traps from the compiler.
+In short, compilers were much less tricky in the early 1990s, but in
+2015, don't even think about omitting <tt>rcu_dereference()</tt>!
+
+<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3>
+
+<p>
+The previous section's simple linked-data-structure scenario clearly
+demonstrates the need for RCU's stringent memory-ordering guarantees on
+systems with more than one CPU:
+
+<ol>
+<li>	Each CPU that has an RCU read-side critical section that
+	begins before <tt>synchronize_rcu()</tt> starts is
+	guaranteed to execute a full memory barrier between the time
+	that the RCU read-side critical section ends and the time that
+	<tt>synchronize_rcu()</tt> returns.
+	Without this guarantee, a pre-existing RCU read-side critical section
+	might hold a reference to the newly removed <tt>struct foo</tt>
+	after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt>.
+<li>	Each CPU that has an RCU read-side critical section that ends
+	after <tt>synchronize_rcu()</tt> returns is guaranteed
+	to execute a full memory barrier between the time that
+	<tt>synchronize_rcu()</tt> begins and the time that the RCU
+	read-side critical section begins.
+	Without this guarantee, a later RCU read-side critical section
+	running after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt> might
+	later run <tt>do_something_gp()</tt> and find the
+	newly deleted <tt>struct foo</tt>.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> remains
+	on a given CPU, then that CPU is guaranteed to execute a full
+	memory barrier sometime during the execution of
+	<tt>synchronize_rcu()</tt>.
+	This guarantee ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on line&nbsp;11.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> migrates
+	among a group of CPUs during that invocation, then each of the
+	CPUs in that group is guaranteed to execute a full memory barrier
+	sometime during the execution of <tt>synchronize_rcu()</tt>.
+	This guarantee also ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on
+	line&nbsp;11, but also in the case where the thread executing the
+	<tt>synchronize_rcu()</tt> migrates in the meantime.
+</ol>
+
+<p><a name="Quick Quiz 5"><b>Quick Quiz 5</b>:</a>
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+<br><a href="#qq5answer">Answer</a>
+
+<p><a name="Quick Quiz 6"><b>Quick Quiz 6</b>:</a>
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+<br><a href="#qq6answer">Answer</a>
+
+<p>
+Note that these memory-barrier requirements do not replace the fundamental
+RCU requirement that a grace period wait for all pre-existing readers.
+On the contrary, the memory barriers called out in this section must operate in
+such a way as to <i>enforce</i> this fundamental requirement.
+Of course, different implementations enforce this requirement in different
+ways, but enforce it they must.
+
+<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3>
+
+<p>
+The common-case RCU primitives are unconditional.
+They are invoked, they do their job, and they return, with no possibility
+of error, and no need to retry.
+This is a key RCU design philosophy.
+
+<p>
+However, this philosophy is pragmatic rather than pigheaded.
+If someone comes up with a good justification for a particular conditional
+RCU primitive, it might well be implemented and added.
+After all, this guarantee was reverse-engineered, not premeditated.
+The unconditional nature of the RCU primitives was initially an
+accident of implementation, and later experience with synchronization
+primitives with conditional primitives caused me to elevate this
+accident to a guarantee.
+Therefore, the justification for adding a conditional primitive to
+RCU would need to be based on detailed and compelling use cases.
+
+<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3>
+
+<p>
+As far as RCU is concerned, it is always possible to carry out an
+update within an RCU read-side critical section.
+For example, that RCU read-side critical section might search for
+a given data element, and then might acquire the update-side
+spinlock in order to update that element, all while remaining
+in that RCU read-side critical section.
+Of course, it is necessary to exit the RCU read-side critical section
+before invoking <tt>synchronize_rcu()</tt>, however, this
+inconvenience can be avoided through use of the
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members
+described later in this document.
+
+<p><a name="Quick Quiz 7"><b>Quick Quiz 7</b>:</a>
+But how does the upgrade-to-write operation exclude other readers?
+<br><a href="#qq7answer">Answer</a>
+
+<p>
+This guarantee allows lookup code to be shared between read-side
+and update-side code, and was premeditated, appearing in the earliest
+DYNIX/ptx RCU documentation.
+
+<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2>
+
+<p>
+RCU provides extremely lightweight readers, and its read-side guarantees,
+though quite useful, are correspondingly lightweight.
+It is therefore all too easy to assume that RCU is guaranteeing more
+than it really is.
+Of course, the list of things that RCU does not guarantee is infinitely
+long, however, the following sections list a few non-guarantees that
+have caused confusion.
+Except where otherwise noted, these non-guarantees were premeditated.
+
+<ol>
+<li>	<a href="#Readers Impose Minimal Ordering">
+	Readers Impose Minimal Ordering</a>
+<li>	<a href="#Readers Do Not Exclude Updaters">
+	Readers Do Not Exclude Updaters</a>
+<li>	<a href="#Updaters Only Wait For Old Readers">
+	Updaters Only Wait For Old Readers</a>
+<li>	<a href="#Grace Periods Don't Partition Read-Side Critical Sections">
+	Grace Periods Don't Partition Read-Side Critical Sections</a>
+<li>	<a href="#Read-Side Critical Sections Don't Partition Grace Periods">
+	Read-Side Critical Sections Don't Partition Grace Periods</a>
+<li>	<a href="#Disabling Preemption Does Not Block Grace Periods">
+	Disabling Preemption Does Not Block Grace Periods</a>
+</ol>
+
+<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3>
+
+<p>
+Reader-side markers such as <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees
+except through their interaction with the grace-period APIs such as
+<tt>synchronize_rcu()</tt>.
+To see this, consider the following pair of threads:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(x, 1);
+ 5   rcu_read_unlock();
+ 6   rcu_read_lock();
+ 7   WRITE_ONCE(y, 1);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   rcu_read_lock();
+14   r1 = READ_ONCE(y);
+15   rcu_read_unlock();
+16   rcu_read_lock();
+17   r2 = READ_ONCE(x);
+18   rcu_read_unlock();
+19 }
+</pre>
+</blockquote>
+
+<p>
+After <tt>thread0()</tt> and <tt>thread1()</tt> execute
+concurrently, it is quite possible to have
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0)
+</pre>
+</blockquote>
+
+(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>),
+which would not be possible if <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> had much in the way of ordering
+properties.
+But they do not, so the CPU is within its rights
+to do significant reordering.
+This is by design:  Any significant ordering constraints would slow down
+these fast-path APIs.
+
+<p><a name="Quick Quiz 8"><b>Quick Quiz 8</b>:</a>
+Can't the compiler also reorder this code?
+<br><a href="#qq8answer">Answer</a>
+
+<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3>
+
+<p>
+Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt>
+exclude updates.
+All they do is to prevent grace periods from ending.
+The following example illustrates this:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   r1 = READ_ONCE(y);
+ 5   if (r1) {
+ 6     do_something_with_nonzero_x();
+ 7     r2 = READ_ONCE(x);
+ 8     WARN_ON(!r2); /* BUG!!! */
+ 9   }
+10   rcu_read_unlock();
+11 }
+12
+13 void thread1(void)
+14 {
+15   spin_lock(&amp;my_lock);
+16   WRITE_ONCE(x, 1);
+17   WRITE_ONCE(y, 1);
+18   spin_unlock(&amp;my_lock);
+19 }
+</pre>
+</blockquote>
+
+<p>
+If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt>
+excluded the <tt>thread1()</tt> function's update,
+the <tt>WARN_ON()</tt> could never fire.
+But the fact is that <tt>rcu_read_lock()</tt> does not exclude
+much of anything aside from subsequent grace periods, of which
+<tt>thread1()</tt> has none, so the
+<tt>WARN_ON()</tt> can and does fire.
+
+<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3>
+
+<p>
+It might be tempting to assume that after <tt>synchronize_rcu()</tt>
+completes, there are no readers executing.
+This temptation must be avoided because
+new readers can start immediately after <tt>synchronize_rcu()</tt>
+starts, and <tt>synchronize_rcu()</tt> is under no
+obligation to wait for these new readers.
+
+<p><a name="Quick Quiz 9"><b>Quick Quiz 9</b>:</a>
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+<br><a href="#qq9answer">Answer</a>
+
+<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections">
+Grace Periods Don't Partition Read-Side Critical Sections</a></h3>
+
+<p>
+It is tempting to assume that if any part of one RCU read-side critical
+section precedes a given grace period, and if any part of another RCU
+read-side critical section follows that same grace period, then all of
+the first RCU read-side critical section must precede all of the second.
+However, this just isn't the case: A single grace period does not
+partition the set of RCU read-side critical sections.
+An example of this situation can be illustrated as follows, where
+<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   r2 = READ_ONCE(b);
+20   r3 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+</pre>
+</blockquote>
+
+<p>
+It turns out that the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0 &amp;&amp; r3 == 1)
+</pre>
+</blockquote>
+
+is entirely possible.
+The following figure show how this can happen, with each circled
+<tt>QS</tt> indicating the point at which RCU recorded a
+<i>quiescent state</i> for each thread, that is, a state in which
+RCU knows that the thread cannot be in the midst of an RCU read-side
+critical section that started before the current grace period:
+
+<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p>
+
+<p>
+If it is necessary to partition RCU read-side critical sections in this
+manner, it is necessary to use two grace periods, where the first
+grace period is known to end before the second grace period starts:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   r2 = READ_ONCE(c);
+19   synchronize_rcu();
+20   WRITE_ONCE(d, 1);
+21 }
+22
+23 void thread3(void)
+24 {
+25   rcu_read_lock();
+26   r3 = READ_ONCE(b);
+27   r4 = READ_ONCE(d);
+28   rcu_read_unlock();
+29 }
+</pre>
+</blockquote>
+
+<p>
+Here, if <tt>(r1 == 1)</tt>, then
+<tt>thread0()</tt>'s write to <tt>b</tt> must happen
+before the end of <tt>thread1()</tt>'s grace period.
+If in addition <tt>(r4 == 1)</tt>, then
+<tt>thread3()</tt>'s read from <tt>b</tt> must happen
+after the beginning of <tt>thread2()</tt>'s grace period.
+If it is also the case that <tt>(r2 == 1)</tt>, then the
+end of <tt>thread1()</tt>'s grace period must precede the
+beginning of <tt>thread2()</tt>'s grace period.
+This mean that the two RCU read-side critical sections cannot overlap,
+guaranteeing that <tt>(r3 == 1)</tt>.
+As a result, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 0 &amp;&amp; r4 == 1)
+</pre>
+</blockquote>
+
+cannot happen.
+
+<p>
+This non-requirement was also non-premeditated, but became apparent
+when studying RCU's interaction with memory ordering.
+
+<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods">
+Read-Side Critical Sections Don't Partition Grace Periods</a></h3>
+
+<p>
+It is also tempting to assume that if an RCU read-side critical section
+happens between a pair of grace periods, then those grace periods cannot
+overlap.
+However, this temptation leads nowhere good, as can be illustrated by
+the following, with all variables initially zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   WRITE_ONCE(d, 1);
+20   r2 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+23
+24 void thread3(void)
+25 {
+26   r3 = READ_ONCE(d);
+27   synchronize_rcu();
+28   WRITE_ONCE(e, 1);
+29 }
+30
+31 void thread4(void)
+32 {
+33   rcu_read_lock();
+34   r4 = READ_ONCE(b);
+35   r5 = READ_ONCE(e);
+36   rcu_read_unlock();
+37 }
+</pre>
+</blockquote>
+
+<p>
+In this case, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 1 &amp;&amp; r4 == 0 &amp&amp; r5 == 1)
+</pre>
+</blockquote>
+
+is entirely possible, as illustrated below:
+
+<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p>
+
+<p>
+Again, an RCU read-side critical section can overlap almost all of a
+given grace period, just so long as it does not overlap the entire
+grace period.
+As a result, an RCU read-side critical section cannot partition a pair
+of RCU grace periods.
+
+<p><a name="Quick Quiz 10"><b>Quick Quiz 10</b>:</a>
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+<br><a href="#qq10answer">Answer</a>
+
+<h3><a name="Disabling Preemption Does Not Block Grace Periods">
+Disabling Preemption Does Not Block Grace Periods</a></h3>
+
+<p>
+There was a time when disabling preemption on any given CPU would block
+subsequent grace periods.
+However, this was an accident of implementation and is not a requirement.
+And in the current Linux-kernel implementation, disabling preemption
+on a given CPU in fact does not block grace periods, as Oleg Nesterov
+<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>.
+
+<p>
+If you need a preempt-disable region to block grace periods, you need to add
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example
+as follows:
+
+<blockquote>
+<pre>
+ 1 preempt_disable();
+ 2 rcu_read_lock();
+ 3 do_something();
+ 4 rcu_read_unlock();
+ 5 preempt_enable();
+ 6
+ 7 /* Spinlocks implicitly disable preemption. */
+ 8 spin_lock(&amp;mylock);
+ 9 rcu_read_lock();
+10 do_something();
+11 rcu_read_unlock();
+12 spin_unlock(&amp;mylock);
+</pre>
+</blockquote>
+
+<p>
+In theory, you could enter the RCU read-side critical section first,
+but it is more efficient to keep the entire RCU read-side critical
+section contained in the preempt-disable region as shown above.
+Of course, RCU read-side critical sections that extend outside of
+preempt-disable regions will work correctly, but such critical sections
+can be preempted, which forces <tt>rcu_read_unlock()</tt> to do
+more work.
+And no, this is <i>not</i> an invitation to enclose all of your RCU
+read-side critical sections within preempt-disable regions, because
+doing so would degrade real-time response.
+
+<p>
+This non-requirement appeared with preemptible RCU.
+If you need a grace period that waits on non-preemptible code regions, use
+<a href="#Sched Flavor">RCU-sched</a>.
+
+<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2>
+
+<p>
+These parallelism facts of life are by no means specific to RCU, but
+the RCU implementation must abide by them.
+They therefore bear repeating:
+
+<ol>
+<li>	Any CPU or task may be delayed at any time,
+	and any attempts to avoid these delays by disabling
+	preemption, interrupts, or whatever are completely futile.
+	This is most obvious in preemptible user-level
+	environments and in virtualized environments (where
+	a given guest OS's VCPUs can be preempted at any time by
+	the underlying hypervisor), but can also happen in bare-metal
+	environments due to ECC errors, NMIs, and other hardware
+	events.
+	Although a delay of more than about 20 seconds can result
+	in splats, the RCU implementation is obligated to use
+	algorithms that can tolerate extremely long delays, but where
+	&ldquo;extremely long&rdquo; is not long enough to allow
+	wrap-around when incrementing a 64-bit counter.
+<li>	Both the compiler and the CPU can reorder memory accesses.
+	Where it matters, RCU must use compiler directives and
+	memory-barrier instructions to preserve ordering.
+<li>	Conflicting writes to memory locations in any given cache line
+	will result in expensive cache misses.
+	Greater numbers of concurrent writes and more-frequent
+	concurrent writes will result in more dramatic slowdowns.
+	RCU is therefore obligated to use algorithms that have
+	sufficient locality to avoid significant performance and
+	scalability problems.
+<li>	As a rough rule of thumb, only one CPU's worth of processing
+	may be carried out under the protection of any given exclusive
+	lock.
+	RCU must therefore use scalable locking designs.
+<li>	Counters are finite, especially on 32-bit systems.
+	RCU's use of counters must therefore tolerate counter wrap,
+	or be designed such that counter wrap would take way more
+	time than a single system is likely to run.
+	An uptime of ten years is quite possible, a runtime
+	of a century much less so.
+	As an example of the latter, RCU's dyntick-idle nesting counter
+	allows 54 bits for interrupt nesting level (this counter
+	is 64 bits even on a 32-bit system).
+	Overflowing this counter requires 2<sup>54</sup>
+	half-interrupts on a given CPU without that CPU ever going idle.
+	If a half-interrupt happened every microsecond, it would take
+	570 years of runtime to overflow this counter, which is currently
+	believed to be an acceptably long time.
+<li>	Linux systems can have thousands of CPUs running a single
+	Linux kernel in a single shared-memory environment.
+	RCU must therefore pay close attention to high-end scalability.
+</ol>
+
+<p>
+This last parallelism fact of life means that RCU must pay special
+attention to the preceding facts of life.
+The idea that Linux might scale to systems with thousands of CPUs would
+have been met with some skepticism in the 1990s, but these requirements
+would have otherwise have been unsurprising, even in the early 1990s.
+
+<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2>
+
+<p>
+These sections list quality-of-implementation requirements.
+Although an RCU implementation that ignores these requirements could
+still be used, it would likely be subject to limitations that would
+make it inappropriate for industrial-strength production use.
+Classes of quality-of-implementation requirements are as follows:
+
+<ol>
+<li>	<a href="#Specialization">Specialization</a>
+<li>	<a href="#Performance and Scalability">Performance and Scalability</a>
+<li>	<a href="#Composability">Composability</a>
+<li>	<a href="#Corner Cases">Corner Cases</a>
+</ol>
+
+<p>
+These classes is covered in the following sections.
+
+<h3><a name="Specialization">Specialization</a></h3>
+
+<p>
+RCU is and always has been intended primarily for read-mostly situations, as
+illustrated by the following figure.
+This means that RCU's read-side primitives are optimized, often at the
+expense of its update-side primitives.
+
+<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p>
+
+<p>
+This focus on read-mostly situations means that RCU must interoperate
+with other synchronization primitives.
+For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt>
+examples discussed earlier use RCU to protect readers and locking to
+coordinate updaters.
+However, the need extends much farther, requiring that a variety of
+synchronization primitives be legal within RCU read-side critical sections,
+including spinlocks, sequence locks, atomic operations, reference
+counters, and memory barriers.
+
+<p><a name="Quick Quiz 11"><b>Quick Quiz 11</b>:</a>
+What about sleeping locks?
+<br><a href="#qq11answer">Answer</a>
+
+<p>
+It often comes as a surprise that many algorithms do not require a
+consistent view of data, but many can function in that mode,
+with network routing being the poster child.
+Internet routing algorithms take significant time to propagate
+updates, so that by the time an update arrives at a given system,
+that system has been sending network traffic the wrong way for
+a considerable length of time.
+Having a few threads continue to send traffic the wrong way for a
+few more milliseconds is clearly not a problem:  In the worst case,
+TCP retransmissions will eventually get the data where it needs to go.
+In general, when tracking the state of the universe outside of the
+computer, some level of inconsistency must be tolerated due to
+speed-of-light delays if nothing else.
+
+<p>
+Furthermore, uncertainty about external state is inherent in many cases.
+For example, a pair of veternarians might use heartbeat to determine
+whether or not a given cat was alive.
+But how long should they wait after the last heartbeat to decide that
+the cat is in fact dead?
+Waiting less than 400 milliseconds makes no sense because this would
+mean that a relaxed cat would be considered to cycle between death
+and life more than 100 times per minute.
+Moreover, just as with human beings, a cat's heart might stop for
+some period of time, so the exact wait period is a judgment call.
+One of our pair of veternarians might wait 30 seconds before pronouncing
+the cat dead, while the other might insist on waiting a full minute.
+The two veternarians would then disagree on the state of the cat during
+the final 30 seconds of the minute following the last heartbeat, as
+fancifully illustrated below:
+
+<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p>
+
+<p>
+Interestingly enough, this same situation applies to hardware.
+When push comes to shove, how do we tell whether or not some
+external server has failed?
+We send messages to it periodically, and declare it failed if we
+don't receive a response within a given period of time.
+Policy decisions can usually tolerate short
+periods of inconsistency.
+The policy was decided some time ago, and is only now being put into
+effect, so a few milliseconds of delay is normally inconsequential.
+
+<p>
+However, there are algorithms that absolutely must see consistent data.
+For example, the translation between a user-level SystemV semaphore
+ID to the corresponding in-kernel data structure is protected by RCU,
+but it is absolutely forbidden to update a semaphore that has just been
+removed.
+In the Linux kernel, this need for consistency is accommodated by acquiring
+spinlocks located in the in-kernel data structure from within
+the RCU read-side critical section, and this is indicated by the
+green box in the figure above.
+Many other techniques may be used, and are in fact used within the
+Linux kernel.
+
+<p>
+In short, RCU is not required to maintain consistency, and other
+mechanisms may be used in concert with RCU when consistency is required.
+RCU's specialization allows it to do its job extremely well, and its
+ability to interoperate with other synchronization mechanisms allows
+the right mix of synchronization tools to be used for a given job.
+
+<h3><a name="Performance and Scalability">Performance and Scalability</a></h3>
+
+<p>
+Energy efficiency is a critical component of performance today,
+and Linux-kernel RCU implementations must therefore avoid unnecessarily
+awakening idle CPUs.
+I cannot claim that this requirement was premeditated.
+In fact, I learned of it during a telephone conversation in which I
+was given &ldquo;frank and open&rdquo; feedback on the importance
+of energy efficiency in battery-powered systems and on specific
+energy-efficiency shortcomings of the Linux-kernel RCU implementation.
+In my experience, the battery-powered embedded community will consider
+any unnecessary wakeups to be extremely unfriendly acts.
+So much so that mere Linux-kernel-mailing-list posts are
+insufficient to vent their ire.
+
+<p>
+Memory consumption is not particularly important for in most
+situations, and has become decreasingly
+so as memory sizes have expanded and memory
+costs have plummeted.
+However, as I learned from Matt Mackall's
+<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
+efforts, memory footprint is critically important on single-CPU systems with
+non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
+<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
+was born.
+Josh Triplett has since taken over the small-memory banner with his
+<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a>
+project, which resulted in
+<a href="#Sleepable RCU">SRCU</a>
+becoming optional for those kernels not needing it.
+
+<p>
+The remaining performance requirements are, for the most part,
+unsurprising.
+For example, in keeping with RCU's read-side specialization,
+<tt>rcu_dereference()</tt> should have negligible overhead (for
+example, suppression of a few minor compiler optimizations).
+Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have exactly zero overhead.
+
+<p>
+In preemptible environments, in the case where the RCU read-side
+critical section was not preempted (as will be the case for the
+highest-priority real-time process), <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have minimal overhead.
+In particular, they should not contain atomic read-modify-write
+operations, memory-barrier instructions, preemption disabling,
+interrupt disabling, or backwards branches.
+However, in the case where the RCU read-side critical section was preempted,
+<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts.
+This is why it is better to nest an RCU read-side critical section
+within a preempt-disable region than vice versa, at least in cases
+where that critical section is short enough to avoid unduly degrading
+real-time latencies.
+
+<p>
+The <tt>synchronize_rcu()</tt> grace-period-wait primitive is
+optimized for throughput.
+It may therefore incur several milliseconds of latency in addition to
+the duration of the longest RCU read-side critical section.
+On the other hand, multiple concurrent invocations of
+<tt>synchronize_rcu()</tt> are required to use batching optimizations
+so that they can be satisfied by a single underlying grace-period-wait
+operation.
+For example, in the Linux kernel, it is not unusual for a single
+grace-period-wait operation to serve more than
+<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a>
+of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation
+overhead down to nearly zero.
+However, the grace-period optimization is also required to avoid
+measurable degradation of real-time scheduling and interrupt latencies.
+
+<p>
+In some cases, the multi-millisecond <tt>synchronize_rcu()</tt>
+latencies are unacceptable.
+In these cases, <tt>synchronize_rcu_expedited()</tt> may be used
+instead, reducing the grace-period latency down to a few tens of
+microseconds on small systems, at least in cases where the RCU read-side
+critical sections are short.
+There are currently no special latency requirements for
+<tt>synchronize_rcu_expedited()</tt> on large systems, but,
+consistent with the empirical nature of the RCU specification,
+that is subject to change.
+However, there most definitely are scalability requirements:
+A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096
+CPUs should at least make reasonable forward progress.
+In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
+is permitted to impose modest degradation of real-time latency
+on non-idle online CPUs.
+That said, it will likely be necessary to take further steps to reduce this
+degradation, hopefully to roughly that of a scheduling-clock interrupt.
+
+<p>
+There are a number of situations where even
+<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period
+latency is unacceptable.
+In these situations, the asynchronous <tt>call_rcu()</tt> can be
+used in place of <tt>synchronize_rcu()</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 static void remove_gp_cb(struct rcu_head *rhp)
+ 8 {
+ 9   struct foo *p = container_of(rhp, struct foo, rh);
+10
+11   kfree(p);
+12 }
+13
+14 bool remove_gp_asynchronous(void)
+15 {
+16   struct foo *p;
+17
+18   spin_lock(&amp;gp_lock);
+19   p = rcu_dereference(gp);
+20   if (!p) {
+21     spin_unlock(&amp;gp_lock);
+22     return false;
+23   }
+24   rcu_assign_pointer(gp, NULL);
+25   call_rcu(&amp;p-&gt;rh, remove_gp_cb);
+26   spin_unlock(&amp;gp_lock);
+27   return true;
+28 }
+</pre>
+</blockquote>
+
+<p>
+A definition of <tt>struct foo</tt> is finally needed, and appears
+on lines&nbsp;1-5.
+The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt>
+on line&nbsp;25, and will be invoked after the end of a subsequent
+grace period.
+This gets the same effect as <tt>remove_gp_synchronous()</tt>,
+but without forcing the updater to wait for a grace period to elapse.
+The <tt>call_rcu()</tt> function may be used in a number of
+situations where neither <tt>synchronize_rcu()</tt> nor
+<tt>synchronize_rcu_expedited()</tt> would be legal,
+including within preempt-disable code, <tt>local_bh_disable()</tt> code,
+interrupt-disable code, and interrupt handlers.
+However, even <tt>call_rcu()</tt> is illegal within NMI handlers.
+The callback function (<tt>remove_gp_cb()</tt> in this case) will be
+executed within softirq (software interrupt) environment within the
+Linux kernel,
+either within a real softirq handler or under the protection
+of <tt>local_bh_disable()</tt>.
+In both the Linux kernel and in userspace, it is bad practice to
+write an RCU callback function that takes too long.
+Long-running operations should be relegated to separate threads or
+(in the Linux kernel) workqueues.
+
+<p><a name="Quick Quiz 12"><b>Quick Quiz 12</b>:</a>
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+<br><a href="#qq12answer">Answer</a>
+
+<p>
+However, all that <tt>remove_gp_cb()</tt> is doing is
+invoking <tt>kfree()</tt> on the data element.
+This is a common idiom, and is supported by <tt>kfree_rcu()</tt>,
+which allows &ldquo;fire and forget&rdquo; operation as shown below:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 bool remove_gp_faf(void)
+ 8 {
+ 9   struct foo *p;
+10
+11   spin_lock(&amp;gp_lock);
+12   p = rcu_dereference(gp);
+13   if (!p) {
+14     spin_unlock(&amp;gp_lock);
+15     return false;
+16   }
+17   rcu_assign_pointer(gp, NULL);
+18   kfree_rcu(p, rh);
+19   spin_unlock(&amp;gp_lock);
+20   return true;
+21 }
+</pre>
+</blockquote>
+
+<p>
+Note that <tt>remove_gp_faf()</tt> simply invokes
+<tt>kfree_rcu()</tt> and proceeds, without any need to pay any
+further attention to the subsequent grace period and <tt>kfree()</tt>.
+It is permissible to invoke <tt>kfree_rcu()</tt> from the same
+environments as for <tt>call_rcu()</tt>.
+Interestingly enough, DYNIX/ptx had the equivalents of
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not
+<tt>synchronize_rcu()</tt>.
+This was due to the fact that RCU was not heavily used within DYNIX/ptx,
+so the very few places that needed something like
+<tt>synchronize_rcu()</tt> simply open-coded it.
+
+<p><a name="Quick Quiz 13"><b>Quick Quiz 13</b>:</a>
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+<br><a href="#qq13answer">Answer</a>
+
+<p>
+But what if the updater must wait for the completion of code to be
+executed after the end of the grace period, but has other tasks
+that can be carried out in the meantime?
+The polling-style <tt>get_state_synchronize_rcu()</tt> and
+<tt>cond_synchronize_rcu()</tt> functions may be used for this
+purpose, as shown below:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_poll(void)
+ 2 {
+ 3   struct foo *p;
+ 4   unsigned long s;
+ 5
+ 6   spin_lock(&amp;gp_lock);
+ 7   p = rcu_access_pointer(gp);
+ 8   if (!p) {
+ 9     spin_unlock(&amp;gp_lock);
+10     return false;
+11   }
+12   rcu_assign_pointer(gp, NULL);
+13   spin_unlock(&amp;gp_lock);
+14   s = get_state_synchronize_rcu();
+15   do_something_while_waiting();
+16   cond_synchronize_rcu(s);
+17   kfree(p);
+18   return true;
+19 }
+</pre>
+</blockquote>
+
+<p>
+On line&nbsp;14, <tt>get_state_synchronize_rcu()</tt> obtains a
+&ldquo;cookie&rdquo; from RCU,
+then line&nbsp;15 carries out other tasks,
+and finally, line&nbsp;16 returns immediately if a grace period has
+elapsed in the meantime, but otherwise waits as required.
+The need for <tt>get_state_synchronize_rcu</tt> and
+<tt>cond_synchronize_rcu()</tt> has appeared quite recently,
+so it is too early to tell whether they will stand the test of time.
+
+<p>
+RCU thus provides a range of tools to allow updaters to strike the
+required tradeoff between latency, flexibility and CPU overhead.
+
+<h3><a name="Composability">Composability</a></h3>
+
+<p>
+Composability has received much attention in recent years, perhaps in part
+due to the collision of multicore hardware with object-oriented techniques
+designed in single-threaded environments for single-threaded use.
+And in theory, RCU read-side critical sections may be composed, and in
+fact may be nested arbitrarily deeply.
+In practice, as with all real-world implementations of composable
+constructs, there are limitations.
+
+<p>
+Implementations of RCU for which <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> generate no code, such as
+Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
+nested arbitrarily deeply.
+After all, there is no overhead.
+Except that if all these instances of <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> are visible to the compiler,
+compilation will eventually fail due to exhausting memory,
+mass storage, or user patience, whichever comes first.
+If the nesting is not visible to the compiler, as is the case with
+mutually recursive functions each in its own translation unit,
+stack overflow will result.
+If the nesting takes the form of loops, either the control variable
+will overflow or (in the Linux kernel) you will get an RCU CPU stall warning.
+Nevertheless, this class of RCU implementations is one
+of the most composable constructs in existence.
+
+<p>
+RCU implementations that explicitly track nesting depth
+are limited by the nesting-depth counter.
+For example, the Linux kernel's preemptible RCU limits nesting to
+<tt>INT_MAX</tt>.
+This should suffice for almost all practical purposes.
+That said, a consecutive pair of RCU read-side critical sections
+between which there is an operation that waits for a grace period
+cannot be enclosed in another RCU read-side critical section.
+This is because it is not legal to wait for a grace period within
+an RCU read-side critical section:  To do so would result either
+in deadlock or
+in RCU implicitly splitting the enclosing RCU read-side critical
+section, neither of which is conducive to a long-lived and prosperous
+kernel.
+
+<p>
+It is worth noting that RCU is not alone in limiting composability.
+For example, many transactional-memory implementations prohibit
+composing a pair of transactions separated by an irrevocable
+operation (for example, a network receive operation).
+For another example, lock-based critical sections can be composed
+surprisingly freely, but only if deadlock is avoided.
+
+<p>
+In short, although RCU read-side critical sections are highly composable,
+care is required in some situations, just as is the case for any other
+composable synchronization mechanism.
+
+<h3><a name="Corner Cases">Corner Cases</a></h3>
+
+<p>
+A given RCU workload might have an endless and intense stream of
+RCU read-side critical sections, perhaps even so intense that there
+was never a point in time during which there was not at least one
+RCU read-side critical section in flight.
+RCU cannot allow this situation to block grace periods:  As long as
+all the RCU read-side critical sections are finite, grace periods
+must also be finite.
+
+<p>
+That said, preemptible RCU implementations could potentially result
+in RCU read-side critical sections being preempted for long durations,
+which has the effect of creating a long-duration RCU read-side
+critical section.
+This situation can arise only in heavily loaded systems, but systems using
+real-time priorities are of course more vulnerable.
+Therefore, RCU priority boosting is provided to help deal with this
+case.
+That said, the exact requirements on RCU priority boosting will likely
+evolve as more experience accumulates.
+
+<p>
+Other workloads might have very high update rates.
+Although one can argue that such workloads should instead use
+something other than RCU, the fact remains that RCU must
+handle such workloads gracefully.
+This requirement is another factor driving batching of grace periods,
+but it is also the driving force behind the checks for large numbers
+of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
+Finally, high update rates should not delay RCU read-side critical
+sections, although some read-side delays can occur when using
+<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
+of <tt>try_stop_cpus()</tt>.
+(In the future, <tt>synchronize_rcu_expedited()</tt> will be
+converted to use lighter-weight inter-processor interrupts (IPIs),
+but this will still disturb readers, though to a much smaller degree.)
+
+<p>
+Although all three of these corner cases were understood in the early
+1990s, a simple user-level test consisting of <tt>close(open(path))</tt>
+in a tight loop
+in the early 2000s suddenly provided a much deeper appreciation of the
+high-update-rate corner case.
+This test also motivated addition of some RCU code to react to high update
+rates, for example, if a given CPU finds itself with more than 10,000
+RCU callbacks queued, it will cause RCU to take evasive action by
+more aggressively starting grace periods and more aggressively forcing
+completion of grace-period processing.
+This evasive action causes the grace period to complete more quickly,
+but at the cost of restricting RCU's batching optimizations, thus
+increasing the CPU overhead incurred by that grace period.
+
+<h2><a name="Software-Engineering Requirements">
+Software-Engineering Requirements</a></h2>
+
+<p>
+Between Murphy's Law and &ldquo;To err is human&rdquo;, it is necessary to
+guard against mishaps and misuse:
+
+<ol>
+<li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
+	everywhere that it is needed, so kernels built with
+	<tt>CONFIG_PROVE_RCU=y</tt> will spat if
+	<tt>rcu_dereference()</tt> is used outside of an
+	RCU read-side critical section.
+	Update-side code can use <tt>rcu_dereference_protected()</tt>,
+	which takes a
+	<a href="https://lwn.net/Articles/371986/">lockdep expression</a>
+	to indicate what is providing the protection.
+	If the indicated protection is not provided, a lockdep splat
+	is emitted.
+
+	<p>
+	Code shared between readers and updaters can use
+	<tt>rcu_dereference_check()</tt>, which also takes a
+	lockdep expression, and emits a lockdep splat if neither
+	<tt>rcu_read_lock()</tt> nor the indicated protection
+	is in place.
+	In addition, <tt>rcu_dereference_raw()</tt> is used in those
+	(hopefully rare) cases where the required protection cannot
+	be easily described.
+	Finally, <tt>rcu_read_lock_held()</tt> is provided to
+	allow a function to verify that it has been invoked within
+	an RCU read-side critical section.
+	I was made aware of this set of requirements shortly after Thomas
+	Gleixner audited a number of RCU uses.
+<li>	A given function might wish to check for RCU-related preconditions
+	upon entry, before using any other RCU API.
+	The <tt>rcu_lockdep_assert()</tt> does this job,
+	asserting the expression in kernels having lockdep enabled
+	and doing nothing otherwise.
+<li>	It is also easy to forget to use <tt>rcu_assign_pointer()</tt>
+	and <tt>rcu_dereference()</tt>, perhaps (incorrectly)
+	substituting a simple assignment.
+	To catch this sort of error, a given RCU-protected pointer may be
+	tagged with <tt>__rcu</tt>, after which running sparse
+	with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain
+	about simple-assignment accesses to that pointer.
+	Arnd Bergmann made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lwn.net/Articles/376011/">patch series</a>.
+<li>	Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt>
+	will splat if a data element is passed to <tt>call_rcu()</tt>
+	twice in a row, without a grace period in between.
+	(This error is similar to a double free.)
+	The corresponding <tt>rcu_head</tt> structures that are
+	dynamically allocated are automatically tracked, but
+	<tt>rcu_head</tt> structures allocated on the stack
+	must be initialized with <tt>init_rcu_head_on_stack()</tt>
+	and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>.
+	Similarly, statically allocated non-stack <tt>rcu_head</tt>
+	structures must be initialized with <tt>init_rcu_head()</tt>
+	and cleaned up with <tt>destroy_rcu_head()</tt>.
+	Mathieu Desnoyers made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>.
+<li>	An infinite loop in an RCU read-side critical section will
+	eventually trigger an RCU CPU stall warning splat, with
+	the duration of &ldquo;eventually&rdquo; being controlled by the
+	<tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or,
+	alternatively, by the
+	<tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs
+	parameter.
+	However, RCU is not obligated to produce this splat
+	unless there is a grace period waiting on that particular
+	RCU read-side critical section.
+	<p>
+	Some extreme workloads might intentionally delay
+	RCU grace periods, and systems running those workloads can
+	be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt>
+	to suppress the splats.
+	This kernel parameter may also be set via <tt>sysfs</tt>.
+	Furthermore, RCU CPU stall warnings are counter-productive
+	during sysrq dumps and during panics.
+	RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and
+	<tt>rcu_sysrq_end()</tt> API members to be called before
+	and after long sysrq dumps.
+	RCU also supplies the <tt>rcu_panic()</tt> notifier that is
+	automatically invoked at the beginning of a panic to suppress
+	further RCU CPU stall warnings.
+
+	<p>
+	This requirement made itself known in the early 1990s, pretty
+	much the first time that it was necessary to debug a CPU stall.
+	That said, the initial implementation in DYNIX/ptx was quite
+	generic in comparison with that of Linux.
+<li>	Although it would be very good to detect pointers leaking out
+	of RCU read-side critical sections, there is currently no
+	good way of doing this.
+	One complication is the need to distinguish between pointers
+	leaking and pointers that have been handed off from RCU to
+	some other synchronization mechanism, for example, reference
+	counting.
+<li>	In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related
+	information is provided via both debugfs and event tracing.
+<li>	Open-coded use of <tt>rcu_assign_pointer()</tt> and
+	<tt>rcu_dereference()</tt> to create typical linked
+	data structures can be surprisingly error-prone.
+	Therefore, RCU-protected
+	<a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a>
+	and, more recently, RCU-protected
+	<a href="https://lwn.net/Articles/612100/">hash tables</a>
+	are available.
+	Many other special-purpose RCU-protected data structures are
+	available in the Linux kernel and the userspace RCU library.
+<li>	Some linked structures are created at compile time, but still
+	require <tt>__rcu</tt> checking.
+	The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this
+	purpose.
+<li>	It is not necessary to use <tt>rcu_assign_pointer()</tt>
+	when creating linked structures that are to be published via
+	a single external pointer.
+	The <tt>RCU_INIT_POINTER()</tt> macro is provided for
+	this task and also for assigning <tt>NULL</tt> pointers
+	at runtime.
+</ol>
+
+<p>
+This not a hard-and-fast list:  RCU's diagnostic capabilities will
+continue to be guided by the number and type of usage bugs found
+in real-world RCU usage.
+
+<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2>
+
+<p>
+The Linux kernel provides an interesting environment for all kinds of
+software, including RCU.
+Some of the relevant points of interest are as follows:
+
+<ol>
+<li>	<a href="#Configuration">Configuration</a>.
+<li>	<a href="#Firmware Interface">Firmware Interface</a>.
+<li>	<a href="#Early Boot">Early Boot</a>.
+<li>	<a href="#Interrupts and NMIs">
+	Interrupts and non-maskable interrupts (NMIs)</a>.
+<li>	<a href="#Loadable Modules">Loadable Modules</a>.
+<li>	<a href="#Hotplug CPU">Hotplug CPU</a>.
+<li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
+<li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
+<li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
+<li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
+<li>	<a href="#Performance, Scalability, Response Time, and Reliability">
+	Performance, Scalability, Response Time, and Reliability</a>.
+</ol>
+
+<p>
+This list is probably incomplete, but it does give a feel for the
+most notable Linux-kernel complications.
+Each of the following sections covers one of the above topics.
+
+<h3><a name="Configuration">Configuration</a></h3>
+
+<p>
+RCU's goal is automatic configuration, so that almost nobody
+needs to worry about RCU's <tt>Kconfig</tt> options.
+And for almost all users, RCU does in fact work well
+&ldquo;out of the box.&rdquo;
+
+<p>
+However, there are specialized use cases that are handled by
+kernel boot parameters and <tt>Kconfig</tt> options.
+Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users
+about new <tt>Kconfig</tt> options, which requires almost all of them
+be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option.
+
+<p>
+This all should be quite obvious, but the fact remains that
+Linus Torvalds recently had to
+<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a>
+me of this requirement.
+
+<h3><a name="Firmware Interface">Firmware Interface</a></h3>
+
+<p>
+In many cases, kernel obtains information about the system from the
+firmware, and sometimes things are lost in translation.
+Or the translation is accurate, but the original message is bogus.
+
+<p>
+For example, some systems' firmware overreports the number of CPUs,
+sometimes by a large factor.
+If RCU naively believed the firmware, as it used to do,
+it would create too many per-CPU kthreads.
+Although the resulting system will still run correctly, the extra
+kthreads needlessly consume memory and can cause confusion
+when they show up in <tt>ps</tt> listings.
+
+<p>
+RCU must therefore wait for a given CPU to actually come online before
+it can allow itself to believe that the CPU actually exists.
+The resulting &ldquo;ghost CPUs&rdquo; (which are never going to
+come online) cause a number of
+<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>.
+
+<h3><a name="Early Boot">Early Boot</a></h3>
+
+<p>
+The Linux kernel's boot sequence is an interesting process,
+and RCU is used early, even before <tt>rcu_init()</tt>
+is invoked.
+In fact, a number of RCU's primitives can be used as soon as the
+initial task's <tt>task_struct</tt> is available and the
+boot CPU's per-CPU variables are set up.
+The read-side primitives (<tt>rcu_read_lock()</tt>,
+<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>,
+and <tt>rcu_access_pointer()</tt>) will operate normally very early on,
+as will <tt>rcu_assign_pointer()</tt>.
+
+<p>
+Although <tt>call_rcu()</tt> may be invoked at any
+time during boot, callbacks are not guaranteed to be invoked until after
+the scheduler is fully up and running.
+This delay in callback invocation is due to the fact that RCU does not
+invoke callbacks until it is fully initialized, and this full initialization
+cannot occur until after the scheduler has initialized itself to the
+point where RCU can spawn and run its kthreads.
+In theory, it would be possible to invoke callbacks earlier,
+however, this is not a panacea because there would be severe restrictions
+on what operations those callbacks could invoke.
+
+<p>
+Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
+<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
+(<a href="#Bottom-Half Flavor">discussed below</a>),
+and
+<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
+will all operate normally
+during very early boot, the reason being that there is only one CPU
+and preemption is disabled.
+This means that the call <tt>synchronize_rcu()</tt> (or friends)
+itself is a quiescent
+state and thus a grace period, so the early-boot implementation can
+be a no-op.
+
+<p>
+Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
+continue to operate normally through the remainder of boot, courtesy
+of the fact that preemption is disabled across their RCU read-side
+critical sections and also courtesy of the fact that there is still
+only one CPU.
+However, once the scheduler starts initializing, preemption is enabled.
+There is still only a single CPU, but the fact that preemption is enabled
+means that the no-op implementation of <tt>synchronize_rcu()</tt> no
+longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
+Therefore, as soon as the scheduler starts initializing, the early-boot
+fastpath is disabled.
+This means that <tt>synchronize_rcu()</tt> switches to its runtime
+mode of operation where it posts callbacks, which in turn means that
+any call to <tt>synchronize_rcu()</tt> will block until the corresponding
+callback is invoked.
+Unfortunately, the callback cannot be invoked until RCU's runtime
+grace-period machinery is up and running, which cannot happen until
+the scheduler has initialized itself sufficiently to allow RCU's
+kthreads to be spawned.
+Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
+initialization can result in deadlock.
+
+<p><a name="Quick Quiz 14"><b>Quick Quiz 14</b>:</a>
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+<br><a href="#qq14answer">Answer</a>
+
+<p>
+I learned of these boot-time requirements as a result of a series of
+system hangs.
+
+<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3>
+
+<p>
+The Linux kernel has interrupts, and RCU read-side critical sections are
+legal within interrupt handlers and within interrupt-disabled regions
+of code, as are invocations of <tt>call_rcu()</tt>.
+
+<p>
+Some Linux-kernel architectures can enter an interrupt handler from
+non-idle process context, and then just never leave it, instead stealthily
+transitioning back to process context.
+This trick is sometimes used to invoke system calls from inside the kernel.
+These &ldquo;half-interrupts&rdquo; mean that RCU has to be very careful
+about how it counts interrupt nesting levels.
+I learned of this requirement the hard way during a rewrite
+of RCU's dyntick-idle code.
+
+<p>
+The Linux kernel has non-maskable interrupts (NMIs), and
+RCU read-side critical sections are legal within NMI handlers.
+Thankfully, RCU update-side primitives, including
+<tt>call_rcu()</tt>, are prohibited within NMI handlers.
+
+<p>
+The name notwithstanding, some Linux-kernel architectures
+can have nested NMIs, which RCU must handle correctly.
+Andy Lutomirski
+<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a>
+with this requirement;
+he also kindly surprised me with
+<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a>
+that meets this requirement.
+
+<h3><a name="Loadable Modules">Loadable Modules</a></h3>
+
+<p>
+The Linux kernel has loadable modules, and these modules can
+also be unloaded.
+After a given module has been unloaded, any attempt to call
+one of its functions results in a segmentation fault.
+The module-unload functions must therefore cancel any
+delayed calls to loadable-module functions, for example,
+any outstanding <tt>mod_timer()</tt> must be dealt with
+via <tt>del_timer_sync()</tt> or similar.
+
+<p>
+Unfortunately, there is no way to cancel an RCU callback;
+once you invoke <tt>call_rcu()</tt>, the callback function is
+going to eventually be invoked, unless the system goes down first.
+Because it is normally considered socially irresponsible to crash the system
+in response to a module unload request, we need some other way
+to deal with in-flight RCU callbacks.
+
+<p>
+RCU therefore provides
+<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>,
+which waits until all in-flight RCU callbacks have been invoked.
+If a module uses <tt>call_rcu()</tt>, its exit function should therefore
+prevent any future invocation of <tt>call_rcu()</tt>, then invoke
+<tt>rcu_barrier()</tt>.
+In theory, the underlying module-unload code could invoke
+<tt>rcu_barrier()</tt> unconditionally, but in practice this would
+incur unacceptable latencies.
+
+<p>
+Nikita Danilov noted this requirement for an analogous filesystem-unmount
+situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
+The need for <tt>rcu_barrier()</tt> for module unloading became
+apparent later.
+
+<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
+
+<p>
+The Linux kernel supports CPU hotplug, which means that CPUs
+can come and go.
+It is of course illegal to use any RCU API member from an offline CPU.
+This requirement was present from day one in DYNIX/ptx, but
+on the other hand, the Linux kernel's CPU-hotplug implementation
+is &ldquo;interesting.&rdquo;
+
+<p>
+The Linux-kernel CPU-hotplug implementation has notifiers that
+are used to allow the various kernel subsystems (including RCU)
+to respond appropriately to a given CPU-hotplug operation.
+Most RCU operations may be invoked from CPU-hotplug notifiers,
+including even normal synchronous grace-period operations
+such as <tt>synchronize_rcu()</tt>.
+However, expedited grace-period operations such as
+<tt>synchronize_rcu_expedited()</tt> are not supported,
+due to the fact that current implementations block CPU-hotplug
+operations, which could result in deadlock.
+
+<p>
+In addition, all-callback-wait operations such as
+<tt>rcu_barrier()</tt> are also not supported, due to the
+fact that there are phases of CPU-hotplug operations where
+the outgoing CPU's callbacks will not be invoked until after
+the CPU-hotplug operation ends, which could also result in deadlock.
+
+<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
+
+<p>
+RCU depends on the scheduler, and the scheduler uses RCU to
+protect some of its data structures.
+This means the scheduler is forbidden from acquiring
+the runqueue locks and the priority-inheritance locks
+in the middle of an outermost RCU read-side critical section unless either
+(1)&nbsp;it releases them before exiting that same
+RCU read-side critical section, or
+(2)&nbsp;interrupts are disabled across
+that entire RCU read-side critical section.
+This same prohibition also applies (recursively!) to any lock that is acquired
+while holding any lock to which this prohibition applies.
+Adhering to this rule prevents preemptible RCU from invoking
+<tt>rcu_read_unlock_special()</tt> while either runqueue or
+priority-inheritance locks are held, thus avoiding deadlock.
+
+<p>
+Prior to v4.4, it was only necessary to disable preemption across
+RCU read-side critical sections that acquired scheduler locks.
+In v4.4, expedited grace periods started using IPIs, and these
+IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath.
+Therefore, this expedited-grace-period change required disabling of
+interrupts, not just preemption.
+
+<p>
+For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt>
+implementation must be written carefully to avoid similar deadlocks.
+In particular, <tt>rcu_read_unlock()</tt> must tolerate an
+interrupt where the interrupt handler invokes both
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+This possibility requires <tt>rcu_read_unlock()</tt> to use
+negative nesting levels to avoid destructive recursion via
+interrupt handler's use of RCU.
+
+<p>
+This pair of mutual scheduler-RCU requirements came as a
+<a href="https://lwn.net/Articles/453002/">complete surprise</a>.
+
+<p>
+As noted above, RCU makes use of kthreads, and it is necessary to
+avoid excessive CPU-time accumulation by these kthreads.
+This requirement was no surprise, but RCU's violation of it
+when running context-switch-heavy workloads when built with
+<tt>CONFIG_NO_HZ_FULL=y</tt>
+<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>.
+RCU has made good progress towards meeting this requirement, even
+for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads,
+but there is room for further improvement.
+
+<h3><a name="Tracing and RCU">Tracing and RCU</a></h3>
+
+<p>
+It is possible to use tracing on RCU code, but tracing itself
+uses RCU.
+For this reason, <tt>rcu_dereference_raw_notrace()</tt>
+is provided for use by tracing, which avoids the destructive
+recursion that could otherwise ensue.
+This API is also used by virtualization in some architectures,
+where RCU readers execute in environments in which tracing
+cannot be used.
+The tracing folks both located the requirement and provided the
+needed fix, so this surprise requirement was relatively painless.
+
+<h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
+
+<p>
+Interrupting idle CPUs is considered socially unacceptable,
+especially by people with battery-powered embedded systems.
+RCU therefore conserves energy by detecting which CPUs are
+idle, including tracking CPUs that have been interrupted from idle.
+This is a large part of the energy-efficiency requirement,
+so I learned of this via an irate phone call.
+
+<p>
+Because RCU avoids interrupting idle CPUs, it is illegal to
+execute an RCU read-side critical section on an idle CPU.
+(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat
+if you try it.)
+The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt>
+event tracing is provided to work around this restriction.
+In addition, <tt>rcu_is_watching()</tt> may be used to
+test whether or not it is currently legal to run RCU read-side
+critical sections on this CPU.
+I learned of the need for diagnostics on the one hand
+and <tt>RCU_NONIDLE()</tt> on the other while inspecting
+idle-loop code.
+Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
+which is used quite heavily in the idle loop.
+
+<p>
+It is similarly socially unacceptable to interrupt an
+<tt>nohz_full</tt> CPU running in userspace.
+RCU must therefore track <tt>nohz_full</tt> userspace
+execution.
+And in
+<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a>
+kernels, RCU must separately track idle CPUs on the one hand and
+CPUs that are either idle or executing in userspace on the other.
+In both cases, RCU must be able to sample state at two points in
+time, and be able to determine whether or not some other CPU spent
+any time idle and/or executing in userspace.
+
+<p>
+These energy-efficiency requirements have proven quite difficult to
+understand and to meet, for example, there have been more than five
+clean-sheet rewrites of RCU's energy-efficiency code, the last of
+which was finally able to demonstrate
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>.
+As noted earlier,
+I learned of many of these requirements via angry phone calls:
+Flaming me on the Linux-kernel mailing list was apparently not
+sufficient to fully vent their ire at RCU's energy-efficiency bugs!
+
+<h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
+
+<p>
+Although small-memory non-realtime systems can simply use Tiny RCU,
+code size is only one aspect of memory efficiency.
+Another aspect is the size of the <tt>rcu_head</tt> structure
+used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>.
+Although this structure contains nothing more than a pair of pointers,
+it does appear in many RCU-protected data structures, including
+some that are size critical.
+The <tt>page</tt> structure is a case in point, as evidenced by
+the many occurrences of the <tt>union</tt> keyword within that structure.
+
+<p>
+This need for memory efficiency is one reason that RCU uses hand-crafted
+singly linked lists to track the <tt>rcu_head</tt> structures that
+are waiting for a grace period to elapse.
+It is also the reason why <tt>rcu_head</tt> structures do not contain
+debug information, such as fields tracking the file and line of the
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them.
+Although this information might appear in debug-only kernel builds at some
+point, in the meantime, the <tt>-&gt;func</tt> field will often provide
+the needed debug information.
+
+<p>
+However, in some cases, the need for memory efficiency leads to even
+more extreme measures.
+Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field
+shares storage with a great many other structures that are used at
+various points in the corresponding page's lifetime.
+In order to correctly resolve certain
+<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>,
+the Linux kernel's memory-management subsystem needs a particular bit
+to remain zero during all phases of grace-period processing,
+and that bit happens to map to the bottom bit of the
+<tt>rcu_head</tt> structure's <tt>-&gt;next</tt> field.
+RCU makes this guarantee as long as <tt>call_rcu()</tt>
+is used to post the callback, as opposed to <tt>kfree_rcu()</tt>
+or some future &ldquo;lazy&rdquo;
+variant of <tt>call_rcu()</tt> that might one day be created for
+energy-efficiency purposes.
+
+<h3><a name="Performance, Scalability, Response Time, and Reliability">
+Performance, Scalability, Response Time, and Reliability</a></h3>
+
+<p>
+Expanding on the
+<a href="#Performance and Scalability">earlier discussion</a>,
+RCU is used heavily by hot code paths in performance-critical
+portions of the Linux kernel's networking, security, virtualization,
+and scheduling code paths.
+RCU must therefore use efficient implementations, especially in its
+read-side primitives.
+To that end, it would be good if preemptible RCU's implementation
+of <tt>rcu_read_lock()</tt> could be inlined, however, doing
+this requires resolving <tt>#include</tt> issues with the
+<tt>task_struct</tt> structure.
+
+<p>
+The Linux kernel supports hardware configurations with up to
+4096 CPUs, which means that RCU must be extremely scalable.
+Algorithms that involve frequent acquisitions of global locks or
+frequent atomic operations on global variables simply cannot be
+tolerated within the RCU implementation.
+RCU therefore makes heavy use of a combining tree based on the
+<tt>rcu_node</tt> structure.
+RCU is required to tolerate all CPUs continuously invoking any
+combination of RCU's runtime primitives with minimal per-operation
+overhead.
+In fact, in many cases, increasing load must <i>decrease</i> the
+per-operation overhead, witness the batching optimizations for
+<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>,
+<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>.
+As a general rule, RCU must cheerfully accept whatever the
+rest of the Linux kernel decides to throw at it.
+
+<p>
+The Linux kernel is used for real-time workloads, especially
+in conjunction with the
+<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>.
+The real-time-latency response requirements are such that the
+traditional approach of disabling preemption across RCU
+read-side critical sections is inappropriate.
+Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
+use an RCU implementation that allows RCU read-side critical
+sections to be preempted.
+This requirement made its presence known after users made it
+clear that an earlier
+<a href="https://lwn.net/Articles/107930/">real-time patch</a>
+did not meet their needs, in conjunction with some
+<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a>
+encountered by a very early version of the -rt patchset.
+
+<p>
+In addition, RCU must make do with a sub-100-microsecond real-time latency
+budget.
+In fact, on smaller systems with the -rt patchset, the Linux kernel
+provides sub-20-microsecond real-time latencies for the whole kernel,
+including RCU.
+RCU's scalability and latency must therefore be sufficient for
+these sorts of configurations.
+To my surprise, the sub-100-microsecond real-time latency budget
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf">
+applies to even the largest systems [PDF]</a>,
+up to and including systems with 4096 CPUs.
+This real-time requirement motivated the grace-period kthread, which
+also simplified handling of a number of race conditions.
+
+<p>
+Finally, RCU's status as a synchronization primitive means that
+any RCU failure can result in arbitrary memory corruption that can be
+extremely difficult to debug.
+This means that RCU must be extremely reliable, which in
+practice also means that RCU must have an aggressive stress-test
+suite.
+This stress-test suite is called <tt>rcutorture</tt>.
+
+<p>
+Although the need for <tt>rcutorture</tt> was no surprise,
+the current immense popularity of the Linux kernel is posing
+interesting&mdash;and perhaps unprecedented&mdash;validation
+challenges.
+To see this, keep in mind that there are well over one billion
+instances of the Linux kernel running today, given Android
+smartphones, Linux-powered televisions, and servers.
+This number can be expected to increase sharply with the advent of
+the celebrated Internet of Things.
+
+<p>
+Suppose that RCU contains a race condition that manifests on average
+once per million years of runtime.
+This bug will be occurring about three times per <i>day</i> across
+the installed base.
+RCU could simply hide behind hardware error rates, given that no one
+should really expect their smartphone to last for a million years.
+However, anyone taking too much comfort from this thought should
+consider the fact that in most jurisdictions, a successful multi-year
+test of a given mechanism, which might include a Linux kernel,
+suffices for a number of types of safety-critical certifications.
+In fact, rumor has it that the Linux kernel is already being used
+in production for safety-critical applications.
+I don't know about you, but I would feel quite bad if a bug in RCU
+killed someone.
+Which might explain my recent focus on validation and verification.
+
+<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2>
+
+<p>
+One of the more surprising things about RCU is that there are now
+no fewer than five <i>flavors</i>, or API families.
+In addition, the primary flavor that has been the sole focus up to
+this point has two different implementations, non-preemptible and
+preemptible.
+The other four flavors are listed below, with requirements for each
+described in a separate section.
+
+<ol>
+<li>	<a href="#Bottom-Half Flavor">Bottom-Half Flavor</a>
+<li>	<a href="#Sched Flavor">Sched Flavor</a>
+<li>	<a href="#Sleepable RCU">Sleepable RCU</a>
+<li>	<a href="#Tasks RCU">Tasks RCU</a>
+</ol>
+
+<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3>
+
+<p>
+The softirq-disable (AKA &ldquo;bottom-half&rdquo;,
+hence the &ldquo;_bh&rdquo; abbreviations)
+flavor of RCU, or <i>RCU-bh</i>, was developed by
+Dipankar Sarma to provide a flavor of RCU that could withstand the
+network-based denial-of-service attacks researched by Robert
+Olsson.
+These attacks placed so much networking load on the system
+that some of the CPUs never exited softirq execution,
+which in turn prevented those CPUs from ever executing a context switch,
+which, in the RCU implementation of that time, prevented grace periods
+from ever ending.
+The result was an out-of-memory condition and a system hang.
+
+<p>
+The solution was the creation of RCU-bh, which does
+<tt>local_bh_disable()</tt>
+across its read-side critical sections, and which uses the transition
+from one type of softirq processing to another as a quiescent state
+in addition to context switch, idle, user mode, and offline.
+This means that RCU-bh grace periods can complete even when some of
+the CPUs execute in softirq indefinitely, thus allowing algorithms
+based on RCU-bh to withstand network-based denial-of-service attacks.
+
+<p>
+Because
+<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt>
+disable and re-enable softirq handlers, any attempt to start a softirq
+handlers during the
+RCU-bh read-side critical section will be deferred.
+In this case, <tt>rcu_read_unlock_bh()</tt>
+will invoke softirq processing, which can take considerable time.
+One can of course argue that this softirq overhead should be associated
+with the code following the RCU-bh read-side critical section rather
+than <tt>rcu_read_unlock_bh()</tt>, but the fact
+is that most profiling tools cannot be expected to make this sort
+of fine distinction.
+For example, suppose that a three-millisecond-long RCU-bh read-side
+critical section executes during a time of heavy networking load.
+There will very likely be an attempt to invoke at least one softirq
+handler during that three milliseconds, but any such invocation will
+be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>.
+This can of course make it appear at first glance as if
+<tt>rcu_read_unlock_bh()</tt> was executing very slowly.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a>
+includes
+<tt>rcu_read_lock_bh()</tt>,
+<tt>rcu_read_unlock_bh()</tt>,
+<tt>rcu_dereference_bh()</tt>,
+<tt>rcu_dereference_bh_check()</tt>,
+<tt>synchronize_rcu_bh()</tt>,
+<tt>synchronize_rcu_bh_expedited()</tt>,
+<tt>call_rcu_bh()</tt>,
+<tt>rcu_barrier_bh()</tt>, and
+<tt>rcu_read_lock_bh_held()</tt>.
+
+<h3><a name="Sched Flavor">Sched Flavor</a></h3>
+
+<p>
+Before preemptible RCU, waiting for an RCU grace period had the
+side effect of also waiting for all pre-existing interrupt
+and NMI handlers.
+However, there are legitimate preemptible-RCU implementations that
+do not have this property, given that any point in the code outside
+of an RCU read-side critical section can be a quiescent state.
+Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
+RCU in that an RCU-sched grace period waits for for pre-existing
+interrupt and NMI handlers.
+In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
+APIs have identical implementations, while kernels built with
+<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
+
+<p>
+Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+disable and re-enable preemption, respectively.
+This means that if there was a preemption attempt during the
+RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt>
+will enter the scheduler, with all the latency and overhead entailed.
+Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look
+as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly.
+However, the highest-priority task won't be preempted, so that task
+will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a>
+includes
+<tt>rcu_read_lock_sched()</tt>,
+<tt>rcu_read_unlock_sched()</tt>,
+<tt>rcu_read_lock_sched_notrace()</tt>,
+<tt>rcu_read_unlock_sched_notrace()</tt>,
+<tt>rcu_dereference_sched()</tt>,
+<tt>rcu_dereference_sched_check()</tt>,
+<tt>synchronize_sched()</tt>,
+<tt>synchronize_rcu_sched_expedited()</tt>,
+<tt>call_rcu_sched()</tt>,
+<tt>rcu_barrier_sched()</tt>, and
+<tt>rcu_read_lock_sched_held()</tt>.
+However, anything that disables preemption also marks an RCU-sched
+read-side critical section, including
+<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>,
+<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>,
+and so on.
+
+<h3><a name="Sleepable RCU">Sleepable RCU</a></h3>
+
+<p>
+For well over a decade, someone saying &ldquo;I need to block within
+an RCU read-side critical section&rdquo; was a reliable indication
+that this someone did not understand RCU.
+After all, if you are always blocking in an RCU read-side critical
+section, you can probably afford to use a higher-overhead synchronization
+mechanism.
+However, that changed with the advent of the Linux kernel's notifiers,
+whose RCU read-side critical
+sections almost never sleep, but sometimes need to.
+This resulted in the introduction of
+<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>,
+or <i>SRCU</i>.
+
+<p>
+SRCU allows different domains to be defined, with each such domain
+defined by an instance of an <tt>srcu_struct</tt> structure.
+A pointer to this structure must be passed in to each SRCU function,
+for example, <tt>synchronize_srcu(&amp;ss)</tt>, where
+<tt>ss</tt> is the <tt>srcu_struct</tt> structure.
+The key benefit of these domains is that a slow SRCU reader in one
+domain does not delay an SRCU grace period in some other domain.
+That said, one consequence of these domains is that read-side code
+must pass a &ldquo;cookie&rdquo; from <tt>srcu_read_lock()</tt>
+to <tt>srcu_read_unlock()</tt>, for example, as follows:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+As noted above, it is legal to block within SRCU read-side critical sections,
+however, with great power comes great responsibility.
+If you block forever in one of a given domain's SRCU read-side critical
+sections, then that domain's grace periods will also be blocked forever.
+Of course, one good way to block forever is to deadlock, which can
+happen if any operation in a given domain's SRCU read-side critical
+section can block waiting, either directly or indirectly, for that domain's
+grace period to elapse.
+For example, this results in a self-deadlock:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 synchronize_srcu(&amp;ss);
+ 6 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+However, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>,
+deadlock would still be possible.
+Furthermore, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>,
+and if an <tt>ss1</tt>-domain SRCU read-side critical section
+acquired another mutex that was held across as <tt>ss</tt>-domain
+<tt>synchronize_srcu()</tt>,
+deadlock would again be possible.
+Such a deadlock cycle could extend across an arbitrarily large number
+of different SRCU domains.
+Again, with great power comes great responsibility.
+
+<p>
+Unlike the other RCU flavors, SRCU read-side critical sections can
+run on idle and even offline CPUs.
+This ability requires that <tt>srcu_read_lock()</tt> and
+<tt>srcu_read_unlock()</tt> contain memory barriers, which means
+that SRCU readers will run a bit slower than would RCU readers.
+It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
+API, which, in combination with <tt>srcu_read_unlock()</tt>,
+guarantees a full memory barrier.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
+includes
+<tt>srcu_read_lock()</tt>,
+<tt>srcu_read_unlock()</tt>,
+<tt>srcu_dereference()</tt>,
+<tt>srcu_dereference_check()</tt>,
+<tt>synchronize_srcu()</tt>,
+<tt>synchronize_srcu_expedited()</tt>,
+<tt>call_srcu()</tt>,
+<tt>srcu_barrier()</tt>, and
+<tt>srcu_read_lock_held()</tt>.
+It also includes
+<tt>DEFINE_SRCU()</tt>,
+<tt>DEFINE_STATIC_SRCU()</tt>, and
+<tt>init_srcu_struct()</tt>
+APIs for defining and initializing <tt>srcu_struct</tt> structures.
+
+<h3><a name="Tasks RCU">Tasks RCU</a></h3>
+
+<p>
+Some forms of tracing use &ldquo;tramopolines&rdquo; to handle the
+binary rewriting required to install different types of probes.
+It would be good to be able to free old trampolines, which sounds
+like a job for some form of RCU.
+However, because it is necessary to be able to install a trace
+anywhere in the code, it is not possible to use read-side markers
+such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+In addition, it does not work to have these markers in the trampoline
+itself, because there would need to be instructions following
+<tt>rcu_read_unlock()</tt>.
+Although <tt>synchronize_rcu()</tt> would guarantee that execution
+reached the <tt>rcu_read_unlock()</tt>, it would not be able to
+guarantee that execution had completely left the trampoline.
+
+<p>
+The solution, in the form of
+<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>,
+is to have implicit
+read-side critical sections that are delimited by voluntary context
+switches, that is, calls to <tt>schedule()</tt>,
+<tt>cond_resched_rcu_qs()</tt>, and
+<tt>synchronize_rcu_tasks()</tt>.
+In addition, transitions to and from userspace execution also delimit
+tasks-RCU read-side critical sections.
+
+<p>
+The tasks-RCU API is quite compact, consisting only of
+<tt>call_rcu_tasks()</tt>,
+<tt>synchronize_rcu_tasks()</tt>, and
+<tt>rcu_barrier_tasks()</tt>.
+
+<h2><a name="Possible Future Changes">Possible Future Changes</a></h2>
+
+<p>
+One of the tricks that RCU uses to attain update-side scalability is
+to increase grace-period latency with increasing numbers of CPUs.
+If this becomes a serious problem, it will be necessary to rework the
+grace-period state machine so as to avoid the need for the additional
+latency.
+
+<p>
+Expedited grace periods scan the CPUs, so their latency and overhead
+increases with increasing numbers of CPUs.
+If this becomes a serious problem on large systems, it will be necessary
+to do some redesign to avoid this scalability problem.
+
+<p>
+RCU disables CPU hotplug in a few places, perhaps most notably in the
+expedited grace-period and <tt>rcu_barrier()</tt> operations.
+If there is a strong reason to use expedited grace periods in CPU-hotplug
+notifiers, it will be necessary to avoid disabling CPU hotplug.
+This would introduce some complexity, so there had better be a <i>very</i>
+good reason.
+
+<p>
+The tradeoff between grace-period latency on the one hand and interruptions
+of other CPUs on the other hand may need to be re-examined.
+The desire is of course for zero grace-period latency as well as zero
+interprocessor interrupts undertaken during an expedited grace period
+operation.
+While this ideal is unlikely to be achievable, it is quite possible that
+further improvements can be made.
+
+<p>
+The multiprocessor implementations of RCU use a combining tree that
+groups CPUs so as to reduce lock contention and increase cache locality.
+However, this combining tree does not spread its memory across NUMA
+nodes nor does it align the CPU groups with hardware features such
+as sockets or cores.
+Such spreading and alignment is currently believed to be unnecessary
+because the hotpath read-side primitives do not access the combining
+tree, nor does <tt>call_rcu()</tt> in the common case.
+If you believe that your architecture needs such spreading and alignment,
+then your architecture should also benefit from the
+<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set
+to the number of CPUs in a socket, NUMA node, or whatever.
+If the number of CPUs is too large, use a fraction of the number of
+CPUs.
+If the number of CPUs is a large prime number, well, that certainly
+is an &ldquo;interesting&rdquo; architectural choice!
+More flexible arrangements might be considered, but only if
+<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only
+if the inadequacy has been demonstrated by a carefully run and
+realistic system-level workload.
+
+<p>
+Please note that arrangements that require RCU to remap CPU numbers will
+require extremely good demonstration of need and full exploration of
+alternatives.
+
+<p>
+There is an embarrassingly large number of flavors of RCU, and this
+number has been increasing over time.
+Perhaps it will be possible to combine some at some future date.
+
+<p>
+RCU's various kthreads are reasonably recent additions.
+It is quite likely that adjustments will be required to more gracefully
+handle extreme loads.
+It might also be necessary to be able to relate CPU utilization by
+RCU's kthreads and softirq handlers to the code that instigated this
+CPU utilization.
+For example, RCU callback overhead might be charged back to the
+originating <tt>call_rcu()</tt> instance, though probably not
+in production kernels.
+
+<h2><a name="Summary">Summary</a></h2>
+
+<p>
+This document has presented more than two decade's worth of RCU
+requirements.
+Given that the requirements keep changing, this will not be the last
+word on this subject, but at least it serves to get an important
+subset of the requirements set forth.
+
+<h2><a name="Acknowledgments">Acknowledgments</a></h2>
+
+I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar,
+Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and
+Andy Lutomirski for their help in rendering
+this article human readable, and to Michelle Rankin for her support
+of this effort.
+Other contributions are acknowledged in the Linux kernel's git archive.
+The cartoon is copyright (c) 2013 by Melissa Broussard,
+and is provided
+under the terms of the Creative Commons Attribution-Share Alike 3.0
+United States license.
+
+<h3><a name="Answers to Quick Quizzes">
+Answers to Quick Quizzes</a></h3>
+
+<a name="qq1answer"></a>
+<p><b>Quick Quiz 1</b>:
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+
+
+</p><p><b>Answer</b>:
+First, if updaters do not wish to be blocked by readers, they can use
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will
+be discussed later.
+Second, even when using <tt>synchronize_rcu()</tt>, the other
+update-side code does run concurrently with readers, whether pre-existing
+or not.
+
+
+</p><p><a href="#Quick%20Quiz%201"><b>Back to Quick Quiz 1</b>.</a>
+
+<a name="qq2answer"></a>
+<p><b>Quick Quiz 2</b>:
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+
+
+</p><p><b>Answer</b>:
+Without that extra grace period, memory reordering could result in
+<tt>do_something_dlm()</tt> executing <tt>do_something()</tt>
+concurrently with the last bits of <tt>recovery()</tt>.
+
+
+</p><p><a href="#Quick%20Quiz%202"><b>Back to Quick Quiz 2</b>.</a>
+
+<a name="qq3answer"></a>
+<p><b>Quick Quiz 3</b>:
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+
+
+</p><p><b>Answer</b>:
+No, it cannot.
+The readers cannot see either of these two fields until
+the assignment to <tt>gp</tt>, by which time both fields are
+fully initialized.
+So reordering the assignments
+to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt> cannot possibly
+cause any problems.
+
+
+</p><p><a href="#Quick%20Quiz%203"><b>Back to Quick Quiz 3</b>.</a>
+
+<a name="qq4answer"></a>
+<p><b>Quick Quiz 4</b>:
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+
+
+</p><p><b>Answer</b>:
+Let's start with what happens to <tt>do_something_gp()</tt>
+if it fails to use <tt>rcu_dereference()</tt>.
+It could reuse a value formerly fetched from this same pointer.
+It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time
+manner, resulting in <i>load tearing</i>, in turn resulting a bytewise
+mash-up of two distince pointer values.
+It might even use value-speculation optimizations, where it makes a wrong
+guess, but by the time it gets around to checking the value, an update
+has changed the pointer to match the wrong guess.
+Too bad about any dereferences that returned pre-initialization garbage
+in the meantime!
+
+<p>
+For <tt>remove_gp_synchronous()</tt>, as long as all modifications
+to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>,
+the above optimizations are harmless.
+However,
+with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>,
+<tt>sparse</tt> will complain if you
+define <tt>gp</tt> with <tt>__rcu</tt> and then
+access it without using
+either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>.
+
+
+</p><p><a href="#Quick%20Quiz%204"><b>Back to Quick Quiz 4</b>.</a>
+
+<a name="qq5answer"></a>
+<p><b>Quick Quiz 5</b>:
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+
+
+</p><p><b>Answer</b>:
+If RCU cannot tell whether or not a given
+RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>,
+then it must assume that the RCU read-side critical section
+started first.
+In other words, a given instance of <tt>synchronize_rcu()</tt>
+can avoid waiting on a given RCU read-side critical section only
+if it can prove that <tt>synchronize_rcu()</tt> started first.
+
+
+</p><p><a href="#Quick%20Quiz%205"><b>Back to Quick Quiz 5</b>.</a>
+
+<a name="qq6answer"></a>
+<p><b>Quick Quiz 6</b>:
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+
+
+</p><p><b>Answer</b>:
+Yes, they really are required.
+To see why the first guarantee is required, consider the following
+sequence of events:
+
+<ol>
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Very likely to return p. */</tt>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>do_something_with(q-&gt;a);
+	/* No smp_mb(), so might happen after kfree(). */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+</ol>
+
+<p>
+Therefore, there absolutely must be a full memory barrier between the
+end of the RCU read-side critical section and the end of the
+grace period.
+
+<p>
+The sequence of events demonstrating the necessity of the second rule
+is roughly similar:
+
+<ol>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Might return p if no memory barrier. */</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+<li>	CPU 1: <tt>do_something_with(q-&gt;a); /* Boom!!! */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+</ol>
+
+<p>
+And similarly, without a memory barrier between the beginning of the
+grace period and the beginning of the RCU read-side critical section,
+CPU&nbsp;1 might end up accessing the freelist.
+
+<p>
+The &ldquo;as if&rdquo; rule of course applies, so that any implementation
+that acts as if the appropriate memory barriers were in place is a
+correct implementation.
+That said, it is much easier to fool yourself into believing that you have
+adhered to the as-if rule than it is to actually adhere to it!
+
+
+</p><p><a href="#Quick%20Quiz%206"><b>Back to Quick Quiz 6</b>.</a>
+
+<a name="qq7answer"></a>
+<p><b>Quick Quiz 7</b>:
+But how does the upgrade-to-write operation exclude other readers?
+
+
+</p><p><b>Answer</b>:
+It doesn't, just like normal RCU updates, which also do not exclude
+RCU readers.
+
+
+</p><p><a href="#Quick%20Quiz%207"><b>Back to Quick Quiz 7</b>.</a>
+
+<a name="qq8answer"></a>
+<p><b>Quick Quiz 8</b>:
+Can't the compiler also reorder this code?
+
+
+</p><p><b>Answer</b>:
+No, the volatile casts in <tt>READ_ONCE()</tt> and
+<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in
+this particular case.
+
+
+</p><p><a href="#Quick%20Quiz%208"><b>Back to Quick Quiz 8</b>.</a>
+
+<a name="qq9answer"></a>
+<p><b>Quick Quiz 9</b>:
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+
+
+</p><p><b>Answer</b>:
+No.
+Even if <tt>synchronize_rcu()</tt> were to wait until
+all readers had completed, a new reader might start immediately after
+<tt>synchronize_rcu()</tt> completed.
+Therefore, the code following
+<tt>synchronize_rcu()</tt> cannot rely on there being no readers
+in any case.
+
+
+</p><p><a href="#Quick%20Quiz%209"><b>Back to Quick Quiz 9</b>.</a>
+
+<a name="qq10answer"></a>
+<p><b>Quick Quiz 10</b>:
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+
+
+</p><p><b>Answer</b>:
+In theory, an infinite number.
+In practice, an unknown number that is sensitive to both implementation
+details and timing considerations.
+Therefore, even in practice, RCU users must abide by the theoretical rather
+than the practical answer.
+
+
+</p><p><a href="#Quick%20Quiz%2010"><b>Back to Quick Quiz 10</b>.</a>
+
+<a name="qq11answer"></a>
+<p><b>Quick Quiz 11</b>:
+What about sleeping locks?
+
+
+</p><p><b>Answer</b>:
+These are forbidden within Linux-kernel RCU read-side critical sections
+because it is not legal to place a quiescent state (in this case,
+voluntary context switch) within an RCU read-side critical section.
+However, sleeping locks may be used within userspace RCU read-side critical
+sections, and also within Linux-kernel sleepable RCU
+<a href="#Sleepable RCU">(SRCU)</a>
+read-side critical sections.
+In addition, the -rt patchset turns spinlocks into a sleeping locks so
+that the corresponding critical sections can be preempted, which
+also means that these sleeplockified spinlocks (but not other sleeping locks!)
+may be acquire within -rt-Linux-kernel RCU read-side critical sections.
+
+<p>
+Note that it <i>is</i> legal for a normal RCU read-side critical section
+to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>),
+but only as long as it does not loop indefinitely attempting to
+conditionally acquire that sleeping locks.
+The key point is that things like <tt>mutex_trylock()</tt>
+either return with the mutex held, or return an error indication if
+the mutex was not immediately available.
+Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping.
+
+
+</p><p><a href="#Quick%20Quiz%2011"><b>Back to Quick Quiz 11</b>.</a>
+
+<a name="qq12answer"></a>
+<p><b>Quick Quiz 12</b>:
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+
+
+</p><p><b>Answer</b>:
+Presumably the <tt>-&gt;gp_lock</tt> acquired on line&nbsp;18 excludes
+any changes, including any insertions that <tt>rcu_dereference()</tt>
+would protect against.
+Therefore, any insertions will be delayed until after <tt>-&gt;gp_lock</tt>
+is released on line&nbsp;25, which in turn means that
+<tt>rcu_access_pointer()</tt> suffices.
+
+
+</p><p><a href="#Quick%20Quiz%2012"><b>Back to Quick Quiz 12</b>.</a>
+
+<a name="qq13answer"></a>
+<p><b>Quick Quiz 13</b>:
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+
+
+</p><p><b>Answer</b>:
+We could define things this way, but keep in mind that this sort of
+definition would say that updates in garbage-collected languages
+cannot complete until the next time the garbage collector runs,
+which does not seem at all reasonable.
+The key point is that in most cases, an updater using either
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the
+next update as soon as it has invoked <tt>call_rcu()</tt> or
+<tt>kfree_rcu()</tt>, without having to wait for a subsequent
+grace period.
+
+
+</p><p><a href="#Quick%20Quiz%2013"><b>Back to Quick Quiz 13</b>.</a>
+
+<a name="qq14answer"></a>
+<p><b>Quick Quiz 14</b>:
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+
+
+</p><p><b>Answer</b>:
+In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
+maps directly to <tt>synchronize_sched()</tt>.
+Therefore, <tt>synchronize_rcu()</tt> works normally throughout
+boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
+However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
+so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
+during scheduler initialization.
+
+
+</p><p><a href="#Quick%20Quiz%2014"><b>Back to Quick Quiz 14</b>.</a>
+
+
+</body></html>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.htmlx b/Documentation/RCU/Design/Requirements/Requirements.htmlx
new file mode 100644
index 000000000000..3a97ba490c42
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/Requirements.htmlx
@@ -0,0 +1,2741 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+        <html>
+        <head><title>A Tour Through RCU's Requirements [LWN.net]</title>
+        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
+
+<h1>A Tour Through RCU's Requirements</h1>
+
+<p>Copyright IBM Corporation, 2015</p>
+<p>Author: Paul E.&nbsp;McKenney</p>
+<p><i>The initial version of this document appeared in the
+<a href="https://lwn.net/">LWN</a> articles
+<a href="https://lwn.net/Articles/652156/">here</a>,
+<a href="https://lwn.net/Articles/652677/">here</a>, and
+<a href="https://lwn.net/Articles/653326/">here</a>.</i></p>
+
+<h2>Introduction</h2>
+
+<p>
+Read-copy update (RCU) is a synchronization mechanism that is often
+used as a replacement for reader-writer locking.
+RCU is unusual in that updaters do not block readers,
+which means that RCU's read-side primitives can be exceedingly fast
+and scalable.
+In addition, updaters can make useful forward progress concurrently
+with readers.
+However, all this concurrency between RCU readers and updaters does raise
+the question of exactly what RCU readers are doing, which in turn
+raises the question of exactly what RCU's requirements are.
+
+<p>
+This document therefore summarizes RCU's requirements, and can be thought
+of as an informal, high-level specification for RCU.
+It is important to understand that RCU's specification is primarily
+empirical in nature;
+in fact, I learned about many of these requirements the hard way.
+This situation might cause some consternation, however, not only
+has this learning process been a lot of fun, but it has also been
+a great privilege to work with so many people willing to apply
+technologies in interesting new ways.
+
+<p>
+All that aside, here are the categories of currently known RCU requirements:
+</p>
+
+<ol>
+<li>	<a href="#Fundamental Requirements">
+	Fundamental Requirements</a>
+<li>	<a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a>
+<li>	<a href="#Parallelism Facts of Life">
+	Parallelism Facts of Life</a>
+<li>	<a href="#Quality-of-Implementation Requirements">
+	Quality-of-Implementation Requirements</a>
+<li>	<a href="#Linux Kernel Complications">
+	Linux Kernel Complications</a>
+<li>	<a href="#Software-Engineering Requirements">
+	Software-Engineering Requirements</a>
+<li>	<a href="#Other RCU Flavors">
+	Other RCU Flavors</a>
+<li>	<a href="#Possible Future Changes">
+	Possible Future Changes</a>
+</ol>
+
+<p>
+This is followed by a <a href="#Summary">summary</a>,
+which is in turn followed by the inevitable
+<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
+
+<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2>
+
+<p>
+RCU's fundamental requirements are the closest thing RCU has to hard
+mathematical requirements.
+These are:
+
+<ol>
+<li>	<a href="#Grace-Period Guarantee">
+	Grace-Period Guarantee</a>
+<li>	<a href="#Publish-Subscribe Guarantee">
+	Publish-Subscribe Guarantee</a>
+<li>	<a href="#Memory-Barrier Guarantees">
+	Memory-Barrier Guarantees</a>
+<li>	<a href="#RCU Primitives Guaranteed to Execute Unconditionally">
+	RCU Primitives Guaranteed to Execute Unconditionally</a>
+<li>	<a href="#Guaranteed Read-to-Write Upgrade">
+	Guaranteed Read-to-Write Upgrade</a>
+</ol>
+
+<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3>
+
+<p>
+RCU's grace-period guarantee is unusual in being premeditated:
+Jack Slingwine and I had this guarantee firmly in mind when we started
+work on RCU (then called &ldquo;rclock&rdquo;) in the early 1990s.
+That said, the past two decades of experience with RCU have produced
+a much more detailed understanding of this guarantee.
+
+<p>
+RCU's grace-period guarantee allows updaters to wait for the completion
+of all pre-existing RCU read-side critical sections.
+An RCU read-side critical section
+begins with the marker <tt>rcu_read_lock()</tt> and ends with
+the marker <tt>rcu_read_unlock()</tt>.
+These markers may be nested, and RCU treats a nested set as one
+big RCU read-side critical section.
+Production-quality implementations of <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> are extremely lightweight, and in
+fact have exactly zero overhead in Linux kernels built for production
+use with <tt>CONFIG_PREEMPT=n</tt>.
+
+<p>
+This guarantee allows ordering to be enforced with extremely low
+overhead to readers, for example:
+
+<blockquote>
+<pre>
+ 1 int x, y;
+ 2
+ 3 void thread0(void)
+ 4 {
+ 5   rcu_read_lock();
+ 6   r1 = READ_ONCE(x);
+ 7   r2 = READ_ONCE(y);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   WRITE_ONCE(x, 1);
+14   synchronize_rcu();
+15   WRITE_ONCE(y, 1);
+16 }
+</pre>
+</blockquote>
+
+<p>
+Because the <tt>synchronize_rcu()</tt> on line&nbsp;14 waits for
+all pre-existing readers, any instance of <tt>thread0()</tt> that
+loads a value of zero from <tt>x</tt> must complete before
+<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must
+also load a value of zero from <tt>y</tt>.
+Similarly, any instance of <tt>thread0()</tt> that loads a value of
+one from <tt>y</tt> must have started after the
+<tt>synchronize_rcu()</tt> started, and must therefore also load
+a value of one from <tt>x</tt>.
+Therefore, the outcome:
+<blockquote>
+<pre>
+(r1 == 0 &amp;&amp; r2 == 1)
+</pre>
+</blockquote>
+cannot happen.
+
+<p>@@QQ@@
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+<p>@@QQA@@
+First, if updaters do not wish to be blocked by readers, they can use
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will
+be discussed later.
+Second, even when using <tt>synchronize_rcu()</tt>, the other
+update-side code does run concurrently with readers, whether pre-existing
+or not.
+<p>@@QQE@@
+
+<p>
+This scenario resembles one of the first uses of RCU in
+<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>,
+which managed a distributed lock manager's transition into
+a state suitable for handling recovery from node failure,
+more or less as follows:
+
+<blockquote>
+<pre>
+ 1 #define STATE_NORMAL        0
+ 2 #define STATE_WANT_RECOVERY 1
+ 3 #define STATE_RECOVERING    2
+ 4 #define STATE_WANT_NORMAL   3
+ 5
+ 6 int state = STATE_NORMAL;
+ 7
+ 8 void do_something_dlm(void)
+ 9 {
+10   int state_snap;
+11
+12   rcu_read_lock();
+13   state_snap = READ_ONCE(state);
+14   if (state_snap == STATE_NORMAL)
+15     do_something();
+16   else
+17     do_something_carefully();
+18   rcu_read_unlock();
+19 }
+20
+21 void start_recovery(void)
+22 {
+23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
+24   synchronize_rcu();
+25   WRITE_ONCE(state, STATE_RECOVERING);
+26   recovery();
+27   WRITE_ONCE(state, STATE_WANT_NORMAL);
+28   synchronize_rcu();
+29   WRITE_ONCE(state, STATE_NORMAL);
+30 }
+</pre>
+</blockquote>
+
+<p>
+The RCU read-side critical section in <tt>do_something_dlm()</tt>
+works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt>
+to guarantee that <tt>do_something()</tt> never runs concurrently
+with <tt>recovery()</tt>, but with little or no synchronization
+overhead in <tt>do_something_dlm()</tt>.
+
+<p>@@QQ@@
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+<p>@@QQA@@
+Without that extra grace period, memory reordering could result in
+<tt>do_something_dlm()</tt> executing <tt>do_something()</tt>
+concurrently with the last bits of <tt>recovery()</tt>.
+<p>@@QQE@@
+
+<p>
+In order to avoid fatal problems such as deadlocks,
+an RCU read-side critical section must not contain calls to
+<tt>synchronize_rcu()</tt>.
+Similarly, an RCU read-side critical section must not
+contain anything that waits, directly or indirectly, on completion of
+an invocation of <tt>synchronize_rcu()</tt>.
+
+<p>
+Although RCU's grace-period guarantee is useful in and of itself, with
+<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>,
+it would be good to be able to use RCU to coordinate read-side
+access to linked data structures.
+For this, the grace-period guarantee is not sufficient, as can
+be seen in function <tt>add_gp_buggy()</tt> below.
+We will look at the reader's code later, but in the meantime, just think of
+the reader as locklessly picking up the <tt>gp</tt> pointer,
+and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the
+<tt>-&gt;a</tt> and <tt>-&gt;b</tt> fields.
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   gp = p; /* ORDERING BUG */
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The problem is that both the compiler and weakly ordered CPUs are within
+their rights to reorder this code as follows:
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy_optimized(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+<b>11   gp = p; /* ORDERING BUG */
+12   p-&gt;a = a;
+13   p-&gt;b = a;</b>
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+If an RCU reader fetches <tt>gp</tt> just after
+<tt>add_gp_buggy_optimized</tt> executes line&nbsp;11,
+it will see garbage in the <tt>-&gt;a</tt> and <tt>-&gt;b</tt>
+fields.
+And this is but one of many ways in which compiler and hardware optimizations
+could cause trouble.
+Therefore, we clearly need some way to prevent the compiler and the CPU from
+reordering in this manner, which brings us to the publish-subscribe
+guarantee discussed in the next section.
+
+<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3>
+
+<p>
+RCU's publish-subscribe guarantee allows data to be inserted
+into a linked data structure without disrupting RCU readers.
+The updater uses <tt>rcu_assign_pointer()</tt> to insert the
+new data, and readers use <tt>rcu_dereference()</tt> to
+access data, whether new or old.
+The following shows an example of insertion:
+
+<blockquote>
+<pre>
+ 1 bool add_gp(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   rcu_assign_pointer(gp, p);
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_assign_pointer()</tt> on line&nbsp;13 is conceptually
+equivalent to a simple assignment statement, but also guarantees
+that its assignment will
+happen after the two assignments in lines&nbsp;11 and&nbsp;12,
+similar to the C11 <tt>memory_order_release</tt> store operation.
+It also prevents any number of &ldquo;interesting&rdquo; compiler
+optimizations, for example, the use of <tt>gp</tt> as a scratch
+location immediately preceding the assignment.
+
+<p>@@QQ@@
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+<p>@@QQA@@
+No, it cannot.
+The readers cannot see either of these two fields until
+the assignment to <tt>gp</tt>, by which time both fields are
+fully initialized.
+So reordering the assignments
+to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt> cannot possibly
+cause any problems.
+<p>@@QQE@@
+
+<p>
+It is tempting to assume that the reader need not do anything special
+to control its accesses to the RCU-protected data,
+as shown in <tt>do_something_gp_buggy()</tt> below:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+However, this temptation must be resisted because there are a
+surprisingly large number of ways that the compiler
+(to say nothing of
+<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>)
+can trip this code up.
+For but one example, if the compiler were short of registers, it
+might choose to refetch from <tt>gp</tt> rather than keeping
+a separate copy in <tt>p</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy_optimized(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
+<b> 5     do_something(gp-&gt;a, gp-&gt;b);</b>
+ 6     rcu_read_unlock();
+ 7     return true;
+ 8   }
+ 9   rcu_read_unlock();
+10   return false;
+11 }
+</pre>
+</blockquote>
+
+<p>
+If this function ran concurrently with a series of updates that
+replaced the current structure with a new one,
+the fetches of <tt>gp-&gt;a</tt>
+and <tt>gp-&gt;b</tt> might well come from two different structures,
+which could cause serious confusion.
+To prevent this (and much else besides), <tt>do_something_gp()</tt> uses
+<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = rcu_dereference(gp);
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha)
+memory barriers in the Linux kernel.
+Should a
+<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a>
+ever appear, then <tt>rcu_dereference()</tt> could be implemented
+as a <tt>memory_order_consume</tt> load.
+Regardless of the exact implementation, a pointer fetched by
+<tt>rcu_dereference()</tt> may not be used outside of the
+outermost RCU read-side critical section containing that
+<tt>rcu_dereference()</tt>, unless protection of
+the corresponding data element has been passed from RCU to some
+other synchronization mechanism, most commonly locking or
+<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>.
+
+<p>
+In short, updaters use <tt>rcu_assign_pointer()</tt> and readers
+use <tt>rcu_dereference()</tt>, and these two RCU API elements
+work together to ensure that readers have a consistent view of
+newly added data elements.
+
+<p>
+Of course, it is also necessary to remove elements from RCU-protected
+data structures, for example, using the following process:
+
+<ol>
+<li>	Remove the data element from the enclosing structure.
+<li>	Wait for all pre-existing RCU read-side critical sections
+	to complete (because only pre-existing readers can possibly have
+	a reference to the newly removed data element).
+<li>	At this point, only the updater has a reference to the
+	newly removed data element, so it can safely reclaim
+	the data element, for example, by passing it to <tt>kfree()</tt>.
+</ol>
+
+This process is implemented by <tt>remove_gp_synchronous()</tt>:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_synchronous(void)
+ 2 {
+ 3   struct foo *p;
+ 4
+ 5   spin_lock(&amp;gp_lock);
+ 6   p = rcu_access_pointer(gp);
+ 7   if (!p) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   rcu_assign_pointer(gp, NULL);
+12   spin_unlock(&amp;gp_lock);
+13   synchronize_rcu();
+14   kfree(p);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+This function is straightforward, with line&nbsp;13 waiting for a grace
+period before line&nbsp;14 frees the old data element.
+This waiting ensures that readers will reach line&nbsp;7 of
+<tt>do_something_gp()</tt> before the data element referenced by
+<tt>p</tt> is freed.
+The <tt>rcu_access_pointer()</tt> on line&nbsp;6 is similar to
+<tt>rcu_dereference()</tt>, except that:
+
+<ol>
+<li>	The value returned by <tt>rcu_access_pointer()</tt>
+	cannot be dereferenced.
+	If you want to access the value pointed to as well as
+	the pointer itself, use <tt>rcu_dereference()</tt>
+	instead of <tt>rcu_access_pointer()</tt>.
+<li>	The call to <tt>rcu_access_pointer()</tt> need not be
+	protected.
+	In contrast, <tt>rcu_dereference()</tt> must either be
+	within an RCU read-side critical section or in a code
+	segment where the pointer cannot change, for example, in
+	code protected by the corresponding update-side lock.
+</ol>
+
+<p>@@QQ@@
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+<p>@@QQA@@
+Let's start with what happens to <tt>do_something_gp()</tt>
+if it fails to use <tt>rcu_dereference()</tt>.
+It could reuse a value formerly fetched from this same pointer.
+It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time
+manner, resulting in <i>load tearing</i>, in turn resulting a bytewise
+mash-up of two distince pointer values.
+It might even use value-speculation optimizations, where it makes a wrong
+guess, but by the time it gets around to checking the value, an update
+has changed the pointer to match the wrong guess.
+Too bad about any dereferences that returned pre-initialization garbage
+in the meantime!
+
+<p>
+For <tt>remove_gp_synchronous()</tt>, as long as all modifications
+to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>,
+the above optimizations are harmless.
+However,
+with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>,
+<tt>sparse</tt> will complain if you
+define <tt>gp</tt> with <tt>__rcu</tt> and then
+access it without using
+either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>.
+<p>@@QQE@@
+
+<p>
+In short, RCU's publish-subscribe guarantee is provided by the combination
+of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>.
+This guarantee allows data elements to be safely added to RCU-protected
+linked data structures without disrupting RCU readers.
+This guarantee can be used in combination with the grace-period
+guarantee to also allow data elements to be removed from RCU-protected
+linked data structures, again without disrupting RCU readers.
+
+<p>
+This guarantee was only partially premeditated.
+DYNIX/ptx used an explicit memory barrier for publication, but had nothing
+resembling <tt>rcu_dereference()</tt> for subscription, nor did it
+have anything resembling the <tt>smp_read_barrier_depends()</tt>
+that was later subsumed into <tt>rcu_dereference()</tt>.
+The need for these operations made itself known quite suddenly at a
+late-1990s meeting with the DEC Alpha architects, back in the days when
+DEC was still a free-standing company.
+It took the Alpha architects a good hour to convince me that any sort
+of barrier would ever be needed, and it then took me a good <i>two</i> hours
+to convince them that their documentation did not make this point clear.
+More recent work with the C and C++ standards committees have provided
+much education on tricks and traps from the compiler.
+In short, compilers were much less tricky in the early 1990s, but in
+2015, don't even think about omitting <tt>rcu_dereference()</tt>!
+
+<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3>
+
+<p>
+The previous section's simple linked-data-structure scenario clearly
+demonstrates the need for RCU's stringent memory-ordering guarantees on
+systems with more than one CPU:
+
+<ol>
+<li>	Each CPU that has an RCU read-side critical section that
+	begins before <tt>synchronize_rcu()</tt> starts is
+	guaranteed to execute a full memory barrier between the time
+	that the RCU read-side critical section ends and the time that
+	<tt>synchronize_rcu()</tt> returns.
+	Without this guarantee, a pre-existing RCU read-side critical section
+	might hold a reference to the newly removed <tt>struct foo</tt>
+	after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt>.
+<li>	Each CPU that has an RCU read-side critical section that ends
+	after <tt>synchronize_rcu()</tt> returns is guaranteed
+	to execute a full memory barrier between the time that
+	<tt>synchronize_rcu()</tt> begins and the time that the RCU
+	read-side critical section begins.
+	Without this guarantee, a later RCU read-side critical section
+	running after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt> might
+	later run <tt>do_something_gp()</tt> and find the
+	newly deleted <tt>struct foo</tt>.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> remains
+	on a given CPU, then that CPU is guaranteed to execute a full
+	memory barrier sometime during the execution of
+	<tt>synchronize_rcu()</tt>.
+	This guarantee ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on line&nbsp;11.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> migrates
+	among a group of CPUs during that invocation, then each of the
+	CPUs in that group is guaranteed to execute a full memory barrier
+	sometime during the execution of <tt>synchronize_rcu()</tt>.
+	This guarantee also ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on
+	line&nbsp;11, but also in the case where the thread executing the
+	<tt>synchronize_rcu()</tt> migrates in the meantime.
+</ol>
+
+<p>@@QQ@@
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+<p>@@QQA@@
+If RCU cannot tell whether or not a given
+RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>,
+then it must assume that the RCU read-side critical section
+started first.
+In other words, a given instance of <tt>synchronize_rcu()</tt>
+can avoid waiting on a given RCU read-side critical section only
+if it can prove that <tt>synchronize_rcu()</tt> started first.
+<p>@@QQE@@
+
+<p>@@QQ@@
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+<p>@@QQA@@
+Yes, they really are required.
+To see why the first guarantee is required, consider the following
+sequence of events:
+
+<ol>
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Very likely to return p. */</tt>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>do_something_with(q-&gt;a);
+	/* No smp_mb(), so might happen after kfree(). */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+</ol>
+
+<p>
+Therefore, there absolutely must be a full memory barrier between the
+end of the RCU read-side critical section and the end of the
+grace period.
+
+<p>
+The sequence of events demonstrating the necessity of the second rule
+is roughly similar:
+
+<ol>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Might return p if no memory barrier. */</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+<li>	CPU 1: <tt>do_something_with(q-&gt;a); /* Boom!!! */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+</ol>
+
+<p>
+And similarly, without a memory barrier between the beginning of the
+grace period and the beginning of the RCU read-side critical section,
+CPU&nbsp;1 might end up accessing the freelist.
+
+<p>
+The &ldquo;as if&rdquo; rule of course applies, so that any implementation
+that acts as if the appropriate memory barriers were in place is a
+correct implementation.
+That said, it is much easier to fool yourself into believing that you have
+adhered to the as-if rule than it is to actually adhere to it!
+<p>@@QQE@@
+
+<p>
+Note that these memory-barrier requirements do not replace the fundamental
+RCU requirement that a grace period wait for all pre-existing readers.
+On the contrary, the memory barriers called out in this section must operate in
+such a way as to <i>enforce</i> this fundamental requirement.
+Of course, different implementations enforce this requirement in different
+ways, but enforce it they must.
+
+<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3>
+
+<p>
+The common-case RCU primitives are unconditional.
+They are invoked, they do their job, and they return, with no possibility
+of error, and no need to retry.
+This is a key RCU design philosophy.
+
+<p>
+However, this philosophy is pragmatic rather than pigheaded.
+If someone comes up with a good justification for a particular conditional
+RCU primitive, it might well be implemented and added.
+After all, this guarantee was reverse-engineered, not premeditated.
+The unconditional nature of the RCU primitives was initially an
+accident of implementation, and later experience with synchronization
+primitives with conditional primitives caused me to elevate this
+accident to a guarantee.
+Therefore, the justification for adding a conditional primitive to
+RCU would need to be based on detailed and compelling use cases.
+
+<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3>
+
+<p>
+As far as RCU is concerned, it is always possible to carry out an
+update within an RCU read-side critical section.
+For example, that RCU read-side critical section might search for
+a given data element, and then might acquire the update-side
+spinlock in order to update that element, all while remaining
+in that RCU read-side critical section.
+Of course, it is necessary to exit the RCU read-side critical section
+before invoking <tt>synchronize_rcu()</tt>, however, this
+inconvenience can be avoided through use of the
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members
+described later in this document.
+
+<p>@@QQ@@
+But how does the upgrade-to-write operation exclude other readers?
+<p>@@QQA@@
+It doesn't, just like normal RCU updates, which also do not exclude
+RCU readers.
+<p>@@QQE@@
+
+<p>
+This guarantee allows lookup code to be shared between read-side
+and update-side code, and was premeditated, appearing in the earliest
+DYNIX/ptx RCU documentation.
+
+<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2>
+
+<p>
+RCU provides extremely lightweight readers, and its read-side guarantees,
+though quite useful, are correspondingly lightweight.
+It is therefore all too easy to assume that RCU is guaranteeing more
+than it really is.
+Of course, the list of things that RCU does not guarantee is infinitely
+long, however, the following sections list a few non-guarantees that
+have caused confusion.
+Except where otherwise noted, these non-guarantees were premeditated.
+
+<ol>
+<li>	<a href="#Readers Impose Minimal Ordering">
+	Readers Impose Minimal Ordering</a>
+<li>	<a href="#Readers Do Not Exclude Updaters">
+	Readers Do Not Exclude Updaters</a>
+<li>	<a href="#Updaters Only Wait For Old Readers">
+	Updaters Only Wait For Old Readers</a>
+<li>	<a href="#Grace Periods Don't Partition Read-Side Critical Sections">
+	Grace Periods Don't Partition Read-Side Critical Sections</a>
+<li>	<a href="#Read-Side Critical Sections Don't Partition Grace Periods">
+	Read-Side Critical Sections Don't Partition Grace Periods</a>
+<li>	<a href="#Disabling Preemption Does Not Block Grace Periods">
+	Disabling Preemption Does Not Block Grace Periods</a>
+</ol>
+
+<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3>
+
+<p>
+Reader-side markers such as <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees
+except through their interaction with the grace-period APIs such as
+<tt>synchronize_rcu()</tt>.
+To see this, consider the following pair of threads:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(x, 1);
+ 5   rcu_read_unlock();
+ 6   rcu_read_lock();
+ 7   WRITE_ONCE(y, 1);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   rcu_read_lock();
+14   r1 = READ_ONCE(y);
+15   rcu_read_unlock();
+16   rcu_read_lock();
+17   r2 = READ_ONCE(x);
+18   rcu_read_unlock();
+19 }
+</pre>
+</blockquote>
+
+<p>
+After <tt>thread0()</tt> and <tt>thread1()</tt> execute
+concurrently, it is quite possible to have
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0)
+</pre>
+</blockquote>
+
+(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>),
+which would not be possible if <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> had much in the way of ordering
+properties.
+But they do not, so the CPU is within its rights
+to do significant reordering.
+This is by design:  Any significant ordering constraints would slow down
+these fast-path APIs.
+
+<p>@@QQ@@
+Can't the compiler also reorder this code?
+<p>@@QQA@@
+No, the volatile casts in <tt>READ_ONCE()</tt> and
+<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in
+this particular case.
+<p>@@QQE@@
+
+<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3>
+
+<p>
+Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt>
+exclude updates.
+All they do is to prevent grace periods from ending.
+The following example illustrates this:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   r1 = READ_ONCE(y);
+ 5   if (r1) {
+ 6     do_something_with_nonzero_x();
+ 7     r2 = READ_ONCE(x);
+ 8     WARN_ON(!r2); /* BUG!!! */
+ 9   }
+10   rcu_read_unlock();
+11 }
+12
+13 void thread1(void)
+14 {
+15   spin_lock(&amp;my_lock);
+16   WRITE_ONCE(x, 1);
+17   WRITE_ONCE(y, 1);
+18   spin_unlock(&amp;my_lock);
+19 }
+</pre>
+</blockquote>
+
+<p>
+If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt>
+excluded the <tt>thread1()</tt> function's update,
+the <tt>WARN_ON()</tt> could never fire.
+But the fact is that <tt>rcu_read_lock()</tt> does not exclude
+much of anything aside from subsequent grace periods, of which
+<tt>thread1()</tt> has none, so the
+<tt>WARN_ON()</tt> can and does fire.
+
+<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3>
+
+<p>
+It might be tempting to assume that after <tt>synchronize_rcu()</tt>
+completes, there are no readers executing.
+This temptation must be avoided because
+new readers can start immediately after <tt>synchronize_rcu()</tt>
+starts, and <tt>synchronize_rcu()</tt> is under no
+obligation to wait for these new readers.
+
+<p>@@QQ@@
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+<p>@@QQA@@
+No.
+Even if <tt>synchronize_rcu()</tt> were to wait until
+all readers had completed, a new reader might start immediately after
+<tt>synchronize_rcu()</tt> completed.
+Therefore, the code following
+<tt>synchronize_rcu()</tt> cannot rely on there being no readers
+in any case.
+<p>@@QQE@@
+
+<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections">
+Grace Periods Don't Partition Read-Side Critical Sections</a></h3>
+
+<p>
+It is tempting to assume that if any part of one RCU read-side critical
+section precedes a given grace period, and if any part of another RCU
+read-side critical section follows that same grace period, then all of
+the first RCU read-side critical section must precede all of the second.
+However, this just isn't the case: A single grace period does not
+partition the set of RCU read-side critical sections.
+An example of this situation can be illustrated as follows, where
+<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   r2 = READ_ONCE(b);
+20   r3 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+</pre>
+</blockquote>
+
+<p>
+It turns out that the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0 &amp;&amp; r3 == 1)
+</pre>
+</blockquote>
+
+is entirely possible.
+The following figure show how this can happen, with each circled
+<tt>QS</tt> indicating the point at which RCU recorded a
+<i>quiescent state</i> for each thread, that is, a state in which
+RCU knows that the thread cannot be in the midst of an RCU read-side
+critical section that started before the current grace period:
+
+<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p>
+
+<p>
+If it is necessary to partition RCU read-side critical sections in this
+manner, it is necessary to use two grace periods, where the first
+grace period is known to end before the second grace period starts:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   r2 = READ_ONCE(c);
+19   synchronize_rcu();
+20   WRITE_ONCE(d, 1);
+21 }
+22
+23 void thread3(void)
+24 {
+25   rcu_read_lock();
+26   r3 = READ_ONCE(b);
+27   r4 = READ_ONCE(d);
+28   rcu_read_unlock();
+29 }
+</pre>
+</blockquote>
+
+<p>
+Here, if <tt>(r1 == 1)</tt>, then
+<tt>thread0()</tt>'s write to <tt>b</tt> must happen
+before the end of <tt>thread1()</tt>'s grace period.
+If in addition <tt>(r4 == 1)</tt>, then
+<tt>thread3()</tt>'s read from <tt>b</tt> must happen
+after the beginning of <tt>thread2()</tt>'s grace period.
+If it is also the case that <tt>(r2 == 1)</tt>, then the
+end of <tt>thread1()</tt>'s grace period must precede the
+beginning of <tt>thread2()</tt>'s grace period.
+This mean that the two RCU read-side critical sections cannot overlap,
+guaranteeing that <tt>(r3 == 1)</tt>.
+As a result, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 0 &amp;&amp; r4 == 1)
+</pre>
+</blockquote>
+
+cannot happen.
+
+<p>
+This non-requirement was also non-premeditated, but became apparent
+when studying RCU's interaction with memory ordering.
+
+<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods">
+Read-Side Critical Sections Don't Partition Grace Periods</a></h3>
+
+<p>
+It is also tempting to assume that if an RCU read-side critical section
+happens between a pair of grace periods, then those grace periods cannot
+overlap.
+However, this temptation leads nowhere good, as can be illustrated by
+the following, with all variables initially zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   WRITE_ONCE(d, 1);
+20   r2 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+23
+24 void thread3(void)
+25 {
+26   r3 = READ_ONCE(d);
+27   synchronize_rcu();
+28   WRITE_ONCE(e, 1);
+29 }
+30
+31 void thread4(void)
+32 {
+33   rcu_read_lock();
+34   r4 = READ_ONCE(b);
+35   r5 = READ_ONCE(e);
+36   rcu_read_unlock();
+37 }
+</pre>
+</blockquote>
+
+<p>
+In this case, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 1 &amp;&amp; r4 == 0 &amp&amp; r5 == 1)
+</pre>
+</blockquote>
+
+is entirely possible, as illustrated below:
+
+<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p>
+
+<p>
+Again, an RCU read-side critical section can overlap almost all of a
+given grace period, just so long as it does not overlap the entire
+grace period.
+As a result, an RCU read-side critical section cannot partition a pair
+of RCU grace periods.
+
+<p>@@QQ@@
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+<p>@@QQA@@
+In theory, an infinite number.
+In practice, an unknown number that is sensitive to both implementation
+details and timing considerations.
+Therefore, even in practice, RCU users must abide by the theoretical rather
+than the practical answer.
+<p>@@QQE@@
+
+<h3><a name="Disabling Preemption Does Not Block Grace Periods">
+Disabling Preemption Does Not Block Grace Periods</a></h3>
+
+<p>
+There was a time when disabling preemption on any given CPU would block
+subsequent grace periods.
+However, this was an accident of implementation and is not a requirement.
+And in the current Linux-kernel implementation, disabling preemption
+on a given CPU in fact does not block grace periods, as Oleg Nesterov
+<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>.
+
+<p>
+If you need a preempt-disable region to block grace periods, you need to add
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example
+as follows:
+
+<blockquote>
+<pre>
+ 1 preempt_disable();
+ 2 rcu_read_lock();
+ 3 do_something();
+ 4 rcu_read_unlock();
+ 5 preempt_enable();
+ 6
+ 7 /* Spinlocks implicitly disable preemption. */
+ 8 spin_lock(&amp;mylock);
+ 9 rcu_read_lock();
+10 do_something();
+11 rcu_read_unlock();
+12 spin_unlock(&amp;mylock);
+</pre>
+</blockquote>
+
+<p>
+In theory, you could enter the RCU read-side critical section first,
+but it is more efficient to keep the entire RCU read-side critical
+section contained in the preempt-disable region as shown above.
+Of course, RCU read-side critical sections that extend outside of
+preempt-disable regions will work correctly, but such critical sections
+can be preempted, which forces <tt>rcu_read_unlock()</tt> to do
+more work.
+And no, this is <i>not</i> an invitation to enclose all of your RCU
+read-side critical sections within preempt-disable regions, because
+doing so would degrade real-time response.
+
+<p>
+This non-requirement appeared with preemptible RCU.
+If you need a grace period that waits on non-preemptible code regions, use
+<a href="#Sched Flavor">RCU-sched</a>.
+
+<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2>
+
+<p>
+These parallelism facts of life are by no means specific to RCU, but
+the RCU implementation must abide by them.
+They therefore bear repeating:
+
+<ol>
+<li>	Any CPU or task may be delayed at any time,
+	and any attempts to avoid these delays by disabling
+	preemption, interrupts, or whatever are completely futile.
+	This is most obvious in preemptible user-level
+	environments and in virtualized environments (where
+	a given guest OS's VCPUs can be preempted at any time by
+	the underlying hypervisor), but can also happen in bare-metal
+	environments due to ECC errors, NMIs, and other hardware
+	events.
+	Although a delay of more than about 20 seconds can result
+	in splats, the RCU implementation is obligated to use
+	algorithms that can tolerate extremely long delays, but where
+	&ldquo;extremely long&rdquo; is not long enough to allow
+	wrap-around when incrementing a 64-bit counter.
+<li>	Both the compiler and the CPU can reorder memory accesses.
+	Where it matters, RCU must use compiler directives and
+	memory-barrier instructions to preserve ordering.
+<li>	Conflicting writes to memory locations in any given cache line
+	will result in expensive cache misses.
+	Greater numbers of concurrent writes and more-frequent
+	concurrent writes will result in more dramatic slowdowns.
+	RCU is therefore obligated to use algorithms that have
+	sufficient locality to avoid significant performance and
+	scalability problems.
+<li>	As a rough rule of thumb, only one CPU's worth of processing
+	may be carried out under the protection of any given exclusive
+	lock.
+	RCU must therefore use scalable locking designs.
+<li>	Counters are finite, especially on 32-bit systems.
+	RCU's use of counters must therefore tolerate counter wrap,
+	or be designed such that counter wrap would take way more
+	time than a single system is likely to run.
+	An uptime of ten years is quite possible, a runtime
+	of a century much less so.
+	As an example of the latter, RCU's dyntick-idle nesting counter
+	allows 54 bits for interrupt nesting level (this counter
+	is 64 bits even on a 32-bit system).
+	Overflowing this counter requires 2<sup>54</sup>
+	half-interrupts on a given CPU without that CPU ever going idle.
+	If a half-interrupt happened every microsecond, it would take
+	570 years of runtime to overflow this counter, which is currently
+	believed to be an acceptably long time.
+<li>	Linux systems can have thousands of CPUs running a single
+	Linux kernel in a single shared-memory environment.
+	RCU must therefore pay close attention to high-end scalability.
+</ol>
+
+<p>
+This last parallelism fact of life means that RCU must pay special
+attention to the preceding facts of life.
+The idea that Linux might scale to systems with thousands of CPUs would
+have been met with some skepticism in the 1990s, but these requirements
+would have otherwise have been unsurprising, even in the early 1990s.
+
+<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2>
+
+<p>
+These sections list quality-of-implementation requirements.
+Although an RCU implementation that ignores these requirements could
+still be used, it would likely be subject to limitations that would
+make it inappropriate for industrial-strength production use.
+Classes of quality-of-implementation requirements are as follows:
+
+<ol>
+<li>	<a href="#Specialization">Specialization</a>
+<li>	<a href="#Performance and Scalability">Performance and Scalability</a>
+<li>	<a href="#Composability">Composability</a>
+<li>	<a href="#Corner Cases">Corner Cases</a>
+</ol>
+
+<p>
+These classes is covered in the following sections.
+
+<h3><a name="Specialization">Specialization</a></h3>
+
+<p>
+RCU is and always has been intended primarily for read-mostly situations, as
+illustrated by the following figure.
+This means that RCU's read-side primitives are optimized, often at the
+expense of its update-side primitives.
+
+<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p>
+
+<p>
+This focus on read-mostly situations means that RCU must interoperate
+with other synchronization primitives.
+For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt>
+examples discussed earlier use RCU to protect readers and locking to
+coordinate updaters.
+However, the need extends much farther, requiring that a variety of
+synchronization primitives be legal within RCU read-side critical sections,
+including spinlocks, sequence locks, atomic operations, reference
+counters, and memory barriers.
+
+<p>@@QQ@@
+What about sleeping locks?
+<p>@@QQA@@
+These are forbidden within Linux-kernel RCU read-side critical sections
+because it is not legal to place a quiescent state (in this case,
+voluntary context switch) within an RCU read-side critical section.
+However, sleeping locks may be used within userspace RCU read-side critical
+sections, and also within Linux-kernel sleepable RCU
+<a href="#Sleepable RCU">(SRCU)</a>
+read-side critical sections.
+In addition, the -rt patchset turns spinlocks into a sleeping locks so
+that the corresponding critical sections can be preempted, which
+also means that these sleeplockified spinlocks (but not other sleeping locks!)
+may be acquire within -rt-Linux-kernel RCU read-side critical sections.
+
+<p>
+Note that it <i>is</i> legal for a normal RCU read-side critical section
+to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>),
+but only as long as it does not loop indefinitely attempting to
+conditionally acquire that sleeping locks.
+The key point is that things like <tt>mutex_trylock()</tt>
+either return with the mutex held, or return an error indication if
+the mutex was not immediately available.
+Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping.
+<p>@@QQE@@
+
+<p>
+It often comes as a surprise that many algorithms do not require a
+consistent view of data, but many can function in that mode,
+with network routing being the poster child.
+Internet routing algorithms take significant time to propagate
+updates, so that by the time an update arrives at a given system,
+that system has been sending network traffic the wrong way for
+a considerable length of time.
+Having a few threads continue to send traffic the wrong way for a
+few more milliseconds is clearly not a problem:  In the worst case,
+TCP retransmissions will eventually get the data where it needs to go.
+In general, when tracking the state of the universe outside of the
+computer, some level of inconsistency must be tolerated due to
+speed-of-light delays if nothing else.
+
+<p>
+Furthermore, uncertainty about external state is inherent in many cases.
+For example, a pair of veternarians might use heartbeat to determine
+whether or not a given cat was alive.
+But how long should they wait after the last heartbeat to decide that
+the cat is in fact dead?
+Waiting less than 400 milliseconds makes no sense because this would
+mean that a relaxed cat would be considered to cycle between death
+and life more than 100 times per minute.
+Moreover, just as with human beings, a cat's heart might stop for
+some period of time, so the exact wait period is a judgment call.
+One of our pair of veternarians might wait 30 seconds before pronouncing
+the cat dead, while the other might insist on waiting a full minute.
+The two veternarians would then disagree on the state of the cat during
+the final 30 seconds of the minute following the last heartbeat, as
+fancifully illustrated below:
+
+<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p>
+
+<p>
+Interestingly enough, this same situation applies to hardware.
+When push comes to shove, how do we tell whether or not some
+external server has failed?
+We send messages to it periodically, and declare it failed if we
+don't receive a response within a given period of time.
+Policy decisions can usually tolerate short
+periods of inconsistency.
+The policy was decided some time ago, and is only now being put into
+effect, so a few milliseconds of delay is normally inconsequential.
+
+<p>
+However, there are algorithms that absolutely must see consistent data.
+For example, the translation between a user-level SystemV semaphore
+ID to the corresponding in-kernel data structure is protected by RCU,
+but it is absolutely forbidden to update a semaphore that has just been
+removed.
+In the Linux kernel, this need for consistency is accommodated by acquiring
+spinlocks located in the in-kernel data structure from within
+the RCU read-side critical section, and this is indicated by the
+green box in the figure above.
+Many other techniques may be used, and are in fact used within the
+Linux kernel.
+
+<p>
+In short, RCU is not required to maintain consistency, and other
+mechanisms may be used in concert with RCU when consistency is required.
+RCU's specialization allows it to do its job extremely well, and its
+ability to interoperate with other synchronization mechanisms allows
+the right mix of synchronization tools to be used for a given job.
+
+<h3><a name="Performance and Scalability">Performance and Scalability</a></h3>
+
+<p>
+Energy efficiency is a critical component of performance today,
+and Linux-kernel RCU implementations must therefore avoid unnecessarily
+awakening idle CPUs.
+I cannot claim that this requirement was premeditated.
+In fact, I learned of it during a telephone conversation in which I
+was given &ldquo;frank and open&rdquo; feedback on the importance
+of energy efficiency in battery-powered systems and on specific
+energy-efficiency shortcomings of the Linux-kernel RCU implementation.
+In my experience, the battery-powered embedded community will consider
+any unnecessary wakeups to be extremely unfriendly acts.
+So much so that mere Linux-kernel-mailing-list posts are
+insufficient to vent their ire.
+
+<p>
+Memory consumption is not particularly important for in most
+situations, and has become decreasingly
+so as memory sizes have expanded and memory
+costs have plummeted.
+However, as I learned from Matt Mackall's
+<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
+efforts, memory footprint is critically important on single-CPU systems with
+non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
+<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
+was born.
+Josh Triplett has since taken over the small-memory banner with his
+<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a>
+project, which resulted in
+<a href="#Sleepable RCU">SRCU</a>
+becoming optional for those kernels not needing it.
+
+<p>
+The remaining performance requirements are, for the most part,
+unsurprising.
+For example, in keeping with RCU's read-side specialization,
+<tt>rcu_dereference()</tt> should have negligible overhead (for
+example, suppression of a few minor compiler optimizations).
+Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have exactly zero overhead.
+
+<p>
+In preemptible environments, in the case where the RCU read-side
+critical section was not preempted (as will be the case for the
+highest-priority real-time process), <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have minimal overhead.
+In particular, they should not contain atomic read-modify-write
+operations, memory-barrier instructions, preemption disabling,
+interrupt disabling, or backwards branches.
+However, in the case where the RCU read-side critical section was preempted,
+<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts.
+This is why it is better to nest an RCU read-side critical section
+within a preempt-disable region than vice versa, at least in cases
+where that critical section is short enough to avoid unduly degrading
+real-time latencies.
+
+<p>
+The <tt>synchronize_rcu()</tt> grace-period-wait primitive is
+optimized for throughput.
+It may therefore incur several milliseconds of latency in addition to
+the duration of the longest RCU read-side critical section.
+On the other hand, multiple concurrent invocations of
+<tt>synchronize_rcu()</tt> are required to use batching optimizations
+so that they can be satisfied by a single underlying grace-period-wait
+operation.
+For example, in the Linux kernel, it is not unusual for a single
+grace-period-wait operation to serve more than
+<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a>
+of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation
+overhead down to nearly zero.
+However, the grace-period optimization is also required to avoid
+measurable degradation of real-time scheduling and interrupt latencies.
+
+<p>
+In some cases, the multi-millisecond <tt>synchronize_rcu()</tt>
+latencies are unacceptable.
+In these cases, <tt>synchronize_rcu_expedited()</tt> may be used
+instead, reducing the grace-period latency down to a few tens of
+microseconds on small systems, at least in cases where the RCU read-side
+critical sections are short.
+There are currently no special latency requirements for
+<tt>synchronize_rcu_expedited()</tt> on large systems, but,
+consistent with the empirical nature of the RCU specification,
+that is subject to change.
+However, there most definitely are scalability requirements:
+A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096
+CPUs should at least make reasonable forward progress.
+In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
+is permitted to impose modest degradation of real-time latency
+on non-idle online CPUs.
+That said, it will likely be necessary to take further steps to reduce this
+degradation, hopefully to roughly that of a scheduling-clock interrupt.
+
+<p>
+There are a number of situations where even
+<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period
+latency is unacceptable.
+In these situations, the asynchronous <tt>call_rcu()</tt> can be
+used in place of <tt>synchronize_rcu()</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 static void remove_gp_cb(struct rcu_head *rhp)
+ 8 {
+ 9   struct foo *p = container_of(rhp, struct foo, rh);
+10
+11   kfree(p);
+12 }
+13
+14 bool remove_gp_asynchronous(void)
+15 {
+16   struct foo *p;
+17
+18   spin_lock(&amp;gp_lock);
+19   p = rcu_dereference(gp);
+20   if (!p) {
+21     spin_unlock(&amp;gp_lock);
+22     return false;
+23   }
+24   rcu_assign_pointer(gp, NULL);
+25   call_rcu(&amp;p-&gt;rh, remove_gp_cb);
+26   spin_unlock(&amp;gp_lock);
+27   return true;
+28 }
+</pre>
+</blockquote>
+
+<p>
+A definition of <tt>struct foo</tt> is finally needed, and appears
+on lines&nbsp;1-5.
+The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt>
+on line&nbsp;25, and will be invoked after the end of a subsequent
+grace period.
+This gets the same effect as <tt>remove_gp_synchronous()</tt>,
+but without forcing the updater to wait for a grace period to elapse.
+The <tt>call_rcu()</tt> function may be used in a number of
+situations where neither <tt>synchronize_rcu()</tt> nor
+<tt>synchronize_rcu_expedited()</tt> would be legal,
+including within preempt-disable code, <tt>local_bh_disable()</tt> code,
+interrupt-disable code, and interrupt handlers.
+However, even <tt>call_rcu()</tt> is illegal within NMI handlers.
+The callback function (<tt>remove_gp_cb()</tt> in this case) will be
+executed within softirq (software interrupt) environment within the
+Linux kernel,
+either within a real softirq handler or under the protection
+of <tt>local_bh_disable()</tt>.
+In both the Linux kernel and in userspace, it is bad practice to
+write an RCU callback function that takes too long.
+Long-running operations should be relegated to separate threads or
+(in the Linux kernel) workqueues.
+
+<p>@@QQ@@
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+<p>@@QQA@@
+Presumably the <tt>-&gt;gp_lock</tt> acquired on line&nbsp;18 excludes
+any changes, including any insertions that <tt>rcu_dereference()</tt>
+would protect against.
+Therefore, any insertions will be delayed until after <tt>-&gt;gp_lock</tt>
+is released on line&nbsp;25, which in turn means that
+<tt>rcu_access_pointer()</tt> suffices.
+<p>@@QQE@@
+
+<p>
+However, all that <tt>remove_gp_cb()</tt> is doing is
+invoking <tt>kfree()</tt> on the data element.
+This is a common idiom, and is supported by <tt>kfree_rcu()</tt>,
+which allows &ldquo;fire and forget&rdquo; operation as shown below:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 bool remove_gp_faf(void)
+ 8 {
+ 9   struct foo *p;
+10
+11   spin_lock(&amp;gp_lock);
+12   p = rcu_dereference(gp);
+13   if (!p) {
+14     spin_unlock(&amp;gp_lock);
+15     return false;
+16   }
+17   rcu_assign_pointer(gp, NULL);
+18   kfree_rcu(p, rh);
+19   spin_unlock(&amp;gp_lock);
+20   return true;
+21 }
+</pre>
+</blockquote>
+
+<p>
+Note that <tt>remove_gp_faf()</tt> simply invokes
+<tt>kfree_rcu()</tt> and proceeds, without any need to pay any
+further attention to the subsequent grace period and <tt>kfree()</tt>.
+It is permissible to invoke <tt>kfree_rcu()</tt> from the same
+environments as for <tt>call_rcu()</tt>.
+Interestingly enough, DYNIX/ptx had the equivalents of
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not
+<tt>synchronize_rcu()</tt>.
+This was due to the fact that RCU was not heavily used within DYNIX/ptx,
+so the very few places that needed something like
+<tt>synchronize_rcu()</tt> simply open-coded it.
+
+<p>@@QQ@@
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+<p>@@QQA@@
+We could define things this way, but keep in mind that this sort of
+definition would say that updates in garbage-collected languages
+cannot complete until the next time the garbage collector runs,
+which does not seem at all reasonable.
+The key point is that in most cases, an updater using either
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the
+next update as soon as it has invoked <tt>call_rcu()</tt> or
+<tt>kfree_rcu()</tt>, without having to wait for a subsequent
+grace period.
+<p>@@QQE@@
+
+<p>
+But what if the updater must wait for the completion of code to be
+executed after the end of the grace period, but has other tasks
+that can be carried out in the meantime?
+The polling-style <tt>get_state_synchronize_rcu()</tt> and
+<tt>cond_synchronize_rcu()</tt> functions may be used for this
+purpose, as shown below:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_poll(void)
+ 2 {
+ 3   struct foo *p;
+ 4   unsigned long s;
+ 5
+ 6   spin_lock(&amp;gp_lock);
+ 7   p = rcu_access_pointer(gp);
+ 8   if (!p) {
+ 9     spin_unlock(&amp;gp_lock);
+10     return false;
+11   }
+12   rcu_assign_pointer(gp, NULL);
+13   spin_unlock(&amp;gp_lock);
+14   s = get_state_synchronize_rcu();
+15   do_something_while_waiting();
+16   cond_synchronize_rcu(s);
+17   kfree(p);
+18   return true;
+19 }
+</pre>
+</blockquote>
+
+<p>
+On line&nbsp;14, <tt>get_state_synchronize_rcu()</tt> obtains a
+&ldquo;cookie&rdquo; from RCU,
+then line&nbsp;15 carries out other tasks,
+and finally, line&nbsp;16 returns immediately if a grace period has
+elapsed in the meantime, but otherwise waits as required.
+The need for <tt>get_state_synchronize_rcu</tt> and
+<tt>cond_synchronize_rcu()</tt> has appeared quite recently,
+so it is too early to tell whether they will stand the test of time.
+
+<p>
+RCU thus provides a range of tools to allow updaters to strike the
+required tradeoff between latency, flexibility and CPU overhead.
+
+<h3><a name="Composability">Composability</a></h3>
+
+<p>
+Composability has received much attention in recent years, perhaps in part
+due to the collision of multicore hardware with object-oriented techniques
+designed in single-threaded environments for single-threaded use.
+And in theory, RCU read-side critical sections may be composed, and in
+fact may be nested arbitrarily deeply.
+In practice, as with all real-world implementations of composable
+constructs, there are limitations.
+
+<p>
+Implementations of RCU for which <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> generate no code, such as
+Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
+nested arbitrarily deeply.
+After all, there is no overhead.
+Except that if all these instances of <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> are visible to the compiler,
+compilation will eventually fail due to exhausting memory,
+mass storage, or user patience, whichever comes first.
+If the nesting is not visible to the compiler, as is the case with
+mutually recursive functions each in its own translation unit,
+stack overflow will result.
+If the nesting takes the form of loops, either the control variable
+will overflow or (in the Linux kernel) you will get an RCU CPU stall warning.
+Nevertheless, this class of RCU implementations is one
+of the most composable constructs in existence.
+
+<p>
+RCU implementations that explicitly track nesting depth
+are limited by the nesting-depth counter.
+For example, the Linux kernel's preemptible RCU limits nesting to
+<tt>INT_MAX</tt>.
+This should suffice for almost all practical purposes.
+That said, a consecutive pair of RCU read-side critical sections
+between which there is an operation that waits for a grace period
+cannot be enclosed in another RCU read-side critical section.
+This is because it is not legal to wait for a grace period within
+an RCU read-side critical section:  To do so would result either
+in deadlock or
+in RCU implicitly splitting the enclosing RCU read-side critical
+section, neither of which is conducive to a long-lived and prosperous
+kernel.
+
+<p>
+It is worth noting that RCU is not alone in limiting composability.
+For example, many transactional-memory implementations prohibit
+composing a pair of transactions separated by an irrevocable
+operation (for example, a network receive operation).
+For another example, lock-based critical sections can be composed
+surprisingly freely, but only if deadlock is avoided.
+
+<p>
+In short, although RCU read-side critical sections are highly composable,
+care is required in some situations, just as is the case for any other
+composable synchronization mechanism.
+
+<h3><a name="Corner Cases">Corner Cases</a></h3>
+
+<p>
+A given RCU workload might have an endless and intense stream of
+RCU read-side critical sections, perhaps even so intense that there
+was never a point in time during which there was not at least one
+RCU read-side critical section in flight.
+RCU cannot allow this situation to block grace periods:  As long as
+all the RCU read-side critical sections are finite, grace periods
+must also be finite.
+
+<p>
+That said, preemptible RCU implementations could potentially result
+in RCU read-side critical sections being preempted for long durations,
+which has the effect of creating a long-duration RCU read-side
+critical section.
+This situation can arise only in heavily loaded systems, but systems using
+real-time priorities are of course more vulnerable.
+Therefore, RCU priority boosting is provided to help deal with this
+case.
+That said, the exact requirements on RCU priority boosting will likely
+evolve as more experience accumulates.
+
+<p>
+Other workloads might have very high update rates.
+Although one can argue that such workloads should instead use
+something other than RCU, the fact remains that RCU must
+handle such workloads gracefully.
+This requirement is another factor driving batching of grace periods,
+but it is also the driving force behind the checks for large numbers
+of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
+Finally, high update rates should not delay RCU read-side critical
+sections, although some read-side delays can occur when using
+<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
+of <tt>try_stop_cpus()</tt>.
+(In the future, <tt>synchronize_rcu_expedited()</tt> will be
+converted to use lighter-weight inter-processor interrupts (IPIs),
+but this will still disturb readers, though to a much smaller degree.)
+
+<p>
+Although all three of these corner cases were understood in the early
+1990s, a simple user-level test consisting of <tt>close(open(path))</tt>
+in a tight loop
+in the early 2000s suddenly provided a much deeper appreciation of the
+high-update-rate corner case.
+This test also motivated addition of some RCU code to react to high update
+rates, for example, if a given CPU finds itself with more than 10,000
+RCU callbacks queued, it will cause RCU to take evasive action by
+more aggressively starting grace periods and more aggressively forcing
+completion of grace-period processing.
+This evasive action causes the grace period to complete more quickly,
+but at the cost of restricting RCU's batching optimizations, thus
+increasing the CPU overhead incurred by that grace period.
+
+<h2><a name="Software-Engineering Requirements">
+Software-Engineering Requirements</a></h2>
+
+<p>
+Between Murphy's Law and &ldquo;To err is human&rdquo;, it is necessary to
+guard against mishaps and misuse:
+
+<ol>
+<li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
+	everywhere that it is needed, so kernels built with
+	<tt>CONFIG_PROVE_RCU=y</tt> will spat if
+	<tt>rcu_dereference()</tt> is used outside of an
+	RCU read-side critical section.
+	Update-side code can use <tt>rcu_dereference_protected()</tt>,
+	which takes a
+	<a href="https://lwn.net/Articles/371986/">lockdep expression</a>
+	to indicate what is providing the protection.
+	If the indicated protection is not provided, a lockdep splat
+	is emitted.
+
+	<p>
+	Code shared between readers and updaters can use
+	<tt>rcu_dereference_check()</tt>, which also takes a
+	lockdep expression, and emits a lockdep splat if neither
+	<tt>rcu_read_lock()</tt> nor the indicated protection
+	is in place.
+	In addition, <tt>rcu_dereference_raw()</tt> is used in those
+	(hopefully rare) cases where the required protection cannot
+	be easily described.
+	Finally, <tt>rcu_read_lock_held()</tt> is provided to
+	allow a function to verify that it has been invoked within
+	an RCU read-side critical section.
+	I was made aware of this set of requirements shortly after Thomas
+	Gleixner audited a number of RCU uses.
+<li>	A given function might wish to check for RCU-related preconditions
+	upon entry, before using any other RCU API.
+	The <tt>rcu_lockdep_assert()</tt> does this job,
+	asserting the expression in kernels having lockdep enabled
+	and doing nothing otherwise.
+<li>	It is also easy to forget to use <tt>rcu_assign_pointer()</tt>
+	and <tt>rcu_dereference()</tt>, perhaps (incorrectly)
+	substituting a simple assignment.
+	To catch this sort of error, a given RCU-protected pointer may be
+	tagged with <tt>__rcu</tt>, after which running sparse
+	with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain
+	about simple-assignment accesses to that pointer.
+	Arnd Bergmann made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lwn.net/Articles/376011/">patch series</a>.
+<li>	Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt>
+	will splat if a data element is passed to <tt>call_rcu()</tt>
+	twice in a row, without a grace period in between.
+	(This error is similar to a double free.)
+	The corresponding <tt>rcu_head</tt> structures that are
+	dynamically allocated are automatically tracked, but
+	<tt>rcu_head</tt> structures allocated on the stack
+	must be initialized with <tt>init_rcu_head_on_stack()</tt>
+	and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>.
+	Similarly, statically allocated non-stack <tt>rcu_head</tt>
+	structures must be initialized with <tt>init_rcu_head()</tt>
+	and cleaned up with <tt>destroy_rcu_head()</tt>.
+	Mathieu Desnoyers made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>.
+<li>	An infinite loop in an RCU read-side critical section will
+	eventually trigger an RCU CPU stall warning splat, with
+	the duration of &ldquo;eventually&rdquo; being controlled by the
+	<tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or,
+	alternatively, by the
+	<tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs
+	parameter.
+	However, RCU is not obligated to produce this splat
+	unless there is a grace period waiting on that particular
+	RCU read-side critical section.
+	<p>
+	Some extreme workloads might intentionally delay
+	RCU grace periods, and systems running those workloads can
+	be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt>
+	to suppress the splats.
+	This kernel parameter may also be set via <tt>sysfs</tt>.
+	Furthermore, RCU CPU stall warnings are counter-productive
+	during sysrq dumps and during panics.
+	RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and
+	<tt>rcu_sysrq_end()</tt> API members to be called before
+	and after long sysrq dumps.
+	RCU also supplies the <tt>rcu_panic()</tt> notifier that is
+	automatically invoked at the beginning of a panic to suppress
+	further RCU CPU stall warnings.
+
+	<p>
+	This requirement made itself known in the early 1990s, pretty
+	much the first time that it was necessary to debug a CPU stall.
+	That said, the initial implementation in DYNIX/ptx was quite
+	generic in comparison with that of Linux.
+<li>	Although it would be very good to detect pointers leaking out
+	of RCU read-side critical sections, there is currently no
+	good way of doing this.
+	One complication is the need to distinguish between pointers
+	leaking and pointers that have been handed off from RCU to
+	some other synchronization mechanism, for example, reference
+	counting.
+<li>	In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related
+	information is provided via both debugfs and event tracing.
+<li>	Open-coded use of <tt>rcu_assign_pointer()</tt> and
+	<tt>rcu_dereference()</tt> to create typical linked
+	data structures can be surprisingly error-prone.
+	Therefore, RCU-protected
+	<a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a>
+	and, more recently, RCU-protected
+	<a href="https://lwn.net/Articles/612100/">hash tables</a>
+	are available.
+	Many other special-purpose RCU-protected data structures are
+	available in the Linux kernel and the userspace RCU library.
+<li>	Some linked structures are created at compile time, but still
+	require <tt>__rcu</tt> checking.
+	The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this
+	purpose.
+<li>	It is not necessary to use <tt>rcu_assign_pointer()</tt>
+	when creating linked structures that are to be published via
+	a single external pointer.
+	The <tt>RCU_INIT_POINTER()</tt> macro is provided for
+	this task and also for assigning <tt>NULL</tt> pointers
+	at runtime.
+</ol>
+
+<p>
+This not a hard-and-fast list:  RCU's diagnostic capabilities will
+continue to be guided by the number and type of usage bugs found
+in real-world RCU usage.
+
+<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2>
+
+<p>
+The Linux kernel provides an interesting environment for all kinds of
+software, including RCU.
+Some of the relevant points of interest are as follows:
+
+<ol>
+<li>	<a href="#Configuration">Configuration</a>.
+<li>	<a href="#Firmware Interface">Firmware Interface</a>.
+<li>	<a href="#Early Boot">Early Boot</a>.
+<li>	<a href="#Interrupts and NMIs">
+	Interrupts and non-maskable interrupts (NMIs)</a>.
+<li>	<a href="#Loadable Modules">Loadable Modules</a>.
+<li>	<a href="#Hotplug CPU">Hotplug CPU</a>.
+<li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
+<li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
+<li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
+<li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
+<li>	<a href="#Performance, Scalability, Response Time, and Reliability">
+	Performance, Scalability, Response Time, and Reliability</a>.
+</ol>
+
+<p>
+This list is probably incomplete, but it does give a feel for the
+most notable Linux-kernel complications.
+Each of the following sections covers one of the above topics.
+
+<h3><a name="Configuration">Configuration</a></h3>
+
+<p>
+RCU's goal is automatic configuration, so that almost nobody
+needs to worry about RCU's <tt>Kconfig</tt> options.
+And for almost all users, RCU does in fact work well
+&ldquo;out of the box.&rdquo;
+
+<p>
+However, there are specialized use cases that are handled by
+kernel boot parameters and <tt>Kconfig</tt> options.
+Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users
+about new <tt>Kconfig</tt> options, which requires almost all of them
+be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option.
+
+<p>
+This all should be quite obvious, but the fact remains that
+Linus Torvalds recently had to
+<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a>
+me of this requirement.
+
+<h3><a name="Firmware Interface">Firmware Interface</a></h3>
+
+<p>
+In many cases, kernel obtains information about the system from the
+firmware, and sometimes things are lost in translation.
+Or the translation is accurate, but the original message is bogus.
+
+<p>
+For example, some systems' firmware overreports the number of CPUs,
+sometimes by a large factor.
+If RCU naively believed the firmware, as it used to do,
+it would create too many per-CPU kthreads.
+Although the resulting system will still run correctly, the extra
+kthreads needlessly consume memory and can cause confusion
+when they show up in <tt>ps</tt> listings.
+
+<p>
+RCU must therefore wait for a given CPU to actually come online before
+it can allow itself to believe that the CPU actually exists.
+The resulting &ldquo;ghost CPUs&rdquo; (which are never going to
+come online) cause a number of
+<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>.
+
+<h3><a name="Early Boot">Early Boot</a></h3>
+
+<p>
+The Linux kernel's boot sequence is an interesting process,
+and RCU is used early, even before <tt>rcu_init()</tt>
+is invoked.
+In fact, a number of RCU's primitives can be used as soon as the
+initial task's <tt>task_struct</tt> is available and the
+boot CPU's per-CPU variables are set up.
+The read-side primitives (<tt>rcu_read_lock()</tt>,
+<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>,
+and <tt>rcu_access_pointer()</tt>) will operate normally very early on,
+as will <tt>rcu_assign_pointer()</tt>.
+
+<p>
+Although <tt>call_rcu()</tt> may be invoked at any
+time during boot, callbacks are not guaranteed to be invoked until after
+the scheduler is fully up and running.
+This delay in callback invocation is due to the fact that RCU does not
+invoke callbacks until it is fully initialized, and this full initialization
+cannot occur until after the scheduler has initialized itself to the
+point where RCU can spawn and run its kthreads.
+In theory, it would be possible to invoke callbacks earlier,
+however, this is not a panacea because there would be severe restrictions
+on what operations those callbacks could invoke.
+
+<p>
+Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
+<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
+(<a href="#Bottom-Half Flavor">discussed below</a>),
+and
+<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
+will all operate normally
+during very early boot, the reason being that there is only one CPU
+and preemption is disabled.
+This means that the call <tt>synchronize_rcu()</tt> (or friends)
+itself is a quiescent
+state and thus a grace period, so the early-boot implementation can
+be a no-op.
+
+<p>
+Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
+continue to operate normally through the remainder of boot, courtesy
+of the fact that preemption is disabled across their RCU read-side
+critical sections and also courtesy of the fact that there is still
+only one CPU.
+However, once the scheduler starts initializing, preemption is enabled.
+There is still only a single CPU, but the fact that preemption is enabled
+means that the no-op implementation of <tt>synchronize_rcu()</tt> no
+longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
+Therefore, as soon as the scheduler starts initializing, the early-boot
+fastpath is disabled.
+This means that <tt>synchronize_rcu()</tt> switches to its runtime
+mode of operation where it posts callbacks, which in turn means that
+any call to <tt>synchronize_rcu()</tt> will block until the corresponding
+callback is invoked.
+Unfortunately, the callback cannot be invoked until RCU's runtime
+grace-period machinery is up and running, which cannot happen until
+the scheduler has initialized itself sufficiently to allow RCU's
+kthreads to be spawned.
+Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
+initialization can result in deadlock.
+
+<p>@@QQ@@
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+<p>@@QQA@@
+In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
+maps directly to <tt>synchronize_sched()</tt>.
+Therefore, <tt>synchronize_rcu()</tt> works normally throughout
+boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
+However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
+so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
+during scheduler initialization.
+<p>@@QQE@@
+
+<p>
+I learned of these boot-time requirements as a result of a series of
+system hangs.
+
+<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3>
+
+<p>
+The Linux kernel has interrupts, and RCU read-side critical sections are
+legal within interrupt handlers and within interrupt-disabled regions
+of code, as are invocations of <tt>call_rcu()</tt>.
+
+<p>
+Some Linux-kernel architectures can enter an interrupt handler from
+non-idle process context, and then just never leave it, instead stealthily
+transitioning back to process context.
+This trick is sometimes used to invoke system calls from inside the kernel.
+These &ldquo;half-interrupts&rdquo; mean that RCU has to be very careful
+about how it counts interrupt nesting levels.
+I learned of this requirement the hard way during a rewrite
+of RCU's dyntick-idle code.
+
+<p>
+The Linux kernel has non-maskable interrupts (NMIs), and
+RCU read-side critical sections are legal within NMI handlers.
+Thankfully, RCU update-side primitives, including
+<tt>call_rcu()</tt>, are prohibited within NMI handlers.
+
+<p>
+The name notwithstanding, some Linux-kernel architectures
+can have nested NMIs, which RCU must handle correctly.
+Andy Lutomirski
+<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a>
+with this requirement;
+he also kindly surprised me with
+<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a>
+that meets this requirement.
+
+<h3><a name="Loadable Modules">Loadable Modules</a></h3>
+
+<p>
+The Linux kernel has loadable modules, and these modules can
+also be unloaded.
+After a given module has been unloaded, any attempt to call
+one of its functions results in a segmentation fault.
+The module-unload functions must therefore cancel any
+delayed calls to loadable-module functions, for example,
+any outstanding <tt>mod_timer()</tt> must be dealt with
+via <tt>del_timer_sync()</tt> or similar.
+
+<p>
+Unfortunately, there is no way to cancel an RCU callback;
+once you invoke <tt>call_rcu()</tt>, the callback function is
+going to eventually be invoked, unless the system goes down first.
+Because it is normally considered socially irresponsible to crash the system
+in response to a module unload request, we need some other way
+to deal with in-flight RCU callbacks.
+
+<p>
+RCU therefore provides
+<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>,
+which waits until all in-flight RCU callbacks have been invoked.
+If a module uses <tt>call_rcu()</tt>, its exit function should therefore
+prevent any future invocation of <tt>call_rcu()</tt>, then invoke
+<tt>rcu_barrier()</tt>.
+In theory, the underlying module-unload code could invoke
+<tt>rcu_barrier()</tt> unconditionally, but in practice this would
+incur unacceptable latencies.
+
+<p>
+Nikita Danilov noted this requirement for an analogous filesystem-unmount
+situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
+The need for <tt>rcu_barrier()</tt> for module unloading became
+apparent later.
+
+<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
+
+<p>
+The Linux kernel supports CPU hotplug, which means that CPUs
+can come and go.
+It is of course illegal to use any RCU API member from an offline CPU.
+This requirement was present from day one in DYNIX/ptx, but
+on the other hand, the Linux kernel's CPU-hotplug implementation
+is &ldquo;interesting.&rdquo;
+
+<p>
+The Linux-kernel CPU-hotplug implementation has notifiers that
+are used to allow the various kernel subsystems (including RCU)
+to respond appropriately to a given CPU-hotplug operation.
+Most RCU operations may be invoked from CPU-hotplug notifiers,
+including even normal synchronous grace-period operations
+such as <tt>synchronize_rcu()</tt>.
+However, expedited grace-period operations such as
+<tt>synchronize_rcu_expedited()</tt> are not supported,
+due to the fact that current implementations block CPU-hotplug
+operations, which could result in deadlock.
+
+<p>
+In addition, all-callback-wait operations such as
+<tt>rcu_barrier()</tt> are also not supported, due to the
+fact that there are phases of CPU-hotplug operations where
+the outgoing CPU's callbacks will not be invoked until after
+the CPU-hotplug operation ends, which could also result in deadlock.
+
+<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
+
+<p>
+RCU depends on the scheduler, and the scheduler uses RCU to
+protect some of its data structures.
+This means the scheduler is forbidden from acquiring
+the runqueue locks and the priority-inheritance locks
+in the middle of an outermost RCU read-side critical section unless either
+(1)&nbsp;it releases them before exiting that same
+RCU read-side critical section, or
+(2)&nbsp;interrupts are disabled across
+that entire RCU read-side critical section.
+This same prohibition also applies (recursively!) to any lock that is acquired
+while holding any lock to which this prohibition applies.
+Adhering to this rule prevents preemptible RCU from invoking
+<tt>rcu_read_unlock_special()</tt> while either runqueue or
+priority-inheritance locks are held, thus avoiding deadlock.
+
+<p>
+Prior to v4.4, it was only necessary to disable preemption across
+RCU read-side critical sections that acquired scheduler locks.
+In v4.4, expedited grace periods started using IPIs, and these
+IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath.
+Therefore, this expedited-grace-period change required disabling of
+interrupts, not just preemption.
+
+<p>
+For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt>
+implementation must be written carefully to avoid similar deadlocks.
+In particular, <tt>rcu_read_unlock()</tt> must tolerate an
+interrupt where the interrupt handler invokes both
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+This possibility requires <tt>rcu_read_unlock()</tt> to use
+negative nesting levels to avoid destructive recursion via
+interrupt handler's use of RCU.
+
+<p>
+This pair of mutual scheduler-RCU requirements came as a
+<a href="https://lwn.net/Articles/453002/">complete surprise</a>.
+
+<p>
+As noted above, RCU makes use of kthreads, and it is necessary to
+avoid excessive CPU-time accumulation by these kthreads.
+This requirement was no surprise, but RCU's violation of it
+when running context-switch-heavy workloads when built with
+<tt>CONFIG_NO_HZ_FULL=y</tt>
+<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>.
+RCU has made good progress towards meeting this requirement, even
+for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads,
+but there is room for further improvement.
+
+<h3><a name="Tracing and RCU">Tracing and RCU</a></h3>
+
+<p>
+It is possible to use tracing on RCU code, but tracing itself
+uses RCU.
+For this reason, <tt>rcu_dereference_raw_notrace()</tt>
+is provided for use by tracing, which avoids the destructive
+recursion that could otherwise ensue.
+This API is also used by virtualization in some architectures,
+where RCU readers execute in environments in which tracing
+cannot be used.
+The tracing folks both located the requirement and provided the
+needed fix, so this surprise requirement was relatively painless.
+
+<h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
+
+<p>
+Interrupting idle CPUs is considered socially unacceptable,
+especially by people with battery-powered embedded systems.
+RCU therefore conserves energy by detecting which CPUs are
+idle, including tracking CPUs that have been interrupted from idle.
+This is a large part of the energy-efficiency requirement,
+so I learned of this via an irate phone call.
+
+<p>
+Because RCU avoids interrupting idle CPUs, it is illegal to
+execute an RCU read-side critical section on an idle CPU.
+(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat
+if you try it.)
+The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt>
+event tracing is provided to work around this restriction.
+In addition, <tt>rcu_is_watching()</tt> may be used to
+test whether or not it is currently legal to run RCU read-side
+critical sections on this CPU.
+I learned of the need for diagnostics on the one hand
+and <tt>RCU_NONIDLE()</tt> on the other while inspecting
+idle-loop code.
+Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
+which is used quite heavily in the idle loop.
+
+<p>
+It is similarly socially unacceptable to interrupt an
+<tt>nohz_full</tt> CPU running in userspace.
+RCU must therefore track <tt>nohz_full</tt> userspace
+execution.
+And in
+<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a>
+kernels, RCU must separately track idle CPUs on the one hand and
+CPUs that are either idle or executing in userspace on the other.
+In both cases, RCU must be able to sample state at two points in
+time, and be able to determine whether or not some other CPU spent
+any time idle and/or executing in userspace.
+
+<p>
+These energy-efficiency requirements have proven quite difficult to
+understand and to meet, for example, there have been more than five
+clean-sheet rewrites of RCU's energy-efficiency code, the last of
+which was finally able to demonstrate
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>.
+As noted earlier,
+I learned of many of these requirements via angry phone calls:
+Flaming me on the Linux-kernel mailing list was apparently not
+sufficient to fully vent their ire at RCU's energy-efficiency bugs!
+
+<h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
+
+<p>
+Although small-memory non-realtime systems can simply use Tiny RCU,
+code size is only one aspect of memory efficiency.
+Another aspect is the size of the <tt>rcu_head</tt> structure
+used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>.
+Although this structure contains nothing more than a pair of pointers,
+it does appear in many RCU-protected data structures, including
+some that are size critical.
+The <tt>page</tt> structure is a case in point, as evidenced by
+the many occurrences of the <tt>union</tt> keyword within that structure.
+
+<p>
+This need for memory efficiency is one reason that RCU uses hand-crafted
+singly linked lists to track the <tt>rcu_head</tt> structures that
+are waiting for a grace period to elapse.
+It is also the reason why <tt>rcu_head</tt> structures do not contain
+debug information, such as fields tracking the file and line of the
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them.
+Although this information might appear in debug-only kernel builds at some
+point, in the meantime, the <tt>-&gt;func</tt> field will often provide
+the needed debug information.
+
+<p>
+However, in some cases, the need for memory efficiency leads to even
+more extreme measures.
+Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field
+shares storage with a great many other structures that are used at
+various points in the corresponding page's lifetime.
+In order to correctly resolve certain
+<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>,
+the Linux kernel's memory-management subsystem needs a particular bit
+to remain zero during all phases of grace-period processing,
+and that bit happens to map to the bottom bit of the
+<tt>rcu_head</tt> structure's <tt>-&gt;next</tt> field.
+RCU makes this guarantee as long as <tt>call_rcu()</tt>
+is used to post the callback, as opposed to <tt>kfree_rcu()</tt>
+or some future &ldquo;lazy&rdquo;
+variant of <tt>call_rcu()</tt> that might one day be created for
+energy-efficiency purposes.
+
+<h3><a name="Performance, Scalability, Response Time, and Reliability">
+Performance, Scalability, Response Time, and Reliability</a></h3>
+
+<p>
+Expanding on the
+<a href="#Performance and Scalability">earlier discussion</a>,
+RCU is used heavily by hot code paths in performance-critical
+portions of the Linux kernel's networking, security, virtualization,
+and scheduling code paths.
+RCU must therefore use efficient implementations, especially in its
+read-side primitives.
+To that end, it would be good if preemptible RCU's implementation
+of <tt>rcu_read_lock()</tt> could be inlined, however, doing
+this requires resolving <tt>#include</tt> issues with the
+<tt>task_struct</tt> structure.
+
+<p>
+The Linux kernel supports hardware configurations with up to
+4096 CPUs, which means that RCU must be extremely scalable.
+Algorithms that involve frequent acquisitions of global locks or
+frequent atomic operations on global variables simply cannot be
+tolerated within the RCU implementation.
+RCU therefore makes heavy use of a combining tree based on the
+<tt>rcu_node</tt> structure.
+RCU is required to tolerate all CPUs continuously invoking any
+combination of RCU's runtime primitives with minimal per-operation
+overhead.
+In fact, in many cases, increasing load must <i>decrease</i> the
+per-operation overhead, witness the batching optimizations for
+<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>,
+<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>.
+As a general rule, RCU must cheerfully accept whatever the
+rest of the Linux kernel decides to throw at it.
+
+<p>
+The Linux kernel is used for real-time workloads, especially
+in conjunction with the
+<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>.
+The real-time-latency response requirements are such that the
+traditional approach of disabling preemption across RCU
+read-side critical sections is inappropriate.
+Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
+use an RCU implementation that allows RCU read-side critical
+sections to be preempted.
+This requirement made its presence known after users made it
+clear that an earlier
+<a href="https://lwn.net/Articles/107930/">real-time patch</a>
+did not meet their needs, in conjunction with some
+<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a>
+encountered by a very early version of the -rt patchset.
+
+<p>
+In addition, RCU must make do with a sub-100-microsecond real-time latency
+budget.
+In fact, on smaller systems with the -rt patchset, the Linux kernel
+provides sub-20-microsecond real-time latencies for the whole kernel,
+including RCU.
+RCU's scalability and latency must therefore be sufficient for
+these sorts of configurations.
+To my surprise, the sub-100-microsecond real-time latency budget
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf">
+applies to even the largest systems [PDF]</a>,
+up to and including systems with 4096 CPUs.
+This real-time requirement motivated the grace-period kthread, which
+also simplified handling of a number of race conditions.
+
+<p>
+Finally, RCU's status as a synchronization primitive means that
+any RCU failure can result in arbitrary memory corruption that can be
+extremely difficult to debug.
+This means that RCU must be extremely reliable, which in
+practice also means that RCU must have an aggressive stress-test
+suite.
+This stress-test suite is called <tt>rcutorture</tt>.
+
+<p>
+Although the need for <tt>rcutorture</tt> was no surprise,
+the current immense popularity of the Linux kernel is posing
+interesting&mdash;and perhaps unprecedented&mdash;validation
+challenges.
+To see this, keep in mind that there are well over one billion
+instances of the Linux kernel running today, given Android
+smartphones, Linux-powered televisions, and servers.
+This number can be expected to increase sharply with the advent of
+the celebrated Internet of Things.
+
+<p>
+Suppose that RCU contains a race condition that manifests on average
+once per million years of runtime.
+This bug will be occurring about three times per <i>day</i> across
+the installed base.
+RCU could simply hide behind hardware error rates, given that no one
+should really expect their smartphone to last for a million years.
+However, anyone taking too much comfort from this thought should
+consider the fact that in most jurisdictions, a successful multi-year
+test of a given mechanism, which might include a Linux kernel,
+suffices for a number of types of safety-critical certifications.
+In fact, rumor has it that the Linux kernel is already being used
+in production for safety-critical applications.
+I don't know about you, but I would feel quite bad if a bug in RCU
+killed someone.
+Which might explain my recent focus on validation and verification.
+
+<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2>
+
+<p>
+One of the more surprising things about RCU is that there are now
+no fewer than five <i>flavors</i>, or API families.
+In addition, the primary flavor that has been the sole focus up to
+this point has two different implementations, non-preemptible and
+preemptible.
+The other four flavors are listed below, with requirements for each
+described in a separate section.
+
+<ol>
+<li>	<a href="#Bottom-Half Flavor">Bottom-Half Flavor</a>
+<li>	<a href="#Sched Flavor">Sched Flavor</a>
+<li>	<a href="#Sleepable RCU">Sleepable RCU</a>
+<li>	<a href="#Tasks RCU">Tasks RCU</a>
+</ol>
+
+<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3>
+
+<p>
+The softirq-disable (AKA &ldquo;bottom-half&rdquo;,
+hence the &ldquo;_bh&rdquo; abbreviations)
+flavor of RCU, or <i>RCU-bh</i>, was developed by
+Dipankar Sarma to provide a flavor of RCU that could withstand the
+network-based denial-of-service attacks researched by Robert
+Olsson.
+These attacks placed so much networking load on the system
+that some of the CPUs never exited softirq execution,
+which in turn prevented those CPUs from ever executing a context switch,
+which, in the RCU implementation of that time, prevented grace periods
+from ever ending.
+The result was an out-of-memory condition and a system hang.
+
+<p>
+The solution was the creation of RCU-bh, which does
+<tt>local_bh_disable()</tt>
+across its read-side critical sections, and which uses the transition
+from one type of softirq processing to another as a quiescent state
+in addition to context switch, idle, user mode, and offline.
+This means that RCU-bh grace periods can complete even when some of
+the CPUs execute in softirq indefinitely, thus allowing algorithms
+based on RCU-bh to withstand network-based denial-of-service attacks.
+
+<p>
+Because
+<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt>
+disable and re-enable softirq handlers, any attempt to start a softirq
+handlers during the
+RCU-bh read-side critical section will be deferred.
+In this case, <tt>rcu_read_unlock_bh()</tt>
+will invoke softirq processing, which can take considerable time.
+One can of course argue that this softirq overhead should be associated
+with the code following the RCU-bh read-side critical section rather
+than <tt>rcu_read_unlock_bh()</tt>, but the fact
+is that most profiling tools cannot be expected to make this sort
+of fine distinction.
+For example, suppose that a three-millisecond-long RCU-bh read-side
+critical section executes during a time of heavy networking load.
+There will very likely be an attempt to invoke at least one softirq
+handler during that three milliseconds, but any such invocation will
+be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>.
+This can of course make it appear at first glance as if
+<tt>rcu_read_unlock_bh()</tt> was executing very slowly.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a>
+includes
+<tt>rcu_read_lock_bh()</tt>,
+<tt>rcu_read_unlock_bh()</tt>,
+<tt>rcu_dereference_bh()</tt>,
+<tt>rcu_dereference_bh_check()</tt>,
+<tt>synchronize_rcu_bh()</tt>,
+<tt>synchronize_rcu_bh_expedited()</tt>,
+<tt>call_rcu_bh()</tt>,
+<tt>rcu_barrier_bh()</tt>, and
+<tt>rcu_read_lock_bh_held()</tt>.
+
+<h3><a name="Sched Flavor">Sched Flavor</a></h3>
+
+<p>
+Before preemptible RCU, waiting for an RCU grace period had the
+side effect of also waiting for all pre-existing interrupt
+and NMI handlers.
+However, there are legitimate preemptible-RCU implementations that
+do not have this property, given that any point in the code outside
+of an RCU read-side critical section can be a quiescent state.
+Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
+RCU in that an RCU-sched grace period waits for for pre-existing
+interrupt and NMI handlers.
+In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
+APIs have identical implementations, while kernels built with
+<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
+
+<p>
+Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+disable and re-enable preemption, respectively.
+This means that if there was a preemption attempt during the
+RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt>
+will enter the scheduler, with all the latency and overhead entailed.
+Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look
+as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly.
+However, the highest-priority task won't be preempted, so that task
+will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a>
+includes
+<tt>rcu_read_lock_sched()</tt>,
+<tt>rcu_read_unlock_sched()</tt>,
+<tt>rcu_read_lock_sched_notrace()</tt>,
+<tt>rcu_read_unlock_sched_notrace()</tt>,
+<tt>rcu_dereference_sched()</tt>,
+<tt>rcu_dereference_sched_check()</tt>,
+<tt>synchronize_sched()</tt>,
+<tt>synchronize_rcu_sched_expedited()</tt>,
+<tt>call_rcu_sched()</tt>,
+<tt>rcu_barrier_sched()</tt>, and
+<tt>rcu_read_lock_sched_held()</tt>.
+However, anything that disables preemption also marks an RCU-sched
+read-side critical section, including
+<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>,
+<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>,
+and so on.
+
+<h3><a name="Sleepable RCU">Sleepable RCU</a></h3>
+
+<p>
+For well over a decade, someone saying &ldquo;I need to block within
+an RCU read-side critical section&rdquo; was a reliable indication
+that this someone did not understand RCU.
+After all, if you are always blocking in an RCU read-side critical
+section, you can probably afford to use a higher-overhead synchronization
+mechanism.
+However, that changed with the advent of the Linux kernel's notifiers,
+whose RCU read-side critical
+sections almost never sleep, but sometimes need to.
+This resulted in the introduction of
+<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>,
+or <i>SRCU</i>.
+
+<p>
+SRCU allows different domains to be defined, with each such domain
+defined by an instance of an <tt>srcu_struct</tt> structure.
+A pointer to this structure must be passed in to each SRCU function,
+for example, <tt>synchronize_srcu(&amp;ss)</tt>, where
+<tt>ss</tt> is the <tt>srcu_struct</tt> structure.
+The key benefit of these domains is that a slow SRCU reader in one
+domain does not delay an SRCU grace period in some other domain.
+That said, one consequence of these domains is that read-side code
+must pass a &ldquo;cookie&rdquo; from <tt>srcu_read_lock()</tt>
+to <tt>srcu_read_unlock()</tt>, for example, as follows:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+As noted above, it is legal to block within SRCU read-side critical sections,
+however, with great power comes great responsibility.
+If you block forever in one of a given domain's SRCU read-side critical
+sections, then that domain's grace periods will also be blocked forever.
+Of course, one good way to block forever is to deadlock, which can
+happen if any operation in a given domain's SRCU read-side critical
+section can block waiting, either directly or indirectly, for that domain's
+grace period to elapse.
+For example, this results in a self-deadlock:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 synchronize_srcu(&amp;ss);
+ 6 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+However, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>,
+deadlock would still be possible.
+Furthermore, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>,
+and if an <tt>ss1</tt>-domain SRCU read-side critical section
+acquired another mutex that was held across as <tt>ss</tt>-domain
+<tt>synchronize_srcu()</tt>,
+deadlock would again be possible.
+Such a deadlock cycle could extend across an arbitrarily large number
+of different SRCU domains.
+Again, with great power comes great responsibility.
+
+<p>
+Unlike the other RCU flavors, SRCU read-side critical sections can
+run on idle and even offline CPUs.
+This ability requires that <tt>srcu_read_lock()</tt> and
+<tt>srcu_read_unlock()</tt> contain memory barriers, which means
+that SRCU readers will run a bit slower than would RCU readers.
+It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
+API, which, in combination with <tt>srcu_read_unlock()</tt>,
+guarantees a full memory barrier.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
+includes
+<tt>srcu_read_lock()</tt>,
+<tt>srcu_read_unlock()</tt>,
+<tt>srcu_dereference()</tt>,
+<tt>srcu_dereference_check()</tt>,
+<tt>synchronize_srcu()</tt>,
+<tt>synchronize_srcu_expedited()</tt>,
+<tt>call_srcu()</tt>,
+<tt>srcu_barrier()</tt>, and
+<tt>srcu_read_lock_held()</tt>.
+It also includes
+<tt>DEFINE_SRCU()</tt>,
+<tt>DEFINE_STATIC_SRCU()</tt>, and
+<tt>init_srcu_struct()</tt>
+APIs for defining and initializing <tt>srcu_struct</tt> structures.
+
+<h3><a name="Tasks RCU">Tasks RCU</a></h3>
+
+<p>
+Some forms of tracing use &ldquo;tramopolines&rdquo; to handle the
+binary rewriting required to install different types of probes.
+It would be good to be able to free old trampolines, which sounds
+like a job for some form of RCU.
+However, because it is necessary to be able to install a trace
+anywhere in the code, it is not possible to use read-side markers
+such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+In addition, it does not work to have these markers in the trampoline
+itself, because there would need to be instructions following
+<tt>rcu_read_unlock()</tt>.
+Although <tt>synchronize_rcu()</tt> would guarantee that execution
+reached the <tt>rcu_read_unlock()</tt>, it would not be able to
+guarantee that execution had completely left the trampoline.
+
+<p>
+The solution, in the form of
+<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>,
+is to have implicit
+read-side critical sections that are delimited by voluntary context
+switches, that is, calls to <tt>schedule()</tt>,
+<tt>cond_resched_rcu_qs()</tt>, and
+<tt>synchronize_rcu_tasks()</tt>.
+In addition, transitions to and from userspace execution also delimit
+tasks-RCU read-side critical sections.
+
+<p>
+The tasks-RCU API is quite compact, consisting only of
+<tt>call_rcu_tasks()</tt>,
+<tt>synchronize_rcu_tasks()</tt>, and
+<tt>rcu_barrier_tasks()</tt>.
+
+<h2><a name="Possible Future Changes">Possible Future Changes</a></h2>
+
+<p>
+One of the tricks that RCU uses to attain update-side scalability is
+to increase grace-period latency with increasing numbers of CPUs.
+If this becomes a serious problem, it will be necessary to rework the
+grace-period state machine so as to avoid the need for the additional
+latency.
+
+<p>
+Expedited grace periods scan the CPUs, so their latency and overhead
+increases with increasing numbers of CPUs.
+If this becomes a serious problem on large systems, it will be necessary
+to do some redesign to avoid this scalability problem.
+
+<p>
+RCU disables CPU hotplug in a few places, perhaps most notably in the
+expedited grace-period and <tt>rcu_barrier()</tt> operations.
+If there is a strong reason to use expedited grace periods in CPU-hotplug
+notifiers, it will be necessary to avoid disabling CPU hotplug.
+This would introduce some complexity, so there had better be a <i>very</i>
+good reason.
+
+<p>
+The tradeoff between grace-period latency on the one hand and interruptions
+of other CPUs on the other hand may need to be re-examined.
+The desire is of course for zero grace-period latency as well as zero
+interprocessor interrupts undertaken during an expedited grace period
+operation.
+While this ideal is unlikely to be achievable, it is quite possible that
+further improvements can be made.
+
+<p>
+The multiprocessor implementations of RCU use a combining tree that
+groups CPUs so as to reduce lock contention and increase cache locality.
+However, this combining tree does not spread its memory across NUMA
+nodes nor does it align the CPU groups with hardware features such
+as sockets or cores.
+Such spreading and alignment is currently believed to be unnecessary
+because the hotpath read-side primitives do not access the combining
+tree, nor does <tt>call_rcu()</tt> in the common case.
+If you believe that your architecture needs such spreading and alignment,
+then your architecture should also benefit from the
+<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set
+to the number of CPUs in a socket, NUMA node, or whatever.
+If the number of CPUs is too large, use a fraction of the number of
+CPUs.
+If the number of CPUs is a large prime number, well, that certainly
+is an &ldquo;interesting&rdquo; architectural choice!
+More flexible arrangements might be considered, but only if
+<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only
+if the inadequacy has been demonstrated by a carefully run and
+realistic system-level workload.
+
+<p>
+Please note that arrangements that require RCU to remap CPU numbers will
+require extremely good demonstration of need and full exploration of
+alternatives.
+
+<p>
+There is an embarrassingly large number of flavors of RCU, and this
+number has been increasing over time.
+Perhaps it will be possible to combine some at some future date.
+
+<p>
+RCU's various kthreads are reasonably recent additions.
+It is quite likely that adjustments will be required to more gracefully
+handle extreme loads.
+It might also be necessary to be able to relate CPU utilization by
+RCU's kthreads and softirq handlers to the code that instigated this
+CPU utilization.
+For example, RCU callback overhead might be charged back to the
+originating <tt>call_rcu()</tt> instance, though probably not
+in production kernels.
+
+<h2><a name="Summary">Summary</a></h2>
+
+<p>
+This document has presented more than two decade's worth of RCU
+requirements.
+Given that the requirements keep changing, this will not be the last
+word on this subject, but at least it serves to get an important
+subset of the requirements set forth.
+
+<h2><a name="Acknowledgments">Acknowledgments</a></h2>
+
+I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar,
+Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and
+Andy Lutomirski for their help in rendering
+this article human readable, and to Michelle Rankin for her support
+of this effort.
+Other contributions are acknowledged in the Linux kernel's git archive.
+The cartoon is copyright (c) 2013 by Melissa Broussard,
+and is provided
+under the terms of the Creative Commons Attribution-Share Alike 3.0
+United States license.
+
+<p>@@QQAL@@
+
+</body></html>
diff --git a/Documentation/RCU/Design/htmlqqz.sh b/Documentation/RCU/Design/htmlqqz.sh
new file mode 100755
index 000000000000..d354f069559b
--- /dev/null
+++ b/Documentation/RCU/Design/htmlqqz.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+#
+# Usage: sh htmlqqz.sh file
+#
+# Extracts and converts quick quizzes in a proto-HTML document file.htmlx.
+# Commands, all of which must be on a line by themselves:
+#
+#	"<p>@@QQ@@": Start of a quick quiz.
+#	"<p>@@QQA@@": Start of a quick-quiz answer.
+#	"<p>@@QQE@@": End of a quick-quiz answer, and thus of the quick quiz.
+#	"<p>@@QQAL@@": Place to put quick-quiz answer list.
+#
+# Places the result in file.html.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (c) 2013 Paul E. McKenney, IBM Corporation.
+
+fn=$1
+if test ! -r $fn.htmlx
+then
+	echo "Error: $fn.htmlx unreadable."
+	exit 1
+fi
+
+echo "<!-- DO NOT HAND EDIT. -->" > $fn.html
+echo "<!-- Instead, edit $fn.htmlx and run 'sh htmlqqz.sh $fn' -->" >> $fn.html
+awk < $fn.htmlx >> $fn.html '
+
+state == "" && $1 != "<p>@@QQ@@" && $1 != "<p>@@QQAL@@" {
+	print $0;
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR " (expected <p>@@QQ@@ or <p>@@QQAL@@)." > "/dev/stderr"
+	next;
+}
+
+state == "" && $1 == "<p>@@QQ@@" {
+	qqn++;
+	qqlineno = NR;
+	haveqq = 1;
+	state = "qq";
+	print "<p><a name=\"Quick Quiz " qqn "\"><b>Quick Quiz " qqn "</b>:</a>"
+	next;
+}
+
+state == "qq" && $1 != "<p>@@QQA@@" {
+	qq[qqn] = qq[qqn] $0 "\n";
+	print $0
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR ". (expected <p>@@QQA@@)" > "/dev/stderr"
+	next;
+}
+
+state == "qq" && $1 == "<p>@@QQA@@" {
+	state = "qqa";
+	print "<br><a href=\"#qq" qqn "answer\">Answer</a>"
+	next;
+}
+
+state == "qqa" && $1 != "<p>@@QQE@@" {
+	qqa[qqn] = qqa[qqn] $0 "\n";
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR " (expected <p>@@QQE@@)." > "/dev/stderr"
+	next;
+}
+
+state == "qqa" && $1 == "<p>@@QQE@@" {
+	state = "";
+	next;
+}
+
+state == "" && $1 == "<p>@@QQAL@@" {
+	haveqq = "";
+	print "<h3><a name=\"Answers to Quick Quizzes\">"
+	print "Answers to Quick Quizzes</a></h3>"
+	print "";
+	for (i = 1; i <= qqn; i++) {
+		print "<a name=\"qq" i "answer\"></a>"
+		print "<p><b>Quick Quiz " i "</b>:"
+		print qq[i];
+		print "";
+		print "</p><p><b>Answer</b>:"
+		print qqa[i];
+		print "";
+		print "</p><p><a href=\"#Quick%20Quiz%20" i "\"><b>Back to Quick Quiz " i "</b>.</a>"
+		print "";
+	}
+	next;
+}
+
+END {
+	if (state != "")
+		print "Unterminated Quick Quiz: " qqlineno "." > "/dev/stderr"
+	else if (haveqq)
+		print "Missing \"<p>@@QQAL@@\", no Quick Quiz." > "/dev/stderr"
+}'
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index f40578026a04..7785fb5eb93f 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -375,7 +375,8 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	if ((nl_sd = create_nl_socket(NETLINK_GENERIC)) < 0)
+	nl_sd = create_nl_socket(NETLINK_GENERIC);
+	if (nl_sd < 0)
 		err(1, "error creating Netlink socket\n");
 
