diff options
345 files changed, 4215 insertions, 3247 deletions
@@ -391,6 +391,10 @@ Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> +Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org> +Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index ad168d16968f..867a4bba6bf6 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -41,13 +41,18 @@ or ``VFAT_FS``. To run ``FAT_KUNIT_TEST``, the ``.kunitconfig`` has: CONFIG_MSDOS_FS=y CONFIG_FAT_KUNIT_TEST=y -1. A good starting point for the ``.kunitconfig``, is the KUnit default - config. Run the command: +1. A good starting point for the ``.kunitconfig`` is the KUnit default config. + You can generate it by running: .. code-block:: bash cd $PATH_TO_LINUX_REPO - cp tools/testing/kunit/configs/default.config .kunitconfig + tools/testing/kunit/kunit.py config + cat .kunit/.kunitconfig + +.. note :: + ``.kunitconfig`` lives in the ``--build_dir`` used by kunit.py, which is + ``.kunit`` by default. .. note :: You may want to remove CONFIG_KUNIT_ALL_TESTS from the ``.kunitconfig`` as diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml index 62c3bd4cb28d..7257fd0ae4da 100644 --- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml +++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml @@ -51,7 +51,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml index 5216c27fc0ad..a412a1da950f 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml @@ -39,7 +39,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml index f29789994b18..c2df8d28aaf5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml @@ -83,6 +83,8 @@ properties: required: - compatible - reg + - width-mm + - height-mm - panel-timing unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 817794e56227..4f15463611f8 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -106,6 +106,12 @@ properties: phy-mode: $ref: "#/properties/phy-connection-type" + pcs-handle: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Specifies a reference to a node representing a PCS PHY device on a MDIO + bus to link with an external PHY (phy-handle) if exists. + phy-handle: $ref: /schemas/types.yaml#/definitions/phandle description: diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt index c5ab62c39133..8d157f0295a5 100644 --- a/Documentation/devicetree/bindings/net/micrel.txt +++ b/Documentation/devicetree/bindings/net/micrel.txt @@ -45,20 +45,3 @@ Optional properties: In fiber mode, auto-negotiation is disabled and the PHY can only work in 100base-fx (full and half duplex) modes. - - - lan8814,ignore-ts: If present the PHY will not support timestamping. - - This option acts as check whether Timestamping is supported by - hardware or not. LAN8814 phy support hardware tmestamping. - - - lan8814,latency_rx_10: Configures Latency value of phy in ingress at 10 Mbps. - - - lan8814,latency_tx_10: Configures Latency value of phy in egress at 10 Mbps. - - - lan8814,latency_rx_100: Configures Latency value of phy in ingress at 100 Mbps. - - - lan8814,latency_tx_100: Configures Latency value of phy in egress at 100 Mbps. - - - lan8814,latency_rx_1000: Configures Latency value of phy in ingress at 1000 Mbps. - - - lan8814,latency_tx_1000: Configures Latency value of phy in egress at 1000 Mbps. diff --git a/Documentation/devicetree/bindings/net/xilinx_axienet.txt b/Documentation/devicetree/bindings/net/xilinx_axienet.txt index b8e4894bc634..1aa4c6006cd0 100644 --- a/Documentation/devicetree/bindings/net/xilinx_axienet.txt +++ b/Documentation/devicetree/bindings/net/xilinx_axienet.txt @@ -26,7 +26,8 @@ Required properties: specified, the TX/RX DMA interrupts should be on that node instead, and only the Ethernet core interrupt is optionally specified here. -- phy-handle : Should point to the external phy device. +- phy-handle : Should point to the external phy device if exists. Pointing + this to the PCS/PMA PHY is deprecated and should be avoided. See ethernet.txt file in the same directory. - xlnx,rxmem : Set to allocated memory buffer for Rx/Tx in the hardware @@ -68,6 +69,11 @@ Optional properties: required through the core's MDIO interface (i.e. always, unless the PHY is accessed through a different bus). + - pcs-handle: Phandle to the internal PCS/PMA PHY in SGMII or 1000Base-X + modes, where "pcs-handle" should be used to point + to the PCS/PMA PHY, and "phy-handle" should point to an + external PHY if exists. + Example: axi_ethernet_eth: ethernet@40c00000 { compatible = "xlnx,axi-ethernet-1.00.a"; diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 55006678394a..36a76cbe9095 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -185,6 +185,12 @@ DMA Fence Chain .. kernel-doc:: include/linux/dma-fence-chain.h :internal: +DMA Fence unwrap +~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/dma-fence-unwrap.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 89bb4fa4c362..ddc1dd039337 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -10,21 +10,21 @@ in joining the effort. Design principles ================= -The Distributed Switch Architecture is a subsystem which was primarily designed -to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line) -using Linux, but has since evolved to support other vendors as well. +The Distributed Switch Architecture subsystem was primarily designed to +support Marvell Ethernet switches (MV88E6xxx, a.k.a. Link Street product +line) using Linux, but has since evolved to support other vendors as well. The original philosophy behind this design was to be able to use unmodified Linux tools such as bridge, iproute2, ifconfig to work transparently whether they configured/queried a switch port network device or a regular network device. -An Ethernet switch is typically comprised of multiple front-panel ports, and one -or more CPU or management port. The DSA subsystem currently relies on the +An Ethernet switch typically comprises multiple front-panel ports and one +or more CPU or management ports. The DSA subsystem currently relies on the presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, -gateways, or even top-of-the rack switches. This host Ethernet controller will +gateways, or even top-of-rack switches. This host Ethernet controller will be later referred to as "master" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed @@ -33,14 +33,14 @@ using upstream and downstream Ethernet links between switches. These specific ports are referred to as "dsa" ports in DSA terminology and code. A collection of multiple switches connected to each other is called a "switch tree". -For each front-panel port, DSA will create specialized network devices which are +For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking stack. These specialized network interfaces are referred to as "slave" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" which is a hardware feature making the switch insert a specific tag for each -Ethernet frames it received to/from specific ports to help the management +Ethernet frame it receives to/from specific ports to help the management interface figure out: - what port is this frame coming from @@ -125,7 +125,7 @@ other switches from the same fabric, and in this case, the outermost switch ports must decapsulate the packet. Note that in certain cases, it might be the case that the tagging format used -by a leaf switch (not connected directly to the CPU) to not be the same as what +by a leaf switch (not connected directly to the CPU) is not the same as what the network stack sees. This can be seen with Marvell switch trees, where the CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA) format, but the DSA links are configured to use the shorter (without Ethertype) @@ -270,21 +270,21 @@ These interfaces are specialized in order to: to/from specific switch ports - query the switch for ethtool operations: statistics, link state, Wake-on-LAN, register dumps... -- external/internal PHY management: link, auto-negotiation etc. +- manage external/internal PHY: link, auto-negotiation, etc. These slave network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking -stack/ethtool, and the switch driver implementation. +stack/ethtool and the switch driver implementation. Upon frame transmission from these slave network devices, DSA will look up which -switch tagging protocol is currently registered with these network devices, and +switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. These frames are then queued for transmission using the master network device -``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the +``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the -management interface and delivers these frames to the physical switch port. +management interface and deliver them to the physical switch port. Graphical representation ------------------------ @@ -330,9 +330,9 @@ MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY library and/or to return link status, link partner pages, auto-negotiation -results etc.. +results, etc. -For Ethernet switches which have both external and internal MDIO busses, the +For Ethernet switches which have both external and internal MDIO buses, the slave MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -349,7 +349,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as table indication (when cascading switches) - ``dsa_platform_data``: platform device configuration data which can reference - a collection of dsa_chip_data structure if multiples switches are cascaded, + a collection of dsa_chip_data structures if multiple switches are cascaded, the master network device this switch tree is attached to needs to be referenced @@ -426,7 +426,7 @@ logic basically looks like this: "phy-handle" property, if found, this PHY device is created and registered using ``of_phy_connect()`` -- if Device Tree is used, and the PHY device is "fixed", that is, conforms to +- if Device Tree is used and the PHY device is "fixed", that is, conforms to the definition of a non-MDIO managed PHY as defined in ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered and connected transparently using the special fixed MDIO bus driver @@ -481,7 +481,7 @@ Device Tree DSA features a standardized binding which is documented in ``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query -per-port PHY specific details: interface connection, MDIO bus location etc.. +per-port PHY specific details: interface connection, MDIO bus location, etc. Driver development ================== @@ -509,7 +509,7 @@ Switch configuration - ``setup``: setup function for the switch, this function is responsible for setting up the ``dsa_switch_ops`` private structure with all it needs: register maps, - interrupts, mutexes, locks etc.. This function is also expected to properly + interrupts, mutexes, locks, etc. This function is also expected to properly configure the switch to separate all network interfaces from each other, that is, they should be isolated by the switch hardware itself, typically by creating a Port-based VLAN ID for each port and allowing only the CPU port and the @@ -526,13 +526,13 @@ PHY devices and link management - ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs, if the PHY library PHY driver needs to know about information it cannot obtain on its own (e.g.: coming from switch memory mapped registers), this function - should return a 32-bits bitmask of "flags", that is private between the switch + should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. - ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link - status, auto-negotiation results, link partner pages etc.. + status, auto-negotiation results, link partner pages, etc. - ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error @@ -554,7 +554,7 @@ Ethtool operations ------------------ - ``get_strings``: ethtool function used to query the driver's strings, will - typically return statistics strings, private flags strings etc. + typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and return their values. DSA overlays slave network devices general statistics: @@ -564,7 +564,7 @@ Ethtool operations - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may, for certain implementations also query the master network device + function may for certain implementations also query the master network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -607,14 +607,14 @@ Power management in a fully active state - ``port_enable``: function invoked by the DSA slave network device ndo_open - function when a port is administratively brought up, this function should be - fully enabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought up, this function should + fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware - ``port_disable``: function invoked by the DSA slave network device ndo_close - function when a port is administratively brought down, this function should be - fully disabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought down, this function should + fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is disabled while being a bridge member @@ -622,12 +622,12 @@ Bridge layer ------------ - ``port_bridge_join``: bridge layer function invoked when a given switch port is - added to a bridge, this function should be doing the necessary at the switch - level to permit the joining port from being added to the relevant logical + added to a bridge, this function should do what's necessary at the switch + level to permit the joining port to be added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. - ``port_bridge_leave``: bridge layer function invoked when a given switch port is - removed from a bridge, this function should be doing the necessary at the + removed from a bridge, this function should do what's necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged out at the switch hardware for the switch to (re) learn MAC addresses behind @@ -663,7 +663,7 @@ Bridge layer point for drivers that need to configure the hardware for enabling this feature. -- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoken when a driver +- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver leaves a bridge port which had the TX forwarding offload feature enabled. Bridge VLAN filtering diff --git a/MAINTAINERS b/MAINTAINERS index fd768d43e048..61d9f114c37f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4791,6 +4791,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> M: Nick Desaulniers <ndesaulniers@google.com> +R: Tom Rix <trix@redhat.com> L: llvm@lists.linux.dev S: Supported W: https://clangbuiltlinux.github.io/ @@ -5715,7 +5716,7 @@ W: http://lanana.org/docs/device-list/index.html DEVICE RESOURCE MANAGEMENT HELPERS M: Hans de Goede <hdegoede@redhat.com> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Maintained F: include/linux/devm-helpers.h @@ -8675,7 +8676,6 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h HFI1 DRIVER -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported @@ -9598,6 +9598,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -11208,7 +11209,7 @@ F: scripts/spdxcheck.py LINEAR RANGES HELPERS M: Mark Brown <broonie@kernel.org> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: lib/linear_ranges.c F: lib/test_linear_ranges.c F: include/linux/linear_range.h @@ -14656,7 +14657,6 @@ F: drivers/rtc/rtc-optee.c OPA-VNIC DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic @@ -16098,7 +16098,6 @@ F: include/uapi/linux/qemu_fw_cfg.h QIB DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qib/ @@ -16616,7 +16615,6 @@ F: drivers/net/ethernet/rdc/r6040.c RDMAVT - RDMA verbs software M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rdmavt @@ -17011,8 +17009,7 @@ S: Odd Fixes F: drivers/tty/serial/rp2.* ROHM BD99954 CHARGER IC -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/power/supply/bd99954-charger.c F: drivers/power/supply/bd99954-charger.h @@ -17035,8 +17032,7 @@ F: drivers/regulator/bd9571mwv-regulator.c F: include/linux/mfd/bd9571mwv.h ROHM POWER MANAGEMENT IC DEVICE DRIVERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/clk/clk-bd718x7.c F: drivers/gpio/gpio-bd71815.c @@ -21118,7 +21114,7 @@ F: include/linux/regulator/ K: regulator_get_optional VOLTAGE AND CURRENT REGULATOR IRQ HELPERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: drivers/regulator/irq_helpers.c VRF diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..ff8f4511df71 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..c31be7eda9df 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..2b3f3d0544b9 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,9 +91,8 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; phdr.p_type = PT_ARM_MEMTAG_MTE; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..5d7762288a24 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -680,6 +681,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2455d721503e 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -38,6 +38,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..3822666fb73d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 32b20efff5f8..4556c86c3465 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -570,8 +570,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); + ACPI_FLUSH_CPU_CACHE(); while (1) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 9efbfe087de7..762b61f67e6c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -588,19 +588,6 @@ static struct acpi_device *handle_to_device(acpi_handle handle, return adev; } -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) -{ - if (!device) - return -EINVAL; - - *device = handle_to_device(handle, NULL); - if (!*device) - return -ENODEV; - - return 0; -} -EXPORT_SYMBOL(acpi_bus_get_device); - /** * acpi_fetch_acpi_dev - Retrieve ACPI device object. * @handle: ACPI handle associated with the requested ACPI device object. diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index e5641e6c52ee..bb45a9c00514 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,14 +115,16 @@ config SATA_AHCI If unsure, say N. -config SATA_LPM_POLICY +config SATA_MOBILE_LPM_POLICY int "Default SATA Link Power Management policy for low power chipsets" range 0 4 default 0 depends on SATA_AHCI help Select the Default SATA Link Power Management (LPM) policy to use - for chipsets / "South Bridges" designated as supporting low power. + for chipsets / "South Bridges" supporting low-power modes. Such + chipsets are typically found on most laptops but desktops and + servers now also widely use chipsets supporting low power modes. The value set has the following meanings: 0 => Keep firmware settings diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 84456c05e845..397dfd27c90d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1595,7 +1595,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, static void ahci_update_initial_lpm_policy(struct ata_port *ap, struct ahci_host_priv *hpriv) { - int policy = CONFIG_SATA_LPM_POLICY; + int policy = CONFIG_SATA_MOBILE_LPM_POLICY; /* Ignore processing for chipsets that don't use policy */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 6ead58c1b6e5..ad11a4c52fbe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -236,7 +236,7 @@ enum { AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read only registers */ AHCI_HFLAG_USE_LPM_POLICY = (1 << 25), /* chipset that should use - SATA_LPM_POLICY + SATA_MOBILE_LPM_POLICY as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cceedde51126..ca64837641be 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4014,6 +4014,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_NO_DMA_LOG | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b3be7a8f5bea..b1666adc1c3a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt); void ata_sff_lost_interrupt(struct ata_port *ap) { - u8 status; + u8 status = 0; struct ata_queued_cmd *qc; /* Only one outstanding command per SFF channel */ diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index bec33d781ae0..e3263e961045 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -137,7 +137,11 @@ struct sata_dwc_device { #endif }; -#define SATA_DWC_QCMD_MAX 32 +/* + * Allow one extra special slot for commands and DMA management + * to account for libata internal commands. + */ +#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1) struct sata_dwc_device_port { struct sata_dwc_device *hsdev; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 4b55e864a0a3..4d3efaa20b7b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1638,22 +1638,22 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); -extern void notify_resource_state(struct sk_buff *, +extern int notify_resource_state(struct sk_buff *, unsigned int, struct drbd_resource *, struct resource_info *, enum drbd_notification_type); -extern void notify_device_state(struct sk_buff *, +extern int notify_device_state(struct sk_buff *, unsigned int, struct drbd_device *, struct device_info *, enum drbd_notification_type); -extern void notify_connection_state(struct sk_buff *, +extern int notify_connection_state(struct sk_buff *, unsigned int, struct drbd_connection *, struct connection_info *, enum drbd_notification_type); -extern void notify_peer_device_state(struct sk_buff *, +extern int notify_peer_device_state(struct sk_buff *, unsigned int, struct drbd_peer_device *, struct peer_device_info *, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 9676a1d214bc..4b0b25cc916e 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2719,6 +2719,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ @@ -2773,12 +2774,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } err = add_disk(disk); if (err) - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2792,8 +2793,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02030c9c4d3b..b7216c186ba4 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -4549,7 +4549,7 @@ static int nla_put_notification_header(struct sk_buff *msg, return drbd_notification_header_to_skb(msg, &nh, true); } -void notify_resource_state(struct sk_buff *skb, +int notify_resource_state(struct sk_buff *skb, unsigned int seq, struct drbd_resource *resource, struct resource_info *resource_info, @@ -4591,16 +4591,17 @@ void notify_resource_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_device_state(struct sk_buff *skb, +int notify_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_device *device, struct device_info *device_info, @@ -4640,16 +4641,17 @@ void notify_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_connection_state(struct sk_buff *skb, +int notify_connection_state(struct sk_buff *skb, unsigned int seq, struct drbd_connection *connection, struct connection_info *connection_info, @@ -4689,16 +4691,17 @@ void notify_connection_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_peer_device_state(struct sk_buff *skb, +int notify_peer_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device *peer_device, struct peer_device_info *peer_device_info, @@ -4739,13 +4742,14 @@ void notify_peer_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } void notify_helper(enum drbd_notification_type type, @@ -4796,7 +4800,7 @@ fail: err, seq); } -static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) { struct drbd_genlmsghdr *dh; int err; @@ -4810,11 +4814,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) if (nla_put_notification_header(skb, NOTIFY_EXISTS)) goto nla_put_failure; genlmsg_end(skb, dh); - return; + return 0; nla_put_failure: nlmsg_free(skb); pr_err("Error %d sending event. Event seq:%u\n", err, seq); + return err; } static void free_state_changes(struct list_head *list) @@ -4841,6 +4846,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) unsigned int seq = cb->args[2]; unsigned int n; enum drbd_notification_type flags = 0; + int err = 0; /* There is no need for taking notification_mutex here: it doesn't matter if the initial state events mix with later state chage @@ -4849,32 +4855,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[5]--; if (cb->args[5] == 1) { - notify_initial_state_done(skb, seq); + err = notify_initial_state_done(skb, seq); goto out; } n = cb->args[4]++; if (cb->args[4] < cb->args[3]) flags |= NOTIFY_CONTINUES; if (n < 1) { - notify_resource_state_change(skb, seq, state_change->resource, + err = notify_resource_state_change(skb, seq, state_change->resource, NOTIFY_EXISTS | flags); goto next; } n--; if (n < state_change->n_connections) { - notify_connection_state_change(skb, seq, &state_change->connections[n], + err = notify_connection_state_change(skb, seq, &state_change->connections[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_connections; if (n < state_change->n_devices) { - notify_device_state_change(skb, seq, &state_change->devices[n], + err = notify_device_state_change(skb, seq, &state_change->devices[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_devices; if (n < state_change->n_devices * state_change->n_connections) { - notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], NOTIFY_EXISTS | flags); goto next; } @@ -4889,7 +4895,10 @@ next: cb->args[4] = 0; } out: - return skb->len; + if (err) + return err; + else + return skb->len; } int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index b8a27818ab3f..4ee11aef6672 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } -void notify_resource_state_change(struct sk_buff *skb, +int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_resource_state_change *resource_state_change, enum drbd_notification_type type) @@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb, .res_susp_fen = resource_state_change->susp_fen[NEW], }; - notify_resource_state(skb, seq, resource, &resource_info, type); + return notify_resource_state(skb, seq, resource, &resource_info, type); } -void notify_connection_state_change(struct sk_buff *skb, +int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_connection_state_change *connection_state_change, enum drbd_notification_type type) @@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb, .conn_role = connection_state_change->peer_role[NEW], }; - notify_connection_state(skb, seq, connection, &connection_info, type); + return notify_connection_state(skb, seq, connection, &connection_info, type); } -void notify_device_state_change(struct sk_buff *skb, +int notify_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_device_state_change *device_state_change, enum drbd_notification_type type) @@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb, .dev_disk_state = device_state_change->disk_state[NEW], }; - notify_device_state(skb, seq, device, &device_info, type); + return notify_device_state(skb, seq, device, &device_info, type); } -void notify_peer_device_state_change(struct sk_buff *skb, +int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device_state_change *p, enum drbd_notification_type type) @@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb, .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], }; - notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); + return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); } static void broadcast_state_change(struct drbd_state_change *state_change) @@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - void (*last_func)(struct sk_buff *, unsigned int, void *, + int (*last_func)(struct sk_buff *, unsigned int, void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index ba80f612d6ab..d5b0479bc9a6 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_ extern void copy_old_to_new_state_change(struct drbd_state_change *); extern void forget_state_change(struct drbd_state_change *); -extern void notify_resource_state_change(struct sk_buff *, +extern int notify_resource_state_change(struct sk_buff *, unsigned int, struct drbd_resource_state_change *, enum drbd_notification_type type); -extern void notify_connection_state_change(struct sk_buff *, +extern int notify_connection_state_change(struct sk_buff *, unsigned int, struct drbd_connection_state_change *, enum drbd_notification_type type); -extern void notify_device_state_change(struct sk_buff *, +extern int notify_device_state_change(struct sk_buff *, unsigned int, struct drbd_device_state_change *, enum drbd_notification_type type); -extern void notify_peer_device_state_change(struct sk_buff *, +extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, struct drbd_peer_device_state_change *, enum drbd_notification_type type); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 7bd10d63ddbe..2dc9da683a13 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1365,7 +1365,6 @@ out_free: */ int cdrom_number_of_slots(struct cdrom_device_info *cdi) { - int status; int nslots = 1; struct cdrom_changer_info *info; @@ -1377,7 +1376,7 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) if (!info) return -ENOMEM; - if ((status = cdrom_read_mech_status(cdi, info)) == 0) + if (cdrom_read_mech_status(cdi, info) == 0) nslots = info->hdr.nslots; kfree(info); diff --git a/drivers/char/random.c b/drivers/char/random.c index 1d8242969751..e15063d61460 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -437,11 +437,8 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], * This shouldn't be set by functions like add_device_randomness(), * where we can't trust the buffer passed to it is guaranteed to be * unpredictable (so it might not have any entropy at all). - * - * Returns the number of bytes processed from input, which is bounded - * by CRNG_INIT_CNT_THRESH if account is true. */ -static size_t crng_pre_init_inject(const void *input, size_t len, bool account) +static void crng_pre_init_inject(const void *input, size_t len, bool account) { static int crng_init_cnt = 0; struct blake2s_state hash; @@ -452,18 +449,15 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) spin_lock_irqsave(&base_crng.lock, flags); if (crng_init != 0) { spin_unlock_irqrestore(&base_crng.lock, flags); - return 0; + return; } - if (account) - len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); - blake2s_update(&hash, base_crng.key, sizeof(base_crng.key)); blake2s_update(&hash, input, len); blake2s_final(&hash, base_crng.key); if (account) { - crng_init_cnt += len; + crng_init_cnt += min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { ++base_crng.generation; crng_init = 1; @@ -474,8 +468,6 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) if (crng_init == 1) pr_notice("fast init done\n"); - - return len; } static void _get_random_bytes(void *buf, size_t nbytes) @@ -531,7 +523,6 @@ EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) { - bool large_request = nbytes > 256; ssize_t ret = 0; size_t len; u32 chacha_state[CHACHA_STATE_WORDS]; @@ -540,22 +531,23 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) if (!nbytes) return 0; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, output, len); - - if (copy_to_user(buf, output, len)) - return -EFAULT; - nbytes -= len; - buf += len; - ret += len; - - while (nbytes) { - if (large_request && need_resched()) { - if (signal_pending(current)) - break; - schedule(); - } + /* + * Immediately overwrite the ChaCha key at index 4 with random + * bytes, in case userspace causes copy_to_user() below to sleep + * forever, so that we still retain forward secrecy in that case. + */ + crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); + /* + * However, if we're doing a read of len <= 32, we don't need to + * use chacha_state after, so we can simply return those bytes to + * the user directly. + */ + if (nbytes <= CHACHA_KEY_SIZE) { + ret = copy_to_user(buf, &chacha_state[4], nbytes) ? -EFAULT : nbytes; + goto out_zero_chacha; + } + do { chacha20_block(chacha_state, output); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; @@ -569,10 +561,18 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) nbytes -= len; buf += len; ret += len; - } - memzero_explicit(chacha_state, sizeof(chacha_state)); + BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0); + if (!(ret % PAGE_SIZE) && nbytes) { + if (signal_pending(current)) + break; + cond_resched(); + } + } while (nbytes); + memzero_explicit(output, sizeof(output)); +out_zero_chacha: + memzero_explicit(chacha_state, sizeof(chacha_state)); return ret; } @@ -1141,12 +1141,9 @@ void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy) { if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) { - size_t ret = crng_pre_init_inject(buffer, count, true); - mix_pool_bytes(buffer, ret); - count -= ret; - buffer += ret; - if (!count || crng_init == 0) - return; + crng_pre_init_inject(buffer, count, true); + mix_pool_bytes(buffer, count); + return; } /* @@ -1545,6 +1542,13 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, { static int maxwarn = 10; + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + if (!crng_ready() && maxwarn > 0) { maxwarn--; if (__ratelimit(&urandom_warning)) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8a7267d116b7..3f2182d66829 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -436,7 +436,6 @@ static int wait_for_media_ready(struct cxl_dev_state *cxlds) for (i = mbox_ready_timeout; i; i--) { u32 temp; - int rc; rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 511805dbeb75..4c9eb53ba3f8 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -12,6 +12,7 @@ dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index cb1bacb5a42b..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index 97d73aaa31da..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,4 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..039f016b57be --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence-unwrap.h> +#if 0 +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> +#endif + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return NULL; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto cleanup; + return &array->base; + +cleanup: + for (i = 0; i < num_fences; ++i) + dma_fence_put(fences[i]); + kfree(fences); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(array); + return 0; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..514d213261df 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file, return 0; } -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - static void add_fence(struct dma_fence **fences, int *i, struct dma_fence *fence) { @@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences, static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { + struct dma_fence *a_fence, *b_fence, **fences; + struct dma_fence_unwrap a_iter, b_iter; + unsigned int index, num_fences; struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; + num_fences = 0; + dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence) + ++num_fences; + dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence) + ++num_fences; - num_fences = a_num_fences + b_num_fences; + if (num_fences > INT_MAX) + goto err_free_sync_file; fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); if (!fences) - goto err; + goto err_free_sync_file; /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. + * We can't guarantee that fences in both a and b are ordered, but it is + * still quite likely. * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. + * So attempt to order the fences as we pass over them and merge fences + * with the same context. */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); + index = 0; + for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter), + b_fence = dma_fence_unwrap_first(b->fence, &b_iter); + a_fence || b_fence; ) { + + if (!b_fence) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + + } else if (!a_fence) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (a_fence->context < b_fence->context) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); + } else if (b_fence->context < a_fence->context) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno, + a_fence->ops)) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); - i_b++; } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; + add_fence(fences, &index, b_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); } } - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); + if (index == 0) + fences[index++] = dma_fence_get_stub(); - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; + if (num_fences > index) { + struct dma_fence **tmp; - fences = nfences; + /* Keep going even when reducing the size failed */ + tmp = krealloc_array(fences, index, sizeof(*fences), + GFP_KERNEL); + if (tmp) + fences = tmp; } - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; + if (sync_file_set_fence(sync_file, fences, index) < 0) + goto err_put_fences; strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; -err: - while (i) - dma_fence_put(fences[--i]); +err_put_fences: + while (index) + dma_fence_put(fences[--index]); kfree(fences); + +err_free_sync_file: fput(sync_file->file); return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e59884cc12a7..085348e08986 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; +#ifdef CONFIG_GPIOLIB_IRQCHIP + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + if (!gc->irq.initialized) + return -EPROBE_DEFER; +#endif + if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; @@ -1593,6 +1603,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, acpi_gpiochip_request_interrupts(gc); + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before initialization of above + * GPIO chip irq members. + */ + barrier(); + + gc->irq.initialized = true; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..b03663f42cc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..940752488330 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..5228421b0f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b30656959fd8..62139ff35476 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..22dabe596dfc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..77ef9d1f9ea8 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -525,6 +526,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,13 +720,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; bool ignore_dpref_ss; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index c3e141c19a77..781334b395ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ab910deed481..4290eaf11a04 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..3fe4bfbb98a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..5504d81c77b7 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -500,6 +511,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +526,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 026e4e29a0f3..f4df344509a8 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -214,6 +214,29 @@ int drm_of_encoder_active_endpoint(struct device_node *node, } EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint); +static int find_panel_or_bridge(struct device_node *node, + struct drm_panel **panel, + struct drm_bridge **bridge) +{ + if (panel) { + *panel = of_drm_find_panel(node); + if (!IS_ERR(*panel)) + return 0; + + /* Clear the panel pointer in case of error. */ + *panel = NULL; + } + + /* No panel found yet, check for a bridge next. */ + if (bridge) { + *bridge = of_drm_find_bridge(node); + if (*bridge) + return 0; + } + + return -EPROBE_DEFER; +} + /** * drm_of_find_panel_or_bridge - return connected panel or bridge device * @np: device tree node containing encoder output ports @@ -236,66 +259,44 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, struct drm_panel **panel, struct drm_bridge **bridge) { - int ret = -EPROBE_DEFER; - struct device_node *remote; + struct device_node *node; + int ret; if (!panel && !bridge) return -EINVAL; + if (panel) *panel = NULL; - - /** - * Devices can also be child nodes when we also control that device - * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). - * - * Lookup for a child node of the given parent that isn't either port - * or ports. - */ - for_each_available_child_of_node(np, remote) { - if (of_node_name_eq(remote, "port") || - of_node_name_eq(remote, "ports")) - continue; - - goto of_find_panel_or_bridge; + if (bridge) + *bridge = NULL; + + /* Check for a graph on the device node first. */ + if (of_graph_is_present(np)) { + node = of_graph_get_remote_node(np, port, endpoint); + if (node) { + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + + if (!ret) + return 0; + } } - /* - * of_graph_get_remote_node() produces a noisy error message if port - * node isn't found and the absence of the port is a legit case here, - * so at first we silently check whether graph presents in the - * device-tree node. - */ - if (!of_graph_is_present(np)) - return -ENODEV; - - remote = of_graph_get_remote_node(np, port, endpoint); - -of_find_panel_or_bridge: - if (!remote) - return -ENODEV; + /* Otherwise check for any child node other than port/ports. */ + for_each_available_child_of_node(np, node) { + if (of_node_name_eq(node, "port") || + of_node_name_eq(node, "ports")) + continue; - if (panel) { - *panel = of_drm_find_panel(remote); - if (!IS_ERR(*panel)) - ret = 0; - else - *panel = NULL; - } - - /* No panel found yet, check for a bridge next. */ - if (bridge) { - if (ret) { - *bridge = of_drm_find_bridge(remote); - if (*bridge) - ret = 0; - } else { - *bridge = NULL; - } + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + /* Stop at the first found occurrence. */ + if (!ret) + return 0; } - of_node_put(remote); - return ret; + return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge); diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 87428fb23d9f..a2277a0d6d06 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np); struct imx_hdmi *hdmi; + int ret; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); if (!hdmi) @@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) hdmi->bridge = of_drm_find_bridge(np); if (!hdmi->bridge) { dev_err(hdmi->dev, "Unable to find bridge\n"); + dw_hdmi_remove(hdmi->hdmi); return -ENODEV; } - return component_add(&pdev->dev, &dw_hdmi_imx_ops); + ret = component_add(&pdev->dev, &dw_hdmi_imx_ops); + if (ret) + dw_hdmi_remove(hdmi->hdmi); + + return ret; } static int dw_hdmi_imx_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index e5078d03020d..fb0e951248f6 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev, edidp = of_get_property(child, "edid", &edid_len); if (edidp) { channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); + if (!channel->edid) + return -ENOMEM; } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06cb1a59b9bc..63ba2ad84679 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + drm_mode_destroy(connector->dev, mode); return ret; + } drm_mode_copy(mode, &imxpd->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index e1772211b0a4..612310d5d481 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -216,6 +216,7 @@ gm20b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gf100_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c index 6bf7fc1bd1e3..1a6f9c3af5ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -23,7 +23,7 @@ */ #include "priv.h" -static void +void gp102_pmu_reset(struct nvkm_pmu *pmu) { struct nvkm_device *device = pmu->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index ba1583bb618b..94cfb1791af6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -83,6 +83,7 @@ gp10b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gp102_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h index bcaade758ff7..21abf31f4442 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32); bool gf100_pmu_enabled(struct nvkm_pmu *); void gf100_pmu_reset(struct nvkm_pmu *); +void gp102_pmu_reset(struct nvkm_pmu *pmu); void gk110_pmu_pgob(struct nvkm_pmu *, bool); diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index a07ef26234e5..6826f4d4826a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc, int ret; vcc = devm_regulator_get_optional(dev, "vcc"); - if (IS_ERR(vcc)) + if (IS_ERR(vcc)) { dev_err(dev, "get optional vcc failed\n"); + vcc = NULL; + } dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver, struct mipi_dbi_dev, drm); diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 666223c6bec4..0a34e0ab4fe6 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di, error = rate / (sig->mode.pixelclock / 1000); - dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n", - rate, div, (signed)(error - 1000) / 10, error % 10); + dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n", + rate, div, error < 1000 ? '-' : '+', + abs(error - 1000) / 10, abs(error - 1000) % 10); /* Allow a 1% error */ if (error < 1010 && error >= 990) { diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 26d269ba947c..85a2142c9384 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * execute: * * (a) In the "normal (i.e., not resuming from hibernation)" path, - * the full barrier in smp_store_mb() guarantees that the store + * the full barrier in virt_store_mb() guarantees that the store * is propagated to all CPUs before the add_channel_work work * is queued. In turn, add_channel_work is queued before the * channel's ring buffer is allocated/initialized and the @@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * recv_int_page before retrieving the channel pointer from the * array of channels. * - * (b) In the "resuming from hibernation" path, the smp_store_mb() + * (b) In the "resuming from hibernation" path, the virt_store_mb() * guarantees that the store is propagated to all CPUs before * the VMBus connection is marked as ready for the resume event * (cf. check_ready_for_resume_event()). The interrupt handler * of the VMBus driver and vmbus_chan_sched() can not run before * vmbus_bus_resume() has completed execution (cf. resume_noirq). */ - smp_store_mb( + virt_store_mb( vmbus_connection.channels[channel->offermsg.child_relid], channel); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 439f99b8b5de..3248b48f37f6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/kthread.h> #include <linux/completion.h> +#include <linux/count_zeros.h> #include <linux/memory_hotplug.h> #include <linux/memory.h> #include <linux/notifier.h> @@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm) struct dm_status status; unsigned long now = jiffies; unsigned long last_post = last_post_time; + unsigned long num_pages_avail, num_pages_committed; if (pressure_report_delay > 0) { --pressure_report_delay; @@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm) * num_pages_onlined) as committed to the host, otherwise it can try * asking us to balloon them out. */ - status.num_avail = si_mem_available(); - status.num_committed = vm_memory_committed() + + num_pages_avail = si_mem_available(); + num_pages_committed = vm_memory_committed() + dm->num_pages_ballooned + (dm->num_pages_added > dm->num_pages_onlined ? dm->num_pages_added - dm->num_pages_onlined : 0) + compute_balloon_floor(); - trace_balloon_status(status.num_avail, status.num_committed, + trace_balloon_status(num_pages_avail, num_pages_committed, vm_memory_committed(), dm->num_pages_ballooned, dm->num_pages_added, dm->num_pages_onlined); + + /* Convert numbers of pages into numbers of HV_HYP_PAGEs. */ + status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE; + status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE; + /* * If our transaction ID is no longer current, just don't * send the status. This can happen if we were interrupted @@ -1653,6 +1660,38 @@ static void disable_page_reporting(void) } } +static int ballooning_enabled(void) +{ + /* + * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE), + * since currently it's unclear to us whether an unballoon request can + * make sure all page ranges are guest page size aligned. + */ + if (PAGE_SIZE != HV_HYP_PAGE_SIZE) { + pr_info("Ballooning disabled because page size is not 4096 bytes\n"); + return 0; + } + + return 1; +} + +static int hot_add_enabled(void) +{ + /* + * Disable hot add on ARM64, because we currently rely on + * memory_add_physaddr_to_nid() to get a node id of a hot add range, + * however ARM64's memory_add_physaddr_to_nid() always return 0 and + * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for + * add_memory(). + */ + if (IS_ENABLED(CONFIG_ARM64)) { + pr_info("Memory hot add disabled on ARM64\n"); + return 0; + } + + return 1; +} + static int balloon_connect_vsp(struct hv_device *dev) { struct dm_version_request version_req; @@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev) * currently still requires the bits to be set, so we have to add code * to fail the host's hot-add and balloon up/down requests, if any. */ - cap_msg.caps.cap_bits.balloon = 1; - cap_msg.caps.cap_bits.hot_add = 1; + cap_msg.caps.cap_bits.balloon = ballooning_enabled(); + cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* * Specify our alignment requirements as it relates diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index c1dd21d0d7ef..ae68298c0dca 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,6 +20,7 @@ #include <linux/panic_notifier.h> #include <linux/ptrace.h> #include <linux/slab.h> +#include <linux/dma-map-ops.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +void hv_setup_dma_ops(struct device *dev, bool coherent) +{ + /* + * Hyper-V does not offer a vIOMMU in the guest + * VM, so pass 0/NULL for the IOMMU settings + */ + arch_setup_dma_ops(dev, 0, 0, NULL, coherent); +} +EXPORT_SYMBOL_GPL(hv_setup_dma_ops); + bool hv_is_hibernation_supported(void) { return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 71efacb90965..3d215d9dec43 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; - u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + u32 write_loc; + + /* + * The Hyper-V host writes the packet data, then uses + * store_release() to update the write_index. Use load_acquire() + * here to prevent loads of the packet data from being re-ordered + * before the read of the write_index and potentially getting + * stale data. + */ + write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 60ee8b329f9e..14de17087864 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE && hyperv_report_reg()) { @@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (hyperv_report_reg()) hyperv_report_panic(regs, val, true); @@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device) } /* + * vmbus_dma_configure -- Configure DMA coherence for VMbus device + */ +static int vmbus_dma_configure(struct device *child_device) +{ + /* + * On ARM64, propagate the DMA coherence setting from the top level + * VMbus ACPI device to the child VMbus device being added here. + * On x86/x64 coherence is assumed and these calls have no effect. + */ + hv_setup_dma_ops(child_device, + device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + return 0; +} + +/* * vmbus_remove - Remove a vmbus device */ static void vmbus_remove(struct device *child_device) @@ -1040,6 +1055,7 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, + .dma_configure = vmbus_dma_configure, .dev_groups = vmbus_dev_groups, .drv_groups = vmbus_drv_groups, .bus_groups = vmbus_bus_groups, @@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Only register if the crash MSRs are available */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { u64 hyperv_crash_ctl; /* - * Sysctl registration is not fatal, since by default - * reporting is enabled. + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. */ hv_ctl_table_hdr = register_sysctl_table(hv_root_table); if (!hv_ctl_table_hdr) @@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj) child_device_obj->device.parent = &hv_acpi_dev->dev; child_device_obj->device.release = vmbus_device_release; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; + child_device_obj->device.dma_mask = &child_device_obj->dma_mask; + dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); + /* * Register with the LDM. This will kick off the driver/device * binding...which will eventually call vmbus_match() and vmbus_probe() @@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); - child_device_obj->device.dma_parms = &child_device_obj->dma_parms; - child_device_obj->device.dma_mask = &child_device_obj->dma_mask; - dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); return 0; err_kset_unregister: @@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device) hv_acpi_dev = device; + /* + * Older versions of Hyper-V for ARM64 fail to include the _CCA + * method on the top level VMbus device in the DSDT. But devices + * are hardware coherent in all current Hyper-V use cases, so fix + * up the ACPI device to behave as if _CCA is present and indicates + * hardware coherence. + */ + ACPI_COMPANION_SET(&device->dev, device); + if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) && + device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) { + pr_info("No ACPI _CCA found; assuming coherent device I/O\n"); + device->flags.cca_seen = true; + device->flags.coherent_dma = true; + } + result = acpi_walk_resources(device->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); @@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void) if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { kmsg_dump_unregister(&hv_kmsg_dumper); unregister_die_notifier(&hyperv_die_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_block); } + /* + * The panic notifier is always registered, hence we should + * also unconditionally unregister it here as well. + */ + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_block); + free_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 35f0d5e7533d..1c107d6d03b9 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work) switch (cm_id_priv->id.state) { case IB_CM_REP_SENT: case IB_CM_DREQ_SENT: + case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->msg); break; case IB_CM_ESTABLISHED: @@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work) cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD) ib_cancel_mad(cm_id_priv->msg); break; - case IB_CM_MRA_REP_RCVD: - break; case IB_CM_TIMEWAIT: atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES] [CM_DREQ_COUNTER]); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 876cc78a22cc..7333646021bb 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) unsigned long flags; struct list_head del_list; + /* Prevent freeing of mm until we are completely finished. */ + mmgrab(handler->mn.mm); + /* Unregister first so we don't get any more notifications. */ mmu_notifier_unregister(&handler->mn, handler->mn.mm); @@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) do_remove(handler, &del_list); + /* Now the mm may be freed. */ + mmdrop(handler->mn.mm); + kfree(handler); } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 956f8e875daa..32ef67e9a6a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -574,8 +574,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) spin_lock_irq(&ent->lock); if (ent->disabled) goto out; - if (need_delay) + if (need_delay) { queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ); + goto out; + } remove_cache_mr_locked(ent); queue_adjust_cache_locked(ent); } @@ -625,6 +627,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { struct mlx5_cache_ent *ent = mr->cache_ent; + WRITE_ONCE(dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); ent->available_mrs++; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index ae50b56e8913..8ef112f883a7 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3190,7 +3190,11 @@ serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) { - int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + int lastwqe; + + spin_lock(&sqp->r_lock); + lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + spin_unlock(&sqp->r_lock); sqp->s_flags &= ~RVT_S_BUSY; spin_unlock_irqrestore(&sqp->s_lock, flags); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 4aab631ef517..d9cf2820c02e 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus", sizeof(phandle)); if (num_iommus < 0) - return 0; + return ERR_PTR(-ENODEV); arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL); if (!arch_data) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index e90adfa57950..9b3ba2df71c7 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6658,13 +6658,13 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v) static int mpt_version_proc_show(struct seq_file *m, void *v) { u8 cb_idx; - int scsi, fc, sas, lan, ctl, targ, dmp; + int scsi, fc, sas, lan, ctl, targ; char *drvname; seq_printf(m, "%s-%s\n", "mptlinux", MPT_LINUX_VERSION_COMMON); seq_printf(m, " Fusion MPT base driver\n"); - scsi = fc = sas = lan = ctl = targ = dmp = 0; + scsi = fc = sas = lan = ctl = targ = 0; for (cb_idx = MPT_MAX_PROTOCOL_DRIVERS-1; cb_idx; cb_idx--) { drvname = NULL; if (MptCallbacks[cb_idx]) { diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..506dc900f5c7 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -993,7 +993,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = @@ -1880,6 +1880,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq) brq->data.error || brq->cmd.resp[0] & CMD_ERRORS; } +static int mmc_spi_err_check(struct mmc_card *card) +{ + u32 status = 0; + int err; + + /* + * SPI does not have a TRAN state we have to wait on, instead the + * card is ready again when it no longer holds the line LOW. + * We still have to ensure two things here before we know the write + * was successful: + * 1. The card has not disconnected during busy and we actually read our + * own pull-up, thinking it was still connected, so ensure it + * still responds. + * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a + * just reconnected card after being disconnected during busy. + */ + err = __mmc_send_status(card, &status, 0); + if (err) + return err; + /* All R1 and R2 bits of SPI are errors in our case */ + if (status) + return -EIO; + return 0; +} + static int mmc_blk_busy_cb(void *cb_data, bool *busy) { struct mmc_blk_busy_data *data = cb_data; @@ -1903,9 +1928,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) struct mmc_blk_busy_data cb_data; int err; - if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) + if (rq_data_dir(req) == READ) return 0; + if (mmc_host_is_spi(card->host)) { + err = mmc_spi_err_check(card); + if (err) + mqrq->brq.data.bytes_xfered = 0; + return err; + } + cb_data.card = card; cb_data.status = 0; err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, @@ -2350,6 +2382,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; + bool cache_enabled = false; + bool fua_enabled = false; devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL); if (devidx < 0) { @@ -2429,13 +2463,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->flags |= MMC_BLK_CMD23; } - if (mmc_card_mmc(card) && - md->flags & MMC_BLK_CMD23 && + if (md->flags & MMC_BLK_CMD23 && ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || card->ext_csd.rel_sectors)) { md->flags |= MMC_BLK_REL_WR; - blk_queue_write_cache(md->queue.queue, true, true); + fua_enabled = true; + cache_enabled = true; } + if (mmc_cache_enabled(card->host)) + cache_enabled = true; + + blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..c6ae16d40766 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1995,7 +1995,7 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) /** * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2003,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..8d9bceeff986 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 9c13f2c31365..4566d7fc9055 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -62,8 +62,8 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * excepted the last element which has no constraint on idmasize */ for_each_sg(data->sg, sg, data->sg_len - 1, i) { - if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) || - !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) { + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { dev_err(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); @@ -71,7 +71,7 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, } } - if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) { + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { dev_err(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 2797a9c0f17d..ddb5ca2f559e 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -144,9 +144,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, return clk_get_rate(priv->clk); if (priv->clkh) { + /* HS400 with 4TAP needs different clock settings */ bool use_4tap = priv->quirks && priv->quirks->hs400_4taps; - bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) || - (host->mmc->ios.timing == MMC_TIMING_MMC_HS400); + bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400; clkh_shift = use_4tap && need_slow_clkh ? 