 
diff --git a/Documentation/arm/Marvell/README b/Documentation/arm/Marvell/README
index 18a775d10172..ae89b67d8e23 100644
--- a/Documentation/arm/Marvell/README
+++ b/Documentation/arm/Marvell/README
@@ -233,29 +233,30 @@ MMP/MMP2 family (communication processor)
    Linux kernel mach directory: arch/arm/mach-mmp
    Linux kernel plat directory: arch/arm/plat-pxa
 
-Berlin family (Digital Entertainment)
+Berlin family (Multimedia Solutions)
 -------------------------------------
 
   Flavors:
-	88DE3005, Armada 1500-mini
+	88DE3005, Armada 1500 Mini
 		Design name:	BG2CD
 		Core:		ARM Cortex-A9, PL310 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500-mini/
+		Homepage:	http://www.marvell.com/multimedia-solutions/armada-1500-mini/
+        88DE3006, Armada 1500 Mini Plus
+                Design name:    BG2CDP
+                Core:           Dual Core ARM Cortex-A7
+                Homepage:       http://www.marvell.com/multimedia-solutions/armada-1500-mini-plus/
 	88DE3100, Armada 1500
 		Design name:	BG2
 		Core:		Marvell PJ4B (ARMv7), Tauros3 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500/
-		Product Brief:	http://www.marvell.com/digital-entertainment/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
+		Product Brief:	http://www.marvell.com/multimedia-solutions/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
 	88DE3114, Armada 1500 Pro
-		Design name:	BG2-Q
+		Design name:	BG2Q
 		Core:		Quad Core ARM Cortex-A9, PL310 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500-pro/
-		Product Brief:	http://www.marvell.com/digital-entertainment/armada-1500-pro/assets/Marvell_ARMADA_1500_PRO-01_product_brief.pdf
 	88DE????
 		Design name:	BG3
 		Core:		ARM Cortex-A15, CA15 integrated L2CC
 
-  Homepage: http://www.marvell.com/digital-entertainment/
+  Homepage: http://www.marvell.com/multimedia-solutions/
   Directory: arch/arm/mach-berlin
 
   Comments:
diff --git a/Documentation/arm/pxa/mfp.txt b/Documentation/arm/pxa/mfp.txt
index a179e5bc02c9..0b7cab978c02 100644
--- a/Documentation/arm/pxa/mfp.txt
+++ b/Documentation/arm/pxa/mfp.txt
@@ -49,7 +49,7 @@ to this new MFP mechanism, here are several key points:
      internal controllers like PWM, SSP and UART, with 128 internal signals
      which can be routed to external through one or more MFPs (e.g. GPIO<0>
      can be routed through either MFP_PIN_GPIO0 as well as MFP_PIN_GPIO0_2,
-     see arch/arm/mach-pxa/mach/include/mfp-pxa300.h)
+     see arch/arm/mach-pxa/mfp-pxa300.h)
 
   2. Alternate function configuration is removed from this GPIO controller,
      the remaining functions are pure GPIO-specific, i.e.
@@ -76,11 +76,11 @@ For board code writers, here are some guidelines:
 
 1. include ONE of the following header files in your <board>.c:
 
-   - #include <mach/mfp-pxa25x.h>
-   - #include <mach/mfp-pxa27x.h>
-   - #include <mach/mfp-pxa300.h>
-   - #include <mach/mfp-pxa320.h>
-   - #include <mach/mfp-pxa930.h>
+   - #include "mfp-pxa25x.h"
+   - #include "mfp-pxa27x.h"
+   - #include "mfp-pxa300.h"
+   - #include "mfp-pxa320.h"
+   - #include "mfp-pxa930.h"
 
    NOTE: only one file in your <board>.c, depending on the processors used,
    because pin configuration definitions may conflict in these file (i.e.
@@ -203,20 +203,20 @@ make them effective there-after.
     1. Unified pin definitions - enum constants for all configurable pins
     2. processor-neutral bit definitions for a possible MFP configuration
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa3xx.h
+  - arch/arm/mach-pxa/mfp-pxa3xx.h
 
   for PXA3xx specific MFPR register bit definitions and PXA3xx common pin
   configurations
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa2xx.h
+  - arch/arm/mach-pxa/mfp-pxa2xx.h
 
   for PXA2xx specific definitions and PXA25x/PXA27x common pin configurations
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa25x.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa27x.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa300.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa320.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa930.h
+  - arch/arm/mach-pxa/mfp-pxa25x.h
+    arch/arm/mach-pxa/mfp-pxa27x.h
+    arch/arm/mach-pxa/mfp-pxa300.h
+    arch/arm/mach-pxa/mfp-pxa320.h
+    arch/arm/mach-pxa/mfp-pxa930.h
 
   for processor specific definitions
 
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
new file mode 100644
index 000000000000..58b71ddf9b60
--- /dev/null
+++ b/Documentation/arm64/silicon-errata.txt
@@ -0,0 +1,58 @@
+                Silicon Errata and Software Workarounds
+                =======================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date  : 27 November 2015
+
+It is an unfortunate fact of life that hardware is often produced with
+so-called "errata", which can cause it to deviate from the architecture
+under specific circumstances.  For hardware produced by ARM, these
+errata are broadly classified into the following categories:
+
+  Category A: A critical error without a viable workaround.
+  Category B: A significant or critical error with an acceptable
+              workaround.
+  Category C: A minor error that is not expected to occur under normal
+              operation.
+
+For more information, consult one of the "Software Developers Errata
+Notice" documents available on infocenter.arm.com (registration
+required).
+
+As far as Linux is concerned, Category B errata may require some special
+treatment in the operating system. For example, avoiding a particular
+sequence of code, or configuring the processor in a particular way. A
+less common situation may require similar actions in order to declassify
+a Category A erratum into a Category C erratum. These are collectively
+known as "software workarounds" and are only required in the minority of
+cases (e.g. those cases that both require a non-secure workaround *and*
+can be triggered by Linux).
+
+For software workarounds that may adversely impact systems unaffected by
+the erratum in question, a Kconfig entry is added under "Kernel
+Features" -> "ARM errata workarounds via the alternatives framework".
+These are enabled by default and patched in at runtime when an affected
+CPU is detected. For less-intrusive workarounds, a Kconfig option is not
+available and the code is structured (preferably with a comment) in such
+a way that the erratum will not be hit.
+
+This approach can make it slightly onerous to determine exactly which
+errata are worked around in an arbitrary kernel source tree, so this
+file acts as a registry of software workarounds in the Linux Kernel and
+will be updated when new workarounds are committed and backported to
+stable kernels.
+
+| Implementor    | Component       | Erratum ID      | Kconfig                 |
++----------------+-----------------+-----------------+-------------------------+
+| ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319    |
+| ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319    |
+| ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069    |
+| ARM            | Cortex-A53      | #819472         | ARM64_ERRATUM_819472    |
+| ARM            | Cortex-A53      | #845719         | ARM64_ERRATUM_845719    |
+| ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419    |
+| ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
+| ARM            | Cortex-A57      | #852523         | N/A                     |
+| ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
+|                |                 |                 |                         |
+| Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index f3bc72945cbd..1e4f835a659d 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -81,14 +81,13 @@ on higher end storage.
 
 Default value for this parameter is 8ms.
 
-latency
--------
-This parameter is used to enable/disable the latency mode of the CFQ
-scheduler. If latency mode (called low_latency) is enabled, CFQ tries
-to recompute the slice time for each process based on the target_latency set
-for the system. This favors fairness over throughput. Disabling low
-latency (setting it to 0) ignores target latency, allowing each process in the
-system to get a full time slice.
+low_latency
+-----------
+This parameter is used to enable/disable the low latency mode of the CFQ
+scheduler. If enabled, CFQ tries to recompute the slice time for each process
+based on the target_latency set for the system. This favors fairness over
+throughput. Disabling low latency (setting it to 0) ignores target latency,
+allowing each process in the system to get a full time slice.
 
 By default low latency mode is enabled.
 
diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroup-v1/00-INDEX
index 3f5a40f57d4a..6ad425f7cf56 100644
--- a/Documentation/cgroups/00-INDEX
+++ b/Documentation/cgroup-v1/00-INDEX
@@ -24,7 +24,5 @@ net_prio.txt
 	- Network priority cgroups details and usages.
 pids.txt
 	- Process number cgroups details and usages.
-resource_counter.txt
-	- Resource Counter API.
 unified-hierarchy.txt
 	- Description the new/next cgroup interface.
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroup-v1/blkio-controller.txt
index 52fa9f353342..673dc34d3f78 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroup-v1/blkio-controller.txt
@@ -84,8 +84,7 @@ Throttling/Upper Limit policy
 
 - Run dd to read a file and see if rate is throttled to 1MB/s or not.
 
-		# dd if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
-		# iflag=direct
+        # dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
         1024+0 records in
         1024+0 records out
         4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
@@ -374,82 +373,3 @@ One can experience an overall throughput drop if you have created multiple
 groups and put applications in that group which are not driving enough
 IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
 on individual groups and throughput should improve.
-
-Writeback
-=========
-
-Page cache is dirtied through buffered writes and shared mmaps and
-written asynchronously to the backing filesystem by the writeback
-mechanism.  Writeback sits between the memory and IO domains and
-regulates the proportion of dirty memory by balancing dirtying and
-write IOs.
-
-On traditional cgroup hierarchies, relationships between different
-controllers cannot be established making it impossible for writeback
-to operate accounting for cgroup resource restrictions and all
-writeback IOs are attributed to the root cgroup.
-
-If both the blkio and memory controllers are used on the v2 hierarchy
-and the filesystem supports cgroup writeback, writeback operations
-correctly follow the resource restrictions imposed by both memory and
-blkio controllers.
-
-Writeback examines both system-wide and per-cgroup dirty memory status
-and enforces the more restrictive of the two.  Also, writeback control
-parameters which are absolute values - vm.dirty_bytes and
-vm.dirty_background_bytes - are distributed across cgroups according
-to their current writeback bandwidth.
-
-There's a peculiarity stemming from the discrepancy in ownership
-granularity between memory controller and writeback.  While memory
-controller tracks ownership per page, writeback operates on inode
-basis.  cgroup writeback bridges the gap by tracking ownership by
-inode but migrating ownership if too many foreign pages, pages which
-don't match the current inode ownership, have been encountered while
-writing back the inode.
-
-This is a conscious design choice as writeback operations are
-inherently tied to inodes making strictly following page ownership
-complicated and inefficient.  The only use case which suffers from
-this compromise is multiple cgroups concurrently dirtying disjoint
-regions of the same inode, which is an unlikely use case and decided
-to be unsupported.  Note that as memory controller assigns page
-ownership on the first use and doesn't update it until the page is
-released, even if cgroup writeback strictly follows page ownership,
-multiple cgroups dirtying overlapping areas wouldn't work as expected.
-In general, write-sharing an inode across multiple cgroups is not well
-supported.
-
-Filesystem support for cgroup writeback
----------------------------------------
-
-A filesystem can make writeback IOs cgroup-aware by updating
-address_space_operations->writepage[s]() to annotate bio's using the
-following two functions.
-
-* wbc_init_bio(@wbc, @bio)
-
-  Should be called for each bio carrying writeback data and associates
-  the bio with the inode's owner cgroup.  Can be called anytime
-  between bio allocation and submission.
-
-* wbc_account_io(@wbc, @page, @bytes)
-
-  Should be called for each data segment being written out.  While
-  this function doesn't care exactly when it's called during the
-  writeback session, it's the easiest and most natural to call it as
-  data segments are added to a bio.
-
-With writeback bio's annotated, cgroup support can be enabled per
-super_block by setting MS_CGROUPWB in ->s_flags.  This allows for
-selective disabling of cgroup writeback support which is helpful when
-certain filesystem features, e.g. journaled data mode, are
-incompatible.
-
-wbc_init_bio() binds the specified bio to its cgroup.  Depending on
-the configuration, the bio may be executed at a lower priority and if
-the writeback session is holding shared resources, e.g. a journal
-entry, may lead to priority inversion.  There is no one easy solution
-for the problem.  Filesystems can try to work around specific problem
-cases by skipping wbc_init_bio() or using bio_associate_blkcg()
-directly.
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroup-v1/cgroups.txt
index c6256ae9885b..c6256ae9885b 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroup-v1/cgroups.txt
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroup-v1/cpuacct.txt
index 9d73cc0cadb9..9d73cc0cadb9 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroup-v1/cpuacct.txt
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroup-v1/cpusets.txt
index fdf7dff3f607..fdf7dff3f607 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroup-v1/cpusets.txt
diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroup-v1/devices.txt
index 3c1095ca02ea..3c1095ca02ea 100644
--- a/Documentation/cgroups/devices.txt
+++ b/Documentation/cgroup-v1/devices.txt
diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroup-v1/freezer-subsystem.txt
index e831cb2b8394..e831cb2b8394 100644
--- a/Documentation/cgroups/freezer-subsystem.txt
+++ b/Documentation/cgroup-v1/freezer-subsystem.txt
diff --git a/Documentation/cgroups/hugetlb.txt b/Documentation/cgroup-v1/hugetlb.txt
index 106245c3aecc..106245c3aecc 100644
--- a/Documentation/cgroups/hugetlb.txt
+++ b/Documentation/cgroup-v1/hugetlb.txt
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt
index 8870b0212150..8870b0212150 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroup-v1/memcg_test.txt
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroup-v1/memory.txt
index ff71e16cc752..ff71e16cc752 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroup-v1/memory.txt
diff --git a/Documentation/cgroups/net_cls.txt b/Documentation/cgroup-v1/net_cls.txt
index ec182346dea2..ec182346dea2 100644
--- a/Documentation/cgroups/net_cls.txt
+++ b/Documentation/cgroup-v1/net_cls.txt
diff --git a/Documentation/cgroups/net_prio.txt b/Documentation/cgroup-v1/net_prio.txt
index a82cbd28ea8a..a82cbd28ea8a 100644
--- a/Documentation/cgroups/net_prio.txt
+++ b/Documentation/cgroup-v1/net_prio.txt
diff --git a/Documentation/cgroups/pids.txt b/Documentation/cgroup-v1/pids.txt
index 1a078b5d281a..1a078b5d281a 100644
--- a/Documentation/cgroups/pids.txt
+++ b/Documentation/cgroup-v1/pids.txt
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
new file mode 100644
index 000000000000..ff49cf901148
--- /dev/null
+++ b/Documentation/cgroup-v2.txt
@@ -0,0 +1,1386 @@
+
+Control Group v2
+
+October, 2015		Tejun Heo <tj@kernel.org>
+
+This is the authoritative documentation on the design, interface and
+conventions of cgroup v2.  It describes all userland-visible aspects
+of cgroup including core and specific controller behaviors.  All
+future changes must be reflected in this document.  Documentation for
+v1 is available under Documentation/cgroup-v1/.
+
+CONTENTS
+
+1. Introduction
+  1-1. Terminology
+  1-2. What is cgroup?
+2. Basic Operations
+  2-1. Mounting
+  2-2. Organizing Processes
+  2-3. [Un]populated Notification
+  2-4. Controlling Controllers
+    2-4-1. Enabling and Disabling
+    2-4-2. Top-down Constraint
+    2-4-3. No Internal Process Constraint
+  2-5. Delegation
+    2-5-1. Model of Delegation
+    2-5-2. Delegation Containment
+  2-6. Guidelines
+    2-6-1. Organize Once and Control
+    2-6-2. Avoid Name Collisions
+3. Resource Distribution Models
+  3-1. Weights
+  3-2. Limits
+  3-3. Protections
+  3-4. Allocations
+4. Interface Files
+  4-1. Format
+  4-2. Conventions
+  4-3. Core Interface Files
+5. Controllers
+  5-1. CPU
+    5-1-1. CPU Interface Files
+  5-2. Memory
+    5-2-1. Memory Interface Files
+    5-2-2. Usage Guidelines
+    5-2-3. Memory Ownership
+  5-3. IO
+    5-3-1. IO Interface Files
+    5-3-2. Writeback
+P. Information on Kernel Programming
+  P-1. Filesystem Support for Writeback
+D. Deprecated v1 Core Features
+R. Issues with v1 and Rationales for v2
+  R-1. Multiple Hierarchies
+  R-2. Thread Granularity
+  R-3. Competition Between Inner Nodes and Threads
+  R-4. Other Interface Issues
+  R-5. Controller Issues and Remedies
+    R-5-1. Memory
+
+
+1. Introduction
+
+1-1. Terminology
+
+"cgroup" stands for "control group" and is never capitalized.  The
+singular form is used to designate the whole feature and also as a
+qualifier as in "cgroup controllers".  When explicitly referring to
+multiple individual control groups, the plural form "cgroups" is used.
+
+
+1-2. What is cgroup?
+
+cgroup is a mechanism to organize processes hierarchically and
+distribute system resources along the hierarchy in a controlled and
+configurable manner.
+
+cgroup is largely composed of two parts - the core and controllers.
+cgroup core is primarily responsible for hierarchically organizing
+processes.  A cgroup controller is usually responsible for
+distributing a specific type of system resource along the hierarchy
+although there are utility controllers which serve purposes other than
+resource distribution.
+
+cgroups form a tree structure and every process in the system belongs
+to one and only one cgroup.  All threads of a process belong to the
+same cgroup.  On creation, all processes are put in the cgroup that
+the parent process belongs to at the time.  A process can be migrated
+to another cgroup.  Migration of a process doesn't affect already
+existing descendant processes.
+
+Following certain structural constraints, controllers may be enabled or
+disabled selectively on a cgroup.  All controller behaviors are
+hierarchical - if a controller is enabled on a cgroup, it affects all
+processes which belong to the cgroups consisting the inclusive
+sub-hierarchy of the cgroup.  When a controller is enabled on a nested
+cgroup, it always restricts the resource distribution further.  The
+restrictions set closer to the root in the hierarchy can not be
+overridden from further away.
+
+
+2. Basic Operations
+
+2-1. Mounting
+
+Unlike v1, cgroup v2 has only single hierarchy.  The cgroup v2
+hierarchy can be mounted with the following mount command.
+
+  # mount -t cgroup2 none $MOUNT_POINT
+
+cgroup2 filesystem has the magic number 0x63677270 ("cgrp").  All
+controllers which support v2 and are not bound to a v1 hierarchy are
+automatically bound to the v2 hierarchy and show up at the root.
+Controllers which are not in active use in the v2 hierarchy can be
+bound to other hierarchies.  This allows mixing v2 hierarchy with the
+legacy v1 multiple hierarchies in a fully backward compatible way.
+
+A controller can be moved across hierarchies only after the controller
+is no longer referenced in its current hierarchy.  Because per-cgroup
+controller states are destroyed asynchronously and controllers may
+have lingering references, a controller may not show up immediately on
+the v2 hierarchy after the final umount of the previous hierarchy.
+Similarly, a controller should be fully disabled to be moved out of
+the unified hierarchy and it may take some time for the disabled
+controller to become available for other hierarchies; furthermore, due
+to inter-controller dependencies, other controllers may need to be
+disabled too.
+
+While useful for development and manual configurations, moving
+controllers dynamically between the v2 and other hierarchies is
+strongly discouraged for production use.  It is recommended to decide
+the hierarchies and controller associations before starting using the
+controllers after system boot.
+
+
+2-2. Organizing Processes
+
+Initially, only the root cgroup exists to which all processes belong.
+A child cgroup can be created by creating a sub-directory.
+
+  # mkdir $CGROUP_NAME
+
+A given cgroup may have multiple child cgroups forming a tree
+structure.  Each cgroup has a read-writable interface file
+"cgroup.procs".  When read, it lists the PIDs of all processes which
+belong to the cgroup one-per-line.  The PIDs are not ordered and the
+same PID may show up more than once if the process got moved to
+another cgroup and then back or the PID got recycled while reading.
+
+A process can be migrated into a cgroup by writing its PID to the
+target cgroup's "cgroup.procs" file.  Only one process can be migrated
+on a single write(2) call.  If a process is composed of multiple
+threads, writing the PID of any thread migrates all threads of the
+process.
+
+When a process forks a child process, the new process is born into the
+cgroup that the forking process belongs to at the time of the
+operation.  After exit, a process stays associated with the cgroup
+that it belonged to at the time of exit until it's reaped; however, a
+zombie process does not appear in "cgroup.procs" and thus can't be
+moved to another cgroup.
+
+A cgroup which doesn't have any children or live processes can be
+destroyed by removing the directory.  Note that a cgroup which doesn't
+have any children and is associated only with zombie processes is
+considered empty and can be removed.
+
+  # rmdir $CGROUP_NAME
+
+"/proc/$PID/cgroup" lists a process's cgroup membership.  If legacy
+cgroup is in use in the system, this file may contain multiple lines,
+one for each hierarchy.  The entry for cgroup v2 is always in the
+format "0::$PATH".
+
+  # cat /proc/842/cgroup
+  ...
+  0::/test-cgroup/test-cgroup-nested
+
+If the process becomes a zombie and the cgroup it was associated with
+is removed subsequently, " (deleted)" is appended to the path.
+
+  # cat /proc/842/cgroup
+  ...
+  0::/test-cgroup/test-cgroup-nested (deleted)
+
+
+2-3. [Un]populated Notification
+
+Each non-root cgroup has a "cgroup.events" file which contains
+"populated" field indicating whether the cgroup's sub-hierarchy has
+live processes in it.  Its value is 0 if there is no live process in
+the cgroup and its descendants; otherwise, 1.  poll and [id]notify
+events are triggered when the value changes.  This can be used, for
+example, to start a clean-up operation after all processes of a given
+sub-hierarchy have exited.  The populated state updates and
+notifications are recursive.  Consider the following sub-hierarchy
+where the numbers in the parentheses represent the numbers of processes
+in each cgroup.
+
+  A(4) - B(0) - C(1)
+              \ D(0)
+
+A, B and C's "populated" fields would be 1 while D's 0.  After the one
+process in C exits, B and C's "populated" fields would flip to "0" and
+file modified events will be generated on the "cgroup.events" files of
+both cgroups.
+
+
+2-4. Controlling Controllers
+
+2-4-1. Enabling and Disabling
+
+Each cgroup has a "cgroup.controllers" file which lists all
+controllers available for the cgroup to enable.
+
+  # cat cgroup.controllers
+  cpu io memory
+
+No controller is enabled by default.  Controllers can be enabled and
+disabled by writing to the "cgroup.subtree_control" file.
+
+  # echo "+cpu +memory -io" > cgroup.subtree_control
+
+Only controllers which are listed in "cgroup.controllers" can be
+enabled.  When multiple operations are specified as above, either they
+all succeed or fail.  If multiple operations on the same controller
+are specified, the last one is effective.
+
+Enabling a controller in a cgroup indicates that the distribution of
+the target resource across its immediate children will be controlled.
+Consider the following sub-hierarchy.  The enabled controllers are
+listed in parentheses.
+
+  A(cpu,memory) - B(memory) - C()
+                            \ D()
+
+As A has "cpu" and "memory" enabled, A will control the distribution
+of CPU cycles and memory to its children, in this case, B.  As B has
+"memory" enabled but not "CPU", C and D will compete freely on CPU
+cycles but their division of memory available to B will be controlled.
+
+As a controller regulates the distribution of the target resource to
+the cgroup's children, enabling it creates the controller's interface
+files in the child cgroups.  In the above example, enabling "cpu" on B
+would create the "cpu." prefixed controller interface files in C and
+D.  Likewise, disabling "memory" from B would remove the "memory."
+prefixed controller interface files from C and D.  This means that the
+controller interface files - anything which doesn't start with
+"cgroup." are owned by the parent rather than the cgroup itself.
+
+
+2-4-2. Top-down Constraint
+
+Resources are distributed top-down and a cgroup can further distribute
+a resource only if the resource has been distributed to it from the
+parent.  This means that all non-root "cgroup.subtree_control" files
+can only contain controllers which are enabled in the parent's
+"cgroup.subtree_control" file.  A controller can be enabled only if
+the parent has the controller enabled and a controller can't be
+disabled if one or more children have it enabled.
+
+
+2-4-3. No Internal Process Constraint
+
+Non-root cgroups can only distribute resources to their children when
+they don't have any processes of their own.  In other words, only
+cgroups which don't contain any processes can have controllers enabled
+in their "cgroup.subtree_control" files.
+
+This guarantees that, when a controller is looking at the part of the
+hierarchy which has it enabled, processes are always only on the
+leaves.  This rules out situations where child cgroups compete against
+internal processes of the parent.
+
+The root cgroup is exempt from this restriction.  Root contains
+processes and anonymous resource consumption which can't be associated
+with any other cgroups and requires special treatment from most
+controllers.  How resource consumption in the root cgroup is governed
+is up to each controller.
+
+Note that the restriction doesn't get in the way if there is no
+enabled controller in the cgroup's "cgroup.subtree_control".  This is
+important as otherwise it wouldn't be possible to create children of a
+populated cgroup.  To control resource distribution of a cgroup, the
+cgroup must create children and transfer all its processes to the
+children before enabling controllers in its "cgroup.subtree_control"
+file.
+
+
+2-5. Delegation
+
+2-5-1. Model of Delegation
+
+A cgroup can be delegated to a less privileged user by granting write
+access of the directory and its "cgroup.procs" file to the user.  Note
+that resource control interface files in a given directory control the
+distribution of the parent's resources and thus must not be delegated
+along with the directory.
+
+Once delegated, the user can build sub-hierarchy under the directory,
+organize processes as it sees fit and further distribute the resources
+it received from the parent.  The limits and other settings of all
+resource controllers are hierarchical and regardless of what happens
+in the delegated sub-hierarchy, nothing can escape the resource
+restrictions imposed by the parent.
+
+Currently, cgroup doesn't impose any restrictions on the number of
+cgroups in or nesting depth of a delegated sub-hierarchy; however,
+this may be limited explicitly in the future.
+
+
+2-5-2. Delegation Containment
+
+A delegated sub-hierarchy is contained in the sense that processes
+can't be moved into or out of the sub-hierarchy by the delegatee.  For
+a process with a non-root euid to migrate a target process into a
+cgroup by writing its PID to the "cgroup.procs" file, the following
+conditions must be met.
+
+- The writer's euid must match either uid or suid of the target process.
+
+- The writer must have write access to the "cgroup.procs" file.
+
+- The writer must have write access to the "cgroup.procs" file of the
+  common ancestor of the source and destination cgroups.
+
+The above three constraints ensure that while a delegatee may migrate
+processes around freely in the delegated sub-hierarchy it can't pull
+in from or push out to outside the sub-hierarchy.
+
+For an example, let's assume cgroups C0 and C1 have been delegated to
+user U0 who created C00, C01 under C0 and C10 under C1 as follows and
+all processes under C0 and C1 belong to U0.
+
+  ~~~~~~~~~~~~~ - C0 - C00
+  ~ cgroup    ~      \ C01
+  ~ hierarchy ~
+  ~~~~~~~~~~~~~ - C1 - C10
+
+Let's also say U0 wants to write the PID of a process which is
+currently in C10 into "C00/cgroup.procs".  U0 has write access to the
+file and uid match on the process; however, the common ancestor of the
+source cgroup C10 and the destination cgroup C00 is above the points
+of delegation and U0 would not have write access to its "cgroup.procs"
+files and thus the write will be denied with -EACCES.
+
+
+2-6. Guidelines
+
+2-6-1. Organize Once and Control
+
+Migrating a process across cgroups is a relatively expensive operation
+and stateful resources such as memory are not moved together with the
+process.  This is an explicit design decision as there often exist
+inherent trade-offs between migration and various hot paths in terms
+of synchronization cost.
+
+As such, migrating processes across cgroups frequently as a means to
+apply different resource restrictions is discouraged.  A workload
+should be assigned to a cgroup according to the system's logical and
+resource structure once on start-up.  Dynamic adjustments to resource
+distribution can be made by changing controller configuration through
+the interface files.
+
+
+2-6-2. Avoid Name Collisions
+
+Interface files for a cgroup and its children cgroups occupy the same
+directory and it is possible to create children cgroups which collide
+with interface files.
+
+All cgroup core interface files are prefixed with "cgroup." and each
+controller's interface files are prefixed with the controller name and
+a dot.  A controller's name is composed of lower case alphabets and
+'_'s but never begins with an '_' so it can be used as the prefix
+character for collision avoidance.  Also, interface file names won't
+start or end with terms which are often used in categorizing workloads
+such as job, service, slice, unit or workload.
+
+cgroup doesn't do anything to prevent name collisions and it's the
+user's responsibility to avoid them.
+
+
+3. Resource Distribution Models
+
+cgroup controllers implement several resource distribution schemes
+depending on the resource type and expected use cases.  This section
+describes major schemes in use along with their expected behaviors.
+
+
+3-1. Weights
+
+A parent's resource is distributed by adding up the weights of all
+active children and giving each the fraction matching the ratio of its
+weight against the sum.  As only children which can make use of the
+resource at the moment participate in the distribution, this is
+work-conserving.  Due to the dynamic nature, this model is usually
+used for stateless resources.
+
+All weights are in the range [1, 10000] with the default at 100.  This
+allows symmetric multiplicative biases in both directions at fine
+enough granularity while staying in the intuitive range.
+
+As long as the weight is in range, all configuration combinations are
+valid and there is no reason to reject configuration changes or
+process migrations.
+
+"cpu.weight" proportionally distributes CPU cycles to active children
+and is an example of this type.
+
+
+3-2. Limits
+
+A child can only consume upto the configured amount of the resource.
+Limits can be over-committed - the sum of the limits of children can
+exceed the amount of resource available to the parent.
+
+Limits are in the range [0, max] and defaults to "max", which is noop.
+
+As limits can be over-committed, all configuration combinations are
+valid and there is no reason to reject configuration changes or
+process migrations.
+
+"io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
+on an IO device and is an example of this type.
+
+
+3-3. Protections
+
+A cgroup is protected to be allocated upto the configured amount of
+the resource if the usages of all its ancestors are under their
+protected levels.  Protections can be hard guarantees or best effort
+soft boundaries.  Protections can also be over-committed in which case
+only upto the amount available to the parent is protected among
+children.
+
+Protections are in the range [0, max] and defaults to 0, which is
+noop.
+
+As protections can be over-committed, all configuration combinations
+are valid and there is no reason to reject configuration changes or
+process migrations.
+
+"memory.low" implements best-effort memory protection and is an
+example of this type.
+
+
+3-4. Allocations
+
+A cgroup is exclusively allocated a certain amount of a finite
+resource.  Allocations can't be over-committed - the sum of the
+allocations of children can not exceed the amount of resource
+available to the parent.
+
+Allocations are in the range [0, max] and defaults to 0, which is no
+resource.
+
+As allocations can't be over-committed, some configuration
+combinations are invalid and should be rejected.  Also, if the
+resource is mandatory for execution of processes, process migrations
+may be rejected.
+
+"cpu.rt.max" hard-allocates realtime slices and is an example of this
+type.
+
+
+4. Interface Files
+
+4-1. Format
+
+All interface files should be in one of the following formats whenever
+possible.
+
+  New-line separated values
+  (when only one value can be written at once)
+
+	VAL0\n
+	VAL1\n
+	...
+
+  Space separated values
+  (when read-only or multiple values can be written at once)
+
+	VAL0 VAL1 ...\n
+
+  Flat keyed
+
+	KEY0 VAL0\n
+	KEY1 VAL1\n
+	...
+
+  Nested keyed
+
+	KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
+	KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
+	...
+
+For a writable file, the format for writing should generally match
+reading; however, controllers may allow omitting later fields or
+implement restricted shortcuts for most common use cases.
+
+For both flat and nested keyed files, only the values for a single key
+can be written at a time.  For nested keyed files, the sub key pairs
+may be specified in any order and not all pairs have to be specified.
+
+
+4-2. Conventions
+
+- Settings for a single feature should be contained in a single file.
+
+- The root cgroup should be exempt from resource control and thus
+  shouldn't have resource control interface files.  Also,
+  informational files on the root cgroup which end up showing global
+  information available elsewhere shouldn't exist.
+
+- If a controller implements weight based resource distribution, its
+  interface file should be named "weight" and have the range [1,
+  10000] with 100 as the default.  The values are chosen to allow
+  enough and symmetric bias in both directions while keeping it
+  intuitive (the default is 100%).
+
+- If a controller implements an absolute resource guarantee and/or
+  limit, the interface files should be named "min" and "max"
+  respectively.  If a controller implements best effort resource
+  guarantee and/or limit, the interface files should be named "low"
+  and "high" respectively.
+
+  In the above four control files, the special token "max" should be
+  used to represent upward infinity for both reading and writing.
+
+- If a setting has a configurable default value and keyed specific
+  overrides, the default entry should be keyed with "default" and
+  appear as the first entry in the file.
+
+  The default value can be updated by writing either "default $VAL" or
+  "$VAL".
+
+  When writing to update a specific override, "default" can be used as
+  the value to indicate removal of the override.  Override entries
+  with "default" as the value must not appear when read.
+
+  For example, a setting which is keyed by major:minor device numbers
+  with integer values may look like the following.
+
+    # cat cgroup-example-interface-file
+    default 150
+    8:0 300
+
+  The default value can be updated by
+
+    # echo 125 > cgroup-example-interface-file
+
+  or
+
+    # echo "default 125" > cgroup-example-interface-file
+
+  An override can be set by
+
+    # echo "8:16 170" > cgroup-example-interface-file
+
+  and cleared by
+
+    # echo "8:0 default" > cgroup-example-interface-file
+    # cat cgroup-example-interface-file
+    default 125
+    8:16 170
+
+- For events which are not very high frequency, an interface file
+  "events" should be created which lists event key value pairs.
+  Whenever a notifiable event happens, file modified event should be
+  generated on the file.
+
+
+4-3. Core Interface Files
+
+All cgroup core files are prefixed with "cgroup."
+
+  cgroup.procs
+
+	A read-write new-line separated values file which exists on
+	all cgroups.
+
+	When read, it lists the PIDs of all processes which belong to
+	the cgroup one-per-line.  The PIDs are not ordered and the
+	same PID may show up more than once if the process got moved
+	to another cgroup and then back or the PID got recycled while
+	reading.
+
+	A PID can be written to migrate the process associated with
+	the PID to the cgroup.  The writer should match all of the
+	following conditions.
+
+	- Its euid is either root or must match either uid or suid of
+          the target process.
+
+	- It must have write access to the "cgroup.procs" file.
+
+	- It must have write access to the "cgroup.procs" file of the
+	  common ancestor of the source and destination cgroups.
+
+	When delegating a sub-hierarchy, write access to this file
+	should be granted along with the containing directory.
+
+  cgroup.controllers
+
+	A read-only space separated values file which exists on all
+	cgroups.
+
+	It shows space separated list of all controllers available to
+	the cgroup.  The controllers are not ordered.
+
+  cgroup.subtree_control
+
+	A read-write space separated values file which exists on all
+	cgroups.  Starts out empty.
+
+	When read, it shows space separated list of the controllers
+	which are enabled to control resource distribution from the
+	cgroup to its children.
+
+	Space separated list of controllers prefixed with '+' or '-'
+	can be written to enable or disable controllers.  A controller
+	name prefixed with '+' enables the controller and '-'
+	disables.  If a controller appears more than once on the list,
+	the last one is effective.  When multiple enable and disable
+	operations are specified, either all succeed or all fail.
+
+  cgroup.events
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  populated
+
+		1 if the cgroup or its descendants contains any live
+		processes; otherwise, 0.
+
+
+5. Controllers
+
+5-1. CPU
+
+[NOTE: The interface for the cpu controller hasn't been merged yet]
+
+The "cpu" controllers regulates distribution of CPU cycles.  This
+controller implements weight and absolute bandwidth limit models for
+normal scheduling policy and absolute bandwidth allocation model for
+realtime scheduling policy.
+
+
+5-1-1. CPU Interface Files
+
+All time durations are in microseconds.
+
+  cpu.stat
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+
+	It reports the following six stats.
+
+	  usage_usec
+	  user_usec
+	  system_usec
+	  nr_periods
+	  nr_throttled
+	  throttled_usec
+
+  cpu.weight
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "100".
+
+	The weight in the range [1, 10000].
+
+  cpu.max
+
+	A read-write two value file which exists on non-root cgroups.
+	The default is "max 100000".
+
+	The maximum bandwidth limit.  It's in the following format.
+
+	  $MAX $PERIOD
+
+	which indicates that the group may consume upto $MAX in each
+	$PERIOD duration.  "max" for $MAX indicates no limit.  If only
+	one number is written, $MAX is updated.
+
+  cpu.rt.max
+
+  [NOTE: The semantics of this file is still under discussion and the
+   interface hasn't been merged yet]
+
+	A read-write two value file which exists on all cgroups.
+	The default is "0 100000".
+
+	The maximum realtime runtime allocation.  Over-committing
+	configurations are disallowed and process migrations are
+	rejected if not enough bandwidth is available.  It's in the
+	following format.
+
+	  $MAX $PERIOD
+
+	which indicates that the group may consume upto $MAX in each
+	$PERIOD duration.  If only one number is written, $MAX is
+	updated.
+
+
+5-2. Memory
+
+The "memory" controller regulates distribution of memory.  Memory is
+stateful and implements both limit and protection models.  Due to the
+intertwining between memory usage and reclaim pressure and the
+stateful nature of memory, the distribution model is relatively
+complex.
+
+While not completely water-tight, all major memory usages by a given
+cgroup are tracked so that the total memory consumption can be
+accounted and controlled to a reasonable extent.  Currently, the
+following types of memory usages are tracked.
+
+- Userland memory - page cache and anonymous memory.
+
+- Kernel data structures such as dentries and inodes.
+
+- TCP socket buffers.
+
+The above list may expand in the future for better coverage.
+
+
+5-2-1. Memory Interface Files
+
+All memory amounts are in bytes.  If a value which is not aligned to
+PAGE_SIZE is written, the value may be rounded up to the closest
+PAGE_SIZE multiple when read back.
+
+  memory.current
+
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of memory currently being used by the cgroup
+	and its descendants.
+
+  memory.low
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	Best-effort memory protection.  If the memory usages of a
+	cgroup and all its ancestors are below their low boundaries,
+	the cgroup's memory won't be reclaimed unless memory can be
+	reclaimed from unprotected cgroups.
+
+	Putting more memory than generally available under this
+	protection is discouraged.
+
+  memory.high
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Memory usage throttle limit.  This is the main mechanism to
+	control memory usage of a cgroup.  If a cgroup's usage goes
+	over the high boundary, the processes of the cgroup are
+	throttled and put under heavy reclaim pressure.
+
+	Going over the high limit never invokes the OOM killer and
+	under extreme conditions the limit may be breached.
+
+  memory.max
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Memory usage hard limit.  This is the final protection
+	mechanism.  If a cgroup's memory usage reaches this limit and
+	can't be reduced, the OOM killer is invoked in the cgroup.
+	Under certain circumstances, the usage may go over the limit
+	temporarily.
+
+	This is the ultimate protection mechanism.  As long as the
+	high limit is used and monitored properly, this limit's
+	utility is limited to providing the final safety net.
+
+  memory.events
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  low
+
+		The number of times the cgroup is reclaimed due to
+		high memory pressure even though its usage is under
+		the low boundary.  This usually indicates that the low
+		boundary is over-committed.
+
+	  high
+
+		The number of times processes of the cgroup are
+		throttled and routed to perform direct memory reclaim
+		because the high memory boundary was exceeded.  For a
+		cgroup whose memory usage is capped by the high limit
+		rather than global memory pressure, this event's
+		occurrences are expected.
+
+	  max
+
+		The number of times the cgroup's memory usage was
+		about to go over the max boundary.  If direct reclaim
+		fails to bring it down, the OOM killer is invoked.
+
+	  oom
+
+		The number of times the OOM killer has been invoked in
+		the cgroup.  This may not exactly match the number of
+		processes killed but should generally be close.
+
+  memory.stat
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+
+	This breaks down the cgroup's memory footprint into different
+	types of memory, type-specific details, and other information
+	on the state and past events of the memory management system.
+
+	All memory amounts are in bytes.
+
+	The entries are ordered to be human readable, and new entries
+	can show up in the middle. Don't rely on items remaining in a
+	fixed position; use the keys to look up specific values!
+
+	  anon
+
+		Amount of memory used in anonymous mappings such as
+		brk(), sbrk(), and mmap(MAP_ANONYMOUS)
+
+	  file
+
+		Amount of memory used to cache filesystem data,
+		including tmpfs and shared memory.
+
+	  sock
+
+		Amount of memory used in network transmission buffers
+
+	  file_mapped
+
+		Amount of cached filesystem data mapped with mmap()
+
+	  file_dirty
+
+		Amount of cached filesystem data that was modified but
+		not yet written back to disk
+
+	  file_writeback
+
+		Amount of cached filesystem data that was modified and
+		is currently being written back to disk
+
+	  inactive_anon
+	  active_anon
+	  inactive_file
+	  active_file
+	  unevictable
+
+		Amount of memory, swap-backed and filesystem-backed,
+		on the internal memory management lists used by the
+		page reclaim algorithm
+
+	  pgfault
+
+		Total number of page faults incurred
+
+	  pgmajfault
+
+		Number of major page faults incurred
+
+  memory.swap.current
+
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of swap currently being used by the cgroup
+	and its descendants.
+
+  memory.swap.max
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Swap usage hard limit.  If a cgroup's swap usage reaches this
+	limit, anonymous meomry of the cgroup will not be swapped out.
+
+
+5-2-2. General Usage
+
+"memory.high" is the main mechanism to control memory usage.
+Over-committing on high limit (sum of high limits > available memory)
+and letting global memory pressure to distribute memory according to
+usage is a viable strategy.
+
+Because breach of the high limit doesn't trigger the OOM killer but
+throttles the offending cgroup, a management agent has ample
+opportunities to monitor and take appropriate actions such as granting
+more memory or terminating the workload.
+
+Determining whether a cgroup has enough memory is not trivial as
+memory usage doesn't indicate whether the workload can benefit from
+more memory.  For example, a workload which writes data received from
+network to a file can use all available memory but can also operate as
+performant with a small amount of memory.  A measure of memory
+pressure - how much the workload is being impacted due to lack of
+memory - is necessary to determine whether a workload needs more
+memory; unfortunately, memory pressure monitoring mechanism isn't
+implemented yet.
+
+
+5-2-3. Memory Ownership
+
+A memory area is charged to the cgroup which instantiated it and stays
+charged to the cgroup until the area is released.  Migrating a process
+to a different cgroup doesn't move the memory usages that it
+instantiated while in the previous cgroup to the new cgroup.
+
+A memory area may be used by processes belonging to different cgroups.
+To which cgroup the area will be charged is in-deterministic; however,
+over time, the memory area is likely to end up in a cgroup which has
+enough memory allowance to avoid high reclaim pressure.
+
+If a cgroup sweeps a considerable amount of memory which is expected
+to be accessed repeatedly by other cgroups, it may make sense to use
+POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
+belonging to the affected files to ensure correct memory ownership.
+
+
+5-3. IO
+
+The "io" controller regulates the distribution of IO resources.  This
+controller implements both weight based and absolute bandwidth or IOPS
+limit distribution; however, weight based distribution is available
+only if cfq-iosched is in use and neither scheme is available for
+blk-mq devices.
+
+
+5-3-1. IO Interface Files
+
+  io.stat
+
+	A read-only nested-keyed file which exists on non-root
+	cgroups.
+
+	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
+	The following nested keys are defined.
+
+	  rbytes	Bytes read
+	  wbytes	Bytes written
+	  rios		Number of read IOs
+	  wios		Number of write IOs
+
+	An example read output follows.
+
+	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
+	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
+
+  io.weight
+
+	A read-write flat-keyed file which exists on non-root cgroups.
+	The default is "default 100".
+
+	The first line is the default weight applied to devices
+	without specific override.  The rest are overrides keyed by
+	$MAJ:$MIN device numbers and not ordered.  The weights are in
+	the range [1, 10000] and specifies the relative amount IO time
+	the cgroup can use in relation to its siblings.
+
+	The default weight can be updated by writing either "default
+	$WEIGHT" or simply "$WEIGHT".  Overrides can be set by writing
+	"$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
+
+	An example read output follows.
+
+	  default 100
+	  8:16 200
+	  8:0 50
+
+  io.max
+
+	A read-write nested-keyed file which exists on non-root
+	cgroups.
+
+	BPS and IOPS based IO limit.  Lines are keyed by $MAJ:$MIN
+	device numbers and not ordered.  The following nested keys are
+	defined.
+
+	  rbps		Max read bytes per second
+	  wbps		Max write bytes per second
+	  riops		Max read IO operations per second
+	  wiops		Max write IO operations per second
+
+	When writing, any number of nested key-value pairs can be
+	specified in any order.  "max" can be specified as the value
+	to remove a specific limit.  If the same key is specified
+	multiple times, the outcome is undefined.
+
+	BPS and IOPS are measured in each IO direction and IOs are
+	delayed if limit is reached.  Temporary bursts are allowed.
+
+	Setting read limit at 2M BPS and write at 120 IOPS for 8:16.
+
+	  echo "8:16 rbps=2097152 wiops=120" > io.max
+
+	Reading returns the following.
+
+	  8:16 rbps=2097152 wbps=max riops=max wiops=120
+
+	Write IOPS limit can be removed by writing the following.
+
+	  echo "8:16 wiops=max" > io.max
+
+	Reading now returns the following.
+
+	  8:16 rbps=2097152 wbps=max riops=max wiops=max
+
+
+5-3-2. Writeback
+
+Page cache is dirtied through buffered writes and shared mmaps and
+written asynchronously to the backing filesystem by the writeback
+mechanism.  Writeback sits between the memory and IO domains and
+regulates the proportion of dirty memory by balancing dirtying and
+write IOs.
+
+The io controller, in conjunction with the memory controller,
+implements control of page cache writeback IOs.  The memory controller
+defines the memory domain that dirty memory ratio is calculated and
+maintained for and the io controller defines the io domain which
+writes out dirty pages for the memory domain.  Both system-wide and
+per-cgroup dirty memory states are examined and the more restrictive
+of the two is enforced.
+
+cgroup writeback requires explicit support from the underlying
+filesystem.  Currently, cgroup writeback is implemented on ext2, ext4
+and btrfs.  On other filesystems, all writeback IOs are attributed to
+the root cgroup.
+
+There are inherent differences in memory and writeback management
+which affects how cgroup ownership is tracked.  Memory is tracked per
+page while writeback per inode.  For the purpose of writeback, an
+inode is assigned to a cgroup and all IO requests to write dirty pages
+from the inode are attributed to that cgroup.
+
+As cgroup ownership for memory is tracked per page, there can be pages
+which are associated with different cgroups than the one the inode is
+associated with.  These are called foreign pages.  The writeback
+constantly keeps track of foreign pages and, if a particular foreign
+cgroup becomes the majority over a certain period of time, switches
+the ownership of the inode to that cgroup.
+
+While this model is enough for most use cases where a given inode is
+mostly dirtied by a single cgroup even when the main writing cgroup
+changes over time, use cases where multiple cgroups write to a single
+inode simultaneously are not supported well.  In such circumstances, a
+significant portion of IOs are likely to be attributed incorrectly.
+As memory controller assigns page ownership on the first use and
+doesn't update it until the page is released, even if writeback
+strictly follows page ownership, multiple cgroups dirtying overlapping
+areas wouldn't work as expected.  It's recommended to avoid such usage
+patterns.
+
+The sysctl knobs which affect writeback behavior are applied to cgroup
+writeback as follows.
+
+  vm.dirty_background_ratio
+  vm.dirty_ratio
+
+	These ratios apply the same to cgroup writeback with the
+	amount of available memory capped by limits imposed by the
+	memory controller and system-wide clean memory.
+
+  vm.dirty_background_bytes
+  vm.dirty_bytes
+
+	For cgroup writeback, this is calculated into ratio against
+	total available memory and applied the same way as
+	vm.dirty[_background]_ratio.
+
+
+P. Information on Kernel Programming
+
+This section contains kernel programming information in the areas
+where interacting with cgroup is necessary.  cgroup core and
+controllers are not covered.
+
+
+P-1. Filesystem Support for Writeback
+
+A filesystem can support cgroup writeback by updating
+address_space_operations->writepage[s]() to annotate bio's using the
+following two functions.
+
+  wbc_init_bio(@wbc, @bio)
+
+	Should be called for each bio carrying writeback data and
+	associates the bio with the inode's owner cgroup.  Can be
+	called anytime between bio allocation and submission.
+
+  wbc_account_io(@wbc, @page, @bytes)
+
+	Should be called for each data segment being written out.
+	While this function doesn't care exactly when it's called
+	during the writeback session, it's the easiest and most
+	natural to call it as data segments are added to a bio.
+
+With writeback bio's annotated, cgroup support can be enabled per
+super_block by setting SB_I_CGROUPWB in ->s_iflags.  This allows for
+selective disabling of cgroup writeback support which is helpful when
+certain filesystem features, e.g. journaled data mode, are
+incompatible.
+
+wbc_init_bio() binds the specified bio to its cgroup.  Depending on
+the configuration, the bio may be executed at a lower priority and if
+the writeback session is holding shared resources, e.g. a journal
+entry, may lead to priority inversion.  There is no one easy solution
+for the problem.  Filesystems can try to work around specific problem
+cases by skipping wbc_init_bio() or using bio_associate_blkcg()
+directly.
+
+
+D. Deprecated v1 Core Features
+
+- Multiple hierarchies including named ones are not supported.
+
+- All mount options and remounting are not supported.
+
+- The "tasks" file is removed and "cgroup.procs" is not sorted.
+
+- "cgroup.clone_children" is removed.
+
+- /proc/cgroups is meaningless for v2.  Use "cgroup.controllers" file
+  at the root instead.
+
+
+R. Issues with v1 and Rationales for v2
+
+R-1. Multiple Hierarchies
+
+cgroup v1 allowed an arbitrary number of hierarchies and each
+hierarchy could host any number of controllers.  While this seemed to
+provide a high level of flexibility, it wasn't useful in practice.
+
+For example, as there is only one instance of each controller, utility
+type controllers such as freezer which can be useful in all
+hierarchies could only be used in one.  The issue is exacerbated by
+the fact that controllers couldn't be moved to another hierarchy once
+hierarchies were populated.  Another issue was that all controllers
+bound to a hierarchy were forced to have exactly the same view of the
+hierarchy.  It wasn't possible to vary the granularity depending on
+the specific controller.
+
+In practice, these issues heavily limited which controllers could be
+put on the same hierarchy and most configurations resorted to putting
+each controller on its own hierarchy.  Only closely related ones, such
+as the cpu and cpuacct controllers, made sense to be put on the same
+hierarchy.  This often meant that userland ended up managing multiple
+similar hierarchies repeating the same steps on each hierarchy
+whenever a hierarchy management operation was necessary.
+
+Furthermore, support for multiple hierarchies came at a steep cost.
+It greatly complicated cgroup core implementation but more importantly
+the support for multiple hierarchies restricted how cgroup could be
+used in general and what controllers was able to do.
+
+There was no limit on how many hierarchies there might be, which meant
+that a thread's cgroup membership couldn't be described in finite
+length.  The key might contain any number of entries and was unlimited
+in length, which made it highly awkward to manipulate and led to
+addition of controllers which existed only to identify membership,
+which in turn exacerbated the original problem of proliferating number
+of hierarchies.
+
+Also, as a controller couldn't have any expectation regarding the
+topologies of hierarchies other controllers might be on, each
+controller had to assume that all other controllers were attached to
+completely orthogonal hierarchies.  This made it impossible, or at
+least very cumbersome, for controllers to cooperate with each other.
+
+In most use cases, putting controllers on hierarchies which are
+completely orthogonal to each other isn't necessary.  What usually is
+called for is the ability to have differing levels of granularity
+depending on the specific controller.  In other words, hierarchy may
+be collapsed from leaf towards root when viewed from specific
+controllers.  For example, a given configuration might not care about
+how memory is distributed beyond a certain level while still wanting
+to control how CPU cycles are distributed.
+
+
+R-2. Thread Granularity
+
+cgroup v1 allowed threads of a process to belong to different cgroups.
+This didn't make sense for some controllers and those controllers
+ended up implementing different ways to ignore such situations but
+much more importantly it blurred the line between API exposed to
+individual applications and system management interface.
+
+Generally, in-process knowledge is available only to the process
+itself; thus, unlike service-level organization of processes,
+categorizing threads of a process requires active participation from
+the application which owns the target process.
+
+cgroup v1 had an ambiguously defined delegation model which got abused
+in combination with thread granularity.  cgroups were delegated to
+individual applications so that they can create and manage their own
+sub-hierarchies and control resource distributions along them.  This
+effectively raised cgroup to the status of a syscall-like API exposed
+to lay programs.
+
+First of all, cgroup has a fundamentally inadequate interface to be
+exposed this way.  For a process to access its own knobs, it has to
+extract the path on the target hierarchy from /proc/self/cgroup,
+construct the path by appending the name of the knob to the path, open
+and then read and/or write to it.  This is not only extremely clunky
+and unusual but also inherently racy.  There is no conventional way to
+define transaction across the required steps and nothing can guarantee
+that the process would actually be operating on its own sub-hierarchy.
+
+cgroup controllers implemented a number of knobs which would never be
+accepted as public APIs because they were just adding control knobs to
+system-management pseudo filesystem.  cgroup ended up with interface
+knobs which were not properly abstracted or refined and directly
+revealed kernel internal details.  These knobs got exposed to
+individual applications through the ill-defined delegation mechanism
+effectively abusing cgroup as a shortcut to implementing public APIs
+without going through the required scrutiny.
+
+This was painful for both userland and kernel.  Userland ended up with
+misbehaving and poorly abstracted interfaces and kernel exposing and
+locked into constructs inadvertently.
+
+
+R-3. Competition Between Inner Nodes and Threads
+
+cgroup v1 allowed threads to be in any cgroups which created an
+interesting problem where threads belonging to a parent cgroup and its
+children cgroups competed for resources.  This was nasty as two
+different types of entities competed and there was no obvious way to
+settle it.  Different controllers did different things.
+
+The cpu controller considered threads and cgroups as equivalents and
+mapped nice levels to cgroup weights.  This worked for some cases but
+fell flat when children wanted to be allocated specific ratios of CPU
+cycles and the number of internal threads fluctuated - the ratios
+constantly changed as the number of competing entities fluctuated.
+There also were other issues.  The mapping from nice level to weight
+wasn't obvious or universal, and there were various other knobs which
+simply weren't available for threads.
+
+The io controller implicitly created a hidden leaf node for each
+cgroup to host the threads.  The hidden leaf had its own copies of all
+the knobs with "leaf_" prefixed.  While this allowed equivalent
+control over internal threads, it was with serious drawbacks.  It
+always added an extra layer of nesting which wouldn't be necessary
+otherwise, made the interface messy and significantly complicated the
+implementation.
+
+The memory controller didn't have a way to control what happened
+between internal tasks and child cgroups and the behavior was not
+clearly defined.  There were attempts to add ad-hoc behaviors and
+knobs to tailor the behavior to specific workloads which would have
+led to problems extremely difficult to resolve in the long term.
+
+Multiple controllers struggled with internal tasks and came up with
+different ways to deal with it; unfortunately, all the approaches were
+severely flawed and, furthermore, the widely different behaviors
+made cgroup as a whole highly inconsistent.
+
+This clearly is a problem which needs to be addressed from cgroup core
+in a uniform way.
+
+
+R-4. Other Interface Issues
+
+cgroup v1 grew without oversight and developed a large number of
+idiosyncrasies and inconsistencies.  One issue on the cgroup core side
+was how an empty cgroup was notified - a userland helper binary was
+forked and executed for each event.  The event delivery wasn't
+recursive or delegatable.  The limitations of the mechanism also led
+to in-kernel event delivery filtering mechanism further complicating
+the interface.
+
+Controller interfaces were problematic too.  An extreme example is
+controllers completely ignoring hierarchical organization and treating
+all cgroups as if they were all located directly under the root
+cgroup.  Some controllers exposed a large amount of inconsistent
+implementation details to userland.
+
+There also was no consistency across controllers.  When a new cgroup
+was created, some controllers defaulted to not imposing extra
+restrictions while others disallowed any resource usage until
+explicitly configured.  Configuration knobs for the same type of
+control used widely differing naming schemes and formats.  Statistics
+and information knobs were named arbitrarily and used different
+formats and units even in the same controller.
+
+cgroup v2 establishes common conventions where appropriate and updates
+controllers so that they expose minimal and consistent interfaces.
+
+
+R-5. Controller Issues and Remedies
+
+R-5-1. Memory
+
+The original lower boundary, the soft limit, is defined as a limit
+that is per default unset.  As a result, the set of cgroups that
+global reclaim prefers is opt-in, rather than opt-out.  The costs for
+optimizing these mostly negative lookups are so high that the
+implementation, despite its enormous size, does not even provide the
+basic desirable behavior.  First off, the soft limit has no
+hierarchical meaning.  All configured groups are organized in a global
+rbtree and treated like equal peers, regardless where they are located
+in the hierarchy.  This makes subtree delegation impossible.  Second,
+the soft limit reclaim pass is so aggressive that it not just
+introduces high allocation latencies into the system, but also impacts
+system performance due to overreclaim, to the point where the feature
+becomes self-defeating.
+
+The memory.low boundary on the other hand is a top-down allocated
+reserve.  A cgroup enjoys reclaim protection when it and all its
+ancestors are below their low boundaries, which makes delegation of
+subtrees possible.  Secondly, new cgroups have no reserve per default
+and in the common case most cgroups are eligible for the preferred
+reclaim pass.  This allows the new low boundary to be efficiently
+implemented with just a minor addition to the generic reclaim code,
+without the need for out-of-band data structures and reclaim passes.
+Because the generic reclaim code considers all cgroups except for the
+ones running low in the preferred first reclaim pass, overreclaim of
+individual groups is eliminated as well, resulting in much better
+overall workload performance.
+
+The original high boundary, the hard limit, is defined as a strict
+limit that can not budge, even if the OOM killer has to be called.
+But this generally goes against the goal of making the most out of the
+available memory.  The memory consumption of workloads varies during
+runtime, and that requires users to overcommit.  But doing that with a
+strict upper limit requires either a fairly accurate prediction of the
+working set size or adding slack to the limit.  Since working set size
+estimation is hard and error prone, and getting it wrong results in
+OOM kills, most users tend to err on the side of a looser limit and
+end up wasting precious resources.
+
+The memory.high boundary on the other hand can be set much more
+conservatively.  When hit, it throttles allocations by forcing them
+into direct reclaim to work off the excess, but it never invokes the
+OOM killer.  As a result, a high boundary that is chosen too
+aggressively will not terminate the processes, but instead it will
+lead to gradual performance degradation.  The user can monitor this
+and make corrections until the minimal memory footprint that still
+gives acceptable performance is found.
+
+In extreme cases, with many concurrent allocations and a complete
+breakdown of reclaim progress within the group, the high boundary can
+be exceeded.  But even then it's mostly better to satisfy the
+allocation from the slack available in other groups or the rest of the
+system than killing the group.  Otherwise, memory.max is there to
+limit this type of spillover and ultimately contain buggy or even
+malicious applications.
+
+The combined memory+swap accounting and limiting is replaced by real
+control over swap space.
+
+The main argument for a combined memory+swap facility in the original
+cgroup design was that global or parental pressure would always be
+able to swap all anonymous memory of a child group, regardless of the
+child's own (possibly untrusted) configuration.  However, untrusted
+groups can sabotage swapping by other means - such as referencing its
+anonymous memory in a tight loop - and an admin can not assume full
+swappability when overcommitting untrusted jobs.
+
+For trusted jobs, on the other hand, a combined counter is not an
+intuitive userspace interface, and it flies in the face of the idea
+that cgroup controllers should account and limit specific physical
+resources.  Swap space is a resource like all others in the system,
+and that's why unified hierarchy allows distributing it separately.
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
deleted file mode 100644
index 781b1d475bcf..000000000000
--- a/Documentation/cgroups/unified-hierarchy.txt
+++ /dev/null
@@ -1,647 +0,0 @@
-
-Cgroup unified hierarchy
-
-April, 2014		Tejun Heo <tj@kernel.org>
-
-This document describes the changes made by unified hierarchy and
-their rationales.  It will eventually be merged into the main cgroup
-documentation.
-
-CONTENTS
-
-1. Background
-2. Basic Operation
-  2-1. Mounting
-  2-2. cgroup.subtree_control
-  2-3. cgroup.controllers
-3. Structural Constraints
-  3-1. Top-down
-  3-2. No internal tasks
-4. Delegation
-  4-1. Model of delegation
-  4-2. Common ancestor rule
-5. Other Changes
-  5-1. [Un]populated Notification
-  5-2. Other Core Changes
-  5-3. Controller File Conventions
-    5-3-1. Format
-    5-3-2. Control Knobs
-  5-4. Per-Controller Changes
-    5-4-1. io
-    5-4-2. cpuset
-    5-4-3. memory
-6. Planned Changes
-  6-1. CAP for resource control
-
-
-1. Background
-
-cgroup allows an arbitrary number of hierarchies and each hierarchy
-can host any number of controllers.  While this seems to provide a
-high level of flexibility, it isn't quite useful in practice.
-
-For example, as there is only one instance of each controller, utility
-type controllers such as freezer which can be useful in all
-hierarchies can only be used in one.  The issue is exacerbated by the
-fact that controllers can't be moved around once hierarchies are
-populated.  Another issue is that all controllers bound to a hierarchy
-are forced to have exactly the same view of the hierarchy.  It isn't
-possible to vary the granularity depending on the specific controller.
-
-In practice, these issues heavily limit which controllers can be put
-on the same hierarchy and most configurations resort to putting each
-controller on its own hierarchy.  Only closely related ones, such as
-the cpu and cpuacct controllers, make sense to put on the same
-hierarchy.  This often means that userland ends up managing multiple
-similar hierarchies repeating the same steps on each hierarchy
-whenever a hierarchy management operation is necessary.
-
-Unfortunately, support for multiple hierarchies comes at a steep cost.
-Internal implementation in cgroup core proper is dazzlingly
-complicated but more importantly the support for multiple hierarchies
-restricts how cgroup is used in general and what controllers can do.
-
-There's no limit on how many hierarchies there may be, which means
-that a task's cgroup membership can't be described in finite length.
-The key may contain any varying number of entries and is unlimited in
-length, which makes it highly awkward to handle and leads to addition
-of controllers which exist only to identify membership, which in turn
-exacerbates the original problem.
-
-Also, as a controller can't have any expectation regarding what shape
-of hierarchies other controllers would be on, each controller has to
-assume that all other controllers are operating on completely
-orthogonal hierarchies.  This makes it impossible, or at least very
-cumbersome, for controllers to cooperate with each other.
-
-In most use cases, putting controllers on hierarchies which are
-completely orthogonal to each other isn't necessary.  What usually is
-called for is the ability to have differing levels of granularity
-depending on the specific controller.  In other words, hierarchy may
-be collapsed from leaf towards root when viewed from specific
-controllers.  For example, a given configuration might not care about
-how memory is distributed beyond a certain level while still wanting
-to control how CPU cycles are distributed.
-
-Unified hierarchy is the next version of cgroup interface.  It aims to
-address the aforementioned issues by having more structure while
-retaining enough flexibility for most use cases.  Various other
-general and controller-specific interface issues are also addressed in
-the process.
-
-
-2. Basic Operation
-
-2-1. Mounting
-
-Currently, unified hierarchy can be mounted with the following mount
-command.  Note that this is still under development and scheduled to
-change soon.
-
- mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT
-
-All controllers which support the unified hierarchy and are not bound
-to other hierarchies are automatically bound to unified hierarchy and
-show up at the root of it.  Controllers which are enabled only in the
-root of unified hierarchy can be bound to other hierarchies.  This
-allows mixing unified hierarchy with the traditional multiple
-hierarchies in a fully backward compatible way.
-
-A controller can be moved across hierarchies only after the controller
-is no longer referenced in its current hierarchy.  Because per-cgroup
-controller states are destroyed asynchronously and controllers may
-have lingering references, a controller may not show up immediately on
-the unified hierarchy after the final umount of the previous
-hierarchy.  Similarly, a controller should be fully disabled to be
-moved out of the unified hierarchy and it may take some time for the
-disabled controller to become available for other hierarchies;
-furthermore, due to dependencies among controllers, other controllers
-may need to be disabled too.
-
-While useful for development and manual configurations, dynamically
-moving controllers between the unified and other hierarchies is
-strongly discouraged for production use.  It is recommended to decide
-the hierarchies and controller associations before starting using the
-controllers.
-
-
-2-2. cgroup.subtree_control
-
-All cgroups on unified hierarchy have a "cgroup.subtree_control" file
-which governs which controllers are enabled on the children of the
-cgroup.  Let's assume a hierarchy like the following.
-
-  root - A - B - C
-               \ D
-
-root's "cgroup.subtree_control" file determines which controllers are
-enabled on A.  A's on B.  B's on C and D.  This coincides with the
-fact that controllers on the immediate sub-level are used to
-distribute the resources of the parent.  In fact, it's natural to
-assume that resource control knobs of a child belong to its parent.
-Enabling a controller in a "cgroup.subtree_control" file declares that
-distribution of the respective resources of the cgroup will be
-controlled.  Note that this means that controller enable states are
-shared among siblings.
-
-When read, the file contains a space-separated list of currently
-enabled controllers.  A write to the file should contain a
-space-separated list of controllers with '+' or '-' prefixed (without
-the quotes).  Controllers prefixed with '+' are enabled and '-'
-disabled.  If a controller is listed multiple times, the last entry
-wins.  The specific operations are executed atomically - either all
-succeed or fail.
-
-
-2-3. cgroup.controllers
-
-Read-only "cgroup.controllers" file contains a space-separated list of
-controllers which can be enabled in the cgroup's
-"cgroup.subtree_control" file.
-
-In the root cgroup, this lists controllers which are not bound to
-other hierarchies and the content changes as controllers are bound to
-and unbound from other hierarchies.
-
-In non-root cgroups, the content of this file equals that of the
-parent's "cgroup.subtree_control" file as only controllers enabled
-from the parent can be used in its children.
-
-
-3. Structural Constraints
-
-3-1. Top-down
-
-As it doesn't make sense to nest control of an uncontrolled resource,
-all non-root "cgroup.subtree_control" files can only contain
-controllers which are enabled in the parent's "cgroup.subtree_control"
-file.  A controller can be enabled only if the parent has the
-controller enabled and a controller can't be disabled if one or more
-children have it enabled.
-
-
-3-2. No internal tasks
-
-One long-standing issue that cgroup faces is the competition between
-tasks belonging to the parent cgroup and its children cgroups.  This
-is inherently nasty as two different types of entities compete and
-there is no agreed-upon obvious way to handle it.  Different
-controllers are doing different things.
-
-The cpu controller considers tasks and cgroups as equivalents and maps
-nice levels to cgroup weights.  This works for some cases but falls
-flat when children should be allocated specific ratios of CPU cycles
-and the number of internal tasks fluctuates - the ratios constantly
-change as the number of competing entities fluctuates.  There also are
-other issues.  The mapping from nice level to weight isn't obvious or
-universal, and there are various other knobs which simply aren't
-available for tasks.
-
-The io controller implicitly creates a hidden leaf node for each
-cgroup to host the tasks.  The hidden leaf has its own copies of all
-the knobs with "leaf_" prefixed.  While this allows equivalent control
-over internal tasks, it's with serious drawbacks.  It always adds an
-extra layer of nesting which may not be necessary, makes the interface
-messy and significantly complicates the implementation.
-
-The memory controller currently doesn't have a way to control what
-happens between internal tasks and child cgroups and the behavior is
-not clearly defined.  There have been attempts to add ad-hoc behaviors
-and knobs to tailor the behavior to specific workloads.  Continuing
-this direction will lead to problems which will be extremely difficult
-to resolve in the long term.
-
-Multiple controllers struggle with internal tasks and came up with
-different ways to deal with it; unfortunately, all the approaches in
-use now are severely flawed and, furthermore, the widely different
-behaviors make cgroup as whole highly inconsistent.
-
-It is clear that this is something which needs to be addressed from
-cgroup core proper in a uniform way so that controllers don't need to
-worry about it and cgroup as a whole shows a consistent and logical
-behavior.  To achieve that, unified hierarchy enforces the following
-structural constraint:
-
- Except for the root, only cgroups which don't contain any task may
- have controllers enabled in their "cgroup.subtree_control" files.
-
-Combined with other properties, this guarantees that, when a
-controller is looking at the part of the hierarchy which has it
-enabled, tasks are always only on the leaves.  This rules out
-situations where child cgroups compete against internal tasks of the
-parent.
-
-There are two things to note.  Firstly, the root cgroup is exempt from
-the restriction.  Root contains tasks and anonymous resource
-consumption which can't be associated with any other cgroup and
-requires special treatment from most controllers.  How resource
-consumption in the root cgroup is governed is up to each controller.
-
-Secondly, the restriction doesn't take effect if there is no enabled
-controller in the cgroup's "cgroup.subtree_control" file.  This is
-important as otherwise it wouldn't be possible to create children of a
-populated cgroup.  To control resource distribution of a cgroup, the
-cgroup must create children and transfer all its tasks to the children
-before enabling controllers in its "cgroup.subtree_control" file.
-
-
-4. Delegation
-
-4-1. Model of delegation
-
-A cgroup can be delegated to a less privileged user by granting write
-access of the directory and its "cgroup.procs" file to the user.  Note
-that the resource control knobs in a given directory concern the
-resources of the parent and thus must not be delegated along with the
-directory.
-
-Once delegated, the user can build sub-hierarchy under the directory,
-organize processes as it sees fit and further distribute the resources
-it got from the parent.  The limits and other settings of all resource
-controllers are hierarchical and regardless of what happens in the
-delegated sub-hierarchy, nothing can escape the resource restrictions
-imposed by the parent.
-
-Currently, cgroup doesn't impose any restrictions on the number of
-cgroups in or nesting depth of a delegated sub-hierarchy; however,
-this may in the future be limited explicitly.
-
-
-4-2. Common ancestor rule
-
-On the unified hierarchy, to write to a "cgroup.procs" file, in
-addition to the usual write permission to the file and uid match, the
-writer must also have write access to the "cgroup.procs" file of the
-common ancestor of the source and destination cgroups.  This prevents
-delegatees from smuggling processes across disjoint sub-hierarchies.
-
-Let's say cgroups C0 and C1 have been delegated to user U0 who created
-C00, C01 under C0 and C10 under C1 as follows.
-
- ~~~~~~~~~~~~~ - C0 - C00
- ~ cgroup    ~      \ C01
- ~ hierarchy ~
- ~~~~~~~~~~~~~ - C1 - C10
-
-C0 and C1 are separate entities in terms of resource distribution
-regardless of their relative positions in the hierarchy.  The
-resources the processes under C0 are entitled to are controlled by
-C0's ancestors and may be completely different from C1.  It's clear
-that the intention of delegating C0 to U0 is allowing U0 to organize
-the processes under C0 and further control the distribution of C0's
-resources.
-
-On traditional hierarchies, if a task has write access to "tasks" or
-"cgroup.procs" file of a cgroup and its uid agrees with the target, it
-can move the target to the cgroup.  In the above example, U0 will not
-only be able to move processes in each sub-hierarchy but also across
-the two sub-hierarchies, effectively allowing it to violate the
-organizational and resource restrictions implied by the hierarchical
-structure above C0 and C1.
-
-On the unified hierarchy, let's say U0 wants to write the pid of a
-process which has a matching uid and is currently in C10 into
-"C00/cgroup.procs".  U0 obviously has write access to the file and
-migration permission on the process; however, the common ancestor of
-the source cgroup C10 and the destination cgroup C00 is above the
-points of delegation and U0 would not have write access to its
-"cgroup.procs" and thus be denied with -EACCES.
-
-
-5. Other Changes
-
-5-1. [Un]populated Notification
-
-cgroup users often need a way to determine when a cgroup's
-subhierarchy becomes empty so that it can be cleaned up.  cgroup
-currently provides release_agent for it; unfortunately, this mechanism
-is riddled with issues.
-
-- It delivers events by forking and execing a userland binary
-  specified as the release_agent.  This is a long deprecated method of
-  notification delivery.  It's extremely heavy, slow and cumbersome to
-  integrate with larger infrastructure.
-
-- There is single monitoring point at the root.  There's no way to
-  delegate management of a subtree.
-
-- The event isn't recursive.  It triggers when a cgroup doesn't have
-  any tasks or child cgroups.  Events for internal nodes trigger only
-  after all children are removed.  This again makes it impossible to
-  delegate management of a subtree.
-
-- Events are filtered from the kernel side.  A "notify_on_release"
-  file is used to subscribe to or suppress release events.  This is
-  unnecessarily complicated and probably done this way because event
-  delivery itself was expensive.
-
-Unified hierarchy implements "populated" field in "cgroup.events"
-interface file which can be used to monitor whether the cgroup's
-subhierarchy has tasks in it or not.  Its value is 0 if there is no
-task in the cgroup and its descendants; otherwise, 1.  poll and
-[id]notify events are triggered when the value changes.
-
-This is significantly lighter and simpler and trivially allows
-delegating management of subhierarchy - subhierarchy monitoring can
-block further propagation simply by putting itself or another process
-in the subhierarchy and monitor events that it's interested in from
-there without interfering with monitoring higher in the tree.
-
-In unified hierarchy, the release_agent mechanism is no longer
-supported and the interface files "release_agent" and
-"notify_on_release" do not exist.
-
-
-5-2. Other Core Changes
-
-- None of the mount options is allowed.
-
-- remount is disallowed.
-
-- rename(2) is disallowed.
-
-- The "tasks" file is removed.  Everything should at process
-  granularity.  Use the "cgroup.procs" file instead.
-
-- The "cgroup.procs" file is not sorted.  pids will be unique unless
-  they got recycled in-between reads.
-
-- The "cgroup.clone_children" file is removed.
-
-- /proc/PID/cgroup keeps reporting the cgroup that a zombie belonged
-  to before exiting.  If the cgroup is removed before the zombie is
-  reaped, " (deleted)" is appeneded to the path.
-
-
-5-3. Controller File Conventions
-
-5-3-1. Format
-
-In general, all controller files should be in one of the following
-formats whenever possible.
-
-- Values only files
-
-  VAL0 VAL1...\n
-
-- Flat keyed files
-
-  KEY0 VAL0\n
-  KEY1 VAL1\n
-  ...
-
-- Nested keyed files
-
-  KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
-  KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
-  ...
-
-For a writeable file, the format for writing should generally match
-reading; however, controllers may allow omitting later fields or
-implement restricted shortcuts for most common use cases.
-
-For both flat and nested keyed files, only the values for a single key
-can be written at a time.  For nested keyed files, the sub key pairs
-may be specified in any order and not all pairs have to be specified.
-
-
-5-3-2. Control Knobs
-
-- Settings for a single feature should generally be implemented in a
-  single file.
-
-- In general, the root cgroup should be exempt from resource control
-  and thus shouldn't have resource control knobs.
-
-- If a controller implements ratio based resource distribution, the
-  control knob should be named "weight" and have the range [1, 10000]
-  and 100 should be the default value.  The values are chosen to allow
-  enough and symmetric bias in both directions while keeping it
-  intuitive (the default is 100%).
-
-- If a controller implements an absolute resource guarantee and/or
-  limit, the control knobs should be named "min" and "max"
-  respectively.  If a controller implements best effort resource
-  gurantee and/or limit, the control knobs should be named "low" and
-  "high" respectively.
-
-  In the above four control files, the special token "max" should be
-  used to represent upward infinity for both reading and writing.
-
-- If a setting has configurable default value and specific overrides,
-  the default settings should be keyed with "default" and appear as
-  the first entry in the file.  Specific entries can use "default" as
-  its value to indicate inheritance of the default value.
-
-- For events which are not very high frequency, an interface file
-  "events" should be created which lists event key value pairs.
-  Whenever a notifiable event happens, file modified event should be
-  generated on the file.
-
-
-5-4. Per-Controller Changes
-
-5-4-1. io
-
-- blkio is renamed to io.  The interface is overhauled anyway.  The
-  new name is more in line with the other two major controllers, cpu
-  and memory, and better suited given that it may be used for cgroup
-  writeback without involving block layer.
-
-- Everything including stat is always hierarchical making separate
-  recursive stat files pointless and, as no internal node can have
-  tasks, leaf weights are meaningless.  The operation model is
-  simplified and the interface is overhauled accordingly.
-
-  io.stat
-
-	The stat file.  The reported stats are from the point where
-	bio's are issued to request_queue.  The stats are counted
-	independent of which policies are enabled.  Each line in the
-	file follows the following format.  More fields may later be
-	added at the end.
-
-	  $MAJ:$MIN rbytes=$RBYTES wbytes=$WBYTES rios=$RIOS wrios=$WIOS
-
-  io.weight
-
-	The weight setting, currently only available and effective if
-	cfq-iosched is in use for the target device.  The weight is
-	between 1 and 10000 and defaults to 100.  The first line
-	always contains the default weight in the following format to
-	use when per-device setting is missing.
-
-	  default $WEIGHT
-
-	Subsequent lines list per-device weights of the following
-	format.
-
-	  $MAJ:$MIN $WEIGHT
-
-	Writing "$WEIGHT" or "default $WEIGHT" changes the default
-	setting.  Writing "$MAJ:$MIN $WEIGHT" sets per-device weight
-	while "$MAJ:$MIN default" clears it.
-
-	This file is available only on non-root cgroups.
-
-  io.max
-
-	The maximum bandwidth and/or iops setting, only available if
-	blk-throttle is enabled.  The file is of the following format.
-
-	  $MAJ:$MIN rbps=$RBPS wbps=$WBPS riops=$RIOPS wiops=$WIOPS
-
-	${R|W}BPS are read/write bytes per second and ${R|W}IOPS are
-	read/write IOs per second.  "max" indicates no limit.  Writing
-	to the file follows the same format but the individual
-	settings may be omitted or specified in any order.
-
-	This file is available only on non-root cgroups.
-
-
-5-4-2. cpuset
-
-- Tasks are kept in empty cpusets after hotplug and take on the masks
-  of the nearest non-empty ancestor, instead of being moved to it.
-
-- A task can be moved into an empty cpuset, and again it takes on the
-  masks of the nearest non-empty ancestor.
-
-
-5-4-3. memory
-
-- use_hierarchy is on by default and the cgroup file for the flag is
-  not created.
-
-- The original lower boundary, the soft limit, is defined as a limit
-  that is per default unset.  As a result, the set of cgroups that
-  global reclaim prefers is opt-in, rather than opt-out.  The costs
-  for optimizing these mostly negative lookups are so high that the
-  implementation, despite its enormous size, does not even provide the
-  basic desirable behavior.  First off, the soft limit has no
-  hierarchical meaning.  All configured groups are organized in a
-  global rbtree and treated like equal peers, regardless where they
-  are located in the hierarchy.  This makes subtree delegation
-  impossible.  Second, the soft limit reclaim pass is so aggressive
-  that it not just introduces high allocation latencies into the
-  system, but also impacts system performance due to overreclaim, to
-  the point where the feature becomes self-defeating.
-
-  The memory.low boundary on the other hand is a top-down allocated
-  reserve.  A cgroup enjoys reclaim protection when it and all its
-  ancestors are below their low boundaries, which makes delegation of
-  subtrees possible.  Secondly, new cgroups have no reserve per
-  default and in the common case most cgroups are eligible for the
-  preferred reclaim pass.  This allows the new low boundary to be
-  efficiently implemented with just a minor addition to the generic
-  reclaim code, without the need for out-of-band data structures and
-  reclaim passes.  Because the generic reclaim code considers all
-  cgroups except for the ones running low in the preferred first
-  reclaim pass, overreclaim of individual groups is eliminated as
-  well, resulting in much better overall workload performance.
-
-- The original high boundary, the hard limit, is defined as a strict
-  limit that can not budge, even if the OOM killer has to be called.
-  But this generally goes against the goal of making the most out of
-  the available memory.  The memory consumption of workloads varies
-  during runtime, and that requires users to overcommit.  But doing
-  that with a strict upper limit requires either a fairly accurate
-  prediction of the working set size or adding slack to the limit.
-  Since working set size estimation is hard and error prone, and
-  getting it wrong results in OOM kills, most users tend to err on the
-  side of a looser limit and end up wasting precious resources.
-
-  The memory.high boundary on the other hand can be set much more
-  conservatively.  When hit, it throttles allocations by forcing them
-  into direct reclaim to work off the excess, but it never invokes the
-  OOM killer.  As a result, a high boundary that is chosen too
-  aggressively will not terminate the processes, but instead it will
-  lead to gradual performance degradation.  The user can monitor this
-  and make corrections until the minimal memory footprint that still
-  gives acceptable performance is found.
-
-  In extreme cases, with many concurrent allocations and a complete
-  breakdown of reclaim progress within the group, the high boundary
-  can be exceeded.  But even then it's mostly better to satisfy the
-  allocation from the slack available in other groups or the rest of
-  the system than killing the group.  Otherwise, memory.max is there
-  to limit this type of spillover and ultimately contain buggy or even
-  malicious applications.
-
-- The original control file names are unwieldy and inconsistent in
-  many different ways.  For example, the upper boundary hit count is
-  exported in the memory.failcnt file, but an OOM event count has to
-  be manually counted by listening to memory.oom_control events, and
-  lower boundary / soft limit events have to be counted by first
-  setting a threshold for that value and then counting those events.
-  Also, usage and limit files encode their units in the filename.
-  That makes the filenames very long, even though this is not
-  information that a user needs to be reminded of every time they type
-  out those names.
-
-  To address these naming issues, as well as to signal clearly that
-  the new interface carries a new configuration model, the naming
-  conventions in it necessarily differ from the old interface.
-
-- The original limit files indicate the state of an unset limit with a
-  Very High Number, and a configured limit can be unset by echoing -1
-  into those files.  But that very high number is implementation and
-  architecture dependent and not very descriptive.  And while -1 can
-  be understood as an underflow into the highest possible value, -2 or
-  -10M etc. do not work, so it's not consistent.
-
-  memory.low, memory.high, and memory.max will use the string "max" to
-  indicate and set the highest possible value.
-
-6. Planned Changes
-
-6-1. CAP for resource control
-
-Unified hierarchy will require one of the capabilities(7), which is
-yet to be decided, for all resource control related knobs.  Process
-organization operations - creation of sub-cgroups and migration of
-processes in sub-hierarchies may be delegated by changing the
-ownership and/or permissions on the cgroup directory and
-"cgroup.procs" interface file; however, all operations which affect
-resource control - writes to a "cgroup.subtree_control" file or any
-controller-specific knobs - will require an explicit CAP privilege.
-
-This, in part, is to prevent the cgroup interface from being
-inadvertently promoted to programmable API used by non-privileged
-binaries.  cgroup exposes various aspects of the system in ways which
-aren't properly abstracted for direct consumption by regular programs.
-This is an administration interface much closer to sysctl knobs than
-system calls.  Even the basic access model, being filesystem path
-based, isn't suitable for direct consumption.  There's no way to
-access "my cgroup" in a race-free way or make multiple operations
-atomic against migration to another cgroup.
-
-Another aspect is that, for better or for worse, the cgroup interface
-goes through far less scrutiny than regular interfaces for
-unprivileged userland.  The upside is that cgroup is able to expose
-useful features which may not be suitable for general consumption in a
-reasonable time frame.  It provides a relatively short path between
-internal details and userland-visible interface.  Of course, this
-shortcut comes with high risk.  We go through what we go through for
-general kernel APIs for good reasons.  It may end up leaking internal
-details in a way which can exert significant pain by locking the
-kernel into a contract that can't be maintained in a reasonable
-manner.
-
-Also, due to the specific nature, cgroup and its controllers don't
-tend to attract attention from a wide scope of developers.  cgroup's
-short history is already fraught with severely mis-designed
-interfaces, unnecessary commitments to and exposing of internal
-details, broken and dangerous implementations of various features.
-
-Keeping cgroup as an administration interface is both advantageous for
-its role and imperative given its nature.  Some of the cgroup features
-may make sense for unprivileged access.  If deemed justified, those
-must be further abstracted and implemented as a different interface,
-be it a system call or process-private filesystem, and survive through
-the scrutiny that any interface for general consumption is required to
-go through.
-
-Requiring CAP is not a complete solution but should serve as a
-significant deterrent against spraying cgroup usages in non-privileged
-programs.
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index be8d4006bf76..f7b12c071d53 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -1,61 +1,131 @@
-Intel P-state driver
+Intel P-State driver
 --------------------
 
-This driver provides an interface to control the P state selection for
-SandyBridge+ Intel processors.  The driver can operate two different
-modes based on the processor model, legacy mode and Hardware P state (HWP)
-mode.
-
-In legacy mode, the Intel P-state implements two internal governors,
-performance and powersave, that differ from the general cpufreq governors of
-the same name (the general cpufreq governors implement target(), whereas the
-internal Intel P-state governors implement setpolicy()).  The internal
-performance governor sets the max_perf_pct and min_perf_pct to 100; that is,
-the governor selects the highest available P state to maximize the performance
-of the core.  The internal powersave governor selects the appropriate P state
-based on the current load on the CPU.
-
-In HWP mode P state selection is implemented in the processor
-itself. The driver provides the interfaces between the cpufreq core and
-the processor to control P state selection based on user preferences
-and reporting frequency to the cpufreq core.  In this mode the
-internal Intel P-state governor code is disabled.
-
-In addition to the interfaces provided by the cpufreq core for
-controlling frequency the driver provides sysfs files for
-controlling P state selection. These files have been added to
-/sys/devices/system/cpu/intel_pstate/
-
-      max_perf_pct: limits the maximum P state that will be requested by
-      the driver stated as a percentage of the available performance. The
-      available (P states) performance may be reduced by the no_turbo
+This driver provides an interface to control the P-State selection for the
+SandyBridge+ Intel processors.
+
+The following document explains P-States:
+http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+As stated in the document, P-State doesn’t exactly mean a frequency. However, for
+the sake of the relationship with cpufreq, P-State and frequency are used
+interchangeably.
+
+Understanding the cpufreq core governors and policies are important before
+discussing more details about the Intel P-State driver. Based on what callbacks
+a cpufreq driver provides to the cpufreq core, it can support two types of
+drivers:
+- with target_index() callback: In this mode, the drivers using cpufreq core
+simply provide the minimum and maximum frequency limits and an additional
+interface target_index() to set the current frequency. The cpufreq subsystem
+has a number of scaling governors ("performance", "powersave", "ondemand",
+etc.). Depending on which governor is in use, cpufreq core will call for
+transitions to a specific frequency using target_index() callback.
+- setpolicy() callback: In this mode, drivers do not provide target_index()
+callback, so cpufreq core can't request a transition to a specific frequency.
+The driver provides minimum and maximum frequency limits and callbacks to set a
+policy. The policy in cpufreq sysfs is referred to as the "scaling governor".
+The cpufreq core can request the driver to operate in any of the two policies:
+"performance: and "powersave". The driver decides which frequency to use based
+on the above policy selection considering minimum and maximum frequency limits.
+
+The Intel P-State driver falls under the latter category, which implements the
+setpolicy() callback. This driver decides what P-State to use based on the
+requested policy from the cpufreq core. If the processor is capable of
+selecting its next P-State internally, then the driver will offload this
+responsibility to the processor (aka HWP: Hardware P-States). If not, the
+driver implements algorithms to select the next P-State.
+
+Since these policies are implemented in the driver, they are not same as the
+cpufreq scaling governors implementation, even if they have the same name in
+the cpufreq sysfs (scaling_governors). For example the "performance" policy is
+similar to cpufreq’s "performance" governor, but "powersave" is completely
+different than the cpufreq "powersave" governor. The strategy here is similar
+to cpufreq "ondemand", where the requested P-State is related to the system load.
+
+Sysfs Interface
+
+In addition to the frequency-controlling interfaces provided by the cpufreq
+core, the driver provides its own sysfs files to control the P-State selection.
+These files have been added to /sys/devices/system/cpu/intel_pstate/.
+Any changes made to these files are applicable to all CPUs (even in a
+multi-package system).
+
+      max_perf_pct: Limits the maximum P-State that will be requested by
+      the driver. It states it as a percentage of the available performance. The
+      available (P-State) performance may be reduced by the no_turbo
       setting described below.
 
-      min_perf_pct: limits the minimum P state that will be  requested by
-      the driver stated as a percentage of the max (non-turbo)
+      min_perf_pct: Limits the minimum P-State that will be requested by
+      the driver. It states it as a percentage of the max (non-turbo)
       performance level.
 
-      no_turbo: limits the driver to selecting P states below the turbo
+      no_turbo: Limits the driver to selecting P-State below the turbo
       frequency range.
 
-      turbo_pct: displays the percentage of the total performance that
-      is supported by hardware that is in the turbo range.  This number
+      turbo_pct: Displays the percentage of the total performance that
+      is supported by hardware that is in the turbo range. This number
       is independent of whether turbo has been disabled or not.
 
-      num_pstates: displays the number of pstates that are supported
-      by hardware.  This number is independent of whether turbo has
+      num_pstates: Displays the number of P-States that are supported
+      by hardware. This number is independent of whether turbo has
       been disabled or not.
 
+For example, if a system has these parameters:
+	Max 1 core turbo ratio: 0x21 (Max 1 core ratio is the maximum P-State)
+	Max non turbo ratio: 0x17
+	Minimum ratio : 0x08 (Here the ratio is called max efficiency ratio)
+
+Sysfs will show :
+	max_perf_pct:100, which corresponds to 1 core ratio
+	min_perf_pct:24, max_efficiency_ratio / max 1 Core ratio
+	no_turbo:0, turbo is not disabled
+	num_pstates:26 = (max 1 Core ratio - Max Efficiency Ratio + 1)
+	turbo_pct:39 = (max 1 core ratio - max non turbo ratio) / num_pstates
+
+Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual
+Volume 3: System Programming Guide" to understand ratios.
+
+cpufreq sysfs for Intel P-State
+
+Since this driver registers with cpufreq, cpufreq sysfs is also presented.
+There are some important differences, which need to be considered.
+
+scaling_cur_freq: This displays the real frequency which was used during
+the last sample period instead of what is requested. Some other cpufreq driver,
+like acpi-cpufreq, displays what is requested (Some changes are on the
+way to fix this for acpi-cpufreq driver). The same is true for frequencies
+displayed at /proc/cpuinfo.
+
+scaling_governor: This displays current active policy. Since each CPU has a
+cpufreq sysfs, it is possible to set a scaling governor to each CPU. But this
+is not possible with Intel P-States, as there is one common policy for all
+CPUs. Here, the last requested policy will be applicable to all CPUs. It is
+suggested that one use the cpupower utility to change policy to all CPUs at the
+same time.
+
+scaling_setspeed: This attribute can never be used with Intel P-State.
+
+scaling_max_freq/scaling_min_freq: This interface can be used similarly to
+the max_perf_pct/min_perf_pct of Intel P-State sysfs. However since frequencies
+are converted to nearest possible P-State, this is prone to rounding errors.
+This method is not preferred to limit performance.
+
+affected_cpus: Not used
+related_cpus: Not used
+
 For contemporary Intel processors, the frequency is controlled by the
-processor itself and the P-states exposed to software are related to
+processor itself and the P-State exposed to software is related to
 performance levels.  The idea that frequency can be set to a single
-frequency is fiction for Intel Core processors. Even if the scaling
-driver selects a single P state the actual frequency the processor
+frequency is fictional for Intel Core processors. Even if the scaling
+driver selects a single P-State, the actual frequency the processor
 will run at is selected by the processor itself.
 
-For legacy mode debugfs files have also been added to allow tuning of
-the internal governor algorythm. These files are located at
-/sys/kernel/debug/pstate_snb/ These files are NOT present in HWP mode.
+Tuning Intel P-State driver
+
+When HWP mode is not used, debugfs files have also been added to allow the
+tuning of the internal governor algorithm. These files are located at
+/sys/kernel/debug/pstate_snb/. The algorithm uses a PID (Proportional
+Integral Derivative) controller. The PID tunable parameters are:
 
       deadband
       d_gain_pct
@@ -63,3 +133,90 @@ the internal governor algorythm. These files are located at
       p_gain_pct
       sample_rate_ms
       setpoint
+
+To adjust these parameters, some understanding of driver implementation is
+necessary. There are some tweeks described here, but be very careful. Adjusting
+them requires expert level understanding of power and performance relationship.
+These limits are only useful when the "powersave" policy is active.
+
+-To make the system more responsive to load changes, sample_rate_ms can
+be adjusted  (current default is 10ms).
+-To make the system use higher performance, even if the load is lower, setpoint
+can be adjusted to a lower number. This will also lead to faster ramp up time
+to reach the maximum P-State.
+If there are no derivative and integral coefficients, The next P-State will be
+equal to:
+	current P-State - ((setpoint - current cpu load) * p_gain_pct)
+
+For example, if the current PID parameters are (Which are defaults for the core
+processors like SandyBridge):
+      deadband = 0
+      d_gain_pct = 0
+      i_gain_pct = 0
+      p_gain_pct = 20
+      sample_rate_ms = 10
+      setpoint = 97
+
+If the current P-State = 0x08 and current load = 100, this will result in the
+next P-State = 0x08 - ((97 - 100) * 0.2) = 8.6 (rounded to 9). Here the P-State
+goes up by only 1. If during next sample interval the current load doesn't
+change and still 100, then P-State goes up by one again. This process will
+continue as long as the load is more than the setpoint until the maximum P-State
+is reached.
+
+For the same load at setpoint = 60, this will result in the next P-State
+= 0x08 - ((60 - 100) * 0.2) = 16
+So by changing the setpoint from 97 to 60, there is an increase of the
+next P-State from 9 to 16. So this will make processor execute at higher
+P-State for the same CPU load. If the load continues to be more than the
+setpoint during next sample intervals, then P-State will go up again till the
+maximum P-State is reached. But the ramp up time to reach the maximum P-State
+will be much faster when the setpoint is 60 compared to 97.
+
+Debugging Intel P-State driver
+
+Event tracing
+To debug P-State transition, the Linux event tracing interface can be used.
+There are two specific events, which can be enabled (Provided the kernel
+configs related to event tracing are enabled).
+
+# cd /sys/kernel/debug/tracing/
+# echo 1 > events/power/pstate_sample/enable
+# echo 1 > events/power/cpu_frequency/enable
+# cat trace
+gnome-terminal--4510  [001] ..s.  1177.680733: pstate_sample: core_busy=107
+	scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618
+		freq=2474476
+cat-5235  [002] ..s.  1177.681723: cpu_frequency: state=2900000 cpu_id=2
+
+
+Using ftrace
+
+If function level tracing is required, the Linux ftrace interface can be used.
+For example if we want to check how often a function to set a P-State is
+called, we can set ftrace filter to intel_pstate_set_pstate.
+
+# cd /sys/kernel/debug/tracing/
+# cat available_filter_functions | grep -i pstate
+intel_pstate_set_pstate
+intel_pstate_cpu_init
+...
+
+# echo intel_pstate_set_pstate > set_ftrace_filter
+# echo function > current_tracer
+# cat trace | head -15
+# tracer: function
+#
+# entries-in-buffer/entries-written: 80/80   #P:4
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+            Xorg-3129  [000] ..s.  2537.644844: intel_pstate_set_pstate <-intel_pstate_timer_func
+ gnome-terminal--4510  [002] ..s.  2537.649844: intel_pstate_set_pstate <-intel_pstate_timer_func
+     gnome-shell-3409  [001] ..s.  2537.650850: intel_pstate_set_pstate <-intel_pstate_timer_func
+          <idle>-0     [000] ..s.  2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
index 9e3c3b33514c..0a94224ad296 100644
--- a/Documentation/cpu-freq/pcc-cpufreq.txt
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -159,8 +159,8 @@ to be strictly associated with a P-state.
 
 2.2 cpuinfo_transition_latency:
 -------------------------------
-The cpuinfo_transition_latency field is 0. The PCC specification does
-not include a field to expose this value currently.
+The cpuinfo_transition_latency field is CPUFREQ_ETERNAL. The PCC specification
+does not include a field to expose this value currently.
 
 2.3 cpuinfo_cur_freq:
 ---------------------
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index f9ad5e048b11..dd68821c22d4 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -150,7 +150,7 @@ an entry as shown below in the output.
 
 If this is not mounted, do the following.
 
-	 #mkdir /sysfs
+	#mkdir /sys
 	#mount -t sysfs sys /sys
 
 Now you should see entries for all present cpu, the following is an example
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
index e15bc1a0fb98..89fd8f9a259f 100644
--- a/Documentation/device-mapper/verity.txt
+++ b/Documentation/device-mapper/verity.txt
@@ -18,11 +18,11 @@ Construction Parameters
 
     0 is the original format used in the Chromium OS.
       The salt is appended when hashing, digests are stored continuously and
-      the rest of the block is padded with zeros.
+      the rest of the block is padded with zeroes.
 
     1 is the current format that should be used for new devices.
       The salt is prepended when hashing and each digest is
-      padded with zeros to the power of two.
+      padded with zeroes to the power of two.
 
 <dev>
     This is the device containing data, the integrity of which needs to be
@@ -79,6 +79,37 @@ restart_on_corruption
     not compatible with ignore_corruption and requires user space support to
     avoid restart loops.
 
+ignore_zero_blocks
+    Do not verify blocks that are expected to contain zeroes and always return
+    zeroes instead. This may be useful if the partition contains unused blocks
+    that are not guaranteed to contain zeroes.
+
+use_fec_from_device <fec_dev>
+    Use forward error correction (FEC) to recover from corruption if hash
+    verification fails. Use encoding data from the specified device. This
+    may be the same device where data and hash blocks reside, in which case
+    fec_start must be outside data and hash areas.
+
+    If the encoding data covers additional metadata, it must be accessible
+    on the hash device after the hash blocks.
+
+    Note: block sizes for data and hash devices must match. Also, if the
+    verity <dev> is encrypted the <fec_dev> should be too.
+
+fec_roots <num>
+    Number of generator roots. This equals to the number of parity bytes in
+    the encoding data. For example, in RS(M, N) encoding, the number of roots
+    is M-N.
+
+fec_blocks <num>
+    The number of encoding data blocks on the FEC device. The block size for
+    the FEC device is <data_block_size>.
+
+fec_start <offset>
+    This is the offset, in <data_block_size> blocks, from the start of the
+    FEC device to the beginning of the encoding data.
+
+
 Theory of operation
 ===================
 
@@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read
 into the page cache. Block hashes are stored linearly, aligned to the nearest
 block size.
 
+If forward error correction (FEC) support is enabled any recovery of
+corrupted data will be verified using the cryptographic hash of the
+corresponding data. This is why combining error correction with
+integrity checking is essential.
+
 Hash Tree
 ---------
 
diff --git a/Documentation/devicetree/bindings/arm/arm,scpi.txt b/Documentation/devicetree/bindings/arm/arm,scpi.txt
index 86302de67c2c..313dabdc14f9 100644
--- a/Documentation/devicetree/bindings/arm/arm,scpi.txt
+++ b/Documentation/devicetree/bindings/arm/arm,scpi.txt
@@ -63,7 +63,7 @@ Required properties:
 - compatible : should be "arm,juno-sram-ns" for Non-secure SRAM on Juno
 
 The rest of the properties should follow the generic mmio-sram description
-found in ../../misc/sysram.txt
+found in ../../sram/sram.txt
 
 Each sub-node represents the reserved area for SCPI.
 
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
index c78576bb7729..11d3056dc2bd 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
@@ -26,6 +26,10 @@ Raspberry Pi Model B+
 Required root node properties:
 compatible = "raspberrypi,model-b-plus", "brcm,bcm2835";
 
+Raspberry Pi 2 Model B
+Required root node properties:
+compatible = "raspberrypi,2-model-b", "brcm,bcm2836";
+
 Raspberry Pi Compute Module
 Required root node properties:
 compatible = "raspberrypi,compute-module", "brcm,bcm2835";
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.txt
index 6b0f49f6f499..8608a776caa7 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.txt
@@ -5,4 +5,11 @@ Boards with the BCM4708 SoC shall have the following properties:
 
 Required root node property:
 
+bcm4708
 compatible = "brcm,bcm4708";
+
+bcm4709
+compatible = "brcm,bcm4709";
+
+bcm53012
+compatible = "brcm,bcm53012";
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,nsp-cpu-method.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,nsp-cpu-method.txt
new file mode 100644
index 000000000000..677ef9d9f445
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,nsp-cpu-method.txt
@@ -0,0 +1,39 @@
+Broadcom Northstar Plus SoC CPU Enable Method
+---------------------------------------------
+This binding defines the enable method used for starting secondary
+CPU in the following Broadcom SoCs:
+  BCM58522, BCM58525, BCM58535, BCM58622, BCM58623, BCM58625, BCM88312
+
+The enable method is specified by defining the following required
+properties in the corresponding secondary "cpu" device tree node:
+  - enable-method = "brcm,bcm-nsp-smp";
+  - secondary-boot-reg = <...>;
+
+The secondary-boot-reg property is a u32 value that specifies the
+physical address of the register which should hold the common
+entry point for a secondary CPU. This entry is cpu node specific
+and should be added per cpu. E.g., in case of NSP (BCM58625) which
+is a dual core CPU SoC, this entry should be added to cpu1 node.
+
+
+Example:
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			next-level-cache = <&L2>;
+			reg = <0>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			next-level-cache = <&L2>;
+			enable-method = "brcm,bcm-nsp-smp";
+			secondary-boot-reg = <0xffff042c>;
+			reg = <1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/compulab-boards.txt b/Documentation/devicetree/bindings/arm/compulab-boards.txt
new file mode 100644
index 000000000000..42a10285af9c
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/compulab-boards.txt
@@ -0,0 +1,25 @@
+CompuLab SB-SOM is a multi-module baseboard capable of carrying:
+ - CM-T43
+ - CM-T54
+ - CM-QS600
+ - CL-SOM-AM57x
+ - CL-SOM-iMX7
+modules with minor modifications to the SB-SOM assembly.
+
+Required root node properties:
+    - compatible = should be "compulab,sb-som"
+
+Compulab CL-SOM-iMX7 is a miniature System-on-Module (SoM) based on
+Freescale i.MX7 ARM Cortex-A7 System-on-Chip.
+
+Required root node properties:
+    - compatible = "compulab,cl-som-imx7", "fsl,imx7d";
+
+Compulab SBC-iMX7 is a single board computer based on the
+Freescale i.MX7 system-on-chip. SBC-iMX7 is implemented with
+the CL-SOM-iMX7 System-on-Module providing most of the functions,
+and SB-SOM-iMX7 carrier board providing additional peripheral
+functions and connectors.
+
+Required root node properties:
+    - compatible = "compulab,sbc-imx7", "compulab,cl-som-imx7", "fsl,imx7d";
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
index 3a07a87fef20..ae9be074d09f 100644
--- a/Documentation/devicetree/bindings/arm/cpus.txt
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -157,6 +157,7 @@ nodes to be present and contain the properties described below.
 			    "arm,cortex-a17"
 			    "arm,cortex-a53"
 			    "arm,cortex-a57"
+			    "arm,cortex-a72"
 			    "arm,cortex-m0"
 			    "arm,cortex-m0+"
 			    "arm,cortex-m1"
@@ -190,6 +191,8 @@ nodes to be present and contain the properties described below.
 			    "allwinner,sun6i-a31"
 			    "allwinner,sun8i-a23"
 			    "arm,psci"
+			    "arm,realview-smp"
+			    "brcm,bcm-nsp-smp"
 			    "brcm,brahma-b15"
 			    "marvell,armada-375-smp"
 			    "marvell,armada-380-smp"
@@ -200,6 +203,7 @@ nodes to be present and contain the properties described below.
 			    "qcom,gcc-msm8660"
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
+			    "rockchip,rk3036-smp"
 			    "rockchip,rk3066-smp"
 			    "ste,dbx500-smp"
 
@@ -242,6 +246,23 @@ nodes to be present and contain the properties described below.
 		Definition: Specifies the syscon node controlling the cpu core
 			    power domains.
 
+	- dynamic-power-coefficient
+		Usage: optional
+		Value type: <prop-encoded-array>
+		Definition: A u32 value that represents the running time dynamic
+			    power coefficient in units of mW/MHz/uVolt^2. The
+			    coefficient can either be calculated from power
+			    measurements or derived by analysis.
+
+			    The dynamic power consumption of the CPU  is
+			    proportional to the square of the Voltage (V) and
+			    the clock frequency (f). The coefficient is used to
+			    calculate the dynamic power as below -
+
+			    Pdyn = dynamic-power-coefficient * V^2 * f
+
+			    where voltage is in uV, frequency is in MHz.
+
 Example 1 (dual-cluster big.LITTLE system 32-bit):
 
 	cpus {
diff --git a/Documentation/devicetree/bindings/arm/fsl.txt b/Documentation/devicetree/bindings/arm/fsl.txt
index 34c88b0c7ab4..752a685d926f 100644
--- a/Documentation/devicetree/bindings/arm/fsl.txt
+++ b/Documentation/devicetree/bindings/arm/fsl.txt
@@ -131,6 +131,10 @@ Example:
 Freescale ARMv8 based Layerscape SoC family Device Tree Bindings
 ----------------------------------------------------------------
 
+LS1043A ARMv8 based RDB Board
+Required root node properties:
+    - compatible = "fsl,ls1043a-rdb", "fsl,ls1043a";
+
 LS2080A ARMv8 based Simulator model
 Required root node properties:
     - compatible = "fsl,ls2080a-simu", "fsl,ls2080a";
diff --git a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
index 6ac7c000af22..e3ccab114006 100644
--- a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+++ b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
@@ -187,6 +187,22 @@ Example:
 		reg = <0xb0000000 0x10000>;
 	};
 
+Hisilicon HiP05 PERISUB system controller
+
+Required properties:
+- compatible : "hisilicon,hip05-perisubc", "syscon";
+- reg : Register address and size
+
+The HiP05 PERISUB system controller is shared by peripheral controllers in
+HiP05 Soc to implement some basic configurations. The peripheral
+controllers include mdio, ddr, iic, uart, timer and so on.
+
+Example:
+	/* for HiP05 perisub-ctrl-c system */
+	peri_c_subctrl: syscon@80000000 {
+		compatible = "hisilicon,hip05-perisubc", "syscon";
+		reg = <0x0 0x80000000 0x0 0x10000>;
+	};
 -----------------------------------------------------------------------
 Hisilicon CPU controller
 
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2c2x0.txt
index 06c88a4d28ac..fe0398c5c77b 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2c2x0.txt
@@ -1,7 +1,8 @@
 * ARM L2 Cache Controller
 
-ARM cores often have a separate level 2 cache controller. There are various
-implementations of the L2 cache controller with compatible programming models.
+ARM cores often have a separate L2C210/L2C220/L2C310 (also known as PL210/PL220/
+PL310 and variants) based level 2 cache controller. All these various implementations
+of the L2 cache controller have compatible programming models (Note 1).
 Some of the properties that are just prefixed "cache-*" are taken from section
 3.7.3 of the ePAPR v1.1 specification which can be found at:
 https://www.power.org/wp-content/uploads/2012/06/Power_ePAPR_APPROVED_v1.1.pdf
@@ -67,12 +68,17 @@ Optional properties:
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
-- arm,shared-override : The default behavior of the pl310 cache controller with
-  respect to the shareable attribute is to transform "normal memory
-  non-cacheable transactions" into "cacheable no allocate" (for reads) or
-  "write through no write allocate" (for writes).
+- arm,shared-override : The default behavior of the L220 or PL310 cache
+  controllers with respect to the shareable attribute is to transform "normal
+  memory non-cacheable transactions" into "cacheable no allocate" (for reads)
+  or "write through no write allocate" (for writes).
   On systems where this may cause DMA buffer corruption, this property must be
   specified to indicate that such transforms are precluded.
+- arm,parity-enable : enable parity checking on the L2 cache (L220 or PL310).
+- arm,parity-disable : disable parity checking on the L2 cache (L220 or PL310).
+- arm,outer-sync-disable : disable the outer sync operation on the L2 cache.
+  Some core tiles, especially ARM PB11MPCore have a faulty L220 cache that
+  will randomly hang unless outer sync operations are disabled.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
@@ -91,3 +97,9 @@ L2: cache-controller {
         cache-level = <2>;
 	interrupts = <45>;
 };
+
+Note 1: The description in this document doesn't apply to integrated L2
+	cache controllers as found in e.g. Cortex-A15/A7/A57/A53. These
+	integrated L2 controllers are assumed to be all preconfigured by
+	early secure boot code. Thus no need to deal with their configuration
+	in the kernel at all.
diff --git a/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt b/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
index 5171ad8f48ff..ab0c9cdf388e 100644
--- a/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
+++ b/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
@@ -24,6 +24,8 @@ board. Currently known boards are:
 "buffalo,lswxl"
 "buffalo,lsxhl"
 "buffalo,lsxl"
+"cloudengines,pogo02"
+"cloudengines,pogoplugv4"
 "dlink,dns-320"
 "dlink,dns-320-a1"
 "dlink,dns-325"
diff --git a/Documentation/devicetree/bindings/arm/mediatek.txt b/Documentation/devicetree/bindings/arm/mediatek.txt
index 618a91994a18..54f43bc2df44 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek.txt
@@ -6,6 +6,7 @@ following property:
 Required root node property:
 
 compatible: Must contain one of
+   "mediatek,mt2701"
    "mediatek,mt6580"
    "mediatek,mt6589"
    "mediatek,mt6592"
@@ -17,6 +18,9 @@ compatible: Must contain one of
 
 Supported boards:
 
+- Evaluation board for MT2701:
+    Required root node properties:
+      - compatible = "mediatek,mt2701-evb", "mediatek,mt2701";
 - Evaluation board for MT6580:
     Required root node properties:
       - compatible = "mediatek,mt6580-evbp1", "mediatek,mt6580";
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
index f6cd3e4192ff..aaf8d1460c4d 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
@@ -18,7 +18,7 @@ The available clocks are defined in dt-bindings/clock/mt*-clk.h.
 Also it uses the common reset controller binding from
 Documentation/devicetree/bindings/reset/reset.txt.
 The available reset outputs are defined in
-dt-bindings/reset-controller/mt*-resets.h
+dt-bindings/reset/mt*-resets.h
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt
index f25b85499a6f..2f6ff86df49f 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt
@@ -18,7 +18,7 @@ The available clocks are defined in dt-bindings/clock/mt*-clk.h.
 Also it uses the common reset controller binding from
 Documentation/devicetree/bindings/reset/reset.txt.
 The available reset outputs are defined in
-dt-bindings/reset-controller/mt*-resets.h
+dt-bindings/reset/mt*-resets.h
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 9f4e5136e568..66422d663184 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -23,6 +23,7 @@ Optional properties:
   during suspend.
 - ti,no-reset-on-init: When present, the module should not be reset at init
 - ti,no-idle-on-init: When present, the module should not be idled at init
+- ti,no-idle: When present, the module is never allowed to idle.
 
 Example:
 
@@ -138,9 +139,21 @@ Boards:
 - AM335X phyBOARD-WEGA: Single Board Computer dev kit
   compatible = "phytec,am335x-wega", "phytec,am335x-phycore-som", "ti,am33xx"
 
+- AM335X CM-T335 : System On Module, built around the Sitara AM3352/4
+  compatible = "compulab,cm-t335", "ti,am33xx"
+
+- AM335X SBC-T335 : single board computer, built around the Sitara AM3352/4
+  compatible = "compulab,sbc-t335", "compulab,cm-t335", "ti,am33xx"
+
 - OMAP5 EVM : Evaluation Module
   compatible = "ti,omap5-evm", "ti,omap5"
 
+- AM437x CM-T43
+  compatible = "compulab,am437x-cm-t43", "ti,am4372", "ti,am43"
+
+- AM437x SBC-T43
+  compatible = "compulab,am437x-sbc-t43", "compulab,am437x-cm-t43", "ti,am4372", "ti,am43"
+
 - AM43x EPOS EVM
   compatible = "ti,am43x-epos-evm", "ti,am4372", "ti,am43"
 
@@ -150,6 +163,12 @@ Boards:
 - AM437x SK EVM: AM437x StarterKit Evaluation Module
   compatible = "ti,am437x-sk-evm", "ti,am4372", "ti,am43"
 
+- AM57XX CL-SOM-AM57x
+  compatible = "compulab,cl-som-am57x", "ti,am5728", "ti,dra742", "ti,dra74", "ti,dra7"
+
+- AM57XX SBC-AM57x
+  compatible = "compulab,sbc-am57x", "compulab,cl-som-am57x", "ti,am5728", "ti,dra742", "ti,dra74", "ti,dra7"
+
 - DRA742 EVM:  Software Development Board for DRA742
   compatible = "ti,dra7-evm", "ti,dra742", "ti,dra74", "ti,dra7"
 
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 97ba45af04fc..56518839f52a 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -9,8 +9,9 @@ Required properties:
 - compatible : should be one of
 	"apm,potenza-pmu"
 	"arm,armv8-pmuv3"
-	"arm.cortex-a57-pmu"
-	"arm.cortex-a53-pmu"
+	"arm,cortex-a72-pmu"
+	"arm,cortex-a57-pmu"
+	"arm,cortex-a53-pmu"
 	"arm,cortex-a17-pmu"
 	"arm,cortex-a15-pmu"
 	"arm,cortex-a12-pmu"
diff --git a/Documentation/devicetree/bindings/arm/psci.txt b/Documentation/devicetree/bindings/arm/psci.txt
index a9adab84e2fe..a2c4f1d52492 100644
--- a/Documentation/devicetree/bindings/arm/psci.txt
+++ b/Documentation/devicetree/bindings/arm/psci.txt
@@ -23,17 +23,20 @@ Main node required properties:
 
  - compatible    : should contain at least one of:
 
-				 * "arm,psci" : for implementations complying to PSCI versions prior to
-					0.2. For these cases function IDs must be provided.
-
-				 * "arm,psci-0.2" : for implementations complying to PSCI 0.2. Function
-					IDs are not required and should be ignored by an OS with PSCI 0.2
-					support, but are permitted to be present for compatibility with
-					existing software when "arm,psci" is later in the compatible list.
-
-				* "arm,psci-1.0" : for implementations complying to PSCI 1.0. PSCI 1.0 is
-					backward compatible with PSCI 0.2 with minor specification updates,
-					as defined in the PSCI specification[2].
+     * "arm,psci"     : For implementations complying to PSCI versions prior
+			to 0.2.
+			For these cases function IDs must be provided.
+
+     * "arm,psci-0.2" : For implementations complying to PSCI 0.2.
+			Function IDs are not required and should be ignored by
+			an OS with PSCI 0.2 support, but are permitted to be
+			present for compatibility with existing software when
+			"arm,psci" is later in the compatible list.
+
+     * "arm,psci-1.0" : For implementations complying to PSCI 1.0.
+			PSCI 1.0 is backward compatible with PSCI 0.2 with
+			minor specification updates, as defined in the PSCI
+			specification[2].
 
  - method        : The method of calling the PSCI firmware. Permitted
                    values are:
diff --git a/Documentation/devicetree/bindings/arm/rockchip.txt b/Documentation/devicetree/bindings/arm/rockchip.txt
index 8e985dd2f181..078c14fcdaaa 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.txt
+++ b/Documentation/devicetree/bindings/arm/rockchip.txt
@@ -1,6 +1,10 @@
 Rockchip platforms device tree bindings
 ---------------------------------------
 
+- Kylin RK3036 board:
+    Required root node properties:
+      - compatible = "rockchip,kylin-rk3036", "rockchip,rk3036";
+
 - MarsBoard RK3066 board:
     Required root node properties:
       - compatible = "haoyu,marsboard-rk3066", "rockchip,rk3066a";
@@ -35,6 +39,11 @@ Rockchip platforms device tree bindings
     Required root node properties:
       - compatible = "netxeon,r89", "rockchip,rk3288";
 
+- Google Brain (dev-board):
+    Required root node properties:
+      - compatible = "google,veyron-brain-rev0", "google,veyron-brain",
+		     "google,veyron", "rockchip,rk3288";
+
 - Google Jaq (Haier Chromebook 11 and more):
     Required root node properties:
       - compatible = "google,veyron-jaq-rev5", "google,veyron-jaq-rev4",
@@ -49,6 +58,15 @@ Rockchip platforms device tree bindings
 		     "google,veyron-jerry-rev3", "google,veyron-jerry",
 		     "google,veyron", "rockchip,rk3288";
 
+- Google Mickey (Asus Chromebit CS10):
+    Required root node properties:
+      - compatible = "google,veyron-mickey-rev8", "google,veyron-mickey-rev7",
+		     "google,veyron-mickey-rev6", "google,veyron-mickey-rev5",
+		     "google,veyron-mickey-rev4", "google,veyron-mickey-rev3",
+		     "google,veyron-mickey-rev2", "google,veyron-mickey-rev1",
+		     "google,veyron-mickey-rev0", "google,veyron-mickey",
+		     "google,veyron", "rockchip,rk3288";
+
 - Google Minnie (Asus Chromebook Flip C100P):
     Required root node properties:
       - compatible = "google,veyron-minnie-rev4", "google,veyron-minnie-rev3",
@@ -69,6 +87,14 @@ Rockchip platforms device tree bindings
 		     "google,veyron-speedy-rev3", "google,veyron-speedy-rev2",
 		     "google,veyron-speedy", "google,veyron", "rockchip,rk3288";
 
+- Rockchip RK3368 evb:
+    Required root node properties:
+      - compatible = "rockchip,rk3368-evb-act8846", "rockchip,rk3368";
+
 - Rockchip R88 board:
     Required root node properties:
       - compatible = "rockchip,r88", "rockchip,rk3368";
+
+- Rockchip RK3228 Evaluation board:
+    Required root node properties:
+      - compatible = "rockchip,rk3228-evb", "rockchip,rk3228";
diff --git a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
index f46ca9a316a2..ccaaec6014bd 100644
--- a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
@@ -47,6 +47,9 @@ Required properties:
 
 - samsung,syscon-phandle Contains the PMU system controller node
 			(To access the ADC_PHY register on Exynos5250/5420/5800/3250)
+Optional properties:
+- has-touchscreen:	If present, indicates that a touchscreen is
+			connected an usable.
 