1 : 2; ref_clk = priv->clkh; } @@ -396,10 +396,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc) SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) | sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - /* Set the sampling clock selection range of HS400 mode */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL, SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN | - 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT); + sd_scc_read32(host, priv, + SH_MOBILE_SDHI_SCC_DTCNTL)); /* Avoid bad TAP */ if (bad_taps & BIT(priv->tap_set)) { diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 666cee4c7f7c..08e838400b52 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); - - /* - * For some reason the controller's Host Control2 register reports - * the bit representing 1.8V signaling as 0 when read after it was - * written as 1. Subsequent read reports 1. - * - * Since this may cause some issues, do an empty read of the Host - * Control2 register here to circumvent this. - */ - sdhci_readw(host, SDHCI_HOST_CONTROL2); } static unsigned int xenon_get_max_clock(struct sdhci_host *host) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1c28495875cf..874fad0a5cf8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3253,6 +3253,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) } qidx = bp->tc_to_qidx[j]; ring->queue_id = bp->q_info[qidx].queue_id; + spin_lock_init(&txr->xdp_tx_lock); if (i < bp->tx_nr_rings_xdp) continue; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) @@ -10338,6 +10339,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (irq_re_init) udp_tunnel_nic_reset_ntf(bp->dev); + if (bp->tx_nr_rings_xdp < num_possible_cpus()) { + if (!static_key_enabled(&bnxt_xdp_locking_key)) + static_branch_enable(&bnxt_xdp_locking_key); + } else if (static_key_enabled(&bnxt_xdp_locking_key)) { + static_branch_disable(&bnxt_xdp_locking_key); + } set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 61aa3e8c5952..98453a78cbd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -593,7 +593,8 @@ struct nqe_cn { #define BNXT_MAX_MTU 9500 #define BNXT_MAX_PAGE_MODE_MTU \ ((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \ - XDP_PACKET_HEADROOM) + XDP_PACKET_HEADROOM - \ + SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))) #define BNXT_MIN_PKT_SIZE 52 @@ -800,6 +801,8 @@ struct bnxt_tx_ring_info { u32 dev_state; struct bnxt_ring_struct tx_ring_struct; + /* Synchronize simultaneous xdp_xmit on same ring */ + spinlock_t xdp_tx_lock; }; #define BNXT_LEGACY_COAL_CMPL_PARAMS \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 52fad0fdeacf..03b1d6c04504 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -20,6 +20,8 @@ #include "bnxt.h" #include "bnxt_xdp.h" +DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len) @@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, ring = smp_processor_id() % bp->tx_nr_rings_xdp; txr = &bp->tx_ring[ring]; + if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING) + return -EINVAL; + + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_lock(&txr->xdp_tx_lock); + for (i = 0; i < num_frames; i++) { struct xdp_frame *xdp = frames[i]; - if (!txr || !bnxt_tx_avail(bp, txr) || - !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP)) + if (!bnxt_tx_avail(bp, txr)) break; mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len, @@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, bnxt_db_write(bp, &txr->tx_db, txr->tx_prod); } + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_unlock(&txr->xdp_tx_lock); + return nxmit; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 0df40c3beb05..067bb5e821f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -10,6 +10,8 @@ #ifndef BNXT_XDP_H #define BNXT_XDP_H +DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index 5f5f8c53c4a0..c8cb541572ff 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) base = of_iomap(node, 0); if (!base) { err = -ENOMEM; - goto err_close; + goto err_put; } err = fsl_mc_allocate_irqs(mc_dev); @@ -210,6 +210,8 @@ err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: iounmap(base); +err_put: + of_node_put(node); err_close: dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); err_free_mcp: diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index 5d7aef73df61..fb5120d90f26 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -586,8 +586,8 @@ static int fun_get_dev_limits(struct fun_dev *fdev) /* Calculate the max QID based on SQ/CQ/doorbell counts. * SQ/CQ doorbells alternate. */ - num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) / - (fdev->db_stride * 4); + num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) >> + (2 + NVME_CAP_STRIDE(fdev->cap_reg)); fdev->max_qid = min3(cq_count, sq_count, num_dbs / 2) - 1; fdev->kern_end_qid = fdev->max_qid + 1; return 0; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d4f1874df7d0..8ed3c9ab7ff7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -672,7 +671,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index af57eb114966..85a94483c2ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index b897926f817d..2774cbd5b12a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1480,6 +1480,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; if (dvm_ena) ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; else @@ -2983,6 +2984,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) + ice_clear_dflt_vsi(pf->first_sw); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b588d7995631..d768925785ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -2569,7 +2562,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } @@ -2765,8 +2758,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -3488,6 +3483,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); + if (ret) + goto finish; + } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged @@ -3495,8 +3504,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) */ vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->add_vlan(vsi, &vlan); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3522,6 +3546,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Make sure VLAN delete is successful before updating VLAN @@ -3530,10 +3557,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return 0; + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); + + return ret; } /** @@ -5475,16 +5525,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 3f1a63815bac..69ff4b929772 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1358,9 +1358,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - /* Skip queue if not enabled */ if (!test_bit(vf_q_id, vf->txq_ena)) - continue; + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + vf_q_id, vsi->vsi_num); ice_fill_txq_meta(vsi, ring, &txq_meta); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dfbcaf08520e..866ee4df9671 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -918,7 +920,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 5f9ab1842d49..c18801490649 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ret = of_get_mac_address(pnp, ppd.mac_addr); - if (ret) + if (ret == -EPROBE_DEFER) return ret; mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig index 93df3049cdc0..830363bafcce 100644 --- a/drivers/net/ethernet/micrel/Kconfig +++ b/drivers/net/ethernet/micrel/Kconfig @@ -28,6 +28,7 @@ config KS8842 config KS8851 tristate "Micrel KS8851 SPI" depends on SPI + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 @@ -39,6 +40,7 @@ config KS8851 config KS8851_MLL tristate "Micrel KS8851 MLL" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 50ac3ee2577a..21d2645885ce 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2903,11 +2903,9 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, status = myri10ge_xmit(curr, dev); if (status != 0) { dev_kfree_skb_any(curr); - if (segs != NULL) { - curr = segs; - segs = next; + skb_list_walk_safe(next, curr, next) { curr->next = NULL; - dev_kfree_skb_any(segs); + dev_kfree_skb_any(curr); } goto drop; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index e3edca187ddf..5250d1d1e49c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -489,7 +489,7 @@ struct split_type_defs { #define STATIC_DEBUG_LINE_DWORDS 9 -#define NUM_COMMON_GLOBAL_PARAMS 11 +#define NUM_COMMON_GLOBAL_PARAMS 10 #define MAX_RECURSION_DEPTH 10 diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index b242000a77fd..b7cc36589f59 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq, buf = page_address(bd->data) + bd->page_offset; skb = build_skb(buf, rxq->rx_buf_seg_size); + if (unlikely(!skb)) + return NULL; + skb_reserve(skb, pad); skb_put(skb, len); diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index f9064532beb6..377df8b7f015 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -786,6 +786,85 @@ void efx_remove_channels(struct efx_nic *efx) kfree(efx->xdp_tx_queues); } +static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + +static void efx_set_xdp_channels(struct efx_nic *efx) +{ + struct efx_tx_queue *tx_queue; + struct efx_channel *channel; + unsigned int next_queue = 0; + int xdp_queue_number = 0; + int rc; + + /* We need to mark which channels really have RX and TX + * queues, and adjust the TX queue numbers if we have separate + * RX-only and TX-only channels. + */ + efx_for_each_channel(channel, efx) { + if (channel->channel < efx->tx_channel_offset) + continue; + + if (efx_channel_is_xdp_tx(channel)) { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } else { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is HW %u\n", + channel->channel, tx_queue->label, + tx_queue->queue); + } + + /* If XDP is borrowing queues from net stack, it must + * use the queue with no csum offload, which is the + * first one of the channel + * (note: tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == + EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } + } + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } +} + int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) { struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; @@ -857,6 +936,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) efx_init_napi_channel(efx->channel[i]); } + efx_set_xdp_channels(efx); out: /* Destroy unused channel structures */ for (i = 0; i < efx->n_channels; i++) { @@ -889,26 +969,9 @@ rollback: goto out; } -static inline int -efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, - struct efx_tx_queue *tx_queue) -{ - if (xdp_queue_number >= efx->xdp_tx_queue_count) - return -EINVAL; - - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - tx_queue->channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - return 0; -} - int efx_set_channels(struct efx_nic *efx) { - struct efx_tx_queue *tx_queue; struct efx_channel *channel; - unsigned int next_queue = 0; - int xdp_queue_number; int rc; efx->tx_channel_offset = @@ -926,61 +989,14 @@ int efx_set_channels(struct efx_nic *efx) return -ENOMEM; } - /* We need to mark which channels really have RX and TX - * queues, and adjust the TX queue numbers if we have separate - * RX-only and TX-only channels. - */ - xdp_queue_number = 0; efx_for_each_channel(channel, efx) { if (channel->channel < efx->n_rx_channels) channel->rx_queue.core_index = channel->channel; else channel->rx_queue.core_index = -1; - - if (channel->channel >= efx->tx_channel_offset) { - if (efx_channel_is_xdp_tx(channel)) { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } else { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n", - channel->channel, tx_queue->label, - tx_queue->queue); - } - - /* If XDP is borrowing queues from net stack, it must use the queue - * with no csum offload, which is the first one of the channel - * (note: channel->tx_queue_by_type is not initialized yet) - */ - if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { - tx_queue = &channel->tx_queue[0]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } - } } - WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number != efx->xdp_tx_queue_count); - WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number > efx->xdp_tx_queue_count); - /* If we have more CPUs than assigned XDP TX queues, assign the already - * existing queues to the exceeding CPUs - */ - next_queue = 0; - while (xdp_queue_number < efx->xdp_tx_queue_count) { - tx_queue = efx->xdp_tx_queues[next_queue++]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } + efx_set_xdp_channels(efx); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) @@ -1124,7 +1140,7 @@ void efx_start_channels(struct efx_nic *efx) struct efx_rx_queue *rx_queue; struct efx_channel *channel; - efx_for_each_channel(channel, efx) { + efx_for_each_channel_rev(channel, efx) { efx_for_each_channel_tx_queue(tx_queue, channel) { efx_init_tx_queue(tx_queue); atomic_inc(&efx->active_queues); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 1b22c7be0088..fa8b9aacca11 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -150,6 +150,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue) struct efx_nic *efx = rx_queue->efx; int i; + if (unlikely(!rx_queue->page_ring)) + return; + /* Unmap and release the pages in the recycle ring. Remove the ring. */ for (i = 0; i <= rx_queue->page_ptr_mask; i++) { struct page *page = rx_queue->page_ring[i]; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d16e031e95f4..6983799e1c05 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (unlikely(!tx_queue)) return -EINVAL; + if (!tx_queue->initialised) + return -EINVAL; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index d530cde2b864..9bc8281b7f5b 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "shutting down TX queue %d\n", tx_queue->queue); + tx_queue->initialised = false; + if (!tx_queue->buffer) return; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index ecf759ee1c9f..017dbbda0c1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -205,7 +205,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = { }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); -struct pci_driver loongson_dwmac_driver = { +static struct pci_driver loongson_dwmac_driver = { .name = "dwmac-loongson-pci", .id_table = loongson_dwmac_id_table, .probe = loongson_dwmac_probe, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5d29f336315b..11e1055e8260 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->phylink_node = np; /* Get max speed of operation from device tree */ - if (of_property_read_u32(np, "max-speed", &plat->max_speed)) - plat->max_speed = -1; + of_property_read_u32(np, "max-speed", &plat->max_speed); plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 0f9c88dd1a4a..d5c1e5c4a508 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -433,8 +433,6 @@ struct axienet_local { struct net_device *ndev; struct device *dev; - struct device_node *phy_node; - struct phylink *phylink; struct phylink_config phylink_config; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c7eb05e4a6bf..d6fc3f7acdf0 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2064,25 +2064,33 @@ static int axienet_probe(struct platform_device *pdev) if (ret) goto cleanup_clk; - lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (lp->phy_node) { - ret = axienet_mdio_setup(lp); - if (ret) - dev_warn(&pdev->dev, - "error registering MDIO bus: %d\n", ret); - } + ret = axienet_mdio_setup(lp); + if (ret) + dev_warn(&pdev->dev, + "error registering MDIO bus: %d\n", ret); + if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII || lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) { - if (!lp->phy_node) { - dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); + np = of_parse_phandle(pdev->dev.of_node, "pcs-handle", 0); + if (!np) { + /* Deprecated: Always use "pcs-handle" for pcs_phy. + * Falling back to "phy-handle" here is only for + * backward compatibility with old device trees. + */ + np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + } + if (!np) { + dev_err(&pdev->dev, "pcs-handle (preferred) or phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; goto cleanup_mdio; } - lp->pcs_phy = of_mdio_find_device(lp->phy_node); + lp->pcs_phy = of_mdio_find_device(np); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; + of_node_put(np); goto cleanup_mdio; } + of_node_put(np); lp->pcs.ops = &axienet_pcs_ops; lp->pcs.poll = true; } @@ -2125,8 +2133,6 @@ cleanup_mdio: put_device(&lp->pcs_phy->dev); if (lp->mii_bus) axienet_mdio_teardown(lp); - of_node_put(lp->phy_node); - cleanup_clk: clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); @@ -2155,9 +2161,6 @@ static int axienet_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); - of_node_put(lp->phy_node); - lp->phy_node = NULL; - free_netdev(ndev); return 0; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index baf7afac7857..53846c6b56ca 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -553,7 +553,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; mhdr->ver = 0x01; - return 0; + return sizeof(struct mctp_i2c_hdr); } static int mctp_i2c_tx_thread(void *data) diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c483ba67c21f..582969751b4c 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -102,6 +102,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) u32 val; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret) goto out; @@ -145,6 +148,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id, struct mscc_miim_dev *miim = bus->priv; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret < 0) goto out; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 19b11e896460..fc53b71dc872 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -99,15 +99,6 @@ #define PTP_TIMESTAMP_EN_PDREQ_ BIT(2) #define PTP_TIMESTAMP_EN_PDRES_ BIT(3) -#define PTP_RX_LATENCY_1000 0x0224 -#define PTP_TX_LATENCY_1000 0x0225 - -#define PTP_RX_LATENCY_100 0x0222 -#define PTP_TX_LATENCY_100 0x0223 - -#define PTP_RX_LATENCY_10 0x0220 -#define PTP_TX_LATENCY_10 0x0221 - #define PTP_TX_PARSE_L2_ADDR_EN 0x0284 #define PTP_RX_PARSE_L2_ADDR_EN 0x0244 @@ -268,15 +259,6 @@ struct lan8814_ptp_rx_ts { u16 seq_id; }; -struct kszphy_latencies { - u16 rx_10; - u16 tx_10; - u16 rx_100; - u16 tx_100; - u16 rx_1000; - u16 tx_1000; -}; - struct kszphy_ptp_priv { struct mii_timestamper mii_ts; struct phy_device *phydev; @@ -296,7 +278,6 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; - struct kszphy_latencies latencies; const struct kszphy_type *type; int led_mode; bool rmii_ref_clk_sel; @@ -304,14 +285,6 @@ struct kszphy_priv { u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; -static struct kszphy_latencies lan8814_latencies = { - .rx_10 = 0x22AA, - .tx_10 = 0x2E4A, - .rx_100 = 0x092A, - .tx_100 = 0x02C1, - .rx_1000 = 0x01AD, - .tx_1000 = 0x00C9, -}; static const struct kszphy_type ksz8021_type = { .led_mode_reg = MII_KSZPHY_CTRL_2, .has_broadcast_disable = true, @@ -2618,55 +2591,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) return 0; } -static int lan8814_read_status(struct phy_device *phydev) -{ - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latencies = &priv->latencies; - int err; - int regval; - - err = genphy_read_status(phydev); - if (err) - return err; - - switch (phydev->speed) { - case SPEED_1000: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_1000, - latencies->rx_1000); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_1000, - latencies->tx_1000); - break; - case SPEED_100: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_100, - latencies->rx_100); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_100, - latencies->tx_100); - break; - case SPEED_10: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_10, - latencies->rx_10); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_10, - latencies->tx_10); - break; - default: - break; - } - - /* Make sure the PHY is not broken. Read idle error count, - * and reset the PHY if it is maxed out. - */ - regval = phy_read(phydev, MII_STAT1000); - if ((regval & 0xFF) == 0xFF) { - phy_init_hw(phydev); - phydev->link = 0; - if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) - phydev->drv->config_intr(phydev); - return genphy_config_aneg(phydev); - } - - return 0; -} - static int lan8814_config_init(struct phy_device *phydev) { int val; @@ -2690,30 +2614,8 @@ static int lan8814_config_init(struct phy_device *phydev) return 0; } -static void lan8814_parse_latency(struct phy_device *phydev) -{ - const struct device_node *np = phydev->mdio.dev.of_node; - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latency = &priv->latencies; - u32 val; - - if (!of_property_read_u32(np, "lan8814,latency_rx_10", &val)) - latency->rx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_10", &val)) - latency->tx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_100", &val)) - latency->rx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_100", &val)) - latency->tx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_1000", &val)) - latency->rx_1000 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_1000", &val)) - latency->tx_1000 = val; -} - static int lan8814_probe(struct phy_device *phydev) { - const struct device_node *np = phydev->mdio.dev.of_node; struct kszphy_priv *priv; u16 addr; int err; @@ -2724,13 +2626,10 @@ static int lan8814_probe(struct phy_device *phydev) priv->led_mode = -1; - priv->latencies = lan8814_latencies; - phydev->priv = priv; if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) || - !