 Note: child nodes can be added for auto probing from device tree.
 
diff --git a/Documentation/devicetree/bindings/arm/scu.txt b/Documentation/devicetree/bindings/arm/scu.txt
index c447680519bb..08a587875996 100644
--- a/Documentation/devicetree/bindings/arm/scu.txt
+++ b/Documentation/devicetree/bindings/arm/scu.txt
@@ -10,10 +10,13 @@ References:
   Revision r2p0
 - Cortex-A5: see DDI0434B Cortex-A5 MPCore Technical Reference Manual
   Revision r0p1
+- ARM11 MPCore: see DDI0360F ARM 11 MPCore Processor Technical Reference
+  Manial Revision r2p0
 
 - compatible : Should be:
 	"arm,cortex-a9-scu"
 	"arm,cortex-a5-scu"
+	"arm,arm11mp-scu"
 
 - reg : Specify the base address and the size of the SCU register window.
 
diff --git a/Documentation/devicetree/bindings/arm/secure.txt b/Documentation/devicetree/bindings/arm/secure.txt
new file mode 100644
index 000000000000..e31303fb233a
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/secure.txt
@@ -0,0 +1,53 @@
+* ARM Secure world bindings
+
+ARM CPUs with TrustZone support have two distinct address spaces,
+"Normal" and "Secure". Most devicetree consumers (including the Linux
+kernel) are not TrustZone aware and run entirely in either the Normal
+world or the Secure world. However some devicetree consumers are
+TrustZone aware and need to be able to determine whether devices are
+visible only in the Secure address space, only in the Normal address
+space, or visible in both. (One example of that situation would be a
+virtual machine which boots Secure firmware and wants to tell the
+firmware about the layout of the machine via devicetree.)
+
+The general principle of the naming scheme for Secure world bindings
+is that any property that needs a different value in the Secure world
+can be supported by prefixing the property name with "secure-". So for
+instance "secure-foo" would override "foo". For property names with
+a vendor prefix, the Secure variant of "vendor,foo" would be
+"vendor,secure-foo". If there is no "secure-" property then the Secure
+world value is the same as specified for the Normal world by the
+non-prefixed property. However, only the properties listed below may
+validly have "secure-" versions; this list will be enlarged on a
+case-by-case basis.
+
+Defining the bindings in this way means that a device tree which has
+been annotated to indicate the presence of Secure-only devices can
+still be processed unmodified by existing Non-secure software (and in
+particular by the kernel).
+
+Note that it is still valid for bindings intended for purely Secure
+world consumers (like kernels that run entirely in Secure) to simply
+describe the view of Secure world using the standard bindings. These
+secure- bindings only need to be used where both the Secure and Normal
+world views need to be described in a single device tree.
+
+Valid Secure world properties:
+
+- secure-status : specifies whether the device is present and usable
+  in the secure world. The combination of this with "status" allows
+  the various possible combinations of device visibility to be
+  specified. If "secure-status" is not specified it defaults to the
+  same value as "status"; if "status" is not specified either then
+  both default to "okay". This means the following combinations are
+  possible:
+
+   /* Neither specified: default to visible in both S and NS */
+   secure-status = "okay";                          /* visible in both */
+   status = "okay";                                 /* visible in both */
+   status = "okay"; secure-status = "okay";         /* visible in both */
+   secure-status = "disabled";                      /* NS-only */
+   status = "okay"; secure-status = "disabled";     /* NS-only */
+   status = "disabled"; secure-status = "okay";     /* S-only */
+   status = "disabled";                             /* disabled in both */
+   status = "disabled"; secure-status = "disabled"; /* disabled in both */
diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt
index 40bb9007cd0d..9cf67e48f222 100644
--- a/Documentation/devicetree/bindings/arm/shmobile.txt
+++ b/Documentation/devicetree/bindings/arm/shmobile.txt
@@ -27,6 +27,8 @@ SoCs:
     compatible = "renesas,r8a7793"
   - R-Car E2 (R8A77940)
     compatible = "renesas,r8a7794"
+  - R-Car H3 (R8A77950)
+    compatible = "renesas,r8a7795"
 
 
 Boards:
@@ -57,5 +59,7 @@ Boards:
     compatible = "renesas,marzen", "renesas,r8a7779"
   - Porter (M2-LCDP)
     compatible = "renesas,porter", "renesas,r8a7791"
+  - Salvator-X (RTP0RC7795SIPB0010S)
+    compatible = "renesas,salvator-x", "renesas,r8a7795";
   - SILK (RTP0RC7794LCB00011S)
     compatible = "renesas,silk", "renesas,r8a7794"
diff --git a/Documentation/devicetree/bindings/arm/technologic.txt b/Documentation/devicetree/bindings/arm/technologic.txt
new file mode 100644
index 000000000000..842298894cf0
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/technologic.txt
@@ -0,0 +1,6 @@
+Technologic Systems Platforms Device Tree Bindings
+--------------------------------------------------
+
+TS-4800 board
+Required root node properties:
+	- compatible = "technologic,imx51-ts4800", "fsl,imx51";
diff --git a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt b/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
index 20ac9bbfa1fd..60872838f1ad 100644
--- a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
+++ b/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
@@ -4,7 +4,9 @@ SATA nodes are defined to describe on-chip Serial ATA controllers.
 Each SATA controller should have its own node.
 
 Required properties:
-- compatible         : compatible list, may contain "brcm,bcm7445-ahci" and/or
+- compatible         : should be one or more of
+                       "brcm,bcm7425-ahci"
+                       "brcm,bcm7445-ahci"
                        "brcm,sata3-ahci"
 - reg                : register mappings for AHCI and SATA_TOP_CTRL
 - reg-names          : "ahci" and "top-ctrl"
diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt
index 2493a5a31655..0764f9ab63dc 100644
--- a/Documentation/devicetree/bindings/ata/sata_rcar.txt
+++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt
@@ -8,6 +8,7 @@ Required properties:
 			  - "renesas,sata-r8a7790" for R-Car H2 other than ES1
 			  - "renesas,sata-r8a7791" for R-Car M2-W
 			  - "renesas,sata-r8a7793" for R-Car M2-N
+			  - "renesas,sata-r8a7795" for R-Car H3
 - reg			: address and length of the SATA registers;
 - interrupts		: must consist of one interrupt specifier.
 - clocks		: must contain a reference to the functional clock.
diff --git a/Documentation/devicetree/bindings/bus/uniphier-system-bus.txt b/Documentation/devicetree/bindings/bus/uniphier-system-bus.txt
new file mode 100644
index 000000000000..68ef80afff16
--- /dev/null
+++ b/Documentation/devicetree/bindings/bus/uniphier-system-bus.txt
@@ -0,0 +1,66 @@
+UniPhier System Bus
+
+The UniPhier System Bus is an external bus that connects on-board devices to
+the UniPhier SoC.  It is a simple (semi-)parallel bus with address, data, and
+some control signals.  It supports up to 8 banks (chip selects).
+
+Before any access to the bus, the bus controller must be configured; the bus
+controller registers provide the control for the translation from the offset
+within each bank to the CPU-viewed address.  The needed setup includes the base
+address, the size of each bank.  Optionally, some timing parameters can be
+optimized for faster bus access.
+
+Required properties:
+- compatible: should be "socionext,uniphier-system-bus".
+- reg: offset and length of the register set for the bus controller device.
+- #address-cells: should be 2.  The first cell is the bank number (chip select).
+  The second cell is the address offset within the bank.
+- #size-cells: should be 1.
+- ranges: should provide a proper address translation from the System Bus to
+  the parent bus.
+
+Note:
+The address region(s) that can be assigned for the System Bus is implementation
+defined.  Some SoCs can use 0x00000000-0x0fffffff and 0x40000000-0x4fffffff,
+while other SoCs can only use 0x40000000-0x4fffffff.  There might be additional
+limitations depending on SoCs and the boot mode.  The address translation is
+arbitrary as long as the banks are assigned in the supported address space with
+the required alignment and they do not overlap one another.
+For example, it is possible to map:
+  bank 0 to 0x42000000-0x43ffffff, bank 5 to 0x46000000-0x46ffffff
+It is also possible to map:
+  bank 0 to 0x48000000-0x49ffffff, bank 5 to 0x44000000-0x44ffffff
+There is no reason to stick to a particular translation mapping, but the
+"ranges" property should provide a "reasonable" default that is known to work.
+The software should initialize the bus controller according to it.
+
+Example:
+
+	system-bus {
+		compatible = "socionext,uniphier-system-bus";
+		reg = <0x58c00000 0x400>;
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <1 0x00000000 0x42000000 0x02000000
+			  5 0x00000000 0x46000000 0x01000000>;
+
+		ethernet@1,01f00000 {
+			compatible = "smsc,lan9115";
+			reg = <1 0x01f00000 0x1000>;
+			interrupts = <0 48 4>
+			phy-mode = "mii";
+		};
+
+		uart@5,00200000 {
+			compatible = "ns16550a";
+			reg = <5 0x00200000 0x20>;
+			interrupts = <0 49 4>
+			clock-frequency = <12288000>;
+		};
+	};
+
+In this example,
+ - the Ethernet device is connected at the offset 0x01f00000 of CS1 and
+   mapped to 0x43f00000 of the parent bus.
+ - the UART device is connected at the offset 0x00200000 of CS5 and
+   mapped to 0x46200000 of the parent bus.
diff --git a/Documentation/devicetree/bindings/clock/arm-syscon-icst.txt b/Documentation/devicetree/bindings/clock/arm-syscon-icst.txt
new file mode 100644
index 000000000000..8b7177cecb36
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/arm-syscon-icst.txt
@@ -0,0 +1,40 @@
+ARM System Controller ICST clocks
+
+The ICS525 and ICS307 oscillators are produced by Integrated Devices
+Technology (IDT). ARM integrated these oscillators deeply into their
+reference designs by adding special control registers that manage such
+oscillators to their system controllers.
+
+The ARM system controller contains logic to serialize and initialize
+an ICST clock request after a write to the 32 bit register at an offset
+into the system controller. Furthermore, to even be able to alter one of
+these frequencies, the system controller must first be unlocked by
+writing a special token to another offset in the system controller.
+
+The ICST oscillator must be provided inside a system controller node.
+
+Required properties:
+- lock-offset: the offset address into the system controller where the
+  unlocking register is located
+- vco-offset: the offset address into the system controller where the
+  ICST control register is located (even 32 bit address)
+- compatible: must be one of "arm,syscon-icst525" or "arm,syscon-icst307"
+- #clock-cells: must be <0>
+- clocks: parent clock, since the ICST needs a parent clock to derive its
+  frequency from, this attribute is compulsory.
+
+Example:
+
+syscon: syscon@10000000 {
+	compatible = "syscon";
+	reg = <0x10000000 0x1000>;
+
+	oscclk0: osc0@0c {
+		compatible = "arm,syscon-icst307";
+		#clock-cells = <0>;
+		lock-offset = <0x20>;
+		vco-offset = <0x0c>;
+		clocks = <&xtal24mhz>;
+	};
+	(...)
+};
diff --git a/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt b/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt
new file mode 100644
index 000000000000..7a837d2182ac
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt
@@ -0,0 +1,31 @@
+Broadcom BCM2835 auxiliary peripheral support
+
+This binding uses the common clock binding:
+    Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The auxiliary peripherals (UART, SPI1, and SPI2) have a small register
+area controlling clock gating to the peripherals, and providing an IRQ
+status register.
+
+Required properties:
+- compatible:	Should be "brcm,bcm2835-aux"
+- #clock-cells:	Should be <1>. The permitted clock-specifier values can be
+		  found in include/dt-bindings/clock/bcm2835-aux.h
+- reg:		Specifies base physical address and size of the registers
+- clocks:	The parent clock phandle
+
+Example:
+
+	clocks: cprman@7e101000 {
+		compatible = "brcm,bcm2835-cprman";
+		#clock-cells = <1>;
+		reg = <0x7e101000 0x2000>;
+		clocks = <&clk_osc>;
+	};
+
+	aux: aux@0x7e215004 {
+		compatible = "brcm,bcm2835-aux";
+		#clock-cells = <1>;
+		reg = <0x7e215000 0x8>;
+		clocks = <&clocks BCM2835_CLOCK_VPU>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt
index ede65a55e21b..0b35e71b39e8 100644
--- a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt
@@ -208,3 +208,8 @@ These clock IDs are defined in:
     ch3_unused	lcpll_ports	4	BCM_NS2_LCPLL_PORTS_CH3_UNUSED
     ch4_unused	lcpll_ports	5	BCM_NS2_LCPLL_PORTS_CH4_UNUSED
     ch5_unused	lcpll_ports	6	BCM_NS2_LCPLL_PORTS_CH5_UNUSED
+
+BCM63138
+--------
+PLL and leaf clock compatible strings for BCM63138 are:
+    "brcm,bcm63138-armpll"
diff --git a/Documentation/devicetree/bindings/clock/cs2000-cp.txt b/Documentation/devicetree/bindings/clock/cs2000-cp.txt
new file mode 100644
index 000000000000..54e6df0bee8a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/cs2000-cp.txt
@@ -0,0 +1,22 @@
+CIRRUS LOGIC Fractional-N Clock Synthesizer & Clock Multiplier
+
+Required properties:
+
+- compatible:		"cirrus,cs2000-cp"
+- reg:			The chip select number on the I2C bus
+- clocks:		common clock binding for CLK_IN, XTI/REF_CLK
+- clock-names:		CLK_IN : clk_in, XTI/REF_CLK : ref_clk
+- #clock-cells:		must be <0>
+
+Example:
+
+&i2c2 {
+	...
+	cs2000: clk_multiplier@4f {
+		#clock-cells = <0>;
+		compatible = "cirrus,cs2000-cp";
+		reg = <0x4f>;
+		clocks = <&rcar_sound 0>, <&x12_clk>;
+		clock-names = "clk_in", "ref_clk";
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/dove-divider-clock.txt b/Documentation/devicetree/bindings/clock/dove-divider-clock.txt
new file mode 100644
index 000000000000..e3eb0f657c5e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/dove-divider-clock.txt
@@ -0,0 +1,28 @@
+PLL divider based Dove clocks
+
+Marvell Dove has a 2GHz PLL, which feeds into a set of dividers to provide
+high speed clocks for a number of peripherals.  These dividers are part of
+the PMU, and thus this node should be a child of the PMU node.
+
+The following clocks are provided:
+
+ID	Clock
+-------------
+0	AXI bus clock
+1	GPU clock
+2	VMeta clock
+3	LCD clock
+
+Required properties:
+- compatible : shall be "marvell,dove-divider-clock"
+- reg : shall be the register address of the Core PLL and Clock Divider
+   Control 0 register.  This will cover that register, as well as the
+   Core PLL and Clock Divider Control 1 register.  Thus, it will have
+   a size of 8.
+- #clock-cells : from common clock binding; shall be set to 1
+
+divider_clk: core-clock@0064 {
+	compatible = "marvell,dove-divider-clock";
+	reg = <0x0064 0x8>;
+	#clock-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/clock/nvidia,tegra210-car.txt b/Documentation/devicetree/bindings/clock/nvidia,tegra210-car.txt
new file mode 100644
index 000000000000..26f237f641b7
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/nvidia,tegra210-car.txt
@@ -0,0 +1,56 @@
+NVIDIA Tegra210 Clock And Reset Controller
+
+This binding uses the common clock binding:
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The CAR (Clock And Reset) Controller on Tegra is the HW module responsible
+for muxing and gating Tegra's clocks, and setting their rates.
+
+Required properties :
+- compatible : Should be "nvidia,tegra210-car"
+- reg : Should contain CAR registers location and length
+- clocks : Should contain phandle and clock specifiers for two clocks:
+  the 32 KHz "32k_in".
+- #clock-cells : Should be 1.
+  In clock consumers, this cell represents the clock ID exposed by the
+  CAR. The assignments may be found in header file
+  <dt-bindings/clock/tegra210-car.h>.
+- #reset-cells : Should be 1.
+  In clock consumers, this cell represents the bit number in the CAR's
+  array of CLK_RST_CONTROLLER_RST_DEVICES_* registers.
+
+Example SoC include file:
+
+/ {
+	tegra_car: clock {
+		compatible = "nvidia,tegra210-car";
+		reg = <0x60006000 0x1000>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+	usb@c5004000 {
+		clocks = <&tegra_car TEGRA210_CLK_USB2>;
+	};
+};
+
+Example board file:
+
+/ {
+	clocks {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		clk_32k: clock@1 {
+			compatible = "fixed-clock";
+			reg = <1>;
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+	};
+
+	&tegra_car {
+		clocks = <&clk_32k>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/nxp,lpc3220-clk.txt b/Documentation/devicetree/bindings/clock/nxp,lpc3220-clk.txt
new file mode 100644
index 000000000000..20cbca3f41d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/nxp,lpc3220-clk.txt
@@ -0,0 +1,30 @@
+NXP LPC32xx Clock Controller
+
+Required properties:
+- compatible: should be "nxp,lpc3220-clk"
+- reg:  should contain clock controller registers location and length
+- #clock-cells: must be 1, the cell holds id of a clock provided by the
+  clock controller
+- clocks: phandles of external oscillators, the list must contain one
+  32768 Hz oscillator and may have one optional high frequency oscillator
+- clock-names: list of external oscillator clock names, must contain
+  "xtal_32k" and may have optional "xtal"
+
+Examples:
+
+	/* System Control Block */
+	scb {
+		compatible = "simple-bus";
+		ranges = <0x0 0x040004000 0x00001000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		clk: clock-controller@0 {
+			compatible = "nxp,lpc3220-clk";
+			reg = <0x00 0x114>;
+			#clock-cells = <1>;
+
+			clocks = <&xtal_32k>, <&xtal>;
+			clock-names = "xtal_32k", "xtal";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/clock/nxp,lpc3220-usb-clk.txt b/Documentation/devicetree/bindings/clock/nxp,lpc3220-usb-clk.txt
new file mode 100644
index 000000000000..0aa249409b51
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/nxp,lpc3220-usb-clk.txt
@@ -0,0 +1,22 @@
+NXP LPC32xx USB Clock Controller
+
+Required properties:
+- compatible: should be "nxp,lpc3220-usb-clk"
+- reg:  should contain clock controller registers location and length
+- #clock-cells: must be 1, the cell holds id of a clock provided by the
+  USB clock controller
+
+Examples:
+
+	usb {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0x0 0x31020000 0x00001000>;
+
+		usbclk: clock-controller@f00 {
+			compatible = "nxp,lpc3220-usb-clk";
+			reg = <0xf00 0x100>;
+			#clock-cells = <1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc.txt b/Documentation/devicetree/bindings/clock/qcom,gcc.txt
index 152dfaab2575..72f82f444091 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc.txt
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc.txt
@@ -13,6 +13,7 @@ Required properties :
 			"qcom,gcc-msm8974"
 			"qcom,gcc-msm8974pro"
 			"qcom,gcc-msm8974pro-ac"
+			"qcom,gcc-msm8996"
 
 - reg : shall contain base register location and length
 - #clock-cells : shall contain 1
diff --git a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt b/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
index 34e7614d5074..8b0f7841af8d 100644
--- a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
+++ b/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
@@ -9,6 +9,7 @@ Required properties :
 			"qcom,mmcc-msm8660"
 			"qcom,mmcc-msm8960"
 			"qcom,mmcc-msm8974"
+			"qcom,mmcc-msm8996"
 
 - reg : shall contain base register location and length
 - #clock-cells : shall contain 1
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
index 38dcf0370143..ae36ab842919 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
@@ -20,6 +20,10 @@ Required Properties:
     clocks must be specified.  For clocks with multiple parents, invalid
     settings must be specified as "<0>".
   - #clock-cells: Must be 0
+
+
+Optional Properties:
+
   - clock-output-names: The name of the clock as a free-form string
 
 
diff --git a/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt b/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt
index 36c2b528245c..399e0da22348 100644
--- a/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt
@@ -2,7 +2,7 @@
 
 Required Properties:
 
-  - compatible: Must be "renesas,sh73a0-h8300-div-clock"
+  - compatible: Must be "renesas,h8300-div-clock"
 
   - clocks: Reference to the parent clocks ("extal1" and "extal2")
 
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
new file mode 100644
index 000000000000..20df350b9ef3
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
@@ -0,0 +1,56 @@
+* Rockchip RK3036 Clock and Reset Unit
+
+The RK3036 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: should be "rockchip,rk3036-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing pll rates are not changeable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/rk3036-cru.h headers and can be
+used in device tree sources. Similar macros exist for the reset sources in
+these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "ext_i2s" - external I2S clock - optional,
+ - "rmii_clkin" - external EMAC clock - optional
+
+Example: Clock controller node:
+
+	cru: cru@20000000 {
+		compatible = "rockchip,rk3036-cru";
+		reg = <0x20000000 0x1000>;
+		rockchip,grf = <&grf>;
+
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@20060000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x20060000 0x100>;
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		clocks = <&cru SCLK_UART0>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3228-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3228-cru.txt
new file mode 100644
index 000000000000..f323048127eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3228-cru.txt
@@ -0,0 +1,58 @@
+* Rockchip RK3228 Clock and Reset Unit
+
+The RK3228 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: should be "rockchip,rk3228-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing pll rates are not changeable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/rk3228-cru.h headers and can be
+used in device tree sources. Similar macros exist for the reset sources in
+these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "ext_i2s" - external I2S clock - optional,
+ - "ext_gmac" - external GMAC clock - optional
+ - "ext_hsadc" - external HSADC clock - optional
+ - "phy_50m_out" - output clock of the pll in the mac phy
+
+Example: Clock controller node:
+
+	cru: cru@20000000 {
+		compatible = "rockchip,rk3228-cru";
+		reg = <0x20000000 0x1000>;
+		rockchip,grf = <&grf>;
+
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@10110000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x10110000 0x100>;
+		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		clocks = <&cru SCLK_UART0>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt b/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt
new file mode 100644
index 000000000000..2726c1d58a79
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt
@@ -0,0 +1,49 @@
+Binding for Samsung S2M and S5M family clock generator block
+============================================================
+
+This is a part of device tree bindings for S2M and S5M family multi-function
+devices.
+More information can be found in bindings/mfd/sec-core.txt file.
+
+The S2MPS11/13/15 and S5M8767 provide three(AP/CP/BT) buffered 32.768 kHz
+outputs. The S2MPS14 provides two (AP/BT) buffered 32.768 KHz outputs.
+
+To register these as clocks with common clock framework instantiate under
+main device node a sub-node named "clocks".
+
+It uses the common clock binding documented in:
+ - Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+
+Required properties of the "clocks" sub-node:
+ - #clock-cells: should be 1.
+ - compatible: Should be one of: "samsung,s2mps11-clk", "samsung,s2mps13-clk",
+               "samsung,s2mps14-clk", "samsung,s5m8767-clk"
+   The S2MPS15 uses the same compatible as S2MPS13, as both provides similar
+   clocks.
+
+
+Each clock is assigned an identifier and client nodes use this identifier
+to specify the clock which they consume.
+    Clock               ID           Devices
+    ----------------------------------------------------------
+    32KhzAP		0            S2MPS11/13/14/15, S5M8767
+    32KhzCP		1            S2MPS11/13/15, S5M8767
+    32KhzBT		2            S2MPS11/13/14/15, S5M8767
+
+Include dt-bindings/clock/samsung,s2mps11.h file to use preprocessor defines
+in device tree sources.
+
+
+Example:
+
+	s2mps11_pmic@66 {
+		compatible = "samsung,s2mps11-pmic";
+		reg = <0x66>;
+
+		s2m_osc: clocks {
+			compatible = "samsung,s2mps11-clk";
+			#clock-cells = <1>;
+			clock-output-names = "xx", "yy", "zz";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index 8a47b77abfca..e59f57b24777 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -27,7 +27,9 @@ Required properties:
 	"allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s
 	"allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20
 	"allwinner,sun6i-a31-ar100-clk" - for the AR100 on A31
+	"allwinner,sun9i-a80-cpus-clk" - for the CPUS on A80
 	"allwinner,sun6i-a31-ahb1-clk" - for the AHB1 clock on A31
+	"allwinner,sun8i-h3-ahb2-clk" - for the AHB2 clock on H3
 	"allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31
 	"allwinner,sun8i-a23-ahb1-gates-clk" - for the AHB1 gates on A23
 	"allwinner,sun9i-a80-ahb0-gates-clk" - for the AHB0 gates on A80
@@ -55,6 +57,9 @@ Required properties:
 	"allwinner,sun9i-a80-apb1-gates-clk" - for the APB1 gates on A80
 	"allwinner,sun6i-a31-apb2-gates-clk" - for the APB2 gates on A31
 	"allwinner,sun8i-a23-apb2-gates-clk" - for the APB2 gates on A23
+	"allwinner,sun8i-h3-bus-gates-clk" - for the bus gates on H3
+	"allwinner,sun9i-a80-apbs-gates-clk" - for the APBS gates on A80
+	"allwinner,sun4i-a10-dram-gates-clk" - for the DRAM gates on A10
 	"allwinner,sun5i-a13-mbus-clk" - for the MBUS clock on A13
 	"allwinner,sun4i-a10-mmc-clk" - for the MMC clock
 	"allwinner,sun9i-a80-mmc-clk" - for mmc module clocks on A80
@@ -68,8 +73,10 @@ Required properties:
 	"allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13
 	"allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31
 	"allwinner,sun8i-a23-usb-clk" - for usb gates + resets on A23
+	"allwinner,sun8i-h3-usb-clk" - for usb gates + resets on H3
 	"allwinner,sun9i-a80-usb-mod-clk" - for usb gates + resets on A80
 	"allwinner,sun9i-a80-usb-phy-clk" - for usb phy gates + resets on A80
+	"allwinner,sun4i-a10-ve-clk" - for the Video Engine clock
 
 Required properties for all clocks:
 - reg : shall be the control register address for the clock.
@@ -89,6 +96,9 @@ Required properties for all clocks:
 And "allwinner,*-usb-clk" clocks also require:
 - reset-cells : shall be set to 1
 
+The "allwinner,sun4i-a10-ve-clk" clock also requires:
+- reset-cells : shall be set to 0
+
 The "allwinner,sun9i-a80-mmc-config-clk" clock also requires:
 - #reset-cells : shall be set to 1
 - resets : shall be the reset control phandle for the mmc block.
diff --git a/Documentation/devicetree/bindings/clock/tango4-clock.txt b/Documentation/devicetree/bindings/clock/tango4-clock.txt
new file mode 100644
index 000000000000..19c580a7bda2
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/tango4-clock.txt
@@ -0,0 +1,23 @@
+* Sigma Designs Tango4 Clock Generator
+
+The Tango4 clock generator outputs cpu_clk and sys_clk (the latter is used
+for RAM and various peripheral devices). The clock binding described here
+is applicable to all Tango4 SoCs.
+
+Required Properties:
+
+- compatible: should be "sigma,tango4-clkgen".
+- reg: physical base address of the device and length of memory mapped region.
+- clocks: phandle of the input clock (crystal oscillator).
+- clock-output-names: should be "cpuclk" and "sysclk".
+- #clock-cells: should be set to 1.
+
+Example:
+
+	clkgen: clkgen@10000 {
+		compatible = "sigma,tango4-clkgen";
+		reg = <0x10000 0x40>;
+		clocks = <&xtal>;
+		clock-output-names = "cpuclk", "sysclk";
+		#clock-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt b/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt
index 0715695e94a9..2aa06ac0fac5 100644
--- a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt
+++ b/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt
@@ -12,7 +12,7 @@ must be present contiguously. Generic DT driver will check only node 'x' for
 cpu:x.
 
 Required properties:
-- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt
+- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt
   for details
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt
index e41c98ffbccb..dd3929e85dec 100644
--- a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt
@@ -11,7 +11,7 @@ Required properties:
 - None
 
 Optional properties:
-- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt for
+- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt for
   details. OPPs *must* be supplied either via DT, i.e. this property, or
   populated at runtime.
 - clock-latency: Specify the possible maximum transition latency for clock,
diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-st.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-st.txt
new file mode 100644
index 000000000000..d91a02a3b6b0
--- /dev/null
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-st.txt
@@ -0,0 +1,91 @@
+Binding for ST's CPUFreq driver
+===============================
+
+ST's CPUFreq driver attempts to read 'process' and 'version' attributes
+from the SoC, then supplies the OPP framework with 'prop' and 'supported
+hardware' information respectively.  The framework is then able to read
+the DT and operate in the usual way.
+
+For more information about the expected DT format [See: ../opp/opp.txt].
+
+Frequency Scaling only
+----------------------
+
+No vendor specific driver required for this.
+
+Located in CPU's node:
+
+- operating-points		: [See: ../power/opp.txt]
+
+Example [safe]
+--------------
+
+cpus {
+	cpu@0 {
+				 /* kHz     uV   */
+		operating-points = <1500000 0
+				    1200000 0
+				    800000  0
+				    500000  0>;
+	};
+};
+
+Dynamic Voltage and Frequency Scaling (DVFS)
+--------------------------------------------
+
+This requires the ST CPUFreq driver to supply 'process' and 'version' info.
+
+Located in CPU's node:
+
+- operating-points-v2		: [See ../power/opp.txt]
+
+Example [unsafe]
+----------------
+
+cpus {
+	cpu@0 {
+		operating-points-v2	= <&cpu0_opp_table>;
+	};
+};
+
+cpu0_opp_table: opp_table {
+	compatible = "operating-points-v2";
+
+	/* ############################################################### */
+	/* # WARNING: Do not attempt to copy/replicate these nodes,      # */
+	/* #          they are only to be supplied by the bootloader !!! # */
+	/* ############################################################### */
+	opp0 {
+		/*			   Major       Minor       Substrate */
+		/*			   2           all         all       */
+		opp-supported-hw	= <0x00000004  0xffffffff  0xffffffff>;
+		opp-hz			= /bits/ 64 <1500000000>;
+		clock-latency-ns	= <10000000>;
+
+		opp-microvolt-pcode0	= <1200000>;
+		opp-microvolt-pcode1	= <1200000>;
+		opp-microvolt-pcode2	= <1200000>;
+		opp-microvolt-pcode3	= <1200000>;
+		opp-microvolt-pcode4	= <1170000>;
+		opp-microvolt-pcode5	= <1140000>;
+		opp-microvolt-pcode6	= <1100000>;
+		opp-microvolt-pcode7	= <1070000>;
+	};
+
+	opp1 {
+		/*			   Major       Minor       Substrate */
+		/*			   all         all         all       */
+		opp-supported-hw	= <0xffffffff  0xffffffff  0xffffffff>;
+		opp-hz			= /bits/ 64 <1200000000>;
+		clock-latency-ns	= <10000000>;
+
+		opp-microvolt-pcode0	= <1110000>;
+		opp-microvolt-pcode1	= <1150000>;
+		opp-microvolt-pcode2	= <1100000>;
+		opp-microvolt-pcode3	= <1080000>;
+		opp-microvolt-pcode4	= <1040000>;
+		opp-microvolt-pcode5	= <1020000>;
+		opp-microvolt-pcode6	= <980000>;
+		opp-microvolt-pcode7	= <930000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt b/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt
new file mode 100644
index 000000000000..096df34b11c1
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt
@@ -0,0 +1,29 @@
+Rockchip Electronics And Security Accelerator
+
+Required properties:
+- compatible: Should be "rockchip,rk3288-crypto"
+- reg: Base physical address of the engine and length of memory mapped
+       region
+- interrupts: Interrupt number
+- clocks: Reference to the clocks about crypto
+- clock-names: "aclk" used to clock data
+	       "hclk" used to clock data
+	       "sclk" used to clock crypto accelerator
+	       "apb_pclk" used to clock dma
+- resets: Must contain an entry for each entry in reset-names.
+	  See ../reset/reset.txt for details.
+- reset-names: Must include the name "crypto-rst".
+
+Examples:
+
+	crypto: cypto-controller@ff8a0000 {
+		compatible = "rockchip,rk3288-crypto";
+		reg = <0xff8a0000 0x4000>;
+		interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru ACLK_CRYPTO>, <&cru HCLK_CRYPTO>,
+			 <&cru SCLK_CRYPTO>, <&cru ACLK_DMAC1>;
+		clock-names = "aclk", "hclk", "sclk", "apb_pclk";
+		resets = <&cru SRST_CRYPTO>;
+		reset-names = "crypto-rst";
+		status = "okay";
+	};
diff --git a/Documentation/devicetree/bindings/display/bridge/tda998x.txt b/Documentation/devicetree/bindings/display/bridge/tda998x.txt
index e9e4bce40760..e178e6b9f9ee 100644
--- a/Documentation/devicetree/bindings/display/bridge/tda998x.txt
+++ b/Documentation/devicetree/bindings/display/bridge/tda998x.txt
@@ -5,6 +5,10 @@ Required properties;
 
   - reg: I2C address
 
+Required node:
+  - port: Input port node with endpoint definition, as described
+        in Documentation/devicetree/bindings/graph.txt
+
 Optional properties:
   - interrupts: interrupt number and trigger type
 	default: polling
diff --git a/Documentation/devicetree/bindings/display/etnaviv/etnaviv-drm.txt b/Documentation/devicetree/bindings/display/etnaviv/etnaviv-drm.txt
new file mode 100644
index 000000000000..ed5e0a7894ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/etnaviv/etnaviv-drm.txt
@@ -0,0 +1,54 @@
+Etnaviv DRM master device
+=========================
+
+The Etnaviv DRM master device is a virtual device needed to list all
+Vivante GPU cores that comprise the GPU subsystem.
+
+Required properties:
+- compatible: Should be one of
+    "fsl,imx-gpu-subsystem"
+    "marvell,dove-gpu-subsystem"
+- cores: Should contain a list of phandles pointing to Vivante GPU devices
+
+example:
+
+gpu-subsystem {
+	compatible = "fsl,imx-gpu-subsystem";
+	cores = <&gpu_2d>, <&gpu_3d>;
+};
+
+
+Vivante GPU core devices
+========================
+
+Required properties:
+- compatible: Should be "vivante,gc"
+  A more specific compatible is not needed, as the cores contain chip
+  identification registers at fixed locations, which provide all the
+  necessary information to the driver.
+- reg: should be register base and length as documented in the
+  datasheet
+- interrupts: Should contain the cores interrupt line
+- clocks: should contain one clock for entry in clock-names
+  see Documentation/devicetree/bindings/clock/clock-bindings.txt
+- clock-names:
+   - "bus":    AXI/register clock
+   - "core":   GPU core clock
+   - "shader": Shader clock (only required if GPU has feature PIPE_3D)
+
+Optional properties:
+- power-domains: a power domain consumer specifier according to
+  Documentation/devicetree/bindings/power/power_domain.txt
+
+example:
+
+gpu_3d: gpu@00130000 {
+	compatible = "vivante,gc";
+	reg = <0x00130000 0x4000>;
+	interrupts = <0 9 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clks IMX6QDL_CLK_GPU3D_AXI>,
+	         <&clks IMX6QDL_CLK_GPU3D_CORE>,
+	         <&clks IMX6QDL_CLK_GPU3D_SHADER>;
+	clock-names = "bus", "core", "shader";
+	power-domains = <&gpc 1>;
+};
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
index 64693f2ebc51..fe4a7a2dea9c 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
@@ -1,3 +1,20 @@
+Device-Tree bindings for Samsung Exynos Embedded DisplayPort Transmitter(eDP)
+
+DisplayPort is industry standard to accommodate the growing board adoption
+of digital display technology within the PC and CE industries.
+It consolidates the internal and external connection methods to reduce device
+complexity and cost. It also supports necessary features for important cross
+industry applications and provides performance scalability to enable the next
+generation of displays that feature higher color depths, refresh rates, and
+display resolutions.
+
+eDP (embedded display port) device is compliant with Embedded DisplayPort
+standard as follows,
+- DisplayPort standard 1.1a for Exynos5250 and Exynos5260.
+- DisplayPort standard 1.3 for Exynos5422s and Exynos5800.
+
+eDP resides between FIMD and panel or FIMD and bridge such as LVDS.
+
 The Exynos display port interface should be configured based on
 the type of panel connected to it.
 
@@ -66,8 +83,15 @@ Optional properties for dp-controller:
 		Hotplug detect GPIO.
 			Indicates which GPIO should be used for hotplug
 			detection
-	-video interfaces: Device node can contain video interface port
-			    nodes according to [1].
+Video interfaces:
+  Device node can contain video interface port nodes according to [1].
+  The following are properties specific to those nodes:
+
+  endpoint node connected to bridge or panel node:
+   - remote-endpoint: specifies the endpoint in panel or bridge node.
+		      This node is required in all kinds of exynos dp
+		      to represent the connection between dp and bridge
+		      or dp and panel.
 
 [1]: Documentation/devicetree/bindings/media/video-interfaces.txt
 
@@ -111,9 +135,18 @@ Board Specific portion:
 		};
 
 		ports {
-			port@0 {
+			port {
 				dp_out: endpoint {
-					remote-endpoint = <&bridge_in>;
+					remote-endpoint = <&dp_in>;
+				};
+			};
+		};
+
+		panel {
+			...
+			port {
+				dp_in: endpoint {
+					remote-endpoint = <&dp_out>;
 				};
 			};
 		};
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt b/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt
index 1fd8cf9cbfac..d474f59be6d6 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt
@@ -2,10 +2,9 @@ Device-Tree bindings for drm hdmi driver
 
 Required properties:
 - compatible: value should be one among the following:
-	1) "samsung,exynos5-hdmi" <DEPRECATED>
-	2) "samsung,exynos4210-hdmi"
-	3) "samsung,exynos4212-hdmi"
-	4) "samsung,exynos5420-hdmi"
+	1) "samsung,exynos4210-hdmi"
+	2) "samsung,exynos4212-hdmi"
+	3) "samsung,exynos5420-hdmi"
 - reg: physical base address of the hdmi and length of memory mapped
 	region.
 - interrupts: interrupt number to the cpu.
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index f344b9e49198..e7423bea1424 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -14,17 +14,20 @@ Required properties:
 - clocks: device clocks
   See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.
 - clock-names: the following clocks are required:
+  * "mdp_core_clk"
+  * "iface_clk"
   * "bus_clk"
-  * "byte_clk"
-  * "core_clk"
   * "core_mmss_clk"
-  * "iface_clk"
-  * "mdp_core_clk"
+  * "byte_clk"
   * "pixel_clk"
+  * "core_clk"
+  For DSIv2, we need an additional clock:
+   * "src_clk"
 - vdd-supply: phandle to vdd regulator device node
 - vddio-supply: phandle to vdd-io regulator device node
 - vdda-supply: phandle to vdda regulator device node
 - qcom,dsi-phy: phandle to DSI PHY device node
+- syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)
 
 Optional properties:
 - panel@0: Node of panel connected to this DSI controller.
@@ -51,6 +54,7 @@ Required properties:
   * "qcom,dsi-phy-28nm-hpm"
   * "qcom,dsi-phy-28nm-lp"
   * "qcom,dsi-phy-20nm"
+  * "qcom,dsi-phy-28nm-8960"
 - reg: Physical base address and length of the registers of PLL, PHY and PHY
   regulator
 - reg-names: The names of register regions. The following regions are required:
diff --git a/Documentation/devicetree/bindings/display/msm/mdp.txt b/Documentation/devicetree/bindings/display/msm/mdp.txt
index 0833edaba4c3..a214f6cd0363 100644
--- a/Documentation/devicetree/bindings/display/msm/mdp.txt
+++ b/Documentation/devicetree/bindings/display/msm/mdp.txt
@@ -2,18 +2,28 @@ Qualcomm adreno/snapdragon display controller
 
 Required properties:
 - compatible:
-  * "qcom,mdp" - mdp4
+  * "qcom,mdp4" - mdp4
+  * "qcom,mdp5" - mdp5
 - reg: Physical base address and length of the controller's registers.
 - interrupts: The interrupt signal from the display controller.
 - connectors: array of phandles for output device(s)
 - clocks: device clocks
   See ../clocks/clock-bindings.txt for details.
-- clock-names: the following clocks are required:
-  * "core_clk"
-  * "iface_clk"
-  * "src_clk"
-  * "hdmi_clk"
-  * "mpd_clk"
+- clock-names: the following clocks are required.
+  For MDP4:
+   * "core_clk"
+   * "iface_clk"
+   * "lut_clk"
+   * "src_clk"
+   * "hdmi_clk"
+   * "mdp_clk"
+  For MDP5:
+   * "bus_clk"
+   * "iface_clk"
+   * "core_clk_src"
+   * "core_clk"
+   * "lut_clk" (some MDP5 versions may not need this)
+   * "vsync_clk"
 
 Optional properties:
 - gpus: phandle for gpu device
@@ -26,7 +36,7 @@ Example:
 	...
 
 	mdp: qcom,mdp@5100000 {
-		compatible = "qcom,mdp";
+		compatible = "qcom,mdp4";
 		reg = <0x05100000 0xf0000>;
 		interrupts = <GIC_SPI 75 0>;
 		connectors = <&hdmi>;
diff --git a/Documentation/devicetree/bindings/display/panel/boe,tv080wum-nl0.txt b/Documentation/devicetree/bindings/display/panel/boe,tv080wum-nl0.txt
new file mode 100644
index 000000000000..50be5e2438b2
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/boe,tv080wum-nl0.txt
@@ -0,0 +1,7 @@
+Boe Corporation 8.0" WUXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "boe,tv080wum-nl0"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/innolux,g121x1-l03.txt b/Documentation/devicetree/bindings/display/panel/innolux,g121x1-l03.txt
new file mode 100644
index 000000000000..649744620ae1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,g121x1-l03.txt
@@ -0,0 +1,7 @@
+Innolux Corporation 12.1" G121X1-L03 XGA (1024x768) TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,g121x1-l03"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/kyo,tcg121xglp.txt b/Documentation/devicetree/bindings/display/panel/kyo,tcg121xglp.txt
new file mode 100644
index 000000000000..a8e940fe731e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/kyo,tcg121xglp.txt
@@ -0,0 +1,7 @@
+Kyocera Corporation 12.1" XGA (1024x768) TFT LCD panel
+
+Required properties:
+- compatible: should be "kyo,tcg121xglp"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/panasonic,vvx10f034n00.txt b/Documentation/devicetree/bindings/display/panel/panasonic,vvx10f034n00.txt
new file mode 100644
index 000000000000..37dedf6a6702
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/panasonic,vvx10f034n00.txt
@@ -0,0 +1,20 @@
+Panasonic 10" WUXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "panasonic,vvx10f034n00"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	mdss_dsi@fd922800 {
+		panel@0 {
+			compatible = "panasonic,vvx10f034n00";
+			reg = <0>;
+			power-supply = <&vreg_vsp>;
+			backlight = <&lp8566_wled>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/qiaodian,qd43003c0-40.txt b/Documentation/devicetree/bindings/display/panel/qiaodian,qd43003c0-40.txt
new file mode 100644
index 000000000000..0fbdab89ac3d
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/qiaodian,qd43003c0-40.txt
@@ -0,0 +1,7 @@
+QiaoDian XianShi Corporation 4"3 TFT LCD panel
+
+Required properties:
+- compatible: should be "qiaodian,qd43003c0-40"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,ls043t1le01.txt b/Documentation/devicetree/bindings/display/panel/sharp,ls043t1le01.txt
new file mode 100644
index 000000000000..3770a111968b
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sharp,ls043t1le01.txt
@@ -0,0 +1,22 @@
+Sharp Microelectronics 4.3" qHD TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,ls043t1le01-qhd"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+- reset-gpios: a GPIO spec for the reset pin
+
+Example:
+
+	mdss_dsi@fd922800 {
+		panel@0 {
+			compatible = "sharp,ls043t1le01-qhd";
+			reg = <0>;
+			avdd-supply = <&pm8941_l22>;
+			backlight = <&pm8941_wled>;
+			reset-gpios = <&pm8941_gpios 19 GPIO_ACTIVE_HIGH>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/startek,startek-kd050c.txt b/Documentation/devicetree/bindings/display/panel/startek,startek-kd050c.txt
new file mode 100644
index 000000000000..70cd8d18d841
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/startek,startek-kd050c.txt
@@ -0,0 +1,4 @@
+Startek Electronic Technology Co. KD050C 5.0" WVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "startek,startek-kd050c"
diff --git a/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
new file mode 100644
index 000000000000..1753f0cc6fad
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
@@ -0,0 +1,60 @@
+Rockchip specific extensions to the Synopsys Designware MIPI DSI
+================================
+
+Required properties:
+- #address-cells: Should be <1>.
+- #size-cells: Should be <0>.
+- compatible: "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi".
+- reg: Represent the physical address range of the controller.
+- interrupts: Represent the controller's interrupt to the CPU(s).
+- clocks, clock-names: Phandles to the controller's pll reference
+  clock(ref) and APB clock(pclk), as described in [1].
+- rockchip,grf: this soc should set GRF regs to mux vopl/vopb.
+- ports: contain a port node with endpoint definitions as defined in [2].
+  For vopb,set the reg = <0> and set the reg = <1> for vopl.
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+[2] Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+	mipi_dsi: mipi@ff960000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi";
+		reg = <0xff960000 0x4000>;
+		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_MIPI_24M>, <&cru PCLK_MIPI_DSI0>;
+		clock-names = "ref", "pclk";
+		rockchip,grf = <&grf>;
+		status = "okay";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			mipi_in: port {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				mipi_in_vopb: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&vopb_out_mipi>;
+				};
+				mipi_in_vopl: endpoint@1 {
+					reg = <1>;
+					remote-endpoint = <&vopl_out_mipi>;
+				};
+			};
+		};
+
+		panel {
+			compatible ="boe,tv080wum-nl0";
+			reg = <0>;
+
+			enable-gpios = <&gpio7 3 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&lcd_en>;
+			backlight = <&backlight>;
+			status = "okay";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
index d15351f2313d..5489b59e3d41 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
@@ -7,6 +7,7 @@ buffer to an external LCD interface.
 Required properties:
 - compatible: value should be one of the following
 		"rockchip,rk3288-vop";
+		"rockchip,rk3036-vop";
 
 - interrupts: should contain a list of all VOP IP block interrupts in the
 		 order: VSYNC, LCD_SYSTEM. The interrupt specifier
diff --git a/Documentation/devicetree/bindings/display/simple-framebuffer.txt b/Documentation/devicetree/bindings/display/simple-framebuffer.txt
index 4474ef6e0b95..8c9e9f515c87 100644
--- a/Documentation/devicetree/bindings/display/simple-framebuffer.txt
+++ b/Documentation/devicetree/bindings/display/simple-framebuffer.txt
@@ -47,10 +47,14 @@ Required properties:
   - a8b8g8r8 (32-bit pixels, d[31:24]=a, d[23:16]=b, d[15:8]=g, d[7:0]=r).
 
 Optional properties:
-- clocks : List of clocks used by the framebuffer. Clocks listed here
-           are expected to already be configured correctly. The OS must
-           ensure these clocks are not modified or disabled while the
-           simple framebuffer remains active.
+- clocks : List of clocks used by the framebuffer.
+- *-supply : Any number of regulators used by the framebuffer. These should
+	     be named according to the names in the device's design.
+
+  The above resources are expected to already be configured correctly.
+  The OS must ensure they are not modified or disabled while the simple
+  framebuffer remains active.
+
 - display : phandle pointing to the primary display hardware node
 
 Example:
@@ -68,6 +72,7 @@ chosen {
 		stride = <(1600 * 2)>;
 		format = "r5g6b5";
 		clocks = <&ahb_gates 36>, <&ahb_gates 43>, <&ahb_gates 44>;
+		lcd-supply = <&reg_dc1sw>;
 		display = <&lcdc0>;
 	};
 	stdout-path = "display0";
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
index 09daeef1ff22..5b902ac8d97e 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
@@ -14,7 +14,14 @@ not described in these device tree bindings.
 
 Required Properties:
 
-- compatible: must contain "renesas,rcar-dmac"
+- compatible: "renesas,dmac-<soctype>", "renesas,rcar-dmac" as fallback.
+	      Examples with soctypes are:
+		- "renesas,dmac-r8a7790" (R-Car H2)
+		- "renesas,dmac-r8a7791" (R-Car M2-W)
+		- "renesas,dmac-r8a7792" (R-Car V2H)
+		- "renesas,dmac-r8a7793" (R-Car M2-N)
+		- "renesas,dmac-r8a7794" (R-Car E2)
+		- "renesas,dmac-r8a7795" (R-Car H3)
 
 - reg: base address and length of the registers block for the DMAC
 
@@ -35,7 +42,7 @@ Required Properties:
 Example: R8A7790 (R-Car H2) SYS-DMACs
 
 	dmac0: dma-controller@e6700000 {
-		compatible = "renesas,rcar-dmac";
+		compatible = "renesas,dmac-r8a7790", "renesas,rcar-dmac";
 		reg = <0 0xe6700000 0 0x20000>;
 		interrupts = <0 197 IRQ_TYPE_LEVEL_HIGH
 			      0 200 IRQ_TYPE_LEVEL_HIGH
@@ -65,7 +72,7 @@ Example: R8A7790 (R-Car H2) SYS-DMACs
 	};
 
 	dmac1: dma-controller@e6720000 {
-		compatible = "renesas,rcar-dmac";
+		compatible = "renesas,dmac-r8a7790", "renesas,rcar-dmac";
 		reg = <0 0xe6720000 0 0x20000>;
 		interrupts = <0 220 IRQ_TYPE_LEVEL_HIGH
 			      0 216 IRQ_TYPE_LEVEL_HIGH
diff --git a/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
index 040f365954cc..e7780a186a36 100644
--- a/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
@@ -1,7 +1,13 @@
 * Renesas USB DMA Controller Device Tree bindings
 
 Required Properties:
-- compatible: must contain "renesas,usb-dmac"
+-compatible: "renesas,<soctype>-usb-dmac", "renesas,usb-dmac" as fallback.
+	Examples with soctypes are:
+	  - "renesas,r8a7790-usb-dmac" (R-Car H2)
+	  - "renesas,r8a7791-usb-dmac" (R-Car M2-W)
+	  - "renesas,r8a7793-usb-dmac" (R-Car M2-N)
+	  - "renesas,r8a7794-usb-dmac" (R-Car E2)
+	  - "renesas,r8a7795-usb-dmac" (R-Car H3)
 - reg: base address and length of the registers block for the DMAC
 - interrupts: interrupt specifiers for the DMAC, one for each entry in
   interrupt-names.
@@ -15,7 +21,7 @@ Required Properties:
 Example: R8A7790 (R-Car H2) USB-DMACs
 
 	usb_dmac0: dma-controller@e65a0000 {
-		compatible = "renesas,usb-dmac";
+		compatible = "renesas,r8a7790-usb-dmac", "renesas,usb-dmac";
 		reg = <0 0xe65a0000 0 0x100>;
 		interrupts = <0 109 IRQ_TYPE_LEVEL_HIGH
 			      0 109 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/dma/stm32-dma.txt b/Documentation/devicetree/bindings/dma/stm32-dma.txt
new file mode 100644
index 000000000000..70cd13f1588a
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/stm32-dma.txt
@@ -0,0 +1,82 @@
+* STMicroelectronics STM32 DMA controller
+
+The STM32 DMA is a general-purpose direct memory access controller capable of
+supporting 8 independent DMA channels. Each channel can have up to 8 requests.
+
+Required properties:
+- compatible: Should be "st,stm32-dma"
+- reg: Should contain DMA registers location and length. This should include
+  all of the per-channel registers.
+- interrupts: Should contain all of the per-channel DMA interrupts in
+  ascending order with respect to the DMA channel index.
+- clocks: Should contain the input clock of the DMA instance.
+- #dma-cells : Must be <4>. See DMA client paragraph for more details.
+
+Optional properties:
+- resets: Reference to a reset controller asserting the DMA controller
+- st,mem2mem: boolean; if defined, it indicates that the controller supports
+  memory-to-memory transfer
+
+Example:
+
+	dma2: dma-controller@40026400 {
+		compatible = "st,stm32-dma";
+		reg = <0x40026400 0x400>;
+		interrupts = <56>,
+			     <57>,
+			     <58>,
+			     <59>,
+			     <60>,
+			     <68>,
+			     <69>,
+			     <70>;
+		clocks = <&clk_hclk>;
+		#dma-cells = <4>;
+		st,mem2mem;
+		resets = <&rcc 150>;
+	};
+
+* DMA client
+
+DMA clients connected to the STM32 DMA controller must use the format
+described in the dma.txt file, using a five-cell specifier for each
+channel: a phandle plus four integer cells.
+The four cells in order are:
+
+1. The channel id
+2. The request line number
+3. A 32bit mask specifying the DMA channel configuration which are device
+   dependent:
+  -bit 9: Peripheral Increment Address
+	0x0: no address increment between transfers
+	0x1: increment address between transfers
+ -bit 10: Memory Increment Address
+	0x0: no address increment between transfers
+	0x1: increment address between transfers
+ -bit 15: Peripheral Increment Offset Size
+	0x0: offset size is linked to the peripheral bus width
+	0x1: offset size is fixed to 4 (32-bit alignment)
+ -bit 16-17: Priority level
+	0x0: low
+	0x1: medium
+	0x2: high
+	0x3: very high
+5. A 32bit mask specifying the DMA FIFO threshold configuration which are device
+   dependent:
+ -bit 0-1: Fifo threshold
+	0x0: 1/4 full FIFO
+	0x1: 1/2 full FIFO
+	0x2: 3/4 full FIFO
+	0x3: full FIFO
+
+Example:
+
+	usart1: serial@40011000 {
+		compatible = "st,stm32-usart", "st,stm32-uart";
+		reg = <0x40011000 0x400>;
+		interrupts = <37>;
+		clocks = <&clk_pclk2>;
+		dmas = <&dma2 2 4 0x10400 0x3>,
+		       <&dma2 7 5 0x10200 0x3>;
+		dma-names = "rx", "tx";
+	};
diff --git a/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
index b152a75dceae..aead5869a28d 100644
--- a/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
+++ b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
@@ -14,6 +14,10 @@ The DMA controller node need to have the following poroperties:
 
 Optional properties:
 - ti,dma-safe-map: Safe routing value for unused request lines
+- ti,reserved-dma-request-ranges: DMA request ranges which should not be used
+		when mapping xbar input to DMA request, they are either
+		allocated to be used by for example the DSP or they are used as
+		memcpy channels in eDMA.
 
 Notes:
 When requesting channel via ti,dra7-dma-crossbar, the DMA clinet must request
@@ -46,6 +50,8 @@ sdma_xbar: dma-router@4a002b78 {
 	#dma-cells = <1>;
 	dma-requests = <205>;
 	ti,dma-safe-map = <0>;
+	/* Protect the sDMA request ranges: 10-14 and 100-126 */
+	ti,reserved-dma-request-ranges = <10 5>, <100 27>;
 	dma-masters = <&sdma>;
 };
 
diff --git a/Documentation/devicetree/bindings/eeprom/eeprom.txt b/Documentation/devicetree/bindings/eeprom/eeprom.txt
index 4342c10de1bf..735bc94444bb 100644
--- a/Documentation/devicetree/bindings/eeprom/eeprom.txt
+++ b/Documentation/devicetree/bindings/eeprom/eeprom.txt
@@ -2,11 +2,22 @@ EEPROMs (I2C)
 
 Required properties:
 
-  - compatible : should be "<manufacturer>,<type>"
-		 If there is no specific driver for <manufacturer>, a generic
-		 driver based on <type> is selected. Possible types are:
-		 24c00, 24c01, 24c02, 24c04, 24c08, 24c16, 24c32, 24c64,
-		 24c128, 24c256, 24c512, 24c1024, spd
+  - compatible : should be "<manufacturer>,<type>", like these:
+
+	"atmel,24c00", "atmel,24c01", "atmel,24c02", "atmel,24c04",
+	"atmel,24c08", "atmel,24c16", "atmel,24c32", "atmel,24c64",
+	"atmel,24c128", "atmel,24c256", "atmel,24c512", "atmel,24c1024"
+
+	"catalyst,24c32"
+
+	"ramtron,24c64"
+
+	"renesas,r1ex24002"
+
+	 If there is no specific driver for <manufacturer>, a generic
+	 driver based on <type> is selected. Possible types are:
+	 "24c00", "24c01", "24c02", "24c04", "24c08", "24c16", "24c32", "24c64",
+	 "24c128", "24c256", "24c512", "24c1024", "spd"
 
   - reg : the I2C address of the EEPROM
 
diff --git a/Documentation/devicetree/bindings/extcon/extcon-arizona.txt b/Documentation/devicetree/bindings/extcon/extcon-arizona.txt
index e1705fae63a8..e27341f8a4c7 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-arizona.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-arizona.txt
@@ -13,3 +13,63 @@ Optional properties:
     ARIZONA_ACCDET_MODE_HPR or 2 - Headphone detect mode is set to HPDETR
     If this node is not mentioned or if the value is unknown, then
     headphone detection mode is set to HPDETL.
+
+  - wlf,use-jd2 : Use the additional JD input along with JD1 for dual pin jack
+    detection.
+  - wlf,use-jd2-nopull : Internal pull on JD2 is disabled when used for
+    jack detection.
+  - wlf,jd-invert : Invert the polarity of the jack detection switch
+
+  - wlf,micd-software-compare : Use a software comparison to determine mic
+    presence
+  - wlf,micd-detect-debounce : Additional software microphone detection
+    debounce specified in milliseconds.
+  - wlf,micd-pol-gpio : GPIO specifier for the GPIO controlling the headset
+    polarity if one exists.
+  - wlf,micd-bias-start-time : Time allowed for MICBIAS to startup prior to
+    performing microphone detection, specified as per the ARIZONA_MICD_TIME_XXX
+    defines.
+  - wlf,micd-rate : Delay between successive microphone detection measurements,
+    specified as per the ARIZONA_MICD_TIME_XXX defines.
+  - wlf,micd-dbtime : Microphone detection hardware debounces specified as the
+    number of measurements to take, valid values being 2 and 4.
+  - wlf,micd-timeout-ms : Timeout for microphone detection, specified in
+    milliseconds.
+  - wlf,micd-force-micbias : Force MICBIAS continuously on during microphone
+    detection.
+  - wlf,micd-configs : Headset polarity configurations (generally used for
+    detection of CTIA / OMTP headsets), the field can be of variable length
+    but should always be a multiple of 3 cells long, each three cell group
+    represents one polarity configuration.
+    The first cell defines the accessory detection pin, zero will use MICDET1
+    and all other values will use MICDET2.
+    The second cell represents the MICBIAS to be used.
+    The third cell represents the value of the micd-pol-gpio pin.
+
+  - wlf,gpsw : Settings for the general purpose switch
+
+Example:
+
+codec: wm8280@0 {
+	compatible = "wlf,wm8280";
+	reg = <0>;
+	...
+
+	wlf,use-jd2;
+	wlf,use-jd2-nopull;
+	wlf,jd-invert;
+
+	wlf,micd-software-compare;
+	wlf,micd-detect-debounce = <0>;
+	wlf,micd-pol-gpio = <&codec 2 0>;
+	wlf,micd-rate = <ARIZONA_MICD_TIME_8MS>;
+	wlf,micd-dbtime = <4>;
+	wlf,micd-timeout-ms = <100>;
+	wlf,micd-force-micbias;
+	wlf,micd-configs = <
+		0 1 0 /* MICDET1 MICBIAS1 GPIO=low */
+		1 2 1 /* MICDET2 MICBIAS2 GPIO=high */
+	>;
+
+	wlf,gpsw = <0>;
+};
diff --git a/Documentation/devicetree/bindings/extcon/extcon-max3355.txt b/Documentation/devicetree/bindings/extcon/extcon-max3355.txt
new file mode 100644
index 000000000000..f2288ea9eb82
--- /dev/null
+++ b/Documentation/devicetree/bindings/extcon/extcon-max3355.txt
@@ -0,0 +1,21 @@
+Maxim Integrated MAX3355 USB OTG chip
+-------------------------------------
+
+MAX3355 integrates a charge pump and comparators to enable a system with an
+integrated USB OTG dual-role transceiver to function as a USB OTG dual-role
+device.
+
+Required properties:
+- compatible: should be "maxim,max3355";
+- maxim,shdn-gpios: should contain a phandle and GPIO specifier for the GPIO pin
+		    connected to the MAX3355's SHDN# pin;
+- id-gpios: should contain a phandle and GPIO specifier for the GPIO pin
+	    connected to the MAX3355's ID_OUT pin.
+
+Example:
+
+	usb-otg {
+		compatible = "maxim,max3355";
+		maxim,shdn-gpios = <&gpio2 4 GPIO_ACTIVE_LOW>;
+		id-gpios = <&gpio5 31 GPIO_ACTIVE_HIGH>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
index 13df9933f4cd..6b4a98f74be3 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -25,6 +25,7 @@ Required properties:
 	ti,tca6416
 	ti,tca6424
 	ti,tca9539
+	onsemi,pca9654
 	exar,xra1202
 
 Example:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-sx150x.txt b/Documentation/devicetree/bindings/gpio/gpio-sx150x.txt
index ba2bb84eeac3..c809acb9c71b 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-sx150x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-sx150x.txt
@@ -5,7 +5,8 @@ Required properties:
 
 - compatible: should be "semtech,sx1506q",
 			"semtech,sx1508q",
-			"semtech,sx1509q".
+			"semtech,sx1509q",
+			"semtech,sx1502q".
 
 - reg: The I2C slave address for this device.
 
diff --git a/Documentation/devicetree/bindings/gpio/gpio-tps65086.txt b/Documentation/devicetree/bindings/gpio/gpio-tps65086.txt
new file mode 100644
index 000000000000..ba051074bedc
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-tps65086.txt
@@ -0,0 +1,16 @@
+* TPS65086 GPO Controller bindings
+
+Required properties:
+ - compatible		: Should be "ti,tps65086-gpio".
+ - gpio-controller	: Marks the device node as a GPIO Controller.
+ - #gpio-cells		: Should be two. The first cell is the pin number
+			    and the second cell is used to specify flags.
+			    See ../gpio/gpio.txt for possible values.
+
+Example:
+
+	gpio4: gpio {
+		compatible = "ti,tps65086-gpio";
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
index dd5d2c0394b1..4d6c8cdc8586 100644
--- a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
@@ -24,7 +24,7 @@ controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt.  Shall be set to 2.  The first cell defines the interrupt number,
   the second encodes the triger flags encoded as described in
-  Documentation/devicetree/bindings/interrupts.txt
+  Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 - interrupt-parent : The parent interrupt controller.
 - interrupts : The interrupt to the parent controller raised when GPIOs
   generate the interrupts.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-at91.txt b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
index 6e81dc153f3b..ef973a0343c7 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-at91.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
@@ -3,7 +3,7 @@ I2C for Atmel platforms
 Required properties :
 - compatible : Must be "atmel,at91rm9200-i2c", "atmel,at91sam9261-i2c",
      "atmel,at91sam9260-i2c", "atmel,at91sam9g20-i2c", "atmel,at91sam9g10-i2c",
-     "atmel,at91sam9x5-i2c" or "atmel,sama5d2-i2c"
+     "atmel,at91sam9x5-i2c", "atmel,sama5d4-i2c" or "atmel,sama5d2-i2c"
 - reg: physical base address of the controller and length of memory mapped
      region.
 - interrupts: interrupt number to the cpu.
@@ -17,6 +17,8 @@ Optional properties:
 - dma-names: should contain "tx" and "rx".
 - atmel,fifo-size: maximum number of data the RX and TX FIFOs can store for FIFO
   capable I2C controllers.
+- i2c-sda-hold-time-ns: TWD hold time, only available for "atmel,sama5d4-i2c"
+  and "atmel,sama5d2-i2c".
 - Child nodes conforming to i2c bus binding
 
 Examples :
@@ -52,6 +54,7 @@ i2c0: i2c@f8034600 {
 	#size-cells = <0>;
 	clocks = <&flx0>;
 	atmel,fifo-size = <16>;
+	i2c-sda-hold-time-ns = <336>;
 
 	wm8731: wm8731@1a {
 		compatible = "wm8731";
diff --git a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
index d6f724efdcf2..aeceaceba3c5 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
@@ -2,7 +2,7 @@ Broadcom stb bsc iic master controller
 
 Required properties:
 
-- compatible: should be "brcm,brcmstb-i2c"
+- compatible: should be "brcm,brcmstb-i2c" or "brcm,brcmper-i2c"
 - clock-frequency: 32-bit decimal value of iic master clock freqency in Hz
 		   valid values are 375000, 390000, 187500, 200000
 		   93750, 97500, 46875 and 50000
diff --git a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt
index ea406eb20fa5..95e97223a71c 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt
@@ -20,6 +20,10 @@ Optional properties:
   propoerty indicates the default frequency 100 kHz.
 - clocks: clock specifier.
 
+- i2c-scl-falling-time-ns: see i2c.txt
+- i2c-scl-internal-delay-ns: see i2c.txt
+- i2c-scl-rising-time-ns: see i2c.txt
+
 Examples :
 
 i2c0: i2c@e6508000 {
diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt
index 8a99150ac3a7..c8d977ed847f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c.txt
@@ -29,12 +29,38 @@ Optional properties
 These properties may not be supported by all drivers. However, if a driver
 wants to support one of the below features, it should adapt the bindings below.
 
-- clock-frequency	- frequency of bus clock in Hz.
-- wakeup-source		- device can be used as a wakeup source.
+- clock-frequency
+	frequency of bus clock in Hz.
 
-- interrupts		- interrupts used by the device.
-- interrupt-names	- "irq" and "wakeup" names are recognized by I2C core,
-			  other names are left to individual drivers.
+- i2c-scl-falling-time-ns
+	Number of nanoseconds the SCL signal takes to fall; t(f) in the I2C
+	specification.
+
+- i2c-scl-internal-delay-ns
+	Number of nanoseconds the IP core additionally needs to setup SCL.
+
+- i2c-scl-rising-time-ns
+	Number of nanoseconds the SCL signal takes to rise; t(r) in the I2C
+	specification.
+
+- i2c-sda-falling-time-ns
+	Number of nanoseconds the SDA signal takes to fall; t(f) in the I2C
+	specification.
+
+- interrupts
+	interrupts used by the device.
+
+- interrupt-names
+	"irq" and "wakeup" names are recognized by I2C core, other names are
+	left to individual drivers.
+
+- multi-master
+	states that there is another master active on this bus. The OS can use
+	this information to adapt power management to keep the arbitration awake
+	all the time, for example.
+
+- wakeup-source
+	device can be used as a wakeup source.
 
 Binding may contain optional "interrupts" property, describing interrupts
 used by the device. I2C core will assign "irq" interrupt (or the very first
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index c50cf13c852e..539874490492 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -20,22 +20,11 @@ adi,adt7476		+/-1C TDM Extended Temp Range I.C
 adi,adt7490		+/-1C TDM Extended Temp Range I.C
 adi,adxl345		Three-Axis Digital Accelerometer
 adi,adxl346		Three-Axis Digital Accelerometer (backward-compatibility value "adi,adxl345" must be listed too)
+ams,iaq-core		AMS iAQ-Core VOC Sensor
 at,24c08		i2c serial eeprom  (24cxx)
-atmel,24c00		i2c serial eeprom  (24cxx)
-atmel,24c01		i2c serial eeprom  (24cxx)
-atmel,24c02		i2c serial eeprom  (24cxx)
-atmel,24c04		i2c serial eeprom  (24cxx)
-atmel,24c16		i2c serial eeprom  (24cxx)
-atmel,24c32		i2c serial eeprom  (24cxx)
-atmel,24c64		i2c serial eeprom  (24cxx)
-atmel,24c128		i2c serial eeprom  (24cxx)
-atmel,24c256		i2c serial eeprom  (24cxx)
-atmel,24c512		i2c serial eeprom  (24cxx)
-atmel,24c1024		i2c serial eeprom  (24cxx)
 atmel,at97sc3204t	i2c trusted platform module (TPM)
 capella,cm32181		CM32181: Ambient Light Sensor
 capella,cm3232		CM3232: Ambient Light Sensor
-catalyst,24c32		i2c serial eeprom
 cirrus,cs42l51		Cirrus Logic CS42L51 audio codec
 dallas,ds1307		64 x 8, Serial, I2C Real-Time Clock
 dallas,ds1338		I2C RTC with 56-Byte NV RAM
@@ -49,11 +38,13 @@ dallas,ds4510		CPU Supervisor with Nonvolatile Memory and Programmable I/O
 dallas,ds75		Digital Thermometer and Thermostat
 dlg,da9053		DA9053: flexible system level PMIC with multicore support
 dlg,da9063		DA9063: system PMIC for quad-core application processors
+epson,rx8010		I2C-BUS INTERFACE REAL TIME CLOCK MODULE
 epson,rx8025		High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE
 epson,rx8581		I2C-BUS INTERFACE REAL TIME CLOCK MODULE
 fsl,mag3110		MAG3110: Xtrinsic High Accuracy, 3D Magnetometer
 fsl,mc13892		MC13892: Power Management Integrated Circuit (PMIC) for i.MX35/51
 fsl,mma8450		MMA8450Q: Xtrinsic Low-power, 3-axis Xtrinsic Accelerometer
+fsl,mpl3115		MPL3115: Absolute Digital Pressure Sensor
 fsl,mpr121		MPR121: Proximity Capacitive Touch Sensor Controller
 fsl,sgtl5000		SGTL5000: Ultra Low-Power Audio Codec
 gmt,g751		G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface
@@ -80,7 +71,6 @@ ovti,ov5642		OV5642: Color CMOS QSXGA (5-megapixel) Image Sensor with OmniBSI an
 pericom,pt7c4338	Real-time Clock Module
 plx,pex8648		48-Lane, 12-Port PCI Express Gen 2 (5.0 GT/s) Switch
 pulsedlight,lidar-lite-v2	Pulsedlight LIDAR range-finding sensor
-ramtron,24c64		i2c serial eeprom  (24cxx)
 ricoh,r2025sd		I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC
 ricoh,r2221tl		I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC
 ricoh,rs5c372a		I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC
diff --git a/Documentation/devicetree/bindings/iio/accel/mma8452.txt b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
index e3c37467d7da..3c10e8581144 100644
--- a/Documentation/devicetree/bindings/iio/accel/mma8452.txt
+++ b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
@@ -7,13 +7,18 @@ Required properties:
     * "fsl,mma8453"
     * "fsl,mma8652"
     * "fsl,mma8653"
+
   - reg: the I2C address of the chip
 
 Optional properties:
 
   - interrupt-parent: should be the phandle for the interrupt controller
+
   - interrupts: interrupt mapping for GPIO IRQ
 
+  - interrupt-names: should contain "INT1" and/or "INT2", the accelerometer's
+		     interrupt line in use.
+
 Example:
 
 	mma8453fc@1d {
@@ -21,4 +26,5 @@ Example:
 		reg = <0x1d>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <5 0>;
+		interrupt-names = "INT2";
 	};
diff --git a/Documentation/devicetree/bindings/iio/adc/imx7d-adc.txt b/Documentation/devicetree/bindings/iio/adc/imx7d-adc.txt
new file mode 100644
index 000000000000..5c184b940669
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/imx7d-adc.txt
@@ -0,0 +1,22 @@
+Freescale imx7d ADC bindings
+
+The devicetree bindings are for the ADC driver written for
+imx7d SoC.
+
+Required properties:
+- compatible: Should be "fsl,imx7d-adc"
+- reg: Offset and length of the register set for the ADC device
+- interrupts: The interrupt number for the ADC device
+- clocks: The root clock of the ADC controller
+- clock-names: Must contain "adc", matching entry in the clocks property
+- vref-supply: The regulator supply ADC reference voltage
+
+Example:
+adc1: adc@30610000 {
+	compatible = "fsl,imx7d-adc";
+	reg = <0x30610000 0x10000>;
+	interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clks IMX7D_ADC_ROOT_CLK>;
+	clock-names = "adc";
+	vref-supply = <&reg_vcc_3v3_mcu>;
+};
diff --git a/Documentation/devicetree/bindings/iio/adc/mcp320x.txt b/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
index 2a1f3af30155..bcd3ac8e6e0c 100644
--- a/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
+++ b/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
@@ -10,16 +10,28 @@ must be specified.
 Required properties:
 	- compatible:  	Must be one of the following, depending on the
 			model:
-				"mcp3001"
-				"mcp3002"
-				"mcp3004"
-				"mcp3008"
-				"mcp3201"
-				"mcp3202"
-				"mcp3204"
-				"mcp3208"
-				"mcp3301"
+				"mcp3001" (DEPRECATED)
+				"mcp3002" (DEPRECATED)
+				"mcp3004" (DEPRECATED)
+				"mcp3008" (DEPRECATED)
+				"mcp3201" (DEPRECATED)
+				"mcp3202" (DEPRECATED)
+				"mcp3204" (DEPRECATED)
+				"mcp3208" (DEPRECATED)
+				"mcp3301" (DEPRECATED)
 
+				"microchip,mcp3001"
+				"microchip,mcp3002"
+				"microchip,mcp3004"
+				"microchip,mcp3008"
+				"microchip,mcp3201"
+				"microchip,mcp3202"
+				"microchip,mcp3204"
+				"microchip,mcp3208"
+				"microchip,mcp3301"
+
+			NOTE: The use of the compatibles with no vendor prefix
+			is deprecated and only listed because old DT use them.
 
 Examples:
 spi_controller {
diff --git a/Documentation/devicetree/bindings/iio/adc/mcp3422.txt b/Documentation/devicetree/bindings/iio/adc/mcp3422.txt
index 333139cc0bfb..dcae4ccfcc52 100644
--- a/Documentation/devicetree/bindings/iio/adc/mcp3422.txt
+++ b/Documentation/devicetree/bindings/iio/adc/mcp3422.txt
@@ -1,7 +1,8 @@
-* Microchip mcp3422/3/4/6/7/8 chip family (ADC)
+* Microchip mcp3421/2/3/4/6/7/8 chip family (ADC)
 
 Required properties:
  - compatible: Should be
+	"microchip,mcp3421" or
 	"microchip,mcp3422" or
 	"microchip,mcp3423" or
 	"microchip,mcp3424" or
diff --git a/Documentation/devicetree/bindings/iio/adc/palmas-gpadc.txt b/Documentation/devicetree/bindings/iio/adc/palmas-gpadc.txt
new file mode 100644
index 000000000000..4bb9a86065d1
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/palmas-gpadc.txt
@@ -0,0 +1,48 @@
+* Palmas general purpose ADC IP block devicetree bindings
+
+Channels list:
+	0 battery type
+	1 battery temp NTC (optional current source)
+	2 GP
+	3 temp (with ext. diode, optional current source)
+	4 GP
+	5 GP
+	6 VBAT_SENSE
+	7 VCC_SENSE
+	8 Backup Battery voltage
+	9 external charger (VCHG)
+	10 VBUS
+	11 DC-DC current probe (how does this work?)
+	12 internal die temp
+	13 internal die temp
+	14 USB ID pin voltage
+	15 test network
+
+Required properties:
+- compatible : Must be "ti,palmas-gpadc".
+- #io-channel-cells: Should be set to <1>.
+
+Optional sub-nodes:
+ti,channel0-current-microamp: Channel 0 current in uA.
+	Values are rounded to derive 0uA, 5uA, 15uA, 20uA.
+ti,channel3-current-microamp: Channel 3 current in uA.
+	Values are rounded to derive 0uA, 10uA, 400uA, 800uA.
+ti,enable-extended-delay: Enable extended delay.
+
+Example:
+
+pmic {
+	compatible = "ti,twl6035-pmic", "ti,palmas-pmic";
+	...
+	gpadc {
+		compatible = "ti,palmas-gpadc";
+		interrupts = <18 0
+			      16 0
+			      17 0>;
+		#io-channel-cells = <1>;
+		ti,channel0-current-microamp = <5>;
+		ti,channel3-current-microamp = <10>;
+		};
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/iio/adc/ti-adc128s052.txt b/Documentation/devicetree/bindings/iio/adc/ti-adc128s052.txt
index 15ca6b47958e..daa2b2c29428 100644
--- a/Documentation/devicetree/bindings/iio/adc/ti-adc128s052.txt
+++ b/Documentation/devicetree/bindings/iio/adc/ti-adc128s052.txt
@@ -1,7 +1,7 @@
-* Texas Instruments' ADC128S052 and ADC122S021 ADC chip
+* Texas Instruments' ADC128S052, ADC122S021 and ADC124S021 ADC chip
 
 Required properties:
- - compatible: Should be "ti,adc128s052" or "ti,adc122s021"
+ - compatible: Should be "ti,adc128s052", "ti,adc122s021" or "ti,adc124s021"
  - reg: spi chip select number for the device
  - vref-supply: The regulator supply for ADC reference voltage
 
diff --git a/Documentation/devicetree/bindings/iio/adc/ti-ads8688.txt b/Documentation/devicetree/bindings/iio/adc/ti-ads8688.txt
new file mode 100644
index 000000000000..a02337d7efa4
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/ti-ads8688.txt
@@ -0,0 +1,20 @@
+* Texas Instruments' ADS8684 and ADS8688 ADC chip
+
+Required properties:
+ - compatible: Should be "ti,ads8684" or "ti,ads8688"
+ - reg: spi chip select number for the device
+
+Recommended properties:
+ - spi-max-frequency: Definition as per
+		Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Optional properties:
+ - vref-supply: The regulator supply for ADC reference voltage
+
+Example:
+adc@0 {
+	compatible = "ti,ads8688";
+	reg = <0>;
+	vref-supply = <&vdd_supply>;
+	spi-max-frequency = <1000000>;
+};
diff --git a/Documentation/devicetree/bindings/iio/health/max30100.txt b/Documentation/devicetree/bindings/iio/health/max30100.txt
new file mode 100644
index 000000000000..f6fbac66ad06
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/health/max30100.txt
@@ -0,0 +1,21 @@
+Maxim MAX30100 heart rate and pulse oximeter sensor
+
+* https://datasheets.maximintegrated.com/en/ds/MAX30100.pdf
+
+Required properties:
+  - compatible: must be "maxim,max30100"
+  - reg: the I2C address of the sensor
+  - interrupt-parent: should be the phandle for the interrupt controller
+  - interrupts: the sole interrupt generated by the device
+
+  Refer to interrupt-controller/interrupts.txt for generic
+  interrupt client node bindings.
+
+Example:
+
+max30100@057 {
+	compatible = "maxim,max30100";
+	reg = <57>;
+	interrupt-parent = <&gpio1>;
+	interrupts = <16 2>;
+};
diff --git a/Documentation/devicetree/bindings/iio/light/us5182d.txt b/Documentation/devicetree/bindings/iio/light/us5182d.txt
index 6f0a530144fd..a61979997f37 100644
--- a/Documentation/devicetree/bindings/iio/light/us5182d.txt
+++ b/Documentation/devicetree/bindings/iio/light/us5182d.txt
@@ -7,13 +7,24 @@ Required properties:
 Optional properties:
 - upisemi,glass-coef: glass attenuation factor - compensation factor of
                       resolution 1000 for material transmittance.
+
 - upisemi,dark-ths: array of 8 elements containing 16-bit thresholds (adc
                     counts) corresponding to every scale.
+
 - upisemi,upper-dark-gain: 8-bit dark gain compensation factor(4 int and 4
                            fractional bits - Q4.4) applied when light > threshold
+
 - upisemi,lower-dark-gain: 8-bit dark gain compensation factor(4 int and 4
                            fractional bits - Q4.4) applied when light < threshold
 
+- upisemi,continuous: This chip has two power modes: one-shot (chip takes one
+                      measurement and then shuts itself down) and continuous (
+                      chip takes continuous measurements). The one-shot mode is
+                      more power-friendly but the continuous mode may be more
+                      reliable. If this property is specified the continuous
+                      mode will be used instead of the default one-shot one for
+                      raw reads.
+
 If the optional properties are not specified these factors will default to the
 values in the below example.
 The glass-coef defaults to no compensation for the covering material.
diff --git a/Documentation/devicetree/bindings/iio/st-sensors.txt b/Documentation/devicetree/bindings/iio/st-sensors.txt
index d3ccdb190c53..d4b87cc1e446 100644
--- a/Documentation/devicetree/bindings/iio/st-sensors.txt
+++ b/Documentation/devicetree/bindings/iio/st-sensors.txt
@@ -36,6 +36,7 @@ Accelerometers:
 - st,lsm303dlm-accel
 - st,lsm330-accel
 - st,lsm303agr-accel
+- st,lis2dh12-accel
 
 Gyroscopes:
 - st,l3g4200d-gyro
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.txt b/Documentation/devicetree/bindings/input/gpio-keys.txt
index cf1333d1dd52..21641236c095 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.txt
+++ b/Documentation/devicetree/bindings/input/gpio-keys.txt
@@ -6,6 +6,7 @@ Required properties:
 Optional properties:
 	- autorepeat: Boolean, Enable auto repeat feature of Linux input
 	  subsystem.
+	- label: String, name of the input device.
 
 Each button (key) is represented as a sub-node of "gpio-keys":
 Subnode properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
index 8ba98eec765b..c98757a69110 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
@@ -13,6 +13,17 @@ Required properties:
  - interrupt-parent	: Interrupt controller to which the chip is connected
  - interrupts		: Interrupt to which the chip is connected
 
+Optional properties:
+
+ - irq-gpios		: GPIO pin used for IRQ. The driver uses the
+			  interrupt gpio pin as output to reset the device.
+ - reset-gpios		: GPIO pin used for reset
+
+ - touchscreen-inverted-x  : X axis is inverted (boolean)
+ - touchscreen-inverted-y  : Y axis is inverted (boolean)
+ - touchscreen-swapped-x-y : X and Y axis are swapped (boolean)
+                             (swapping is done after inverting the axis)
+
 Example:
 
 	i2c@00000000 {
@@ -23,6 +34,9 @@ Example:
 			reg = <0x5d>;
 			interrupt-parent = <&gpio>;
 			interrupts = <0 0>;
+
+			irq-gpios = <&gpio1 0 0>;
+			reset-gpios = <&gpio1 1 0>;
 		};
 
 		/* ... */
diff --git a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
index 8eb240a287c8..697a3e7831e7 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
@@ -9,7 +9,9 @@ Required properties:
 - touchscreen-size-y: vertical resolution of touchscreen (in pixels)
 
 Optional properties:
-- reset-gpio: GPIO connected to the RESET line of the chip
+- reset-gpios: GPIO connected to the RESET line of the chip
+- enable-gpios: GPIO connected to the ENABLE line of the chip
+- wake-gpios: GPIO connected to the WAKE line of the chip
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ts4800-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/ts4800-ts.txt
new file mode 100644
index 000000000000..4c1c092c276b
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/ts4800-ts.txt
@@ -0,0 +1,11 @@
+* TS-4800 Touchscreen bindings
+
+Required properties:
+- compatible: must be "technologic,ts4800-ts"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- syscon: phandle / integers array that points to the syscon node which
+          describes the FPGA's syscon registers.
+          - phandle to FPGA's syscon
+          - offset to the touchscreen register
+          - offset to the touchscreen enable bit
diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun67i-sc-nmi.txt b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
index d1c5cdabc3e0..81cd3692405e 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun67i-sc-nmi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
@@ -4,7 +4,7 @@ Allwinner Sunxi NMI Controller
 Required properties:
 
 - compatible : should be "allwinner,sun7i-a20-sc-nmi" or
-  "allwinner,sun6i-a31-sc-nmi"
+  "allwinner,sun6i-a31-sc-nmi" or "allwinner,sun9i-a80-nmi"
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 7803e77d85cb..007a5b46256a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -24,9 +24,8 @@ Main node required properties:
 		1 = edge triggered
 		4 = level triggered
 
-  Cells 4 and beyond are reserved for future use. When the 1st cell
-  has a value of 0 or 1, cells 4 and beyond act as padding, and may be
-  ignored. It is recommended that padding cells have a value of 0.
+  Cells 4 and beyond are reserved for future use and must have a value
+  of 0 if present.
 
 - reg : Specifies base physical address(s) and size of the GIC
   registers, in the following order:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
index cc56021eb60b..5a1cb4bc3dfe 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
@@ -18,6 +18,7 @@ Main node required properties:
 	"arm,cortex-a9-gic"
 	"arm,gic-400"
 	"arm,pl390"
+	"arm,tc11mp-gic"
 	"brcm,brahma-b15-gic"
 	"qcom,msm-8660-qgic"
 	"qcom,msm-qgic2"
diff --git a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
new file mode 100644
index 000000000000..720f7c92e9a1
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
@@ -0,0 +1,74 @@
+Hisilicon mbigen device tree bindings.
+=======================================
+
+Mbigen means: message based interrupt generator.
+
+MBI is kind of msi interrupt only used on Non-PCI devices.
+
+To reduce the wired interrupt number connected to GIC,
+Hisilicon designed mbigen to collect and generate interrupt.
+
+
+Non-pci devices can connect to mbigen and generate the
+interrupt by writing ITS register.
+
+The mbigen chip and devices connect to mbigen have the following properties:
+
+Mbigen main node required properties:
+-------------------------------------------
+- compatible: Should be "hisilicon,mbigen-v2"
+
+- reg: Specifies the base physical address and size of the Mbigen
+  registers.
+
+- interrupt controller: Identifies the node as an interrupt controller
+
+- msi-parent: Specifies the MSI controller this mbigen use.
+  For more detail information,please refer to the generic msi-parent binding in
+  Documentation/devicetree/bindings/interrupt-controller/msi.txt.
+
+- num-pins: the total number of pins implemented in this Mbigen
+  instance.
+
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. The value must be 2.
+
+  The 1st cell is hardware pin number of the interrupt.This number is local to
+  each mbigen chip and in the range from 0 to the maximum interrupts number
+  of the mbigen.
+
+  The 2nd cell is the interrupt trigger type.
+	The value of this cell should be:
+	1: rising edge triggered
+	or
+	4: high level triggered
+
+Examples:
+
+	mbigen_device_gmac:intc {
+			compatible = "hisilicon,mbigen-v2";
+			reg = <0x0 0xc0080000 0x0 0x10000>;
+			interrupt-controller;
+			msi-parent = <&its_dsa 0x40b1c>;
+			num-pins = <9>;
+			#interrupt-cells = <2>;
+	};
+
+Devices connect to mbigen required properties:
+----------------------------------------------------
+-interrupt-parent: Specifies the mbigen device node which device connected.
+
+-interrupts:Specifies the interrupt source.
+ For the specific information of each cell in this property,please refer to
+ the "interrupt-cells" description mentioned above.
+
+Examples:
+	gmac0: ethernet@c2080000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0 0xc2080000 0 0x20000>,
+		      <0 0xc0000000 0 0x1000>;
+		interrupt-parent  = <&mbigen_device_gmac>;
+		interrupts =	<656 1>,
+				<657 1>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
index afef6a85ac51..b8e1674c7837 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
@@ -14,6 +14,7 @@ Required properties:
 	"mediatek,mt6582-sysirq"
 	"mediatek,mt6580-sysirq"
 	"mediatek,mt6577-sysirq"
+	"mediatek,mt2701-sysirq"
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Use the same format as specified by GIC in
   Documentation/devicetree/bindings/arm/gic.txt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/microchip,pic32-evic.txt b/Documentation/devicetree/bindings/interrupt-controller/microchip,pic32-evic.txt
new file mode 100644
index 000000000000..c3a1b37c4c35
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/microchip,pic32-evic.txt
@@ -0,0 +1,67 @@
+Microchip PIC32 Interrupt Controller
+====================================
+
+The Microchip PIC32 contains an Enhanced Vectored Interrupt Controller (EVIC).
+It handles all internal and external interrupts. This controller exists outside
+of the CPU and is the arbitrator of all interrupts (including interrupts from
+the CPU itself) before they are presented to the CPU.
+
+External interrupts have a software configurable edge polarity. Non external
+interrupts have a type and polarity that is determined by the source of the
+interrupt.
+
+Required properties
+-------------------
+
+- compatible: Should be "microchip,pic32mzda-evic"
+- reg: Specifies physical base address and size of register range.
+- interrupt-controller: Identifies the node as an interrupt controller.
+- #interrupt cells: Specifies the number of cells used to encode an interrupt
+  source connected to this controller. The value shall be 2 and interrupt
+  descriptor shall have the following format:
+
+	<hw_irq irq_type>
+
+  hw_irq - represents the hardware interrupt number as in the data sheet.
+  irq_type - is used to describe the type and polarity of an interrupt. For
+  internal interrupts use IRQ_TYPE_EDGE_RISING for non persistent interrupts and
+  IRQ_TYPE_LEVEL_HIGH for persistent interrupts. For external interrupts use
+  IRQ_TYPE_EDGE_RISING or IRQ_TYPE_EDGE_FALLING to select the desired polarity.
+
+Optional properties
+-------------------
+- microchip,external-irqs: u32 array of external interrupts with software
+  polarity configuration. This array corresponds to the bits in the INTCON
+  SFR.
+
+Example
+-------
+
+evic: interrupt-controller@1f810000 {
+	compatible = "microchip,pic32mzda-evic";
+	interrupt-controller;
+	#interrupt-cells = <2>;
+	reg = <0x1f810000 0x1000>;
+	microchip,external-irqs = <3 8 13 18 23>;
+};
+
+Each device/peripheral must request its interrupt line with the associated type
+and polarity.
+
+Internal interrupt DTS snippet
+------------------------------
+
+device@1f800000 {
+	...
+	interrupts = <113 IRQ_TYPE_LEVEL_HIGH>;
+	...
+};
+
+External interrupt DTS snippet
+------------------------------
+
+device@1f800000 {
+	...
+	interrupts = <3 IRQ_TYPE_EDGE_RISING>;
+	...
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
index ec96b1f01478..475ae9bd562b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
@@ -22,7 +22,7 @@ Interrupt Controllers bindings used by client devices.
 Example:
 
 	interrupt-controller@18060010 {
-		compatible = "qca,ar9132-misc-intc", qca,ar7100-misc-intc";
+		compatible = "qca,ar9132-misc-intc", "qca,ar7100-misc-intc";
 		reg = <0x18060010 0x4>;
 
 		interrupt-parent = <&cpuintc>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
new file mode 100644
index 000000000000..7f15f1b0325b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
@@ -0,0 +1,16 @@
+TS-4800 FPGA interrupt controller
+
+TS-4800 FPGA has an internal interrupt controller. When one of the
+interrupts is triggered, the SoC is notified, usually using a GPIO as
+parent interrupt source.
+
+Required properties:
+- compatible: should be "technologic,ts4800-irqc"
+- interrupt-controller: identifies the node as an interrupt controller
+- reg: physical base address of the controller and length of memory mapped
+  region
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- interrupt-parent: phandle to the parent interrupt controller this one is
+  cascaded from
+- interrupts: specifies the interrupt line in the interrupt-parent controller
diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
index cd29083e16ec..48ffb38f699e 100644
--- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
+++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
@@ -7,7 +7,15 @@ connected to the IPMMU through a port called micro-TLB.
 
 Required Properties:
 
-  - compatible: Must contain "renesas,ipmmu-vmsa".
+  - compatible: Must contain SoC-specific and generic entries from below.
+
+    - "renesas,ipmmu-r8a73a4" for the R8A73A4 (R-Mobile APE6) IPMMU.
+    - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU.
+    - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU.
+    - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.
+    - "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU.
+    - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU.
+
   - reg: Base address and size of the IPMMU registers.
   - interrupts: Specifiers for the MMU fault interrupts. For instances that
     support secure mode two interrupts must be specified, for non-secure and
@@ -27,7 +35,7 @@ node with the following property:
 Example: R8A7791 IPMMU-MX and VSP1-D0 bus master
 
 	ipmmu_mx: mmu@fe951000 {
-		compatible = "renasas,ipmmu-vmsa";
+		compatible = "renasas,ipmmu-r8a7791", "renasas,ipmmu-vmsa";
 		reg = <0 0xfe951000 0 0x1000>;
 		interrupts = <0 222 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 221 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/media/exynos5-gsc.txt b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
index 0604d42f38d1..5fe9372abb37 100644
--- a/Documentation/devicetree/bindings/media/exynos5-gsc.txt
+++ b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
@@ -7,6 +7,10 @@ Required properties:
 - reg: should contain G-Scaler physical address location and length.
 - interrupts: should contain G-Scaler interrupt number
 
+Optional properties:
+- samsung,sysreg: handle to syscon used to control the system registers to
+  set writeback input and destination
+
 Example:
 
 gsc_0:  gsc@0x13e00000 {
diff --git a/Documentation/devicetree/bindings/media/i2c/adp1653.txt b/Documentation/devicetree/bindings/media/i2c/adp1653.txt
index 5ce66f2104e3..4cce0de40ee9 100644
--- a/Documentation/devicetree/bindings/media/i2c/adp1653.txt
+++ b/Documentation/devicetree/bindings/media/i2c/adp1653.txt
@@ -12,12 +12,13 @@ There are two LED outputs available - flash and indicator. One LED is
 represented by one child node, nodes need to be named "flash" and "indicator".
 
 Required properties of the LED child node:
-- max-microamp : see Documentation/devicetree/bindings/leds/common.txt
+- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
 
 Required properties of the flash LED child node:
 
 - flash-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
 - flash-timeout-us : see Documentation/devicetree/bindings/leds/common.txt
+- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
 
 Example:
 
@@ -29,9 +30,9 @@ Example:
 		flash {
 			flash-timeout-us = <500000>;
 			flash-max-microamp = <320000>;
-			max-microamp = <50000>;
+			led-max-microamp = <50000>;
 		};
 		indicator {
-			max-microamp = <17500>;
+			led-max-microamp = <17500>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
index d4def767bdfe..cc51b1fd6e0c 100644
--- a/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
+++ b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
@@ -35,7 +35,7 @@ Required properties (tsin (child) node):
 
 - tsin-num	: tsin id of the InputBlock (must be between 0 to 6)
 - i2c-bus	: phandle to the I2C bus DT node which the demodulators & tuners on this tsin channel are connected.
-- rst-gpio	: reset gpio for this tsin channel.
+- reset-gpios	: reset gpio for this tsin channel.
 
 Optional properties (tsin (child) node):
 
@@ -55,27 +55,27 @@ Example:
 		status = "okay";
 		reg = <0x08a20000 0x10000>, <0x08a00000 0x4000>;
 		reg-names = "stfe", "stfe-ram";
-		interrupts = <0 34 0>, <0 35 0>;
+		interrupts = <GIC_SPI 34 IRQ_TYPE_NONE>, <GIC_SPI 35 IRQ_TYPE_NONE>;
 		interrupt-names = "stfe-error-irq", "stfe-idle-irq";
-
-		pinctrl-names	= "tsin0-serial", "tsin0-parallel", "tsin3-serial",
-				"tsin4-serial", "tsin5-serial";
-
 		pinctrl-0	= <&pinctrl_tsin0_serial>;
 		pinctrl-1	= <&pinctrl_tsin0_parallel>;
 		pinctrl-2	= <&pinctrl_tsin3_serial>;
 		pinctrl-3	= <&pinctrl_tsin4_serial_alt3>;
 		pinctrl-4	= <&pinctrl_tsin5_serial_alt1>;
-
+		pinctrl-names	= "tsin0-serial",
+				  "tsin0-parallel",
+				  "tsin3-serial",
+				  "tsin4-serial",
+				  "tsin5-serial";
 		clocks = <&clk_s_c0_flexgen CLK_PROC_STFE>;
-		clock-names = "stfe";
+		clock-names = "c8sectpfe";
 
 		/* tsin0 is TSA on NIMA */
 		tsin0: port@0 {
 			tsin-num		= <0>;
 			serial-not-parallel;
 			i2c-bus			= <&ssc2>;
-			rst-gpio		= <&pio15 4 0>;
+			reset-gpios		= <&pio15 4 GPIO_ACTIVE_HIGH>;
 			dvb-card		= <STV0367_TDA18212_NIMA_1>;
 		};
 
@@ -83,7 +83,7 @@ Example:
 			tsin-num		= <3>;
 			serial-not-parallel;
 			i2c-bus			= <&ssc3>;
-			rst-gpio		= <&pio15 7 0>;
+			reset-gpios		= <&pio15 7 GPIO_ACTIVE_HIGH>;
 			dvb-card		= <STV0367_TDA18212_NIMB_1>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt b/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt
index efe35a065714..c81af75bcd88 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt
@@ -1,6 +1,6 @@
 Binding for Qualcomm  Atheros AR7xxx/AR9xxx DDR controller
 
-The DDR controller of the ARxxx and AR9xxx families provides an interface
+The DDR controller of the AR7xxx and AR9xxx families provides an interface
 to flush the FIFO between various devices and the DDR. This is mainly used
 by the IRQ controller to flush the FIFO before running the interrupt handler
 of such devices.
@@ -11,9 +11,9 @@ Required properties:
   "qca,[ar7100|ar7240]-ddr-controller" as fallback.
   On SoC with PCI support "qca,ar7100-ddr-controller" should be used as
   fallback, otherwise "qca,ar7240-ddr-controller" should be used.
-- reg: Base address and size of the controllers memory area
-- #qca,ddr-wb-channel-cells: has to be 1, the index of the write buffer
-  channel
+- reg: Base address and size of the controller's memory area
+- #qca,ddr-wb-channel-cells: Specifies the number of cells needed to encode
+			     the write buffer channel index, should be 1.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt
index 18be0cbfb456..9b30011ecabe 100644
--- a/Documentation/devicetree/bindings/mfd/arizona.txt
+++ b/Documentation/devicetree/bindings/mfd/arizona.txt
@@ -1,4 +1,4 @@
-Wolfson Arizona class audio SoCs
+Cirrus Logic/Wolfson Microelectronics Arizona class audio SoCs
 
 These devices are audio SoCs with extensive digital capabilites and a range
 of analogue I/O.
@@ -6,12 +6,14 @@ of analogue I/O.
 Required properties:
 
   - compatible : One of the following chip-specific strings:
+        "cirrus,cs47l24"
         "wlf,wm5102"
         "wlf,wm5110"
         "wlf,wm8280"
         "wlf,wm8997"
         "wlf,wm8998"
         "wlf,wm1814"
+        "wlf,wm1831"
 
   - reg : I2C slave address when connected using I2C, chip select number when
     using SPI.
@@ -24,7 +26,7 @@ Required properties:
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
-    Documentation/devicetree/bindings/interrupts.txt
+    Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
   - gpio-controller : Indicates this device is a GPIO controller.
   - #gpio-cells : Must be 2. The first cell is the pin number and the
@@ -41,10 +43,21 @@ Required properties:
 
   - SPKVDD-supply : Speaker driver power supply (wm8997)
 
+  - DCVDD-supply : Main power supply (cs47l24, wm1831)
+
+  - MICVDD-supply : Microphone power supply (cs47l24, wm1831)
+
 Optional properties:
 
   - wlf,reset : GPIO specifier for the GPIO controlling /RESET
 
+  - clocks: Should reference the clocks supplied on MCLK1 and MCLK2
+  - clock-names: Should contains two strings:
+      "mclk1" for the clock supplied on MCLK1, recommended to be a high
+      quality audio reference clock
+      "mclk2" for the clock supplied on MCLK2, recommended to be an always on
+      32k clock
+
   - wlf,gpio-defaults : A list of GPIO configuration register values. Defines
     for the appropriate values can found in <dt-bindings/mfd/arizona.txt>. If
     absent, no configuration of these registers is performed. If any entry has
@@ -59,6 +72,12 @@ Optional properties:
     that have not been specified are set to 0 by default. Entries are:
     <IN1, IN2, IN3, IN4> (wm5102, wm5110, wm8280, wm8997)
     <IN1A, IN2A, IN1B, IN2B> (wm8998, wm1814)
+  - wlf,out-mono : A list of boolean values indicating whether each output is
+    mono or stereo. Position within the list indicates the output affected
+    (eg. First entry in the list corresponds to output 1). A non-zero value
+    indicates a mono output. If present, the number of values should be less
+    than or equal to the number of outputs, if less values are supplied the
+    additional outputs will be treated as stereo.
 