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING) || - of_property_read_bool(np, "lan8814,ignore-ts")) + !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return 0; /* Strap-in value for PHY address, below register read gives starting @@ -2746,7 +2645,6 @@ static int lan8814_probe(struct phy_device *phydev) return err; } - lan8814_parse_latency(phydev); lan8814_ptp_init(phydev); return 0; @@ -2928,7 +2826,7 @@ static struct phy_driver ksphy_driver[] = { .config_init = lan8814_config_init, .probe = lan8814_probe, .soft_reset = genphy_soft_reset, - .read_status = lan8814_read_status, + .read_status = ksz9031_read_status, .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 88396ff99f03..6865d32270e5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -469,7 +469,7 @@ static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue) spin_lock(&sl->lock); if (netif_queue_stopped(dev)) { - if (!netif_running(dev)) + if (!netif_running(dev) || !sl->tty) goto out; /* May be we must check transmitter timeout here ? diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index ea06d10e1c21..ca409d450a29 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1102,10 +1102,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (start_of_descs != desc_offset) goto err; - /* self check desc_offset from header*/ - if (desc_offset >= skb_len) + /* self check desc_offset from header and make sure that the + * bounds of the metadata array are inside the SKB + */ + if (pkt_count * 2 + desc_offset >= skb_len) goto err; + /* Packets must not overlap the metadata array */ + skb_trim(skb, desc_offset); + if (pkt_count == 0) goto err; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 85e362461d71..cfc30ce4c6e1 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1265,6 +1265,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. @@ -1294,9 +1295,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, - u16 proto) + u16 proto, struct net_device *orig_dev) { - if (skb_mac_header_was_set(skb)) + if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); @@ -1402,6 +1403,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { + struct net_device *orig_dev = skb->dev; + vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; @@ -1410,7 +1413,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, - ETH_P_IPV6); + ETH_P_IPV6, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); @@ -1440,6 +1444,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { + struct net_device *orig_dev = skb->dev; + skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; @@ -1460,7 +1466,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, if (!list_empty(&vrf_dev->ptype_all)) { int err; - err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP); + err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 63e1c2d783c5..73693c66cef1 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1633,7 +1633,7 @@ static void ath10k_sdio_hif_power_down(struct ath10k *ar) return; } - ret = mmc_hw_reset(ar_sdio->func->card->host); + ret = mmc_hw_reset(ar_sdio->func->card); if (ret) ath10k_warn(ar, "unable to reset sdio: %d\n", ret); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ba3c159111d3..55285cad527f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4165,7 +4165,7 @@ static int brcmf_sdio_bus_reset(struct device *dev) /* reset the adapter */ sdio_claim_host(sdiodev->func1); - mmc_hw_reset(sdiodev->func1->card->host); + mmc_hw_reset(sdiodev->func1->card); sdio_release_host(sdiodev->func1); brcmf_bus_change_state(sdiodev->bus_if, BRCMF_BUS_DOWN); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..4f3238d2a171 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -2639,7 +2639,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - ret = mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card); sdio_release_host(func); switch (ret) { diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 72fc41ac83c0..9140b0163474 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -146,7 +146,7 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) * To guarantee that the SDIO card is power cycled, as required to make * the FW programming to succeed, let's do a brute force HW reset. */ - mmc_hw_reset(card->host); + mmc_hw_reset(card); sdio_enable_func(func); sdio_release_host(func); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 558b35aba610..d270a204324e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; #endif hbus->hdev = hdev; diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index afdcb91601d2..1e2d69453771 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -187,7 +187,7 @@ source "drivers/perf/hisilicon/Kconfig" config MARVELL_CN10K_DDR_PMU tristate "Enable MARVELL CN10K DRAM Subsystem(DSS) PMU Support" - depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT) help Enable perf support for Marvell DDR Performance monitoring event on CN10K platform. diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 94ebc1ecace7..b1b2a55de77f 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -29,7 +29,7 @@ #define CNTL_OVER_MASK 0xFFFFFFFE #define CNTL_CSV_SHIFT 24 -#define CNTL_CSV_MASK (0xFF << CNTL_CSV_SHIFT) +#define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) #define EVENT_CYCLES_ID 0 #define EVENT_CYCLES_COUNTER 0 diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 7640491aab12..30234c261b05 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( { u64 mpidr; int cpu_cluster_id; - struct cluster_pmu *cluster = NULL; + struct cluster_pmu *cluster; /* * This assumes that the cluster_id is in MPIDR[aff1] for @@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( cluster->cluster_id); cpumask_set_cpu(cpu, &cluster->cluster_cpus); *per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster; - break; + return cluster; } - return cluster; + return NULL; } static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index 05147d2c3842..485e58b264c0 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -292,6 +292,7 @@ enum atc2603c_reg_ids { .bypass_mask = BIT(5), \ .active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \ .active_discharge_mask = BIT(1), \ + .active_discharge_on = BIT(1), \ .owner = THIS_MODULE, \ } diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c index f21e3f8b21f2..8e13dea354a2 100644 --- a/drivers/regulator/rtq2134-regulator.c +++ b/drivers/regulator/rtq2134-regulator.c @@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = { .enable_mask = RTQ2134_VOUTEN_MASK, \ .active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \ .active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \ + .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \ .ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \ .ramp_mask = RTQ2134_RSPUP_MASK, \ .ramp_delay_table = rtq2134_buck_ramp_delay_table, \ diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index cadea0344486..40befdd9dfa9 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -82,6 +82,35 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .min_uV = 2400000, .uV_step = 100000, .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, + { + .name = "LDO2", + .id = 2, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO2_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_2, + .vsel_mask = WM8994_LDO2_VSEL_MASK, + .ops = &wm8994_ldo2_ops, + .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, +}; + +static const struct regulator_desc wm8958_ldo_desc[] = { + { + .name = "LDO1", + .id = 1, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO1_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_1, + .vsel_mask = WM8994_LDO1_VSEL_MASK, + .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -172,9 +201,16 @@ static int wm8994_ldo_probe(struct platform_device *pdev) * regulator core and we need not worry about it on the * error path. */ - ldo->regulator = devm_regulator_register(&pdev->dev, - &wm8994_ldo_desc[id], - &config); + if (ldo->wm8994->type == WM8994) { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8994_ldo_desc[id], + &config); + } else { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8958_ldo_desc[id], + &config); + } + if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 5f554a3a0f62..caeebfb67149 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -317,14 +317,18 @@ enum { }; struct aha152x_cmd_priv { - struct scsi_pointer scsi_pointer; + char *ptr; + int this_residual; + struct scatterlist *buffer; + int status; + int message; + int sent_command; + int phase; }; -static struct scsi_pointer *aha152x_scsi_pointer(struct scsi_cmnd *cmd) +static struct aha152x_cmd_priv *aha152x_priv(struct scsi_cmnd *cmd) { - struct aha152x_cmd_priv *acmd = scsi_cmd_priv(cmd); - - return &acmd->scsi_pointer; + return scsi_cmd_priv(cmd); } MODULE_AUTHOR("Jürgen Fischer"); @@ -890,17 +894,16 @@ void aha152x_release(struct Scsi_Host *shpnt) static int setup_expected_interrupts(struct Scsi_Host *shpnt) { if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; - if (scsi_pointer->phase & selecting) { + if (acp->phase & selecting) { SETPORT(SSTAT1, SELTO); SETPORT(SIMODE0, ENSELDO | (DISCONNECTED_SC ? ENSELDI : 0)); SETPORT(SIMODE1, ENSELTIMO); } else { - SETPORT(SIMODE0, (scsi_pointer->phase & spiordy) ? ENSPIORDY : 0); + SETPORT(SIMODE0, (acp->phase & spiordy) ? ENSPIORDY : 0); SETPORT(SIMODE1, ENPHASEMIS | ENSCSIRST | ENSCSIPERR | ENBUSFREE); } } else if(STATE==seldi) { @@ -924,17 +927,16 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt) static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, struct completion *complete, int phase) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(SCpnt); + struct aha152x_cmd_priv *acp = aha152x_priv(SCpnt); struct Scsi_Host *shpnt = SCpnt->device->host; unsigned long flags; - scsi_pointer->phase = not_issued | phase; - scsi_pointer->Status = 0x1; /* Ilegal status by SCSI standard */ - scsi_pointer->Message = 0; - scsi_pointer->have_data_in = 0; - scsi_pointer->sent_command = 0; + acp->phase = not_issued | phase; + acp->status = 0x1; /* Illegal status by SCSI standard */ + acp->message = 0; + acp->sent_command = 0; - if (scsi_pointer->phase & (resetting | check_condition)) { + if (acp->phase & (resetting | check_condition)) { if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "cannot reuse command\n"); return FAILED; @@ -957,15 +959,15 @@ static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, SCp.phase : current state of the command */ if ((phase & resetting) || !scsi_sglist(SCpnt)) { - scsi_pointer->ptr = NULL; - scsi_pointer->this_residual = 0; + acp->ptr = NULL; + acp->this_residual = 0; scsi_set_resid(SCpnt, 0); - scsi_pointer->buffer = NULL; + acp->buffer = NULL; } else { scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); - scsi_pointer->buffer = scsi_sglist(SCpnt); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = scsi_sglist(SCpnt); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } DO_LOCK(flags); @@ -1015,7 +1017,7 @@ static void reset_done(struct scsi_cmnd *SCpnt) static void aha152x_scsi_done(struct scsi_cmnd *SCpnt) { - if (aha152x_scsi_pointer(SCpnt)->phase & resetting) + if (aha152x_priv(SCpnt)->phase & resetting) reset_done(SCpnt); else scsi_done(SCpnt); @@ -1101,7 +1103,7 @@ static int aha152x_device_reset(struct scsi_cmnd * SCpnt) DO_LOCK(flags); - if (aha152x_scsi_pointer(SCpnt)->phase & resetted) { + if (aha152x_priv(SCpnt)->phase & resetted) { HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); @@ -1395,31 +1397,30 @@ static void busfree_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRBUSFREE); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase &= ~syncneg; + acp->phase &= ~syncneg; - if (scsi_pointer->phase & completed) { + if (acp->phase & completed) { /* target sent COMMAND COMPLETE */ - done(shpnt, scsi_pointer->Status, DID_OK); + done(shpnt, acp->status, DID_OK); - } else if (scsi_pointer->phase & aborted) { - done(shpnt, scsi_pointer->Status, DID_ABORT); + } else if (acp->phase & aborted) { + done(shpnt, acp->status, DID_ABORT); - } else if (scsi_pointer->phase & resetted) { - done(shpnt, scsi_pointer->Status, DID_RESET); + } else if (acp->phase & resetted) { + done(shpnt, acp->status, DID_RESET); - } else if (scsi_pointer->phase & disconnected) { + } else if (acp->phase & disconnected) { /* target sent DISCONNECT */ #if defined(AHA152X_STAT) HOSTDATA(shpnt)->disconnections++; #endif append_SC(&DISCONNECTED_SC, CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; CURRENT_SC = NULL; } else { @@ -1438,24 +1439,23 @@ static void busfree_run(struct Scsi_Host *shpnt) action++; #endif - if (aha152x_scsi_pointer(DONE_SC)->phase & check_condition) { + if (aha152x_priv(DONE_SC)->phase & check_condition) { struct scsi_cmnd *cmd = HOSTDATA(shpnt)->done_SC; struct aha152x_scdata *sc = SCDATA(cmd); scsi_eh_restore_cmnd(cmd, &sc->ses); - aha152x_scsi_pointer(cmd)->Status = SAM_STAT_CHECK_CONDITION; + aha152x_priv(cmd)->status = SAM_STAT_CHECK_CONDITION; HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - } else if (aha152x_scsi_pointer(DONE_SC)->Status == - SAM_STAT_CHECK_CONDITION) { + } else if (aha152x_priv(DONE_SC)->status == SAM_STAT_CHECK_CONDITION) { #if defined(AHA152X_STAT) HOSTDATA(shpnt)->busfree_with_check_condition++; #endif - if(!(aha152x_scsi_pointer(DONE_SC)->phase & not_issued)) { + if (!(aha152x_priv(DONE_SC)->phase & not_issued)) { struct aha152x_scdata *sc; struct scsi_cmnd *ptr = DONE_SC; DONE_SC=NULL; @@ -1480,7 +1480,7 @@ static void busfree_run(struct Scsi_Host *shpnt) if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - if (!(aha152x_scsi_pointer(ptr)->phase & resetting)) { + if (!(aha152x_priv(ptr)->phase & resetting)) { kfree(ptr->host_scribble); ptr->host_scribble=NULL; } @@ -1503,13 +1503,12 @@ static void busfree_run(struct Scsi_Host *shpnt) DO_UNLOCK(flags); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase |= selecting; + acp->phase |= selecting; /* clear selection timeout */ SETPORT(SSTAT1, SELTO); @@ -1537,13 +1536,13 @@ static void busfree_run(struct Scsi_Host *shpnt) */ static void seldo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); SETPORT(SCSISIG, 0); SETPORT(SSTAT1, CLRBUSFREE); SETPORT(SSTAT1, CLRPHASECHG); - scsi_pointer->phase &= ~(selecting | not_issued); + acp->phase &= ~(selecting | not_issued); SETPORT(SCSISEQ, 0); @@ -1558,12 +1557,12 @@ static void seldo_run(struct Scsi_Host *shpnt) ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); - if (scsi_pointer->phase & aborting) { + if (acp->phase & aborting) { ADDMSGO(ABORT); - } else if (scsi_pointer->phase & resetting) { + } else if (acp->phase & resetting) { ADDMSGO(BUS_DEVICE_RESET); } else if (SYNCNEG==0 && SYNCHRONOUS) { - scsi_pointer->phase |= syncneg; + acp->phase |= syncneg; MSGOLEN += spi_populate_sync_msg(&MSGO(MSGOLEN), 50, 8); SYNCNEG=1; /* negotiation in progress */ } @@ -1578,7 +1577,7 @@ static void seldo_run(struct Scsi_Host *shpnt) */ static void selto_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp; SETPORT(SCSISEQ, 0); SETPORT(SSTAT1, CLRSELTIMO); @@ -1586,9 +1585,10 @@ static void selto_run(struct Scsi_Host *shpnt) if (!CURRENT_SC) return; - scsi_pointer->phase &= ~selecting; + acp = aha152x_priv(CURRENT_SC); + acp->phase &= ~selecting; - if (scsi_pointer->phase & aborted) + if (acp->phase & aborted) done(shpnt, SAM_STAT_GOOD, DID_ABORT); else if (TESTLO(SSTAT0, SELINGO)) done(shpnt, SAM_STAT_GOOD, DID_BUS_BUSY); @@ -1616,10 +1616,9 @@ static void seldi_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRPHASECHG); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - if (!(scsi_pointer->phase & not_issued)) + if (!(acp->phase & not_issued)) scmd_printk(KERN_ERR, CURRENT_SC, "command should not have been issued yet\n"); @@ -1676,7 +1675,7 @@ static void seldi_run(struct Scsi_Host *shpnt) static void msgi_run(struct Scsi_Host *shpnt) { for(;;) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; int sstat1 = GETPORT(SSTAT1); if(sstat1 & (PHASECHG|PHASEMIS|BUSFREE) || !(sstat1 & REQINIT)) @@ -1714,9 +1713,9 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); - scsi_pointer->phase &= ~disconnected; + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); + acp->phase &= ~disconnected; MSGILEN=0; @@ -1724,8 +1723,8 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); switch (MSGI(0)) { case DISCONNECT: @@ -1733,11 +1732,11 @@ static void msgi_run(struct Scsi_Host *shpnt) scmd_printk(KERN_WARNING, CURRENT_SC, "target was not allowed to disconnect\n"); - scsi_pointer->phase |= disconnected; + acp->phase |= disconnected; break; case COMMAND_COMPLETE: - scsi_pointer->phase |= completed; + acp->phase |= completed; break; case MESSAGE_REJECT: @@ -1867,11 +1866,9 @@ static void msgi_end(struct Scsi_Host *shpnt) */ static void msgo_init(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if(MSGOLEN==0) { - if ((scsi_pointer->phase & syncneg) && SYNCNEG==2 && - SYNCRATE==0) { + if ((aha152x_priv(CURRENT_SC)->phase & syncneg) && + SYNCNEG == 2 && SYNCRATE == 0) { ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); } else { scmd_printk(KERN_INFO, CURRENT_SC, @@ -1888,7 +1885,7 @@ static void msgo_init(struct Scsi_Host *shpnt) */ static void msgo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); while(MSGO_I<MSGOLEN) { if (TESTLO(SSTAT0, SPIORDY)) @@ -1901,13 +1898,13 @@ static void msgo_run(struct Scsi_Host *shpnt) if (MSGO(MSGO_I) & IDENTIFY_BASE) - scsi_pointer->phase |= identified; + acp->phase |= identified; if (MSGO(MSGO_I)==ABORT) - scsi_pointer->phase |= aborted; + acp->phase |= aborted; if (MSGO(MSGO_I)==BUS_DEVICE_RESET) - scsi_pointer->phase |= resetted; + acp->phase |= resetted; SETPORT(SCSIDAT, MSGO(MSGO_I++)); } @@ -1936,7 +1933,7 @@ static void msgo_end(struct Scsi_Host *shpnt) */ static void cmd_init(struct Scsi_Host *shpnt) { - if (aha152x_scsi_pointer(CURRENT_SC)->sent_command) { + if (aha152x_priv(CURRENT_SC)->sent_command) { scmd_printk(KERN_ERR, CURRENT_SC, "command already sent\n"); done(shpnt, SAM_STAT_GOOD, DID_ERROR); @@ -1967,7 +1964,7 @@ static void cmd_end(struct Scsi_Host *shpnt) "command sent incompletely (%d/%d)\n", CMD_I, CURRENT_SC->cmd_len); else - aha152x_scsi_pointer(CURRENT_SC)->sent_command++; + aha152x_priv(CURRENT_SC)->sent_command++; } /* @@ -1979,7 +1976,7 @@ static void status_run(struct Scsi_Host *shpnt) if (TESTLO(SSTAT0, SPIORDY)) return; - aha152x_scsi_pointer(CURRENT_SC)->Status = GETPORT(SCSIDAT); + aha152x_priv(CURRENT_SC)->status = GETPORT(SCSIDAT); } @@ -2003,7 +2000,7 @@ static void datai_init(struct Scsi_Host *shpnt) static void datai_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; unsigned long the_time; int fifodata, data_count; @@ -2041,36 +2038,35 @@ static void datai_run(struct Scsi_Host *shpnt) fifodata = GETPORT(FIFOSTAT); } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if (scsi_pointer->this_residual > 0) { - while (fifodata > 0 && scsi_pointer->this_residual > 0) { - data_count = fifodata > scsi_pointer->this_residual ? - scsi_pointer->this_residual : - fifodata; + acp = aha152x_priv(CURRENT_SC); + if (acp->this_residual > 0) { + while (fifodata > 0 && acp->this_residual > 0) { + data_count = fifodata > acp->this_residual ? + acp->this_residual : fifodata; fifodata -= data_count; if (data_count & 1) { SETPORT(DMACNTRL0, ENDMA|_8BIT); - *scsi_pointer->ptr++ = GETPORT(DATAPORT); - scsi_pointer->this_residual--; + *acp->ptr++ = GETPORT(DATAPORT); + acp->this_residual--; DATA_LEN++; SETPORT(DMACNTRL0, ENDMA); } if (data_count > 1) { data_count >>= 1; - insw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + insw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; DATA_LEN += 2 * data_count; } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && + !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } } } else if (fifodata > 0) { @@ -2138,15 +2134,15 @@ static void datao_init(struct Scsi_Host *shpnt) static void datao_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); unsigned long the_time; int data_count; /* until phase changes or all data sent */ - while (TESTLO(DMASTAT, INTSTAT) && scsi_pointer->this_residual > 0) { + while (TESTLO(DMASTAT, INTSTAT) && acp->this_residual > 0) { data_count = 128; - if (data_count > scsi_pointer->this_residual) - data_count = scsi_pointer->this_residual; + if (data_count > acp->this_residual) + data_count = acp->this_residual; if(TESTLO(DMASTAT, DFIFOEMP)) { scmd_printk(KERN_ERR, CURRENT_SC, @@ -2157,26 +2153,25 @@ static void datao_run(struct Scsi_Host *shpnt) if(data_count & 1) { SETPORT(DMACNTRL0,WRITE_READ|ENDMA|_8BIT); - SETPORT(DATAPORT, *scsi_pointer->ptr++); - scsi_pointer->this_residual--; + SETPORT(DATAPORT, *acp->ptr++); + acp->this_residual--; CMD_INC_RESID(CURRENT_SC, -1); SETPORT(DMACNTRL0,WRITE_READ|ENDMA); } if(data_count > 1) { data_count >>= 1; - outsw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + outsw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; CMD_INC_RESID(CURRENT_SC, -2 * data_count); } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } the_time=jiffies + 100*HZ; @@ -2192,7 +2187,7 @@ static void datao_run(struct Scsi_Host *shpnt) static void datao_end(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); if(TESTLO(DMASTAT, DFIFOEMP)) { u32 datao_cnt = GETSTCNT(); @@ -2211,10 +2206,9 @@ static void datao_end(struct Scsi_Host *shpnt) sg = sg_next(sg); } - scsi_pointer->buffer = sg; - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer) + done; - scsi_pointer->this_residual = scsi_pointer->buffer->length - - done; + acp->buffer = sg; + acp->ptr = SG_ADDRESS(acp->buffer) + done; + acp->this_residual = acp->buffer->length - done; } SETPORT(SXFRCTL0, CH1|CLRCH1|CLRSTCNT); @@ -2229,7 +2223,6 @@ static void datao_end(struct Scsi_Host *shpnt) */ static int update_state(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); int dataphase=0; unsigned int stat0 = GETPORT(SSTAT0); unsigned int stat1 = GETPORT(SSTAT1); @@ -2244,7 +2237,7 @@ static int update_state(struct Scsi_Host *shpnt) } else if (stat0 & SELDI && PREVSTATE == busfree) { STATE=seldi; } else if (stat0 & SELDO && CURRENT_SC && - (scsi_pointer->phase & selecting)) { + (aha152x_priv(CURRENT_SC)->phase & selecting)) { STATE=seldo; } else if(stat1 & SELTO) { STATE=selto; @@ -2376,8 +2369,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(SXFRCTL0, CH1); SETPORT(DMACNTRL0, 0); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase &= - ~spiordy; + aha152x_priv(CURRENT_SC)->phase &= ~spiordy; } /* @@ -2399,8 +2391,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(DMACNTRL0, 0); SETPORT(SXFRCTL0, CH1|SPIOEN); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase |= - spiordy; + aha152x_priv(CURRENT_SC)->phase |= spiordy; } /* @@ -2490,7 +2481,7 @@ static void disp_enintr(struct Scsi_Host *shpnt) */ static void show_command(struct scsi_cmnd *ptr) { - const int phase = aha152x_scsi_pointer(ptr)->phase; + const int phase = aha152x_priv(ptr)->phase; scsi_print_command(ptr); scmd_printk(KERN_DEBUG, ptr, @@ -2538,8 +2529,8 @@ static void show_queues(struct Scsi_Host *shpnt) static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(ptr); - const int phase = scsi_pointer->phase; + struct aha152x_cmd_priv *acp = aha152x_priv(ptr); + const int phase = acp->phase; int i; seq_printf(m, "%p: target=%d; lun=%d; cmnd=( ", @@ -2549,8 +2540,8 @@ static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) seq_printf(m, "0x%02x ", ptr->cmnd[i]); seq_printf(m, "); resid=%d; residual=%d; buffers=%d; phase |", - scsi_get_resid(ptr), scsi_pointer->this_residual, - sg_nents(scsi_pointer->buffer) - 1); + scsi_get_resid(ptr), acp->this_residual, + sg_nents(acp->buffer) - 1); if (phase & not_issued) seq_puts(m, "not issued|"); diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h index 679a4fd13874..793fe19993a9 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.h +++ b/drivers/scsi/aic7xxx/aic79xx_osm.h @@ -420,8 +420,6 @@ ahd_unlock(struct ahd_softc *ahd, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e /****************************** PCI-X definitions *****************************/ #define PCIXR_COMMAND 0x96 diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 2f0bdb9225a4..5fad41b1ab58 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -260,8 +260,8 @@ ahd_find_pci_device(ahd_dev_softc_t pci) vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahd_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahd_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahd_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahd_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahd_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahd_compose_id(device, vendor, subdevice, @@ -298,7 +298,7 @@ ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry) * Record if this is an HP board. */ subvendor = ahd_pci_read_config(ahd->dev_softc, - PCIR_SUBVEND_0, /*bytes*/2); + PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); if (subvendor == SUBID_HP) ahd->flags |= AHD_HP_BOARD; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.h b/drivers/scsi/aic7xxx/aic7xxx_osm.h index 4782a304e93c..51d9f4de0734 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.h +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.h @@ -433,8 +433,6 @@ ahc_unlock(struct ahc_softc *ahc, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e typedef enum { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index dab3a6d12c4d..2d4c85426dc3 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -673,8 +673,8 @@ ahc_find_pci_device(ahc_dev_softc_t pci) vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahc_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahc_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahc_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahc_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahc_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahc_compose_id(device, vendor, subdevice, subvendor); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 0103f811cc25..776544385598 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1169,7 +1169,7 @@ static void bnx2fc_process_ofld_cmpl(struct bnx2fc_hba *hba, ofld_kcqe->fcoe_conn_context_id); interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mismatch\n"); goto ofld_cmpl_err; } /* @@ -1226,12 +1226,12 @@ static void bnx2fc_process_enable_conn_cmpl(struct bnx2fc_hba *hba, * and enable */ if (tgt->context_id != context_id) { - printk(KERN_ERR PFX "context id mis-match\n"); + printk(KERN_ERR PFX "context id mismatch\n"); return; } interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mismatch\n"); goto enbl_cmpl_err; } if (!ofld_kcqe->completion_status) diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..7fe7f53a41c0 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -2398,7 +2398,7 @@ static void bnx2i_process_conn_destroy_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "conn destroy- error hba mis-match\n"); + printk(KERN_ALERT "conn destroy- error hba mismatch\n"); return; } @@ -2432,7 +2432,7 @@ static void bnx2i_process_ofld_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "ofld_cmpl: error hba mis-match\n"); + printk(KERN_ALERT "ofld_cmpl: error hba mismatch\n"); return; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 461ef8a76c4c..4bda2f6cb352 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -442,7 +442,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_INTERNAL_ABORT: hisi_sas_task_prep_abort(hisi_hba, slot); break; - fallthrough; default: return; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 80238e6a3c98..eee1a24f7e15 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -36,7 +36,7 @@ #define IBMVSCSIS_VERSION "v0.2" -#define INITIAL_SRP_LIMIT 800 +#define INITIAL_SRP_LIMIT 1024 #define DEFAULT_MAX_SECTORS 256 #define MAX_TXU 1024 * 1024 diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index d690d9cf7eb1..35589b6af90d 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -413,7 +413,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for io request object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -428,7 +428,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for remote device object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -462,7 +462,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) } else dev_err(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received event 0x%x " - "for remote device object 0x%0x that doesnt " + "for remote device object 0x%0x that doesn't " "exist.\n", __func__, ihost, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d09926e6c8a8..cf4211c6500d 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3045,7 +3045,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index f0cf8ffdc5f3..0025760230e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -897,6 +897,11 @@ enum lpfc_irq_chann_mode { NHT_MODE, }; +enum lpfc_hba_bit_flags { + FABRIC_COMANDS_BLOCKED, + HBA_PCI_ERR, +}; + struct lpfc_hba { /* SCSI interface function jump table entries */ struct lpfc_io_buf * (*lpfc_get_scsi_buf) @@ -1043,7 +1048,6 @@ struct lpfc_hba { * Firmware supports Forced Link Speed * capability */ -#define HBA_PCI_ERR 0x80000 /* The PCI slot is offline */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ #define HBA_SHORT_CMF 0x200000 /* shorter CMF timer routine */ #define HBA_CGN_DAY_WRAP 0x400000 /* HBA Congestion info day wraps */ @@ -1350,7 +1354,6 @@ struct lpfc_hba { atomic_t fabric_iocb_count; struct timer_list fabric_block_timer; unsigned long bit_flags; -#define FABRIC_COMANDS_BLOCKED 0 atomic_t num_rsrc_err; atomic_t num_cmd_success; unsigned long last_rsrc_error_time; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 96408cd6c4c8..9897a1aa387b 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -670,3 +670,6 @@ struct lpfc_vmid *lpfc_get_vmid_from_hashtable(struct lpfc_vport *vport, uint32_t hash, uint8_t *buf); void lpfc_vmid_vport_cleanup(struct lpfc_vport *vport); int lpfc_issue_els_qfpa(struct lpfc_vport *vport); + +void lpfc_sli_rpi_release(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0144da30e3db..2b877dff5ed4 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -109,8 +109,8 @@ lpfc_rport_invalid(struct fc_rport *rport) ndlp = rdata->pnode; if (!rdata->pnode) { - pr_err("**** %s: NULL ndlp on rport x%px SID x%x\n", - __func__, rport, rport->scsi_target_id); + pr_info("**** %s: NULL ndlp on rport x%px SID x%x\n", + __func__, rport, rport->scsi_target_id); return -EINVAL; } @@ -169,9 +169,10 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "3181 dev_loss_callbk x%06x, rport x%px flg x%x " - "load_flag x%x refcnt %d\n", + "load_flag x%x refcnt %d state %d xpt x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag, - vport->load_flag, kref_read(&ndlp->kref)); + vport->load_flag, kref_read(&ndlp->kref), + ndlp->nlp_state, ndlp->fc4_xpt_flags); /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. @@ -181,6 +182,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD; + /* clear the NLP_XPT_REGD if the node is not registered + * with nvme-fc + */ + if (ndlp->fc4_xpt_flags == NLP_XPT_REGD) + ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD; /* Remove the node reference from remote_port_add now. * The driver will not call remote_port_delete. @@ -225,18 +231,36 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; spin_unlock_irqrestore(&ndlp->lock, iflags); - /* We need to hold the node by incrementing the reference - * count until this queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); + if (phba->worker_thread) { + /* We need to hold the node by incrementing the reference + * count until this queued work is done + */ + evtp->evt_arg1 = lpfc_nlp_get(ndlp); + + spin_lock_irqsave(&phba->hbalock, iflags); + if (evtp->evt_arg1) { + evtp->evt = LPFC_EVT_DEV_LOSS; + list_add_tail(&evtp->evt_listp, &phba->work_list); + lpfc_worker_wake_up(phba); + } + spin_unlock_irqrestore(&phba->hbalock, iflags); + } else { + lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, + "3188 worker thread is stopped %s x%06x, " + " rport x%px flg x%x load_flag x%x refcnt " + "%d\n", __func__, ndlp->nlp_DID, + ndlp->rport, ndlp->nlp_flag, + vport->load_flag, kref_read(&ndlp->kref)); + if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) { + spin_lock_irqsave(&ndlp->lock, iflags); + /* Node is in dev loss. No further transaction. */ + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_disc_state_machine(vport, ndlp, NULL, + NLP_EVT_DEVICE_RM); + } - spin_lock_irqsave(&phba->hbalock, iflags); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_DEV_LOSS; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); } - spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -503,11 +527,12 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, "0203 Devloss timeout on " "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x " - "NPort x%06x Data: x%x x%x x%x\n", + "NPort x%06x Data: x%x x%x x%x refcnt %d\n", *name, *(name+1), *(name+2), *(name+3), *(name+4), *(name+5), *(name+6), *(name+7), ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_state, ndlp->nlp_rpi); + ndlp->nlp_state, ndlp->nlp_rpi, + kref_read(&ndlp->kref)); } else { lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT, "0204 Devloss timeout on " @@ -755,18 +780,22 @@ lpfc_work_list_done(struct lpfc_hba *phba) int free_evt; int fcf_inuse; uint32_t nlp_did; + bool hba_pci_err; spin_lock_irq(&phba->hbalock); while (!list_empty(&phba->work_list)) { list_remove_head((&phba->work_list), evtp, typeof(*evtp), evt_listp); spin_unlock_irq(&phba->hbalock); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); free_evt = 1; switch (evtp->evt) { case LPFC_EVT_ELS_RETRY: ndlp = (struct lpfc_nodelist *) (evtp->evt_arg1); - lpfc_els_retry_delay_handler(ndlp); - free_evt = 0; /* evt is part of ndlp */ + if (!hba_pci_err) { + lpfc_els_retry_delay_handler(ndlp); + free_evt = 0; /* evt is part of ndlp */ + } /* decrement the node reference count held * for this queued work */ @@ -788,8 +817,10 @@ lpfc_work_list_done(struct lpfc_hba *phba) break; case LPFC_EVT_RECOVER_PORT: ndlp = (struct lpfc_nodelist *)(evtp->evt_arg1); - lpfc_sli_abts_recover_port(ndlp->vport, ndlp); - free_evt = 0; + if (!hba_pci_err) { + lpfc_sli_abts_recover_port(ndlp->vport, ndlp); + free_evt = 0; + } /* decrement the node reference count held for * this queued work */ @@ -859,14 +890,18 @@ lpfc_work_done(struct lpfc_hba *phba) struct lpfc_vport **vports; struct lpfc_vport *vport; int i; + bool hba_pci_err; + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); spin_lock_irq(&phba->hbalock); ha_copy = phba->work_ha; phba->work_ha = 0; spin_unlock_irq(&phba->hbalock); + if (hba_pci_err) + ha_copy = 0; /* First, try to post the next mailbox command to SLI4 device */ - if (phba->pci_dev_grp == LPFC_PCI_DEV_OC) + if (phba->pci_dev_grp == LPFC_PCI_DEV_OC && !hba_pci_err) lpfc_sli4_post_async_mbox(phba); if (ha_copy & HA_ERATT) { @@ -886,7 +921,7 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_latt(phba); /* Handle VMID Events */ - if (lpfc_is_vmid_enabled(phba)) { + if (lpfc_is_vmid_enabled(phba) && !hba_pci_err) { if (phba->pport->work_port_events & WORKER_CHECK_VMID_ISSUE_QFPA) { lpfc_check_vmid_qfpa_issue(phba); @@ -936,6 +971,8 @@ lpfc_work_done(struct lpfc_hba *phba) work_port_events = vport->work_port_events; vport->work_port_events &= ~work_port_events; spin_unlock_irq(&vport->work_port_lock); + if (hba_pci_err) + continue; if (work_port_events & WORKER_DISC_TMO) lpfc_disc_timeout_handler(vport); if (work_port_events & WORKER_ELS_TMO) @@ -1173,12 +1210,14 @@ lpfc_linkdown(struct lpfc_hba *phba) struct lpfc_vport **vports; LPFC_MBOXQ_t *mb; int i; + int offline; if (phba->link_state == LPFC_LINK_DOWN) return 0; /* Block all SCSI stack I/Os */ lpfc_scsi_dev_block(phba); + offline = pci_channel_offline(phba->pcidev); phba->defer_flogi_acc_flag = false; @@ -1219,7 +1258,7 @@ lpfc_linkdown(struct lpfc_hba *phba) lpfc_destroy_vport_work_array(phba, vports); /* Clean up any SLI3 firmware default rpi's */ - if (phba->sli_rev > LPFC_SLI_REV3) + if (phba->sli_rev > LPFC_SLI_REV3 || offline) goto skip_unreg_did; mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -4712,6 +4751,11 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); if (!(ndlp->fc4_xpt_flags & NLP_XPT_REGD)) { spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "0999 %s Not regd: ndlp x%px rport x%px DID " + "x%x FLG x%x XPT x%x\n", + __func__, ndlp, ndlp->rport, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); return; } @@ -4722,6 +4766,13 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->fc4_xpt_flags & SCSI_XPT_REGD) { vport->phba->nport_event_cnt++; lpfc_unregister_remote_port(ndlp); + } else if (!ndlp->rport) { + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "1999 %s NDLP in devloss x%px DID x%x FLG x%x" + " XPT x%x refcnt %d\n", + __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); } if (ndlp->fc4_xpt_flags & NVME_XPT_REGD) { @@ -5371,6 +5422,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; mempool_free(mbox, phba->mbox_mem_pool); acc_plogi = 1; + lpfc_nlp_put(ndlp); } } else { lpfc_printf_vlog(vport, KERN_INFO, @@ -6097,12 +6149,34 @@ lpfc_disc_flush_list(struct lpfc_vport *vport) } } +/* + * lpfc_notify_xport_npr - notifies xport of node disappearance + * @vport: Pointer to Virtual Port object. + * + * Transitions all ndlps to NPR state. When lpfc_nlp_set_state + * calls lpfc_nlp_state_cleanup, the ndlp->rport is unregistered + * and transport notified that the node is gone. + * Return Code: + * none + */ +static void +lpfc_notify_xport_npr(struct lpfc_vport *vport) +{ + struct lpfc_nodelist *ndlp, *next_ndlp; + + list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, + nlp_listp) { + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } +} void lpfc_cleanup_discovery_resources(struct lpfc_vport *vport) { lpfc_els_flush_rscn(vport); lpfc_els_flush_cmd(vport); lpfc_disc_flush_list(vport); + if (pci_channel_offline(vport->phba->pcidev)) + lpfc_notify_xport_npr(vport); } /*****************************************************************************/ diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index eed6464bd880..461d333b1b3a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -95,6 +95,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba); static uint16_t lpfc_find_cpu_handle(struct lpfc_hba *, uint16_t, int); static void lpfc_setup_bg(struct lpfc_hba *, struct Scsi_Host *); static int lpfc_sli4_cgn_parm_chg_evt(struct lpfc_hba *); +static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba); static struct scsi_transport_template *lpfc_transport_template = NULL; static struct scsi_transport_template *lpfc_vport_transport_template = NULL; @@ -1642,7 +1643,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) { spin_lock_irq(&phba->hbalock); if (phba->link_state == LPFC_HBA_ERROR && - phba->hba_flag & HBA_PCI_ERR) { + test_bit(HBA_PCI_ERR, &phba->bit_flags)) { spin_unlock_irq(&phba->hbalock); return; } @@ -1985,6 +1986,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) if (pci_channel_offline(phba->pcidev)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3166 pci channel is offline\n"); + lpfc_sli_flush_io_rings(phba); return; } @@ -2973,6 +2975,22 @@ lpfc_cleanup(struct lpfc_vport *vport) NLP_EVT_DEVICE_RM); } + /* This is a special case flush to return all + * IOs before entering this loop. There are + * two points in the code where a flush is + * avoided if the FC_UNLOADING flag is set. + * one is in the multipool destroy, + * (this prevents a crash) and the other is + * in the nvme abort handler, ( also prevents + * a crash). Both of these exceptions are + * cases where the slot is still accessible. + * The flush here is only when the pci slot + * is offline. + */ + if (vport->load_flag & FC_UNLOADING && + pci_channel_offline(phba->pcidev)) + lpfc_sli_flush_io_rings(vport->phba); + /* At this point, ALL ndlp's should be gone * because of the previous NLP_EVT_DEVICE_RM. * Lets wait for this to happen, if needed. @@ -2985,7 +3003,7 @@ lpfc_cleanup(struct lpfc_vport *vport) list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, - LOG_TRACE_EVENT, + LOG_DISCOVERY, "0282 did:x%x ndlp:x%px " "refcnt:%d xflags x%x nflag x%x\n", ndlp->nlp_DID, (void *)ndlp, @@ -3682,7 +3700,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) struct lpfc_vport **vports; struct Scsi_Host *shost; int i; - int offline = 0; + int offline; + bool hba_pci_err; if (vport->fc_flag & FC_OFFLINE_MODE) return; @@ -3692,6 +3711,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) lpfc_linkdown(phba); offline = pci_channel_offline(phba->pcidev); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); /* Issue an unreg_login to all nodes on all vports */ vports = lpfc_create_vport_work_array(phba); @@ -3715,11 +3735,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) ndlp->nlp_flag &= ~NLP_NPR_ADISC; spin_unlock_irq(&ndlp->lock); - if (offline) { + if (offline || hba_pci_err) { spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~(NLP_UNREG_INP | NLP_RPI_REGISTERED); spin_unlock_irq(&ndlp->lock); + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_sli_rpi_release(vports[i], + ndlp); } else { lpfc_unreg_rpi(vports[i], ndlp); } @@ -13354,8 +13377,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Abort all iocbs associated with the hba */ lpfc_sli_hba_iocb_abort(phba); - /* Wait for completion of device XRI exchange busy */ - lpfc_sli4_xri_exchange_busy_wait(phba); + if (!pci_channel_offline(phba->pcidev)) + /* Wait for completion of device XRI exchange busy */ + lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ if (phba->pport) @@ -13374,15 +13398,12 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Disable FW logging to host memory */ lpfc_ras_stop_fwlog(phba); - /* Unset the queues shared with the hardware then release all - * allocated resources. - */ - lpfc_sli4_queue_unset(phba); - lpfc_sli4_queue_destroy(phba); - /* Reset SLI4 HBA FCoE function */ lpfc_pci_function_reset(phba); + /* release all queue allocated resources. */ + lpfc_sli4_queue_destroy(phba); + /* Free RAS DMA memory */ if (phba->ras_fwlog.ras_enabled) lpfc_sli4_ras_dma_free(phba); @@ -14262,6 +14283,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) "2711 PCI channel permanent disable for failure\n"); /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); + lpfc_sli4_prep_dev_for_reset(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -15057,24 +15079,28 @@ lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba) static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2826 PCI channel disable preparing for reset\n"); + int offline = pci_channel_offline(phba->pcidev); + + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2826 PCI channel disable preparing for reset offline" + " %d\n", offline); /* Block any management I/Os to the device */ lpfc_block_mgmt_io(phba, LPFC_MBX_NO_WAIT); - /* Block all SCSI devices' I/Os on the host */ - lpfc_scsi_dev_block(phba); + /* HBA_PCI_ERR was set in io_error_detect */ + lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); /* Flush all driver's outstanding I/Os as we are to reset */ lpfc_sli_flush_io_rings(phba); + lpfc_offline(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); + lpfc_sli4_queue_destroy(phba); /* Disable interrupt and pci device */ lpfc_sli4_disable_intr(phba); - lpfc_sli4_queue_destroy(phba); pci_disable_device(phba->pcidev); } @@ -15123,6 +15149,7 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) { struct Scsi_Host *shost = pci_get_drvdata(pdev); struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + bool hba_pci_err; switch (state) { case pci_channel_io_normal: @@ -15130,17 +15157,24 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) lpfc_sli4_prep_dev_for_recover(phba); return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Fatal error, prepare for slot reset */ - lpfc_sli4_prep_dev_for_reset(phba); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2832 Already handling PCI error " + "state: x%x\n", state); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: - phba->hba_flag |= HBA_PCI_ERR; + set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Permanent failure, prepare for device down */ lpfc_sli4_prep_dev_for_perm_failure(phba); return PCI_ERS_RESULT_DISCONNECT; default: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); /* Unknown state, prepare and request slot reset */ lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2825 Unknown PCI error state: x%x\n", state); @@ -15174,17 +15208,21 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; struct lpfc_sli *psli = &phba->sli; uint32_t intr_mode; + bool hba_pci_err; dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n"); if (pci_enable_device_mem(pdev)) { printk(KERN_ERR "lpfc: Cannot re-enable " - "PCI device after reset.\n"); + "PCI device after reset.\n"); return PCI_ERS_RESULT_DISCONNECT; } pci_restore_state(pdev); - phba->hba_flag &= ~HBA_PCI_ERR; + hba_pci_err = test_and_clear_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + dev_info(&pdev->dev, + "hba_pci_err was not set, recovering slot reset.\n"); /* * As the new kernel behavior of pci_restore_state() API call clears * device saved_state flag, need to save the restored state again. @@ -15198,6 +15236,8 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) psli->sli_flag &= ~LPFC_SLI_ACTIVE; spin_unlock_irq(&phba->hbalock); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, phba->intr_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -15239,8 +15279,6 @@ lpfc_io_resume_s4(struct pci_dev *pdev) */ if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) { /* Perform device reset */ - lpfc_offline_prep(phba, LPFC_MBX_WAIT); - lpfc_offline(phba); lpfc_sli_brdrestart(phba); /* Bring the device back online */ lpfc_online(phba); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 1213a299f9aa..8d26f207ebd2 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -93,6 +93,11 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lport = (struct lpfc_nvme_lport *)pnvme_lport->private; vport = lport->vport; + + if (!vport || vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; + qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL); if (qhandle == NULL) return -ENOMEM; @@ -267,7 +272,8 @@ lpfc_nvme_handle_lsreq(struct lpfc_hba *phba, return -EINVAL; remoteport = lpfc_rport->remoteport; - if (!vport->localport) + if (!vport->localport || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -EINVAL; lport = vport->localport->private; @@ -559,6 +565,8 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_DID, ntype, nstate); return -ENODEV; } + if (vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; if (!vport->phba->sli4_hba.nvmels_wq) return -ENOMEM; @@ -662,7 +670,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, return -EINVAL; vport = lport->vport; - if (vport->load_flag & FC_UNLOADING) + if (vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -ENODEV; atomic_inc(&lport->fc4NvmeLsRequests); @@ -1516,7 +1525,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, phba = vport->phba; - if (unlikely(vport->load_flag & FC_UNLOADING)) { + if ((unlikely(vport->load_flag & FC_UNLOADING)) || + phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -2169,8 +2179,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_nvme = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; - if (!vport || !vport->localport || - !qp || !qp->io_wq) + if (!vport->localport || !qp || !qp->io_wq) return; pring = qp->io_wq->pring; @@ -2180,8 +2189,9 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_scsi += qp->abts_scsi_io_bufs; abts_nvme += qp->abts_nvme_io_bufs; } - if (!vport || !vport->localport || - vport->phba->hba_flag & HBA_PCI_ERR) + if (!vport->localport || + test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) || + vport->load_flag & FC_UNLOADING) return; lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -2541,8 +2551,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * return values is ignored. The upcall is a courtesy to the * transport. */ - if (vport->load_flag & FC_UNLOADING || - unlikely(vport->phba->hba_flag & HBA_PCI_ERR)) + if (vport->load_flag & FC_UNLOADING) (void)nvme_fc_set_remoteport_devloss(remoteport, 0); ret = nvme_fc_unregister_remoteport(remoteport); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 3c132604fd91..ba9dbb51b75f 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5929,13 +5929,15 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) } lpfc_cmd->waitq = &waitq; - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { spin_unlock(&pring_s4->ring_lock); - else + ret_val = lpfc_sli4_issue_abort_iotag(phba, iocb, + lpfc_sli_abort_fcp_cmpl); + } else { pring = &phba->sli.sli3_ring[LPFC_FCP_RING]; - - ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, - lpfc_sli_abort_fcp_cmpl); + ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, + lpfc_sli_abort_fcp_cmpl); + } /* Make sure HBA is alive */ lpfc_issue_hb_tmo(phba); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 20d40957a385..bda2a7ba4e77 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2828,6 +2828,12 @@ __lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; } +void +lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + __lpfc_sli_rpi_release(vport, ndlp); +} + /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler * @phba: Pointer to HBA context object. @@ -3715,7 +3721,15 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, unsigned long iflag; u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag; + if (phba->sli_rev == LPFC_SLI_REV4) + spin_lock_irqsave(&pring->ring_lock, iflag); + else + spin_lock_irqsave(&phba->hbalock, iflag); cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq); + if (phba->sli_rev == LPFC_SLI_REV4) + spin_unlock_irqrestore(&pring->ring_lock, iflag); + else + spin_unlock_irqrestore(&phba->hbalock, iflag); ulp_command = get_job_cmnd(phba, saveq); ulp_status = get_job_ulpstatus(phba, saveq); @@ -4052,10 +4066,8 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba, break; } - spin_unlock_irqrestore(&phba->hbalock, iflag); cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring, &rspiocbq); - spin_lock_irqsave(&phba->hbalock, iflag); if (unlikely(!cmdiocbq)) break; if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) @@ -4536,42 +4548,62 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba, void lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { - LIST_HEAD(completions); + LIST_HEAD(tx_completions); + LIST_HEAD(txcmplq_completions); struct lpfc_iocbq *iocb, *next_iocb; + int offline; if (pring->ringno == LPFC_ELS_RING) { lpfc_fabric_abort_hba(phba); } + offline = pci_channel_offline(phba->pcidev); /* Error everything on txq and txcmplq * First do the txq. */ if (phba->sli_rev >= LPFC_SLI_REV4) { spin_lock_irq(&pring->ring_lock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - spin_lock_irq(&phba->hbalock); - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); - spin_unlock_irq(&phba->hbalock); + if (offline) { + list_splice_init(&pring->txcmplq, + &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } + spin_unlock_irq(&pring->ring_lock); } else { spin_lock_irq(&phba->hbalock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); + if (offline) { + list_splice_init(&pring->txcmplq, &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } spin_unlock_irq(&phba->hbalock); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (offline) { + /* Cancel all the IOCBs from the completions list */ + lpfc_sli_cancel_iocbs(phba, &txcmplq_completions, + IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); + } else { + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); + } /* Cancel all the IOCBs from the completions list */ - lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT, + lpfc_sli_cancel_iocbs(phba, &tx_completions, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); } @@ -4624,11 +4656,6 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); - if (phba->hba_flag & HBA_IOQ_FLUSH || - !phba->sli4_hba.hdwq) { - spin_unlock_irq(&phba->hbalock); - return; - } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -10997,6 +11024,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, unsigned long iflags; int rc; + /* If the PCI channel is in offline state, do not post iocbs. */ + if (unlikely(pci_channel_offline(phba->pcidev))) + return IOCB_ERROR; + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli_prep_wqe(phba, piocb); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index e52f37e5d896..a4d3259b8c52 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.2.0.0" +#define LPFC_DRIVER_VERSION "14.2.0.1" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 611871ef15b5..4919ea54b827 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2560,6 +2560,9 @@ struct megasas_instance_template { #define MEGASAS_IS_LOGICAL(sdev) \ ((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) +#define MEGASAS_IS_LUN_VALID(sdev) \ + (((sdev)->lun == 0) ? 1 : 0) + #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ scp->device->id) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8bf72dbc33b7..db6793608447 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2126,6 +2126,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev) goto scan_target; } return -ENXIO; + } else if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return -ENXIO; } scan_target: @@ -2156,6 +2159,10 @@ static void megasas_slave_destroy(struct scsi_device *sdev) instance = megasas_lookup_instance(sdev->host->host_no); if (MEGASAS_IS_LOGICAL(sdev)) { + if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return; + } ld_tgt_id = MEGASAS_TARGET_ID(sdev); instance->ld_tgtid_status[ld_tgt_id] = LD_TARGET_ID_DELETED; if (megasas_dbg_lvl & LD_PD_DEBUG) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b57f1803371e..538d2c0cd971 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5716,13 +5716,12 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) /** * mpt3sas_check_same_4gb_region - checks whether all reply queues in a set are * having same upper 32bits in their base memory address. - * @reply_pool_start_address: Base address of a reply queue set + * @start_address: Base address of a reply queue set * @pool_sz: Size of single Reply Descriptor Post Queues pool size * * Return: 1 if reply queues in a set have a same upper 32bits in their base * memory address, else 0. */ - static int mpt3sas_check_same_4gb_region(dma_addr_t start_address, u32 pool_sz) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index 0563078227de..a8dd14c91efd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -394,10 +394,13 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t retry_count++; if (ioc->config_cmds.smid == smid) mpt3sas_base_free_smid(ioc, smid); - if ((ioc->shost_recovery) || (ioc->config_cmds.status & - MPT3_CMD_RESET) || ioc->pci_error_recovery) + if (ioc->config_cmds.status & MPT3_CMD_RESET) goto retry_config; - issue_host_reset = 1; + if (ioc->shost_recovery || ioc->pci_error_recovery) { + issue_host_reset = 0; + r = -EFAULT; + } else + issue_host_reset = 1; goto free_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 00792767c620..7e476f50935b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, { struct _sas_port *mpt3sas_port, *next; unsigned long flags; + int port_id; /* remove sibling ports attached to this expander */ list_for_each_entry_safe(mpt3sas_port, next, @@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, mpt3sas_port->hba_port); } + port_id = sas_expander->port->port_id; + mpt3sas_transport_port_remove(ioc, sas_expander->sas_address, sas_expander->sas_address_parent, sas_expander->port); @@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, "expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n", sas_expander->handle, (unsigned long long) sas_expander->sas_address, - sas_expander->port->port_id); + port_id); spin_lock_irqsave(&ioc->sas_node_lock, flags); list_del(&sas_expander->list); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 7ac63eb5ccd3..2fde496fff5f 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -647,6 +647,7 @@ static struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1300), chip_1300 }, { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1320), chip_1320 }, { PCI_VDEVICE(ADAPTEC2, 0x0450), chip_6440 }, + { PCI_VDEVICE(TTI, 0x2640), chip_6440 }, { PCI_VDEVICE(TTI, 0x2710), chip_9480 }, { PCI_VDEVICE(TTI, 0x2720), chip_9480 }, { PCI_VDEVICE(TTI, 0x2721), chip_9480 }, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index c4a838635893..5d7dfefd6f6c 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -192,10 +192,11 @@ struct sym53c500_data { int fast_pio; }; -static struct scsi_pointer *sym53c500_scsi_pointer(struct scsi_cmnd *cmd) -{ - return scsi_cmd_priv(cmd); -} +struct sym53c500_cmd_priv { + int status; + int message; + int phase; +}; enum Phase { idle, @@ -356,7 +357,7 @@ SYM53C500_intr(int irq, void *dev_id) struct sym53c500_data *data = (struct sym53c500_data *)dev->hostdata; struct scsi_cmnd *curSC = data->current_SC; - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(curSC); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(curSC); int fast_pio = data->fast_pio; spin_lock_irqsave(dev->host_lock, flags); @@ -403,12 +404,11 @@ SYM53C500_intr(int irq, void *dev_id) if (int_reg & 0x20) { /* Disconnect */ DEB(printk("SYM53C500: disconnect intr received\n")); - if (scsi_pointer->phase != message_in) { /* Unexpected disconnect */ + if (scp->phase != message_in) { /* Unexpected disconnect */ curSC->result = DID_NO_CONNECT << 16; } else { /* Command complete, return status and message */ - curSC->result = (scsi_pointer->Status & 0xff) | - ((scsi_pointer->Message & 0xff) << 8) | - (DID_OK << 16); + curSC->result = (scp->status & 0xff) | + ((scp->message & 0xff) << 8) | (DID_OK << 16); } goto idle_out; } @@ -419,7 +419,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_out; + scp->phase = data_out; VDEB(printk("SYM53C500: Data-Out phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -438,7 +438,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_in; + scp->phase = data_in; VDEB(printk("SYM53C500: Data-In phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -453,12 +453,12 @@ SYM53C500_intr(int irq, void *dev_id) break; case 0x02: /* COMMAND */ - scsi_pointer->phase = command_ph; + scp->phase = command_ph; printk("SYM53C500: Warning: Unknown interrupt occurred in command phase!