   - wlf,dmic-ref : DMIC reference voltage source for each input, can be
     selected from either MICVDD or one of the MICBIAS's, defines
@@ -69,6 +88,7 @@ Optional properties:
   - DCVDD-supply, MICVDD-supply : Power supplies, only need to be specified if
     they are being externally supplied. As covered in
     Documentation/devicetree/bindings/regulator/regulator.txt
+    (wm5102, wm5110, wm8280, wm8997, wm8998, wm1814)
 
 Also see child specific device properties:
   Regulator - ../regulator/arizona-regulator.txt
diff --git a/Documentation/devicetree/bindings/mfd/palmas.txt b/Documentation/devicetree/bindings/mfd/palmas.txt
index eda898978d33..8ae1a32bfb7e 100644
--- a/Documentation/devicetree/bindings/mfd/palmas.txt
+++ b/Documentation/devicetree/bindings/mfd/palmas.txt
@@ -24,7 +24,7 @@ and also the generic series names
 - #interrupt-cells : should be set to 2 for IRQ number and flags
   The first cell is the IRQ number.
   The second cell is the flags, encoded as the trigger masks from
-  Documentation/devicetree/bindings/interrupts.txt
+  Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 - interrupt-parent : The parent interrupt controller.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mfd/s2mpa01.txt b/Documentation/devicetree/bindings/mfd/s2mpa01.txt
deleted file mode 100644
index c13d3d8c3947..000000000000
--- a/Documentation/devicetree/bindings/mfd/s2mpa01.txt
+++ /dev/null
@@ -1,90 +0,0 @@
-
-* Samsung S2MPA01 Voltage and Current Regulator
-
-The Samsung S2MPA01 is a multi-function device which includes high
-efficiency buck converters including Dual-Phase buck converter, various LDOs,
-and an RTC. It is interfaced to the host controller using an I2C interface.
-Each sub-block is addressed by the host system using different I2C slave
-addresses.
-
-Required properties:
-- compatible: Should be "samsung,s2mpa01-pmic".
-- reg: Specifies the I2C slave address of the PMIC block. It should be 0x66.
-
-Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from s2mpa01 are delivered to.
-- interrupts: An interrupt specifier for the sole interrupt generated by the
-  device.
-
-Optional nodes:
-- regulators: The regulators of s2mpa01 that have to be instantiated should be
-  included in a sub-node named 'regulators'. Regulator nodes and constraints
-  included in this sub-node use the standard regulator bindings which are
-  documented elsewhere.
-
-Properties for BUCK regulator nodes:
-- regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500
-  (default), 25000, or 50000. May be 0 for disabling the ramp delay on
-  BUCK{1,2,3,4}.
-
- In the absence of the regulator-ramp-delay property, the default ramp
- delay will be used.
-
-  NOTE: Some BUCKs share the ramp rate setting i.e. same ramp value will be set
-  for a particular group of BUCKs. So provide same regulator-ramp-delay=<value>.
-
-  The following BUCKs share ramp settings:
-  * 1 and 6
-  * 2 and 4
-  * 8, 9, and 10
-
-The following are the names of the regulators that the s2mpa01 PMIC block
-supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
-as per the datasheet of s2mpa01.
-
-	- LDOn
-		  - valid values for n are 1 to 26
-		  - Example: LDO1, LD02, LDO26
-	- BUCKn
-		  - valid values for n are 1 to 10.
-		  - Example: BUCK1, BUCK2, BUCK9
-
-Example:
-
-	s2mpa01_pmic@66 {
-		compatible = "samsung,s2mpa01-pmic";
-		reg = <0x66>;
-
-		regulators {
-			ldo1_reg: LDO1 {
-				regulator-name = "VDD_ALIVE";
-				regulator-min-microvolt = <1000000>;
-				regulator-max-microvolt = <1000000>;
-			};
-
-			ldo2_reg: LDO2 {
-				regulator-name = "VDDQ_MMC2";
-				regulator-min-microvolt = <2800000>;
-				regulator-max-microvolt = <2800000>;
-				regulator-always-on;
-			};
-
-			buck1_reg: BUCK1 {
-				regulator-name = "vdd_mif";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			buck2_reg: BUCK2 {
-				regulator-name = "vdd_arm";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-ramp-delay = <50000>;
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/mfd/s2mps11.txt b/Documentation/devicetree/bindings/mfd/s2mps11.txt
deleted file mode 100644
index 09b94c97faac..000000000000
--- a/Documentation/devicetree/bindings/mfd/s2mps11.txt
+++ /dev/null
@@ -1,153 +0,0 @@
-
-* Samsung S2MPS11/13/14/15 and S2MPU02 Voltage and Current Regulator
-
-The Samsung S2MPS11 is a multi-function device which includes voltage and
-current regulators, RTC, charger controller and other sub-blocks. It is
-interfaced to the host controller using an I2C interface. Each sub-block is
-addressed by the host system using different I2C slave addresses.
-
-Required properties:
-- compatible: Should be one of the following
-	- "samsung,s2mps11-pmic"
-	- "samsung,s2mps13-pmic"
-	- "samsung,s2mps14-pmic"
-	- "samsung,s2mps15-pmic"
-	- "samsung,s2mpu02-pmic".
-- reg: Specifies the I2C slave address of the pmic block. It should be 0x66.
-
-Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from s2mps11 are delivered to.
-- interrupts: Interrupt specifiers for interrupt sources.
-- samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled
-  down. When the system is suspended it will always go down thus triggerring
-  unwanted buck warm reset (setting buck voltages to default values).
-- samsung,s2mps11-acokb-ground: Indicates that ACOKB pin of S2MPS11 PMIC is
-  connected to the ground so the PMIC must manually set PWRHOLD bit in CTRL1
-  register to turn off the power. Usually the ACOKB is pulled up to VBATT so
-  when PWRHOLD pin goes low, the rising ACOKB will trigger power off.
-
-Optional nodes:
-- clocks: s2mps11, s2mps13, s2mps15 and s5m8767 provide three(AP/CP/BT) buffered 32.768
-  KHz outputs, so to register these as clocks with common clock framework
-  instantiate a sub-node named "clocks". It uses the common clock binding
-  documented in :
-  [Documentation/devicetree/bindings/clock/clock-bindings.txt]
-  The s2mps14 provides two (AP/BT) buffered 32.768 KHz outputs.
-  - #clock-cells: should be 1.
-
-  - The following is the list of clocks generated by the controller. Each clock
-    is assigned an identifier and client nodes use this identifier to specify
-    the clock which they consume.
-    Clock               ID           Devices
-    ----------------------------------------------------------
-    32KhzAP		0            S2MPS11, S2MPS13, S2MPS14, S2MPS15, S5M8767
-    32KhzCP		1            S2MPS11, S2MPS13, S2MPS15, S5M8767
-    32KhzBT		2            S2MPS11, S2MPS13, S2MPS14, S2MPS15, S5M8767
-
-  - compatible: Should be one of: "samsung,s2mps11-clk", "samsung,s2mps13-clk",
-		"samsung,s2mps14-clk", "samsung,s5m8767-clk"
-    The s2msp15 uses the same compatible as s2mps13, as both provides similar clocks.
-
-- regulators: The regulators of s2mps11 that have to be instantiated should be
-included in a sub-node named 'regulators'. Regulator nodes included in this
-sub-node should be of the format as listed below.
-
-	regulator_name {
-		[standard regulator constraints....];
-	};
-
- regulator-ramp-delay for BUCKs = [6250/12500/25000(default)/50000] uV/us
-
- BUCK[2/3/4/6] supports disabling ramp delay on hardware, so explicitly
- regulator-ramp-delay = <0> can be used for them to disable ramp delay.
- In the absence of the regulator-ramp-delay property, the default ramp
- delay will be used.
-
-NOTE: Some BUCKs share the ramp rate setting i.e. same ramp value will be set
-for a particular group of BUCKs. So provide same regulator-ramp-delay<value>.
-Grouping of BUCKs sharing ramp rate setting is as follow : BUCK[1, 6],
-BUCK[3, 4], and BUCK[7, 8, 10]
-
-On S2MPS14 the LDO10, LDO11 and LDO12 can be configured to external control
-over GPIO. To turn this feature on this property must be added to the regulator
-sub-node:
-	- samsung,ext-control-gpios: GPIO specifier for one GPIO
-		controlling this regulator (enable/disable);
-Example:
-	LDO12 {
-		regulator-name = "V_EMMC_2.8V";
-		regulator-min-microvolt = <2800000>;
-		regulator-max-microvolt = <2800000>;
-		samsung,ext-control-gpios = <&gpk0 2 0>;
-	};
-
-
-The regulator constraints inside the regulator nodes use the standard regulator
-bindings which are documented elsewhere.
-
-The following are the names of the regulators that the s2mps11 pmic block
-supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
-as per the datasheet of s2mps11.
-
-	- LDOn
-		  - valid values for n are:
-			- S2MPS11: 1 to 38
-			- S2MPS13: 1 to 40
-			- S2MPS14: 1 to 25
-			- S2MPS15: 1 to 27
-			- S2MPU02: 1 to 28
-		  - Example: LDO1, LDO2, LDO28
-	- BUCKn
-		  - valid values for n are:
-			- S2MPS11: 1 to 10
-			- S2MPS13: 1 to 10
-			- S2MPS14: 1 to 5
-			- S2MPS15: 1 to 10
-			- S2MPU02: 1 to 7
-		  - Example: BUCK1, BUCK2, BUCK9
-
-Example:
-
-	s2mps11_pmic@66 {
-		compatible = "samsung,s2mps11-pmic";
-		reg = <0x66>;
-
-		s2m_osc: clocks {
-			compatible = "samsung,s2mps11-clk";
-			#clock-cells = <1>;
-			clock-output-names = "xx", "yy", "zz";
-		};
-
-		regulators {
-			ldo1_reg: LDO1 {
-				regulator-name = "VDD_ABB_3.3V";
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-			};
-
-			ldo2_reg: LDO2 {
-				regulator-name = "VDD_ALIVE_1.1V";
-				regulator-min-microvolt = <1100000>;
-				regulator-max-microvolt = <1100000>;
-				regulator-always-on;
-			};
-
-			buck1_reg: BUCK1 {
-				regulator-name = "vdd_mif";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			buck2_reg: BUCK2 {
-				regulator-name = "vdd_arm";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-ramp-delay = <50000>;
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
new file mode 100644
index 000000000000..cdd079bfc287
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
@@ -0,0 +1,88 @@
+Binding for Samsung S2M and S5M family multi-function device
+============================================================
+
+This is a part of device tree bindings for S2M and S5M family multi-function
+devices.
+
+The Samsung S2MPA01, S2MPS11/13/14/15, S2MPU02 and S5M8767 is a family
+of multi-function devices which include voltage and current regulators, RTC,
+charger controller, clock outputs and other sub-blocks. It is interfaced
+to the host controller using an I2C interface. Each sub-block is usually
+addressed by the host system using different I2C slave addresses.
+
+
+This document describes bindings for main device node. Optional sub-blocks
+must be a sub-nodes to it. Bindings for them can be found in:
+ - bindings/regulator/samsung,s2mpa01.txt
+ - bindings/regulator/samsung,s2mps11.txt
+ - bindings/regulator/samsung,s5m8767.txt
+ - bindings/clock/samsung,s2mps11.txt
+
+
+Required properties:
+ - compatible: Should be one of the following
+	- "samsung,s2mpa01-pmic",
+	- "samsung,s2mps11-pmic",
+	- "samsung,s2mps13-pmic",
+	- "samsung,s2mps14-pmic",
+	- "samsung,s2mps15-pmic",
+	- "samsung,s2mpu02-pmic",
+	- "samsung,s5m8767-pmic".
+ - reg: Specifies the I2C slave address of the pmic block. It should be 0x66.
+
+Optional properties:
+ - interrupt-parent: Specifies the phandle of the interrupt controller to which
+   the interrupts from s2mps11 are delivered to.
+ - interrupts: Interrupt specifiers for interrupt sources.
+ - samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled
+   down. When the system is suspended it will always go down thus triggerring
+   unwanted buck warm reset (setting buck voltages to default values).
+ - samsung,s2mps11-acokb-ground: Indicates that ACOKB pin of S2MPS11 PMIC is
+   connected to the ground so the PMIC must manually set PWRHOLD bit in CTRL1
+   register to turn off the power. Usually the ACOKB is pulled up to VBATT so
+   when PWRHOLD pin goes low, the rising ACOKB will trigger power off.
+
+Example:
+
+	s2mps11_pmic@66 {
+		compatible = "samsung,s2mps11-pmic";
+		reg = <0x66>;
+
+		s2m_osc: clocks {
+			compatible = "samsung,s2mps11-clk";
+			#clock-cells = <1>;
+			clock-output-names = "xx", "yy", "zz";
+		};
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ABB_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDD_ALIVE_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "vdd_arm";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-ramp-delay = <50000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/syscon.txt b/Documentation/devicetree/bindings/mfd/syscon.txt
index fe8150bb3248..408f768686f1 100644
--- a/Documentation/devicetree/bindings/mfd/syscon.txt
+++ b/Documentation/devicetree/bindings/mfd/syscon.txt
@@ -13,6 +13,10 @@ Required properties:
 - compatible: Should contain "syscon".
 - reg: the register region can be accessed from syscon
 
+Optional property:
+- reg-io-width: the size (in bytes) of the IO accesses that should be
+  performed on the device.
+
 Examples:
 gpr: iomuxc-gpr@020e0000 {
 	compatible = "fsl,imx6q-iomuxc-gpr", "syscon";
diff --git a/Documentation/devicetree/bindings/mips/pic32/microchip,pic32mzda.txt b/Documentation/devicetree/bindings/mips/pic32/microchip,pic32mzda.txt
new file mode 100644
index 000000000000..1c8dbc45feec
--- /dev/null
+++ b/Documentation/devicetree/bindings/mips/pic32/microchip,pic32mzda.txt
@@ -0,0 +1,31 @@
+* Microchip PIC32MZDA Platforms
+
+PIC32MZDA Starter Kit
+Required root node properties:
+    - compatible = "microchip,pic32mzda-sk", "microchip,pic32mzda"
+
+CPU nodes:
+----------
+A "cpus" node is required.  Required properties:
+ - #address-cells: Must be 1.
+ - #size-cells: Must be 0.
+A CPU sub-node is also required.  Required properties:
+ - device_type: Must be "cpu".
+ - compatible: Must be "mti,mips14KEc".
+Example:
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "mti,mips14KEc";
+		};
+	};
+
+Boot protocol
+--------------
+In accordance with Unified Hosting Interface Reference Manual (MD01069), the
+bootloader must pass the following arguments to the kernel:
+ - $a0: -2.
+ - $a1: KSEG0 address of the flattened device-tree blob.
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index cae29eb5733d..ff611fa66871 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -11,6 +11,7 @@ Required properties:
 	- "renesas,mmcif-r8a7740" for the MMCIF found in r8a7740 SoCs
 	- "renesas,mmcif-r8a7790" for the MMCIF found in r8a7790 SoCs
 	- "renesas,mmcif-r8a7791" for the MMCIF found in r8a7791 SoCs
+	- "renesas,mmcif-r8a7793" for the MMCIF found in r8a7793 SoCs
 	- "renesas,mmcif-r8a7794" for the MMCIF found in r8a7794 SoCs
 
 - clocks: reference to the functional clock
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
index 4ff7128ee3b2..c2546ced9c02 100644
--- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -45,6 +45,8 @@ Required properties:
 - #size-cells      : <0>
 
 Optional properties:
+- clock                     : reference to the clock for the NAND controller
+- clock-names               : "nand" (required for the above clock)
 - brcm,nand-has-wp          : Some versions of this IP include a write-protect
                               (WP) control bit. It is always available on >=
                               v7.0. Use this property to describe the rare
@@ -72,6 +74,12 @@ we define additional 'compatible' properties and associated register resources w
        and enable registers
      - reg-names: (required) "nand-int-base"
 
+   * "brcm,nand-bcm6368"
+     - compatible: should contain "brcm,nand-bcm<soc>", "brcm,nand-bcm6368"
+     - reg: (required) the 'NAND_INTR_BASE' register range, with combined status
+       and enable registers, and boot address registers
+     - reg-names: (required) "nand-int-base"
+
    * "brcm,nand-iproc"
      - reg: (required) the "IDM" register range, for interrupt enable and APB
        bus access endianness configuration, and the "EXT" register range,
@@ -148,3 +156,27 @@ nand@f0442800 {
 		};
 	};
 };
+
+nand@10000200 {
+	compatible = "brcm,nand-bcm63168", "brcm,nand-bcm6368",
+		"brcm,brcmnand-v4.0", "brcm,brcmnand";
+	reg = <0x10000200 0x180>,
+	      <0x10000600 0x200>,
+	      <0x100000b0 0x10>;
+	reg-names = "nand", "nand-cache", "nand-int-base";
+	interrupt-parent = <&periph_intc>;
+	interrupts = <50>;
+	clocks = <&periph_clk 20>;
+	clock-names = "nand";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	nand0: nandcs@0 {
+		compatible = "brcm,nandcs";
+		reg = <0>;
+		nand-on-flash-bbt;
+		nand-ecc-strength = <1>;
+		nand-ecc-step-size = <512>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
index 862aa2f8837a..00c587b3d3ae 100644
--- a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
+++ b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
@@ -2,7 +2,8 @@
 
 Required properties:
   - compatible : Should be "fsl,vf610-qspi", "fsl,imx6sx-qspi",
-		 "fsl,imx7d-qspi", "fsl,imx6ul-qspi"
+		 "fsl,imx7d-qspi", "fsl,imx6ul-qspi",
+		 "fsl,ls1021-qspi"
   - reg : the first contains the register location and length,
           the second contains the memory mapping address and length
   - reg-names: Should contain the reg names "QuadSPI" and "QuadSPI-memory"
diff --git a/Documentation/devicetree/bindings/mtd/ingenic,jz4780-nand.txt b/Documentation/devicetree/bindings/mtd/ingenic,jz4780-nand.txt
new file mode 100644
index 000000000000..29ea5853ca91
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/ingenic,jz4780-nand.txt
@@ -0,0 +1,86 @@
+* Ingenic JZ4780 NAND/BCH
+
+This file documents the device tree bindings for NAND flash devices on the
+JZ4780. NAND devices are connected to the NEMC controller (described in
+memory-controllers/ingenic,jz4780-nemc.txt), and thus NAND device nodes must
+be children of the NEMC node.
+
+Required NAND controller device properties:
+- compatible: Should be set to "ingenic,jz4780-nand".
+- reg: For each bank with a NAND chip attached, should specify a bank number,
+  an offset of 0 and a size of 0x1000000 (i.e. the whole NEMC bank).
+
+Optional NAND controller device properties:
+- ingenic,bch-controller: To make use of the hardware BCH controller, this
+  property must contain a phandle for the BCH controller node. The required
+  properties for this node are described below. If this is not specified,
+  software BCH will be used instead.
+
+Optional children nodes:
+- Individual NAND chips are children of the NAND controller node.
+
+Required children node properties:
+- reg: An integer ranging from 1 to 6 representing the CS line to use.
+
+Optional children node properties:
+- nand-ecc-step-size: ECC block size in bytes.
+- nand-ecc-strength: ECC strength (max number of correctable bits).
+- nand-ecc-mode: String, operation mode of the NAND ecc mode. "hw" by default
+- nand-on-flash-bbt: boolean to enable on flash bbt option, if not present false
+- rb-gpios: GPIO specifier for the busy pin.
+- wp-gpios: GPIO specifier for the write protect pin.
+
+Optional child node of NAND chip nodes:
+- partitions: see Documentation/devicetree/bindings/mtd/partition.txt
+
+Example:
+
+nemc: nemc@13410000 {
+	...
+
+	nandc: nand-controller@1 {
+		compatible = "ingenic,jz4780-nand";
+		reg = <1 0 0x1000000>;	/* Bank 1 */
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ingenic,bch-controller = <&bch>;
+
+		nand@1 {
+			reg = <1>;
+
+			nand-ecc-step-size = <1024>;
+			nand-ecc-strength = <24>;
+			nand-ecc-mode = "hw";
+			nand-on-flash-bbt;
+
+			rb-gpios = <&gpa 20 GPIO_ACTIVE_LOW>;
+			wp-gpios = <&gpf 22 GPIO_ACTIVE_LOW>;
+
+			partitions {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				...
+			}
+		};
+	};
+};
+
+The BCH controller is a separate SoC component used for error correction on
+NAND devices. The following is a description of the device properties for a
+BCH controller.
+
+Required BCH properties:
+- compatible: Should be set to "ingenic,jz4780-bch".
+- reg: Should specify the BCH controller registers location and length.
+- clocks: Clock for the BCH controller.
+
+Example:
+
+bch: bch@134d0000 {
+	compatible = "ingenic,jz4780-bch";
+	reg = <0x134d0000 0x10000>;
+
+	clocks = <&cgu JZ4780_CLK_BCH>;
+};
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 2bee68103b01..2c91c03e7eb0 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -1,15 +1,61 @@
-* MTD SPI driver for ST M25Pxx (and similar) serial flash chips
+* SPI NOR flash: ST M25Pxx (and similar) serial flash chips
 
 Required properties:
 - #address-cells, #size-cells : Must be present if the device has sub-nodes
   representing partitions.
 - compatible : May include a device-specific string consisting of the
-               manufacturer and name of the chip. Bear in mind the DT binding
-               is not Linux-only, but in case of Linux, see the "m25p_ids"
-               table in drivers/mtd/devices/m25p80.c for the list of supported
-               chips.
+               manufacturer and name of the chip. A list of supported chip
+               names follows.
                Must also include "jedec,spi-nor" for any SPI NOR flash that can
                be identified by the JEDEC READ ID opcode (0x9F).
+
+               Supported chip names:
+                 at25df321a
+                 at25df641
+                 at26df081a
+                 mr25h256
+                 mx25l4005a
+                 mx25l1606e
+                 mx25l6405d
+                 mx25l12805d
+                 mx25l25635e
+                 n25q064
+                 n25q128a11
+                 n25q128a13
+                 n25q512a
+                 s25fl256s1
+                 s25fl512s
+                 s25sl12801
+                 s25fl008k
+                 s25fl064k
+                 sst25vf040b
+                 m25p40
+                 m25p80
+                 m25p16
+                 m25p32
+                 m25p64
+                 m25p128
+                 w25x80
+                 w25x32
+                 w25q32
+                 w25q32dw
+                 w25q80bl
+                 w25q128
+                 w25q256
+
+               The following chip names have been used historically to
+               designate quirky versions of flash chips that do not support the
+               JEDEC READ ID opcode (0x9F):
+                 m25p05-nonjedec
+                 m25p10-nonjedec
+                 m25p20-nonjedec
+                 m25p40-nonjedec
+                 m25p80-nonjedec
+                 m25p16-nonjedec
+                 m25p32-nonjedec
+                 m25p64-nonjedec
+                 m25p128-nonjedec
+
 - reg : Chip-Select number
 - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at
 
diff --git a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
new file mode 100644
index 000000000000..fb314f09861b
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
@@ -0,0 +1,41 @@
+* Serial NOR flash controller for MTK MT81xx (and similar)
+
+Required properties:
+- compatible: 	  should be "mediatek,mt8173-nor";
+- reg: 		  physical base address and length of the controller's register
+- clocks: 	  the phandle of the clocks needed by the nor controller
+- clock-names: 	  the names of the clocks
+		  the clocks should be named "spi" and "sf". "spi" is used for spi bus,
+		  and "sf" is used for controller, these are the clocks witch
+		  hardware needs to enabling nor flash and nor flash controller.
+		  See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
+- #address-cells: should be <1>
+- #size-cells:	  should be <0>
+
+The SPI flash must be a child of the nor_flash node and must have a
+compatible property. Also see jedec,spi-nor.txt.
+
+Required properties:
+- compatible:	  May include a device-specific string consisting of the manufacturer
+		  and name of the chip. Must also include "jedec,spi-nor" for any
+		  SPI NOR flash that can be identified by the JEDEC READ ID opcode (0x9F).
+- reg :		  Chip-Select number
+
+Example:
+
+nor_flash: spi@1100d000 {
+	compatible = "mediatek,mt8173-nor";
+	reg = <0 0x1100d000 0 0xe0>;
+	clocks = <&pericfg CLK_PERI_SPI>,
+		 <&topckgen CLK_TOP_SPINFI_IFR_SEL>;
+	clock-names = "spi", "sf";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "disabled";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+	};
+};
+
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
index 1c63e40659fc..81a224da63be 100644
--- a/Documentation/devicetree/bindings/mtd/partition.txt
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -32,6 +32,8 @@ Optional properties:
   partition should only be mounted read-only. This is usually used for flash
   partitions containing early-boot firmware images or data which should not be
   clobbered.
+- lock : Do not unlock the partition at initialization time (not supported on
+  all devices)
 
 Examples:
 
diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
index 451fef26b4df..10587bdadbbe 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
@@ -68,7 +68,7 @@ ethernet@f0b60000 {
 		phy1: ethernet-phy@1 {
 			max-speed = <1000>;
 			reg = <0x1>;
-			compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22";
+			compatible = "ethernet-phy-ieee802.3-c22";
 		};
 	};
 };
@@ -115,7 +115,7 @@ ethernet@f0ba0000 {
 		phy0: ethernet-phy@0 {
 			max-speed = <1000>;
 			reg = <0x0>;
-			compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22";
+			compatible = "ethernet-phy-ieee802.3-c22";
 		};
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt
deleted file mode 100644
index 4451ee973223..000000000000
--- a/Documentation/devicetree/bindings/net/cdns-emac.txt
+++ /dev/null
@@ -1,20 +0,0 @@
-* Cadence EMAC Ethernet controller
-
-Required properties:
-- compatible: Should be "cdns,[<chip>-]{emac}"
-  Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC.
-  Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.
-  Or the generic form: "cdns,emac".
-- reg: Address and length of the register set for the device
-- interrupts: Should contain macb interrupt
-- phy-mode: see ethernet.txt file in the same directory.
-
-Examples:
-
-	macb0: ethernet@fffc4000 {
-		compatible = "cdns,at91rm9200-emac";
-		reg = <0xfffc4000 0x4000>;
-		interrupts = <21>;
-		phy-mode = "rmii";
-		local-mac-address = [3a 0e 03 04 05 06];
-	};
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index 04e6bef3ac3f..5fdbbcdf8c4b 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -31,6 +31,8 @@ A switch child node has the following optional property:
 			  switch. Must be set if the switch can not detect
 			  the presence and/or size of a connected EEPROM,
 			  otherwise optional.
+- reset-gpios		: phandle and specifier to a gpio line connected to
+			  reset pin of the switch chip.
 
 A switch may have multiple "port" children nodes
 
@@ -114,6 +116,7 @@ Example:
 			#size-cells = <0>;
 			reg = <17 1>;	/* MDIO address 17, switch 1 in tree */
 			mii-bus = <&mii_bus1>;
+			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
 
 			switch1port0: port@0 {
 				reg = <0>;
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
index 80411b2f0490..ecacfa44b1eb 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2".
   "hisilicon,hns-dsaf-v1" is for hip05.
   "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612.
-- dsa-name: dsa fabric name who provide this interface.
-  should be "dsafX", X is the dsaf id.
 - mode: dsa fabric mode string. only support one of dsaf modes like these:
 		"2port-64vf",
 		"6port-16rss",
@@ -26,9 +24,8 @@ Required properties:
 
 Example:
 
-dsa: dsa@c7000000 {
+dsaf0: dsa@c7000000 {
 	compatible = "hisilicon,hns-dsaf-v1";
-	dsa_name = "dsaf0";
 	mode = "6port-16rss";
 	interrupt-parent = <&mbigen_dsa>;
 	reg = <0x0 0xC0000000 0x0 0x420000
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt
index 9c23fdf25018..4a7ede9657b0 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt
@@ -1,7 +1,12 @@
 Hisilicon MDIO bus controller
 
 Properties:
-- compatible: "hisilicon,mdio","hisilicon,hns-mdio".
+- compatible: can be one of:
+	"hisilicon,hns-mdio"
+	"hisilicon,mdio"
+  "hisilicon,hns-mdio" is recommended to be used for hip05 and later SOCs,
+  while "hisilicon,mdio" is optional for backwards compatibility only on
+  hip04 Soc.
 - reg: The base address of the MDIO bus controller register bank.
 - #address-cells: Must be <1>.
 - #size-cells: Must be <0>.  MDIO addresses have no size component.
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
index 41d19be7011e..e6a9d1c30878 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
@@ -4,8 +4,9 @@ Required properties:
 - compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2".
   "hisilicon,hns-nic-v1" is for hip05.
   "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612.
-- ae-name: accelerator name who provides this interface,
-  is simply a name referring to the name of name in the accelerator node.
+- ae-handle: accelerator engine handle for hns,
+  specifies a reference to the associating hardware driver node.
+  see Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
 - port-id: is the index of port provided by DSAF (the accelerator). DSAF can
   connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They
   are called debug ports.
@@ -41,7 +42,7 @@ Example:
 
 	ethernet@0{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <0>;
 		local-mac-address = [a2 14 e4 4b 56 76];
 	};
diff --git a/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt
new file mode 100644
index 000000000000..dea5124cdc52
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt
@@ -0,0 +1,18 @@
+* ADF7242 IEEE 802.15.4 *
+
+Required properties:
+  - compatible:		should be "adi,adf7242"
+  - spi-max-frequency:	maximal bus speed (12.5 MHz)
+  - reg:		the chipselect index
+  - interrupts:		the interrupt generated by the device via pin IRQ1.
+			IRQ_TYPE_LEVEL_HIGH (4) or IRQ_TYPE_EDGE_FALLING (1)
+
+Example:
+
+	adf7242@0 {
+		compatible = "adi,adf7242";
+		spi-max-frequency = <10000000>;
+		reg = <0>;
+		interrupts = <98 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-parent = <&gpio3>;
+	};
diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt
index b5d79761ac97..d2e243b1ec0e 100644
--- a/Documentation/devicetree/bindings/net/macb.txt
+++ b/Documentation/devicetree/bindings/net/macb.txt
@@ -2,15 +2,19 @@
 
 Required properties:
 - compatible: Should be "cdns,[<chip>-]{macb|gem}"
+  Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC.
   Use "cdns,at91sam9260-macb" for Atmel at91sam9 SoCs or the 10/100Mbit IP
   available on sama5d3 SoCs.
+  Use "cdns,np4-macb" for NP4 SoC devices.
   Use "cdns,at32ap7000-macb" for other 10/100 usage or use the generic form: "cdns,macb".
   Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on
   the Cadence GEM, or the generic form: "cdns,gem".
   Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs.
   Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs.
   Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs.
+  Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.
   Use "cdns,zynqmp-gem" for Zynq Ultrascale+ MPSoC.
+  Or the generic form: "cdns,emac".
 - reg: Address and length of the register set for the device
 - interrupts: Should contain macb interrupt
 - phy-mode: See ethernet.txt file in the same directory.
@@ -19,6 +23,9 @@ Required properties:
 	Optional elements: 'tx_clk'
 - clocks: Phandles to input clocks.
 
+Optional properties for PHY child node:
+- reset-gpios : Should specify the gpio for phy reset
+
 Examples:
 
 	macb0: ethernet@fffc4000 {
@@ -29,4 +36,8 @@ Examples:
 		local-mac-address = [3a 0e 03 04 05 06];
 		clock-names = "pclk", "hclk", "tx_clk";
 		clocks = <&clkc 30>, <&clkc 30>, <&clkc 13>;
+		ethernet-phy@1 {
+			reg = <0x1>;
+			reset-gpios = <&pioE 6 1>;
+		};
 	};
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index aeea50c84e92..d0cb8693963b 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -6,12 +6,17 @@ Required properties:
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
 - phy-mode: See ethernet.txt file in the same directory
-- clocks: a pointer to the reference clock for this device.
+- clocks: List of clocks for this device. At least one clock is
+  mandatory for the core clock. If several clocks are given, then the
+  clock-names property must be used to identify them.
 
 Optional properties:
 - tx-csum-limit: maximum mtu supported by port that allow TX checksum.
   Value is presented in bytes. If not used, by default 1600B is set for
   "marvell,armada-370-neta" and 9800B for others.
+- clock-names: List of names corresponding to clocks property; shall be
+  "core" for core clock and "bus" for the optional bus clock.
+
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
index 79384113c2b0..694987d3c17a 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
@@ -38,7 +38,6 @@ Example :
 
 			phy11: ethernet-phy@1 {
 				reg = <1>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -48,7 +47,6 @@ Example :
 			};
 			phy12: ethernet-phy@2 {
 				reg = <2>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -58,7 +56,6 @@ Example :
 			};
 			phy13: ethernet-phy@3 {
 				reg = <3>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -68,7 +65,6 @@ Example :
 			};
 			phy14: ethernet-phy@4 {
 				reg = <4>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -85,7 +81,6 @@ Example :
 
 			phy21: ethernet-phy@1 {
 				reg = <1>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -95,7 +90,6 @@ Example :
 			};
 			phy22: ethernet-phy@2 {
 				reg = <2>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -105,7 +99,6 @@ Example :
 			};
 			phy23: ethernet-phy@3 {
 				reg = <3>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -115,7 +108,6 @@ Example :
 			};
 			phy24: ethernet-phy@4 {
 				reg = <4>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt
index f65606f8d632..491f5bd55203 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux.txt
@@ -47,7 +47,6 @@ Example :
 
 			phy11: ethernet-phy@1 {
 				reg = <1>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -57,7 +56,6 @@ Example :
 			};
 			phy12: ethernet-phy@2 {
 				reg = <2>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -67,7 +65,6 @@ Example :
 			};
 			phy13: ethernet-phy@3 {
 				reg = <3>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -77,7 +74,6 @@ Example :
 			};
 			phy14: ethernet-phy@4 {
 				reg = <4>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -94,7 +90,6 @@ Example :
 
 			phy21: ethernet-phy@1 {
 				reg = <1>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -104,7 +99,6 @@ Example :
 			};
 			phy22: ethernet-phy@2 {
 				reg = <2>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -114,7 +108,6 @@ Example :
 			};
 			phy23: ethernet-phy@3 {
 				reg = <3>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
@@ -124,7 +117,6 @@ Example :
 			};
 			phy24: ethernet-phy@4 {
 				reg = <4>;
-				compatible = "marvell,88e1149r";
 				marvell,reg-init = <3 0x10 0 0x5777>,
 					<3 0x11 0 0x00aa>,
 					<3 0x12 0 0x4105>,
diff --git a/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
new file mode 100644
index 000000000000..aa6313024176
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
@@ -0,0 +1,26 @@
+Mediatek Gigabit Switch
+=======================
+
+The mediatek gigabit switch can be found on Mediatek SoCs (mt7620, mt7621).
+
+Required properties:
+- compatible: Should be "mediatek,mt7620-gsw" or "mediatek,mt7621-gsw"
+- reg: Address and length of the register set for the device
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the gigabit switches interrupt
+- resets: Should contain the gigabit switches resets
+- reset-names: Should contain the reset names "gsw"
+
+Example:
+
+gsw@10110000 {
+	compatible = "ralink,mt7620-gsw";
+	reg = <0x10110000 8000>;
+
+	resets = <&rstctrl 23>;
+	reset-names = "gsw";
+
+	interrupt-parent = <&intc>;
+	interrupts = <17>;
+};
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
index 692076fda0e5..f9c32adab5c6 100644
--- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
@@ -1,8 +1,9 @@
 Micrel KSZ9021/KSZ9031 Gigabit Ethernet PHY
 
-Some boards require special tuning values, particularly when it comes to
-clock delays. You can specify clock delay values by adding
-micrel-specific properties to an Ethernet OF device node.
+Some boards require special tuning values, particularly when it comes
+to clock delays. You can specify clock delay values in the PHY OF
+device node. Deprecated, but still supported, these properties can
+also be added to an Ethernet OF device node.
 
 Note that these settings are applied after any phy-specific fixup from
 phy_fixup_list (see phy_init_hw() from drivers/net/phy/phy_device.c),
@@ -57,16 +58,6 @@ KSZ9031:
 
 Examples:
 
-	/* Attach to an Ethernet device with autodetected PHY */
-	&enet {
-		rxc-skew-ps = <3000>;
-		rxdv-skew-ps = <0>;
-		txc-skew-ps = <3000>;
-		txen-skew-ps = <0>;
-		status = "okay";
-	};
-
-	/* Attach to an explicitly-specified PHY */
 	mdio {
 		phy0: ethernet-phy@0 {
 			rxc-skew-ps = <3000>;
diff --git a/Documentation/devicetree/bindings/net/nfc/st95hf.txt b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
new file mode 100644
index 000000000000..ea3178bc9ddd
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
@@ -0,0 +1,50 @@
+* STMicroelectronics : NFC Transceiver ST95HF
+
+ST NFC Transceiver is required to attach with SPI bus.
+ST95HF node should be defined in DT as SPI slave device of SPI
+master with which ST95HF transceiver is physically connected.
+The properties defined below are required to be the part of DT
+to include ST95HF transceiver into the platform.
+
+Required properties:
+===================
+- reg: Address of SPI slave "ST95HF transceiver" on SPI master bus.
+
+- compatible: should be "st,st95hf" for ST95HF NFC transceiver
+
+- spi-max-frequency: Max. operating SPI frequency for ST95HF
+	transceiver.
+
+- enable-gpio: GPIO line to enable ST95HF transceiver.
+
+- interrupt-parent : Standard way to specify the controller to which
+	ST95HF transceiver's interrupt is routed.
+
+- interrupts : Standard way to define ST95HF transceiver's out
+	interrupt.
+
+Optional property:
+=================
+- st95hfvin-supply : This is an optional property. It contains a
+	phandle to ST95HF transceiver's regulator supply node in DT.
+
+Example:
+=======
+spi@9840000 {
+	reg = <0x9840000 0x110>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	cs-gpios = <&pio0 4>;
+	status = "okay";
+
+	st95hf@0{
+		reg = <0>;
+		compatible = "st,st95hf";
+		status = "okay";
+		spi-max-frequency = <1000000>;
+		enable-gpio = <&pio4 0>;
+		interrupt-parent = <&pio0>;
+		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 525e1658f2da..bc1c3c8bf8fa 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -17,8 +17,7 @@ Optional Properties:
   "ethernet-phy-ieee802.3-c22" or "ethernet-phy-ieee802.3-c45" for
   PHYs that implement IEEE802.3 clause 22 or IEEE802.3 clause 45
   specifications. If neither of these are specified, the default is to
-  assume clause 22. The compatible list may also contain other
-  elements.
+  assume clause 22.
 
   If the phy's identifier is known then the list may contain an entry
   of the form: "ethernet-phy-idAAAA.BBBB" where
@@ -28,6 +27,9 @@ Optional Properties:
             4 hex digits. This is the chip vendor OUI bits 19:24,
             followed by 10 bits of a vendor specific ID.
 
+  The compatible list should not contain other values than those
+  listed here.
+
 - max-speed: Maximum PHY supported speed (10, 100, 1000...)
 
 - broken-turn-around: If set, indicates the PHY device does not correctly
diff --git a/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
new file mode 100644
index 000000000000..88b095d1f13b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
@@ -0,0 +1,61 @@
+Ralink Frame Engine Ethernet controller
+=======================================
+
+The Ralink frame engine ethernet controller can be found on Ralink and
+Mediatek SoCs (RT288x, RT3x5x, RT366x, RT388x, rt5350, mt7620, mt7621, mt76x8).
+
+Depending on the SoC, there is a number of ports connected to the CPU port
+directly and/or via a (gigabit-)switch.
+
+* Ethernet controller node
+
+Required properties:
+- compatible: Should be one of "ralink,rt2880-eth", "ralink,rt3050-eth",
+  "ralink,rt3050-eth", "ralink,rt3883-eth", "ralink,rt5350-eth",
+  "mediatek,mt7620-eth", "mediatek,mt7621-eth"
+- reg: Address and length of the register set for the device
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the frame engines interrupt
+- resets: Should contain the frame engines resets
+- reset-names: Should contain the reset names "fe". If a switch is present
+  "esw" is also required.
+
+
+* Ethernet port node
+
+Required properties:
+- compatible: Should be "ralink,eth-port"
+- reg: The number of the physical port
+- phy-handle: reference to the node describing the phy
+
+Example:
+
+mdio-bus {
+	...
+	phy0: ethernet-phy@0 {
+		phy-mode = "mii";
+		reg = <0>;
+	};
+};
+
+ethernet@400000 {
+	compatible = "ralink,rt2880-eth";
+	reg = <0x00400000 10000>;
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	resets = <&rstctrl 18>;
+	reset-names = "fe";
+
+	interrupt-parent = <&cpuintc>;
+	interrupts = <5>;
+
+	port@0 {
+		compatible = "ralink,eth-port";
+		reg = <0>;
+		phy-handle = <&phy0>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
new file mode 100644
index 000000000000..2e79bd376c56
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
@@ -0,0 +1,32 @@
+Ralink Fast Ethernet Embedded Switch
+====================================
+
+The ralink fast ethernet embedded switch can be found on Ralink and Mediatek
+SoCs (RT3x5x, RT5350, MT76x8).
+
+Required properties:
+- compatible: Should be "ralink,rt3050-esw"
+- reg: Address and length of the register set for the device
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the embedded switches interrupt
+- resets: Should contain the embedded switches resets
+- reset-names: Should contain the reset names "esw"
+
+Optional properties:
+- ralink,portmap: can be used to choose if the default switch setup is
+  llllw or wllll
+- ralink,led_polarity: override the active high/low settings of the leds
+
+Example:
+
+esw@10110000 {
+	compatible = "ralink,rt3050-esw";
+	reg = <0x10110000 8000>;
+
+	resets = <&rstctrl 23>;
+	reset-names = "esw";
+
+	interrupt-parent = <&intc>;
+	interrupts = <17>;
+};
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index b486f3f5f6a3..c8ac222eac67 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -5,8 +5,18 @@ interface contains.
 
 Required properties:
 - compatible: "renesas,etheravb-r8a7790" if the device is a part of R8A7790 SoC.
+	      "renesas,etheravb-r8a7791" if the device is a part of R8A7791 SoC.
+	      "renesas,etheravb-r8a7792" if the device is a part of R8A7792 SoC.
+	      "renesas,etheravb-r8a7793" if the device is a part of R8A7793 SoC.
 	      "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC.
 	      "renesas,etheravb-r8a7795" if the device is a part of R8A7795 SoC.
+	      "renesas,etheravb-rcar-gen2" for generic R-Car Gen 2 compatible interface.
+	      "renesas,etheravb-rcar-gen3" for generic R-Car Gen 3 compatible interface.
+
+	      When compatible with the generic version, nodes must list the
+	      SoC-specific version corresponding to the platform first
+	      followed by the generic version.
+
 - reg: offset and length of (1) the register block and (2) the stream buffer.
 - interrupts: A list of interrupt-specifiers, one for each entry in
 	      interrupt-names.
@@ -37,7 +47,7 @@ Optional properties:
 Example:
 
 	ethernet@e6800000 {
-		compatible = "renesas,etheravb-r8a7795";
+		compatible = "renesas,etheravb-r8a7795", "renesas,etheravb-rcar-gen3";
 		reg = <0 0xe6800000 0 0x800>, <0 0xe6a00000 0 0x10000>;
 		interrupt-parent = <&gic>;
 		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
@@ -72,8 +82,8 @@ Example:
 				  "ch16", "ch17", "ch18", "ch19",
 				  "ch20", "ch21", "ch22", "ch23",
 				  "ch24";
-		clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>;
-		power-domains = <&cpg_clocks>;
+		clocks = <&cpg CPG_MOD 812>;
+		power-domains = <&cpg>;
 		phy-mode = "rgmii-id";
 		phy-handle = <&phy0>;
 
diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
index 3a9d67951606..72d82d684342 100644
--- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
@@ -11,6 +11,8 @@ Required properties:
 		  designware version numbers documented in stmmac.txt
  - altr,sysmgr-syscon : Should be the phandle to the system manager node that
    encompasses the glue register, the register offset, and the register shift.
+ - altr,f2h_ptp_ref_clk use f2h_ptp_ref_clk instead of default eosc1 clock
+   for ptp ref clk. This affects all emacs as the clock is common.
 
 Optional properties:
 altr,emac-splitter: Should be the phandle to the emac splitter soft IP node if
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index f34fc3c81a75..e862a922bd3f 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -35,18 +35,18 @@ Optional properties:
 - reset-names: Should contain the reset signal name "stmmaceth", if a
 	reset phandle is given
 - max-frame-size: See ethernet.txt file in the same directory
-- clocks: If present, the first clock should be the GMAC main clock and
-  the second clock should be peripheral's register interface clock. Further
-  clocks may be specified in derived bindings.
-- clock-names: One name for each entry in the clocks property, the
-  first one should be "stmmaceth" and the second one should be "pclk".
-- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
-  available this clock is used for programming the Timestamp Addend Register.
-  If not passed then the system clock will be used and this is fine on some
-  platforms.
+- clocks: If present, the first clock should be the GMAC main clock
+  The optional second clock should be peripheral's register interface clock.
+  The third optional clock should be the ptp reference clock.
+  Further clocks may be specified in derived bindings.
+- clock-names: One name for each entry in the clocks property.
+  The first one should be "stmmaceth".
+  The optional second one should be "pclk".
+  The optional third one should be "clk_ptp_ref".
 - snps,burst_len: The AXI burst lenth value of the AXI BUS MODE register.
 - tx-fifo-depth: See ethernet.txt file in the same directory
 - rx-fifo-depth: See ethernet.txt file in the same directory
+- mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus.
 
 Examples:
 
@@ -65,4 +65,11 @@ Examples:
 		tx-fifo-depth = <16384>;
 		clocks = <&clock>;
 		clock-names = "stmmaceth";
+		mdio0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "snps,dwmac-mdio";
+			phy1: ethernet-phy@0 {
+			};
+		};
 	};
diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 0cb44dc21f97..601256fe8c0d 100644
--- a/Documentation/devicetree/bindings/opp/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -45,21 +45,10 @@ Devices supporting OPPs must set their "operating-points-v2" property with
 phandle to a OPP table in their DT node. The OPP core will use this phandle to
 find the operating points for the device.
 
-Devices may want to choose OPP tables at runtime and so can provide a list of
-phandles here. But only *one* of them should be chosen at runtime. This must be
-accompanied by a corresponding "operating-points-names" property, to uniquely
-identify the OPP tables.
-
 If required, this can be extended for SoC vendor specfic bindings. Such bindings
 should be documented as Documentation/devicetree/bindings/power/<vendor>-opp.txt
 and should have a compatible description like: "operating-points-v2-<vendor>".
 
-Optional properties:
-- operating-points-names: Names of OPP tables (required if multiple OPP
-  tables are present), to uniquely identify them. The same list must be present
-  for all the CPUs which are sharing clock/voltage rails and hence the OPP
-  tables.
-
 * OPP Table Node
 
 This describes the OPPs belonging to a device. This node can have following
@@ -100,6 +89,14 @@ Optional properties:
   Entries for multiple regulators must be present in the same order as
   regulators are specified in device's DT node.
 
+- opp-microvolt-<name>: Named opp-microvolt property. This is exactly similar to
+  the above opp-microvolt property, but allows multiple voltage ranges to be
+  provided for the same OPP. At runtime, the platform can pick a <name> and
+  matching opp-microvolt-<name> property will be enabled for all OPPs. If the
+  platform doesn't pick a specific <name> or the <name> doesn't match with any
+  opp-microvolt-<name> properties, then opp-microvolt property shall be used, if
+  present.
+
 - opp-microamp: The maximum current drawn by the device in microamperes
   considering system specific parameters (such as transients, process, aging,
   maximum operating temperature range etc.) as necessary. This may be used to
@@ -112,6 +109,9 @@ Optional properties:
   for few regulators, then this should be marked as zero for them. If it isn't
   required for any regulator, then this property need not be present.
 
+- opp-microamp-<name>: Named opp-microamp property. Similar to
+  opp-microvolt-<name> property, but for microamp instead.
+
 - clock-latency-ns: Specifies the maximum possible transition latency (in
   nanoseconds) for switching to this OPP from any other OPP.
 
@@ -123,6 +123,26 @@ Optional properties:
 - opp-suspend: Marks the OPP to be used during device suspend. Only one OPP in
   the table should have this.
 
+- opp-supported-hw: This enables us to select only a subset of OPPs from the
+  larger OPP table, based on what version of the hardware we are running on. We
+  still can't have multiple nodes with the same opp-hz value in OPP table.
+
+  It's an user defined array containing a hierarchy of hardware version numbers,
+  supported by the OPP. For example: a platform with hierarchy of three levels
+  of versions (A, B and C), this field should be like <X Y Z>, where X
+  corresponds to Version hierarchy A, Y corresponds to version hierarchy B and Z
+  corresponds to version hierarchy C.
+
+  Each level of hierarchy is represented by a 32 bit value, and so there can be
+  only 32 different supported version per hierarchy. i.e. 1 bit per version. A
+  value of 0xFFFFFFFF will enable the OPP for all versions for that hierarchy
+  level. And a value of 0x00000000 will disable the OPP completely, and so we
+  never want that to happen.
+
+  If 32 values aren't sufficient for a version hierarchy, than that version
+  hierarchy can be contained in multiple 32 bit values. i.e. <X Y Z1 Z2> in the
+  above example, Z1 & Z2 refer to the version hierarchy Z.
+
 - status: Marks the node enabled/disabled.
 
 Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
@@ -157,20 +177,20 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
-		opp01 {
+		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
-		opp02 {
+		opp@1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			clock-latency-ns = <290000>;
@@ -236,20 +256,20 @@ independently.
 		 * independently.
 		 */
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
-		opp01 {
+		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
-		opp02 {
+		opp@1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000;
@@ -312,20 +332,20 @@ DVFS state together.
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
-		opp01 {
+		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
-		opp02 {
+		opp@1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000>;
@@ -338,20 +358,20 @@ DVFS state together.
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp10 {
+		opp@1300000000 {
 			opp-hz = /bits/ 64 <1300000000>;
 			opp-microvolt = <1045000 1050000 1055000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
 			opp-suspend;
 		};
-		opp11 {
+		opp@1400000000 {
 			opp-hz = /bits/ 64 <1400000000>;
 			opp-microvolt = <1075000>;
 			opp-microamp = <100000>;
 			clock-latency-ns = <400000>;
 		};
-		opp12 {
+		opp@1500000000 {
 			opp-hz = /bits/ 64 <1500000000>;
 			opp-microvolt = <1010000 1100000 1110000>;
 			opp-microamp = <95000>;
@@ -378,7 +398,7 @@ Example 4: Handling multiple regulators
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000>, /* Supply 0 */
 					<960000>, /* Supply 1 */
@@ -391,7 +411,7 @@ Example 4: Handling multiple regulators
 
 		/* OR */
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
@@ -404,7 +424,7 @@ Example 4: Handling multiple regulators
 
 		/* OR */
 
-		opp00 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
@@ -417,7 +437,8 @@ Example 4: Handling multiple regulators
 	};
 };
 
-Example 5: Multiple OPP tables
+Example 5: opp-supported-hw
+(example: three level hierarchy of versions: cuts, substrate and process)
 
 / {
 	cpus {
@@ -426,40 +447,73 @@ Example 5: Multiple OPP tables
 			...
 
 			cpu-supply = <&cpu_supply>
-			operating-points-v2 = <&cpu0_opp_table_slow>, <&cpu0_opp_table_fast>;
-			operating-points-names = "slow", "fast";
+			operating-points-v2 = <&cpu0_opp_table_slow>;
 		};
 	};
 
-	cpu0_opp_table_slow: opp_table_slow {
+	opp_table {
 		compatible = "operating-points-v2";
 		status = "okay";
 		opp-shared;
 
-		opp00 {
+		opp@600000000 {
+			/*
+			 * Supports all substrate and process versions for 0xF
+			 * cuts, i.e. only first four cuts.
+			 */
+			opp-supported-hw = <0xF 0xFFFFFFFF 0xFFFFFFFF>
 			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <900000 915000 925000>;
 			...
 		};
 
-		opp01 {
+		opp@800000000 {
+			/*
+			 * Supports:
+			 * - cuts: only one, 6th cut (represented by 6th bit).
+			 * - substrate: supports 16 different substrate versions
+			 * - process: supports 9 different process versions
+			 */
+			opp-supported-hw = <0x20 0xff0000ff 0x0000f4f0>
 			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <900000 915000 925000>;
 			...
 		};
 	};
+};
+
+Example 6: opp-microvolt-<name>, opp-microamp-<name>:
+(example: device with two possible microvolt ranges: slow and fast)
 
-	cpu0_opp_table_fast: opp_table_fast {
+/ {
+	cpus {
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			...
+
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+	};
+
+	cpu0_opp_table: opp_table0 {
 		compatible = "operating-points-v2";
-		status = "okay";
 		opp-shared;
 
-		opp10 {
+		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			...
+			opp-microvolt-slow = <900000 915000 925000>;
+			opp-microvolt-fast = <970000 975000 985000>;
+			opp-microamp-slow =  <70000>;
+			opp-microamp-fast =  <71000>;
 		};
 
-		opp11 {
-			opp-hz = /bits/ 64 <1100000000>;
-			...
+		opp@1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt-slow = <900000 915000 925000>, /* Supply vcc0 */
+					      <910000 925000 935000>; /* Supply vcc1 */
+			opp-microvolt-fast = <970000 975000 985000>, /* Supply vcc0 */
+					     <960000 965000 975000>; /* Supply vcc1 */
+			opp-microamp =  <70000>; /* Will be used for both slow/fast */
 		};
 	};
 };
diff --git a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
index 45c2a8094a9f..01b88f4e0d5b 100644
--- a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
@@ -1,7 +1,10 @@
 * Broadcom iProc PCIe controller with the platform bus interface
 
 Required properties:
-- compatible: Must be "brcm,iproc-pcie"
+- compatible: Must be "brcm,iproc-pcie" for PAXB, or "brcm,iproc-pcie-paxc"
+  for PAXC.  PAXB-based root complex is used for external endpoint devices.
+  PAXC-based root complex is connected to emulated endpoint devices
+  internal to the ASIC
 - reg: base address and length of the PCIe controller I/O register space
 - #interrupt-cells: set to <1>
 - interrupt-map-mask and interrupt-map, standard PCI properties to define the
@@ -32,6 +35,28 @@ Optional:
 - brcm,pcie-ob-oarr-size: Some iProc SoCs need the OARR size bit to be set to
 increase the outbound window size
 
+MSI support (optional):
+
+For older platforms without MSI integrated in the GIC, iProc PCIe core provides
+an event queue based MSI support.  The iProc MSI uses host memories to store
+MSI posted writes in the event queues
+
+- msi-parent: Link to the device node of the MSI controller.  On newer iProc
+platforms, the MSI controller may be gicv2m or gicv3-its.  On older iProc
+platforms without MSI support in its interrupt controller, one may use the
+event queue based MSI support integrated within the iProc PCIe core.
+
+When the iProc event queue based MSI is used, one needs to define the
+following properties in the MSI device node:
+- compatible: Must be "brcm,iproc-msi"
+- msi-controller: claims itself as an MSI controller
+- interrupt-parent: Link to its parent interrupt device
+- interrupts: List of interrupt IDs from its parent interrupt device
+
+Optional properties:
+- brcm,pcie-msi-inten: Needs to be present for some older iProc platforms that
+require the interrupt enable registers to be set explicitly to enable MSI
+
 Example:
 	pcie0: pcie@18012000 {
 		compatible = "brcm,iproc-pcie";
@@ -58,6 +83,19 @@ Example:
 		brcm,pcie-ob-oarr-size;
 		brcm,pcie-ob-axi-offset = <0x00000000>;
 		brcm,pcie-ob-window-size = <256>;
+
+		msi-parent = <&msi0>;
+
+		/* iProc event queue based MSI */
+		msi0: msi@18012000 {
+			compatible = "brcm,iproc-msi";
+			msi-controller;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>,
+				     <GIC_SPI 97 IRQ_TYPE_NONE>,
+				     <GIC_SPI 98 IRQ_TYPE_NONE>,
+				     <GIC_SPI 99 IRQ_TYPE_NONE>,
+		};
 	};
 
 	pcie1: pcie@18013000 {
diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
index 17c6ed9c6059..b721beacfe4d 100644
--- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
@@ -1,4 +1,4 @@
-HiSilicon PCIe host bridge DT description
+HiSilicon Hip05 and Hip06 PCIe host bridge DT description
 
 HiSilicon PCIe host controller is based on Designware PCI core.
 It shares common functions with PCIe Designware core driver and inherits
@@ -7,8 +7,8 @@ Documentation/devicetree/bindings/pci/designware-pci.txt.
 
 Additional properties are described here:
 
-Required properties:
-- compatible: Should contain "hisilicon,hip05-pcie".
+Required properties
+- compatible: Should contain "hisilicon,hip05-pcie" or "hisilicon,hip06-pcie".
 - reg: Should contain rc_dbi, config registers location and length.
 - reg-names: Must include the following entries:
   "rc_dbi": controller configuration registers;
@@ -20,7 +20,7 @@ Optional properties:
 - status: Either "ok" or "disabled".
 - dma-coherent: Present if DMA operations are coherent.
 
-Example:
+Hip05 Example (note that Hip06 is the same except compatible):
 	pcie@0xb0080000 {
 		compatible = "hisilicon,hip05-pcie", "snps,dw-pcie";
 		reg = <0 0xb0080000 0 0x10000>, <0x220 0x00000000 0 0x2000>;
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
index 7fab84b33531..07a75094c5a8 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -8,7 +8,15 @@ OHCI and EHCI controllers.
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
 	      "renesas,pci-r8a7791" for the R8A7791 SoC;
-	      "renesas,pci-r8a7794" for the R8A7794 SoC.
+	      "renesas,pci-r8a7793" for the R8A7793 SoC;
+	      "renesas,pci-r8a7794" for the R8A7794 SoC;
+	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 compatible device
+
+
+	      When compatible with the generic version, nodes must list the
+	      SoC-specific version corresponding to the platform first
+	      followed by the generic version.
+
 - reg:	A list of physical regions to access the device: the first is
 	the operational registers for the OHCI/EHCI controllers and the
 	second is for the bridge configuration and control registers.
@@ -24,10 +32,15 @@ Required properties:
 - interrupt-map-mask: standard property that helps to define the interrupt
   mapping.
 
+Optional properties:
+- dma-ranges: a single range for the inbound memory region. If not supplied,
+  defaults to 1GiB at 0x40000000. Note there are hardware restrictions on the
+  allowed combinations of address and size.
+
 Example SoC configuration:
 
 	pci0: pci@ee090000  {
-		compatible = "renesas,pci-r8a7790";
+		compatible = "renesas,pci-r8a7790", "renesas,pci-rcar-gen2";
 		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
 		reg = <0x0 0xee090000 0x0 0xc00>,
 		      <0x0 0xee080000 0x0 0x1100>;
@@ -38,6 +51,7 @@ Example SoC configuration:
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
+		dma-ranges = <0x42000000 0 0x40000000 0 0x40000000 0 0x40000000>;
 		interrupt-map-mask = <0xff00 0 0 0x7>;
 		interrupt-map = <0x0000 0 0 1 &gic 0 108 IRQ_TYPE_LEVEL_HIGH
 				 0x0800 0 0 1 &gic 0 108 IRQ_TYPE_LEVEL_HIGH
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.txt b/Documentation/devicetree/bindings/pci/qcom,pcie.txt
new file mode 100644
index 000000000000..4059a6f89bc1
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.txt
@@ -0,0 +1,233 @@
+* Qualcomm PCI express root complex
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: Value should contain
+			- "qcom,pcie-ipq8064" for ipq8064
+			- "qcom,pcie-apq8064" for apq8064
+			- "qcom,pcie-apq8084" for apq8084
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Register ranges as listed in the reg-names property
+
+- reg-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: Must include the following entries
+			- "parf"   Qualcomm specific registers
+			- "dbi"	   Designware PCIe registers
+			- "elbi"   External local bus interface registers
+			- "config" PCIe configuration space
+
+- device_type:
+	Usage: required
+	Value type: <string>
+	Definition: Should be "pci". As specified in designware-pcie.txt
+
+- #address-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Should be 3. As specified in designware-pcie.txt
+
+- #size-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Should be 2. As specified in designware-pcie.txt
+
+- ranges:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: As specified in designware-pcie.txt
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: MSI interrupt
+
+- interrupt-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: Should contain "msi"
+
+- #interrupt-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Should be 1. As specified in designware-pcie.txt
+
+- interrupt-map-mask:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: As specified in designware-pcie.txt
+
+- interrupt-map:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: As specified in designware-pcie.txt
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: List of phandle and clock specifier pairs as listed
+		    in clock-names property
+
+- clock-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "iface"	Configuration AHB clock
+
+- clock-names:
+	Usage: required for ipq/apq8064
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "core"	Clocks the pcie hw block
+			- "phy"		Clocks the pcie PHY block
+- clock-names:
+	Usage: required for apq8084
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "aux"		Auxiliary (AUX) clock
+			- "bus_master"	Master AXI clock
+			- "bus_slave"	Slave AXI clock
+- resets:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: List of phandle and reset specifier pairs as listed
+		    in reset-names property
+
+- reset-names:
+	Usage: required for ipq/apq8064
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "axi"  AXI reset
+			- "ahb"  AHB reset
+			- "por"  POR reset
+			- "pci"  PCI reset
+			- "phy"  PHY reset
+
+- reset-names:
+	Usage: required for apq8084
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "core" Core reset
+
+- power-domains:
+	Usage: required for apq8084
+	Value type: <prop-encoded-array>
+	Definition: A phandle and power domain specifier pair to the
+		    power domain which is responsible for collapsing
+		    and restoring power to the peripheral
+
+- vdda-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: A phandle to the core analog power supply
+
+- vdda_phy-supply:
+	Usage: required for ipq/apq8064
+	Value type: <phandle>
+	Definition: A phandle to the analog power supply for PHY
+
+- vdda_refclk-supply:
+	Usage: required for ipq/apq8064
+	Value type: <phandle>
+	Definition: A phandle to the analog power supply for IC which generates
+		    reference clock
+
+- phys:
+	Usage: required for apq8084
+	Value type: <phandle>
+	Definition: List of phandle(s) as listed in phy-names property
+
+- phy-names:
+	Usage: required for apq8084
+	Value type: <stringlist>
+	Definition: Should contain "pciephy"
+
+- <name>-gpios:
+	Usage: optional
+	Value type: <prop-encoded-array>
+	Definition: List of phandle and gpio specifier pairs. Should contain
+			- "perst-gpios"	PCIe endpoint reset signal line
+			- "wake-gpios"	PCIe endpoint wake signal line
+
+* Example for ipq/apq8064
+	pcie@1b500000 {
+		compatible = "qcom,pcie-apq8064", "qcom,pcie-ipq8064", "snps,dw-pcie";
+		reg = <0x1b500000 0x1000
+		       0x1b502000 0x80
+		       0x1b600000 0x100
+		       0x0ff00000 0x100000>;
+		reg-names = "dbi", "elbi", "parf", "config";
+		device_type = "pci";
+		linux,pci-domain = <0>;
+		bus-range = <0x00 0xff>;
+		num-lanes = <1>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges = <0x81000000 0 0 0x0fe00000 0 0x00100000   /* I/O */
+			  0x82000000 0 0 0x08000000 0 0x07e00000>; /* memory */
+		interrupts = <GIC_SPI 238 IRQ_TYPE_NONE>;
+		interrupt-names = "msi";
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0x7>;
+		interrupt-map = <0 0 0 1 &intc 0 36 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+				<0 0 0 2 &intc 0 37 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+				<0 0 0 3 &intc 0 38 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+				<0 0 0 4 &intc 0 39 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+		clocks = <&gcc PCIE_A_CLK>,
+			 <&gcc PCIE_H_CLK>,
+			 <&gcc PCIE_PHY_CLK>;
+		clock-names = "core", "iface", "phy";
+		resets = <&gcc PCIE_ACLK_RESET>,
+			 <&gcc PCIE_HCLK_RESET>,
+			 <&gcc PCIE_POR_RESET>,
+			 <&gcc PCIE_PCI_RESET>,
+			 <&gcc PCIE_PHY_RESET>;
+		reset-names = "axi", "ahb", "por", "pci", "phy";
+		pinctrl-0 = <&pcie_pins_default>;
+		pinctrl-names = "default";
+	};
+
+* Example for apq8084
+	pcie0@fc520000 {
+		compatible = "qcom,pcie-apq8084", "snps,dw-pcie";
+		reg = <0xfc520000 0x2000>,
+		      <0xff000000 0x1000>,
+		      <0xff001000 0x1000>,
+		      <0xff002000 0x2000>;
+		reg-names = "parf", "dbi", "elbi", "config";
+		device_type = "pci";
+		linux,pci-domain = <0>;
+		bus-range = <0x00 0xff>;
+		num-lanes = <1>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges = <0x81000000 0 0          0xff200000 0 0x00100000   /* I/O */
+			  0x82000000 0 0x00300000 0xff300000 0 0x00d00000>; /* memory */
+		interrupts = <GIC_SPI 243 IRQ_TYPE_NONE>;
+		interrupt-names = "msi";
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0x7>;
+		interrupt-map = <0 0 0 1 &intc 0 244 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+				<0 0 0 2 &intc 0 245 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+				<0 0 0 3 &intc 0 247 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+				<0 0 0 4 &intc 0 248 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+		clocks = <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
+			 <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
+			 <&gcc GCC_PCIE_0_SLV_AXI_CLK>,
+			 <&gcc GCC_PCIE_0_AUX_CLK>;
+		clock-names = "iface", "master_bus", "slave_bus", "aux";
+		resets = <&gcc GCC_PCIE_0_BCR>;
+		reset-names = "core";
+		power-domains = <&gcc PCIE0_GDSC>;
+		vdda-supply = <&pma8084_l3>;
+		phys = <&pciephy0>;
+		phy-names = "pciephy";
+		perst-gpio = <&tlmm 70 GPIO_ACTIVE_LOW>;
+		pinctrl-0 = <&pcie0_pins_default>;
+		pinctrl-names = "default";
+	};
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci.txt b/Documentation/devicetree/bindings/pci/rcar-pci.txt
index 29d3b989d3b0..6cf99690eef9 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci.txt
+++ b/Documentation/devicetree/bindings/pci/rcar-pci.txt
@@ -1,8 +1,17 @@
 * Renesas RCar PCIe interface
 
 Required properties:
-- compatible: should contain one of the following
-	"renesas,pcie-r8a7779", "renesas,pcie-r8a7790", "renesas,pcie-r8a7791"
+compatible: "renesas,pcie-r8a7779" for the R8A7779 SoC;
+	    "renesas,pcie-r8a7790" for the R8A7790 SoC;
+	    "renesas,pcie-r8a7791" for the R8A7791 SoC;
+	    "renesas,pcie-r8a7793" for the R8A7793 SoC;
+	    "renesas,pcie-r8a7795" for the R8A7795 SoC;
+	    "renesas,pcie-rcar-gen2" for a generic R-Car Gen2 compatible device.
+
+	    When compatible with the generic version, nodes must list the
+	    SoC-specific version corresponding to the platform first
+	    followed by the generic version.
+
 - reg: base address and length of the pcie controller registers.
 - #address-cells: set to <3>
 - #size-cells: set to <2>
@@ -25,7 +34,7 @@ Example:
 SoC specific DT Entry:
 
 	pcie: pcie@fe000000 {
-		compatible = "renesas,pcie-r8a7791";
+		compatible = "renesas,pcie-r8a7791", "renesas,pcie-rcar-gen2";
 		reg = <0 0xfe000000 0 0x80000>;
 		#address-cells = <3>;
 		#size-cells = <2>;
diff --git a/Documentation/devicetree/bindings/phy/brcm,brcmstb-sata-phy.txt b/Documentation/devicetree/bindings/phy/brcm,brcmstb-sata-phy.txt
index 7f81ef90146a..d87ab7c127b8 100644
--- a/Documentation/devicetree/bindings/phy/brcm,brcmstb-sata-phy.txt
+++ b/Documentation/devicetree/bindings/phy/brcm,brcmstb-sata-phy.txt
@@ -2,6 +2,7 @@
 
 Required properties:
 - compatible: should be one or more of
+     "brcm,bcm7425-sata-phy"
      "brcm,bcm7445-sata-phy"
      "brcm,phy-sata3"
 - address-cells: should be 1
diff --git a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
new file mode 100644
index 000000000000..cafe2197dad9
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
@@ -0,0 +1,18 @@
+* Atheros AR71XX/9XXX USB PHY
+
+Required properties:
+- compatible: "qca,ar7100-usb-phy"
+- #phys-cells: should be 0
+- reset-names: "usb-phy"[, "usb-suspend-override"]
+- resets: references to the reset controllers
+
+Example:
+
+	usb-phy {
+		compatible = "qca,ar7100-usb-phy";
+
+		reset-names = "usb-phy", "usb-suspend-override";
+		resets = <&rst 4>, <&rst 3>;
+
+		#phy-cells = <0>;
+	};
diff --git a/Documentation/devicetree/bindings/phy/phy-hi6220-usb.txt b/Documentation/devicetree/bindings/phy/phy-hi6220-usb.txt
new file mode 100644
index 000000000000..f17a56e2152f
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/phy-hi6220-usb.txt
@@ -0,0 +1,16 @@
+Hisilicon hi6220 usb PHY
+-----------------------
+
+Required properties:
+- compatible: should be "hisilicon,hi6220-usb-phy"
+- #phy-cells: must be 0
+- hisilicon,peripheral-syscon: phandle of syscon used to control phy.
+Refer to phy/phy-bindings.txt for the generic PHY binding properties
+
+Example:
+	usb_phy: usbphy {
+		compatible = "hisilicon,hi6220-usb-phy";
+		#phy-cells = <0>;
+		phy-supply = <&fixed_5v_hub>;
+		hisilicon,peripheral-syscon = <&sys_ctrl>;
+	};
diff --git a/Documentation/devicetree/bindings/phy/rcar-gen3-phy-usb2.txt b/Documentation/devicetree/bindings/phy/rcar-gen3-phy-usb2.txt
new file mode 100644
index 000000000000..2390e4e9c84c
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/rcar-gen3-phy-usb2.txt
@@ -0,0 +1,39 @@
+* Renesas R-Car generation 3 USB 2.0 PHY
+
+This file provides information on what the device node for the R-Car generation
+3 USB 2.0 PHY contains.
+
+Required properties:
+- compatible: "renesas,usb2-phy-r8a7795" if the device is a part of an R8A7795
+	      SoC.
+- reg: offset and length of the partial USB 2.0 Host register block.
+- reg-names: must be "usb2_host".
+- clocks: clock phandle and specifier pair(s).
+- #phy-cells: see phy-bindings.txt in the same directory, must be <0>.
+
+Optional properties:
+To use a USB channel where USB 2.0 Host and HSUSB (USB 2.0 Peripheral) are
+combined, the device tree node should set HSUSB properties to reg and reg-names
+properties. This is because HSUSB has registers to select USB 2.0 host or
+peripheral at that channel:
+- reg: offset and length of the partial HSUSB register block.
+- reg-names: must be "hsusb".
+- interrupts: interrupt specifier for the PHY.
+
+Example (R-Car H3):
+
+	usb-phy@ee080200 {
+		compatible = "renesas,usb2-phy-r8a7795";
+		reg = <0 0xee080200 0 0x700>, <0 0xe6590100 0 0x100>;
+		reg-names = "usb2_host", "hsusb";
+		interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7795_CLK_EHCI0>,
+			 <&mstp7_clks R8A7795_CLK_HSUSB>;
+	};
+
+	usb-phy@ee0a0200 {
+		compatible = "renesas,usb2-phy-r8a7795";
+		reg = <0 0xee0a0200 0 0x700>;
+		reg-names = "usb2_host";
+		clocks = <&mstp7_clks R8A7795_CLK_EHCI0>;
+	};
diff --git a/Documentation/devicetree/bindings/phy/rockchip-usb-phy.txt b/Documentation/devicetree/bindings/phy/rockchip-usb-phy.txt
index 826454ac43bb..68498d560354 100644
--- a/Documentation/devicetree/bindings/phy/rockchip-usb-phy.txt
+++ b/Documentation/devicetree/bindings/phy/rockchip-usb-phy.txt
@@ -1,7 +1,10 @@
 ROCKCHIP USB2 PHY
 
 Required properties:
- - compatible: rockchip,rk3288-usb-phy
+ - compatible: matching the soc type, one of
+     "rockchip,rk3066a-usb-phy"
+     "rockchip,rk3188-usb-phy"
+     "rockchip,rk3288-usb-phy"
  - rockchip,grf : phandle to the syscon managing the "general
    register files"
  - #address-cells: should be 1
@@ -21,6 +24,7 @@ required properties:
 Optional Properties:
 - clocks : phandle + clock specifier for the phy clocks
 - clock-names: string, clock name, must be "phyclk"
+- #clock-cells: for users of the phy-pll, should be 0
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
index 0cebf7454517..95736d77fbb7 100644
--- a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
+++ b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
@@ -9,6 +9,7 @@ Required properties:
   * allwinner,sun7i-a20-usb-phy
   * allwinner,sun8i-a23-usb-phy
   * allwinner,sun8i-a33-usb-phy
+  * allwinner,sun8i-h3-usb-phy
 - reg : a list of offset + length pairs
 - reg-names :
   * "phy_ctrl"
diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt
index 9cf9446eaf2e..a3b394587874 100644
--- a/Documentation/devicetree/bindings/phy/ti-phy.txt
+++ b/Documentation/devicetree/bindings/phy/ti-phy.txt
@@ -31,6 +31,8 @@ OMAP USB2 PHY
 
 Required properties:
  - compatible: Should be "ti,omap-usb2"
+	       Should be "ti,dra7x-usb2-phy2" for the 2nd instance of USB2 PHY
+	       in DRA7x
  - reg : Address and length of the register set for the device.
  - #phy-cells: determine the number of cells that should be given in the
    phandle while referencing this phy.
@@ -40,10 +42,14 @@ Required properties:
    * "wkupclk" - wakeup clock.
    * "refclk" - reference clock (optional).
 
-Optional properties:
+Deprecated properties:
  - ctrl-module : phandle of the control module used by PHY driver to power on
    the PHY.
 
+Recommended properies:
+- syscon-phy-power : phandle/offset pair. Phandle to the system control
+  module and the register offset to power on/off the PHY.
+
 This is usually a subnode of ocp2scp to which it is connected.
 
 usb2phy@4a0ad080 {
@@ -77,14 +83,22 @@ Required properties:
    * "div-clk" - apll clock
 
 Optional properties:
- - ctrl-module : phandle of the control module used by PHY driver to power on
-   the PHY.
  - id: If there are multiple instance of the same type, in order to
    differentiate between each instance "id" can be used (e.g., multi-lane PCIe
    PHY). If "id" is not provided, it is set to default value of '1'.
  - syscon-pllreset: Handle to system control region that contains the
    CTRL_CORE_SMA_SW_0 register and register offset to the CTRL_CORE_SMA_SW_0
    register that contains the SATA_PLL_SOFT_RESET bit. Only valid for sata_phy.
+ - syscon-pcs : phandle/offset pair. Phandle to the system control module and the
+   register offset to write the PCS delay value.
+
+Deprecated properties:
+ - ctrl-module : phandle of the control module used by PHY driver to power on
+   the PHY.
+
+Recommended properies:
+ - syscon-phy-power : phandle/offset pair. Phandle to the system control
+   module and the register offset to power on/off the PHY.
 
 This is usually a subnode of ocp2scp to which it is connected.
 
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index b321b26780dc..9213b27e1036 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -17,7 +17,10 @@ Required properties:
   "allwinner,sun8i-a23-pinctrl"
   "allwinner,sun8i-a23-r-pinctrl"
   "allwinner,sun8i-a33-pinctrl"
+  "allwinner,sun9i-a80-pinctrl"
+  "allwinner,sun9i-a80-r-pinctrl"
   "allwinner,sun8i-a83t-pinctrl"
+  "allwinner,sun8i-h3-pinctrl"
 
 - reg: Should contain the register physical address and length for the
   pin controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-gpio.txt b/Documentation/devicetree/bindings/pinctrl/brcm,iproc-gpio.txt
index 16589fb6f420..e4277921f3e3 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,iproc-gpio.txt
@@ -1,4 +1,4 @@
-Broadcom Cygnus GPIO/PINCONF Controller
+Broadcom iProc GPIO/PINCONF Controller
 
 Required properties:
 
@@ -7,9 +7,12 @@ Required properties:
     "brcm,cygnus-crmu-gpio" or "brcm,iproc-gpio"
 
 - reg:
-    Define the base and range of the I/O address space that contains the Cygnus
+    Define the base and range of the I/O address space that contains SoC
 GPIO/PINCONF controller registers
 
+- ngpios:
+    Total number of in-use slots in GPIO controller
+
 - #gpio-cells:
     Must be two. The first cell is the GPIO pin number (within the
 controller's pin space) and the second cell is used for the following:
@@ -57,6 +60,7 @@ Example:
 		compatible = "brcm,cygnus-ccm-gpio";
 		reg = <0x1800a000 0x50>,
 		      <0x0301d164 0x20>;
+		ngpios = <24>;
 		#gpio-cells = <2>;
 		gpio-controller;
 		interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
@@ -78,6 +82,7 @@ Example:
 	gpio_asiu: gpio@180a5000 {
 		compatible = "brcm,cygnus-asiu-gpio";
 		reg = <0x180a5000 0x668>;
+		ngpios = <146>;
 		#gpio-cells = <2>;
 		gpio-controller;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt b/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt
new file mode 100644
index 000000000000..0844168a6dd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt
@@ -0,0 +1,80 @@
+Broadcom Northstar plus (NSP) GPIO/PINCONF Controller
+
+Required properties:
+- compatible:
+    Must be "brcm,nsp-gpio-a"
+
+- reg:
+    Should contain the register physical address and length for each of
+    GPIO base, IO control registers
+
+- #gpio-cells:
+    Must be two. The first cell is the GPIO pin number (within the
+    controller's pin space) and the second cell is used for the following:
+    bit[0]: polarity (0 for active high and 1 for active low)
+
+- gpio-controller:
+    Specifies that the node is a GPIO controller
+
+- ngpios:
+    Number of gpios supported (58x25 supports 32 and 58x23 supports 24)
+
+Optional properties:
+- interrupts:
+    Interrupt ID
+
+- interrupt-controller:
+    Specifies that the node is an interrupt controller
+
+- gpio-ranges:
+    Specifies the mapping between gpio controller and pin-controllers pins.
+    This requires 4 fields in cells defined as -
+    1. Phandle of pin-controller.
+    2. GPIO base pin offset.
+    3  Pin-control base pin offset.
+    4. number of gpio pins which are linearly mapped from pin base.
+
+Supported generic PINCONF properties in child nodes:
+- pins:
+    The list of pins (within the controller's own pin space) that properties
+    in the node apply to. Pin names are "gpio-<pin>"
+
+- bias-disable:
+    Disable pin bias
+
+- bias-pull-up:
+    Enable internal pull up resistor
+
+- bias-pull-down:
+    Enable internal pull down resistor
+
+- drive-strength:
+    Valid drive strength values include 2, 4, 6, 8, 10, 12, 14, 16 (mA)
+
+Example:
+
+	gpioa: gpio@18000020 {
+		compatible = "brcm,nsp-gpio-a";
+		reg = <0x18000020 0x100>,
+		      <0x1803f1c4 0x1c>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		ngpios = <32>;
+		gpio-ranges = <&pinctrl 0 0 31>;
+		interrupt-controller;
+		interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
+
+		/* Hog a few default settings */
+		pinctrl-names = "default";
+		pinctrl-0 = <&led>;
+		led: led {
+			pins = "gpio-1";
+			bias-pull-up;
+		};
+
+		pwr: pwr {
+			gpio-hog;
+			gpios = <3 1>;
+			output-high;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
index e89b4677567d..8e5216bcd748 100644
--- a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
+++ b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
@@ -1,7 +1,16 @@
 Lantiq XWAY pinmux controller
 
 Required properties:
-- compatible: "lantiq,pinctrl-xway" or "lantiq,pinctrl-xr9"
+- compatible: "lantiq,pinctrl-xway", (DEPRECATED: Use "lantiq,pinctrl-danube")
+	      "lantiq,pinctrl-xr9", (DEPRECATED: Use "lantiq,xrx100-pinctrl" or
+					"lantiq,xrx200-pinctrl")
+	      "lantiq,pinctrl-ase", (DEPRECATED: Use "lantiq,ase-pinctrl")
+	      "lantiq,<chip>-pinctrl", where <chip> is:
+		"ase" (XWAY AMAZON Family)
+		"danube" (XWAY DANUBE Family)
+		"xrx100" (XWAY xRX100 Family)
+		"xrx200" (XWAY xRX200 Family)
+		"xrx300" (XWAY xRX300 Family)
 - reg: Should contain the physical address and length of the gpio/pinmux
   register range
 
@@ -36,19 +45,87 @@ Required subnode-properties:
 
 Valid values for group and function names:
 
+XWAY: (DEPRECATED: Use DANUBE)
   mux groups:
     exin0, exin1, exin2, jtag, ebu a23, ebu a24, ebu a25, ebu clk, ebu cs1,
     ebu wait, nand ale, nand cs1, nand cle, spi, spi_cs1, spi_cs2, spi_cs3,
-    spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi , gpt1, gpt2,
+    spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi, gpt1, gpt2,
     gpt3, clkout0, clkout1, clkout2, clkout3, gnt1, gnt2, gnt3, req1, req2,
     req3
 
-  additional mux groups (XR9 only):
-    mdio, nand rdy, nand rd, exin3, exin4, gnt4, req4
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu
+
+XR9: ( DEPRECATED: Use xRX100/xRX200)
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, jtag, ebu a23, ebu a24, ebu a25,
+    ebu clk, ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy,
+    nand rd, spi, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5, spi_cs6,
+    asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1,
+    clkout2, clkout3, gnt1, gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio,
+    gphy0 led0, gphy0 led1, gphy0 led2, gphy1 led0, gphy1 led1, gphy1 led2
+
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, mdio, gphy
+
+AMAZON:
+  mux groups:
+    exin0, exin1, exin2, jtag, spi_di, spi_do, spi_clk, spi_cs1, spi_cs2,
+    spi_cs3, spi_cs4, spi_cs5, spi_cs6, asc, stp, gpt1, gpt2, gpt3, clkout0,
+    clkout1, clkout2, mdio, dfe led0, dfe led1, ephy led0, ephy led1, ephy led2
+
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, mdio, ephy, dfe
+
+DANUBE:
+  mux groups:
+    exin0, exin1, exin2, jtag, ebu a23, ebu a24, ebu a25, ebu clk, ebu cs1,
+    ebu wait, nand ale, nand cs1, nand cle, spi_di, spi_do, spi_clk, spi_cs1,
+    spi_cs2, spi_cs3, spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi,
+    gpt1, gpt2, gpt3, clkout0, clkout1, clkout2, clkout3, gnt1, gnt2, gnt3,
+    req1, req2, req3, dfe led0, dfe led1
 
   functions:
-    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, mdio
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, dfe
 
+xRX100:
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, ebu a23, ebu a24, ebu a25, ebu clk,
+    ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy, nand rd,
+    spi_di, spi_do, spi_clk, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5,
+    spi_cs6, asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1,
+    clkout2, clkout3, gnt1, gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio,
+    dfe led0, dfe led1
+
+  functions:
+    spi, asc, cgu, exin, stp, gpt, nmi, pci, ebu, mdio, dfe
+
+xRX200:
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, ebu a23, ebu a24, ebu a25, ebu clk,
+    ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy, nand rd,
+    spi_di, spi_do, spi_clk, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5,
+    spi_cs6, usif uart_rx, usif uart_tx, usif uart_rts, usif uart_cts,
+    usif uart_dtr, usif uart_dsr, usif uart_dcd, usif uart_ri, usif spi_di,
+    usif spi_do, usif spi_clk, usif spi_cs0, usif spi_cs1, usif spi_cs2,
+    stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1, clkout2, clkout3, gnt1,
+    gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio, dfe led0, dfe led1,
+    gphy0 led0, gphy0 led1, gphy0 led2, gphy1 led0, gphy1 led1, gphy1 led2
+
+  functions:
+    spi, usif, cgu, exin, stp, gpt, nmi, pci, ebu, mdio, dfe, gphy
+
+xRX300:
+  mux groups:
+    exin0, exin1, exin2, exin4, nand ale, nand cs0, nand cs1, nand cle,
+    nand rdy, nand rd, nand_d0, nand_d1, nand_d2, nand_d3, nand_d4, nand_d5,
+    nand_d6, nand_d7, nand_d1, nand wr, nand wp, nand se, spi_di, spi_do,
+    spi_clk, spi_cs1, spi_cs4, spi_cs6, usif uart_rx, usif uart_tx,
+    usif spi_di, usif spi_do, usif spi_clk, usif spi_cs0, stp, clkout2,
+    mdio, dfe led0, dfe led1, ephy0 led0, ephy0 led1, ephy1 led0, ephy1 led1
+
+  functions:
+    spi, usif, cgu, exin, stp, ebu, mdio, dfe, ephy
 
 
 Definition of pin configurations:
@@ -62,15 +139,32 @@ Optional subnode-properties:
     0: none, 1: down, 2: up.
 - lantiq,open-drain: Boolean, enables open-drain on the defined pin.
 
-Valid values for XWAY pin names:
+Valid values for XWAY pin names: (DEPRECATED: Use DANUBE)
   Pinconf pins can be referenced via the names io0-io31.
 
-Valid values for XR9 pin names:
+Valid values for XR9 pin names: (DEPRECATED: Use xrX100/xRX200)
   Pinconf pins can be referenced via the names io0-io55.
 
+Valid values for AMAZON pin names:
+  Pinconf pins can be referenced via the names io0-io31.
+
+Valid values for DANUBE pin names:
+  Pinconf pins can be referenced via the names io0-io31.
+
+Valid values for xRX100 pin names:
+  Pinconf pins can be referenced via the names io0-io55.
+
+Valid values for xRX200 pin names:
+  Pinconf pins can be referenced via the names io0-io49.
+
+Valid values for xRX300 pin names:
+  Pinconf pins can be referenced via the names io0-io1,io3-io6,io8-io11,
+						io13-io19,io23-io27,io34-io36,
+						io42-io43,io48-io61.
+
 Example:
 	gpio: pinmux@E100B10 {
-		compatible = "lantiq,pinctrl-xway";
+		compatible = "lantiq,danube-pinctrl";
 		pinctrl-names = "default";
 		pinctrl-0 = <&state_default>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
index 0480bc31bfd7..9ffb0b276bb4 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
@@ -4,10 +4,11 @@ The Mediatek's Pin controller is used to control SoC pins.
 
 Required properties:
 - compatible: value should be one of the following.
-    (a) "mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
-    (b) "mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
-    (c) "mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
-    (d) "mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
+	"mediatek,mt2701-pinctrl", compatible with mt2701 pinctrl.
+	"mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
+	"mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
+	"mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
+	"mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
 - pins-are-numbered: Specify the subnodes are using numbered pinmux to
   specify pins.
 - gpio-controller : Marks the device node as a gpio controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
new file mode 100644
index 000000000000..e312a71b2f94
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
@@ -0,0 +1,199 @@
+Qualcomm MSM8996 TLMM block
+
+This binding describes the Top Level Mode Multiplexer block found in the
+MSM8996 platform.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "qcom,msm8996-pinctrl"
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: the base address and size of the TLMM register space.
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: should specify the TLMM summary IRQ.
+
+- interrupt-controller:
+	Usage: required
+	Value type: <none>
+	Definition: identifies this node as an interrupt controller
+
+- #interrupt-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 2. Specifying the pin number and flags, as defined
+		    in <dt-bindings/interrupt-controller/irq.h>
+
+- gpio-controller:
+	Usage: required
+	Value type: <none>
+	Definition: identifies this node as a gpio controller
+
+- #gpio-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 2. Specifying the pin number and flags, as defined
+		    in <dt-bindings/gpio/gpio.h>
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+The pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin, a group, or a list of pins or groups. This configuration can include the
+mux function to select on those pin(s)/group(s), and various pin configuration
+parameters, such as pull-up, drive strength, etc.
+
+
+PIN CONFIGURATION NODES:
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+
+- pins:
+	Usage: required
+	Value type: <string-array>
+	Definition: List of gpio pins affected by the properties specified in
+		    this subnode.
+
+		    Valid pins are:
+		      gpio0-gpio149
+		        Supports mux, bias and drive-strength
+
+		      sdc1_clk, sdc1_cmd, sdc1_data sdc2_clk, sdc2_cmd,
+		      sdc2_data sdc1_rclk
+		        Supports bias and drive-strength
+
+- function:
+	Usage: required
+	Value type: <string>
+	Definition: Specify the alternative function to be configured for the
+		    specified pins. Functions are only valid for gpio pins.
+		    Valid values are:
+
+		    blsp_uart1, blsp_spi1, blsp_i2c1, blsp_uim1, atest_tsens,
+		    bimc_dte1, dac_calib0, blsp_spi8, blsp_uart8, blsp_uim8,
+		    qdss_cti_trig_out_b, bimc_dte0, dac_calib1, qdss_cti_trig_in_b,
+		    dac_calib2, atest_tsens2, atest_usb1, blsp_spi10, blsp_uart10,
+		    blsp_uim10, atest_bbrx1, atest_usb13, atest_bbrx0, atest_usb12,
+		    mdp_vsync, edp_lcd, blsp_i2c10, atest_gpsadc1, atest_usb11,
+		    atest_gpsadc0, edp_hot, atest_usb10, m_voc, dac_gpio, atest_char,
+		    cam_mclk, pll_bypassnl, qdss_stm7, blsp_i2c8, qdss_tracedata_b,
+		    pll_reset, qdss_stm6, qdss_stm5, qdss_stm4, atest_usb2, cci_i2c,
+		    qdss_stm3, dac_calib3, atest_usb23, atest_char3, dac_calib4,
+		    qdss_stm2, atest_usb22, atest_char2, qdss_stm1, dac_calib5,
+		    atest_usb21, atest_char1, dbg_out, qdss_stm0, dac_calib6,
+		    atest_usb20, atest_char0, dac_calib10, qdss_stm10,
+		    qdss_cti_trig_in_a, cci_timer4, blsp_spi6, blsp_uart6, blsp_uim6,
+		    blsp2_spi, qdss_stm9, qdss_cti_trig_out_a, dac_calib11,
+		    qdss_stm8, cci_timer0, qdss_stm13, dac_calib7, cci_timer1,
+		    qdss_stm12, dac_calib8, cci_timer2, blsp1_spi, qdss_stm11,
+		    dac_calib9, cci_timer3, cci_async, dac_calib12, blsp_i2c6,
+		    qdss_tracectl_a, dac_calib13, qdss_traceclk_a, dac_calib14,
+		    dac_calib15, hdmi_rcv, dac_calib16, hdmi_cec, pwr_modem,
+		    dac_calib17, hdmi_ddc, pwr_nav, dac_calib18, pwr_crypto,
+		    dac_calib19, hdmi_hot, dac_calib20, dac_calib21, pci_e0,
+		    dac_calib22, dac_calib23, dac_calib24, tsif1_sync, dac_calib25,
+		    sd_write, tsif1_error, blsp_spi2, blsp_uart2, blsp_uim2,
+		    qdss_cti, blsp_i2c2, blsp_spi3, blsp_uart3, blsp_uim3, blsp_i2c3,
+		    uim3, blsp_spi9, blsp_uart9, blsp_uim9, blsp10_spi, blsp_i2c9,
+		    blsp_spi7, blsp_uart7, blsp_uim7, qdss_tracedata_a, blsp_i2c7,
+		    qua_mi2s, gcc_gp1_clk_a, ssc_irq, uim4, blsp_spi11, blsp_uart11,
+		    blsp_uim11, gcc_gp2_clk_a, gcc_gp3_clk_a, blsp_i2c11, cri_trng0,
+		    cri_trng1, cri_trng, qdss_stm18, pri_mi2s, qdss_stm17, blsp_spi4,
+		    blsp_uart4, blsp_uim4, qdss_stm16, qdss_stm15, blsp_i2c4,
+		    qdss_stm14, dac_calib26, spkr_i2s, audio_ref, lpass_slimbus,
+		    isense_dbg, tsense_pwm1, tsense_pwm2, btfm_slimbus, ter_mi2s,
+		    qdss_stm22, qdss_stm21, qdss_stm20, qdss_stm19, gcc_gp1_clk_b,
+		    sec_mi2s, blsp_spi5, blsp_uart5, blsp_uim5, gcc_gp2_clk_b,
+		    gcc_gp3_clk_b, blsp_i2c5, blsp_spi12, blsp_uart12, blsp_uim12,
+		    qdss_stm25, qdss_stm31, blsp_i2c12, qdss_stm30, qdss_stm29,
+		    tsif1_clk, qdss_stm28, tsif1_en, tsif1_data, sdc4_cmd, qdss_stm27,
+		    qdss_traceclk_b, tsif2_error, sdc43, vfr_1, qdss_stm26, tsif2_clk,
+		    sdc4_clk, qdss_stm24, tsif2_en, sdc42, qdss_stm23, qdss_tracectl_b,
+		    sd_card, tsif2_data, sdc41, tsif2_sync, sdc40, mdp_vsync_p_b,
+		    ldo_en, mdp_vsync_s_b, ldo_update, blsp11_uart_tx_b, blsp11_uart_rx_b,
+		    blsp11_i2c_sda_b, prng_rosc, blsp11_i2c_scl_b, uim2, uim1, uim_batt,
+		    pci_e2, pa_indicator, adsp_ext, ddr_bist, qdss_tracedata_11,
+		    qdss_tracedata_12, modem_tsync, nav_dr, nav_pps, pci_e1, gsm_tx,
+		    qspi_cs, ssbi2, ssbi1, mss_lte, qspi_clk, qspi0, qspi1, qspi2, qspi3,
+		    gpio
+
+- bias-disable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as no pull.
+
+- bias-pull-down:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as pull down.
+
+- bias-pull-up:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as pull up.
+
+- output-high:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    high.
+		    Not valid for sdc pins.
+
+- output-low:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    low.
+		    Not valid for sdc pins.
+
+- drive-strength:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the drive strength for the specified pins, in mA.
+		    Valid values are: 2, 4, 6, 8, 10, 12, 14 and 16
+
+Example:
+
+	tlmm: pinctrl@01010000 {
+		compatible = "qcom,msm8996-pinctrl";
+		reg = <0x01010000 0x300000>;
+		interrupts = <0 208 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+
+		uart_console_active: uart_console_active {
+			mux {
+				pins = "gpio4", "gpio5";
+				function = "blsp_uart8";
+			};
+
+			config {
+				pins = "gpio4", "gpio5";
+				drive-strength = <2>;
+				bias-disable;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
index 1ae63c0acd40..a90c812ad642 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
@@ -14,6 +14,7 @@ PMIC's from Qualcomm.
 		    "qcom,pm8917-gpio"
 		    "qcom,pm8921-gpio"
 		    "qcom,pm8941-gpio"
+		    "qcom,pm8994-gpio"
 		    "qcom,pma8084-gpio"
 
 - reg:
@@ -79,6 +80,7 @@ to specify in a pin configuration subnode:
 		    gpio1-gpio38 for pm8917
 		    gpio1-gpio44 for pm8921
 		    gpio1-gpio36 for pm8941
+		    gpio1-gpio22 for pm8994
 		    gpio1-gpio22 for pma8084
 
 - function:
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
index d7803a2a94e9..d74e631e10da 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
@@ -15,6 +15,7 @@ of PMIC's from Qualcomm.
 		    "qcom,pm8917-mpp",
 		    "qcom,pm8921-mpp",
 		    "qcom,pm8941-mpp",
+		    "qcom,pm8994-mpp",
 		    "qcom,pma8084-mpp",
 
 - reg:
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 391ef4be8d50..0cd701b1947f 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -21,7 +21,8 @@ defined as gpio sub-nodes of the pinmux controller.
 Required properties for iomux controller:
   - compatible: one of "rockchip,rk2928-pinctrl", "rockchip,rk3066a-pinctrl"
 		       "rockchip,rk3066b-pinctrl", "rockchip,rk3188-pinctrl"
-		       "rockchip,rk3288-pinctrl", "rockchip,rk3368-pinctrl"
+		       "rockchip,rk3228-pinctrl", "rockchip,rk3288-pinctrl"
+		       "rockchip,rk3368-pinctrl"
   - rockchip,grf: phandle referencing a syscon providing the
 	 "general register files"
 
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 9d2a995293e6..6db16b90873a 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -17,6 +17,7 @@ Required Properties:
   - "samsung,exynos4x12-pinctrl": for Exynos4x12 compatible pin-controller.
   - "samsung,exynos5250-pinctrl": for Exynos5250 compatible pin-controller.
   - "samsung,exynos5260-pinctrl": for Exynos5260 compatible pin-controller.
+  - "samsung,exynos5410-pinctrl": for Exynos5410 compatible pin-controller.
   - "samsung,exynos5420-pinctrl": for Exynos5420 compatible pin-controller.
   - "samsung,exynos7-pinctrl": for Exynos7 compatible pin-controller.
 
diff --git a/Documentation/devicetree/bindings/pwm/lpc32xx-pwm.txt b/Documentation/devicetree/bindings/pwm/lpc32xx-pwm.txt
index cfe1db3bb6e9..74b5bc5dd19a 100644
--- a/Documentation/devicetree/bindings/pwm/lpc32xx-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/lpc32xx-pwm.txt
@@ -6,7 +6,12 @@ Required properties:
 
 Examples:
 
-pwm@0x4005C000 {
+pwm@4005c000 {
 	compatible = "nxp,lpc3220-pwm";
-	reg = <0x4005C000 0x8>;
+	reg = <0x4005c000 0x4>;
+};
+
+pwm@4005c004 {
+	compatible = "nxp,lpc3220-pwm";
+	reg = <0x4005c004 0x4>;
 };
diff --git a/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt b/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
new file mode 100644
index 000000000000..5befb538db95
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
@@ -0,0 +1,18 @@
+* OMAP PWM for dual-mode timers
+
+Required properties:
+- compatible: Shall contain "ti,omap-dmtimer-pwm".
+- ti,timers: phandle to PWM capable OMAP timer. See arm/omap/timer.txt for info
+  about these timers.
+- #pwm-cells: Should be 3. See pwm.txt in this directory for a description of
+  the cells format.
+
+Optional properties:
+- ti,prescaler: Should be a value between 0 and 7, see the timers datasheet
+
+Example:
+	pwm9: dmtimer-pwm@9 {
+		compatible = "ti,omap-dmtimer-pwm";
+		ti,timers = <&timer9>;
+		#pwm-cells = <3>;
+	};
diff --git a/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt b/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt
new file mode 100644
index 000000000000..8f14df9d1205
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt
@@ -0,0 +1,34 @@
+TI LMU LM363x regulator device tree bindings
+
+LM363x regulator driver supports LM3631 and LM3632.
+LM3631 has five regulators and LM3632 supports three regulators.
+
+Required property:
+  - compatible: "ti,lm363x-regulator"
+
+Optional properties:
+  LM3632 has external enable pins for two LDOs.
+  - ti,lcm-en1-gpio: A GPIO specifier for Vpos control pin.
+  - ti,lcm-en2-gpio: A GPIO specifier for Vneg control pin.
+
+Child nodes:
+  LM3631
+  - vboost
+  - vcont
+  - voref
+  - vpos
+  - vneg
+
+  LM3632
+  - vboost
+  - vpos
+  - vneg
+
+  Optional properties of a child node:
+  Each sub-node should contain the constraints and initialization.
+  Please refer to [1].
+
+Examples: Please refer to ti-lmu dt-bindings [2].
+
+[1] ../regulator/regulator.txt
+[2] ../mfd/ti-lmu.txt
diff --git a/Documentation/devicetree/bindings/regulator/pv88060.txt b/Documentation/devicetree/bindings/regulator/pv88060.txt
new file mode 100644
index 000000000000..10a6dadc008e
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/pv88060.txt
@@ -0,0 +1,124 @@
+* Powerventure Semiconductor PV88060 Voltage Regulator
+
+Required properties:
+- compatible: "pvs,pv88060".
+- reg: I2C slave address, usually 0x49.
+- interrupts: the interrupt outputs of the controller
+- regulators: A node that houses a sub-node for each regulator within the
+  device. Each sub-node is identified using the node's name, with valid
+  values listed below. The content of each sub-node is defined by the
+  standard binding for regulators; see regulator.txt.
+  BUCK1, LDO1, LDO2, LDO3, LDO4, LDO5, LDO6, LDO7, SW1, SW2, SW3, SW4,
+  SW5, and SW6.
+
+Optional properties:
+- Any optional property defined in regulator.txt
+
+Example
+
+	pmic: pv88060@49 {
+		compatible = "pvs,pv88060";
+		reg = <0x49>;
+		interrupt-parent = <&gpio>;
+		interrupts = <24 24>;
+
+		regulators {
+			BUCK1 {
+				regulator-name = "buck1";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <4387500>;
+				regulator-min-microamp 	= <1496000>;
+				regulator-max-microamp 	= <4189000>;
+				regulator-boot-on;
+			};
+
+			LDO1 {
+				regulator-name = "ldo1";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO2 {
+				regulator-name = "ldo2";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO3 {
+				regulator-name = "ldo3";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO4 {
+				regulator-name = "ldo4";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO5 {
+				regulator-name = "ldo5";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO6 {
+				regulator-name = "ldo6";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			LDO7 {
+				regulator-name = "ldo7";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3350000>;
+				regulator-boot-on;
+			};
+
+			SW1 {
+				regulator-name = "sw1";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+			};
+
+			SW2 {
+				regulator-name = "sw2";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-boot-on;
+			};
+
+			SW3 {
+				regulator-name = "sw3";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-boot-on;
+			};
+
+			SW4 {
+				regulator-name = "sw4";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-boot-on;
+			};
+
+			SW5 {
+				regulator-name = "sw5";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-boot-on;
+			};
+
+			SW6 {
+				regulator-name = "sw6";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+			};
+		};
+	};
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/regulator/pv88090.txt b/Documentation/devicetree/bindings/regulator/pv88090.txt
new file mode 100644
index 000000000000..e52b2a95cdde
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/pv88090.txt
@@ -0,0 +1,65 @@
+* Powerventure Semiconductor PV88090 Voltage Regulator
+
+Required properties:
+- compatible: "pvs,pv88090".
+- reg: I2C slave address, usually 0x48.
+- interrupts: the interrupt outputs of the controller
+- regulators: A node that houses a sub-node for each regulator within the
+  device. Each sub-node is identified using the node's name, with valid
+  values listed below. The content of each sub-node is defined by the
+  standard binding for regulators; see regulator.txt.
+  BUCK1, BUCK2, BUCK3, LDO1, and LDO2.
+
+Optional properties:
+- Any optional property defined in regulator.txt
+
+Example
+
+	pmic: pv88090@48 {
+		compatible = "pvs,pv88090";
+		reg = <0x48>;
+		interrupt-parent = <&gpio>;
+		interrupts = <24 24>;
+
+		regulators {
+			BUCK1 {
+				regulator-name = "buck1";
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1393750>;
+				regulator-min-microamp 	= < 220000>;
+				regulator-max-microamp 	= <7040000>;
+				regulator-boot-on;
+			};
+
+			BUCK2 {
+				regulator-name = "buck2";
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1393750>;
+				regulator-min-microamp 	= <1496000>;
+				regulator-max-microamp 	= <4189000>;
+			};
+
+			BUCK3 {
+				regulator-name = "buck3";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <1393750>;
+				regulator-min-microamp 	= <1496000>;
+				regulator-max-microamp 	= <4189000>;
+				regulator-boot-on;
+			};
+
+			LDO1 {
+				regulator-name = "ldo1";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <4350000>;
+				regulator-boot-on;
+			};
+
+			LDO2 {
+				regulator-name = "ldo2";
+				regulator-min-microvolt = < 650000>;
+				regulator-max-microvolt = <2225000>;
+				regulator-boot-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
index e27f5c4c54fd..1f8d6f84b657 100644
--- a/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
@@ -1,27 +1,17 @@
-Qualcomm Resource Power Manager (RPM) over SMD
+QCOM SMD RPM REGULATOR
 
-This driver is used to interface with the Resource Power Manager (RPM) found in
-various Qualcomm platforms. The RPM allows each component in the system to vote
-for state of the system resources, such as clocks, regulators and bus
-frequencies.
+The Qualcomm RPM over SMD regulator is modelled as a subdevice of the RPM.
+Because SMD is used as the communication transport mechanism, the RPM resides as
+a subnode of the SMD.  As such, the SMD-RPM regulator requires that the SMD and
+RPM nodes be present.
 
-- compatible:
-	Usage: required
-	Value type: <string>
-	Definition: must be one of:
-		    "qcom,rpm-msm8974"
+Please refer to Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt for
+information pertaining to the SMD node.
 
-- qcom,smd-channels:
-	Usage: required
-	Value type: <stringlist>
-	Definition: Shared Memory channel used for communication with the RPM
+Please refer to Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt for
+information regarding the RPM node.
 
-= SUBDEVICES
-
-The RPM exposes resources to its subnodes. The below bindings specify the set
-of valid subnodes that can operate on these resources.
-
-== Regulators
+== Regulator
 
 Regulator nodes are identified by their compatible:
 
@@ -30,7 +20,9 @@ Regulator nodes are identified by their compatible:
 	Value type: <string>
 	Definition: must be one of:
 		    "qcom,rpm-pm8841-regulators"
+		    "qcom,rpm-pm8916-regulators"
 		    "qcom,rpm-pm8941-regulators"
+		    "qcom,rpm-pma8084-regulators"
 
 - vdd_s1-supply:
 - vdd_s2-supply:
@@ -48,6 +40,19 @@ Regulator nodes are identified by their compatible:
 - vdd_s1-supply:
 - vdd_s2-supply:
 - vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_l1_l2_l3-supply:
+- vdd_l4_l5_l6-supply:
+- vdd_l7-supply:
+- vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18-supply:
+	Usage: optional (pm8916 only)
+	Value type: <phandle>
+	Definition: reference to regulator supplying the input pin, as
+		    described in the data sheet
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
 - vdd_l1_l3-supply:
 - vdd_l2_lvs1_2_3-supply:
 - vdd_l4_l11-supply:
@@ -63,6 +68,35 @@ Regulator nodes are identified by their compatible:
 	Definition: reference to regulator supplying the input pin, as
 		    described in the data sheet
 
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_s5-supply:
+- vdd_s6-supply:
+- vdd_s7-supply:
+- vdd_s8-supply:
+- vdd_s9-supply:
+- vdd_s10-supply:
+- vdd_s11-supply:
+- vdd_s12-supply:
+- vdd_l1_l11-supply:
+- vdd_l2_l3_l4_l27-supply:
+- vdd_l5_l7-supply:
+- vdd_l6_l12_l14_l15_l26-supply:
+- vdd_l8-supply:
+- vdd_l9_l10_l13_l20_l23_l24-supply:
+- vdd_l16_l25-supply:
+- vdd_l17-supply:
+- vdd_l18-supply:
+- vdd_l19-supply:
+- vdd_l21-supply:
+- vdd_l22-supply:
+	Usage: optional (pma8084 only)
+	Value type: <phandle>
+	Definition: reference to regulator supplying the input pin, as
+		    described in the data sheet
+
 The regulator node houses sub-nodes for each regulator within the device. Each
 sub-node is identified using the node's name, with valid values listed for each
 of the pmics below.
@@ -70,11 +104,20 @@ of the pmics below.
 pm8841:
 	s1, s2, s3, s4, s5, s6, s7, s8
 
+pm8916:
+	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
+	l14, l15, l16, l17, l18
+
 pm8941:
 	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
 	l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2,
 	lvs3, 5vs1, 5vs2
 
+pma8084:
+	s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, l1, l2, l3, l4, l5,
+	l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20,
+	l21, l22, l23, l24, l25, l26, l27, lvs1, lvs2, lvs3, lvs4, 5vs1
+
 The content of each sub-node is defined by the standard binding for regulators -
 see regulator.txt.
 
@@ -114,4 +157,3 @@ see regulator.txt.
 			};
 		};
 	};
-
diff --git a/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt b/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt
deleted file mode 100644
index 20191315e444..000000000000
--- a/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt
+++ /dev/null
@@ -1,163 +0,0 @@
-* Samsung S5M8767 Voltage and Current Regulator
-
-The Samsung S5M8767 is a multi-function device which includes voltage and
-current regulators, rtc, charger controller and other sub-blocks. It is
-interfaced to the host controller using a i2c interface. Each sub-block is
-addressed by the host system using different i2c slave address. This document
-describes the bindings for 'pmic' sub-block of s5m8767.
-
-Required properties:
-- compatible: Should be "samsung,s5m8767-pmic".
-- reg: Specifies the i2c slave address of the pmic block. It should be 0x66.
-
-- s5m8767,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
-  units for buck2 when changing voltage using gpio dvs. Refer to [1] below
-  for additional information.
-
-- s5m8767,pmic-buck3-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
-  units for buck3 when changing voltage using gpio dvs. Refer to [1] below
-  for additional information.
-
-- s5m8767,pmic-buck4-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
-  units for buck4 when changing voltage using gpio dvs. Refer to [1] below
-  for additional information.
-
-- s5m8767,pmic-buck-ds-gpios: GPIO specifiers for three host gpio's used
-  for selecting GPIO DVS lines. It is one-to-one mapped to dvs gpio lines.
-
-[1] If none of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional
-    property is specified, the 's5m8767,pmic-buck[2/3/4]-dvs-voltage'
-    property should specify atleast one voltage level (which would be a
-    safe operating voltage).
-
-    If either of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional
-    property is specified, then all the eight voltage values for the
-    's5m8767,pmic-buck[2/3/4]-dvs-voltage' should be specified.
-
-Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from s5m8767 are delivered to.
-- interrupts: Interrupt specifiers for two interrupt sources.
-  - First interrupt specifier is for 'irq1' interrupt.
-  - Second interrupt specifier is for 'alert' interrupt.
-- s5m8767,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs.
-- s5m8767,pmic-buck3-uses-gpio-dvs: 'buck3' can be controlled by gpio dvs.
-- s5m8767,pmic-buck4-uses-gpio-dvs: 'buck4' can be controlled by gpio dvs.
-
-Additional properties required if either of the optional properties are used:
-
-- s5m8767,pmic-buck234-default-dvs-idx: Default voltage setting selected from
-  the possible 8 options selectable by the dvs gpios. The value of this
-  property should be between 0 and 7. If not specified or if out of range, the
-  default value of this property is set to 0.
-
-- s5m8767,pmic-buck-dvs-gpios: GPIO specifiers for three host gpio's used
-  for dvs. The format of the gpio specifier depends in the gpio controller.
-
-Regulators: The regulators of s5m8767 that have to be instantiated should be
-included in a sub-node named 'regulators'. Regulator nodes included in this
-sub-node should be of the format as listed below.
-
-	regulator_name {
-		ldo1_reg: LDO1 {
-			regulator-name = "VDD_ALIVE_1.0V";
-			regulator-min-microvolt = <1100000>;
-			regulator-max-microvolt = <1100000>;
-			regulator-always-on;
-			regulator-boot-on;
-			op_mode = <1>; /* Normal Mode */
-		};
-	};
-The above regulator entries are defined in regulator bindings documentation
-except these properties:
-	- op_mode: describes the different operating modes of the LDO's with
-		power mode change in SOC. The different possible values are,
-		0 - always off mode
-		1 - on in normal mode
-		2 - low power mode
-		3 - suspend mode
-	- s5m8767,pmic-ext-control-gpios: (optional) GPIO specifier for one
-		GPIO controlling this regulator (enable/disable); This is
-		valid only for buck9.
-
-The following are the names of the regulators that the s5m8767 pmic block
-supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
-as per the datasheet of s5m8767.
-
-	- LDOn
-		  - valid values for n are 1 to 28
-		  - Example: LDO1, LDO2, LDO28
-	- BUCKn
-		  - valid values for n are 1 to 9.
-		  - Example: BUCK1, BUCK2, BUCK9
-
-The bindings inside the regulator nodes use the standard regulator bindings
-which are documented elsewhere.
-
-Example:
-
-	s5m8767_pmic@66 {
-		compatible = "samsung,s5m8767-pmic";
-		reg = <0x66>;
-
-		s5m8767,pmic-buck2-uses-gpio-dvs;
-		s5m8767,pmic-buck3-uses-gpio-dvs;
-		s5m8767,pmic-buck4-uses-gpio-dvs;
-
-		s5m8767,pmic-buck-default-dvs-idx = <0>;
-
-		s5m8767,pmic-buck-dvs-gpios = <&gpx0 0 0>, /* DVS1 */
-						 <&gpx0 1 0>, /* DVS2 */
-						 <&gpx0 2 0>; /* DVS3 */
-
-		s5m8767,pmic-buck-ds-gpios = <&gpx2 3 0>, /* SET1 */
-						<&gpx2 4 0>, /* SET2 */
-						<&gpx2 5 0>; /* SET3 */
-
-		s5m8767,pmic-buck2-dvs-voltage = <1350000>, <1300000>,
-						 <1250000>, <1200000>,
-						 <1150000>, <1100000>,
-						 <1000000>, <950000>;
-
-		s5m8767,pmic-buck3-dvs-voltage = <1100000>, <1100000>,
-						 <1100000>, <1100000>,
-						 <1000000>, <1000000>,
-						 <1000000>, <1000000>;
-
-		s5m8767,pmic-buck4-dvs-voltage = <1200000>, <1200000>,
-						 <1200000>, <1200000>,
-						 <1200000>, <1200000>,
-						 <1200000>, <1200000>;
-
-		regulators {
-			ldo1_reg: LDO1 {
-				regulator-name = "VDD_ABB_3.3V";
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-				op_mode = <1>; /* Normal Mode */
-			};
-
-			ldo2_reg: LDO2 {
-				regulator-name = "VDD_ALIVE_1.1V";
-				regulator-min-microvolt = <1100000>;
-				regulator-max-microvolt = <1100000>;
-				regulator-always-on;
-			};
-
-			buck1_reg: BUCK1 {
-				regulator-name = "VDD_MIF_1.2V";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			vemmc_reg: BUCK9 {
-				regulator-name = "VMEM_VDD_2.8V";
-				regulator-min-microvolt = <2800000>;
-				regulator-max-microvolt = <2800000>;
-				op_mode = <3>; /* Standby Mode */
-				s5m8767,pmic-ext-control-gpios = <&gpk0 2 0>;
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt
new file mode 100644
index 000000000000..bae3c7f838cf
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt
@@ -0,0 +1,79 @@
+Binding for Samsung S2MPA01 regulator block
+===========================================
+
+This is a part of device tree bindings for S2M family multi-function devices.
+More information can be found in bindings/mfd/sec-core.txt file.
+
+The S2MPA01 device provide buck and LDO regulators.
+
+To register these with regulator framework instantiate under main device node
+a sub-node named "regulators" with more sub-nodes for each regulator using the
+common regulator binding documented in:
+ - Documentation/devicetree/bindings/regulator/regulator.txt
+
+
+Names of regulators supported by S2MPA01 device:
+	- LDOn
+		  - valid values for n are 1 to 26
+		  - Example: LDO1, LD02, LDO26
+	- BUCKn
+		  - valid values for n are 1 to 10.
+		  - Example: BUCK1, BUCK2, BUCK9
+Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
+as per the datasheet of device.
+
+
+Optional properties of buck regulator nodes under "regulators" sub-node:
+ - regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500
+   (default), 25000, or 50000. May be 0 for disabling the ramp delay on
+   BUCK{1,2,3,4}.
+
+   In the absence of the regulator-ramp-delay property, the default ramp
+   delay will be used.
+
+   Note: Some bucks share the ramp rate setting i.e. same ramp value
+   will be set for a particular group of bucks so provide the same
+   regulator-ramp-delay value for them.
+   Groups sharing ramp rate:
+    - buck{1,6},
+    - buck{2,4},
+    - buck{8,9,10}.
+
+Example:
+
+	s2mpa01_pmic@66 {
+		compatible = "samsung,s2mpa01-pmic";
+		reg = <0x66>;
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ALIVE";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDDQ_MMC2";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "vdd_arm";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-ramp-delay = <50000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt
new file mode 100644
index 000000000000..27a48bf1b185
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt
@@ -0,0 +1,102 @@
+Binding for Samsung S2M family regulator block
+==============================================
+
+This is a part of device tree bindings for S2M family multi-function devices.
+More information can be found in bindings/mfd/sec-core.txt file.
+
+The S2MPS11/13/14/15 and S2MPU02 devices provide buck and LDO regulators.
+
+To register these with regulator framework instantiate under main device node
+a sub-node named "regulators" with more sub-nodes for each regulator using the
+common regulator binding documented in:
+ - Documentation/devicetree/bindings/regulator/regulator.txt
+
+
+Names of regulators supported by different devices:
+	- LDOn
+		  - valid values for n are:
+			- S2MPS11: 1 to 38
+			- S2MPS13: 1 to 40
+			- S2MPS14: 1 to 25
+			- S2MPS15: 1 to 27
+			- S2MPU02: 1 to 28
+		  - Example: LDO1, LDO2, LDO28
+	- BUCKn
+		  - valid values for n are:
+			- S2MPS11: 1 to 10
+			- S2MPS13: 1 to 10
+			- S2MPS14: 1 to 5
+			- S2MPS15: 1 to 10
+			- S2MPU02: 1 to 7
+		  - Example: BUCK1, BUCK2, BUCK9
+Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
+as per the datasheet of device.
+
+
+Optional properties of the nodes under "regulators" sub-node:
+ - regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500,
+   25000 (default) or 50000.
+
+   Additionally S2MPS11 supports disabling ramp delay for BUCK{2,3,4,6}
+   by setting it to <0>.
+
+   Note: On S2MPS11 some bucks share the ramp rate setting i.e. same ramp value
+   will be set for a particular group of bucks so provide the same
+   regulator-ramp-delay value for them.
+   Groups sharing ramp rate:
+    - buck{1,6},
+    - buck{3,4},
+    - buck{7,8,10}.
+
+ - samsung,ext-control-gpios: On S2MPS14 the LDO10, LDO11 and LDO12 can be
+   configured to external control over GPIO. To turn this feature on this
+   property must be added to the regulator sub-node:
+    - samsung,ext-control-gpios: GPIO specifier for one GPIO
+                                 controlling this regulator (enable/disable)
+  Example:
+	LDO12 {
+		regulator-name = "V_EMMC_2.8V";
+		regulator-min-microvolt = <2800000>;
+		regulator-max-microvolt = <2800000>;
+		samsung,ext-control-gpios = <&gpk0 2 0>;
+	};
+
+
+Example:
+
+	s2mps11_pmic@66 {
+		compatible = "samsung,s2mps11-pmic";
+		reg = <0x66>;
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ABB_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDD_ALIVE_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "vdd_arm";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-ramp-delay = <50000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt
new file mode 100644
index 000000000000..093edda0c8df
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt
@@ -0,0 +1,145 @@
+Binding for Samsung S5M8767 regulator block
+===========================================
+
+This is a part of device tree bindings for S5M family multi-function devices.
+More information can be found in bindings/mfd/sec-core.txt file.
+
+The S5M8767 device provide buck and LDO regulators.
+
+To register these with regulator framework instantiate under main device node
+a sub-node named "regulators" with more sub-nodes for each regulator using the
+common regulator binding documented in:
+ - Documentation/devicetree/bindings/regulator/regulator.txt
+
+
+Required properties of the main device node (the parent!):
+ - s5m8767,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+   units for buck2 when changing voltage using gpio dvs. Refer to [1] below
+   for additional information.
+
+ - s5m8767,pmic-buck3-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+   units for buck3 when changing voltage using gpio dvs. Refer to [1] below
+   for additional information.
+
+ - s5m8767,pmic-buck4-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+   units for buck4 when changing voltage using gpio dvs. Refer to [1] below
+   for additional information.
+
+ - s5m8767,pmic-buck-ds-gpios: GPIO specifiers for three host gpio's used
+   for selecting GPIO DVS lines. It is one-to-one mapped to dvs gpio lines.
+
+ [1] If none of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional
+     property is specified, the 's5m8767,pmic-buck[2/3/4]-dvs-voltage'
+     property should specify atleast one voltage level (which would be a
+     safe operating voltage).
+
+     If either of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional
+     property is specified, then all the eight voltage values for the
+     's5m8767,pmic-buck[2/3/4]-dvs-voltage' should be specified.
+
+Optional properties of the main device node (the parent!):
+ - s5m8767,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs.
+ - s5m8767,pmic-buck3-uses-gpio-dvs: 'buck3' can be controlled by gpio dvs.
+ - s5m8767,pmic-buck4-uses-gpio-dvs: 'buck4' can be controlled by gpio dvs.
+
+Additional properties required if either of the optional properties are used:
+
+ - s5m8767,pmic-buck234-default-dvs-idx: Default voltage setting selected from
+   the possible 8 options selectable by the dvs gpios. The value of this
+   property should be between 0 and 7. If not specified or if out of range, the
+   default value of this property is set to 0.
+
+ - s5m8767,pmic-buck-dvs-gpios: GPIO specifiers for three host gpio's used
+   for dvs. The format of the gpio specifier depends in the gpio controller.
+
+
+Names of regulators supported by S5M8767 device:
+	- LDOn
+		  - valid values for n are 1 to 28
+		  - Example: LDO1, LDO2, LDO28
+	- BUCKn
+		  - valid values for n are 1 to 9.
+		  - Example: BUCK1, BUCK2, BUCK9
+Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
+as per the datasheet of device.
+
+
+Optional properties of the nodes under "regulators" sub-node:
+ - op_mode: describes the different operating modes of the LDO's with
+            power mode change in SOC. The different possible values are,
+             0 - always off mode
+             1 - on in normal mode
+             2 - low power mode
+             3 - suspend mode
+ - s5m8767,pmic-ext-control-gpios: (optional) GPIO specifier for one
+                                   GPIO controlling this regulator
+                                   (enable/disable); This is valid only
+                                   for buck9.
+
+Example:
+
+	s5m8767_pmic@66 {
+		compatible = "samsung,s5m8767-pmic";
+		reg = <0x66>;
+
+		s5m8767,pmic-buck2-uses-gpio-dvs;
+		s5m8767,pmic-buck3-uses-gpio-dvs;
+		s5m8767,pmic-buck4-uses-gpio-dvs;
+
+		s5m8767,pmic-buck-default-dvs-idx = <0>;
+
+		s5m8767,pmic-buck-dvs-gpios = <&gpx0 0 0>, /* DVS1 */
+						 <&gpx0 1 0>, /* DVS2 */
+						 <&gpx0 2 0>; /* DVS3 */
+
+		s5m8767,pmic-buck-ds-gpios = <&gpx2 3 0>, /* SET1 */
+						<&gpx2 4 0>, /* SET2 */
+						<&gpx2 5 0>; /* SET3 */
+
+		s5m8767,pmic-buck2-dvs-voltage = <1350000>, <1300000>,
+						 <1250000>, <1200000>,
+						 <1150000>, <1100000>,
+						 <1000000>, <950000>;
+
+		s5m8767,pmic-buck3-dvs-voltage = <1100000>, <1100000>,
+						 <1100000>, <1100000>,
+						 <1000000>, <1000000>,
+						 <1000000>, <1000000>;
+
+		s5m8767,pmic-buck4-dvs-voltage = <1200000>, <1200000>,
+						 <1200000>, <1200000>,
+						 <1200000>, <1200000>,
+						 <1200000>, <1200000>;
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ABB_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				op_mode = <1>; /* Normal Mode */
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDD_ALIVE_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "VDD_MIF_1.2V";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			vemmc_reg: BUCK9 {
+				regulator-name = "VMEM_VDD_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				op_mode = <3>; /* Standby Mode */
+				s5m8767,pmic-ext-control-gpios = <&gpk0 2 0>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt b/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt
new file mode 100644
index 000000000000..e0b185a944ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt
@@ -0,0 +1,34 @@
+Hisilicon System Reset Controller
+======================================
+
+Please also refer to reset.txt in this directory for common reset
+controller binding usage.
+
+The reset controller registers are part of the system-ctl block on
+hi6220 SoC.
+
+Required properties:
+- compatible: may be "hisilicon,hi6220-sysctrl"
+- reg: should be register base and length as documented in the
+  datasheet
+- #reset-cells: 1, see below
+
+Example:
+sys_ctrl: sys_ctrl@f7030000 {
+	compatible = "hisilicon,hi6220-sysctrl", "syscon";
+	reg = <0x0 0xf7030000 0x0 0x2000>;
+	#clock-cells = <1>;
+	#reset-cells = <1>;
+};
+
+Specifying reset lines connected to IP modules
+==============================================
+example:
+
+        uart1: serial@..... {
+                ...
+                resets = <&sys_ctrl PERIPH_RSTEN3_UART1>;
+                ...
+        };
+
+The index could be found in <dt-bindings/reset/hisi,hi6220-resets.h>.
diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
index ac2fcd6ff4b8..1068ffce9f91 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
@@ -14,6 +14,10 @@ Required properties:
   interrupt number is the rtc alarm interrupt and second interrupt number
   is the rtc tick interrupt. The number of cells representing a interrupt
   depends on the parent interrupt controller.
+- clocks: Must contain a list of phandle and clock specifier for the rtc
+          and source clocks.
+- clock-names: Must contain "rtc" and "rtc_src" entries sorted in the
+               same order as the clocks property.
 
 Example:
 
@@ -21,4 +25,6 @@ Example:
 		compatible = "samsung,s3c6410-rtc";
 		reg = <0x10070000 0x100>;
 		interrupts = <44 0 45 0>;
+		clocks = <&clock CLK_RTC>, <&s2mps11_osc S2MPS11_CLK_AP>;
+		clock-names = "rtc", "rtc_src";
 	};
diff --git a/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
new file mode 100644
index 000000000000..f67e761bcc18
--- /dev/null
+++ b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
@@ -0,0 +1,69 @@
+* HiSilicon SAS controller
+
+The HiSilicon SAS controller supports SAS/SATA.
+
+Main node required properties:
+  - compatible : value should be as follows:
+	(a) "hisilicon,hip05-sas-v1" for v1 hw in hip05 chipset
+  - sas-addr : array of 8 bytes for host SAS address
+  - reg : Address and length of the SAS register
+  - hisilicon,sas-syscon: phandle of syscon used for sas control
+  - ctrl-reset-reg : offset to controller reset register in ctrl reg
+  - ctrl-reset-sts-reg : offset to controller reset status register in ctrl reg
+  - ctrl-clock-ena-reg : offset to controller clock enable register in ctrl reg
+  - queue-count : number of delivery and completion queues in the controller
+  - phy-count : number of phys accessible by the controller
+  - interrupts : Interrupts for phys, completion queues, and fatal
+		sources; the interrupts are ordered in 3 groups, as follows:
+			- Phy interrupts
+			- Completion queue interrupts
+			- Fatal interrupts
+		Phy interrupts : Each phy has 3 interrupt sources:
+			- broadcast
+			- phyup
+			- abnormal
+		The phy interrupts are ordered into groups of 3 per phy
+		(broadcast, phyup, and abnormal) in increasing order.
+		Completion queue interrupts : each completion queue has 1
+			interrupt source.
+			The interrupts are ordered in increasing order.
+		Fatal interrupts : the fatal interrupts are ordered as follows:
+			- ECC
+			- AXI bus
+
+Example:
+	sas0: sas@c1000000 {
+		compatible = "hisilicon,hip05-sas-v1";
+		sas-addr = [50 01 88 20 16 00 00 0a];
+		reg = <0x0 0xc1000000 0x0 0x10000>;
+		hisilicon,sas-syscon = <&pcie_sas>;
+		ctrl-reset-reg = <0xa60>;
+		ctrl-reset-sts-reg = <0x5a30>;
+		ctrl-clock-ena-reg = <0x338>;
+		queue-count = <32>;
+		phy-count = <8>;
+		dma-coherent;
+		interrupt-parent = <&mbigen_dsa>;
+		interrupts =    <259 4>,<263 4>,<264 4>,/* phy0 */
+				<269 4>,<273 4>,<274 4>,/* phy1 */
+				<279 4>,<283 4>,<284 4>,/* phy2 */
+				<289 4>,<293 4>,<294 4>,/* phy3 */
+				<299 4>,<303 4>,<304 4>,/* phy4 */
+				<309 4>,<313 4>,<314 4>,/* phy5 */
+				<319 4>,<323 4>,<324 4>,/* phy6 */
+				<329 4>,<333 4>,<334 4>,/* phy7 */
+				<336 1>,<337 1>,<338 1>,/* cq0-2 */
+				<339 1>,<340 1>,<341 1>,/* cq3-5 */
+				<342 1>,<343 1>,<344 1>,/* cq6-8 */
+				<345 1>,<346 1>,<347 1>,/* cq9-11 */
+				<348 1>,<349 1>,<350 1>,/* cq12-14 */
+				<351 1>,<352 1>,<353 1>,/* cq15-17 */
+				<354 1>,<355 1>,<356 1>,/* cq18-20 */
+				<357 1>,<358 1>,<359 1>,/* cq21-23 */
+				<360 1>,<361 1>,<362 1>,/* cq24-26 */
+				<363 1>,<364 1>,<365 1>,/* cq27-29 */
+				<366 1>,<367 1>/* cq30-31 */
+				<376 4>,/* fatal ecc */
+				<381 4>;/* fatal axi */
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt
index 91d5ab0e60fc..936ab5b87324 100644
--- a/Documentation/devicetree/bindings/serial/8250.txt
+++ b/Documentation/devicetree/bindings/serial/8250.txt
@@ -14,7 +14,6 @@ Required properties:
 	  tegra132, or tegra210.
 	- "nxp,lpc3220-uart"
 	- "ralink,rt2880-uart"
-	- "ibm,qpace-nwp-serial"
 	- "altr,16550-FIFO32"
 	- "altr,16550-FIFO64"
 	- "altr,16550-FIFO128"
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
index 35ae1fb3537f..ed94c217c98d 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
@@ -9,7 +9,7 @@ Optional properties:
 - fsl,uart-has-rtscts : Indicate the uart has rts and cts
 - fsl,irda-mode : Indicate the uart supports irda mode
 - fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
-                  is DCE mode by default.
+                  in DCE mode by default.
 
 Note: Each uart controller should have an alias correctly numbered
 in "aliases" node.
diff --git a/Documentation/devicetree/bindings/serial/mtk-uart.txt b/Documentation/devicetree/bindings/serial/mtk-uart.txt
index 2d47add34765..a833a016f656 100644
--- a/Documentation/devicetree/bindings/serial/mtk-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mtk-uart.txt
@@ -2,15 +2,15 @@
 
 Required properties:
 - compatible should contain:
-  * "mediatek,mt8135-uart" for MT8135 compatible UARTS
+  * "mediatek,mt2701-uart" for MT2701 compatible UARTS
+  * "mediatek,mt6580-uart" for MT6580 compatible UARTS
+  * "mediatek,mt6582-uart" for MT6582 compatible UARTS
+  * "mediatek,mt6589-uart" for MT6589 compatible UARTS
+  * "mediatek,mt6795-uart" for MT6795 compatible UARTS
   * "mediatek,mt8127-uart" for MT8127 compatible UARTS
+  * "mediatek,mt8135-uart" for MT8135 compatible UARTS
   * "mediatek,mt8173-uart" for MT8173 compatible UARTS
-  * "mediatek,mt6795-uart" for MT6795 compatible UARTS
-  * "mediatek,mt6589-uart" for MT6589 compatible UARTS
-  * "mediatek,mt6582-uart" for MT6582 compatible UARTS
-  * "mediatek,mt6580-uart" for MT6580 compatible UARTS
-  * "mediatek,mt6577-uart" for all compatible UARTS (MT8173, MT6795,
-        MT6589, MT6582, MT6580, MT6577)
+  * "mediatek,mt6577-uart" for MT6577 and all of the above
 
 - reg: The base address of the UART register bank.
 
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index 73f825e5e644..401b1b33c2c4 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -2,7 +2,7 @@
 
 Required properties:
 
-  - compatible: Must contain one of the following:
+  - compatible: Must contain one or more of the following:
 
     - "renesas,scif-r7s72100" for R7S72100 (RZ/A1H) SCIF compatible UART.
     - "renesas,scifa-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFA compatible UART.
@@ -15,10 +15,14 @@ Required properties:
     - "renesas,scifa-r8a7790" for R8A7790 (R-Car H2) SCIFA compatible UART.
     - "renesas,scifb-r8a7790" for R8A7790 (R-Car H2) SCIFB compatible UART.
     - "renesas,hscif-r8a7790" for R8A7790 (R-Car H2) HSCIF compatible UART.
-    - "renesas,scif-r8a7791" for R8A7791 (R-Car M2) SCIF compatible UART.
-    - "renesas,scifa-r8a7791" for R8A7791 (R-Car M2) SCIFA compatible UART.
-    - "renesas,scifb-r8a7791" for R8A7791 (R-Car M2) SCIFB compatible UART.
-    - "renesas,hscif-r8a7791" for R8A7791 (R-Car M2) HSCIF compatible UART.
+    - "renesas,scif-r8a7791" for R8A7791 (R-Car M2-W) SCIF compatible UART.
+    - "renesas,scifa-r8a7791" for R8A7791 (R-Car M2-W) SCIFA compatible UART.
+    - "renesas,scifb-r8a7791" for R8A7791 (R-Car M2-W) SCIFB compatible UART.
+    - "renesas,hscif-r8a7791" for R8A7791 (R-Car M2-W) HSCIF compatible UART.
+    - "renesas,scif-r8a7793" for R8A7793 (R-Car M2-N) SCIF compatible UART.
+    - "renesas,scifa-r8a7793" for R8A7793 (R-Car M2-N) SCIFA compatible UART.
+    - "renesas,scifb-r8a7793" for R8A7793 (R-Car M2-N) SCIFB compatible UART.
+    - "renesas,hscif-r8a7793" for R8A7793 (R-Car M2-N) HSCIF compatible UART.
     - "renesas,scif-r8a7794" for R8A7794 (R-Car E2) SCIF compatible UART.
     - "renesas,scifa-r8a7794" for R8A7794 (R-Car E2) SCIFA compatible UART.
     - "renesas,scifb-r8a7794" for R8A7794 (R-Car E2) SCIFB compatible UART.
@@ -27,6 +31,14 @@ Required properties:
     - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART.
     - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART.
     - "renesas,scifb-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFB compatible UART.
+    - "renesas,rcar-gen1-scif" for R-Car Gen1 SCIF compatible UART,
+    - "renesas,rcar-gen2-scif" for R-Car Gen2 SCIF compatible UART,
+    - "renesas,rcar-gen3-scif" for R-Car Gen3 SCIF compatible UART,
+    - "renesas,rcar-gen2-scifa" for R-Car Gen2 SCIFA compatible UART,
+    - "renesas,rcar-gen2-scifb" for R-Car Gen2 SCIFB compatible UART,
+    - "renesas,rcar-gen1-hscif" for R-Car Gen1 HSCIF compatible UART,
+    - "renesas,rcar-gen2-hscif" for R-Car Gen2 HSCIF compatible UART,
+    - "renesas,rcar-gen3-hscif" for R-Car Gen3 HSCIF compatible UART,
     - "renesas,scif" for generic SCIF compatible UART.
     - "renesas,scifa" for generic SCIFA compatible UART.
     - "renesas,scifb" for generic SCIFB compatible UART.
@@ -34,15 +46,26 @@ Required properties:
     - "renesas,sci" for generic SCI compatible UART.
 
     When compatible with the generic version, nodes must list the
-    SoC-specific version corresponding to the platform first followed by the
-    generic version.
+    SoC-specific version corresponding to the platform first, followed by the
+    family-specific and/or generic versions.
 
   - reg: Base address and length of the I/O registers used by the UART.
   - interrupts: Must contain an interrupt-specifier for the SCIx interrupt.
 
   - clocks: Must contain a phandle and clock-specifier pair for each entry
     in clock-names.
-  - clock-names: Must contain "sci_ick" for the SCIx UART interface clock.
+  - clock-names: Must contain "fck" for the SCIx UART functional clock.
+    Apart from the divided functional clock, there may be other possible
+    sources for the sampling clock, depending on SCIx variant.
+    On (H)SCI(F) and some SCIFA, an additional clock may be specified:
+      - "hsck" for the optional external clock input (on HSCIF),
+      - "sck" for the optional external clock input (on other variants).
+    On UARTs equipped with a Baud Rate Generator for External Clock (BRG)
+    (some SCIF and HSCIF), additional clocks may be specified:
+      - "brg_int" for the optional internal clock source for the frequency
+	divider (typically the (AXI or SHwy) bus clock),
+      - "scif_clk" for the optional external clock source for the frequency
+	divider (SCIF_CLK).
 
 Note: Each enabled SCIx UART should have an alias correctly numbered in the
 "aliases" node.
@@ -58,12 +81,13 @@ Example:
 	};
 
 	scifa0: serial@e6c40000 {
-		compatible = "renesas,scifa-r8a7790", "renesas,scifa";
+		compatible = "renesas,scifa-r8a7790",
+			     "renesas,rcar-gen2-scifa", "renesas,scifa";
 		reg = <0 0xe6c40000 0 64>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 144 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFA0>;
-		clock-names = "sci_ick";
+		clock-names = "fck";
 		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
 		dma-names = "tx", "rx";
 	};
diff --git a/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt b/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt
new file mode 100644
index 000000000000..30942cf7992b
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt
@@ -0,0 +1,47 @@
+Raspberry Pi power domain driver
+
+Required properties:
+
+- compatible:		Should be "raspberrypi,bcm2835-power".
+- firmware:		Reference to the RPi firmware device node.
+- #power-domain-cells:	Should be <1>, we providing multiple power domains.
+
+The valid defines for power domain are:
+
+ RPI_POWER_DOMAIN_I2C0
+ RPI_POWER_DOMAIN_I2C1
+ RPI_POWER_DOMAIN_I2C2
+ RPI_POWER_DOMAIN_VIDEO_SCALER
+ RPI_POWER_DOMAIN_VPU1
+ RPI_POWER_DOMAIN_HDMI
+ RPI_POWER_DOMAIN_USB
+ RPI_POWER_DOMAIN_VEC
+ RPI_POWER_DOMAIN_JPEG
+ RPI_POWER_DOMAIN_H264
+ RPI_POWER_DOMAIN_V3D
+ RPI_POWER_DOMAIN_ISP
+ RPI_POWER_DOMAIN_UNICAM0
+ RPI_POWER_DOMAIN_UNICAM1
+ RPI_POWER_DOMAIN_CCP2RX
+ RPI_POWER_DOMAIN_CSI2
+ RPI_POWER_DOMAIN_CPI
+ RPI_POWER_DOMAIN_DSI0
+ RPI_POWER_DOMAIN_DSI1
+ RPI_POWER_DOMAIN_TRANSPOSER
+ RPI_POWER_DOMAIN_CCP2TX
+ RPI_POWER_DOMAIN_CDP
+ RPI_POWER_DOMAIN_ARM
+
+Example:
+
+power: power {
+	compatible = "raspberrypi,bcm2835-power";
+	firmware = <&firmware>;
+	#power-domain-cells = <1>;
+};
+
+Example for using power domain:
+
+&usb {
+       power-domains = <&power RPI_POWER_DOMAIN_USB>;
+};
diff --git a/Documentation/devicetree/bindings/soc/dove/pmu.txt b/Documentation/devicetree/bindings/soc/dove/pmu.txt
new file mode 100644
index 000000000000..edd40b796b74
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/dove/pmu.txt
@@ -0,0 +1,56 @@
+Device Tree bindings for Marvell PMU
+
+Required properties:
+ - compatible: value should be "marvell,dove-pmu".
+    May also include "simple-bus" if there are child devices, in which
+    case the ranges node is required.
+ - reg: two base addresses and sizes of the PM controller and PMU.
+ - interrupts: single interrupt number for the PMU interrupt
+ - interrupt-controller: must be specified as the PMU itself is an
+    interrupt controller.
+ - #interrupt-cells: must be 1.
+ - #reset-cells: must be 1.
+ - domains: sub-node containing domain descriptions
+
+Optional properties:
+ - ranges: defines the address mapping for child devices, as per the
+   standard property of this name.  Required when compatible includes
+   "simple-bus".
+
+Power domain descriptions are listed as child nodes of the "domains"
+sub-node.  Each domain has the following properties:
+
+Required properties:
+ - #power-domain-cells: must be 0.
+
+Optional properties:
+ - marvell,pmu_pwr_mask: specifies the mask value for PMU power register
+ - marvell,pmu_iso_mask: specifies the mask value for PMU isolation register
+ - resets: points to the reset manager (PMU node) and reset index.
+
+Example:
+
+	pmu: power-management@d0000 {
+		compatible = "marvell,dove-pmu";
+		reg = <0xd0000 0x8000>, <0xd8000 0x8000>;
+		interrupts = <33>;
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		#reset-cells = <1>;
+
+		domains {
+			vpu_domain: vpu-domain {
+				#power-domain-cells = <0>;
+				marvell,pmu_pwr_mask = <0x00000008>;
+				marvell,pmu_iso_mask = <0x00000001>;
+				resets = <&pmu 16>;
+			};
+
+			gpu_domain: gpu-domain {
+				#power-domain-cells = <0>;
+				marvell,pmu_pwr_mask = <0x00000004>;
+				marvell,pmu_iso_mask = <0x00000002>;
+				resets = <&pmu 18>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
index a6c8afc8385a..e8f15e34027f 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
+++ b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
@@ -21,6 +21,18 @@ Required properties:
 		      These are the clocks which hardware needs to be enabled
 		      before enabling certain power domains.
 
+Optional properties:
+- vdec-supply: Power supply for the vdec power domain
+- venc-supply: Power supply for the venc power domain
+- isp-supply: Power supply for the isp power domain
+- mm-supply: Power supply for the mm power domain
+- venc_lt-supply: Power supply for the venc_lt power domain
+- audio-supply: Power supply for the audio power domain
+- usb-supply: Power supply for the usb power domain
+- mfg_async-supply: Power supply for the mfg_async power domain
+- mfg_2d-supply: Power supply for the mfg_2d power domain
+- mfg-supply: Power supply for the mfg power domain
+
 Example:
 
 	scpsys: scpsys@10006000 {
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt
new file mode 100644
index 000000000000..a48049ccf6d0
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt
@@ -0,0 +1,58 @@
+Qualcomm Resource Power Manager (RPM) over SMD
+
+This driver is used to interface with the Resource Power Manager (RPM) found in
+various Qualcomm platforms. The RPM allows each component in the system to vote
+for state of the system resources, such as clocks, regulators and bus
+frequencies.
+
+The SMD information for the RPM edge should be filled out.  See qcom,smd.txt for
+the required edge properties.  All SMD related properties will reside within the
+RPM node itself.
+
+= SUBDEVICES
+
+The RPM exposes resources to its subnodes.  The rpm_requests node must be
+present and this subnode may contain children that designate regulator
+resources.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,rpm-apq8084"
+		    "qcom,rpm-msm8916"
+		    "qcom,rpm-msm8974"
+
+- qcom,smd-channels:
+	Usage: required
+	Value type: <string>
+	Definition: must be "rpm_requests"
+
+Refer to Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
+for information on the regulator subnodes that can exist under the rpm_requests.
+
+Example:
+
+	soc {
+		apcs: syscon@f9011000 {
+			compatible = "syscon";
+			reg = <0xf9011000 0x1000>;
+		};
+	};
+
+	smd {
+		compatible = "qcom,smd";
+
+		rpm {
+			interrupts = <0 168 1>;
+			qcom,ipc = <&apcs 8 0>;
+			qcom,smd-edge = <15>;
+
+			rpm_requests {
+				compatible = "qcom,rpm-msm8974";
+				qcom,smd-channels = "rpm_requests";
+
+				...
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
new file mode 100644
index 000000000000..5cc82b8353d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
@@ -0,0 +1,104 @@
+Qualcomm Shared Memory Point 2 Point binding
+
+The Shared Memory Point to Point (SMP2P) protocol facilitates communication of
+a single 32-bit value between two processors.  Each value has a single writer
+(the local side) and a single reader (the remote side).  Values are uniquely
+identified in the system by the directed edge (local processor ID to remote
+processor ID) and a string identifier.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,smp2p"
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: one entry specifying the smp2p notification interrupt
+
+- qcom,ipc:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: three entries specifying the outgoing ipc bit used for
+		    signaling the remote end of the smp2p edge:
+		    - phandle to a syscon node representing the apcs registers
+		    - u32 representing offset to the register within the syscon
+		    - u32 representing the ipc bit within the register
+
+- qcom,smem:
+	Usage: required
+	Value type: <u32 array>
+	Definition: two identifiers of the inbound and outbound smem items used
+		    for this edge
+
+- qcom,local-pid:
+	Usage: required
+	Value type: <u32>
+	Definition: specifies the identfier of the local endpoint of this edge
+
+- qcom,remote-pid:
+	Usage: required
+	Value type: <u32>
+	Definition: specifies the identfier of the remote endpoint of this edge
+
+= SUBNODES
+Each SMP2P pair contain a set of inbound and outbound entries, these are
+described in subnodes of the smp2p device node. The node names are not
+important.
+
+- qcom,entry-name:
+	Usage: required
+	Value type: <string>
+	Definition: specifies the name of this entry, for inbound entries this
+		    will be used to match against the remotely allocated entry
+		    and for outbound entries this name is used for allocating
+		    entries
+
+- interrupt-controller:
+	Usage: required for incoming entries
+	Value type: <empty>
+	Definition: marks the entry as inbound; the node should be specified
+		    as a two cell interrupt-controller as defined in
+		    "../interrupt-controller/interrupts.txt"
+		    If not specified this node will denote the outgoing entry
+
+- #interrupt-cells:
+	Usage: required for incoming entries
+	Value type: <u32>
+	Definition: must be 2 - denoting the bit in the entry and IRQ flags
+
+- #qcom,state-cells:
+	Usage: required for outgoing entries
+	Value type: <u32>
+	Definition: must be 1 - denoting the bit in the entry
+
+= EXAMPLE
+The following example shows the SMP2P setup with the wireless processor,
+defined from the 8974 apps processor's point-of-view. It encompasses one
+inbound and one outbound entry:
+
+wcnss-smp2p {
+	compatible = "qcom,smp2p";
+	qcom,smem = <431>, <451>;
+
+	interrupts = <0 143 1>;
+
+	qcom,ipc = <&apcs 8 18>;
+
+	qcom,local-pid = <0>;
+	qcom,remote-pid = <4>;
+
+	wcnss_smp2p_out: master-kernel {
+		qcom,entry-name = "master-kernel";
+
+		#qcom,state-cells = <1>;
+	};
+
+	wcnss_smp2p_in: slave-kernel {
+		qcom,entry-name = "slave-kernel";
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt
new file mode 100644
index 000000000000..a6634c70850d
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt
@@ -0,0 +1,104 @@
+Qualcomm Shared Memory State Machine
+
+The Shared Memory State Machine facilitates broadcasting of single bit state
+information between the processors in a Qualcomm SoC. Each processor is
+assigned 32 bits of state that can be modified. A processor can through a
+matrix of bitmaps signal subscription of notifications upon changes to a
+certain bit owned by a certain remote processor.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,smsm"
+
+- qcom,ipc-N:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: three entries specifying the outgoing ipc bit used for
+		    signaling the N:th remote processor
+		    - phandle to a syscon node representing the apcs registers
+		    - u32 representing offset to the register within the syscon
+		    - u32 representing the ipc bit within the register
+
+- qcom,local-host:
+	Usage: optional
+	Value type: <u32>
+	Definition: identifier of the local processor in the list of hosts, or
+		    in other words specifier of the column in the subscription
+		    matrix representing the local processor
+		    defaults to host 0
+
+- #address-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 1
+
+- #size-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 0
+
+= SUBNODES
+Each processor's state bits are described by a subnode of the smsm device node.
+Nodes can either be flagged as an interrupt-controller to denote a remote
+processor's state bits or the local processors bits.  The node names are not
+important.
+
+- reg:
+	Usage: required
+	Value type: <u32>
+	Definition: specifies the offset, in words, of the first bit for this
+		    entry
+
+- #qcom,state-cells:
+	Usage: required for local entry
+	Value type: <u32>
+	Definition: must be 1 - denotes bit number
+
+- interrupt-controller:
+	Usage: required for remote entries
+	Value type: <empty>
+	Definition: marks the entry as a interrupt-controller and the state bits
+		    to belong to a remote processor
+
+- #interrupt-cells:
+	Usage: required for remote entries
+	Value type: <u32>
+	Definition: must be 2 - denotes bit number and IRQ flags
+
+- interrupts:
+	Usage: required for remote entries
+	Value type: <prop-encoded-array>
+	Definition: one entry specifying remote IRQ used by the remote processor
+		    to signal changes of its state bits
+
+
+= EXAMPLE
+The following example shows the SMEM setup for controlling properties of the
+wireless processor, defined from the 8974 apps processor's point-of-view. It
+encompasses one outbound entry and the outgoing interrupt for the wireless
+processor.
+
+smsm {
+	compatible = "qcom,smsm";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	qcom,ipc-3 = <&apcs 8 19>;
+
+	apps_smsm: apps@0 {
+		reg = <0>;
+
+		#qcom,state-cells = <1>;
+	};
+
+	wcnss_smsm: wcnss@7 {
+		reg = <7>;
+		interrupts = <0 144 1>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/soc/ti/wkup_m3_ipc.txt b/Documentation/devicetree/bindings/soc/ti/wkup_m3_ipc.txt
new file mode 100644
index 000000000000..401550487ed6
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/ti/wkup_m3_ipc.txt
@@ -0,0 +1,57 @@
+Wakeup M3 IPC Driver
+=====================
+
+The TI AM33xx and AM43xx family of devices use a small Cortex M3 co-processor
+(commonly referred to as Wakeup M3 or CM3) to help with various low power tasks
+that cannot be controlled from the MPU, like suspend/resume and certain deep
+C-states for CPU Idle. Once the wkup_m3_ipc driver uses the wkup_m3_rproc driver
+to boot the wkup_m3, it handles communication with the CM3 using IPC registers
+present in the SoC's control module and a mailbox. The wkup_m3_ipc exposes an
+API to allow the SoC PM code to execute specific PM tasks.
+
+Wkup M3 Device Node:
+====================
+A wkup_m3_ipc device node is used to represent the IPC registers within an
+SoC.
+
+Required properties:
+--------------------
+- compatible:		Should be,
+				"ti,am3352-wkup-m3-ipc" for AM33xx SoCs
+				"ti,am4372-wkup-m3-ipc" for AM43xx SoCs
+- reg:			Contains the IPC register address space to communicate
+			with the Wakeup M3 processor
+- interrupts:		Contains the interrupt information for the wkup_m3
+			interrupt that signals the MPU.
+- ti,rproc:		phandle to the wkup_m3 rproc node so the IPC driver
+			can boot it.
+- mboxes:		phandles used by IPC framework to get correct mbox
+			channel for communication. Must point to appropriate
+			mbox_wkupm3 child node.
+
+Example:
+--------
+/* AM33xx */
+	l4_wkup: l4_wkup@44c00000 {
+		...
+
+		scm: scm@210000 {
+			compatible = "ti,am3-scm", "simple-bus";
+			reg = <0x210000 0x2000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x210000 0x2000>;
+
+			...
+
+			wkup_m3_ipc: wkup_m3_ipc@1324 {
+				compatible = "ti,am3352-wkup-m3-ipc";
+				reg = <0x1324 0x24>;
+				interrupts = <78>;
+				ti,rproc = <&wkup_m3>;
+				mboxes = <&mailbox &mbox_wkupm3>;
+			};
+
+			...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/ak4613.txt b/Documentation/devicetree/bindings/sound/ak4613.txt
index 15a919522b42..1783f9ef0930 100644
--- a/Documentation/devicetree/bindings/sound/ak4613.txt
+++ b/Documentation/devicetree/bindings/sound/ak4613.txt
@@ -7,6 +7,16 @@ Required properties:
 - compatible : "asahi-kasei,ak4613"
 - reg : The chip select number on the I2C bus
 
+Optional properties:
+- asahi-kasei,in1-single-end	: Boolean. Indicate input / output pins are single-ended.
+- asahi-kasei,in2-single-end	  rather than differential.
+- asahi-kasei,out1-single-end
+- asahi-kasei,out2-single-end
+- asahi-kasei,out3-single-end
+- asahi-kasei,out4-single-end
+- asahi-kasei,out5-single-end
+- asahi-kasei,out6-single-end
+
 Example:
 
 &i2c {
diff --git a/Documentation/devicetree/bindings/sound/atmel-classd.txt b/Documentation/devicetree/bindings/sound/atmel-classd.txt
index 0018451c4351..549e701cb7a1 100644
--- a/Documentation/devicetree/bindings/sound/atmel-classd.txt
+++ b/Documentation/devicetree/bindings/sound/atmel-classd.txt
@@ -16,6 +16,10 @@ Required properties:
 	Required elements: "pclk", "gclk" and "aclk".
 - clocks
 	Please refer to clock-bindings.txt.
+- assigned-clocks
+	Should be <&classd_gclk>.
+- assigned-clock-parents
+	Should be <&audio_pll_pmc>.
 
 Optional properties:
 - pinctrl-names, pinctrl-0
@@ -43,6 +47,8 @@ classd: classd@fc048000 {
 		dma-names = "tx";
 		clocks = <&classd_clk>, <&classd_gclk>, <&audio_pll_pmc>;
 		clock-names = "pclk", "gclk", "aclk";
+		assigned-clocks = <&classd_gclk>;
+		assigned-clock-parents = <&audio_pll_pmc>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_classd_default>;
diff --git a/Documentation/devicetree/bindings/sound/atmel-pdmic.txt b/Documentation/devicetree/bindings/sound/atmel-pdmic.txt
new file mode 100644
index 000000000000..e0875f17c229
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/atmel-pdmic.txt
@@ -0,0 +1,55 @@
+* Atmel PDMIC driver under ALSA SoC architecture
+
+Required properties:
+- compatible
+	Should be "atmel,sama5d2-pdmic".
+- reg
+	Should contain PDMIC registers location and length.
+- interrupts
+	Should contain the IRQ line for the PDMIC.
+- dmas
+	One DMA specifiers as described in atmel-dma.txt and dma.txt files.
+- dma-names
+	Must be "rx".
+- clock-names
+	Required elements:
+	- "pclk"	peripheral clock
+	- "gclk"	generated clock
+- clocks
+	Must contain an entry for each required entry in clock-names.
+	Please refer to clock-bindings.txt.
+- atmel,mic-min-freq
+	The minimal frequency that the micphone supports.
+- atmel,mic-max-freq
+	The maximal frequency that the micphone supports.
+
+Optional properties:
+- pinctrl-names, pinctrl-0
+	Please refer to pinctrl-bindings.txt.
+- atmel,model
+	The user-visible name of this sound card.
+	The default value is "PDMIC".
+- atmel,mic-offset
+	The offset that should be added.
+	The range is from -32768 to 32767.
+	The default value is 0.
+
+Example:
+	pdmic@f8018000 {
+				compatible = "atmel,sama5d2-pdmic";
+				reg = <0xf8018000 0x124>;
+				interrupts = <48 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)
+					| AT91_XDMAC_DT_PERID(50))>;
+				dma-names = "rx";
+				clocks = <&pdmic_clk>, <&pdmic_gclk>;
+				clock-names = "pclk", "gclk";
+
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_pdmic_default>;
+				atmel,model = "PDMIC @ sama5d2_xplained";
+				atmel,mic-min-freq = <1000000>;
+				atmel,mic-max-freq = <3246000>;
+				atmel,mic-offset = <0x0>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
new file mode 100644
index 000000000000..5ca5a709b6aa
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -0,0 +1,104 @@
+Dialog Semiconductor DA7218 Audio Codec bindings
+
+DA7218 is an audio codec with HP detect feature.
+
+======
+
+Required properties:
+- compatible : Should be "dlg,da7217" or "dlg,da7218"
+- reg: Specifies the I2C slave address
+
+- VDD-supply: VDD power supply for the device
+- VDDMIC-supply: VDDMIC power supply for the device
+- VDDIO-supply: VDDIO power supply for the device
+  (See Documentation/devicetree/bindings/regulator/regulator.txt for further
+   information relating to regulators)
+
+Optional properties:
+- interrupt-parent: Specifies the phandle of the interrupt controller to which
+  the IRQs from DA7218 are delivered to.
+- interrupts: IRQ line info for DA7218 chip.
+  (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
+   further information relating to interrupt properties)
+- interrupt-names : Name associated with interrupt line. Should be "wakeup" if
+  interrupt is to be used to wake system, otherwise "irq" should be used.
+- wakeup-source: Flag to indicate this device can wake system (suspend/resume).
+
+- clocks : phandle and clock specifier for codec MCLK.
+- clock-names : Clock name string for 'clocks' attribute, should be "mclk".
+
+- dlg,micbias1-lvl-millivolt : Voltage (mV) for Mic Bias 1
+	[<1200>, <1600>, <1800>, <2000>, <2200>, <2400>, <2600>, <2800>, <3000>]
+- dlg,micbias2-lvl-millivolt : Voltage (mV) for Mic Bias 2
+	[<1200>, <1600>, <1800>, <2000>, <2200>, <2400>, <2600>, <2800>, <3000>]
+- dlg,mic1-amp-in-sel : Mic1 input source type
+	["diff", "se_p", "se_n"]
+- dlg,mic2-amp-in-sel : Mic2 input source type
+	["diff", "se_p", "se_n"]
+- dlg,dmic1-data-sel : DMIC1 channel select based on clock edge.
+	["lrise_rfall", "lfall_rrise"]
+- dlg,dmic1-samplephase : When to sample audio from DMIC1.
+	["on_clkedge", "between_clkedge"]
+- dlg,dmic1-clkrate-hz : DMic1 clock frequency (Hz).
+	[<1500000>, <3000000>]
+- dlg,dmic2-data-sel : DMic2 channel select based on clock edge.
+	["lrise_rfall", "lfall_rrise"]
+- dlg,dmic2-samplephase : When to sample audio from DMic2.
+	["on_clkedge", "between_clkedge"]
+- dlg,dmic2-clkrate-hz : DMic2 clock frequency (Hz).
+	[<1500000>, <3000000>]
+- dlg,hp-diff-single-supply : Boolean flag, use single supply for HP
+			      (DA7217 only)
+
+======
+
+Optional Child node - 'da7218_hpldet' (DA7218 only):
+
+Optional properties:
+- dlg,jack-rate-us : Time between jack detect measurements (us)
+	[<5>, <10>, <20>, <40>, <80>, <160>, <320>, <640>]
+- dlg,jack-debounce : Number of debounce measurements taken for jack detect
+	[<0>, <2>, <3>, <4>]
+- dlg,jack-threshold-pct : Threshold level for jack detection (% of VDD)
+	[<84>, <88>, <92>, <96>]
+- dlg,comp-inv : Boolean flag, invert comparator output
+- dlg,hyst : Boolean flag, enable hysteresis
+- dlg,discharge : Boolean flag, auto discharge of Mic Bias on jack removal
+
+======
+
+Example:
+
+	codec: da7218@1a {
+		compatible = "dlg,da7218";
+		reg = <0x1a>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		wakeup-source;
+
+		VDD-supply = <&reg_audio>;
+		VDDMIC-supply = <&reg_audio>;
+		VDDIO-supply = <&reg_audio>;
+
+		clocks = <&clks 201>;
+		clock-names = "mclk";
+
+		dlg,micbias1-lvl-millivolt = <2600>;
+		dlg,micbias2-lvl-millivolt = <2600>;
+		dlg,mic1-amp-in-sel = "diff";
+		dlg,mic2-amp-in-sel = "diff";
+
+		dlg,dmic1-data-sel = "lrise_rfall";
+		dlg,dmic1-samplephase = "on_clkedge";
+		dlg,dmic1-clkrate-hz = <3000000>;
+		dlg,dmic2-data-sel = "lrise_rfall";
+		dlg,dmic2-samplephase = "on_clkedge";
+		dlg,dmic2-clkrate-hz = <3000000>;
+
+		da7218_hpldet {
+			dlg,jack-rate-us = <40>;
+			dlg,jack-debounce = <2>;
+			dlg,jack-threshold-pct = <84>;
+			dlg,hyst;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index 1b7030911a3b..cf61681826b6 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -28,13 +28,15 @@ Optional properties:
 - clocks : phandle and clock specifier for codec MCLK.
 - clock-names : Clock name string for 'clocks' attribute, should be "mclk".
 
-- dlg,ldo-lvl : Required internal LDO voltage (mV) level for digital engine
-	[<1050>, <1100>, <1200>, <1400>]
 - dlg,micbias-lvl : Voltage (mV) for Mic Bias
-	[<1800>, <2000>, <2200>, <2400>, <2600>]
+	[<1600>, <1800>, <2000>, <2200>, <2400>, <2600>]
 - dlg,mic-amp-in-sel : Mic input source type
 	["diff", "se_p", "se_n"]
 
+Deprecated properties:
+- dlg,ldo-lvl : Required internal LDO voltage (mV) level for digital engine
+  (LDO unavailable in production HW so property no longer required).
+
 ======
 
 Child node - 'da7219_aad':
diff --git a/Documentation/devicetree/bindings/sound/fsl,asrc.txt b/Documentation/devicetree/bindings/sound/fsl,asrc.txt
index b93362a570be..3e26a9478e57 100644
--- a/Documentation/devicetree/bindings/sound/fsl,asrc.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,asrc.txt
@@ -25,6 +25,11 @@ Required properties:
 	"mem"		  Peripheral access clock to access registers.
 	"ipg"		  Peripheral clock to driver module.
 	"asrck_<0-f>"	  Clock sources for input and output clock.
+	"spba"		  The spba clock is required when ASRC is placed as a
+			  bus slave of the Shared Peripheral Bus and when two
+			  or more bus masters (CPU, DMA or DSP) try to access
+			  it. This property is optional depending on the SoC
+			  design.
 
    - big-endian		: If this property is absent, the little endian mode
 			  will be in use as default. Otherwise, the big endian
diff --git a/Documentation/devicetree/bindings/sound/fsl,esai.txt b/Documentation/devicetree/bindings/sound/fsl,esai.txt
index d3b6b5f48010..cd3ee5d84f03 100644
--- a/Documentation/devicetree/bindings/sound/fsl,esai.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,esai.txt
@@ -27,6 +27,11 @@ Required properties:
 			  derive HCK, SCK and FS.
 	"fsys"		  The system clock derived from ahb clock used to
 			  derive HCK, SCK and FS.
+	"spba"		  The spba clock is required when ESAI is placed as a
+			  bus slave of the Shared Peripheral Bus and when two
+			  or more bus masters (CPU, DMA or DSP) try to access
+			  it. This property is optional depending on the SoC
+			  design.
 
   - fsl,fifo-depth	: The number of elements in the transmit and receive
 			  FIFOs. This number is the maximum allowed value for
diff --git a/Documentation/devicetree/bindings/sound/fsl,spdif.txt b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
index b5ee32ee3706..4ca39ddc0417 100644
--- a/Documentation/devicetree/bindings/sound/fsl,spdif.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
@@ -27,6 +27,11 @@ Required properties:
 			  Transceiver Clock Diagram" of SoC reference manual.
 			  It can also be referred to TxClk_Source bit of
 			  register SPDIF_STC.
+	"spba"		  The spba clock is required when SPDIF is placed as a
+			  bus slave of the Shared Peripheral Bus and when two
+			  or more bus masters (CPU, DMA or DSP) try to access
+			  it. This property is optional depending on the SoC
+			  design.
 
    - big-endian		: If this property is absent, the native endian mode
 			  will be in use as default, or the big endian mode
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
index ce55c0a6f757..4da41bf1888e 100644
--- a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -30,6 +30,8 @@ The compatible list for this generic sound card currently:
  "fsl,imx-audio-sgtl5000"
  (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
 
+ "fsl,imx-audio-wm8960"
+
 Required properties:
 
   - compatible		: Contains one of entries in the compatible list.
diff --git a/Documentation/devicetree/bindings/sound/img,i2s-in.txt b/Documentation/devicetree/bindings/sound/img,i2s-in.txt
new file mode 100644
index 000000000000..423265cfc3d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,i2s-in.txt
@@ -0,0 +1,47 @@
+Imagination Technologies I2S Input Controller
+
+Required Properties:
+
+  - compatible : Compatible list, must contain "img,i2s-in"
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - reg : Offset and length of the register set for the device
+
+  - clocks : Contains an entry for each entry in clock-names
+
+  - clock-names : Must include the following entry:
+	"sys"	The system clock
+
+  - dmas: Contains an entry for each entry in dma-names.
+
+  - dma-names: Must include the following entry:
+	"rx"	Single DMA channel used by all active I2S channels
+
+  - img,i2s-channels : Number of I2S channels instantiated in the I2S in block
+
+Optional Properties:
+
+  - interrupts : Contains the I2S in interrupts. Depending on
+	the configuration, there may be no interrupts, one interrupt,
+	or an interrupt per I2S channel. For the case where there is
+	one interrupt per channel, the interrupts should be listed
+	in ascending channel order
+
+  - resets: Contains a phandle to the I2S in reset signal
+
+  - reset-names: Contains the reset signal name "rst"
+
+Example:
+
+i2s_in: i2s-in@18100800 {
+	compatible = "img,i2s-in";
+	reg = <0x18100800 0x200>;
+	interrupts = <GIC_SHARED 7 IRQ_TYPE_LEVEL_HIGH>;
+	dmas = <&mdc 30 0xffffffff 0>;
+	dma-names = "rx";
+	clocks = <&cr_periph SYS_CLK_I2S_IN>;
+	clock-names = "sys";
+	img,i2s-channels = <6>;
+	#sound-dai-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/img,i2s-out.txt b/Documentation/devicetree/bindings/sound/img,i2s-out.txt
new file mode 100644
index 000000000000..0159415b3338
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,i2s-out.txt
@@ -0,0 +1,51 @@
+Imagination Technologies I2S Output Controller
+
+Required Properties:
+
+  - compatible : Compatible list, must contain "img,i2s-out"
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - reg : Offset and length of the register set for the device
+
+  - clocks : Contains an entry for each entry in clock-names
+
+  - clock-names : Must include the following entries:
+	"sys"	The system clock
+	"ref"	The reference clock
+
+  - dmas: Contains an entry for each entry in dma-names.
+
+  - dma-names: Must include the following entry:
+	"tx"	Single DMA channel used by all active I2S channels
+
+  - img,i2s-channels : Number of I2S channels instantiated in the I2S out block
+
+  - resets: Contains a phandle to the I2S out reset signal
+
+  - reset-names: Contains the reset signal name "rst"
+
+Optional Properties:
+
+  - interrupts : Contains the I2S out interrupts. Depending on
+	the configuration, there may be no interrupts, one interrupt,
+	or an interrupt per I2S channel. For the case where there is
+	one interrupt per channel, the interrupts should be listed
+	in ascending channel order
+
+Example:
+
+i2s_out: i2s-out@18100A00 {
+	compatible = "img,i2s-out";
+	reg = <0x18100A00 0x200>;
+	interrupts = <GIC_SHARED 13 IRQ_TYPE_LEVEL_HIGH>;
+	dmas = <&mdc 23 0xffffffff 0>;
+	dma-names = "tx";
+	clocks = <&cr_periph SYS_CLK_I2S_OUT>,
+		 <&clk_core CLK_I2S>;
+	clock-names = "sys", "ref";
+	img,i2s-channels = <6>;
+	resets = <&pistachio_reset PISTACHIO_RESET_I2S_OUT>;
+	reset-names = "rst";
+	#sound-dai-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/img,parallel-out.txt b/Documentation/devicetree/bindings/sound/img,parallel-out.txt
new file mode 100644
index 000000000000..a3015d2a06e0
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,parallel-out.txt
@@ -0,0 +1,44 @@
+Imagination Technologies Parallel Output Controller
+
+Required Properties:
+
+  - compatible : Compatible list, must contain "img,parallel-out".
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - reg : Offset and length of the register set for the device.
+
+  - dmas: Contains an entry for each entry in dma-names.
+
+  - dma-names: Must include the following entry:
+	"tx"
+
+  - clocks : Contains an entry for each entry in clock-names.
+
+  - clock-names : Includes the following entries:
+	"sys"	The system clock
+	"ref"	The reference clock
+
+  - resets: Contains a phandle to the parallel out reset signal
+
+  - reset-names: Contains the reset signal name "rst"
+
+Optional Properties:
+
+  - interrupts : Contains the parallel out interrupt, if present
+
+Example:
+
+parallel_out: parallel-out@18100C00 {
+	compatible = "img,parallel-out";
+	reg = <0x18100C00 0x100>;
+	interrupts = <GIC_SHARED 19 IRQ_TYPE_LEVEL_HIGH>;
+	dmas = <&mdc 16 0xffffffff 0>;
+	dma-names = "tx";
+	clocks = <&cr_periph SYS_CLK_PAUD_OUT>,
+		 <&clk_core CLK_AUDIO_DAC>;
+	clock-names = "sys", "ref";
+	resets = <&pistachio_reset PISTACHIO_RESET_PRL_OUT>;
+	reset-names = "rst";
+	#sound-dai-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/img,pistachio-internal-dac.txt b/Documentation/devicetree/bindings/sound/img,pistachio-internal-dac.txt
new file mode 100644
index 000000000000..4cc18fc0477e
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,pistachio-internal-dac.txt
@@ -0,0 +1,18 @@
+Pistachio internal DAC DT bindings
+
+Required properties:
+
+  - compatible: "img,pistachio-internal-dac"
+
+  - img,cr-top : Must contain a phandle to the top level control syscon
+		 node which contains the internal dac control registers
+
+  - VDD-supply : Digital power supply regulator (+1.8V or +3.3V)
+
+Examples:
+
+internal_dac: internal-dac {
+	compatible = "img,pistachio-internal-dac";
+	img,cr-top = <&cr_top>;
+	VDD-supply = <&supply3v3>;
+};
diff --git a/Documentation/devicetree/bindings/sound/img,spdif-in.txt b/Documentation/devicetree/bindings/sound/img,spdif-in.txt
new file mode 100644
index 000000000000..aab9a81f7e13
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,spdif-in.txt
@@ -0,0 +1,41 @@
+Imagination Technologies SPDIF Input Controller
+
+Required Properties:
+
+  - compatible : Compatible list, must contain "img,spdif-in"
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - reg : Offset and length of the register set for the device
+
+  - dmas: Contains an entry for each entry in dma-names.
+
+  - dma-names: Must include the following entry:
+	"rx"
+
+  - clocks : Contains an entry for each entry in clock-names
+
+  - clock-names : Includes the following entries:
+	"sys"	The system clock
+
+Optional Properties:
+
+  - resets: Should contain a phandle to the spdif in reset signal, if any
+
+  - reset-names: Should contain the reset signal name "rst", if a
+	reset phandle is given
+
+  - interrupts : Contains the spdif in interrupt, if present
+
+Example:
+
+spdif_in: spdif-in@18100E00 {
+	compatible = "img,spdif-in";
+	reg = <0x18100E00 0x100>;
+	interrupts = <GIC_SHARED 20 IRQ_TYPE_LEVEL_HIGH>;
+	dmas = <&mdc 15 0xffffffff 0>;
+	dma-names = "rx";
+	clocks = <&cr_periph SYS_CLK_SPDIF_IN>;
+	clock-names = "sys";
+	#sound-dai-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/img,spdif-out.txt b/Documentation/devicetree/bindings/sound/img,spdif-out.txt
new file mode 100644
index 000000000000..470a5191e101
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/img,spdif-out.txt
@@ -0,0 +1,44 @@
+Imagination Technologies SPDIF Output Controller
+
+Required Properties:
+
+  - compatible : Compatible list, must contain "img,spdif-out"
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - reg : Offset and length of the register set for the device
+
+  - dmas: Contains an entry for each entry in dma-names.
+
+  - dma-names: Must include the following entry:
+	"tx"
+
+  - clocks : Contains an entry for each entry in clock-names.
+
+  - clock-names : Includes the following entries:
+	"sys"	The system clock
+	"ref"	The reference clock
+
+  - resets: Contains a phandle to the spdif out reset signal
+
+  - reset-names: Contains the reset signal name "rst"
+
+Optional Properties:
+
+  - interrupts : Contains the parallel out interrupt, if present
+
+Example:
+
+spdif_out: spdif-out@18100D00 {
+	compatible = "img,spdif-out";
+	reg = <0x18100D00 0x100>;
+	interrupts = <GIC_SHARED 21 IRQ_TYPE_LEVEL_HIGH>;
+	dmas = <&mdc 14 0xffffffff 0>;
+	dma-names = "tx";
+	clocks = <&cr_periph SYS_CLK_SPDIF_OUT>,
+		 <&clk_core CLK_SPDIF>;
+	clock-names = "sys", "ref";
+	resets = <&pistachio_reset PISTACHIO_RESET_SPDIF_OUT>;
+	reset-names = "rst";
+	#sound-dai-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/inno-rk3036.txt b/Documentation/devicetree/bindings/sound/inno-rk3036.txt
new file mode 100644
index 000000000000..758de8e27561
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/inno-rk3036.txt
@@ -0,0 +1,20 @@
+Inno audio codec for RK3036
+
+Inno audio codec is integrated inside RK3036 SoC.
+
+Required properties:
+- compatible : Should be "rockchip,rk3036-codec".
+- reg : The registers of codec.
+- clock-names : Should be "acodec_pclk".
+- clocks : The clock of codec.
+- rockchip,grf : The phandle of grf device node.
+
+Example:
+
+	acodec: acodec-ana@20030000 {
+		compatible = "rk3036-codec";
+		reg = <0x20030000 0x4000>;
+		rockchip,grf = <&grf>;
+		clock-names = "acodec_pclk";
+		clocks = <&cru ACLK_VCODEC>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/pcm1792a.txt b/Documentation/devicetree/bindings/sound/pcm179x.txt
index 970ba1ed576f..4ae70d3462d6 100644
--- a/Documentation/devicetree/bindings/sound/pcm1792a.txt
+++ b/Documentation/devicetree/bindings/sound/pcm179x.txt
@@ -1,4 +1,4 @@
-Texas Instruments pcm1792a DT bindings
+Texas Instruments pcm179x DT bindings
 
 This driver supports the SPI bus.
 
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index c57cbd65736c..8ee0fa91e4a0 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -7,8 +7,11 @@ Required properties:
 				  "renesas,rcar_sound-gen3" if generation3
 				  Examples with soctypes are:
 				    - "renesas,rcar_sound-r8a7778" (R-Car M1A)
+				    - "renesas,rcar_sound-r8a7779" (R-Car H1)
 				    - "renesas,rcar_sound-r8a7790" (R-Car H2)
 				    - "renesas,rcar_sound-r8a7791" (R-Car M2-W)
+				    - "renesas,rcar_sound-r8a7793" (R-Car M2-N)
+				    - "renesas,rcar_sound-r8a7794" (R-Car E2)
 				    - "renesas,rcar_sound-r8a7795" (R-Car H3)
 - reg				: Should contain the register physical address.
 				  required register is
@@ -34,6 +37,8 @@ Required properties:
 				  see below for detail.
 - #sound-dai-cells		: it must be 0 if your system is using single DAI
 				  it must be 1 if your system is using multi  DAI
+
+Optional properties:
 - #clock-cells			: it must be 0 if your system has audio_clkout
 				  it must be 1 if your system has audio_clkout0/1/2/3
 - clock-frequency		: for all audio_clkout0/1/2/3
@@ -244,3 +249,80 @@ rcar_sound: sound@ec500000 {
 		};
 	};
 };
+
+Example: simple sound card
+
+	rsnd_ak4643: sound {
+		compatible = "simple-audio-card";
+
+		simple-audio-card,format = "left_j";
+		simple-audio-card,bitclock-master = <&sndcodec>;
+		simple-audio-card,frame-master = <&sndcodec>;
+
+		sndcpu: simple-audio-card,cpu {
+			sound-dai = <&rcar_sound>;
+		};
+
+		sndcodec: simple-audio-card,codec {
+			sound-dai = <&ak4643>;
+			clocks = <&audio_clock>;
+		};
+	};
+
+&rcar_sound {
+	pinctrl-0 = <&sound_pins &sound_clk_pins>;
+	pinctrl-names = "default";
+
+	/* Single DAI */
+	#sound-dai-cells = <0>;
+
+	status = "okay";
+
+	rcar_sound,dai {
+		dai0 {
+			playback = <&ssi0 &src2 &dvc0>;
+			capture  = <&ssi1 &src3 &dvc1>;
+		};
+	};
+};
+
+&ssi1 {
+	shared-pin;
+};
+
+Example: simple sound card for TDM
+
+	rsnd_tdm: sound {
+		compatible = "simple-audio-card";
+
+		simple-audio-card,format = "left_j";
+		simple-audio-card,bitclock-master = <&sndcodec>;
+		simple-audio-card,frame-master = <&sndcodec>;
+
+		sndcpu: simple-audio-card,cpu {
+			sound-dai = <&rcar_sound>;
+			dai-tdm-slot-num = <6>;
+		};
+
+		sndcodec: simple-audio-card,codec {
+			sound-dai = <&xxx>;
+		};
+	};
+
+Example: simple sound card for Multi channel
+
+&rcar_sound {
+	pinctrl-0 = <&sound_pins &sound_clk_pins>;
+	pinctrl-names = "default";
+
+	/* Single DAI */
+	#sound-dai-cells = <0>;
+
+	status = "okay";
+
+	rcar_sound,dai {
+		dai0 {
+			playback = <&ssi0 &ssi1 &ssi2 &src0 &dvc0>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt b/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
index 962748a8d919..2b2caa281ce3 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
@@ -4,8 +4,8 @@ Renesas Sampling Rate Convert Sound Card specifies audio DAI connections of SoC
 
 Required properties:
 
-- compatible				: "renesas,rsrc-card,<board>"
-					  Examples with soctypes are:
+- compatible				: "renesas,rsrc-card{,<board>}"
+					  Examples with boards are:
 					    - "renesas,rsrc-card"
 					    - "renesas,rsrc-card,lager"
 					    - "renesas,rsrc-card,koelsch"
diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
index 2267d249ca0e..b7f3a9325ebd 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
@@ -19,6 +19,7 @@ Required properties:
 - clock-names: should contain followings:
    - "i2s_hclk": clock for I2S BUS
    - "i2s_clk" : clock for I2S controller
+- rockchip,playback-channels: max playback channels, if not set, 8 channels default.
 - rockchip,capture-channels: max capture channels, if not set, 2 channels default.
 
 Example for rk3288 I2S controller:
@@ -31,5 +32,6 @@ i2s@ff890000 {
 	dma-names = "tx", "rx";
 	clock-names = "i2s_hclk", "i2s_clk";
 	clocks = <&cru HCLK_I2S0>, <&cru SCLK_I2S0>;
+	rockchip,playback-channels = <8>;
 	rockchip,capture-channels = <2>;
 };
diff --git a/Documentation/devicetree/bindings/sound/rt5616.txt b/Documentation/devicetree/bindings/sound/rt5616.txt
new file mode 100644
index 000000000000..efc48c65198d
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5616.txt
@@ -0,0 +1,26 @@
+RT5616 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5616".
+
+- reg : The I2C address of the device.
+
+Pins on the device (for linking into audio routes) for RT5616:
+
+  * IN1P
+  * IN2P
+  * IN2N
+  * LOUTL
+  * LOUTR
+  * HPOL
+  * HPOR
+
+Example:
+
+codec: rt5616@1b {
+	compatible = "realtek,rt5616";
+	reg = <0x1b>;
+};
diff --git a/Documentation/devicetree/bindings/sound/rt5651.txt b/Documentation/devicetree/bindings/sound/rt5651.txt
new file mode 100644
index 000000000000..3875233095f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5651.txt
@@ -0,0 +1,41 @@
+RT5651 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5651".
+
+- reg : The I2C address of the device.
+
+Optional properties:
+
+- realtek,in2-differential
+  Boolean. Indicate MIC2 input are differential, rather than single-ended.
+
+- realtek,dmic-en
+  Boolean. true if dmic is used.
+
+Pins on the device (for linking into audio routes) for RT5651:
+
+  * DMIC L1
+  * DMIC R1
+  * IN1P
+  * IN2P
+  * IN2N
+  * IN3P
+  * HPOL
+  * HPOR
+  * LOUTL
+  * LOUTR
+  * PDML
+  * PDMR
+
+Example:
+
+codec: rt5651@1a {
+	compatible = "realtek,rt5651";
+	reg = <0x1a>;
+	realtek,dmic-en = "true";
+	realtek,in2-diff = "false";
+};
diff --git a/Documentation/devicetree/bindings/sound/rt5659.txt b/Documentation/devicetree/bindings/sound/rt5659.txt
new file mode 100644
index 000000000000..5f79e7fde032
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5659.txt
@@ -0,0 +1,75 @@
+RT5659/RT5658 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : One of "realtek,rt5659" or "realtek,rt5658".
+
+- reg : The I2C address of the device.
+
+- interrupts : The CODEC's interrupt output.
+
+Optional properties:
+
+- realtek,in1-differential
+- realtek,in3-differential
+- realtek,in4-differential
+  Boolean. Indicate MIC1/3/4 input are differential, rather than single-ended.
+
+- realtek,dmic1-data-pin
+  0: dmic1 is not used
+  1: using IN2N pin as dmic1 data pin
+  2: using GPIO5 pin as dmic1 data pin
+  3: using GPIO9 pin as dmic1 data pin
+  4: using GPIO11 pin as dmic1 data pin
+
+- realtek,dmic2-data-pin
+  0: dmic2 is not used
+  1: using IN2P pin as dmic2 data pin
+  2: using GPIO6 pin as dmic2 data pin
+  3: using GPIO10 pin as dmic2 data pin
+  4: using GPIO12 pin as dmic2 data pin
+
+- realtek,jd-src
+  0: No JD is used
+  1: using JD3 as JD source
+
+- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
+- realtek,reset-gpios : The GPIO that controls the CODEC's RESET pin.
+
+Pins on the device (for linking into audio routes) for RT5659/RT5658:
+
+  * DMIC L1
+  * DMIC R1
+  * DMIC L2
+  * DMIC R2
+  * IN1P
+  * IN1N
+  * IN2P
+  * IN2N
+  * IN3P
+  * IN3N
+  * IN4P
+  * IN4N
+  * HPOL
+  * HPOR
+  * SPOL
+  * SPOR
+  * LOUTL
+  * LOUTR
+  * MONOOUT
+  * PDML
+  * PDMR
+  * SPDIF
+
+Example:
+
+rt5659 {
+	compatible = "realtek,rt5659";
+	reg = <0x1b>;
+	interrupt-parent = <&gpio>;
+	interrupts = <TEGRA_GPIO(W, 3) GPIO_ACTIVE_HIGH>;
+	realtek,ldo1-en-gpios =
+		<&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_HIGH>;
+};
diff --git a/Documentation/devicetree/bindings/sound/rt5677.txt b/Documentation/devicetree/bindings/sound/rt5677.txt
index f07078997f87..1b3c13d206ff 100644
--- a/Documentation/devicetree/bindings/sound/rt5677.txt
+++ b/Documentation/devicetree/bindings/sound/rt5677.txt
@@ -18,7 +18,7 @@ Required properties:
 Optional properties:
 
 - realtek,pow-ldo2-gpio : The GPIO that controls the CODEC's POW_LDO2 pin.
-- realtek,reset-gpio : The GPIO that controls the CODEC's RESET pin.
+- realtek,reset-gpio : The GPIO that controls the CODEC's RESET pin. Active low.
 
 - realtek,in1-differential
 - realtek,in2-differential
diff --git a/Documentation/devicetree/bindings/sound/sun4i-codec.txt b/Documentation/devicetree/bindings/sound/sun4i-codec.txt
index c92966bd5488..0dce690f78f5 100644
--- a/Documentation/devicetree/bindings/sound/sun4i-codec.txt
+++ b/Documentation/devicetree/bindings/sound/sun4i-codec.txt
@@ -14,6 +14,9 @@ Required properties:
    - "apb": the parent APB clock for this controller
    - "codec": the parent module clock
 
+Optional properties:
+- allwinner,pa-gpios: gpio to enable external amplifier
+
 Example:
 codec: codec@01c22c00 {
 	#sound-dai-cells = <0>;
diff --git a/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt b/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt
new file mode 100644
index 000000000000..5d9cb84c661d
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt
@@ -0,0 +1,48 @@
+Texas Instruments pcm3168a DT bindings
+
+This driver supports both SPI and I2C bus access for this codec
+
+Required properties:
+
+  - compatible: "ti,pcm3168a"
+
+  - clocks : Contains an entry for each entry in clock-names
+
+  - clock-names : Includes the following entries:
+	"scki"	The system clock
+
+  - VDD1-supply : Digital power supply regulator 1 (+3.3V)
+
+  - VDD2-supply : Digital power supply regulator 2 (+3.3V)
+
+  - VCCAD1-supply : ADC power supply regulator 1 (+5V)
+
+  - VCCAD2-supply : ADC power supply regulator 2 (+5V)
+
+  - VCCDA1-supply : DAC power supply regulator 1 (+5V)
+
+  - VCCDA2-supply : DAC power supply regulator 2 (+5V)
+
+For required properties on SPI/I2C, consult SPI/I2C device tree documentation
+
+Examples:
+
+i2c0: i2c0@0 {
+
+	...
+
+	pcm3168a: audio-codec@44 {
+		compatible = "ti,pcm3168a";
+		reg = <0x44>;
+		clocks = <&clk_core CLK_AUDIO>;
+		clock-names = "scki";
+		VDD1-supply = <&supply3v3>;
+		VDD2-supply = <&supply3v3>;
+		VCCAD1-supply = <&supply5v0>;
+		VCCAD2-supply = <&supply5v0>;
+		VCCDA1-supply = <&supply5v0>;
+		VCCDA2-supply = <&supply5v0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&dac_clk_pin>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/wlf,wm8974.txt b/Documentation/devicetree/bindings/sound/wlf,wm8974.txt
new file mode 100644
index 000000000000..01d3a7c83419
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/wlf,wm8974.txt
@@ -0,0 +1,15 @@
+WM8974 audio CODEC
+
+This device supports both I2C and SPI (configured with pin strapping
+on the board).
+
+Required properties:
+  - compatible: "wlf,wm8974"
+  - reg: the I2C address or SPI chip select number of the device
+
+Examples:
+
+codec: wm8974@1a {
+	compatible = "wlf,wm8974";
+	reg = <0x1a>;
+};
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index e045e90a0924..68c4e8d96bed 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -30,7 +30,7 @@ Optional properties:
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
-    Documentation/devicetree/bindings/interrupts.txt
+    Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
   - clocks : A list of up to two phandle and clock specifier pairs
   - clock-names : A list of clock names sorted in the same order as clocks.
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index 705075da2f10..aa005c1d10d9 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -10,6 +10,7 @@ Required properties:
 			 "renesas,msiof-r8a7792" (R-Car V2H)
 			 "renesas,msiof-r8a7793" (R-Car M2-N)
 			 "renesas,msiof-r8a7794" (R-Car E2)
+			 "renesas,msiof-sh73a0" (SH-Mobile AG5)
 - reg                  : A list of offsets and lengths of the register sets for
 			 the device.
 			 If only one register set is present, it is to be used
diff --git a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
index ce363c923f44..e43f4cf4cf35 100644
--- a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -2,9 +2,10 @@ Binding for MTK SPI controller
 
 Required properties:
 - compatible: should be one of the following.
-    - mediatek,mt8173-spi: for mt8173 platforms
-    - mediatek,mt8135-spi: for mt8135 platforms
+    - mediatek,mt2701-spi: for mt2701 platforms
     - mediatek,mt6589-spi: for mt6589 platforms
+    - mediatek,mt8135-spi: for mt8135 platforms
+    - mediatek,mt8173-spi: for mt8173 platforms
 
 - #address-cells: should be 1.
 
@@ -29,10 +30,10 @@ Required properties:
   muxes clock, and "spi-clk" for the clock gate.
 
 Optional properties:
--cs-gpios: see spi-bus.txt, only required for MT8173.
+-cs-gpios: see spi-bus.txt.
 
 - mediatek,pad-select: specify which pins group(ck/mi/mo/cs) spi
-  controller used. This is a array, the element value should be 0~3,
+  controller used. This is an array, the element value should be 0~3,
   only required for MT8173.
     0: specify GPIO69,70,71,72 for spi pins.
     1: specify GPIO102,103,104,105 for spi pins.
diff --git a/Documentation/devicetree/bindings/spi/ti_qspi.txt b/Documentation/devicetree/bindings/spi/ti_qspi.txt
index 601a360531a5..cc8304aa64ac 100644
--- a/Documentation/devicetree/bindings/spi/ti_qspi.txt
+++ b/Documentation/devicetree/bindings/spi/ti_qspi.txt
@@ -15,14 +15,32 @@ Recommended properties:
 - spi-max-frequency: Definition as per
                      Documentation/devicetree/bindings/spi/spi-bus.txt
 
+Optional properties:
+- syscon-chipselects: Handle to system control region contains QSPI
+		      chipselect register and offset of that register.
+
 Example:
 
+For am4372:
 qspi: qspi@4b300000 {
-	compatible = "ti,dra7xxx-qspi";
-	reg = <0x47900000 0x100>, <0x30000000 0x3ffffff>;
+	compatible = "ti,am4372-qspi";
+	reg = <0x47900000 0x100>, <0x30000000 0x4000000>;
 	reg-names = "qspi_base", "qspi_mmap";
 	#address-cells = <1>;
 	#size-cells = <0>;
 	spi-max-frequency = <25000000>;
 	ti,hwmods = "qspi";
 };
+
+For dra7xx:
+qspi: qspi@4b300000 {
+	compatible = "ti,dra7xxx-qspi";
+	reg = <0x4b300000 0x100>,
+	      <0x5c000000 0x4000000>,
+	reg-names = "qspi_base", "qspi_mmap";
+	syscon-chipselects = <&scm_conf 0x558>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	spi-max-frequency = <48000000>;
+	ti,hwmods = "qspi";
+};
diff --git a/Documentation/devicetree/bindings/arm/rockchip/pmu-sram.txt b/Documentation/devicetree/bindings/sram/rockchip-pmu-sram.txt
index 6b42fda306ff..6b42fda306ff 100644
--- a/Documentation/devicetree/bindings/arm/rockchip/pmu-sram.txt
+++ b/Documentation/devicetree/bindings/sram/rockchip-pmu-sram.txt
diff --git a/Documentation/devicetree/bindings/arm/rockchip/smp-sram.txt b/Documentation/devicetree/bindings/sram/rockchip-smp-sram.txt
index d9416fb8db6f..800701ecffca 100644
--- a/Documentation/devicetree/bindings/arm/rockchip/smp-sram.txt
+++ b/Documentation/devicetree/bindings/sram/rockchip-smp-sram.txt
@@ -12,7 +12,7 @@ Required sub-node properties:
 - compatible : should be "rockchip,rk3066-smp-sram"
 
 The rest of the properties should follow the generic mmio-sram discription
-found in ../../misc/sram.txt
+found in Documentation/devicetree/bindings/sram/sram.txt
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/arm/exynos/smp-sysram.txt b/Documentation/devicetree/bindings/sram/samsung-sram.txt
index 4a0a4f70a0ce..6bc474b2b885 100644
--- a/Documentation/devicetree/bindings/arm/exynos/smp-sysram.txt
+++ b/Documentation/devicetree/bindings/sram/samsung-sram.txt
@@ -15,7 +15,7 @@ Required sub-node properties:
 		"samsung,exynos4210-sysram-ns" : for Non-secure SYSRAM
 
 The rest of the properties should follow the generic mmio-sram discription
-found in ../../misc/sysram.txt
+found in Documentation/devicetree/bindings/sram/sram.txt
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/misc/sram.txt b/Documentation/devicetree/bindings/sram/sram.txt
index 42ee9438b771..42ee9438b771 100644
--- a/Documentation/devicetree/bindings/misc/sram.txt
+++ b/Documentation/devicetree/bindings/sram/sram.txt
diff --git a/Documentation/devicetree/bindings/soc/sunxi/sram.txt b/Documentation/devicetree/bindings/sram/sunxi-sram.txt
index 067698112f5f..8d5665468fe7 100644
--- a/Documentation/devicetree/bindings/soc/sunxi/sram.txt
+++ b/Documentation/devicetree/bindings/sram/sunxi-sram.txt
@@ -16,7 +16,7 @@ SRAM nodes
 ----------
 
 Each SRAM is described using the mmio-sram bindings documented in
-Documentation/devicetree/bindings/misc/sram.txt
+Documentation/devicetree/bindings/sram/sram.txt
 
 Each SRAM will have SRAM sections that are going to be handled by the
 SRAM controller as subnodes. These sections are represented following
diff --git a/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt b/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt
new file mode 100644
index 000000000000..c59e27c632c1
--- /dev/null
+++ b/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt
@@ -0,0 +1,31 @@
+Hi6220 SoC ION
+===================================================================
+Required properties:
+- compatible : "hisilicon,hi6220-ion"
+- list of the ION heaps
+	- heap name : maybe heap_sys_user@0
+	- heap id   : id should be unique in the system.
+	- heap base : base ddr address of the heap,0 means that
+	it is dynamic.
+	- heap size : memory size and 0 means it is dynamic.
+	- heap type : the heap type of the heap, please also
+	see the define in ion.h(drivers/staging/android/uapi/ion.h)
+-------------------------------------------------------------------
+Example:
+	hi6220-ion {
+		compatible = "hisilicon,hi6220-ion";
+		heap_sys_user@0 {
+			heap-name = "sys_user";
+			heap-id   = <0x0>;
+			heap-base = <0x0>;
+			heap-size = <0x0>;
+			heap-type = "ion_system";
+		};
+		heap_sys_contig@0 {
+			heap-name = "sys_contig";
+			heap-id   = <0x1>;
+			heap-base = <0x0>;
+			heap-size = <0x0>;
+			heap-type = "ion_system_contig";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt
new file mode 100644
index 000000000000..66223d561972
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt
@@ -0,0 +1,63 @@
+* Thermal Monitoring Unit (TMU) on Freescale QorIQ SoCs
+
+Required properties:
+- compatible : Must include "fsl,qoriq-tmu". The version of the device is
+	determined by the TMU IP Block Revision Register (IPBRR0) at
+	offset 0x0BF8.
+	Table of correspondences between IPBRR0 values and example  chips:
+		Value           Device
+		----------      -----
+		0x01900102      T1040
+- reg : Address range of TMU registers.
+- interrupts : Contains the interrupt for TMU.
+- fsl,tmu-range : The values to be programmed into TTRnCR, as specified by
+	the SoC reference manual. The first cell is TTR0CR, the second is
+	TTR1CR, etc.
+- fsl,tmu-calibration : A list of cell pairs containing temperature
+	calibration data, as specified by the SoC reference manual.
+	The first cell of each pair is the value to be written to TTCFGR,
+	and the second is the value to be written to TSCFGR.
+
+Example:
+
+tmu@f0000 {
+	compatible = "fsl,qoriq-tmu";
+	reg = <0xf0000 0x1000>;
+	interrupts = <18 2 0 0>;
+	fsl,tmu-range = <0x000a0000 0x00090026 0x0008004a 0x0001006a>;
+	fsl,tmu-calibration = <0x00000000 0x00000025
+			       0x00000001 0x00000028
+			       0x00000002 0x0000002d
+			       0x00000003 0x00000031
+			       0x00000004 0x00000036
+			       0x00000005 0x0000003a
+			       0x00000006 0x00000040
+			       0x00000007 0x00000044
+			       0x00000008 0x0000004a
+			       0x00000009 0x0000004f
+			       0x0000000a 0x00000054
+
+			       0x00010000 0x0000000d
+			       0x00010001 0x00000013
+			       0x00010002 0x00000019
+			       0x00010003 0x0000001f
+			       0x00010004 0x00000025
+			       0x00010005 0x0000002d
+			       0x00010006 0x00000033
+			       0x00010007 0x00000043
+			       0x00010008 0x0000004b
+			       0x00010009 0x00000053
+
+			       0x00020000 0x00000010
+			       0x00020001 0x00000017
+			       0x00020002 0x0000001f
+			       0x00020003 0x00000029
+			       0x00020004 0x00000031
+			       0x00020005 0x0000003c
+			       0x00020006 0x00000042
+			       0x00020007 0x0000004d
+			       0x00020008 0x00000056
+
+			       0x00030000 0x00000012
+			       0x00030001 0x0000001d>;
+};
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
index 332e625f6ed0..e5ee3f159893 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
@@ -1,8 +1,9 @@
 * Renesas R-Car Thermal
 
 Required properties:
-- compatible		: "renesas,thermal-<soctype>", "renesas,rcar-thermal"
-			  as fallback.
+- compatible		: "renesas,thermal-<soctype>",
+			   "renesas,rcar-gen2-thermal" (with thermal-zone) or
+			   "renesas,rcar-thermal" (without thermal-zone) as fallback.
 			  Examples with soctypes are:
 			    - "renesas,thermal-r8a73a4" (R-Mobile APE6)
 			    - "renesas,thermal-r8a7779" (R-Car H1)
@@ -36,3 +37,35 @@ thermal@e61f0000 {
 		0xe61f0300 0x38>;
 	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+Example (with thermal-zone):
+
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		polling-delay-passive	= <1000>;
+		polling-delay		= <5000>;
+
+		thermal-sensors = <&thermal>;
+
+		trips {
+			cpu-crit {
+				temperature	= <115000>;
+				hysteresis	= <0>;
+				type		= "critical";
+			};
+		};
+		cooling-maps {
+		};
+	};
+};
+
+thermal: thermal@e61f0000 {
+	compatible =	"renesas,thermal-r8a7790",
+			"renesas,rcar-gen2-thermal",
+			"renesas,rcar-thermal";
+	reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+	power-domains = <&cpg_clocks>;
+	#thermal-sensor-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
index 0dfa60d88dd3..08efe6bc2193 100644
--- a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
@@ -2,8 +2,10 @@
 
 Required properties:
 - compatible : should be "rockchip,<name>-tsadc"
+   "rockchip,rk3228-tsadc": found on RK3228 SoCs
    "rockchip,rk3288-tsadc": found on RK3288 SoCs
    "rockchip,rk3368-tsadc": found on RK3368 SoCs
+   "rockchip,rk3399-tsadc": found on RK3399 SoCs
 - reg : physical base address of the controller and length of memory mapped
 	region.
 - interrupts : The interrupt number to the cpu. The interrupt specifier format
diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
index 64083bc5633c..8ff54eb464dc 100644
--- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
@@ -3,6 +3,7 @@ Mediatek MT6577, MT6572 and MT6589 Timers
 
 Required properties:
 - compatible should contain:
+	* "mediatek,mt2701-timer" for MT2701 compatible timers
 	* "mediatek,mt6580-timer" for MT6580 compatible timers
 	* "mediatek,mt6589-timer" for MT6589 compatible timers
 	* "mediatek,mt8127-timer" for MT8127 compatible timers
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
index fd132cbee70e..221368207ca4 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -4,6 +4,7 @@ Platform DesignWare HS OTG USB 2.0 controller
 Required properties:
 - compatible : One of:
   - brcm,bcm2835-usb: The DWC2 USB controller instance in the BCM2835 SoC.
+  - hisilicon,hi6220-usb: The DWC2 USB controller instance in the hi6220 SoC.
   - rockchip,rk3066-usb: The DWC2 USB controller instance in the rk3066 Soc;
   - "rockchip,rk3188-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3188 Soc;
   - "rockchip,rk3288-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3288 Soc;
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.txt b/Documentation/devicetree/bindings/usb/dwc3-xilinx.txt
new file mode 100644
index 000000000000..30361b32a460
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.txt
@@ -0,0 +1,33 @@
+Xilinx SuperSpeed DWC3 USB SoC controller
+
+Required properties:
+- compatible:	Should contain "xlnx,zynqmp-dwc3"
+- clocks:	A list of phandles for the clocks listed in clock-names
+- clock-names:	Should contain the following:
+  "bus_clk"	 Master/Core clock, have to be >= 125 MHz for SS
+		 operation and >= 60MHz for HS operation
+
+  "ref_clk"	 Clock source to core during PHY power down
+
+Required child node:
+A child node must exist to represent the core DWC3 IP block. The name of
+the node is not important. The content of the node is defined in dwc3.txt.
+
+Example device node:
+
+		usb@0 {
+			#address-cells = <0x2>;
+			#size-cells = <0x1>;
+			status = "okay";
+			compatible = "xlnx,zynqmp-dwc3";
+			clock-names = "bus_clk" "ref_clk";
+			clocks = <&clk125>, <&clk125>;
+			ranges;
+
+			dwc3@fe200000 {
+				compatible = "snps,dwc3";
+				reg = <0x0 0xfe200000 0x40000>;
+				interrupts = <0x0 0x41 0x4>;
+				dr_mode = "host";
+			};
+		};
diff --git a/Documentation/devicetree/bindings/usb/mt8173-xhci.txt b/Documentation/devicetree/bindings/usb/mt8173-xhci.txt
new file mode 100644
index 000000000000..b3a7ffa48852
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/mt8173-xhci.txt
@@ -0,0 +1,51 @@
+MT8173 xHCI
+
+The device node for Mediatek SOC USB3.0 host controller
+
+Required properties:
+ - compatible : should contain "mediatek,mt8173-xhci"
+ - reg : specifies physical base address and size of the registers,
+	the first one for MAC, the second for IPPC
+ - interrupts : interrupt used by the controller
+ - power-domains : a phandle to USB power domain node to control USB's
+	mtcmos
+ - vusb33-supply : regulator of USB avdd3.3v
+
+ - clocks : a list of phandle + clock-specifier pairs, one for each
+	entry in clock-names
+ - clock-names : must contain
+	"sys_ck": for clock of xHCI MAC
+	"wakeup_deb_p0": for USB wakeup debounce clock of port0
+	"wakeup_deb_p1": for USB wakeup debounce clock of port1
+
+ - phys : a list of phandle + phy specifier pairs
+
+Optional properties:
+ - mediatek,wakeup-src : 1: ip sleep wakeup mode; 2: line state wakeup
+	mode;
+ - mediatek,syscon-wakeup : phandle to syscon used to access USB wakeup
+	control register, it depends on "mediatek,wakeup-src".
+ - vbus-supply : reference to the VBUS regulator;
+ - usb3-lpm-capable : supports USB3.0 LPM
+
+Example:
+usb30: usb@11270000 {
+	compatible = "mediatek,mt8173-xhci";
+	reg = <0 0x11270000 0 0x1000>,
+	      <0 0x11280700 0 0x0100>;
+	interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_LOW>;
+	power-domains = <&scpsys MT8173_POWER_DOMAIN_USB>;
+	clocks = <&topckgen CLK_TOP_USB30_SEL>,
+		 <&pericfg CLK_PERI_USB0>,
+		 <&pericfg CLK_PERI_USB1>;
+	clock-names = "sys_ck",
+		      "wakeup_deb_p0",
+		      "wakeup_deb_p1";
+	phys = <&phy_port0 PHY_TYPE_USB3>,
+	       <&phy_port1 PHY_TYPE_USB2>;
+	vusb33-supply = <&mt6397_vusb_reg>;
+	vbus-supply = <&usb_p1_vbus>;
+	usb3-lpm-capable;
+	mediatek,syscon-wakeup = <&pericfg>;
+	mediatek,wakeup-src = <1>;
+};
diff --git a/Documentation/devicetree/bindings/usb/octeon-usb.txt b/Documentation/devicetree/bindings/usb/octeon-usb.txt
new file mode 100644
index 000000000000..205c8d24d6e3
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/octeon-usb.txt
@@ -0,0 +1,62 @@
+OCTEON/OCTEON+ USB BLOCK
+
+1) Main node
+
+   Required properties:
+
+   - compatible: must be "cavium,octeon-5750-usbn"
+
+   - reg: specifies the physical base address of the USBN block and
+     the length of the memory mapped region.
+
+   - #address-cells: specifies the number of cells needed to encode an
+     address. The value must be 2.
+
+   - #size-cells: specifies the number of cells used to represent the size
+     of an address. The value must be 2.
+
+   - ranges: specifies the translation between child address space and parent
+     address space.
+
+   - clock-frequency: speed of the USB reference clock. Allowed values are
+     12000000, 24000000 or 48000000.
+
+   - cavium,refclk-type: type of the USB reference clock. Allowed values are
+     "crystal" or "external".
+
+   - refclk-frequency: deprecated, use "clock-frequency".
+
+   - refclk-type: deprecated, use "cavium,refclk-type".
+
+2) Child node
+
+   The main node must have one child node which describes the built-in
+   USB controller.
+
+   Required properties:
+
+   - compatible: must be "cavium,octeon-5750-usbc"
+
+   - reg: specifies the physical base address of the USBC block and
+     the length of the memory mapped region.
+
+   - interrupts: specifies the interrupt number for the USB controller.
+
+3) Example:
+
+	usbn: usbn@1180068000000 {
+		compatible = "cavium,octeon-5750-usbn";
+		reg = <0x11800 0x68000000 0x0 0x1000>;
+		ranges; /* Direct mapping */
+		#address-cells = <2>;
+		#size-cells = <2>;
+		clock-frequency = <12000000>;
+		cavium,refclk-type = "crystal";
+
+		usbc@16f0010000000 {
+			compatible = "cavium,octeon-5750-usbc";
+			reg = <0x16f00 0x10000000 0x0 0x80000>;
+			interrupts = <0 56>;
+		};
+	};
+
diff --git a/Documentation/devicetree/bindings/usb/renesas_usb3.txt b/Documentation/devicetree/bindings/usb/renesas_usb3.txt
new file mode 100644
index 000000000000..8d52766f07b9
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/renesas_usb3.txt
@@ -0,0 +1,23 @@
+Renesas Electronics USB3.0 Peripheral driver
+
+Required properties:
+  - compatible: Must contain one of the following:
+	- "renesas,r8a7795-usb3-peri"
+  - reg: Base address and length of the register for the USB3.0 Peripheral
+  - interrupts: Interrupt specifier for the USB3.0 Peripheral
+  - clocks: clock phandle and specifier pair
+
+Example:
+	usb3_peri0: usb@ee020000 {
+		compatible = "renesas,r8a7795-usb3-peri";
+		reg = <0 0xee020000 0 0x400>;
+		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cpg CPG_MOD 328>;
+	};
+
+	usb3_peri1: usb@ee060000 {
+		compatible = "renesas,r8a7795-usb3-peri";
+		reg = <0 0xee060000 0 0x400>;
+		interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cpg CPG_MOD 327>;
+	};
diff --git a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
index 7d48f63db44e..b6040563e51a 100644
--- a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
+++ b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
@@ -1,11 +1,21 @@
 Renesas Electronics USBHS driver
 
 Required properties:
-  - compatible: Must contain one of the following:
-	- "renesas,usbhs-r8a7790"
-	- "renesas,usbhs-r8a7791"
-	- "renesas,usbhs-r8a7794"
-	- "renesas,usbhs-r8a7795"
+  - compatible: Must contain one or more of the following:
+
+	- "renesas,usbhs-r8a7790" for r8a7790 (R-Car H2) compatible device
+	- "renesas,usbhs-r8a7791" for r8a7791 (R-Car M2-W) compatible device
+	- "renesas,usbhs-r8a7792" for r8a7792 (R-Car V2H) compatible device
+	- "renesas,usbhs-r8a7793" for r8a7793 (R-Car M2-N) compatible device
+	- "renesas,usbhs-r8a7794" for r8a7794 (R-Car E2) compatible device
+	- "renesas,usbhs-r8a7795" for r8a7795 (R-Car H3) compatible device
+	- "renesas,rcar-gen2-usbhs" for R-Car Gen2 compatible device
+	- "renesas,rcar-gen3-usbhs" for R-Car Gen3 compatible device
+
+	When compatible with the generic version, nodes must list the
+	SoC-specific version corresponding to the platform first followed
+	by the generic version.
+
   - reg: Base address and length of the register for the USBHS
   - interrupts: Interrupt specifier for the USBHS
   - clocks: A list of phandle + clock specifier pairs
@@ -22,7 +32,7 @@ Optional properties:
 
 Example:
 	usbhs: usb@e6590000 {
-		compatible = "renesas,usbhs-r8a7790";
+		compatible = "renesas,usbhs-r8a7790", "renesas,rcar-gen2-usbhs";
 		reg = <0 0xe6590000 0 0x100>;
 		interrupts = <0 107 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp7_clks R8A7790_CLK_HSUSB>;
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index 86f67f0886bc..082573289f1e 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -3,8 +3,8 @@ USB xHCI controllers
 Required properties:
   - compatible: should be one of "generic-xhci",
     "marvell,armada-375-xhci", "marvell,armada-380-xhci",
-    "renesas,xhci-r8a7790", "renesas,xhci-r8a7791" (deprecated:
-    "xhci-platform").
+    "renesas,xhci-r8a7790", "renesas,xhci-r8a7791", "renesas,xhci-r8a7793",
+    "renesas,xhci-r8a7795" (deprecated: "xhci-platform").
   - reg: should contain address and length of the standard XHCI
     register set for the device.
   - interrupts: one XHCI interrupt should be described here.
diff --git a/Documentation/devicetree/bindings/usb/usb3503.txt b/Documentation/devicetree/bindings/usb/usb3503.txt
index 52493b1480e2..c1a0a9191d26 100644
--- a/Documentation/devicetree/bindings/usb/usb3503.txt
+++ b/Documentation/devicetree/bindings/usb/usb3503.txt
@@ -18,7 +18,8 @@ Optional properties:
 - refclk: Clock used for driving REFCLK signal (optional, if not provided
 	the driver assumes that clock signal is always available, its
 	rate is specified by REF_SEL pins and a value from the primary
-	reference clock frequencies table is used)
+	reference clock frequencies table is used). Use clocks and
+	clock-names in order to assign it
 - refclk-frequency: Frequency of the REFCLK signal as defined by REF_SEL
 	pins (optional, if not provided, driver will not set rate of the
 	REFCLK signal and assume that a value from the primary reference
@@ -33,4 +34,6 @@ Examples:
 		intn-gpios = <&gpx3 4 1>;
 		reset-gpios = <&gpx3 5 1>;
 		initial-mode = <1>;
+		clocks = <&clks 80>;
+		clock-names = "refclk";
 	};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 55df1d444e9f..72e2c5a2b327 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -33,6 +33,7 @@ auo	AU Optronics Corporation
 avago	Avago Technologies
 avic	Shanghai AVIC Optoelectronics Co., Ltd.
 axis	Axis Communications AB
+boe	BOE Technology Group Co., Ltd.
 bosch	Bosch Sensortec GmbH
 boundary	Boundary Devices Inc.
 brcm	Broadcom Corporation
@@ -123,6 +124,8 @@ jedec	JEDEC Solid State Technology Association
 karo	Ka-Ro electronics GmbH
 keymile	Keymile GmbH
 kinetic Kinetic Technologies
+kosagi	Sutajio Ko-Usagi PTE Ltd.
+kyo	Kyocera Corporation
 lacie	LaCie
 lantiq	Lantiq Semiconductor
 lenovo	Lenovo Group Ltd.
@@ -161,6 +164,7 @@ nuvoton	Nuvoton Technology Corporation
 nvidia	NVIDIA
 nxp	NXP Semiconductors
 okaya	Okaya Electric America, Inc.
+olimex	OLIMEX Ltd.
 onnn	ON Semiconductor Corp.
 opencores	OpenCores.org
 option	Option NV
@@ -180,6 +184,7 @@ qca	Qualcomm Atheros, Inc.
 qcom	Qualcomm Technologies, Inc
 qemu	QEMU, a generic and open source machine emulator and virtualizer
 qi	Qi Hardware
+qiaodian	QiaoDian XianShi Corporation
 qnap	QNAP Systems, Inc.
 radxa	Radxa
 raidsonic	RaidSonic Technology GmbH
@@ -218,11 +223,13 @@ sony	Sony Corporation
 spansion	Spansion Inc.
 sprd	Spreadtrum Communications Inc.
 st	STMicroelectronics
+startek	Startek
 ste	ST-Ericsson
 stericsson	ST-Ericsson
 synology	Synology, Inc.
 tbs	TBS Technologies
 tcl	Toby Churchill Ltd.
+technologic	Technologic Systems
 thine	THine Electronics, Inc.
 ti	Texas Instruments
 tlm	Trusted Logic Mobility
@@ -238,6 +245,7 @@ v3	V3 Semiconductor
 variscite	Variscite Ltd.
 via	VIA Technologies, Inc.
 virtio	Virtual I/O Device Specification, developed by the OASIS consortium
+vivante	Vivante Corporation
 voipac	Voipac Technologies s.r.o.
 wexler	Wexler
 winbond Winbond Electronics corp.
diff --git a/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt b/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt
new file mode 100644
index 000000000000..75b265a04047
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt
@@ -0,0 +1,35 @@
+Alphascale asm9260 Watchdog timer
+
+Required properties:
+
+- compatible : should be "alphascale,asm9260-wdt".
+- reg : Specifies base physical address and size of the registers.
+- clocks : the clocks feeding the watchdog timer. See clock-bindings.txt
+- clock-names : should be set to
+	"mod" - source for tick counter.
+	"ahb" - ahb gate.
+- resets : phandle pointing to the system reset controller with
+	line index for the watchdog.
+- reset-names : should be set to "wdt_rst".
+
+Optional properties:
+- timeout-sec : shall contain the default watchdog timeout in seconds,
+	if unset, the default timeout is 30 seconds.
+- alphascale,mode : three modes are supported
+	"hw" - hw reset (default).
+	"sw" - sw reset.
+	"debug" - no action is taken.
+
+Example:
+
+watchdog0: watchdog@80048000 {
+	compatible = "alphascale,asm9260-wdt";
+	reg = <0x80048000 0x10>;
+	clocks = <&acc CLKID_SYS_WDT>, <&acc CLKID_AHB_WDT>;
+	clock-names = "mod", "ahb";
+	interrupts = <55>;
+	resets = <&rst WDT_RESET>;
+	reset-names = "wdt_rst";
+	timeout-sec = <30>;
+	alphascale,mode = "hw";
+};
diff --git a/Documentation/devicetree/bindings/watchdog/meson6-wdt.txt b/Documentation/devicetree/bindings/watchdog/meson-wdt.txt
index 9200fc2d508c..ae70185d96e6 100644
--- a/Documentation/devicetree/bindings/watchdog/meson6-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/meson-wdt.txt
@@ -2,7 +2,7 @@ Meson SoCs Watchdog timer
 
 Required properties:
 
-- compatible : should be "amlogic,meson6-wdt"
+- compatible : should be "amlogic,meson6-wdt" or "amlogic,meson8b-wdt"
 - reg : Specifies base physical address and size of the registers.
 
 Example:
diff --git a/Documentation/devicetree/bindings/watchdog/mt7621-wdt.txt b/Documentation/devicetree/bindings/watchdog/mt7621-wdt.txt
new file mode 100644
index 000000000000..c15ef0ef609f
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/mt7621-wdt.txt
@@ -0,0 +1,12 @@
+Ralink Watchdog Timers
+
+Required properties:
+- compatible: must be "mediatek,mt7621-wdt"
+- reg: physical base address of the controller and length of the register range
+
+Example:
+
+	watchdog@100 {
+		compatible = "mediatek,mt7621-wdt";
+		reg = <0x100 0x10>;
+	};
diff --git a/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt b/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt
index af9eb5b8a253..6a00939a059a 100644
--- a/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt
@@ -2,7 +2,11 @@ Mediatek SoCs Watchdog timer
 
 Required properties:
 
-- compatible : should be "mediatek,mt6589-wdt"
+- compatible should contain:
+	* "mediatek,mt2701-wdt" for MT2701 compatible watchdog timers
+	* "mediatek,mt6589-wdt" for all compatible watchdog timers (MT2701,
+		MT6589)
+
 - reg : Specifies base physical address and size of the registers.
 
 Example:
diff --git a/Documentation/devicetree/bindings/watchdog/sigma,smp8642-wdt.txt b/Documentation/devicetree/bindings/watchdog/sigma,smp8642-wdt.txt
new file mode 100644
index 000000000000..5b7ec2c707d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/sigma,smp8642-wdt.txt
@@ -0,0 +1,18 @@
+Sigma Designs SMP86xx/SMP87xx watchdog
+
+Required properties:
+- compatible: Should be "sigma,smp8642-wdt"
+- reg: Specifies the physical address region
+- clocks: Should be a phandle to the clock
+
+Optional properties:
+- timeout-sec: watchdog timeout in seconds
+
+Example:
+
+watchdog@1fd00 {
+	compatible = "sigma,smp8642-wdt";
+	reg = <0x1fd00 8>;
+	clocks = <&xtal_in_clk>;
+	timeout-sec = <30>;
+};
diff --git a/Documentation/devicetree/bindings/watchdog/sp805-wdt.txt b/Documentation/devicetree/bindings/watchdog/sp805-wdt.txt
new file mode 100644
index 000000000000..edc4f0ea54a3
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/sp805-wdt.txt
@@ -0,0 +1,31 @@
+* ARM SP805 Watchdog Timer (WDT) Controller
+
+SP805 WDT is a ARM Primecell Peripheral and has a standard-id register that
+can be used to identify the peripheral type, vendor, and revision.
+This value can be used for driver matching.
+
+As SP805 WDT is a primecell IP, it follows the base bindings specified in
+'arm/primecell.txt'
+
+Required properties:
+- compatible : Should be "arm,sp805-wdt", "arm,primecell"
+- reg : Base address and size of the watchdog timer registers.
+- clocks : From common clock binding.
+           First clock is PCLK and the second is WDOGCLK.
+           WDOGCLK can be equal to or be a sub-multiple of the PCLK frequency.
+- clock-names : From common clock binding.
+                Shall be "apb_pclk" for first clock and "wdog_clk" for the
+                second one.
+
+Optional properties:
+- interrupts : Should specify WDT interrupt number.
+
+Examples:
+
+		cluster1_core0_watchdog: wdt@c000000 {
+			compatible = "arm,sp805-wdt", "arm,primecell";
+			reg = <0x0 0xc000000 0x0 0x1000>;
+			clocks = <&clockgen 4 3>, <&clockgen 4 3>;
+			clock-names = "apb_pclk", "wdog_clk";
+		};
+
diff --git a/Documentation/devicetree/bindings/watchdog/ts4800-wdt.txt b/Documentation/devicetree/bindings/watchdog/ts4800-wdt.txt
new file mode 100644
index 000000000000..8f6caad4258d
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/ts4800-wdt.txt
@@ -0,0 +1,25 @@
+Technologic Systems Watchdog
+
+Required properties:
+- compatible: must be "technologic,ts4800-wdt"
+- syscon: phandle / integer array that points to the syscon node which
+          describes the FPGA's syscon registers.
+          - phandle to FPGA's syscon
+          - offset to the watchdog register
+
+Optional property:
+- timeout-sec: contains the watchdog timeout in seconds.
+
+Example:
+
+syscon: syscon@b0010000 {
+	compatible = "syscon", "simple-mfd";
+	reg = <0xb0010000 0x3d>;
+	reg-io-width = <2>;
+
+	wdt@e {
+		compatible = "technologic,ts4800-wdt";
+		syscon = <&syscon 0xe>;
+		timeout-sec = <10>;
+	};
+}
diff --git a/Documentation/devicetree/bindings/watchdog/ziirave-wdt.txt b/Documentation/devicetree/bindings/watchdog/ziirave-wdt.txt
new file mode 100644
index 000000000000..3d878184ec3f
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/ziirave-wdt.txt
@@ -0,0 +1,19 @@
+Zodiac RAVE Watchdog Timer
+
+Required properties:
+- compatible: must be "zii,rave-wdt"
+- reg: i2c slave address of device, usually 0x38
+
+Optional Properties:
+- timeout-sec: Watchdog timeout value in seconds.
+- reset-duration-ms: Duration of the pulse generated when the watchdog times
+  out. Value in milliseconds.
+
+Example:
+
+	watchdog@38 {
+		compatible = "zii,rave-wdt";
+		reg = <0x38>;
+		timeout-sec = <30>;
+		reset-duration-ms = <30>;
+	};
diff --git a/Documentation/dmaengine/client.txt b/Documentation/dmaengine/client.txt
index 11fb87ff6cd0..9e33189745f0 100644
--- a/Documentation/dmaengine/client.txt
+++ b/Documentation/dmaengine/client.txt
@@ -22,25 +22,14 @@ The slave DMA usage consists of following steps:
    Channel allocation is slightly different in the slave DMA context,
    client drivers typically need a channel from a particular DMA
    controller only and even in some cases a specific channel is desired.
-   To request a channel dma_request_channel() API is used.
+   To request a channel dma_request_chan() API is used.
 
    Interface:
-	struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
-			dma_filter_fn filter_fn,
-			void *filter_param);
-   where dma_filter_fn is defined as:
-	typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+	struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 
-   The 'filter_fn' parameter is optional, but highly recommended for
-   slave and cyclic channels as they typically need to obtain a specific
-   DMA channel.
-
-   When the optional 'filter_fn' parameter is NULL, dma_request_channel()
-   simply returns the first channel that satisfies the capability mask.
-
-   Otherwise, the 'filter_fn' routine will be called once for each free
-   channel which has a capability in 'mask'.  'filter_fn' is expected to
-   return 'true' when the desired DMA channel is found.
+   Which will find and return the 'name' DMA channel associated with the 'dev'
+   device. The association is done via DT, ACPI or board file based
+   dma_slave_map matching table.
 
    A channel allocated via this interface is exclusive to the caller,
    until dma_release_channel() is called.
@@ -128,7 +117,7 @@ The slave DMA usage consists of following steps:
 	transaction.
 
 	For cyclic DMA, a callback function may wish to terminate the
-	DMA via dmaengine_terminate_all().
+	DMA via dmaengine_terminate_async().
 
 	Therefore, it is important that DMA engine drivers drop any
 	locks before calling the callback function which may cause a
@@ -166,12 +155,29 @@ The slave DMA usage consists of following steps:
 
 Further APIs:
 
-1. int dmaengine_terminate_all(struct dma_chan *chan)
+1. int dmaengine_terminate_sync(struct dma_chan *chan)
+   int dmaengine_terminate_async(struct dma_chan *chan)
+   int dmaengine_terminate_all(struct dma_chan *chan) /* DEPRECATED */
 
    This causes all activity for the DMA channel to be stopped, and may
    discard data in the DMA FIFO which hasn't been fully transferred.
    No callback functions will be called for any incomplete transfers.
 
+   Two variants of this function are available.
+
+   dmaengine_terminate_async() might not wait until the DMA has been fully
+   stopped or until any running complete callbacks have finished. But it is
+   possible to call dmaengine_terminate_async() from atomic context or from
+   within a complete callback. dmaengine_synchronize() must be called before it
+   is safe to free the memory accessed by the DMA transfer or free resources
+   accessed from within the complete callback.
+
+   dmaengine_terminate_sync() will wait for the transfer and any running
+   complete callbacks to finish before it returns. But the function must not be
+   called from atomic context or from within a complete callback.
+
+   dmaengine_terminate_all() is deprecated and should not be used in new code.
+
 2. int dmaengine_pause(struct dma_chan *chan)
 
    This pauses activity on the DMA channel without data loss.
@@ -197,3 +203,20 @@ Further APIs:
 	a running DMA channel.  It is recommended that DMA engine users
 	pause or stop (via dmaengine_terminate_all()) the channel before
 	using this API.
+
+5. void dmaengine_synchronize(struct dma_chan *chan)
+
+  Synchronize the termination of the DMA channel to the current context.
+
+  This function should be used after dmaengine_terminate_async() to synchronize
+  the termination of the DMA channel to the current context. The function will
+  wait for the transfer and any running complete callbacks to finish before it
+  returns.
+
+  If dmaengine_terminate_async() is used to stop the DMA channel this function
+  must be called before it is safe to free memory accessed by previously
+  submitted descriptors or to free any resources accessed within the complete
+  callback of previously submitted descriptors.
+
+  The behavior of this function is undefined if dma_async_issue_pending() has
+  been called between dmaengine_terminate_async() and this function.
diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt
index 67d4ce4df109..122b7f4876bb 100644
--- a/Documentation/dmaengine/provider.txt
+++ b/Documentation/dmaengine/provider.txt
@@ -327,8 +327,24 @@ supported.
 
    * device_terminate_all
      - Aborts all the pending and ongoing transfers on the channel
-     - This command should operate synchronously on the channel,
-       terminating right away all the channels
+     - For aborted transfers the complete callback should not be called
+     - Can be called from atomic context or from within a complete
+       callback of a descriptor. Must not sleep. Drivers must be able
+       to handle this correctly.
+     - Termination may be asynchronous. The driver does not have to
+       wait until the currently active transfer has completely stopped.
+       See device_synchronize.
+
+   * device_synchronize
+     - Must synchronize the termination of a channel to the current
+       context.
+     - Must make sure that memory for previously submitted
+       descriptors is no longer accessed by the DMA controller.
+     - Must make sure that all complete callbacks for previously
+       submitted descriptors have finished running and none are
+       scheduled to run.
+     - May sleep.
+
 
 Misc notes (stuff that should be documented, but don't really know
 where to put them)
diff --git a/Documentation/dvb/README.dvb-usb b/Documentation/dvb/README.dvb-usb
index 8eb92264ee04..669dc6ce4330 100644
--- a/Documentation/dvb/README.dvb-usb
+++ b/Documentation/dvb/README.dvb-usb
@@ -45,7 +45,7 @@ Supported devices
 See the LinuxTV DVB Wiki at www.linuxtv.org for a complete list of
 cards/drivers/firmwares:
 
-http://www.linuxtv.org/wiki/index.php/DVB_USB
+https://linuxtv.org/wiki/index.php/DVB_USB
 
 0. History & News:
   2005-06-30 - added support for WideView WT-220U (Thanks to Steve Chang)
@@ -121,7 +121,7 @@ working.
 Have a look at the Wikipage for the DVB-USB-drivers to find out, which firmware
 you need for your device:
 
-http://www.linuxtv.org/wiki/index.php/DVB_USB
+https://linuxtv.org/wiki/index.php/DVB_USB
 
 1.2. Compiling
 
diff --git a/Documentation/dvb/faq.txt b/Documentation/dvb/faq.txt
index 97b1373f2428..a0be92012877 100644
--- a/Documentation/dvb/faq.txt
+++ b/Documentation/dvb/faq.txt
@@ -76,7 +76,7 @@ Some very frequently asked questions about linuxtv-dvb
 		the TuxBox CVS many interesting DVB applications and the dBox2
 		DVB source
 
-	http://www.linuxtv.org/downloads/	
+	https://linuxtv.org/downloads
 		DVB Swiss Army Knife library and utilities
 
 	http://www.nenie.org/misc/mpsys/
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 91b43d2738c7..1a0a04125f71 100755
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -152,7 +152,7 @@ sub tda10046lifeview {
 
 sub av7110 {
     my $sourcefile = "dvb-ttpci-01.fw-261d";
-    my $url = "http://www.linuxtv.org/downloads/firmware/$sourcefile";
+    my $url = "https://linuxtv.org/downloads/firmware/$sourcefile";
     my $hash = "603431b6259715a8e88f376a53b64e2f";
     my $outfile = "dvb-ttpci-01.fw";
 
@@ -303,7 +303,7 @@ sub vp7049 {
 }
 
 sub dibusb {
-	my $url = "http://www.linuxtv.org/downloads/firmware/dvb-usb-dibusb-5.0.0.11.fw";
+	my $url = "https://linuxtv.org/downloads/firmware/dvb-usb-dibusb-5.0.0.11.fw";
 	my $outfile = "dvb-dibusb-5.0.0.11.fw";
 	my $hash = "fa490295a527360ca16dcdf3224ca243";
 
@@ -351,7 +351,7 @@ sub nxt2004 {
 
 sub or51211 {
     my $fwfile = "dvb-fe-or51211.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "d830949c771a289505bf9eafc225d491";
 
     checkstandard();
@@ -364,7 +364,7 @@ sub or51211 {
 
 sub cx231xx {
     my $fwfile = "v4l-cx231xx-avcore-01.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "7d3bb956dc9df0eafded2b56ba57cc42";
 
     checkstandard();
@@ -376,7 +376,7 @@ sub cx231xx {
 }
 
 sub cx18 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx23418-apu.fw' => '588f081b562f5c653a3db1ad8f65939a',
@@ -450,7 +450,7 @@ sub mpc718 {
 }
 
 sub cx23885 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx23885-avcore-01.fw' => 'a9f8f5d901a7fb42f552e1ee6384f3bb',
@@ -472,7 +472,7 @@ sub cx23885 {
 }
 
 sub pvrusb2 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx25840.fw'           => 'dadb79e9904fc8af96e8111d9cb59320',
@@ -494,7 +494,7 @@ sub pvrusb2 {
 
 sub or51132_qam {
     my $fwfile = "dvb-fe-or51132-qam.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "7702e8938612de46ccadfe9b413cb3b5";
 
     checkstandard();
@@ -507,7 +507,7 @@ sub or51132_qam {
 
 sub or51132_vsb {
     my $fwfile = "dvb-fe-or51132-vsb.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "c16208e02f36fc439a557ad4c613364a";
 
     checkstandard();
@@ -519,7 +519,7 @@ sub or51132_vsb {
 }
 
 sub bluebird {
-	my $url = "http://www.linuxtv.org/download/dvb/firmware/dvb-usb-bluebird-01.fw";
+	my $url = "https://linuxtv.org/download/dvb/firmware/dvb-usb-bluebird-01.fw";
 	my $outfile = "dvb-usb-bluebird-01.fw";
 	my $hash = "658397cb9eba9101af9031302671f49d";
 
@@ -677,7 +677,7 @@ sub drxk_hauppauge_hvr930c {
 }
 
 sub drxk_terratec_h5 {
-    my $url = "http://www.linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
     my $hash = "19000dada8e2741162ccc50cc91fa7f1";
     my $fwfile = "dvb-usb-terratec-h5-drxk.fw";
 
diff --git a/Documentation/dvb/readme.txt b/Documentation/dvb/readme.txt
index 0b0380c91990..89965041a266 100644
--- a/Documentation/dvb/readme.txt
+++ b/Documentation/dvb/readme.txt
@@ -2,12 +2,12 @@ Linux Digital Video Broadcast (DVB) subsystem
 =============================================
 
 The main development site and CVS repository for these
-drivers is http://linuxtv.org/.
+drivers is https://linuxtv.org.
 
 The developer mailing list linux-dvb is also hosted there,
-see http://linuxtv.org/lists.php. Please check
-the archive http://linuxtv.org/pipermail/linux-dvb/
-and the Wiki http://linuxtv.org/wiki/
+see https://linuxtv.org/lists.php. Please check
+the archive https://linuxtv.org/pipermail/linux-dvb/
+and the Wiki https://linuxtv.org/wiki/
 before asking newbie questions on the list.
 
 API documentation, utilities and test/example programs
@@ -16,7 +16,7 @@ are available as part of the old driver package for Linux 2.4
 We plan to split this into separate packages, but it's not
 been done yet.
 
-http://linuxtv.org/downloads/
+https://linuxtv.org/downloads/
 
 What's inside this directory:
 
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index 80841a2d640c..f89cfd85ae13 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -1,9 +1,13 @@
 EDAC - Error Detection And Correction
 =====================================
 
-"bluesmoke" was the name for this device driver when it was "out-of-tree"
-and maintained at sourceforge.net.  When it was pushed into 2.6.16 for the
-first time, it was renamed to 'EDAC'.
+"bluesmoke" was the name for this device driver when it
+was "out-of-tree" and maintained at sourceforge.net -
+bluesmoke.sourceforge.net. That site is mostly archaic now and can be
+used only for historical purposes.
+
+When the subsystem was pushed into 2.6.16 for the first time, it was
+renamed to 'EDAC'.
 
 PURPOSE
 -------
diff --git a/Documentation/fault-injection/notifier-error-inject.txt b/Documentation/fault-injection/notifier-error-inject.txt
index 09adabef513f..83d3f4e43e91 100644
--- a/Documentation/fault-injection/notifier-error-inject.txt
+++ b/Documentation/fault-injection/notifier-error-inject.txt
@@ -10,6 +10,7 @@ modules that can be used to test the following notifiers.
  * PM notifier
  * Memory hotplug notifier
  * powerpc pSeries reconfig notifier
+ * Netdevice notifier
 
 CPU notifier error injection module
 -----------------------------------
@@ -87,6 +88,30 @@ Possible pSeries reconfig notifier events to be failed are:
  * PSERIES_DRCONF_MEM_ADD
  * PSERIES_DRCONF_MEM_REMOVE
 
+Netdevice notifier error injection module
+----------------------------------------------
+This feature is controlled through debugfs interface
+/sys/kernel/debug/notifier-error-inject/netdev/actions/<notifier event>/error
+
+Netdevice notifier events which can be failed are:
+
+ * NETDEV_REGISTER
+ * NETDEV_CHANGEMTU
+ * NETDEV_CHANGENAME
+ * NETDEV_PRE_UP
+ * NETDEV_PRE_TYPE_CHANGE
+ * NETDEV_POST_INIT
+ * NETDEV_PRECHANGEMTU
+ * NETDEV_PRECHANGEUPPER
+ * NETDEV_CHANGEUPPER
+
+Example: Inject netdevice mtu change error (-22 == -EINVAL)
+
+	# cd /sys/kernel/debug/notifier-error-inject/netdev
+	# echo -22 > actions/NETDEV_CHANGEMTU/error
+	# ip link set eth0 mtu 1024
+	RTNETLINK answers: Invalid argument
+
 For more usage examples
 -----------------------
 There are tools/testing/selftests using the notifier error injection features
diff --git a/Documentation/features/io/dma_map_attrs/arch-support.txt b/Documentation/features/io/dma_map_attrs/arch-support.txt
deleted file mode 100644
index 51d0f1c02a3e..000000000000
--- a/Documentation/features/io/dma_map_attrs/arch-support.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-#
-# Feature name:          dma_map_attrs
-#         Kconfig:       HAVE_DMA_ATTRS
-#         description:   arch provides dma_*map*_attrs() APIs
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: |  ok  |
-    |         arc: | TODO |
-    |         arm: |  ok  |
-    |       arm64: |  ok  |
-    |       avr32: | TODO |
-    |    blackfin: | TODO |
-    |         c6x: | TODO |
-    |        cris: | TODO |
-    |         frv: | TODO |
-    |       h8300: |  ok  |
-    |     hexagon: |  ok  |
-    |        ia64: |  ok  |
-    |        m32r: | TODO |
-    |        m68k: | TODO |
-    |       metag: | TODO |
-    |  microblaze: |  ok  |
-    |        mips: |  ok  |
-    |     mn10300: | TODO |
-    |       nios2: | TODO |
-    |    openrisc: |  ok  |
-    |      parisc: | TODO |
-    |     powerpc: |  ok  |
-    |        s390: |  ok  |
-    |       score: | TODO |
-    |          sh: |  ok  |
-    |       sparc: |  ok  |
-    |        tile: |  ok  |
-    |          um: | TODO |
-    |   unicore32: |  ok  |
-    |         x86: |  ok  |
-    |      xtensa: | TODO |
-    -----------------------
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index 76d39d66a5d7..4f66ec133951 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -33,7 +33,7 @@
     |          sh: | TODO |
     |       sparc: | TODO |
     |        tile: |  ok  |
-    |          um: | TODO |
+    |          um: |  ok  |
     |   unicore32: | TODO |
     |         x86: |  ok  |
     |      xtensa: | TODO |
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
index e63316239938..4199ffecc0ff 100644
--- a/Documentation/features/time/irq-time-acct/arch-support.txt
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: |  ..  |
     |         arc: | TODO |
     |         arm: |  ok  |
-    |       arm64: |  ..  |
+    |       arm64: |  ok  |
     |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
diff --git a/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt b/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt
deleted file mode 100644
index 26f74b457e0b..000000000000
--- a/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-#
-# Feature name:          pmdp_splitting_flush
-#         Kconfig:       __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-#         description:   arch supports the pmdp_splitting_flush() VM API
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: | TODO |
-    |         arc: | TODO |
-    |         arm: |  ok  |
-    |       arm64: |  ok  |
-    |       avr32: | TODO |
-    |    blackfin: | TODO |
-    |         c6x: | TODO |
-    |        cris: | TODO |
-    |         frv: | TODO |
-    |       h8300: | TODO |
-    |     hexagon: | TODO |
-    |        ia64: | TODO |
-    |        m32r: | TODO |
-    |        m68k: | TODO |
-    |       metag: | TODO |
-    |  microblaze: | TODO |
-    |        mips: |  ok  |
-    |     mn10300: | TODO |
-    |       nios2: | TODO |
-    |    openrisc: | TODO |
-    |      parisc: | TODO |
-    |     powerpc: |  ok  |
-    |        s390: |  ok  |
-    |       score: | TODO |
-    |          sh: | TODO |
-    |       sparc: | TODO |
-    |        tile: | TODO |
-    |          um: | TODO |
-    |   unicore32: | TODO |
-    |         x86: |  ok  |
-    |      xtensa: | TODO |
-    -----------------------
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 06d443450f21..619af9bfdcb3 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -50,8 +50,7 @@ prototypes:
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	const char *(*follow_link) (struct dentry *, void **);
-	void (*put_link) (struct inode *, void *);
+	const char *(*get_link) (struct dentry *, struct inode *, void **);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
@@ -83,8 +82,7 @@ rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
 rename2:	yes (all)	(see below)
 readlink:	no
-follow_link:	no
-put_link:	no
+get_link:	no
 setattr:	yes
 permission:	no (may not block if called in rcu-walk mode)
 get_acl:	no
diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt
index af68efdbbfad..e5fe521eea1d 100644
--- a/Documentation/filesystems/configfs/configfs.txt
+++ b/Documentation/filesystems/configfs/configfs.txt
@@ -51,15 +51,27 @@ configfs tree is always there, whether mounted on /config or not.
 An item is created via mkdir(2).  The item's attributes will also
 appear at this time.  readdir(3) can determine what the attributes are,
 read(2) can query their default values, and write(2) can store new
-values.  Like sysfs, attributes should be ASCII text files, preferably
-with only one value per file.  The same efficiency caveats from sysfs
-apply.  Don't mix more than one attribute in one attribute file.
-
-Like sysfs, configfs expects write(2) to store the entire buffer at
-once.  When writing to configfs attributes, userspace processes should
-first read the entire file, modify the portions they wish to change, and
-then write the entire buffer back.  Attribute files have a maximum size
-of one page (PAGE_SIZE, 4096 on i386).
+values.  Don't mix more than one attribute in one attribute file.
+
+There are two types of configfs attributes:
+
+* Normal attributes, which similar to sysfs attributes, are small ASCII text
+files, with a maximum size of one page (PAGE_SIZE, 4096 on i386).  Preferably
+only one value per file should be used, and the same caveats from sysfs apply.
+Configfs expects write(2) to store the entire buffer at once.  When writing to
+normal configfs attributes, userspace processes should first read the entire
+file, modify the portions they wish to change, and then write the entire
+buffer back.
+
+* Binary attributes, which are somewhat similar to sysfs binary attributes,
+but with a few slight changes to semantics.  The PAGE_SIZE limitation does not
+apply, but the whole binary item must fit in single kernel vmalloc'ed buffer.
+The write(2) calls from user space are buffered, and the attributes'
+write_bin_attribute method will be invoked on the final close, therefore it is
+imperative for user-space to check the return code of close(2) in order to
+verify that the operation finished successfully.
+To avoid a malicious user OOMing the kernel, there's a per-binary attribute
+maximum buffer value.
 
 When an item needs to be destroyed, remove it with rmdir(2).  An
 item cannot be destroyed if any other item has a link to it (via
@@ -171,6 +183,7 @@ among other things.  For that, it needs a type.
 		struct configfs_item_operations         *ct_item_ops;
 		struct configfs_group_operations        *ct_group_ops;
 		struct configfs_attribute               **ct_attrs;
+		struct configfs_bin_attribute		**ct_bin_attrs;
 	};
 
 The most basic function of a config_item_type is to define what
@@ -201,6 +214,32 @@ be called whenever userspace asks for a read(2) on the attribute.  If an
 attribute is writable and provides a ->store  method, that method will be
 be called whenever userspace asks for a write(2) on the attribute.
 
+[struct configfs_bin_attribute]
+
+	struct configfs_attribute {
+		struct configfs_attribute	cb_attr;
+		void				*cb_private;
+		size_t				cb_max_size;
+	};
+
+The binary attribute is used when the one needs to use binary blob to
+appear as the contents of a file in the item's configfs directory.
+To do so add the binary attribute to the NULL-terminated array
+config_item_type->ct_bin_attrs, and the item appears in configfs, the
+attribute file will appear with the configfs_bin_attribute->cb_attr.ca_name
+filename.  configfs_bin_attribute->cb_attr.ca_mode specifies the file
+permissions.
+The cb_private member is provided for use by the driver, while the
+cb_max_size member specifies the maximum amount of vmalloc buffer
+to be used.
+
+If binary attribute is readable and the config_item provides a
+ct_item_ops->read_bin_attribute() method, that method will be called
+whenever userspace asks for a read(2) on the attribute.  The converse
+will happen for write(2). The reads/writes are bufferred so only a
+single read/write will occur; the attributes' need not concern itself
+with it.
+
 [struct config_group]
 
 A config_item cannot live in a vacuum.  The only way one can be created
diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
index c477af086e65..686a64bba775 100644
--- a/Documentation/filesystems/efivarfs.txt
+++ b/Documentation/filesystems/efivarfs.txt
@@ -14,3 +14,10 @@ filesystem.
 efivarfs is typically mounted like this,
 
 	mount -t efivarfs none /sys/firmware/efi/efivars
+
+Due to the presence of numerous firmware bugs where removing non-standard
+UEFI variables causes the system firmware to fail to POST, efivarfs
+files that are not well-known standardized variables are created
+as immutable files.  This doesn't prevent removal - "chattr -i" will work -
+but it does prevent this kind of failure from being accomplished
+accidentally.
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index b102b436563e..e1c9f0849da6 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -102,7 +102,7 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        collection, triggered in background when I/O subsystem is
                        idle. If background_gc=on, it will turn on the garbage
                        collection and if background_gc=off, garbage collection
-                       will be truned off. If background_gc=sync, it will turn
+                       will be turned off. If background_gc=sync, it will turn
                        on synchronous garbage collection running in background.
                        Default value for this option is on. So garbage
                        collection is on by default.
@@ -145,10 +145,12 @@ extent_cache           Enable an extent cache based on rb-tree, it can cache
                        as many as extent which map between contiguous logical
                        address and physical address per inode, resulting in
                        increasing the cache hit ratio. Set by default.
-noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+noextent_cache         Disable an extent cache based on rb-tree explicitly, see
                        the above extent_cache mount option.
 noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
+data_flush             Enable data flushing before checkpoint in order to
+                       persist data of regular and symlink.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -192,7 +194,7 @@ Files in /sys/fs/f2fs/<devname>
                               policy for garbage collection. Setting gc_idle = 0
                               (default) will disable this option. Setting
                               gc_idle = 1 will select the Cost Benefit approach
-                              & setting gc_idle = 2 will select the greedy aproach.
+                              & setting gc_idle = 2 will select the greedy approach.
 
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
@@ -298,7 +300,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
 file. Each file is dump_ssa and dump_sit.
 
 The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
-It shows on-disk inode information reconized by a given inode number, and is
+It shows on-disk inode information recognized by a given inode number, and is
 able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
 ./dump_sit respectively.
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index f24d1b833957..f1b87d8aa2da 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -504,3 +504,24 @@ in your dentry operations instead.
 [mandatory]
 	__fd_install() & fd_install() can now sleep. Callers should not
 	hold a spinlock	or other resources that do not allow a schedule.
+--
+[mandatory]
+	any symlink that might use page_follow_link_light/page_put_link() must
+	have inode_nohighmem(inode) called before anything might start playing with
+	its pagecache.  No highmem pages should end up in the pagecache of such
+	symlinks.  That includes any preseeding that might be done during symlink
+	creation.  __page_symlink() will honour the mapping gfp flags, so once
+	you've done inode_nohighmem() it's safe to use, but if you allocate and
+	insert the page manually, make sure to use the right gfp flags.
+--
+[mandatory]
+	->follow_link() is replaced with ->get_link(); same API, except that
+		* ->get_link() gets inode as a separate argument
+		* ->get_link() may be called in RCU mode - in that case NULL
+		  dentry is passed
+--
+[mandatory]
+	->get_link() gets struct delayed_call *done now, and should do
+	set_delayed_call() where it used to set *cookie.
+	->put_link() is gone - just give the destructor to set_delayed_call()
+	in ->get_link().
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 402ab99e409f..843b045b4069 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -169,6 +169,9 @@ read the file /proc/PID/status:
   VmLck:         0 kB
   VmHWM:       476 kB
   VmRSS:       476 kB
+  RssAnon:             352 kB
+  RssFile:             120 kB
+  RssShmem:              4 kB
   VmData:      156 kB
   VmStk:        88 kB
   VmExe:        68 kB
@@ -231,14 +234,20 @@ Table 1-2: Contents of the status files (as of 4.1)
  VmSize                      total program size
  VmLck                       locked memory size
  VmHWM                       peak resident set size ("high water mark")
- VmRSS                       size of memory portions
- VmData                      size of data, stack, and text segments
- VmStk                       size of data, stack, and text segments
+ VmRSS                       size of memory portions. It contains the three
+                             following parts (VmRSS = RssAnon + RssFile + RssShmem)
+ RssAnon                     size of resident anonymous memory
+ RssFile                     size of resident file mappings
+ RssShmem                    size of resident shmem memory (includes SysV shm,
+                             mapping of tmpfs and shared anonymous mappings)
+ VmData                      size of private data segments
+ VmStk                       size of stack segments
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
  VmPMD                       size of second level page tables
- VmSwap                      size of swap usage (the number of referred swapents)
+ VmSwap                      amount of swap used by anonymous private data
+                             (shmem swap usage is not included)
  HugetlbPages                size of hugetlb memory portions
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
@@ -265,7 +274,8 @@ Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
  Field    Content
  size     total program size (pages)		(same as VmSize in status)
  resident size of memory portions (pages)	(same as VmRSS in status)
- shared   number of pages that are shared	(i.e. backed by a file)
+ shared   number of pages that are shared	(i.e. backed by a file, same
+						as RssFile+RssShmem in status)
  trs      number of pages that are 'code'	(not including libs; broken,
 							includes data segment)
  lrs      number of pages of library		(always 0 on 2.6)
@@ -346,7 +356,7 @@ address           perms offset  dev   inode      pathname
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
@@ -378,7 +388,6 @@ is not associated with a file:
 
  [heap]                   = the heap of the program
  [stack]                  = the stack of the main process
- [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
 
@@ -386,10 +395,8 @@ is not associated with a file:
 
 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. This is a key difference from the
-content of /proc/PID/maps, where you will see all mappings that are being used
-as stack by all of those tasks. Hence, for the example above, the task-level
-map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
+as [stack] if that task sees it as a stack. Hence, for the example above, the
+task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 
 08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
@@ -459,7 +466,10 @@ and a page is modified, the file page is replaced by a private anonymous copy.
 hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
 reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
 "Swap" shows how much would-be-anonymous memory is also used, but out on swap.
-"SwapPss" shows proportional swap share of this mapping.
+For shmem mappings, "Swap" includes also the size of the mapped (and not
+replaced by copy-on-write) part of the underlying shmem object out on swap.
+"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
+does not take into account swapped out page of underlying shmem objects.
 "Locked" indicates whether the mapping is locked in memory or not.
 
 "VmFlags" field deserves a separate description. This member represents the kernel
@@ -807,7 +817,7 @@ by migrate-type and finishes with details on how many page blocks of each
 type exist.
 
 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
-from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can
 make an estimate of the likely number of huge pages that can be allocated
 at a given point in time. All the "Movable" blocks should be allocatable
 unless memory has been mlock()'d. Some of the Reclaimable blocks should
@@ -842,6 +852,7 @@ Dirty:             968 kB
 Writeback:           0 kB
 AnonPages:      861800 kB
 Mapped:         280372 kB
+Shmem:             644 kB
 Slab:           284364 kB
 SReclaimable:   159856 kB
 SUnreclaim:     124508 kB
@@ -898,6 +909,7 @@ MemAvailable: An estimate of how much memory is available for starting new
    AnonPages: Non-file backed pages mapped into userspace page tables
 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
       Mapped: files which have been mmaped, such as libraries
+       Shmem: Total memory used by shared memory (shmem) and tmpfs
         Slab: in-kernel data structures cache
 SReclaimable: Part of Slab, that might be reclaimed, such as caches
   SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 32a173dd3158..e3f4c778eb98 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -664,7 +664,7 @@ replicas continue to be exactly same.
 		if one rbind mounts a tree within the same subtree 'n' times
 		the number of mounts created is an exponential function of 'n'.
 		Having unbindable mount can help prune the unneeded bind
-		mounts. Here is a example.
+		mounts. Here is an example.
 
 		step 1:
 		   let's say the root tree has just two directories with
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 98ef55124158..d392e1505f17 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -17,10 +17,10 @@ RAM, where you have to create an ordinary filesystem on top. Ramdisks
 cannot swap and you do not have the possibility to resize them. 
 
 Since tmpfs lives completely in the page cache and on swap, all tmpfs
-pages currently in memory will show up as cached. It will not show up
-as shared or something like that. Further on you can check the actual
-RAM+swap use of a tmpfs instance with df(1) and du(1).
-
+pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
+free(1). Notice that these counters also include shared memory
+(shmem, see ipcs(1)). The most reliable way to get the count is
+using df(1) and du(1).
 
 tmpfs has the following uses:
 
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ce1126aceed8..223c32171dcc 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -180,6 +180,16 @@ dos1xfloppy  -- If set, use a fallback default BIOS Parameter Block
 
 <bool>: 0,1,yes,no,true,false
 
+LIMITATION
+---------------------------------------------------------------------
+* The fallocated region of file is discarded at umount/evict time
+  when using fallocate with FALLOC_FL_KEEP_SIZE.
+  So, User should assume that fallocated region can be discarded at
+  last close if there is memory pressure resulting in eviction of
+  the inode from the memory. As a result, for any dependency on
+  the fallocated region, user should make sure to recheck fallocate
+  after reopening the file.
+
 TODO
 ----------------------------------------------------------------------
 * Need to get rid of the raw scanning stuff.  Instead, always use
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 8c6f07ad373a..b02a7d598258 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -350,8 +350,8 @@ struct inode_operations {
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	const char *(*follow_link) (struct dentry *, void **);
-	void (*put_link) (struct inode *, void *);
+	const char *(*get_link) (struct dentry *, struct inode *,
+				 struct delayed_call *);
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
@@ -434,20 +434,19 @@ otherwise noted.
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links
 
-  follow_link: called by the VFS to follow a symbolic link to the
+  get_link: called by the VFS to follow a symbolic link to the
 	inode it points to.  Only required if you want to support
 	symbolic links.  This method returns the symlink body
 	to traverse (and possibly resets the current position with
 	nd_jump_link()).  If the body won't go away until the inode
 	is gone, nothing else is needed; if it needs to be otherwise
-	pinned, the data needed to release whatever we'd grabbed
-	is to be stored in void * variable passed by address to
-	follow_link() instance.
-
-  put_link: called by the VFS to release resources allocated by
-	follow_link().  The cookie stored by follow_link() is passed
-	to this method as the last parameter; only called when
-	cookie isn't NULL.
+	pinned, arrange for its release by having get_link(..., ..., done)
+	do set_delayed_call(done, destructor, argument).
+	In that case destructor(argument) will be called once VFS is
+	done with the body you've returned.
+	May be called in RCU mode; that is indicated by NULL dentry
+	argument.  If request can't be handled without leaving RCU mode,
+	have it return ERR_PTR(-ECHILD).
 
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index e000502fde20..05676fdacfe3 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -260,7 +260,7 @@ will be driven low.
 
 To summarize:
 
-Function (example)               active-low proporty  physical line
+Function (example)               active-low property  physical line
 gpiod_set_raw_value(desc, 0);        don't care           low
 gpiod_set_raw_value(desc, 1);        don't care           high
 gpiod_set_value(desc, 0);       default (active-high)     low
diff --git a/Documentation/gpio/driver.txt b/Documentation/gpio/driver.txt
index 12a61948ec91..bbeec415f406 100644
--- a/Documentation/gpio/driver.txt
+++ b/Documentation/gpio/driver.txt
@@ -113,8 +113,8 @@ GPIO irqchips usually fall in one of two categories:
   it will be threaded IRQ handler on -RT and hard IRQ handler on non-RT
   (for example, see [3]).
   Know W/A: The generic_handle_irq() is expected to be called with IRQ disabled,
-  so IRQ core will complain if it will be called from IRQ handler wich is forced
-  thread. The "fake?" raw lock can be used to W/A this problem:
+  so IRQ core will complain if it will be called from IRQ handler which is
+  forced thread. The "fake?" raw lock can be used to W/A this problem:
 
 	raw_spinlock_t wa_lock;
 	static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank)
@@ -224,7 +224,7 @@ Real-Time compliance for GPIO IRQ chips
 ---------------------------------------
 
 Any provider of irqchips needs to be carefully tailored to support Real Time
-preemption. It is desireable that all irqchips in the GPIO subsystem keep this
+preemption. It is desirable that all irqchips in the GPIO subsystem keep this
 in mind and does the proper testing to assure they are real time-enabled.
 So, pay attention on above " RT_FULL:" notes, please.
 The following is a checklist to follow when preparing a driver for real
diff --git a/Documentation/gpio/drivers-on-gpio.txt b/Documentation/gpio/drivers-on-gpio.txt
index f6121328630f..14bf95a13bae 100644
--- a/Documentation/gpio/drivers-on-gpio.txt
+++ b/Documentation/gpio/drivers-on-gpio.txt
@@ -54,7 +54,7 @@ hardware descriptions such as device tree or ACPI:
   drivers for the I2C devices on the bus like any other I2C bus driver.
 
 - spi_gpio: drivers/spi/spi-gpio.c is used to drive an SPI bus (variable number
-  of wires, atleast SCK and optionally MISO, MOSI and chip select lines) using
+  of wires, at least SCK and optionally MISO, MOSI and chip select lines) using
   GPIO hammering (bitbang). It will appear as any other SPI bus on the system
   and makes it possible to connect drivers for SPI devices on the bus like
   any other SPI bus driver. For example any MMC/SD card can then be connected
@@ -75,7 +75,7 @@ hardware descriptions such as device tree or ACPI:
 
 - gpio-wdt: drivers/watchdog/gpio_wdt.c is used to provide a watchdog timer
   that will periodically "ping" a hardware connected to a GPIO line by toggling
-  it from 1-to-0-to-1. If that hardware does not recieve its "ping"
+  it from 1-to-0-to-1. If that hardware does not receive its "ping"
   periodically, it will reset the system.
 
 - gpio-nand: drivers/mtd/nand/gpio.c is used to connect a NAND flash chip to
@@ -91,5 +91,5 @@ usually connected directly to the flash.
 
 Use those instead of talking directly to the GPIOs using sysfs; they integrate
 with kernel frameworks better than your userspace code could. Needless to say,
-just using the apropriate kernel drivers will simplify and speed up your
+just using the appropriate kernel drivers will simplify and speed up your
 embedded hacking in particular by providing ready-made components.
diff --git a/Documentation/hwmon/htu21 b/Documentation/hwmon/htu21
deleted file mode 100644
index f39a215fb6ae..000000000000
--- a/Documentation/hwmon/htu21
+++ /dev/null
@@ -1,46 +0,0 @@
-Kernel driver htu21
-===================
-
-Supported chips:
-  * Measurement Specialties HTU21D
-    Prefix: 'htu21'
-    Addresses scanned: none
-    Datasheet: Publicly available at the Measurement Specialties website
-    http://www.meas-spec.com/downloads/HTU21D.pdf
-
-
-Author:
-  William Markezana <william.markezana@meas-spec.com>
-
-Description
------------
-
-The HTU21D is a humidity and temperature sensor in a DFN package of
-only 3 x 3 mm footprint and 0.9 mm height.
-
-The devices communicate with the I2C protocol. All sensors are set to the
-same I2C address 0x40, so an entry with I2C_BOARD_INFO("htu21", 0x40) can
-be used in the board setup code.
-
-This driver does not auto-detect devices. You will have to instantiate the
-devices explicitly. Please see Documentation/i2c/instantiating-devices
-for details.
-
-sysfs-Interface
----------------
-
-temp1_input - temperature input
-humidity1_input - humidity input
-
-Notes
------
-
-The driver uses the default resolution settings of 12 bit for humidity and 14
-bit for temperature, which results in typical measurement times of 11 ms for
-humidity and 44 ms for temperature. To keep self heating below 0.1 degree
-Celsius, the device should not be active for more than 10% of the time. For
-this reason, the driver performs no more than two measurements per second and
-reports cached information if polled more frequently.
-
-Different resolutions, the on-chip heater, using the CRC checksum and reading
-the serial number are not supported yet.
diff --git a/Documentation/hwmon/ltc3815 b/Documentation/hwmon/ltc3815
new file mode 100644
index 000000000000..eb7db2d13587
--- /dev/null
+++ b/Documentation/hwmon/ltc3815
@@ -0,0 +1,61 @@
+Kernel driver ltc3815
+=====================
+
+Supported chips:
+  * Linear Technology LTC3815
+    Prefix: 'ltc3815'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc3815
+
+Author: Guenter Roeck <linux@roeck-us.net>
+
+
+Description
+-----------
+
+LTC3815 is a Monolithic Synchronous DC/DC Step-Down Converter.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+Example: the following commands will load the driver for an LTC3815
+at address 0x20 on I2C bus #1:
+
+# modprobe ltc3815
+# echo ltc3815 0x20 > /sys/bus/i2c/devices/i2c-1/new_device
+
+
+Sysfs attributes
+----------------
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_alarm		Input voltage alarm.
+in1_highest		Highest input voltage.
+in1_reset_history	Reset input voltage history.
+
+in2_label		"vout1".
+in2_input		Measured output voltage.
+in2_alarm		Output voltage alarm.
+in2_highest		Highest output voltage.
+in2_reset_history	Reset output voltage history.
+
+temp1_input		Measured chip temperature.
+temp1_alarm		Temperature alarm.
+temp1_highest		Highest measured temperature.
+temp1_reset_history	Reset temperature history.
+
+curr1_label		"iin".
+curr1_input		Measured input current.
+curr1_highest		Highest input current.
+curr1_reset_history	Reset input current history.
+
+curr2_label		"iout1".
+curr2_input		Measured output current.
+curr2_alarm		Output current alarm.
+curr2_highest		Highest output current.
+curr2_reset_history	Reset output current history.
diff --git a/Documentation/iio/iio_configfs.txt b/Documentation/iio/iio_configfs.txt
new file mode 100644
index 000000000000..f0add35cd52e
--- /dev/null
+++ b/Documentation/iio/iio_configfs.txt
@@ -0,0 +1,93 @@
+Industrial IIO configfs support
+
+1. Overview
+
+Configfs is a filesystem-based manager of kernel objects. IIO uses some
+objects that could be easily configured using configfs (e.g.: devices,
+triggers).
+
+See Documentation/filesystems/configfs/configfs.txt for more information
+about how configfs works.
+
+2. Usage
+
+In order to use configfs support in IIO we need to select it at compile
+time via CONFIG_IIO_CONFIGFS config option.
+
+Then, mount the configfs filesystem (usually under /config directory):
+
+$ mkdir /config
+$ mount -t configfs none /config
+
+At this point, all default IIO groups will be created and can be accessed
+under /config/iio. Next chapters will describe available IIO configuration
+objects.
+
+3. Software triggers
+
+One of the IIO default configfs groups is the "triggers" group. It is
+automagically accessible when the configfs is mounted and can be found
+under /config/iio/triggers.
+
+IIO software triggers implementation offers support for creating multiple
+trigger types. A new trigger type is usually implemented as a separate
+kernel module following the interface in include/linux/iio/sw_trigger.h:
+
+/*
+ * drivers/iio/trigger/iio-trig-sample.c
+ * sample kernel module implementing a new trigger type
+ */
+#include <linux/iio/sw_trigger.h>
+
+
+static struct iio_sw_trigger *iio_trig_sample_probe(const char *name)
+{
+	/*
+	 * This allocates and registers an IIO trigger plus other
+	 * trigger type specific initialization.
+	 */
+}
+
+static int iio_trig_hrtimer_remove(struct iio_sw_trigger *swt)
+{
+	/*
+	 * This undoes the actions in iio_trig_sample_probe
+	 */
+}
+
+static const struct iio_sw_trigger_ops iio_trig_sample_ops = {
+	.probe		= iio_trig_sample_probe,
+	.remove		= iio_trig_sample_remove,
+};
+
+static struct iio_sw_trigger_type iio_trig_sample = {
+	.name = "trig-sample",
+	.owner = THIS_MODULE,
+	.ops = &iio_trig_sample_ops,
+};
+
+module_iio_sw_trigger_driver(iio_trig_sample);
+
+Each trigger type has its own directory under /config/iio/triggers. Loading
+iio-trig-sample module will create 'trig-sample' trigger type directory
+/config/iio/triggers/trig-sample.
+
+We support the following interrupt sources (trigger types):
+	* hrtimer, uses high resolution timers as interrupt source
+
+3.1 Hrtimer triggers creation and destruction
+
+Loading iio-trig-hrtimer module will register hrtimer trigger types allowing
+users to create hrtimer triggers under /config/iio/triggers/hrtimer.
+
+e.g:
+
+$ mkdir /config/triggers/hrtimer/instance1
+$ rmdir /config/triggers/hrtimer/instance1
+
+Each trigger can have one or more attributes specific to the trigger type.
+
+3.2 "hrtimer" trigger types attributes
+
+"hrtimer" trigger type doesn't have any configurable attribute from /config dir.
+It does introduce the sampling_frequency attribute to trigger directory.
diff --git a/Documentation/infiniband/core_locking.txt b/Documentation/infiniband/core_locking.txt
index e1678542279a..4b1f36b6ada0 100644
--- a/Documentation/infiniband/core_locking.txt
+++ b/Documentation/infiniband/core_locking.txt
@@ -15,7 +15,6 @@ Sleeping and interrupt context
     modify_ah
     query_ah
     destroy_ah
-    bind_mw
     post_send
     post_recv
     poll_cq
@@ -31,7 +30,6 @@ Sleeping and interrupt context
     ib_modify_ah
     ib_query_ah
     ib_destroy_ah
-    ib_bind_mw
     ib_post_send
     ib_post_recv
     ib_req_notify_cq
diff --git a/Documentation/ioctl/botching-up-ioctls.txt b/Documentation/ioctl/botching-up-ioctls.txt
index 45fe78c58019..cc30b14791cb 100644
--- a/Documentation/ioctl/botching-up-ioctls.txt
+++ b/Documentation/ioctl/botching-up-ioctls.txt
@@ -122,7 +122,7 @@ Time, Waiting and Missing it
 ----------------------------
 
 GPUs do most everything asynchronously, so we have a need to time operations and
-wait for oustanding ones. This is really tricky business; at the moment none of
+wait for outstanding ones. This is really tricky business; at the moment none of
 the ioctls supported by the drm/i915 get this fully right, which means there's
 still tons more lessons to learn here.
 
@@ -146,7 +146,7 @@ still tons more lessons to learn here.
    ioctl restartable relative timeouts tend to be too coarse and can
    indefinitely extend your wait time due to rounding on each restart.
    Especially if your reference clock is something really slow like the display
-   frame counter. With a spec laywer hat on this isn't a bug since timeouts can
+   frame counter. With a spec lawyer hat on this isn't a bug since timeouts can
    always be extended - but users will surely hate you if their neat animations
    starts to stutter due to this.
 
@@ -176,7 +176,7 @@ entails its own little set of pitfalls:
 
  * Ensure that you have sufficient insulation between different clients. By
    default pick a private per-fd namespace which forces any sharing to be done
-   explictly. Only go with a more global per-device namespace if the objects
+   explicitly. Only go with a more global per-device namespace if the objects
    are truly device-unique. One counterexample in the drm modeset interfaces is
    that the per-device modeset objects like connectors share a namespace with
    framebuffer objects, which mostly are not shared at all. A separate
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 5a0f2bdc2cf9..8d5465d3fdef 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -245,7 +245,7 @@ Linux カーネルソースツリーの中に含まれる、きれいにし、�
 自己参照方式で、索引がついた web 形式で、ソースコードを参照することが
 できます。この最新の素晴しいカーネルコードのリポジトリは以下で見つかり
 ます-
-	http://lxr.linux.no/+trees
+	http://lxr.free-electrons.com/
 
 開発プロセス
 -----------------------
@@ -366,7 +366,6 @@ http://patchwork.kernel.org/ でリストされています。
 に全サブシステムツリーからほぼ毎日プルされてできる特別なテスト用のリ
 ポジトリが存在します-
        http://git.kernel.org/?p=linux/kernel/git/next/linux-next.git
-       http://linux.f-seidel.de/linux-next/pmwiki/
 
 このやり方によって、-next カーネルは次のマージ機会でどんなものがメイン
 ラインカーネルにマージされるか、おおまかなの展望を提供します。-next 
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt
index 08913361e054..fe217c1c2f7f 100644
--- a/Documentation/kernel-docs.txt
+++ b/Documentation/kernel-docs.txt
@@ -631,7 +631,7 @@
        between two versions of a file".
 
      * Name: "Cross-Referencing Linux"
-       URL: http://lxr.linux.no/source/
+       URL: http://lxr.free-electrons.com/
        Keywords: Browsing source code.
        Description: Another web-based Linux kernel source code browser.
        Lots of cross references to variables and functions. You can see
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 742f69d18fc8..9a53c929f017 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -472,6 +472,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
 
+	apic_extnmi=	[APIC,X86] External NMI delivery setting
+			Format: { bsp (default) | all | none }
+			bsp:  External NMI is delivered only to CPU 0
+			all:  External NMIs are broadcast to all CPUs as a
+			      backup of CPU 0
+			none: External NMI is masked for all CPUs. This is
+			      useful so that a dump capture kernel won't be
+			      shot down by NMI
+
 	autoconf=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
@@ -599,6 +608,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			cut the overhead, others just disable the usage. So
 			only cgroup_disable=memory is actually worthy}
 
+	cgroup.memory=	[KNL] Pass options to the cgroup memory controller.
+			Format: <string>
+			nosocket -- Disable socket memory accounting.
+			nokmem -- Disable kernel memory accounting.
+
 	checkreqprot	[SELINUX] Set initial checkreqprot flag value.
 			Format: { "0" | "1" }
 			See security/selinux/Kconfig help text.
@@ -721,16 +735,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 		uart[8250],io,<addr>[,options]
 		uart[8250],mmio,<addr>[,options]
+		uart[8250],mmio16,<addr>[,options]
 		uart[8250],mmio32,<addr>[,options]
 		uart[8250],0x<addr>[,options]
 			Start an early, polled-mode console on the 8250/16550
 			UART at the specified I/O port or MMIO address,
 			switching to the matching ttyS device later.
 			MMIO inter-register address stride is either 8-bit
-			(mmio) or 32-bit (mmio32).
-			If none of [io|mmio|mmio32], <addr> is assumed to be
-			equivalent to 'mmio'. 'options' are specified in the
-			same format described for ttyS above; if unspecified,
+			(mmio), 16-bit (mmio16), or 32-bit (mmio32).
+			If none of [io|mmio|mmio16|mmio32], <addr> is assumed
+			to be equivalent to 'mmio'. 'options' are specified in
+			the same format described for ttyS above; if unspecified,
 			the h/w is not re-initialized.
 
 		hvc<n>	Use the hypervisor console device <n>. This is for
@@ -1002,10 +1017,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			unspecified, the h/w is not initialized.
 
 		pl011,<addr>
+		pl011,mmio32,<addr>
 			Start an early, polled-mode console on a pl011 serial
 			port at the specified address. The pl011 serial port
 			must already be setup and configured. Options are not
-			yet supported.
+			yet supported.  If 'mmio32' is specified, then only
+			the driver will use only 32-bit accessors to read/write
+			the device registers.
 
 		msm_serial,<addr>
 			Start an early, polled-mode console on an msm serial
@@ -1436,6 +1454,41 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			In such case C2/C3 won't be used again.
 			idle=nomwait: Disable mwait for CPU C-states
 
+	ieee754=	[MIPS] Select IEEE Std 754 conformance mode
+			Format: { strict | legacy | 2008 | relaxed }
+			Default: strict
+
+			Choose which programs will be accepted for execution
+			based on the IEEE 754 NaN encoding(s) supported by
+			the FPU and the NaN encoding requested with the value
+			of an ELF file header flag individually set by each
+			binary.  Hardware implementations are permitted to
+			support either or both of the legacy and the 2008 NaN
+			encoding mode.
+
+			Available settings are as follows:
+			strict	accept binaries that request a NaN encoding
+				supported by the FPU
+			legacy	only accept legacy-NaN binaries, if supported
+				by the FPU
+			2008	only accept 2008-NaN binaries, if supported
+				by the FPU
+			relaxed	accept any binaries regardless of whether
+				supported by the FPU
+
+			The FPU emulator is always able to support both NaN
+			encodings, so if no FPU hardware is present or it has
+			been disabled with 'nofpu', then the settings of
+			'legacy' and '2008' strap the emulator accordingly,
+			'relaxed' straps the emulator for both legacy-NaN and
+			2008-NaN, whereas 'strict' enables legacy-NaN only on
+			legacy processors and both NaN encodings on MIPS32 or
+			MIPS64 CPUs.
+
+			The setting for ABS.fmt/NEG.fmt instruction execution
+			mode generally follows that for the NaN encoding,
+			except where unsupported by hardware.
+
 	ignore_loglevel	[KNL]
 			Ignore loglevel setting - this will print /all/
 			kernel messages to the console. Useful for debugging.
@@ -1443,6 +1496,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			could change it dynamically, usually by
 			/sys/module/printk/parameters/ignore_loglevel.
 
+	ignore_rlimit_data
+			Ignore RLIMIT_DATA setting for data mappings,
+			print warning at first misuse.  Can be changed via
+			/sys/module/kernel/parameters/ignore_rlimit_data.
+
 	ihash_entries=	[KNL]
 			Set number of hash buckets for inode cache.
 
@@ -2575,8 +2633,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	notsc		[BUGS=X86-32] Disable Time Stamp Counter
 
-	nousb		[USB] Disable the USB subsystem
-
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
                         soft-lockup and NMI watchdog (hard-lockup).
 
@@ -2733,10 +2789,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				hardware access methods are allowed. Use this
 				if you experience crashes upon bootup and you
 				suspect they are caused by the BIOS.
-		conf1		[X86] Force use of PCI Configuration
-				Mechanism 1.
-		conf2		[X86] Force use of PCI Configuration
-				Mechanism 2.
+		conf1		[X86] Force use of PCI Configuration Access
+				Mechanism 1 (config address in IO port 0xCF8,
+				data in IO port 0xCFC, both 32-bit).
+		conf2		[X86] Force use of PCI Configuration Access
+				Mechanism 2 (IO port 0xCF8 is an 8-bit port for
+				the function, IO port 0xCFA, also 8-bit, sets
+				bus number. The config space is then accessed
+				through ports 0xC000-0xCFFF).
+				See http://wiki.osdev.org/PCI for more info
+				on the configuration access mechanisms.
 		noaer		[PCIE] If the PCIEAER kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of PCIE advanced error reporting.
@@ -2978,6 +3040,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			may be specified.
 			Format: <port>,<port>....
 
+	ppc_strict_facility_enable
+			[PPC] This option catches any kernel floating point,
+			Altivec, VSX and SPE outside of regions specifically
+			allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
+			There is some performance impact when enabling this.
+
 	print-fatal-signals=
 			[KNL] debug: print fatal signals
 
@@ -3050,9 +3118,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	raid=		[HW,RAID]
 			See Documentation/md.txt.
 
-	ramdisk_blocksize=	[RAM]
-			See Documentation/blockdev/ramdisk.txt.
-
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
@@ -3296,18 +3361,35 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	rcutorture.verbose= [KNL]
 			Enable additional printk() statements.
 
+	rcupdate.rcu_cpu_stall_suppress= [KNL]
+			Suppress RCU CPU stall warning messages.
+
+	rcupdate.rcu_cpu_stall_timeout= [KNL]
+			Set timeout for RCU CPU stall warning messages.
+
 	rcupdate.rcu_expedited= [KNL]
 			Use expedited grace-period primitives, for
 			example, synchronize_rcu_expedited() instead
 			of synchronize_rcu().  This reduces latency,
 			but can increase CPU utilization, degrade
 			real-time latency, and degrade energy efficiency.
-
-	rcupdate.rcu_cpu_stall_suppress= [KNL]
-			Suppress RCU CPU stall warning messages.
-
-	rcupdate.rcu_cpu_stall_timeout= [KNL]
-			Set timeout for RCU CPU stall warning messages.
+			No effect on CONFIG_TINY_RCU kernels.
+
+	rcupdate.rcu_normal= [KNL]
+			Use only normal grace-period primitives,
+			for example, synchronize_rcu() instead of
+			synchronize_rcu_expedited().  This improves
+			real-time latency, CPU utilization, and
+			energy efficiency, but can expose users to
+			increased grace-period latency.  This parameter
+			overrides rcupdate.rcu_expedited.  No effect on
+			CONFIG_TINY_RCU kernels.
+
+	rcupdate.rcu_normal_after_boot= [KNL]
+			Once boot has completed (that is, after
+			rcu_end_inkernel_boot() has been invoked), use
+			only normal grace-period primitives.  No effect
+			on CONFIG_TINY_RCU kernels.
 
 	rcupdate.rcu_task_stall_timeout= [KNL]
 			Set timeout in jiffies for RCU task stall warning
@@ -3874,6 +3956,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	usbcore.usbfs_snoop=
 			[USB] Set to log all usbfs traffic (default 0 = off).
 
+	usbcore.usbfs_snoop_max=
+			[USB] Maximum number of bytes to snoop in each URB
+			(default = 65536).
+
 	usbcore.blinkenlights=
 			[USB] Set to cycle leds on hubs (default 0 = off).
 
@@ -3894,6 +3980,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                         USB_REQ_GET_DESCRIPTOR request in milliseconds
 			(default 5000 = 5.0 seconds).
 
+	usbcore.nousb	[USB] Disable the USB subsystem
+
 	usbhid.mousepoll=
 			[USBHID] The interval which mice are to be polled at.
 
@@ -4114,6 +4202,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			or other driver-specific files in the
 			Documentation/watchdog/ directory.
 
+	workqueue.watchdog_thresh=
+			If CONFIG_WQ_WATCHDOG is configured, workqueue can
+			warn stall conditions and dump internal state to
+			help debugging.  0 disables workqueue stall
+			detection; otherwise, it's the stall threshold
+			duration in seconds.  The default value is 30 and
+			it can be updated at runtime by writing to the
+			corresponding sysfs file.
+
 	workqueue.disable_numa
 			By default, all work items queued to unbound
 			workqueues are affine to the NUMA nodes they're
@@ -4138,6 +4235,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
index f4cbfe0ba108..edec3a3e648d 100644
--- a/Documentation/kernel-per-CPU-kthreads.txt
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -90,7 +90,7 @@ BLOCK_SOFTIRQ:  Do all of the following:
 	from being initiated from tasks that might run on the CPU to
 	be de-jittered.  (It is OK to force this CPU offline and then
 	bring it back online before you start your application.)
-BLOCK_IOPOLL_SOFTIRQ:  Do all of the following:
+IRQ_POLL_SOFTIRQ:  Do all of the following:
 1.	Force block-device interrupts onto some other CPU.
 2.	Initiate any block I/O and block-I/O polling on other CPUs.
 3.	Once your application has started, prevent CPU-hotplug operations
diff --git a/Documentation/ko_KR/HOWTO b/Documentation/ko_KR/HOWTO
index dc2ff8f611e0..1aef53e6cb98 100644
--- a/Documentation/ko_KR/HOWTO
+++ b/Documentation/ko_KR/HOWTO
@@ -213,7 +213,7 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
 것은 Linux Cross-Reference project이며 그것은 자기 참조 방식이며
 소스코드를 인덱스된 웹 페이지들의 형태로 보여준다. 최신의 멋진 커널
 코드 저장소는 다음을 통하여 참조할 수 있다.
-      http://lxr.linux.no/+trees
+      http://lxr.free-electrons.com/
 
 
 개발 프로세스
@@ -222,16 +222,16 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
 리눅스 커널 개발 프로세스는 현재 몇몇 다른 메인 커널 "브랜치들"과
 서브시스템에 특화된 커널 브랜치들로 구성된다. 몇몇 다른 메인
 브랜치들은 다음과 같다.
-  - main 3.x 커널 트리
-  - 3.x.y - 안정된 커널 트리
-  - 3.x -git 커널 패치들
+  - main 4.x 커널 트리
+  - 4.x.y - 안정된 커널 트리
+  - 4.x -git 커널 패치들
   - 서브시스템을 위한 커널 트리들과 패치들
-  - 3.x - 통합 테스트를 위한 next 커널 트리
+  - 4.x - 통합 테스트를 위한 next 커널 트리
 
-3.x 커널 트리
+4.x 커널 트리
 ---------------
 
-3.x 커널들은 Linux Torvalds가 관리하며 kernel.org의 pub/linux/kernel/v3.x/
+4.x 커널들은 Linux Torvalds가 관리하며 kernel.org의 pub/linux/kernel/v4.x/
 디렉토리에서 참조될 수 있다.개발 프로세스는 다음과 같다.
   - 새로운 커널이 배포되자마자 2주의 시간이 주어진다. 이 기간동은
     메인테이너들은 큰 diff들을 Linus에게 제출할 수 있다. 대개 이 패치들은
@@ -262,20 +262,20 @@ Andrew Morton의 글이 있다.
          버그의 상황에 따라 배포되는 것이지 미리정해 놓은 시간에 따라
          배포되는 것은 아니기 때문이다."
 
-3.x.y - 안정 커널 트리
+4.x.y - 안정 커널 트리
 ------------------------
 
-3 자리 숫자로 이루어진 버젼의 커널들은 -stable 커널들이다. 그것들은 3.x
+3 자리 숫자로 이루어진 버젼의 커널들은 -stable 커널들이다. 그것들은 4.x
 커널에서 발견된 큰 회귀들이나 보안 문제들 중 비교적 작고 중요한 수정들을
 포함한다.
 
 이것은 가장 최근의 안정적인 커널을 원하는 사용자에게 추천되는 브랜치이며,
 개발/실험적 버젼을 테스트하는 것을 돕고자 하는 사용자들과는 별로 관련이 없다.
 
-어떤 3.x.y 커널도 사용할 수 없다면 그때는 가장 높은 숫자의 3.x
+어떤 4.x.y 커널도 사용할 수 없다면 그때는 가장 높은 숫자의 4.x
 커널이 현재의 안정 커널이다.
 
-3.x.y는 "stable" 팀<stable@vger.kernel.org>에 의해 관리되며 거의 매번 격주로
+4.x.y는 "stable" 팀<stable@vger.kernel.org>에 의해 관리되며 거의 매번 격주로
 배포된다.
 
 커널 트리 문서들 내에 Documentation/stable_kernel_rules.txt 파일은 어떤
@@ -283,7 +283,7 @@ Andrew Morton의 글이 있다.
 진행되는지를 설명한다.
 
 
-3.x -git 패치들
+4.x -git 패치들
 ------------------
 git 저장소(그러므로 -git이라는 이름이 붙음)에는 날마다 관리되는 Linus의
 커널 트리의 snapshot 들이 있다. 이 패치들은 일반적으로 날마다 배포되며
@@ -312,13 +312,12 @@ Linus의 트리의 현재 상태를 나타낸다. 이 패치들은 정상적인�
 대부분의 이러한 patchwork 사이트는 http://patchwork.kernel.org/ 또는
 http://patchwork.ozlabs.org/ 에 나열되어 있다.
 
-3.x - 통합 테스트를 위한 next 커널 트리
+4.x - 통합 테스트를 위한 next 커널 트리
 -----------------------------------------
-서브시스템 트리들의 변경사항들은 mainline 3.x 트리로 들어오기 전에 통합
+서브시스템 트리들의 변경사항들은 mainline 4.x 트리로 들어오기 전에 통합
 테스트를 거쳐야 한다. 이런 목적으로, 모든 서브시스템 트리의 변경사항을 거의
 매일 받아가는 특수한 테스트 저장소가 존재한다:
        http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
-       http://linux.f-seidel.de/linux-next/pmwiki/
 
 이런 식으로, -next 커널을 통해 다음 머지 기간에 메인라인 커널에 어떤 변경이
 가해질 것인지 간략히 알 수 있다. 모험심 강한 테스터라면 -next 커널에서 테스트를
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 62261c04060a..d406d98339b2 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -52,6 +52,19 @@ above leaves scope for further attributes should they be needed. If sections
 of the name don't apply, just leave that section blank.
 
 
+Brightness setting API
+======================
+
+LED subsystem core exposes following API for setting brightness:
+
+    - led_set_brightness : it is guaranteed not to sleep, passing LED_OFF stops
+		blinking,
+    - led_set_brightness_sync : for use cases when immediate effect is desired -
+		it can block the caller for the time required for accessing
+		device registers and can sleep, passing LED_OFF stops hardware
+		blinking, returns -EBUSY if software blink fallback is enabled.
+
+
 Hardware accelerated blink of LEDs
 ==================================
 
diff --git a/Documentation/md-cluster.txt b/Documentation/md-cluster.txt
index 1b794369e03a..c100c7163507 100644
--- a/Documentation/md-cluster.txt
+++ b/Documentation/md-cluster.txt
@@ -3,7 +3,7 @@ The cluster MD is a shared-device RAID for a cluster.
 
 1. On-disk format
 
-Separate write-intent-bitmap are used for each cluster node.
+Separate write-intent-bitmaps are used for each cluster node.
 The bitmaps record all writes that may have been started on that node,
 and may not yet have finished. The on-disk layout is:
 
@@ -14,117 +14,161 @@ and may not yet have finished. The on-disk layout is:
 | bm super[2] + bits  | bm bits [2, contd]  | bm super[3] + bits  |
 | bm bits [3, contd]  |                     |                     |
 
-During "normal" functioning we assume the filesystem ensures that only one
-node writes to any given block at a time, so a write
-request will
+During "normal" functioning we assume the filesystem ensures that only
+one node writes to any given block at a time, so a write request will
+
  - set the appropriate bit (if not already set)
  - commit the write to all mirrors
  - schedule the bit to be cleared after a timeout.
 
-Reads are just handled normally.  It is up to the filesystem to
-ensure one node doesn't read from a location where another node (or the same
+Reads are just handled normally. It is up to the filesystem to ensure
+one node doesn't read from a location where another node (or the same
 node) is writing.
 
 
 2. DLM Locks for management
 
-There are two locks for managing the device:
+There are three groups of locks for managing the device:
 
 2.1 Bitmap lock resource (bm_lockres)
 
- The bm_lockres protects individual node bitmaps. They are named in the
- form bitmap001 for node 1, bitmap002 for node and so on. When a node
- joins the cluster, it acquires the lock in PW mode and it stays so
- during the lifetime the node is part of the cluster. The lock resource
- number is based on the slot number returned by the DLM subsystem. Since
- DLM starts node count from one and bitmap slots start from zero, one is
- subtracted from the DLM slot number to arrive at the bitmap slot number.
+ The bm_lockres protects individual node bitmaps. They are named in
+ the form bitmap000 for node 1, bitmap001 for node 2 and so on. When a
+ node joins the cluster, it acquires the lock in PW mode and it stays
+ so during the lifetime the node is part of the cluster. The lock
+ resource number is based on the slot number returned by the DLM
+ subsystem. Since DLM starts node count from one and bitmap slots
+ start from zero, one is subtracted from the DLM slot number to arrive
+ at the bitmap slot number.
+
+ The LVB of the bitmap lock for a particular node records the range
+ of sectors that are being re-synced by that node.  No other
+ node may write to those sectors.  This is used when a new nodes
+ joins the cluster.
+
+2.2 Message passing locks
+
+ Each node has to communicate with other nodes when starting or ending
+ resync, and for metadata superblock updates.  This communication is
+ managed through three locks: "token", "message", and "ack", together
+ with the Lock Value Block (LVB) of one of the "message" lock.
+
+2.3 new-device management
+
+ A single lock: "no-new-dev" is used to co-ordinate the addition of
+ new devices - this must be synchronized across the array.
+ Normally all nodes hold a concurrent-read lock on this device.
 
 3. Communication
 
-Each node has to communicate with other nodes when starting or ending
-resync, and metadata superblock updates.
+ Messages can be broadcast to all nodes, and the sender waits for all
+ other nodes to acknowledge the message before proceeding.  Only one
+ message can be processed at a time.
 
 3.1 Message Types
 
- There are 3 types, of messages which are passed
+ There are six types of messages which are passed:
 
- 3.1.1 METADATA_UPDATED: informs other nodes that the metadata has been
-   updated, and the node must re-read the md superblock. This is performed
-   synchronously.
+ 3.1.1 METADATA_UPDATED: informs other nodes that the metadata has
+   been updated, and the node must re-read the md superblock. This is
+   performed synchronously. It is primarily used to signal device
+   failure.
 
- 3.1.2 RESYNC: informs other nodes that a resync is initiated or ended
-   so that each node may suspend or resume the region.
+ 3.1.2 RESYNCING: informs other nodes that a resync is initiated or
+   ended so that each node may suspend or resume the region.  Each
+   RESYNCING message identifies a range of the devices that the
+   sending node is about to resync. This over-rides any pervious
+   notification from that node: only one ranged can be resynced at a
+   time per-node.
+
+ 3.1.3 NEWDISK: informs other nodes that a device is being added to
+   the array. Message contains an identifier for that device.  See
+   below for further details.
+
+ 3.1.4 REMOVE: A failed or spare device is being removed from the
+   array. The slot-number of the device is included in the message.
+
+ 3.1.5 RE_ADD: A failed device is being re-activated - the assumption
+   is that it has been determined to be working again.
+
+ 3.1.6 BITMAP_NEEDS_SYNC: if a node is stopped locally but the bitmap
+   isn't clean, then another node is informed to take the ownership of
+   resync.
 
 3.2 Communication mechanism
 
  The DLM LVB is used to communicate within nodes of the cluster. There
  are three resources used for the purpose:
 
-  3.2.1 Token: The resource which protects the entire communication
+  3.2.1 token: The resource which protects the entire communication
    system. The node having the token resource is allowed to
    communicate.
 
-  3.2.2 Message: The lock resource which carries the data to
+  3.2.2 message: The lock resource which carries the data to
    communicate.
 
-  3.2.3 Ack: The resource, acquiring which means the message has been
+  3.2.3 ack: The resource, acquiring which means the message has been
    acknowledged by all nodes in the cluster. The BAST of the resource
-   is used to inform the receive node that a node wants to communicate.
+   is used to inform the receiving node that a node wants to
+   communicate.
 
 The algorithm is:
 
- 1. receive status
+ 1. receive status - all nodes have concurrent-reader lock on "ack".
 
-   sender                         receiver                   receiver
-   ACK:CR                          ACK:CR                     ACK:CR
+   sender                         receiver                 receiver
+   "ack":CR                       "ack":CR                 "ack":CR
 
- 2. sender get EX of TOKEN
-    sender get EX of MESSAGE
+ 2. sender get EX on "token"
+    sender get EX on "message"
     sender                        receiver                 receiver
-    TOKEN:EX                       ACK:CR                   ACK:CR
-    MESSAGE:EX
-    ACK:CR
+    "token":EX                    "ack":CR                 "ack":CR
+    "message":EX
+    "ack":CR
 
-    Sender checks that it still needs to send a message. Messages received
-    or other events that happened while waiting for the TOKEN may have made
-    this message inappropriate or redundant.
+    Sender checks that it still needs to send a message. Messages
+    received or other events that happened while waiting for the
+    "token" may have made this message inappropriate or redundant.
 
- 3. sender write LVB.
-    sender down-convert MESSAGE from EX to CW
-    sender try to get EX of ACK
-    [ wait until all receiver has *processed* the MESSAGE ]
+ 3. sender writes LVB.
+    sender down-convert "message" from EX to CW
+    sender try to get EX of "ack"
+    [ wait until all receivers have *processed* the "message" ]
 
-                                     [ triggered by bast of ACK ]
-                                     receiver get CR of MESSAGE
+                                     [ triggered by bast of "ack" ]
+                                     receiver get CR on "message"
                                      receiver read LVB
                                      receiver processes the message
                                      [ wait finish ]
-                                     receiver release ACK
-
-   sender                         receiver                   receiver
-   TOKEN:EX                       MESSAGE:CR                 MESSAGE:CR
-   MESSAGE:CR
-   ACK:EX
-
- 4. triggered by grant of EX on ACK (indicating all receivers have processed
-    message)
-    sender down-convert ACK from EX to CR
-    sender release MESSAGE
-    sender release TOKEN
-                               receiver upconvert to PR of MESSAGE
-                               receiver get CR of ACK
-                               receiver release MESSAGE
+                                     receiver releases "ack"
+                                     receiver tries to get PR on "message"
+
+   sender                         receiver                  receiver
+   "token":EX                     "message":CR              "message":CR
+   "message":CW
+   "ack":EX
+
+ 4. triggered by grant of EX on "ack" (indicating all receivers
+    have processed message)
+    sender down-converts "ack" from EX to CR
+    sender releases "message"
+    sender releases "token"
+                               receiver upconvert to PR on "message"
+                               receiver get CR of "ack"
+                               receiver release "message"
 
    sender                      receiver                   receiver
-   ACK:CR                       ACK:CR                     ACK:CR
+   "ack":CR                    "ack":CR                   "ack":CR
 
 
 4. Handling Failures
 
 4.1 Node Failure
- When a node fails, the DLM informs the cluster with the slot. The node
- starts a cluster recovery thread. The cluster recovery thread:
+
+ When a node fails, the DLM informs the cluster with the slot
+ number. The node starts a cluster recovery thread. The cluster
+ recovery thread:
+
 	- acquires the bitmap<number> lock of the failed node
 	- opens the bitmap
 	- reads the bitmap of the failed node
@@ -132,45 +176,143 @@ The algorithm is:
 	- cleans the bitmap of the failed node
 	- releases bitmap<number> lock of the failed node
 	- initiates resync of the bitmap on the current node
+		md_check_recovery is invoked within recover_bitmaps,
+		then md_check_recovery -> metadata_update_start/finish,
+		it will lock the communication by lock_comm.
+		Which means when one node is resyncing it blocks all
+		other nodes from writing anywhere on the array.
 
- The resync process, is the regular md resync. However, in a clustered
+ The resync process is the regular md resync. However, in a clustered
  environment when a resync is performed, it needs to tell other nodes
  of the areas which are suspended. Before a resync starts, the node
- send out RESYNC_START with the (lo,hi) range of the area which needs
- to be suspended. Each node maintains a suspend_list, which contains
- the list  of ranges which are currently suspended. On receiving
- RESYNC_START, the node adds the range to the suspend_list. Similarly,
- when the node performing resync finishes, it send RESYNC_FINISHED
- to other nodes and other nodes remove the corresponding entry from
- the suspend_list.
+ send out RESYNCING with the (lo,hi) range of the area which needs to
+ be suspended. Each node maintains a suspend_list, which contains the
+ list of ranges which are currently suspended. On receiving RESYNCING,
+ the node adds the range to the suspend_list. Similarly, when the node
+ performing resync finishes, it sends RESYNCING with an empty range to
+ other nodes and other nodes remove the corresponding entry from the
+ suspend_list.
 
- A helper function, should_suspend() can be used to check if a particular
- I/O range should be suspended or not.
+ A helper function, ->area_resyncing() can be used to check if a
+ particular I/O range should be suspended or not.
 
 4.2 Device Failure
+
  Device failures are handled and communicated with the metadata update
- routine.
+ routine.  When a node detects a device failure it does not allow
+ any further writes to that device until the failure has been
+ acknowledged by all other nodes.
 
 5. Adding a new Device
-For adding a new device, it is necessary that all nodes "see" the new device
-to be added. For this, the following algorithm is used:
+
+ For adding a new device, it is necessary that all nodes "see" the new
+ device to be added. For this, the following algorithm is used:
 
     1. Node 1 issues mdadm --manage /dev/mdX --add /dev/sdYY which issues
-       ioctl(ADD_NEW_DISC with disc.state set to MD_DISK_CLUSTER_ADD)
-    2. Node 1 sends NEWDISK with uuid and slot number
+       ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CLUSTER_ADD)
+    2. Node 1 sends a NEWDISK message with uuid and slot number
     3. Other nodes issue kobject_uevent_env with uuid and slot number
        (Steps 4,5 could be a udev rule)
     4. In userspace, the node searches for the disk, perhaps
        using blkid -t SUB_UUID=""
-    5. Other nodes issue either of the following depending on whether the disk
-       was found:
+    5. Other nodes issue either of the following depending on whether
+       the disk was found:
        ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CANDIDATE and
-                disc.number set to slot number)
+             disc.number set to slot number)
        ioctl(CLUSTERED_DISK_NACK)
-    6. Other nodes drop lock on no-new-devs (CR) if device is found
-    7. Node 1 attempts EX lock on no-new-devs
-    8. If node 1 gets the lock, it sends METADATA_UPDATED after unmarking the disk
-       as SpareLocal
-    9. If not (get no-new-dev lock), it fails the operation and sends METADATA_UPDATED
-    10. Other nodes get the information whether a disk is added or not
-	by the following METADATA_UPDATED.
+    6. Other nodes drop lock on "no-new-devs" (CR) if device is found
+    7. Node 1 attempts EX lock on "no-new-dev"
+    8. If node 1 gets the lock, it sends METADATA_UPDATED after
+       unmarking the disk as SpareLocal
+    9. If not (get "no-new-dev" lock), it fails the operation and sends
+       METADATA_UPDATED.
+   10. Other nodes get the information whether a disk is added or not
+       by the following METADATA_UPDATED.
+
+6. Module interface.
+
+ There are 17 call-backs which the md core can make to the cluster
+ module.  Understanding these can give a good overview of the whole
+ process.
+
+6.1 join(nodes) and leave()
+
+ These are called when an array is started with a clustered bitmap,
+ and when the array is stopped.  join() ensures the cluster is
+ available and initializes the various resources.
+ Only the first 'nodes' nodes in the cluster can use the array.
+
+6.2 slot_number()
+
+ Reports the slot number advised by the cluster infrastructure.
+ Range is from 0 to nodes-1.
+
+6.3 resync_info_update()
+
+ This updates the resync range that is stored in the bitmap lock.
+ The starting point is updated as the resync progresses.  The
+ end point is always the end of the array.
+ It does *not* send a RESYNCING message.
+
+6.4 resync_start(), resync_finish()
+
+ These are called when resync/recovery/reshape starts or stops.
+ They update the resyncing range in the bitmap lock and also
+ send a RESYNCING message.  resync_start reports the whole
+ array as resyncing, resync_finish reports none of it.
+
+ resync_finish() also sends a BITMAP_NEEDS_SYNC message which
+ allows some other node to take over.
+
+6.5 metadata_update_start(), metadata_update_finish(),
+    metadata_update_cancel().
+
+ metadata_update_start is used to get exclusive access to
+ the metadata.  If a change is still needed once that access is
+ gained, metadata_update_finish() will send a METADATA_UPDATE
+ message to all other nodes, otherwise metadata_update_cancel()
+ can be used to release the lock.
+
+6.6 area_resyncing()
+
+ This combines two elements of functionality.
+
+ Firstly, it will check if any node is currently resyncing
+ anything in a given range of sectors.  If any resync is found,
+ then the caller will avoid writing or read-balancing in that
+ range.
+
+ Secondly, while node recovery is happening it reports that
+ all areas are resyncing for READ requests.  This avoids races
+ between the cluster-filesystem and the cluster-RAID handling
+ a node failure.
+
+6.7 add_new_disk_start(), add_new_disk_finish(), new_disk_ack()
+
+ These are used to manage the new-disk protocol described above.
+ When a new device is added, add_new_disk_start() is called before
+ it is bound to the array and, if that succeeds, add_new_disk_finish()
+ is called the device is fully added.
+
+ When a device is added in acknowledgement to a previous
+ request, or when the device is declared "unavailable",
+ new_disk_ack() is called.
+
+6.8 remove_disk()
+
+ This is called when a spare or failed device is removed from
+ the array.  It causes a REMOVE message to be send to other nodes.
+
+6.9 gather_bitmaps()
+
+ This sends a RE_ADD message to all other nodes and then
+ gathers bitmap information from all bitmaps.  This combined
+ bitmap is then used to recovery the re-added device.
+
+6.10 lock_all_bitmaps() and unlock_all_bitmaps()
+
+ These are called when change bitmap to none. If a node plans
+ to clear the cluster raid's bitmap, it need to make sure no other
+ nodes are using the raid which is achieved by lock all bitmap
+ locks within the cluster, and also those locks are unlocked
+ accordingly.
diff --git a/Documentation/media-framework.txt b/Documentation/media-framework.txt
deleted file mode 100644
index f552a75c0e70..000000000000
--- a/Documentation/media-framework.txt
+++ /dev/null
@@ -1,372 +0,0 @@
-Linux kernel media framework
-============================
-
-This document describes the Linux kernel media framework, its data structures,
-functions and their usage.
-
-
-Introduction
-------------
-
-The media controller API is documented in DocBook format in
-Documentation/DocBook/media/v4l/media-controller.xml. This document will focus
-on the kernel-side implementation of the media framework.
-
-
-Abstract media device model
----------------------------
-
-Discovering a device internal topology, and configuring it at runtime, is one
-of the goals of the media framework. To achieve this, hardware devices are
-modelled as an oriented graph of building blocks called entities connected
-through pads.
-
-An entity is a basic media hardware building block. It can correspond to
-a large variety of logical blocks such as physical hardware devices
-(CMOS sensor for instance), logical hardware devices (a building block
-in a System-on-Chip image processing pipeline), DMA channels or physical
-connectors.
-
-A pad is a connection endpoint through which an entity can interact with
-other entities. Data (not restricted to video) produced by an entity
-flows from the entity's output to one or more entity inputs. Pads should
-not be confused with physical pins at chip boundaries.
-
-A link is a point-to-point oriented connection between two pads, either
-on the same entity or on different entities. Data flows from a source
-pad to a sink pad.
-
-
-Media device
-------------
-
-A media device is represented by a struct media_device instance, defined in
-include/media/media-device.h. Allocation of the structure is handled by the
-media device driver, usually by embedding the media_device instance in a
-larger driver-specific structure.
-
-Drivers register media device instances by calling
-
-	media_device_register(struct media_device *mdev);
-
-The caller is responsible for initializing the media_device structure before
-registration. The following fields must be set:
-
- - dev must point to the parent device (usually a pci_dev, usb_interface or
-   platform_device instance).
-
- - model must be filled with the device model name as a NUL-terminated UTF-8
-   string. The device/model revision must not be stored in this field.
-
-The following fields are optional:
-
- - serial is a unique serial number stored as a NUL-terminated ASCII string.
-   The field is big enough to store a GUID in text form. If the hardware
-   doesn't provide a unique serial number this field must be left empty.
-
- - bus_info represents the location of the device in the system as a
-   NUL-terminated ASCII string. For PCI/PCIe devices bus_info must be set to
-   "PCI:" (or "PCIe:") followed by the value of pci_name(). For USB devices,
-   the usb_make_path() function must be used. This field is used by
-   applications to distinguish between otherwise identical devices that don't
-   provide a serial number.
-
- - hw_revision is the hardware device revision in a driver-specific format.
-   When possible the revision should be formatted with the KERNEL_VERSION
-   macro.
-
- - driver_version is formatted with the KERNEL_VERSION macro. The version
-   minor must be incremented when new features are added to the userspace API
-   without breaking binary compatibility. The version major must be
-   incremented when binary compatibility is broken.
-
-Upon successful registration a character device named media[0-9]+ is created.
-The device major and minor numbers are dynamic. The model name is exported as
-a sysfs attribute.
-
-Drivers unregister media device instances by calling
-
-	media_device_unregister(struct media_device *mdev);
-
-Unregistering a media device that hasn't been registered is *NOT* safe.
-
-
-Entities, pads and links
-------------------------
-
-- Entities
-
-Entities are represented by a struct media_entity instance, defined in
-include/media/media-entity.h. The structure is usually embedded into a
-higher-level structure, such as a v4l2_subdev or video_device instance,
-although drivers can allocate entities directly.
-
-Drivers initialize entities by calling
-
-	media_entity_init(struct media_entity *entity, u16 num_pads,
-			  struct media_pad *pads, u16 extra_links);
-
-The media_entity name, type, flags, revision and group_id fields can be
-initialized before or after calling media_entity_init. Entities embedded in
-higher-level standard structures can have some of those fields set by the
-higher-level framework.
-
-As the number of pads is known in advance, the pads array is not allocated
-dynamically but is managed by the entity driver. Most drivers will embed the
-pads array in a driver-specific structure, avoiding dynamic allocation.
-
-Drivers must set the direction of every pad in the pads array before calling
-media_entity_init. The function will initialize the other pads fields.
-
-Unlike the number of pads, the total number of links isn't always known in
-advance by the entity driver. As an initial estimate, media_entity_init
-pre-allocates a number of links equal to the number of pads plus an optional
-number of extra links. The links array will be reallocated if it grows beyond
-the initial estimate.
-
-Drivers register entities with a media device by calling
-
-	media_device_register_entity(struct media_device *mdev,
-				     struct media_entity *entity);
-
-Entities are identified by a unique positive integer ID. Drivers can provide an
-ID by filling the media_entity id field prior to registration, or request the
-media controller framework to assign an ID automatically. Drivers that provide
-IDs manually must ensure that all IDs are unique. IDs are not guaranteed to be
-contiguous even when they are all assigned automatically by the framework.
-
-Drivers unregister entities by calling
-
-	media_device_unregister_entity(struct media_entity *entity);
-
-Unregistering an entity will not change the IDs of the other entities, and the
-ID will never be reused for a newly registered entity.
-
-When a media device is unregistered, all its entities are unregistered
-automatically. No manual entities unregistration is then required.
-
-Drivers free resources associated with an entity by calling
-
-	media_entity_cleanup(struct media_entity *entity);
-
-This function must be called during the cleanup phase after unregistering the
-entity. Note that the media_entity instance itself must be freed explicitly by
-the driver if required.
-
-Entities have flags that describe the entity capabilities and state.
-
-	MEDIA_ENT_FL_DEFAULT indicates the default entity for a given type.
-	This can be used to report the default audio and video devices or the
-	default camera sensor.
-
-Logical entity groups can be defined by setting the group ID of all member
-entities to the same non-zero value. An entity group serves no purpose in the
-kernel, but is reported to userspace during entities enumeration. The group_id
-field belongs to the media device driver and must not by touched by entity
-drivers.
-
-Media device drivers should define groups if several entities are logically
-bound together. Example usages include reporting
-
-	- ALSA, VBI and video nodes that carry the same media stream
-	- lens and flash controllers associated with a sensor
-
-- Pads
-
-Pads are represented by a struct media_pad instance, defined in
-include/media/media-entity.h. Each entity stores its pads in a pads array
-managed by the entity driver. Drivers usually embed the array in a
-driver-specific structure.
-
-Pads are identified by their entity and their 0-based index in the pads array.
-Both information are stored in the media_pad structure, making the media_pad
-pointer the canonical way to store and pass link references.
-
-Pads have flags that describe the pad capabilities and state.
-
-	MEDIA_PAD_FL_SINK indicates that the pad supports sinking data.
-	MEDIA_PAD_FL_SOURCE indicates that the pad supports sourcing data.
-
-One and only one of MEDIA_PAD_FL_SINK and MEDIA_PAD_FL_SOURCE must be set for
-each pad.
-
-- Links
-
-Links are represented by a struct media_link instance, defined in
-include/media/media-entity.h. Each entity stores all links originating at or
-targeting any of its pads in a links array. A given link is thus stored
-twice, once in the source entity and once in the target entity. The array is
-pre-allocated and grows dynamically as needed.
-
-Drivers create links by calling
-
-	media_entity_create_link(struct media_entity *source, u16 source_pad,
-				 struct media_entity *sink,   u16 sink_pad,
-				 u32 flags);
-
-An entry in the link array of each entity is allocated and stores pointers
-to source and sink pads.
-
-Links have flags that describe the link capabilities and state.
-
-	MEDIA_LNK_FL_ENABLED indicates that the link is enabled and can be used
-	to transfer media data. When two or more links target a sink pad, only
-	one of them can be enabled at a time.
-	MEDIA_LNK_FL_IMMUTABLE indicates that the link enabled state can't be
-	modified at runtime. If MEDIA_LNK_FL_IMMUTABLE is set, then
-	MEDIA_LNK_FL_ENABLED must also be set since an immutable link is always
-	enabled.
-
-
-Graph traversal
----------------
-
-The media framework provides APIs to iterate over entities in a graph.
-
-To iterate over all entities belonging to a media device, drivers can use the
-media_device_for_each_entity macro, defined in include/media/media-device.h.
-
-	struct media_entity *entity;
-
-	media_device_for_each_entity(entity, mdev) {
-		/* entity will point to each entity in turn */
-		...
-	}
-
-Drivers might also need to iterate over all entities in a graph that can be
-reached only through enabled links starting at a given entity. The media
-framework provides a depth-first graph traversal API for that purpose.
-
-Note that graphs with cycles (whether directed or undirected) are *NOT*
-supported by the graph traversal API. To prevent infinite loops, the graph
-traversal code limits the maximum depth to MEDIA_ENTITY_ENUM_MAX_DEPTH,
-currently defined as 16.
-
-Drivers initiate a graph traversal by calling
-
-	media_entity_graph_walk_start(struct media_entity_graph *graph,
-				      struct media_entity *entity);
-
-The graph structure, provided by the caller, is initialized to start graph
-traversal at the given entity.
-
-Drivers can then retrieve the next entity by calling
-
-	media_entity_graph_walk_next(struct media_entity_graph *graph);
-
-When the graph traversal is complete the function will return NULL.
-
-Graph traversal can be interrupted at any moment. No cleanup function call is
-required and the graph structure can be freed normally.
-
-Helper functions can be used to find a link between two given pads, or a pad
-connected to another pad through an enabled link
-
-	media_entity_find_link(struct media_pad *source,
-			       struct media_pad *sink);
-
-	media_entity_remote_pad(struct media_pad *pad);
-
-Refer to the kerneldoc documentation for more information.
-
-
-Use count and power handling
-----------------------------
-
-Due to the wide differences between drivers regarding power management needs,
-the media controller does not implement power management. However, the
-media_entity structure includes a use_count field that media drivers can use to
-track the number of users of every entity for power management needs.
-
-The use_count field is owned by media drivers and must not be touched by entity
-drivers. Access to the field must be protected by the media device graph_mutex
-lock.
-
-
-Links setup
------------
-
-Link properties can be modified at runtime by calling
-
-	media_entity_setup_link(struct media_link *link, u32 flags);
-
-The flags argument contains the requested new link flags.
-
-The only configurable property is the ENABLED link flag to enable/disable a
-link. Links marked with the IMMUTABLE link flag can not be enabled or disabled.
-
-When a link is enabled or disabled, the media framework calls the
-link_setup operation for the two entities at the source and sink of the link,
-in that order. If the second link_setup call fails, another link_setup call is
-made on the first entity to restore the original link flags.
-
-Media device drivers can be notified of link setup operations by setting the
-media_device::link_notify pointer to a callback function. If provided, the
-notification callback will be called before enabling and after disabling
-links.
-
-Entity drivers must implement the link_setup operation if any of their links
-is non-immutable. The operation must either configure the hardware or store
-the configuration information to be applied later.
-
-Link configuration must not have any side effect on other links. If an enabled
-link at a sink pad prevents another link at the same pad from being enabled,
-the link_setup operation must return -EBUSY and can't implicitly disable the
-first enabled link.
-
-
-Pipelines and media streams
----------------------------
-
-When starting streaming, drivers must notify all entities in the pipeline to
-prevent link states from being modified during streaming by calling
-
-	media_entity_pipeline_start(struct media_entity *entity,
-				    struct media_pipeline *pipe);
-
-The function will mark all entities connected to the given entity through
-enabled links, either directly or indirectly, as streaming.
-
-The media_pipeline instance pointed to by the pipe argument will be stored in
-every entity in the pipeline. Drivers should embed the media_pipeline structure
-in higher-level pipeline structures and can then access the pipeline through
-the media_entity pipe field.
-
-Calls to media_entity_pipeline_start() can be nested. The pipeline pointer must
-be identical for all nested calls to the function.
-
-media_entity_pipeline_start() may return an error. In that case, it will
-clean up any of the changes it did by itself.
-
-When stopping the stream, drivers must notify the entities with
-
-	media_entity_pipeline_stop(struct media_entity *entity);
-
-If multiple calls to media_entity_pipeline_start() have been made the same
-number of media_entity_pipeline_stop() calls are required to stop streaming. The
-media_entity pipe field is reset to NULL on the last nested stop call.
-
-Link configuration will fail with -EBUSY by default if either end of the link is
-a streaming entity. Links that can be modified while streaming must be marked
-with the MEDIA_LNK_FL_DYNAMIC flag.
-
-If other operations need to be disallowed on streaming entities (such as
-changing entities configuration parameters) drivers can explicitly check the
-media_entity stream_count field to find out if an entity is streaming. This
-operation must be done with the media_device graph_mutex held.
-
-
-Link validation
----------------
-
-Link validation is performed by media_entity_pipeline_start() for any
-entity which has sink pads in the pipeline. The
-media_entity::link_validate() callback is used for that purpose. In
-link_validate() callback, entity driver should check that the properties of
-the source pad of the connected entity and its own sink pad match. It is up
-to the type of the entity (and in the end, the properties of the hardware)
-what matching actually means.
-
-Subsystems should facilitate link validation by providing subsystem specific
-helper functions to provide easy access for commonly needed information, and
-in the end provide a way to use driver-specific callbacks.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index aef9487303d0..904ee42d078e 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,7 +194,7 @@ There are some minimal guarantees that may be expected of a CPU:
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	WRITE_ONCE(Q, P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
+	Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
@@ -202,9 +202,9 @@ There are some minimal guarantees that may be expected of a CPU:
 
      and always in that order.  On most systems, smp_read_barrier_depends()
      does nothing, but it is required for DEC Alpha.  The READ_ONCE()
-     and WRITE_ONCE() are required to prevent compiler mischief.  Please
-     note that you should normally use something like rcu_dereference()
-     instead of open-coding smp_read_barrier_depends().
+     is required to prevent compiler mischief.  Please note that you
+     should normally use something like rcu_dereference() instead of
+     open-coding smp_read_barrier_depends().
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
@@ -1655,17 +1655,18 @@ macro is a good place to start looking.
 SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
 systems because it is assumed that a CPU will appear to be self-consistent,
 and will order overlapping accesses correctly with respect to itself.
+However, see the subsection on "Virtual Machine Guests" below.
 
 [!] Note that SMP memory barriers _must_ be used to control the ordering of
 references to shared memory on SMP systems, though the use of locking instead
 is sufficient.
 
 Mandatory barriers should not be used to control SMP effects, since mandatory
-barriers unnecessarily impose overhead on UP systems. They may, however, be
-used to control MMIO effects on accesses through relaxed memory I/O windows.
-These are required even on non-SMP systems as they affect the order in which
-memory operations appear to a device by prohibiting both the compiler and the
-CPU from reordering them.
+barriers impose unnecessary overhead on both SMP and UP systems. They may,
+however, be used to control MMIO effects on accesses through relaxed memory I/O
+windows.  These barriers are required even on non-SMP systems as they affect
+the order in which memory operations appear to a device by prohibiting both the
+compiler and the CPU from reordering them.
 
 
 There are some more advanced barrier functions:
@@ -1673,8 +1674,8 @@ There are some more advanced barrier functions:
  (*) smp_store_mb(var, value)
 
      This assigns the value to the variable and then inserts a full memory
-     barrier after it, depending on the function.  It isn't guaranteed to
-     insert anything more than a compiler barrier in a UP compilation.
+     barrier after it.  It isn't guaranteed to insert anything more than a
+     compiler barrier in a UP compilation.
 
 
  (*) smp_mb__before_atomic();
@@ -2948,6 +2949,23 @@ The Alpha defines the Linux kernel's memory barrier model.
 
 See the subsection on "Cache Coherency" above.
 
+VIRTUAL MACHINE GUESTS
+-------------------
+
+Guests running within virtual machines might be affected by SMP effects even if
+the guest itself is compiled without SMP support.  This is an artifact of
+interfacing with an SMP host while running an UP kernel.  Using mandatory
+barriers for this use-case would be possible but is often suboptimal.
+
+To handle this case optimally, low-level virt_mb() etc macros are available.
+These have the same effect as smp_mb() etc when SMP is enabled, but generate
+identical code for SMP and non-SMP systems. For example, virtual machine guests
+should use virt_mb() rather than smp_mb() when synchronizing against a
+(possibly SMP) host.
+
+These are equivalent to smp_mb() etc counterparts in all other respects,
+in particular, they do not control MMIO effects: to control
+MMIO effects, use mandatory barriers.
 
 ============
 EXAMPLE USES
diff --git a/Documentation/mtd/nand_ecc.txt b/Documentation/mtd/nand_ecc.txt
index e129b2479ea8..f8c3284bf6a7 100644
--- a/Documentation/mtd/nand_ecc.txt
+++ b/Documentation/mtd/nand_ecc.txt
@@ -107,7 +107,7 @@ for (i = 0; i < 256; i++)
     if (i & 0x01)
        rp1 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
     else
-       rp0 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
+       rp0 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp0;
     if (i & 0x02)
        rp3 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp3;
     else
@@ -127,7 +127,7 @@ for (i = 0; i < 256; i++)
     if (i & 0x20)
       rp11 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp11;
     else
-    rp10 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp10;
+      rp10 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp10;
     if (i & 0x40)
       rp13 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp13;
     else
@@ -158,7 +158,7 @@ the values in any order. So instead of calculating all the bits
 individually, let us try to rearrange things.
 For the column parity this is easy. We can just xor the bytes and in the
 end filter out the relevant bits. This is pretty nice as it will bring
-all cp calculation out of the if loop.
+all cp calculation out of the for loop.
 
 Similarly we can first xor the bytes for the various rows.
 This leads to:
@@ -271,11 +271,11 @@ to write our code in such a way that we process data in 32 bit chunks.
 Of course this means some modification as the row parity is byte by
 byte. A quick analysis:
 for the column parity we use the par variable. When extending to 32 bits
-we can in the end easily calculate p0 and p1 from it.
+we can in the end easily calculate rp0 and rp1 from it.
 (because par now consists of 4 bytes, contributing to rp1, rp0, rp1, rp0
-respectively)
+respectively, from MSB to LSB)
 also rp2 and rp3 can be easily retrieved from par as rp3 covers the
-first two bytes and rp2 the last two bytes.
+first two MSBs and rp2 covers the last two LSBs.
 
 Note that of course now the loop is executed only 64 times (256/4).
 And note that care must taken wrt byte ordering. The way bytes are
@@ -387,11 +387,11 @@ Analysis 2
 
 The code (of course) works, and hurray: we are a little bit faster than
 the linux driver code (about 15%). But wait, don't cheer too quickly.
-THere is more to be gained.
+There is more to be gained.
 If we look at e.g. rp14 and rp15 we see that we either xor our data with
 rp14 or with rp15. However we also have par which goes over all data.
 This means there is no need to calculate rp14 as it can be calculated from
-rp15 through rp14 = par ^ rp15;
+rp15 through rp14 = par ^ rp15, because par = rp14 ^ rp15;
 (or if desired we can avoid calculating rp15 and calculate it from
 rp14).  That is why some places refer to inverse parity.
 Of course the same thing holds for rp4/5, rp6/7, rp8/9, rp10/11 and rp12/13.
@@ -419,12 +419,12 @@ with
         if (i & 0x20) rp15 ^= cur;
 
         and outside the loop added:
-    rp4  = par ^ rp5;
-    rp6  = par ^ rp7;
-    rp8  = par ^ rp9;
-    rp10  = par ^ rp11;
-    rp12  = par ^ rp13;
-    rp14  = par ^ rp15;
+        rp4  = par ^ rp5;
+        rp6  = par ^ rp7;
+        rp8  = par ^ rp9;
+        rp10  = par ^ rp11;
+        rp12  = par ^ rp13;
+        rp14  = par ^ rp15;
 
 And after that the code takes about 30% more time, although the number of
 statements is reduced. This is also reflected in the assembly code.
@@ -524,12 +524,12 @@ THe code within the for loop was changed to:
 
         cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
         cur = *bp++; tmppar ^= cur; rp6 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
 
-	    cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; rp8 ^= cur;
         cur = *bp++; tmppar ^= cur; rp6 ^= cur; rp8 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp8 ^= cur;
         cur = *bp++; tmppar ^= cur; rp8 ^= cur;
 
         cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
@@ -537,7 +537,7 @@ THe code within the for loop was changed to:
         cur = *bp++; tmppar ^= cur; rp4 ^= cur;
         cur = *bp++; tmppar ^= cur;
 
-	    par ^= tmppar;
+        par ^= tmppar;
         if ((i & 0x1) == 0) rp12 ^= tmppar;
         if ((i & 0x2) == 0) rp14 ^= tmppar;
     }
@@ -548,8 +548,8 @@ to rp12 and rp14.
 
 While making the changes I also found that I could exploit that tmppar
 contains the running parity for this iteration. So instead of having:
-rp4 ^= cur; rp6 = cur;
-I removed the rp6 = cur; statement and did rp6 ^= tmppar; on next
+rp4 ^= cur; rp6 ^= cur;
+I removed the rp6 ^= cur; statement and did rp6 ^= tmppar; on next
 statement. A similar change was done for rp8 and rp10
 
 
@@ -593,22 +593,22 @@ The new code now looks like:
 
         cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
         cur = *bp++; tmppar ^= cur; rp6 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
 
-	    notrp8 = tmppar;
-	    cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        notrp8 = tmppar;
+        cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
         cur = *bp++; tmppar ^= cur; rp6 ^= cur;
-	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
         cur = *bp++; tmppar ^= cur;
-	    rp8 = rp8 ^ tmppar ^ notrp8;
+        rp8 = rp8 ^ tmppar ^ notrp8;
 
         cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
         cur = *bp++; tmppar ^= cur; rp6 ^= cur;
         cur = *bp++; tmppar ^= cur; rp4 ^= cur;
         cur = *bp++; tmppar ^= cur;
 
-	    par ^= tmppar;
+        par ^= tmppar;
         if ((i & 0x1) == 0) rp12 ^= tmppar;
         if ((i & 0x2) == 0) rp14 ^= tmppar;
     }
@@ -700,7 +700,7 @@ Conclusion
 The gain when calculating the ecc is tremendous. Om my development hardware
 a speedup of a factor of 18 for ecc calculation was achieved. On a test on an
 embedded system with a MIPS core a factor 7 was obtained.
-On  a test with a Linksys NSLU2 (ARMv5TE processor) the speedup was a factor
+On a test with a Linksys NSLU2 (ARMv5TE processor) the speedup was a factor
 5 (big endian mode, gcc 4.1.2, -O3)
 For correction not much gain could be obtained (as bitflips are rare). Then
 again there are also much less cycles spent there.
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index 58e49042fc20..ff23b755f5e4 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -115,14 +115,17 @@ The "bat0" interface can be used like any  other  regular  inter-
 face.  It needs an IP address which can be either statically con-
 figured or dynamically (by using DHCP or similar services):
 
-# NodeA: ifconfig bat0 192.168.0.1
-# NodeB: ifconfig bat0 192.168.0.2
+# NodeA: ip link set up dev bat0
+# NodeA: ip addr add 192.168.0.1/24 dev bat0
+
+# NodeB: ip link set up dev bat0
+# NodeB: ip addr add 192.168.0.2/24 dev bat0
 # NodeB: ping 192.168.0.1
 
 Note:  In  order to avoid problems remove all IP addresses previ-
 ously assigned to interfaces now used by batman advanced, e.g.
 
-# ifconfig eth0 0.0.0.0
+# ip addr flush dev eth0
 
 
 LOGGING/DEBUGGING
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 05fd83bb3596..6ab619fcc517 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -372,6 +372,15 @@ solution for a couple of reasons:
     nbytes = sendto(s, &frame, sizeof(struct can_frame),
                     0, (struct sockaddr*)&addr, sizeof(addr));
 
+  An accurate timestamp can be obtained with an ioctl(2) call after reading
+  a message from the socket:
+
+    struct timeval tv;
+    ioctl(s, SIOCGSTAMP, &tv);
+
+  The timestamp has a resolution of one microsecond and is set automatically
+  at the reception of a CAN frame.
+
   Remark about CAN FD (flexible data rate) support:
 
   Generally the handling of CAN FD is very similar to the formerly described
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 2ea4c45cf1c8..73b36d7c7b0d 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -335,6 +335,14 @@ tcp_keepalive_intvl - INTEGER
 	after probes started. Default value: 75sec i.e. connection
 	will be aborted after ~11 minutes of retries.
 
+tcp_l3mdev_accept - BOOLEAN
+	Enables child sockets to inherit the L3 master device index.
+	Enabling this option allows a "global" listen socket to work
+	across L3 master domains (e.g., VRFs) with connected sockets
+	derived from the listen socket to be bound to the L3 domain in
+	which the packets originated. Only valid when the kernel was
+	compiled with CONFIG_NET_L3_MASTER_DEV.
+
 tcp_low_latency - BOOLEAN
 	If set, the TCP stack makes decisions that prefer lower
 	latency as opposed to higher throughput.  By default, this
@@ -586,7 +594,7 @@ tcp_fastopen - INTEGER
 
 tcp_syn_retries - INTEGER
 	Number of times initial SYNs for an active TCP connection attempt
-	will be retransmitted. Should not be higher than 255. Default value
+	will be retransmitted. Should not be higher than 127. Default value
 	is 6, which corresponds to 63seconds till the last retransmission
 	with the current initial RTO of 1second. With this the final timeout
 	for an active TCP connection attempt will happen after 127seconds.
@@ -1723,6 +1731,25 @@ addip_enable - BOOLEAN
 
 	Default: 0
 
+pf_enable - INTEGER
+	Enable or disable pf (pf is short for potentially failed) state. A value
+	of pf_retrans > path_max_retrans also disables pf state. That is, one of
+	both pf_enable and pf_retrans > path_max_retrans can disable pf state.
+	Since pf_retrans and path_max_retrans can be changed by userspace
+	application, sometimes user expects to disable pf state by the value of
+	pf_retrans > path_max_retrans, but occasionally the value of pf_retrans
+	or path_max_retrans is changed by the user application, this pf state is
+	enabled. As such, it is necessary to add this to dynamically enable
+	and disable pf state. See:
+	https://datatracker.ietf.org/doc/draft-ietf-tsvwg-sctp-failover for
+	details.
+
+	1: Enable pf.
+
+	0: Disable pf.
+
+	Default: 1
+
 addip_noauth_enable - BOOLEAN
 	Dynamic Address Reconfiguration (ADD-IP) requires the use of
 	authentication to protect the operations of adding or removing new
@@ -1799,7 +1826,9 @@ pf_retrans - INTEGER
 	having to reduce path_max_retrans to a very low value.  See:
 	http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
 	for details.  Note also that a value of pf_retrans > path_max_retrans
-	disables this feature
+	disables this feature. Since both pf_retrans and path_max_retrans can
+	be changed by userspace application, a variable pf_enable is used to
+	disable pf state.
 
 	Default: 0
 
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index 91994134efca..fad63136ee3e 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -304,8 +304,12 @@ certain netdevs from flooding unicast traffic for which there is no FDB entry.
 IGMP Snooping
 ^^^^^^^^^^^^^
 
-XXX: complete this section
-
+In order to support IGMP snooping, the port netdevs should trap to the bridge
+driver all IGMP join and leave messages.
+The bridge multicast module will notify port netdevs on every multicast group
+changed whether it is static configured or dynamically joined/leave.
+The hardware implementation should be forwarding all registered multicast
+traffic groups only to the configured ports.
 
 L3 Routing Offload
 ------------------
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index b0e911e0e8f5..44558882aa60 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -999,7 +999,7 @@ from its probe routine to make runtime PM work for the device.
 
 It is important to remember that the driver's runtime_suspend() callback
 may be executed right after the usage counter has been decremented, because
-user space may already have cuased the pm_runtime_allow() helper function
+user space may already have caused the pm_runtime_allow() helper function
 unblocking the runtime PM of the device to run via sysfs, so the driver must
 be prepared to cope with that.
 
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 0784bc3a2ab5..7328cf85236c 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -371,6 +371,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - increment the device's usage counter, run pm_runtime_resume(dev) and
       return its result
 
+  int pm_runtime_get_if_in_use(struct device *dev);
+    - return -EINVAL if 'power.disable_depth' is nonzero; otherwise, if the
+      runtime PM status is RPM_ACTIVE and the runtime PM usage counter is
+      nonzero, increment the counter and return 1; otherwise return 0 without
+      changing the counter
+
   void pm_runtime_put_noidle(struct device *dev);
     - decrement the device's usage counter
 
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index b784c270105f..5d1128bf0282 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -250,6 +250,12 @@ dentry names:
 
 	Passed by reference.
 
+block_device names:
+
+	%pg	sda, sda1 or loop0p1
+
+	For printing name of block_device pointers.
+
 struct va_format:
 
 	%pV
@@ -300,15 +306,6 @@ Network device features:
 
 	Passed by reference.
 
-Command from struct task_struct
-
-	%pT	ls
-
-	For printing executable name excluding path from struct
-	task_struct.
-
-	Passed by reference.
-
 If you add other %p extensions, please extend lib/test_printf.c with
 one or more test cases, if at all feasible.
 
diff --git a/Documentation/s390/zfcpdump.txt b/Documentation/s390/zfcpdump.txt
index dc929be96016..b064aa59714d 100644
--- a/Documentation/s390/zfcpdump.txt
+++ b/Documentation/s390/zfcpdump.txt
@@ -15,19 +15,15 @@ the s390-tools package) to make the device bootable. The operator of a Linux
 system can then trigger a SCSI dump by booting the SCSI disk, where zfcpdump
 resides on.
 
-The kernel part of zfcpdump is implemented as a debugfs file under "zcore/mem",
-which exports memory and registers of the crashed Linux in an s390
-standalone dump format. It can be used in the same way as e.g. /dev/mem. The
-dump format defines a 4K header followed by plain uncompressed memory. The
-register sets are stored in the prefix pages of the respective CPUs. To build a
-dump enabled kernel with the zcore driver, the kernel config option
-CONFIG_CRASH_DUMP has to be set. When reading from "zcore/mem", the part of
-memory, which has been saved by hardware is read by the driver via the SCLP
-hardware interface. The second part is just copied from the non overwritten real
-memory.
-
-Since kernel version 3.12 also the /proc/vmcore file can also be used to access
-the dump.
+The user space dump tool accesses the memory of the crashed system by means
+of the /proc/vmcore interface. This interface exports the crashed system's
+memory and registers in ELF core dump format. To access the memory which has
+been saved by the hardware SCLP requests will be created at the time the data
+is needed by /proc/vmcore. The tail part of the crashed systems memory which
+has not been stashed by hardware can just be copied from real memory.
+
+To build a dump enabled kernel the kernel config option CONFIG_CRASH_DUMP
+has to be set.
 
 To get a valid zfcpdump kernel configuration use "make zfcpdump_defconfig".
 
diff --git a/Documentation/security/keys-trusted-encrypted.txt b/Documentation/security/keys-trusted-encrypted.txt
index e105ae97a4f5..324ddf5223b3 100644
--- a/Documentation/security/keys-trusted-encrypted.txt
+++ b/Documentation/security/keys-trusted-encrypted.txt
@@ -27,17 +27,26 @@ Usage:
     keyctl print keyid
 
     options:
-       keyhandle= ascii hex value of sealing key default 0x40000000 (SRK)
-       keyauth=	  ascii hex auth for sealing key default 0x00...i
-		  (40 ascii zeros)
-       blobauth=  ascii hex auth for sealed data default 0x00...
-		  (40 ascii zeros)
-       blobauth=  ascii hex auth for sealed data default 0x00...
-		  (40 ascii zeros)
-       pcrinfo=	  ascii hex of PCR_INFO or PCR_INFO_LONG (no default)
-       pcrlock=	  pcr number to be extended to "lock" blob
-       migratable= 0|1 indicating permission to reseal to new PCR values,
-                   default 1 (resealing allowed)
+       keyhandle=    ascii hex value of sealing key default 0x40000000 (SRK)
+       keyauth=	     ascii hex auth for sealing key default 0x00...i
+                     (40 ascii zeros)
+       blobauth=     ascii hex auth for sealed data default 0x00...
+                     (40 ascii zeros)
+       blobauth=     ascii hex auth for sealed data default 0x00...
+                     (40 ascii zeros)
+       pcrinfo=	     ascii hex of PCR_INFO or PCR_INFO_LONG (no default)
+       pcrlock=	     pcr number to be extended to "lock" blob
+       migratable=   0|1 indicating permission to reseal to new PCR values,
+                     default 1 (resealing allowed)
+       hash=         hash algorithm name as a string. For TPM 1.x the only
+                     allowed value is sha1. For TPM 2.x the allowed values
+                     are sha1, sha256, sha384, sha512 and sm3-256.
+       policydigest= digest for the authorization policy. must be calculated
+                     with the same hash algorithm as specified by the 'hash='
+                     option.
+       policyhandle= handle to an authorization policy session that defines the
+                     same policy and with the same hash algorithm as was used to
+                     seal the key.
 
 "keyctl print" returns an ascii hex copy of the sealed key, which is in standard
 TPM_STORED_DATA format.  The key length for new keys are always in bytes.
diff --git a/Documentation/sound/alsa/img,spdif-in.txt b/Documentation/sound/alsa/img,spdif-in.txt
new file mode 100644
index 000000000000..8b7505785fa6
--- /dev/null
+++ b/Documentation/sound/alsa/img,spdif-in.txt
@@ -0,0 +1,49 @@
+The Imagination Technologies SPDIF Input controller contains the following
+controls:
+
+name='IEC958 Capture Mask',index=0
+
+This control returns a mask that shows which of the IEC958 status bits
+can be read using the 'IEC958 Capture Default' control.
+
+name='IEC958 Capture Default',index=0
+
+This control returns the status bits contained within the SPDIF stream that
+is being received. The 'IEC958 Capture Mask' shows which bits can be read
+from this control.
+
+name='SPDIF In Multi Frequency Acquire',index=0
+name='SPDIF In Multi Frequency Acquire',index=1
+name='SPDIF In Multi Frequency Acquire',index=2
+name='SPDIF In Multi Frequency Acquire',index=3
+
+This control is used to attempt acquisition of up to four different sample
+rates. The active rate can be obtained by reading the 'SPDIF In Lock Frequency'
+control.
+
+When the value of this control is set to {0,0,0,0}, the rate given to hw_params
+will determine the single rate the block will capture. Else, the rate given to
+hw_params will be ignored, and the block will attempt capture for each of the
+four sample rates set here.
+
+If less than four rates are required, the same rate can be specified more than
+once
+
+name='SPDIF In Lock Frequency',index=0
+
+This control returns the active capture rate, or 0 if a lock has not been
+acquired
+
+name='SPDIF In Lock TRK',index=0
+
+This control is used to modify the locking/jitter rejection characteristics
+of the block. Larger values increase the locking range, but reduce jitter
+rejection.
+
+name='SPDIF In Lock Acquire Threshold',index=0
+
+This control is used to change the threshold at which a lock is acquired.
+
+name='SPDIF In Lock Release Threshold',index=0
+
+This control is used to change the threshold at which a lock is released.
diff --git a/Documentation/spi/.gitignore b/Documentation/spi/.gitignore
deleted file mode 100644
index 4280576397e8..000000000000
--- a/Documentation/spi/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-spidev_fdx
-spidev_test
diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX
index a128fa835512..4644bf0d9832 100644
--- a/Documentation/spi/00-INDEX
+++ b/Documentation/spi/00-INDEX
@@ -10,13 +10,9 @@ pxa2xx
 	- PXA2xx SPI master controller build by spi_message fifo wq
 spidev
 	- Intro to the userspace API for spi devices
-spidev_fdx.c
-	- spidev example file
 spi-lm70llp
 	- Connecting an LM70-LLP sensor to the kernel via the SPI subsys.
 spi-sc18is602
 	- NXP SC18IS602/603 I2C-bus to SPI bridge
 spi-summary
 	- (Linux) SPI overview. If unsure about SPI or SPI in Linux, start here.
-spidev_test.c
-	- SPI testing utility.
diff --git a/Documentation/spi/Makefile b/Documentation/spi/Makefile
deleted file mode 100644
index efa255813e9d..000000000000
--- a/Documentation/spi/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# List of programs to build
-hostprogs-y := spidev_test spidev_fdx
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_spidev_test.o += -I$(objtree)/usr/include
-HOSTCFLAGS_spidev_fdx.o += -I$(objtree)/usr/include
diff --git a/Documentation/spi/spidev_fdx.c b/Documentation/spi/spidev_fdx.c
deleted file mode 100644
index 0ea3e51292fc..000000000000
--- a/Documentation/spi/spidev_fdx.c
+++ /dev/null
@@ -1,158 +0,0 @@
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <fcntl.h>
-#include <string.h>
-
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/types.h>
-#include <linux/spi/spidev.h>
-
-
-static int verbose;
-
-static void do_read(int fd, int len)
-{
-	unsigned char	buf[32], *bp;
-	int		status;
-
-	/* read at least 2 bytes, no more than 32 */
-	if (len < 2)
-		len = 2;
-	else if (len > sizeof(buf))
-		len = sizeof(buf);
-	memset(buf, 0, sizeof buf);
-
-	status = read(fd, buf, len);
-	if (status < 0) {
-		perror("read");
-		return;
-	}
-	if (status != len) {
-		fprintf(stderr, "short read\n");
-		return;
-	}
-
-	printf("read(%2d, %2d): %02x %02x,", len, status,
-		buf[0], buf[1]);
-	status -= 2;
-	bp = buf + 2;
-	while (status-- > 0)
-		printf(" %02x", *bp++);
-	printf("\n");
-}
-
-static void do_msg(int fd, int len)
-{
-	struct spi_ioc_transfer	xfer[2];
-	unsigned char		buf[32], *bp;
-	int			status;
-
-	memset(xfer, 0, sizeof xfer);
-	memset(buf, 0, sizeof buf);
-
-	if (len > sizeof buf)
-		len = sizeof buf;
-
-	buf[0] = 0xaa;
-	xfer[0].tx_buf = (unsigned long)buf;
-	xfer[0].len = 1;
-
-	xfer[1].rx_buf = (unsigned long) buf;
-	xfer[1].len = len;
-
-	status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
-	if (status < 0) {
-		perror("SPI_IOC_MESSAGE");
-		return;
-	}
-
-	printf("response(%2d, %2d): ", len, status);
-	for (bp = buf; len; len--)
-		printf(" %02x", *bp++);
-	printf("\n");
-}
-
-static void dumpstat(const char *name, int fd)
-{
-	__u8	lsb, bits;
-	__u32	mode, speed;
-
-	if (ioctl(fd, SPI_IOC_RD_MODE32, &mode) < 0) {
-		perror("SPI rd_mode");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
-		perror("SPI rd_lsb_fist");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
-		perror("SPI bits_per_word");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
-		perror("SPI max_speed_hz");
-		return;
-	}
-
-	printf("%s: spi mode 0x%x, %d bits %sper word, %d Hz max\n",
-		name, mode, bits, lsb ? "(lsb first) " : "", speed);
-}
-
-int main(int argc, char **argv)
-{
-	int		c;
-	int		readcount = 0;
-	int		msglen = 0;
-	int		fd;
-	const char	*name;
-
-	while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
-		switch (c) {
-		case 'm':
-			msglen = atoi(optarg);
-			if (msglen < 0)
-				goto usage;
-			continue;
-		case 'r':
-			readcount = atoi(optarg);
-			if (readcount < 0)
-				goto usage;
-			continue;
-		case 'v':
-			verbose++;
-			continue;
-		case 'h':
-		case '?':
-usage:
-			fprintf(stderr,
-				"usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
-				argv[0]);
-			return 1;
-		}
-	}
-
-	if ((optind + 1) != argc)
-		goto usage;
-	name = argv[optind];
-
-	fd = open(name, O_RDWR);
-	if (fd < 0) {
-		perror("open");
-		return 1;
-	}
-
-	dumpstat(name, fd);
-
-	if (msglen)
-		do_msg(fd, msglen);
-
-	if (readcount)
-		do_read(fd, readcount);
-
-	close(fd);
-	return 0;
-}
diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
deleted file mode 100644
index 135b3f592b83..000000000000
--- a/Documentation/spi/spidev_test.c
+++ /dev/null
@@ -1,318 +0,0 @@
-/*
- * SPI testing utility (using spidev driver)
- *
- * Copyright (c) 2007  MontaVista Software, Inc.
- * Copyright (c) 2007  Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * Cross-compile with cross-gcc -I/path/to/cross-kernel/include
- */
-
-#include <stdint.h>
-#include <unistd.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <getopt.h>
-#include <fcntl.h>
-#include <sys/ioctl.h>
-#include <linux/types.h>
-#include <linux/spi/spidev.h>
-
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))
-
-static void pabort(const char *s)
-{
-	perror(s);
-	abort();
-}
-
-static const char *device = "/dev/spidev1.1";
-static uint32_t mode;
-static uint8_t bits = 8;
-static uint32_t speed = 500000;
-static uint16_t delay;
-static int verbose;
-
-uint8_t default_tx[] = {
-	0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-	0x40, 0x00, 0x00, 0x00, 0x00, 0x95,
-	0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-	0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-	0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-	0xF0, 0x0D,
-};
-
-uint8_t default_rx[ARRAY_SIZE(default_tx)] = {0, };
-char *input_tx;
-
-static void hex_dump(const void *src, size_t length, size_t line_size, char *prefix)
-{
-	int i = 0;
-	const unsigned char *address = src;
-	const unsigned char *line = address;
-	unsigned char c;
-
-	printf("%s | ", prefix);
-	while (length-- > 0) {
-		printf("%02X ", *address++);
-		if (!(++i % line_size) || (length == 0 && i % line_size)) {
-			if (length == 0) {
-				while (i++ % line_size)
-					printf("__ ");
-			}
-			printf(" | ");  /* right close */
-			while (line < address) {
-				c = *line++;
-				printf("%c", (c < 33 || c == 255) ? 0x2E : c);
-			}
-			printf("\n");
-			if (length > 0)
-				printf("%s | ", prefix);
-		}
-	}
-}
-
-/*
- *  Unescape - process hexadecimal escape character
- *      converts shell input "\x23" -> 0x23
- */
-static int unescape(char *_dst, char *_src, size_t len)
-{
-	int ret = 0;
-	char *src = _src;
-	char *dst = _dst;
-	unsigned int ch;
-
-	while (*src) {
-		if (*src == '\\' && *(src+1) == 'x') {
-			sscanf(src + 2, "%2x", &ch);
-			src += 4;
-			*dst++ = (unsigned char)ch;
-		} else {
-			*dst++ = *src++;
-		}
-		ret++;
-	}
-	return ret;
-}
-
-static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len)
-{
-	int ret;
-
-	struct spi_ioc_transfer tr = {
-		.tx_buf = (unsigned long)tx,
-		.rx_buf = (unsigned long)rx,
-		.len = len,
-		.delay_usecs = delay,
-		.speed_hz = speed,
-		.bits_per_word = bits,
-	};
-
-	if (mode & SPI_TX_QUAD)
-		tr.tx_nbits = 4;
-	else if (mode & SPI_TX_DUAL)
-		tr.tx_nbits = 2;
-	if (mode & SPI_RX_QUAD)
-		tr.rx_nbits = 4;
-	else if (mode & SPI_RX_DUAL)
-		tr.rx_nbits = 2;
-	if (!(mode & SPI_LOOP)) {
-		if (mode & (SPI_TX_QUAD | SPI_TX_DUAL))
-			tr.rx_buf = 0;
-		else if (mode & (SPI_RX_QUAD | SPI_RX_DUAL))
-			tr.tx_buf = 0;
-	}
-
-	ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-	if (ret < 1)
-		pabort("can't send spi message");
-
-	if (verbose)
-		hex_dump(tx, len, 32, "TX");
-	hex_dump(rx, len, 32, "RX");
-}
-
-static void print_usage(const char *prog)
-{
-	printf("Usage: %s [-DsbdlHOLC3]\n", prog);
-	puts("  -D --device   device to use (default /dev/spidev1.1)\n"
-	     "  -s --speed    max speed (Hz)\n"
-	     "  -d --delay    delay (usec)\n"
-	     "  -b --bpw      bits per word \n"
-	     "  -l --loop     loopback\n"
-	     "  -H --cpha     clock phase\n"
-	     "  -O --cpol     clock polarity\n"
-	     "  -L --lsb      least significant bit first\n"
-	     "  -C --cs-high  chip select active high\n"
-	     "  -3 --3wire    SI/SO signals shared\n"
-	     "  -v --verbose  Verbose (show tx buffer)\n"
-	     "  -p            Send data (e.g. \"1234\\xde\\xad\")\n"
-	     "  -N --no-cs    no chip select\n"
-	     "  -R --ready    slave pulls low to pause\n"
-	     "  -2 --dual     dual transfer\n"
-	     "  -4 --quad     quad transfer\n");
-	exit(1);
-}
-
-static void parse_opts(int argc, char *argv[])
-{
-	while (1) {
-		static const struct option lopts[] = {
-			{ "device",  1, 0, 'D' },
-			{ "speed",   1, 0, 's' },
-			{ "delay",   1, 0, 'd' },
-			{ "bpw",     1, 0, 'b' },
-			{ "loop",    0, 0, 'l' },
-			{ "cpha",    0, 0, 'H' },
-			{ "cpol",    0, 0, 'O' },
-			{ "lsb",     0, 0, 'L' },
-			{ "cs-high", 0, 0, 'C' },
-			{ "3wire",   0, 0, '3' },
-			{ "no-cs",   0, 0, 'N' },
-			{ "ready",   0, 0, 'R' },
-			{ "dual",    0, 0, '2' },
-			{ "verbose", 0, 0, 'v' },
-			{ "quad",    0, 0, '4' },
-			{ NULL, 0, 0, 0 },
-		};
-		int c;
-
-		c = getopt_long(argc, argv, "D:s:d:b:lHOLC3NR24p:v", lopts, NULL);
-
-		if (c == -1)
-			break;
-
-		switch (c) {
-		case 'D':
-			device = optarg;
-			break;
-		case 's':
-			speed = atoi(optarg);
-			break;
-		case 'd':
-			delay = atoi(optarg);
-			break;
-		case 'b':
-			bits = atoi(optarg);
-			break;
-		case 'l':
-			mode |= SPI_LOOP;
-			break;
-		case 'H':
-			mode |= SPI_CPHA;
-			break;
-		case 'O':
-			mode |= SPI_CPOL;
-			break;
-		case 'L':
-			mode |= SPI_LSB_FIRST;
-			break;
-		case 'C':
-			mode |= SPI_CS_HIGH;
-			break;
-		case '3':
-			mode |= SPI_3WIRE;
-			break;
-		case 'N':
-			mode |= SPI_NO_CS;
-			break;
-		case 'v':
-			verbose = 1;
-			break;
-		case 'R':
-			mode |= SPI_READY;
-			break;
-		case 'p':
-			input_tx = optarg;
-			break;
-		case '2':
-			mode |= SPI_TX_DUAL;
-			break;
-		case '4':
-			mode |= SPI_TX_QUAD;
-			break;
-		default:
-			print_usage(argv[0]);
-			break;
-		}
-	}
-	if (mode & SPI_LOOP) {
-		if (mode & SPI_TX_DUAL)
-			mode |= SPI_RX_DUAL;
-		if (mode & SPI_TX_QUAD)
-			mode |= SPI_RX_QUAD;
-	}
-}
-
-int main(int argc, char *argv[])
-{
-	int ret = 0;
-	int fd;
-	uint8_t *tx;
-	uint8_t *rx;
-	int size;
-
-	parse_opts(argc, argv);
-
-	fd = open(device, O_RDWR);
-	if (fd < 0)
-		pabort("can't open device");
-
-	/*
-	 * spi mode
-	 */
-	ret = ioctl(fd, SPI_IOC_WR_MODE32, &mode);
-	if (ret == -1)
-		pabort("can't set spi mode");
-
-	ret = ioctl(fd, SPI_IOC_RD_MODE32, &mode);
-	if (ret == -1)
-		pabort("can't get spi mode");
-
-	/*
-	 * bits per word
-	 */
-	ret = ioctl(fd, SPI_IOC_WR_BITS_PER_WORD, &bits);
-	if (ret == -1)
-		pabort("can't set bits per word");
-
-	ret = ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits);
-	if (ret == -1)
-		pabort("can't get bits per word");
-
-	/*
-	 * max speed hz
-	 */
-	ret = ioctl(fd, SPI_IOC_WR_MAX_SPEED_HZ, &speed);
-	if (ret == -1)
-		pabort("can't set max speed hz");
-
-	ret = ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed);
-	if (ret == -1)
-		pabort("can't get max speed hz");
-
-	printf("spi mode: 0x%x\n", mode);
-	printf("bits per word: %d\n", bits);
-	printf("max speed: %d Hz (%d KHz)\n", speed, speed/1000);
-
-	if (input_tx) {
-		size = strlen(input_tx+1);
-		tx = malloc(size);
-		rx = malloc(size);
-		size = unescape((char *)tx, input_tx, size);
-		transfer(fd, tx, rx, size);
-		free(rx);
-		free(tx);
-	} else {
-		transfer(fd, default_tx, default_rx, sizeof(default_tx));
-	}
-
-	close(fd);
-
-	return ret;
-}
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index 3049a612291b..ffd4575ec9f2 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -93,7 +93,7 @@ format in the sign-off area:
 Also, some patches may have kernel version prerequisites.  This can be
 specified in the following format in the sign-off area:
 
-     Cc:  <stable@vger.kernel.org> # 3.3.x-
+     Cc: <stable@vger.kernel.org> # 3.3.x-
 
    The tag has the meaning of:
      git cherry-pick <this commit>
diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 88152f214f48..302b5ed616a6 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@@ -159,6 +161,27 @@ The default is 65534.
 
 ==============================================================
 
+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index af70d1541d3a..a93b414672a7 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -551,6 +551,21 @@ the recommended setting is 60.
 
 ==============================================================
 
+panic_on_io_nmi:
+
+Controls the kernel's behavior when a CPU receives an NMI caused by
+an IO error.
+
+0: try to continue operation (default)
+
+1: panic immediately. The IO error triggered an NMI. This indicates a
+   serious system condition which could result in IO data corruption.
+   Rather than continuing, panicking might be a better choice. Some
+   servers issue this sort of NMI when the dump button is pushed,
+   and you can use this option to take a crash dump.
+
+==============================================================
+
 panic_on_oops:
 
 Controls the kernel's behaviour when an oops or BUG is encountered.
@@ -810,14 +825,13 @@ via the /proc/sys interface:
        Each write syscall must fully contain the sysctl value to be
        written, and multiple writes on the same sysctl file descriptor
        will rewrite the sysctl value, regardless of file position.
-   0 - (default) Same behavior as above, but warn about processes that
-       perform writes to a sysctl file descriptor when the file position
-       is not 0.
-   1 - Respect file position when writing sysctl strings. Multiple writes
-       will append to the sysctl value buffer. Anything past the max length
-       of the sysctl value buffer will be ignored. Writes to numeric sysctl
-       entries must always be at file position 0 and the value must be
-       fully contained in the buffer sent in the write syscall.
+   0 - Same behavior as above, but warn about processes that perform writes
+       to a sysctl file descriptor when the file position is not 0.
+   1 - (default) Respect file position when writing sysctl strings. Multiple
+       writes will append to the sysctl value buffer. Anything past the max
+       length of the sysctl value buffer will be ignored. Writes to numeric
+       sysctl entries must always be at file position 0 and the value must
+       be fully contained in the buffer sent in the write syscall.
 
 ==============================================================
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index f72370b440b1..89a887c76629 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -42,6 +42,8 @@ Currently, these files are in /proc/sys/vm:
 - min_slab_ratio
 - min_unmapped_ratio
 - mmap_min_addr
+- mmap_rnd_bits
+- mmap_rnd_compat_bits
 - nr_hugepages
 - nr_overcommit_hugepages
 - nr_trim_pages         (only if CONFIG_MMU=n)
@@ -135,7 +137,7 @@ Contains, as a percentage of total available memory that contains free pages
 and reclaimable pages, the number of pages at which the background kernel
 flusher threads will start writing out dirty data.
 
-The total avaiable memory is not equal to total system memory.
+The total available memory is not equal to total system memory.
 
 ==============================================================
 
@@ -170,7 +172,7 @@ Contains, as a percentage of total available memory that contains free pages
 and reclaimable pages, the number of pages at which a process which is
 generating disk writes will itself start writing out dirty data.
 
-The total avaiable memory is not equal to total system memory.
+The total available memory is not equal to total system memory.
 
 ==============================================================
 
@@ -485,6 +487,33 @@ against future potential kernel bugs.
 
 ==============================================================
 
+mmap_rnd_bits:
+
+This value can be used to select the number of bits to use to
+determine the random offset to the base address of vma regions
+resulting from mmap allocations on architectures which support
+tuning address space randomization.  This value will be bounded
+by the architecture's minimum and maximum supported values.
+
+This value can be changed after boot using the
+/proc/sys/vm/mmap_rnd_bits tunable
+
+==============================================================
+
+mmap_rnd_compat_bits:
+
+This value can be used to select the number of bits to use to
+determine the random offset to the base address of vma regions
+resulting from mmap allocations for applications run in
+compatibility mode on architectures which support tuning address
+space randomization.  This value will be bounded by the
+architecture's minimum and maximum supported values.
+
+This value can be changed after boot using the
+/proc/sys/vm/mmap_rnd_compat_bits tunable
+
+==============================================================
+
 nr_hugepages
 
 Change the minimum size of the hugepage pool.
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index 10f062ea6bc2..8c745c8931da 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -364,6 +364,7 @@ integral_cutoff
 	accumulates error when temperature is above the desired
 	temperature trip point. For more information see
 	Documentation/thermal/power_allocator.txt
+	Unit: millidegree Celsius
 	RW, Optional
 
 slope
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 767392ffd31e..a484d2c109d7 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -1,9 +1,7 @@
 		High Precision Event Timer Driver for Linux
 
 The High Precision Event Timer (HPET) hardware follows a specification
-by Intel and Microsoft which can be found at
-
-	http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+by Intel and Microsoft, revision 1.
 
 Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
 and up to 32 comparators.  Normally three or more comparators are provided,
diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt
new file mode 100644
index 000000000000..78c383bf06aa
--- /dev/null
+++ b/Documentation/trace/events-msr.txt
@@ -0,0 +1,37 @@
+
+The x86 kernel supports tracing most MSR (Model Specific Register) accesses.
+To see the definition of the MSRs on Intel systems please see the SDM
+at http://www.intel.com/sdm (Volume 3)
+
+Available trace points:
+
+/sys/kernel/debug/tracing/events/msr/
+
+Trace MSR reads
+
+read_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace MSR writes
+
+write_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace RDPMC in kernel
+
+rdpmc
+
+The trace data can be post processed with the postprocess/decode_msr.py script
+
+cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h
+
+to add symbolic MSR names.
+
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
new file mode 100644
index 000000000000..0ab40e0db580
--- /dev/null
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python
+# add symbolic names to read_msr / write_msr in trace
+# decode_msr msr-index.h < trace
+import sys
+import re
+
+msrs = dict()
+
+with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f:
+	for j in f:
+		m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j)
+		if m:
+			msrs[int(m.group(2), 16)] = m.group(1)
+
+extra_ranges = (
+	( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ),
+	( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ),
+	( "LBR_INFO_%d", 0xdc0, 0xddf ),
+)
+
+for j in sys.stdin:
+	m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j)
+	if m:
+		r = None
+		num = int(m.group(2), 16)
+		if num in msrs:
+			r = msrs[num]
+		else:
+			for er in extra_ranges:
+				if er[1] <= num <= er[2]:
+					r = er[0] % (num - er[1],)
+					break
+		if r:
+			j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")")
+	print j,
+
+
diff --git a/Documentation/ubsan.txt b/Documentation/ubsan.txt
new file mode 100644
index 000000000000..f58215ef5797
--- /dev/null
+++ b/Documentation/ubsan.txt
@@ -0,0 +1,84 @@
+Undefined Behavior Sanitizer - UBSAN
+
+Overview
+--------
+
+UBSAN is a runtime undefined behaviour checker.
+
+UBSAN uses compile-time instrumentation to catch undefined behavior (UB).
+Compiler inserts code that perform certain kinds of checks before operations
+that may cause UB. If check fails (i.e. UB detected) __ubsan_handle_*
+function called to print error message.
+
+GCC has that feature since 4.9.x [1] (see -fsanitize=undefined option and
+its suboptions). GCC 5.x has more checkers implemented [2].
+
+Report example
+---------------
+
+	 ================================================================================
+	 UBSAN: Undefined behaviour in ../include/linux/bitops.h:110:33
+	 shift exponent 32 is to large for 32-bit type 'unsigned int'
+	 CPU: 0 PID: 0 Comm: swapper Not tainted 4.4.0-rc1+ #26
+	  0000000000000000 ffffffff82403cc8 ffffffff815e6cd6 0000000000000001
+	  ffffffff82403cf8 ffffffff82403ce0 ffffffff8163a5ed 0000000000000020
+	  ffffffff82403d78 ffffffff8163ac2b ffffffff815f0001 0000000000000002
+	 Call Trace:
+	  [<ffffffff815e6cd6>] dump_stack+0x45/0x5f
+	  [<ffffffff8163a5ed>] ubsan_epilogue+0xd/0x40
+	  [<ffffffff8163ac2b>] __ubsan_handle_shift_out_of_bounds+0xeb/0x130
+	  [<ffffffff815f0001>] ? radix_tree_gang_lookup_slot+0x51/0x150
+	  [<ffffffff8173c586>] _mix_pool_bytes+0x1e6/0x480
+	  [<ffffffff83105653>] ? dmi_walk_early+0x48/0x5c
+	  [<ffffffff8173c881>] add_device_randomness+0x61/0x130
+	  [<ffffffff83105b35>] ? dmi_save_one_device+0xaa/0xaa
+	  [<ffffffff83105653>] dmi_walk_early+0x48/0x5c
+	  [<ffffffff831066ae>] dmi_scan_machine+0x278/0x4b4
+	  [<ffffffff8111d58a>] ? vprintk_default+0x1a/0x20
+	  [<ffffffff830ad120>] ? early_idt_handler_array+0x120/0x120
+	  [<ffffffff830b2240>] setup_arch+0x405/0xc2c
+	  [<ffffffff830ad120>] ? early_idt_handler_array+0x120/0x120
+	  [<ffffffff830ae053>] start_kernel+0x83/0x49a
+	  [<ffffffff830ad120>] ? early_idt_handler_array+0x120/0x120
+	  [<ffffffff830ad386>] x86_64_start_reservations+0x2a/0x2c
+	  [<ffffffff830ad4f3>] x86_64_start_kernel+0x16b/0x17a
+	 ================================================================================
+
+Usage
+-----
+
+To enable UBSAN configure kernel with:
+
+	CONFIG_UBSAN=y
+
+and to check the entire kernel:
+
+        CONFIG_UBSAN_SANITIZE_ALL=y
+
+To enable instrumentation for specific files or directories, add a line
+similar to the following to the respective kernel Makefile:
+
+        For a single file (e.g. main.o):
+                UBSAN_SANITIZE_main.o := y
+
+        For all files in one directory:
+                UBSAN_SANITIZE := y
+
+To exclude files from being instrumented even if
+CONFIG_UBSAN_SANITIZE_ALL=y, use:
+
+                UBSAN_SANITIZE_main.o := n
+        and:
+                UBSAN_SANITIZE := n
+
+Detection of unaligned accesses controlled through the separate option -
+CONFIG_UBSAN_ALIGNMENT. It's off by default on architectures that support
+unaligned accesses (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y). One could
+still enable it in config, just note that it will produce a lot of UBSAN
+reports.
+
+References
+----------
+
+[1] - https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/Debugging-Options.html
+[2] - https://gcc.gnu.org/onlinedocs/gcc/Debugging-Options.html
diff --git a/Documentation/usb/chipidea.txt b/Documentation/usb/chipidea.txt
index 3f848c1f2940..05f735a1b5a5 100644
--- a/Documentation/usb/chipidea.txt
+++ b/Documentation/usb/chipidea.txt
@@ -7,8 +7,8 @@ with 2 Freescale i.MX6Q sabre SD boards.
 ---------------------------------------
 Select CONFIG_USB_OTG_FSM, rebuild kernel Image and modules.
 If you want to check some internal variables for otg fsm,
-select CONFIG_USB_CHIPIDEA_DEBUG, there are 2 files which
-can show otg fsm variables and some controller registers value:
+mount debugfs, there are 2 files which can show otg fsm
+variables and some controller registers value:
 cat /sys/kernel/debug/ci_hdrc.0/otg
 cat /sys/kernel/debug/ci_hdrc.0/registers
 
diff --git a/Documentation/usb/gadget-testing.txt b/Documentation/usb/gadget-testing.txt
index b24d3ef89166..581960574889 100644
--- a/Documentation/usb/gadget-testing.txt
+++ b/Documentation/usb/gadget-testing.txt
@@ -434,7 +434,7 @@ On host: serialc -v <vendorID> -p <productID> -i<interface#> -a1 -s1024 \
 
 where seriald and serialc are Felipe's utilities found here:
 
-https://git.gitorious.org/usb/usb-tools.git master
+https://github.com/felipebalbi/usb-tools.git master
 
 12. PHONET function
 ===================
@@ -579,6 +579,8 @@ The SOURCESINK function provides these attributes in its function directory:
 	isoc_mult	- 0..2 (hs/ss only)
 	isoc_maxburst	- 0..15 (ss only)
 	bulk_buflen	- buffer length
+	bulk_qlen	- depth of queue for bulk
+	iso_qlen	- depth of queue for iso
 
 Testing the SOURCESINK function
 -------------------------------
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 4a15c90bc11d..0a94ffe17ab6 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
 		can write y/Y/1 or n/N/0 to the file to	enable/disable
 		USB2 hardware LPM manually. This is for	test purpose mainly.
 
-	power/usb3_hardware_lpm
+	power/usb3_hardware_lpm_u1
+	power/usb3_hardware_lpm_u2
 
 		When a USB 3.0 lpm-capable device is plugged in to a
 		xHCI host which supports link PM, it will check if U1
 		and U2 exit latencies have been set in the BOS
 		descriptor; if the check is is passed and the host
 		supports USB3 hardware LPM, USB3 hardware LPM will be
-		enabled for the device and this file will be created.
-		The file holds a string value (enable or disable)
-		indicating whether or not USB3 hardware LPM is
-		enabled for the device.
+		enabled for the device and these files will be created.
+		The files hold a string value (enable or disable)
+		indicating whether or not USB3 hardware LPM U1 or U2
+		is enabled for the device.
 
 	USB Port Power Control
 	----------------------
diff --git a/Documentation/video4linux/API.html b/Documentation/video4linux/API.html
index 256f8efa992c..eaf948cf1ae7 100644
--- a/Documentation/video4linux/API.html
+++ b/Documentation/video4linux/API.html
@@ -9,7 +9,7 @@
   <table border="0">
    <tr>
     <td>
-     <a href="http://linuxtv.org/downloads/legacy/video4linux/API/V4L1_API.html">V4L original API</a>
+     <a href="https://linuxtv.org/downloads/legacy/video4linux/API/V4L1_API.html">V4L original API</a>
     </td>
     <td>
      Obsoleted by V4L2 API
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 9e57ce43c4f4..67209998a439 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -41,8 +41,8 @@
  40 -> Plextor ConvertX PX-TV100U               (em2861)        [093b:a005]
  41 -> Kworld 350 U DVB-T                       (em2870)        [eb1a:e350]
  42 -> Kworld 355 U DVB-T                       (em2870)        [eb1a:e355,eb1a:e357,eb1a:e359]
- 43 -> Terratec Cinergy T XS                    (em2870)        [0ccd:0043]
- 44 -> Terratec Cinergy T XS (MT2060)           (em2870)
+ 43 -> Terratec Cinergy T XS                    (em2870)
+ 44 -> Terratec Cinergy T XS (MT2060)           (em2870)        [0ccd:0043]
  45 -> Pinnacle PCTV DVB-T                      (em2870)
  46 -> Compro, VideoMate U3                     (em2870)        [185b:2870]
  47 -> KWorld DVB-T 305U                        (em2880)        [eb1a:e305]
diff --git a/Documentation/video4linux/fimc.txt b/Documentation/video4linux/fimc.txt
index e0c6b8bc4743..4fab231be52e 100644
--- a/Documentation/video4linux/fimc.txt
+++ b/Documentation/video4linux/fimc.txt
@@ -58,7 +58,7 @@ Not currently supported:
 4.1. Media device interface
 
 The driver supports Media Controller API as defined at
-http://linuxtv.org/downloads/v4l-dvb-apis/media_common.html
+https://linuxtv.org/downloads/v4l-dvb-apis/media_common.html
 The media device driver name is "SAMSUNG S5P FIMC".
 
 The purpose of this interface is to allow changing assignment of FIMC instances
@@ -83,11 +83,11 @@ undefined behaviour.
 4.3. Capture video node
 
 The driver supports V4L2 Video Capture Interface as defined at:
-http://linuxtv.org/downloads/v4l-dvb-apis/devices.html
+https://linuxtv.org/downloads/v4l-dvb-apis/devices.html
 
 At the capture and mem-to-mem video nodes only the multi-planar API is
 supported. For more details see:
-http://linuxtv.org/downloads/v4l-dvb-apis/planar-apis.html
+https://linuxtv.org/downloads/v4l-dvb-apis/planar-apis.html
 
 4.4. Camera capture subdevs
 
diff --git a/Documentation/video4linux/omap4_camera.txt b/Documentation/video4linux/omap4_camera.txt
index 25d9b40a4651..a6734aa77242 100644
--- a/Documentation/video4linux/omap4_camera.txt
+++ b/Documentation/video4linux/omap4_camera.txt
@@ -47,7 +47,7 @@ Tested platforms
 File list
 ---------
 drivers/staging/media/omap4iss/
-include/media/omap4iss.h
+include/linux/platform_data/media/omap4iss.h
 
 References
 ----------
diff --git a/Documentation/video4linux/si4713.txt b/Documentation/video4linux/si4713.txt
index 2e7392a4fee1..2ddc6b095a76 100644
--- a/Documentation/video4linux/si4713.txt
+++ b/Documentation/video4linux/si4713.txt
@@ -157,7 +157,7 @@ int main (int argc, char *argv[])
 }
 
 The struct si4713_rnl and SI4713_IOC_MEASURE_RNL are defined under
-include/media/si4713.h.
+include/linux/platform_data/media/si4713.h.
 
 Stereo/Mono and RDS subchannels
 ===============================
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index 75d5c18d689a..fa41608ab2b4 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -295,16 +295,16 @@ module owner. This is done for you if you use the i2c helper functions.
 
 If integration with the media framework is needed, you must initialize the
 media_entity struct embedded in the v4l2_subdev struct (entity field) by
-calling media_entity_init():
+calling media_entity_pads_init(), if the entity has pads:
 
 	struct media_pad *pads = &my_sd->pads;
 	int err;
 
-	err = media_entity_init(&sd->entity, npads, pads, 0);
+	err = media_entity_pads_init(&sd->entity, npads, pads);
 
 The pads array must have been previously initialized. There is no need to
-manually set the struct media_entity type and name fields, but the revision
-field must be initialized if needed.
+manually set the struct media_entity function and name fields, but the
+revision field must be initialized if needed.
 
 A reference to the entity will be automatically acquired/released when the
 subdev device node (if any) is opened/closed.
@@ -695,12 +695,12 @@ difference is that the inode argument is omitted since it is never used.
 
 If integration with the media framework is needed, you must initialize the
 media_entity struct embedded in the video_device struct (entity field) by
-calling media_entity_init():
+calling media_entity_pads_init():
 
 	struct media_pad *pad = &my_vdev->pad;
 	int err;
 
-	err = media_entity_init(&vdev->entity, 1, pad, 0);
+	err = media_entity_pads_init(&vdev->entity, 1, pad);
 
 The pads array must have been previously initialized. There is no need to
 manually set the struct media_entity type and name fields.
diff --git a/Documentation/video4linux/v4l2-pci-skeleton.c b/Documentation/video4linux/v4l2-pci-skeleton.c
index 95ae82860092..79af0c041056 100644
--- a/Documentation/video4linux/v4l2-pci-skeleton.c
+++ b/Documentation/video4linux/v4l2-pci-skeleton.c
@@ -163,11 +163,10 @@ static irqreturn_t skeleton_irq(int irq, void *dev_id)
  * minimum number: many DMA engines need a minimum of 2 buffers in the
  * queue and you need to have another available for userspace processing.
  */
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct skeleton *skel = vb2_get_drv_priv(vq);
 
 	skel->field = skel->format.field;
@@ -183,12 +182,12 @@ static int queue_setup(struct vb2_queue *vq, const void *parg,
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
+	alloc_ctxs[0] = skel->alloc_ctx;
 
-	if (fmt && fmt->fmt.pix.sizeimage < skel->format.sizeimage)
-		return -EINVAL;
+	if (*nplanes)
+		return sizes[0] < skel->format.sizeimage ? -EINVAL : 0;
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : skel->format.sizeimage;
-	alloc_ctxs[0] = skel->alloc_ctx;
+	sizes[0] = skel->format.sizeimage;
 	return 0;
 }
 
@@ -509,7 +508,7 @@ static int skeleton_s_dv_timings(struct file *file, void *_fh,
 		return -EINVAL;
 
 	/* Return 0 if the new timings are the same as the current timings. */
-	if (v4l2_match_dv_timings(timings, &skel->timings, 0))
+	if (v4l2_match_dv_timings(timings, &skel->timings, 0, false))
 		return 0;
 
 	/*
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 092ee9fbaf2b..07e4cdf02407 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1451,6 +1451,7 @@ struct kvm_irq_routing_entry {
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
 		struct kvm_irq_routing_s390_adapter adapter;
+		struct kvm_irq_routing_hv_sint hv_sint;
 		__u32 pad[8];
 	} u;
 };
@@ -1459,6 +1460,7 @@ struct kvm_irq_routing_entry {
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
 
 No flags are specified so far, the corresponding field must be set to zero.
 
@@ -1482,6 +1484,10 @@ struct kvm_irq_routing_s390_adapter {
 	__u32 adapter_id;
 };
 
+struct kvm_irq_routing_hv_sint {
+	__u32 vcpu;
+	__u32 sint;
+};
 
 4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
 
@@ -3019,7 +3025,7 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
 which is the maximum number of possibly pending cpu-local interrupts.
 
-4.90 KVM_SMI
+4.96 KVM_SMI
 
 Capability: KVM_CAP_X86_SMM
 Architectures: x86
@@ -3331,6 +3337,28 @@ the userspace IOAPIC should process the EOI and retrigger the interrupt if
 it is still asserted.  Vector is the LAPIC interrupt vector for which the
 EOI was received.
 
+		struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC          1
+			__u32 type;
+			union {
+				struct {
+					__u32 msr;
+					__u64 control;
+					__u64 evt_page;
+					__u64 msg_page;
+				} synic;
+			} u;
+		};
+		/* KVM_EXIT_HYPERV */
+                struct kvm_hyperv_exit hyperv;
+Indicates that the VCPU exits into userspace to process some tasks
+related to Hyper-V emulation.
+Valid values for 'type' are:
+	KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
+Hyper-V SynIC state change. Notification is used to remap SynIC
+event/message pages and to enable/disable SynIC messages/events processing
+in userspace.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -3685,3 +3713,16 @@ available, means that that the kernel has an implementation of the
 H_RANDOM hypercall backed by a hardware random-number generator.
 If present, the kernel H_RANDOM handler can be enabled for guest use
 with the KVM_CAP_PPC_ENABLE_HCALL capability.
+
+8.2 KVM_CAP_HYPERV_SYNIC
+
+Architectures: x86
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel has an implementation of the
+Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
+used to support Windows Hyper-V based guest paravirt drivers(VMBus).
+
+In order to use SynIC, it has to be activated by setting this
+capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
+will disable the use of APIC hardware virtualization even if supported
+by the CPU, as it's incompatible with SynIC auto-EOI behavior.
diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt
index 2d09d1ed86d0..f083a168eb35 100644
--- a/Documentation/virtual/kvm/devices/vm.txt
+++ b/Documentation/virtual/kvm/devices/vm.txt
@@ -37,7 +37,8 @@ Returns: -EFAULT if the given address is not accessible
 Allows userspace to query the actual limit and set a new limit for
 the maximum guest memory size. The limit will be rounded up to
 2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
-the number of page table levels.
+the number of page table levels. In the case that there is no limit we will set
+the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
 
 2. GROUP: KVM_S390_VM_CPU_MODEL
 Architectures: s390
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 3a4d681c3e98..c81731096a43 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -203,10 +203,10 @@ Shadow pages contain the following information:
     page cannot be destroyed.  See role.invalid.
   parent_ptes:
     The reverse mapping for the pte/ptes pointing at this page's spt. If
-    parent_ptes bit 0 is zero, only one spte points at this pages and
+    parent_ptes bit 0 is zero, only one spte points at this page and
     parent_ptes points at this single spte, otherwise, there exists multiple
     sptes pointing at this page and (parent_ptes & ~0x1) points at a data
-    structure with a list of parent_ptes.
+    structure with a list of parent sptes.
   unsync:
     If true, then the translations in this page may not match the guest's
     translation.  This is equivalent to the state of the tlb when a pte is
@@ -358,7 +358,8 @@ In the first case there are two additional complications:
 - if CR4.SMEP is enabled: since we've turned the page into a kernel page,
   the kernel may now execute it.  We handle this by also setting spte.nx.
   If we get a user fetch or read fault, we'll change spte.u=1 and
-  spte.nx=gpte.nx back.
+  spte.nx=gpte.nx back.  For this to work, KVM forces EFER.NX to 1 when
+  shadow paging is in use.
 - if CR4.SMAP is disabled: since the page has been changed to a kernel
   page, it can not be reused when CR4.SMAP is enabled. We set
   CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index 699d8ea5c230..f0d340959319 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -8,7 +8,7 @@ SLUB can enable debugging only for selected slabs in order to avoid
 an impact on overall system performance which may make a bug more
 difficult to find.
 
-In order to switch debugging on one can add a option "slub_debug"
+In order to switch debugging on one can add an option "slub_debug"
 to the kernel command line. That will enable full debugging for
 all slabs.
 
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 8a282687ee06..21cf34f3ddb2 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -35,10 +35,10 @@ miss is going to run faster.
 
 == Design ==
 
-- "graceful fallback": mm components which don't have transparent
-  hugepage knowledge fall back to breaking a transparent hugepage and
-  working on the regular pages and their respective regular pmd/pte
-  mappings
+- "graceful fallback": mm components which don't have transparent hugepage
+  knowledge fall back to breaking huge pmd mapping into table of ptes and,
+  if necessary, split a transparent hugepage. Therefore these components
+  can continue working on the regular pages or regular pte mappings.
 
 - if a hugepage allocation fails because of memory fragmentation,
   regular pages should be gracefully allocated instead and mixed in
@@ -221,9 +221,18 @@ thp_collapse_alloc_failed is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
 	the allocation.
 
-thp_split is incremented every time a huge page is split into base
+thp_split_page is incremented every time a huge page is split into base
 	pages. This can happen for a variety of reasons but a common
 	reason is that a huge page is old and is being reclaimed.
+	This action implies splitting all PMD the page mapped with.
+
+thp_split_page_failed is is incremented if kernel fails to split huge
+	page. This can happen if the page was pinned by somebody.
+
+thp_split_pmd is incremented every time a PMD split into table of PTEs.
+	This can happen, for instance, when application calls mprotect() or
+	munmap() on part of huge page. It doesn't split huge page, only
+	page table entry.
 
 thp_zero_page_alloc is incremented every time a huge zero page is
 	successfully allocated. It includes allocations which where
@@ -274,10 +283,8 @@ is complete, so they won't ever notice the fact the page is huge. But
 if any driver is going to mangle over the page structure of the tail
 page (like for checking page->mapping or other bits that are relevant
 for the head page and not the tail page), it should be updated to jump
-to check head page instead (while serializing properly against
-split_huge_page() to avoid the head and tail pages to disappear from
-under it, see the futex code to see an example of that, hugetlbfs also
-needed special handling in futex code for similar reasons).
+to check head page instead. Taking reference on any head/tail page would
+prevent page from being split by anyone.
 
 NOTE: these aren't new constraints to the GUP API, and they match the
 same constrains that applies to hugetlbfs too, so any driver capable
@@ -312,9 +319,9 @@ unaffected. libhugetlbfs will also work fine as usual.
 == Graceful fallback ==
 
 Code walking pagetables but unware about huge pmds can simply call
-split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by
+split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by
 pmd_offset. It's trivial to make the code transparent hugepage aware
-by just grepping for "pmd_offset" and adding split_huge_page_pmd where
+by just grepping for "pmd_offset" and adding split_huge_pmd where
 missing after pmd_offset returns the pmd. Thanks to the graceful
 fallback design, with a one liner change, you can avoid to write
 hundred if not thousand of lines of complex code to make your code
@@ -323,7 +330,8 @@ hugepage aware.
 If you're not walking pagetables but you run into a physical hugepage
 but you can't handle it natively in your code, you can split it by
 calling split_huge_page(page). This is what the Linux VM does before
-it tries to swapout the hugepage for example.
+it tries to swapout the hugepage for example. split_huge_page() can fail
+if the page is pinned and you must handle this correctly.
 
 Example to make mremap.c transparent hugepage aware with a one liner
 change:
@@ -335,14 +343,14 @@ diff --git a/mm/mremap.c b/mm/mremap.c
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
-+	split_huge_page_pmd(vma, addr, pmd);
++	split_huge_pmd(vma, pmd, addr);
 	if (pmd_none_or_clear_bad(pmd))
 		return NULL;
 
 == Locking in hugepage aware code ==
 
 We want as much code as possible hugepage aware, as calling
-split_huge_page() or split_huge_page_pmd() has a cost.
+split_huge_page() or split_huge_pmd() has a cost.
 
 To make pagetable walks huge pmd aware, all you need to do is to call
 pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
@@ -351,47 +359,80 @@ created from under you by khugepaged (khugepaged collapse_huge_page
 takes the mmap_sem in write mode in addition to the anon_vma lock). If
 pmd_trans_huge returns false, you just fallback in the old code
 paths. If instead pmd_trans_huge returns true, you have to take the
-mm->page_table_lock and re-run pmd_trans_huge. Taking the
-page_table_lock will prevent the huge pmd to be converted into a
-regular pmd from under you (split_huge_page can run in parallel to the
+page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the
+page table lock will prevent the huge pmd to be converted into a
+regular pmd from under you (split_huge_pmd can run in parallel to the
 pagetable walk). If the second pmd_trans_huge returns false, you
-should just drop the page_table_lock and fallback to the old code as
-before. Otherwise you should run pmd_trans_splitting on the pmd. In
-case pmd_trans_splitting returns true, it means split_huge_page is
-already in the middle of splitting the page. So if pmd_trans_splitting
-returns true it's enough to drop the page_table_lock and call
-wait_split_huge_page and then fallback the old code paths. You are
-guaranteed by the time wait_split_huge_page returns, the pmd isn't
-huge anymore. If pmd_trans_splitting returns false, you can proceed to
-process the huge pmd and the hugepage natively. Once finished you can
-drop the page_table_lock.
-
-== compound_lock, get_user_pages and put_page ==
+should just drop the page table lock and fallback to the old code as
+before. Otherwise you can proceed to process the huge pmd and the
+hugepage natively. Once finished you can drop the page table lock.
+
+== Refcounts and transparent huge pages ==
+
+Refcounting on THP is mostly consistent with refcounting on other compound
+pages:
+
+  - get_page()/put_page() and GUP operate in head page's ->_count.
+
+  - ->_count in tail pages is always zero: get_page_unless_zero() never
+    succeed on tail pages.
+
+  - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
+    on relevant sub-page of the compound page.
+
+  - map/unmap of the whole compound page accounted in compound_mapcount
+    (stored in first tail page).
+
+PageDoubleMap() indicates that ->_mapcount in all subpages is offset up by one.
+This additional reference is required to get race-free detection of unmap of
+subpages when we have them mapped with both PMDs and PTEs.
+
+This is optimization required to lower overhead of per-subpage mapcount
+tracking. The alternative is alter ->_mapcount in all subpages on each
+map/unmap of the whole compound page.
+
+We set PG_double_map when a PMD of the page got split for the first time,
+but still have PMD mapping. The addtional references go away with last
+compound_mapcount.
 
 split_huge_page internally has to distribute the refcounts in the head
-page to the tail pages before clearing all PG_head/tail bits from the
-page structures. It can do that easily for refcounts taken by huge pmd
-mappings. But the GUI API as created by hugetlbfs (that returns head
-and tail pages if running get_user_pages on an address backed by any
-hugepage), requires the refcount to be accounted on the tail pages and
-not only in the head pages, if we want to be able to run
-split_huge_page while there are gup pins established on any tail
-page. Failure to be able to run split_huge_page if there's any gup pin
-on any tail page, would mean having to split all hugepages upfront in
-get_user_pages which is unacceptable as too many gup users are
-performance critical and they must work natively on hugepages like
-they work natively on hugetlbfs already (hugetlbfs is simpler because
-hugetlbfs pages cannot be split so there wouldn't be requirement of
-accounting the pins on the tail pages for hugetlbfs). If we wouldn't
-account the gup refcounts on the tail pages during gup, we won't know
-anymore which tail page is pinned by gup and which is not while we run
-split_huge_page. But we still have to add the gup pin to the head page
-too, to know when we can free the compound page in case it's never
-split during its lifetime. That requires changing not just
-get_page, but put_page as well so that when put_page runs on a tail
-page (and only on a tail page) it will find its respective head page,
-and then it will decrease the head page refcount in addition to the
-tail page refcount. To obtain a head page reliably and to decrease its
-refcount without race conditions, put_page has to serialize against
-__split_huge_page_refcount using a special per-page lock called
-compound_lock.
+page to the tail pages before clearing all PG_head/tail bits from the page
+structures. It can be done easily for refcounts taken by page table
+entries. But we don't have enough information on how to distribute any
+additional pins (i.e. from get_user_pages). split_huge_page() fails any
+requests to split pinned huge page: it expects page count to be equal to
+sum of mapcount of all sub-pages plus one (split_huge_page caller must
+have reference for head page).
+
+split_huge_page uses migration entries to stabilize page->_count and
+page->_mapcount.
+
+We safe against physical memory scanners too: the only legitimate way
+scanner can get reference to a page is get_page_unless_zero().
+
+All tail pages has zero ->_count until atomic_add(). It prevent scanner
+from geting reference to tail page up to the point. After the atomic_add()
+we don't care about ->_count value.  We already known how many references
+with should uncharge from head page.
+
+For head page get_page_unless_zero() will succeed and we don't mind. It's
+clear where reference should go after split: it will stay on head page.
+
+Note that split_huge_pmd() doesn't have any limitation on refcounting:
+pmd can be split at any point and never fails.
+
+== Partial unmap and deferred_split_huge_page() ==
+
+Unmapping part of THP (with munmap() or other way) is not going to free
+memory immediately. Instead, we detect that a subpage of THP is not in use
+in page_remove_rmap() and queue the THP for splitting if memory pressure
+comes. Splitting will free up unused subpages.
+
+Splitting the page right away is not an option due to locking context in
+the place where we can detect partial unmap. It's also might be
+counterproductive since in many cases partial unmap unmap happens during
+exit(2) if an THP crosses VMA boundary.
+
+Function deferred_split_huge_page() is used to queue page for splitting.
+The splitting itself will happen when we get memory pressure via shrinker
+interface.
diff --git a/Documentation/watchdog/watchdog-kernel-api.txt b/Documentation/watchdog/watchdog-kernel-api.txt
index d8b0d3367706..55120a055a14 100644
--- a/Documentation/watchdog/watchdog-kernel-api.txt
+++ b/Documentation/watchdog/watchdog-kernel-api.txt
@@ -44,17 +44,18 @@ The watchdog device structure looks like this:
 
 struct watchdog_device {
 	int id;
-	struct cdev cdev;
-	struct device *dev;
 	struct device *parent;
+	const struct attribute_group **groups;
 	const struct watchdog_info *info;
 	const struct watchdog_ops *ops;
 	unsigned int bootstatus;
 	unsigned int timeout;
 	unsigned int min_timeout;
 	unsigned int max_timeout;
+	struct notifier_block reboot_nb;
+	struct notifier_block restart_nb;
 	void *driver_data;
-	struct mutex lock;
+	struct watchdog_core_data *wd_data;
 	unsigned long status;
 	struct list_head deferred;
 };
@@ -64,27 +65,32 @@ It contains following fields:
   /dev/watchdog0 cdev (dynamic major, minor 0) as well as the old
   /dev/watchdog miscdev. The id is set automatically when calling
   watchdog_register_device.
-* cdev: cdev for the dynamic /dev/watchdog<id> device nodes. This
-  field is also populated by watchdog_register_device.
-* dev: device under the watchdog class (created by watchdog_register_device).
 * parent: set this to the parent device (or NULL) before calling
   watchdog_register_device.
+* groups: List of sysfs attribute groups to create when creating the watchdog
+  device.
 * info: a pointer to a watchdog_info structure. This structure gives some
   additional information about the watchdog timer itself. (Like it's unique name)
 * ops: a pointer to the list of watchdog operations that the watchdog supports.
 * timeout: the watchdog timer's timeout value (in seconds).
 * min_timeout: the watchdog timer's minimum timeout value (in seconds).
 * max_timeout: the watchdog timer's maximum timeout value (in seconds).
+* reboot_nb: notifier block that is registered for reboot notifications, for
+  internal use only. If the driver calls watchdog_stop_on_reboot, watchdog core
+  will stop the watchdog on such notifications.
+* restart_nb: notifier block that is registered for machine restart, for
+  internal use only. If a watchdog is capable of restarting the machine, it
+  should define ops->restart. Priority can be changed through
+  watchdog_set_restart_priority.
 * bootstatus: status of the device after booting (reported with watchdog
   WDIOF_* status bits).
 * driver_data: a pointer to the drivers private data of a watchdog device.
   This data should only be accessed via the watchdog_set_drvdata and
   watchdog_get_drvdata routines.
-* lock: Mutex for WatchDog Timer Driver Core internal use only.
+* wd_data: a pointer to watchdog core internal data.
 * status: this field contains a number of status bits that give extra
   information about the status of the device (Like: is the watchdog timer
-  running/active, is the nowayout bit set, is the device opened via
-  the /dev/watchdog interface or not, ...).
+  running/active, or is the nowayout bit set).
 * deferred: entry in wtd_deferred_reg_list which is used to
   register early initialized watchdogs.
 
@@ -100,8 +106,9 @@ struct watchdog_ops {
 	unsigned int (*status)(struct watchdog_device *);
 	int (*set_timeout)(struct watchdog_device *, unsigned int);
 	unsigned int (*get_timeleft)(struct watchdog_device *);
-	void (*ref)(struct watchdog_device *);
-	void (*unref)(struct watchdog_device *);
+	int (*restart)(struct watchdog_device *);
+	void (*ref)(struct watchdog_device *) __deprecated;
+	void (*unref)(struct watchdog_device *) __deprecated;
 	long (*ioctl)(struct watchdog_device *, unsigned int, unsigned long);
 };
 
@@ -110,20 +117,6 @@ driver's operations. This module owner will be used to lock the module when
 the watchdog is active. (This to avoid a system crash when you unload the
 module and /dev/watchdog is still open).
 
-If the watchdog_device struct is dynamically allocated, just locking the module
-is not enough and a driver also needs to define the ref and unref operations to
-ensure the structure holding the watchdog_device does not go away.
-
-The simplest (and usually sufficient) implementation of this is to:
-1) Add a kref struct to the same structure which is holding the watchdog_device
-2) Define a release callback for the kref which frees the struct holding both
-3) Call kref_init on this kref *before* calling watchdog_register_device()
-4) Define a ref operation calling kref_get on this kref
-5) Define a unref operation calling kref_put on this kref
-6) When it is time to cleanup:
- * Do not kfree() the struct holding both, the last kref_put will do this!
- * *After* calling watchdog_unregister_device() call kref_put on the kref
-
 Some operations are mandatory and some are optional. The mandatory operations
 are:
 * start: this is a pointer to the routine that starts the watchdog timer
@@ -164,34 +157,23 @@ they are supported. These optional routines/operations are:
   (Note: the WDIOF_SETTIMEOUT needs to be set in the options field of the
   watchdog's info structure).
 * get_timeleft: this routines returns the time that's left before a reset.
-* ref: the operation that calls kref_get on the kref of a dynamically
-  allocated watchdog_device struct.
-* unref: the operation that calls kref_put on the kref of a dynamically
-  allocated watchdog_device struct.
+* restart: this routine restarts the machine. It returns 0 on success or a
+  negative errno code for failure.
 * ioctl: if this routine is present then it will be called first before we do
   our own internal ioctl call handling. This routine should return -ENOIOCTLCMD
   if a command is not supported. The parameters that are passed to the ioctl
   call are: watchdog_device, cmd and arg.
 
+The 'ref' and 'unref' operations are no longer used and deprecated.
+
 The status bits should (preferably) be set with the set_bit and clear_bit alike
 bit-operations. The status bits that are defined are:
 * WDOG_ACTIVE: this status bit indicates whether or not a watchdog timer device
   is active or not. When the watchdog is active after booting, then you should
   set this status bit (Note: when you register the watchdog timer device with
   this bit set, then opening /dev/watchdog will skip the start operation)
-* WDOG_DEV_OPEN: this status bit shows whether or not the watchdog device
-  was opened via /dev/watchdog.
-  (This bit should only be used by the WatchDog Timer Driver Core).
-* WDOG_ALLOW_RELEASE: this bit stores whether or not the magic close character
-  has been sent (so that we can support the magic close feature).
-  (This bit should only be used by the WatchDog Timer Driver Core).
 * WDOG_NO_WAY_OUT: this bit stores the nowayout setting for the watchdog.
   If this bit is set then the watchdog timer will not be able to stop.
-* WDOG_UNREGISTERED: this bit gets set by the WatchDog Timer Driver Core
-  after calling watchdog_unregister_device, and then checked before calling
-  any watchdog_ops, so that you can be sure that no operations (other then
-  unref) will get called after unregister, even if userspace still holds a
-  reference to /dev/watchdog
 
   To set the WDOG_NO_WAY_OUT status bit (before registering your watchdog
   timer device) you can either:
@@ -231,3 +213,18 @@ the device tree (if the module timeout parameter is invalid). Best practice is
 to set the default timeout value as timeout value in the watchdog_device and
 then use this function to set the user "preferred" timeout value.
 This routine returns zero on success and a negative errno code for failure.
+
+To disable the watchdog on reboot, the user must call the following helper:
+
+static inline void watchdog_stop_on_reboot(struct watchdog_device *wdd);
+
+To change the priority of the restart handler the following helper should be
+used:
+
+void watchdog_set_restart_priority(struct watchdog_device *wdd, int priority);
+
+User should follow the following guidelines for setting the priority:
+* 0: should be called in last resort, has limited restart capabilities
+* 128: default restart handler, use if no other handler is expected to be
+  available, and/or if restart is sufficient to restart the entire system
+* 255: highest priority, will preempt all other restart handlers
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index 9f9ec9f76039..4e4b6f10d841 100644
--- a/Documentation/watchdog/watchdog-parameters.txt
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -400,3 +400,7 @@ wm8350_wdt:
 nowayout: Watchdog cannot be stopped once started
 	(default=kernel config parameter)
 -------------------------------------------------
+sun4v_wdt:
+timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000)
+nowayout: Watchdog cannot be stopped once started
+-------------------------------------------------
diff --git a/Documentation/zh_CN/video4linux/v4l2-framework.txt b/Documentation/zh_CN/video4linux/v4l2-framework.txt
index 2b828e631e31..698660b7f21f 100644
--- a/Documentation/zh_CN/video4linux/v4l2-framework.txt
+++ b/Documentation/zh_CN/video4linux/v4l2-framework.txt
@@ -289,13 +289,13 @@ struct v4l2_subdev_ops {
 然后，你必须用一个唯一的名字初始化 subdev->name，并初始化模块的
 owner 域。若使用 i2c 辅助函数，这些都会帮你处理好。
 
-若需同媒体框架整合，你必须调用 media_entity_init() 初始化 v4l2_subdev
+若需同媒体框架整合，你必须调用 media_entity_pads_init() 初始化 v4l2_subdev
 结构体中的 media_entity 结构体（entity 域）：
 
 	struct media_pad *pads = &my_sd->pads;
 	int err;
 
-	err = media_entity_init(&sd->entity, npads, pads, 0);
+	err = media_entity_pads_init(&sd->entity, npads, pads);
 
 pads 数组必须预先初始化。无须手动设置 media_entity 的 type 和
 name 域，但如有必要，revision 域必须初始化。
@@ -596,13 +596,13 @@ void v4l2_disable_ioctl(struct video_device *vdev, unsigned int cmd);
 v4l2_file_operations 结构体是 file_operations 的一个子集。其主要
 区别在于：因 inode 参数从未被使用，它将被忽略。
 
-如果需要与媒体框架整合，你必须通过调用 media_entity_init() 初始化
+如果需要与媒体框架整合，你必须通过调用 media_entity_pads_init() 初始化
 嵌入在 video_device 结构体中的 media_entity（entity 域）结构体：
 
 	struct media_pad *pad = &my_vdev->pad;
 	int err;
 
-	err = media_entity_init(&vdev->entity, 1, pad, 0);
+	err = media_entity_pads_init(&vdev->entity, 1, pad);
 
 pads 数组必须预先初始化。没有必要手动设置 media_entity 的 type 和
 name 域。