\n"); break; case 0x03: /* STATUS */ - scsi_pointer->phase = status_ph; + scp->phase = status_ph; VDEB(printk("SYM53C500: Status phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); outb(INIT_CMD_COMPLETE, port_base + CMD_REG); @@ -471,24 +471,22 @@ SYM53C500_intr(int irq, void *dev_id) case 0x06: /* MESSAGE-OUT */ DEB(printk("SYM53C500: Message-Out phase\n")); - scsi_pointer->phase = message_out; + scp->phase = message_out; outb(SET_ATN, port_base + CMD_REG); /* Reject the message */ outb(MSG_ACCEPT, port_base + CMD_REG); break; case 0x07: /* MESSAGE-IN */ VDEB(printk("SYM53C500: Message-In phase\n")); - scsi_pointer->phase = message_in; + scp->phase = message_in; - scsi_pointer->Status = inb(port_base + SCSI_FIFO); - scsi_pointer->Message = inb(port_base + SCSI_FIFO); + scp->status = inb(port_base + SCSI_FIFO); + scp->message = inb(port_base + SCSI_FIFO); VDEB(printk("SCSI FIFO size=%d\n", inb(port_base + FIFO_FLAGS) & 0x1f)); - DEB(printk("Status = %02x Message = %02x\n", - scsi_pointer->Status, scsi_pointer->Message)); + DEB(printk("Status = %02x Message = %02x\n", scp->status, scp->message)); - if (scsi_pointer->Message == SAVE_POINTERS || - scsi_pointer->Message == DISCONNECT) { + if (scp->message == SAVE_POINTERS || scp->message == DISCONNECT) { outb(SET_ATN, port_base + CMD_REG); /* Reject message */ DEB(printk("Discarding SAVE_POINTERS message\n")); } @@ -500,7 +498,7 @@ out: return IRQ_HANDLED; idle_out: - scsi_pointer->phase = idle; + scp->phase = idle; scsi_done(curSC); goto out; } @@ -548,7 +546,7 @@ SYM53C500_info(struct Scsi_Host *SChost) static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) { - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(SCpnt); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(SCpnt); int i; int port_base = SCpnt->device->host->io_port; struct sym53c500_data *data = @@ -565,9 +563,9 @@ static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) VDEB(printk("\n")); data->current_SC = SCpnt; - scsi_pointer->phase = command_ph; - scsi_pointer->Status = 0; - scsi_pointer->Message = 0; + scp->phase = command_ph; + scp->status = 0; + scp->message = 0; /* We are locked here already by the mid layer */ REG0(port_base); @@ -682,7 +680,7 @@ static struct scsi_host_template sym53c500_driver_template = { .this_id = 7, .sg_tablesize = 32, .shost_groups = SYM53C500_shost_groups, - .cmd_size = sizeof(struct scsi_pointer), + .cmd_size = sizeof(struct sym53c500_cmd_priv), }; static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data) diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 928532180d32..fd674ed1febe 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3182,124 +3182,6 @@ static int pmcraid_build_ioadl( } /** - * pmcraid_free_sglist - Frees an allocated SG buffer list - * @sglist: scatter/gather list pointer - * - * Free a DMA'able memory previously allocated with pmcraid_alloc_sglist - * - * Return value: - * none - */ -static void pmcraid_free_sglist(struct pmcraid_sglist *sglist) -{ - sgl_free_order(sglist->scatterlist, sglist->order); - kfree(sglist); -} - -/** - * pmcraid_alloc_sglist - Allocates memory for a SG list - * @buflen: buffer length - * - * Allocates a DMA'able buffer in chunks and assembles a scatter/gather - * list. - * - * Return value - * pointer to sglist / NULL on failure - */ -static struct pmcraid_sglist *pmcraid_alloc_sglist(int buflen) -{ - struct pmcraid_sglist *sglist; - int sg_size; - int order; - - sg_size = buflen / (PMCRAID_MAX_IOADLS - 1); - order = (sg_size > 0) ? get_order(sg_size) : 0; - - /* Allocate a scatter/gather list for the DMA */ - sglist = kzalloc(sizeof(struct pmcraid_sglist), GFP_KERNEL); - if (sglist == NULL) - return NULL; - - sglist->order = order; - sgl_alloc_order(buflen, order, false, GFP_KERNEL | __GFP_ZERO, - &sglist->num_sg); - - return sglist; -} - -/** - * pmcraid_copy_sglist - Copy user buffer to kernel buffer's SG list - * @sglist: scatter/gather list pointer - * @buffer: buffer pointer - * @len: buffer length - * @direction: data transfer direction - * - * Copy a user buffer into a buffer allocated by pmcraid_alloc_sglist - * - * Return value: - * 0 on success / other on failure - */ -static int pmcraid_copy_sglist( - struct pmcraid_sglist *sglist, - void __user *buffer, - u32 len, - int direction -) -{ - struct scatterlist *sg; - void *kaddr; - int bsize_elem; - int i; - int rc = 0; - - /* Determine the actual number of bytes per element */ - bsize_elem = PAGE_SIZE * (1 << sglist->order); - - sg = sglist->scatterlist; - - for (i = 0; i < (len / bsize_elem); i++, sg = sg_next(sg), buffer += bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, bsize_elem); - else - rc = copy_to_user(buffer, kaddr, bsize_elem); - - kunmap(page); - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - return -EFAULT; - } - - sg->length = bsize_elem; - } - - if (len % bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, len % bsize_elem); - else - rc = copy_to_user(buffer, kaddr, len % bsize_elem); - - kunmap(page); - - sg->length = len % bsize_elem; - } - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - rc = -EFAULT; - } - - return rc; -} - -/** * pmcraid_queuecommand_lck - Queue a mid-layer request * @scsi_cmd: scsi command struct * @@ -3454,365 +3336,6 @@ static int pmcraid_chr_fasync(int fd, struct file *filep, int mode) return rc; } - -/** - * pmcraid_build_passthrough_ioadls - builds SG elements for passthrough - * commands sent over IOCTL interface - * - * @cmd : pointer to struct pmcraid_cmd - * @buflen : length of the request buffer - * @direction : data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static int pmcraid_build_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = NULL; - struct scatterlist *sg = NULL; - struct pmcraid_ioarcb *ioarcb = &cmd->ioa_cb->ioarcb; - struct pmcraid_ioadl_desc *ioadl; - int i; - - sglist = pmcraid_alloc_sglist(buflen); - - if (!sglist) { - pmcraid_err("can't allocate memory for passthrough SGls\n"); - return -ENOMEM; - } - - sglist->num_dma_sg = dma_map_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, direction); - - if (!sglist->num_dma_sg || sglist->num_dma_sg > PMCRAID_MAX_IOADLS) { - dev_err(&cmd->drv_inst->pdev->dev, - "Failed to map passthrough buffer!\n"); - pmcraid_free_sglist(sglist); - return -EIO; - } - - cmd->sglist = sglist; - ioarcb->request_flags0 |= NO_LINK_DESCS; - - ioadl = pmcraid_init_ioadls(cmd, sglist->num_dma_sg); - - /* Initialize IOADL descriptor addresses */ - for_each_sg(sglist->scatterlist, sg, sglist->num_dma_sg, i) { - ioadl[i].data_len = cpu_to_le32(sg_dma_len(sg)); - ioadl[i].address = cpu_to_le64(sg_dma_address(sg)); - ioadl[i].flags = 0; - } - - /* setup the last descriptor */ - ioadl[i - 1].flags = IOADL_FLAGS_LAST_DESC; - - return 0; -} - - -/** - * pmcraid_release_passthrough_ioadls - release passthrough ioadls - * - * @cmd: pointer to struct pmcraid_cmd for which ioadls were allocated - * @buflen: size of the request buffer - * @direction: data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static void pmcraid_release_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = cmd->sglist; - - if (buflen > 0) { - dma_unmap_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, - direction); - pmcraid_free_sglist(sglist); - cmd->sglist = NULL; - } -} - -/** - * pmcraid_ioctl_passthrough - handling passthrough IOCTL commands - * - * @pinstance: pointer to adapter instance structure - * @ioctl_cmd: ioctl code - * @buflen: unused - * @arg: pointer to pmcraid_passthrough_buffer user buffer - * - * Return value - * 0 on success, non-zero error code on failure - */ -static long pmcraid_ioctl_passthrough( - struct pmcraid_instance *pinstance, - unsigned int ioctl_cmd, - unsigned int buflen, - void __user *arg -) -{ - struct pmcraid_passthrough_ioctl_buffer *buffer; - struct pmcraid_ioarcb *ioarcb; - struct pmcraid_cmd *cmd; - struct pmcraid_cmd *cancel_cmd; - void __user *request_buffer; - unsigned long request_offset; - unsigned long lock_flags; - void __user *ioasa; - u32 ioasc; - int request_size; - int buffer_size; - u8 direction; - int rc = 0; - - /* If IOA reset is in progress, wait 10 secs for reset to complete */ - if (pinstance->ioa_reset_in_progress) { - rc = wait_event_interruptible_timeout( - pinstance->reset_wait_q, - !pinstance->ioa_reset_in_progress, - msecs_to_jiffies(10000)); - - if (!rc) - return -ETIMEDOUT; - else if (rc < 0) - return -ERESTARTSYS; - } - - /* If adapter is not in operational state, return error */ - if (pinstance->ioa_state != IOA_STATE_OPERATIONAL) { - pmcraid_err("IOA is not operational\n"); - return -ENOTTY; - } - - buffer_size = sizeof(struct pmcraid_passthrough_ioctl_buffer); - buffer = kmalloc(buffer_size, GFP_KERNEL); - - if (!buffer) { - pmcraid_err("no memory for passthrough buffer\n"); - return -ENOMEM; - } - - request_offset = - offsetof(struct pmcraid_passthrough_ioctl_buffer, request_buffer); - - request_buffer = arg + request_offset; - - rc = copy_from_user(buffer, arg, - sizeof(struct pmcraid_passthrough_ioctl_buffer)); - - ioasa = arg + offsetof(struct pmcraid_passthrough_ioctl_buffer, ioasa); - - if (rc) { - pmcraid_err("ioctl: can't copy passthrough buffer\n"); - rc = -EFAULT; - goto out_free_buffer; - } - - request_size = le32_to_cpu(buffer->ioarcb.data_transfer_length); - - if (buffer->ioarcb.request_flags0 & TRANSFER_DIR_WRITE) { - direction = DMA_TO_DEVICE; - } else { - direction = DMA_FROM_DEVICE; - } - - if (request_size < 0) { - rc = -EINVAL; - goto out_free_buffer; - } - - /* check if we have any additional command parameters */ - if (le16_to_cpu(buffer->ioarcb.add_cmd_param_length) - > PMCRAID_ADD_CMD_PARAM_LEN) { - rc = -EINVAL; - goto out_free_buffer; - } - - cmd = pmcraid_get_free_cmd(pinstance); - - if (!cmd) { - pmcraid_err("free command block is not available\n"); - rc = -ENOMEM; - goto out_free_buffer; - } - - cmd->scsi_cmd = NULL; - ioarcb = &(cmd->ioa_cb->ioarcb); - - /* Copy the user-provided IOARCB stuff field by field */ - ioarcb->resource_handle = buffer->ioarcb.resource_handle; - ioarcb->data_transfer_length = buffer->ioarcb.data_transfer_length; - ioarcb->cmd_timeout = buffer->ioarcb.cmd_timeout; - ioarcb->request_type = buffer->ioarcb.request_type; - ioarcb->request_flags0 = buffer->ioarcb.request_flags0; - ioarcb->request_flags1 = buffer->ioarcb.request_flags1; - memcpy(ioarcb->cdb, buffer->ioarcb.cdb, PMCRAID_MAX_CDB_LEN); - - if (buffer->ioarcb.add_cmd_param_length) { - ioarcb->add_cmd_param_length = - buffer->ioarcb.add_cmd_param_length; - ioarcb->add_cmd_param_offset = - buffer->ioarcb.add_cmd_param_offset; - memcpy(ioarcb->add_data.u.add_cmd_params, - buffer->ioarcb.add_data.u.add_cmd_params, - le16_to_cpu(buffer->ioarcb.add_cmd_param_length)); - } - - /* set hrrq number where the IOA should respond to. Note that all cmds - * generated internally uses hrrq_id 0, exception to this is the cmd - * block of scsi_cmd which is re-used (e.g. cancel/abort), which uses - * hrrq_id assigned here in queuecommand - */ - ioarcb->hrrq_id = atomic_add_return(1, &(pinstance->last_message_id)) % - pinstance->num_hrrq; - - if (request_size) { - rc = pmcraid_build_passthrough_ioadls(cmd, - request_size, - direction); - if (rc) { - pmcraid_err("couldn't build passthrough ioadls\n"); - goto out_free_cmd; - } - } - - /* If data is being written into the device, copy the data from user - * buffers - */ - if (direction == DMA_TO_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - goto out_free_sglist; - } - } - - /* passthrough ioctl is a blocking command so, put the user to sleep - * until timeout. Note that a timeout value of 0 means, do timeout. - */ - cmd->cmd_done = pmcraid_internal_done; - init_completion(&cmd->wait_for_completion); - cmd->completion_req = 1; - - pmcraid_info("command(%d) (CDB[0] = %x) for %x\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0], - le32_to_cpu(cmd->ioa_cb->ioarcb.resource_handle)); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - _pmcraid_fire_command(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - /* NOTE ! Remove the below line once abort_task is implemented - * in firmware. This line disables ioctl command timeout handling logic - * similar to IO command timeout handling, making ioctl commands to wait - * until the command completion regardless of timeout value specified in - * ioarcb - */ - buffer->ioarcb.cmd_timeout = 0; - - /* If command timeout is specified put caller to wait till that time, - * otherwise it would be blocking wait. If command gets timed out, it - * will be aborted. - */ - if (buffer->ioarcb.cmd_timeout == 0) { - wait_for_completion(&cmd->wait_for_completion); - } else if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(le16_to_cpu(buffer->ioarcb.cmd_timeout) * 1000))) { - - pmcraid_info("aborting cmd %d (CDB[0] = %x) due to timeout\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0]); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - cancel_cmd = pmcraid_abort_cmd(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - if (cancel_cmd) { - wait_for_completion(&cancel_cmd->wait_for_completion); - ioasc = le32_to_cpu(cancel_cmd->ioa_cb->ioasa.ioasc); - pmcraid_return_cmd(cancel_cmd); - - /* if abort task couldn't find the command i.e it got - * completed prior to aborting, return good completion. - * if command got aborted successfully or there was IOA - * reset due to abort task itself getting timedout then - * return -ETIMEDOUT - */ - if (ioasc == PMCRAID_IOASC_IOA_WAS_RESET || - PMCRAID_IOASC_SENSE_KEY(ioasc) == 0x00) { - if (ioasc != PMCRAID_IOASC_GC_IOARCB_NOTFOUND) - rc = -ETIMEDOUT; - goto out_handle_response; - } - } - - /* no command block for abort task or abort task failed to abort - * the IOARCB, then wait for 150 more seconds and initiate reset - * sequence after timeout - */ - if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(150 * 1000))) { - pmcraid_reset_bringup(cmd->drv_inst); - rc = -ETIMEDOUT; - } - } - -out_handle_response: - /* copy entire IOASA buffer and return IOCTL success. - * If copying IOASA to user-buffer fails, return - * EFAULT - */ - if (copy_to_user(ioasa, &cmd->ioa_cb->ioasa, - sizeof(struct pmcraid_ioasa))) { - pmcraid_err("failed to copy ioasa buffer to user\n"); - rc = -EFAULT; - } - - /* If the data transfer was from device, copy the data onto user - * buffers - */ - else if (direction == DMA_FROM_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - rc = -EFAULT; - } - } - -out_free_sglist: - pmcraid_release_passthrough_ioadls(cmd, request_size, direction); - -out_free_cmd: - pmcraid_return_cmd(cmd); - -out_free_buffer: - kfree(buffer); - - return rc; -} - - - - /** * pmcraid_ioctl_driver - ioctl handler for commands handled by driver itself * @@ -3922,20 +3445,6 @@ static long pmcraid_chr_ioctl( switch (_IOC_TYPE(cmd)) { - case PMCRAID_PASSTHROUGH_IOCTL: - /* If ioctl code is to download microcode, we need to block - * mid-layer requests. - */ - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_block_requests(pinstance->host); - - retval = pmcraid_ioctl_passthrough(pinstance, cmd, - hdr->buffer_length, argp); - - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_unblock_requests(pinstance->host); - break; - case PMCRAID_DRIVER_IOCTL: arg += sizeof(struct pmcraid_ioctl_header); retval = pmcraid_ioctl_driver(pinstance, cmd, diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index bbb75318f1e7..9f59930e8b4f 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -1023,40 +1023,15 @@ struct pmcraid_ioctl_header { #define PMCRAID_IOCTL_SIGNATURE "PMCRAID" /* - * pmcraid_passthrough_ioctl_buffer - structure given as argument to - * passthrough(or firmware handled) IOCTL commands. Note that ioarcb requires - * 32-byte alignment so, it is necessary to pack this structure to avoid any - * holes between ioctl_header and passthrough buffer - * - * .ioactl_header : ioctl header - * .ioarcb : filled-up ioarcb buffer, driver always reads this buffer - * .ioasa : buffer for ioasa, driver fills this with IOASA from firmware - * .request_buffer: The I/O buffer (flat), driver reads/writes to this based on - * the transfer directions passed in ioarcb.flags0. Contents - * of this buffer are valid only when ioarcb.data_transfer_len - * is not zero. - */ -struct pmcraid_passthrough_ioctl_buffer { - struct pmcraid_ioctl_header ioctl_header; - struct pmcraid_ioarcb ioarcb; - struct pmcraid_ioasa ioasa; - u8 request_buffer[]; -} __attribute__ ((packed, aligned(PMCRAID_IOARCB_ALIGNMENT))); - -/* * keys to differentiate between driver handled IOCTLs and passthrough * IOCTLs passed to IOA. driver determines the ioctl type using macro * _IOC_TYPE */ #define PMCRAID_DRIVER_IOCTL 'D' -#define PMCRAID_PASSTHROUGH_IOCTL 'F' #define DRV_IOCTL(n, size) \ _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_DRIVER_IOCTL, (n), (size)) -#define FMW_IOCTL(n, size) \ - _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_PASSTHROUGH_IOCTL, (n), (size)) - /* * _ARGSIZE: macro that gives size of the argument type passed to an IOCTL cmd. * This is to facilitate applications avoiding un-necessary memory allocations. @@ -1069,12 +1044,4 @@ struct pmcraid_passthrough_ioctl_buffer { #define PMCRAID_IOCTL_RESET_ADAPTER \ DRV_IOCTL(5, sizeof(struct pmcraid_ioctl_header)) -/* passthrough/firmware handled commands */ -#define PMCRAID_IOCTL_PASSTHROUGH_COMMAND \ - FMW_IOCTL(1, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - -#define PMCRAID_IOCTL_DOWNLOAD_MICROCODE \ - FMW_IOCTL(2, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - - #endif /* _PMCRAID_H */ diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index c607755cce00..ff78ef702f22 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7519,12 +7519,13 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) struct sdebug_defer *sd_dp; sqp = sdebug_q_arr + queue_num; - qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); - if (qc_idx >= sdebug_max_queue) - return 0; spin_lock_irqsave(&sqp->qc_lock, iflags); + qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); + if (qc_idx >= sdebug_max_queue) + goto unlock; + for (first = true; first || qc_idx + 1 < sdebug_max_queue; ) { if (first) { first = false; @@ -7589,6 +7590,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) break; } +unlock: spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (num_entries > 0) diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ff89de86545d..b02af340c2d3 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - if (!rq->q->disk) + if (!rq->q || !rq->q->disk) return NULL; return rq->q->disk->disk_name; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f4e6c68ac99e..2ef78083f1ef 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int ret; struct sbitmap sb_backup; + depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev)); + /* * realloc if new shift is calculated, which is caused by setting * up one new default queue depth after calling ->slave_configure @@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, scsi_device_max_queue_depth(sdev), new_shift, GFP_KERNEL, sdev->request_queue->node, false, true); + if (!ret) + sbitmap_resize(&sdev->budget_map, depth); + if (need_free) { if (ret) sdev->budget_map = sb_backup; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 226a50944c00..dc6872e352bd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1384,10 +1384,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { sdev->bsg_dev = scsi_bsg_register_queue(sdev); if (IS_ERR(sdev->bsg_dev)) { - /* - * We're treating error on bsg register as non-fatal, so - * pretend nothing went wrong. - */ error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a390679cf458..dc6e55761fd1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3216,6 +3216,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); + sd_read_cpr(sdkp); } sd_print_capacity(sdkp, old_capacity); @@ -3225,7 +3226,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_read_cpr(sdkp); } /* @@ -3475,6 +3475,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { put_device(&sdkp->disk_dev); + blk_cleanup_disk(gd); goto out; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 5ba9df334968..cbd92891a762 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -535,7 +535,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, scsi_autopm_get_device(sdev); - if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) { + if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) goto put; diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 0d2e950d0865..586c0e567ff9 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -957,18 +957,6 @@ static const struct reset_control_ops ufs_qcom_reset_ops = { .deassert = ufs_qcom_reset_deassert, }; -#define ANDROID_BOOT_DEV_MAX 30 -static char android_boot_dev[ANDROID_BOOT_DEV_MAX]; - -#ifndef MODULE -static int __init get_android_boot_dev(char *str) -{ - strlcpy(android_boot_dev, str, ANDROID_BOOT_DEV_MAX); - return 1; -} -__setup("androidboot.bootdevice=", get_android_boot_dev); -#endif - /** * ufs_qcom_init - bind phy with controller * @hba: host controller instance @@ -988,9 +976,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct resource *res; struct ufs_clk_info *clki; - if (strlen(android_boot_dev) && strcmp(android_boot_dev, dev_name(dev))) - return -ENODEV; - host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) { err = -ENOMEM; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f76692053ca1..e892b9feffb1 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mtl_init(struct ufs_hba *hba) +{ + hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_mtl_init, + .exit = ufs_intel_common_exit, + .hce_enable_notify = ufs_intel_hce_enable_notify, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 88c20f3608c2..94f545be183a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -820,8 +820,6 @@ struct ufs_hba { enum ufs_pm_level rpm_lvl; /* Desired UFS power management level during system PM */ enum ufs_pm_level spm_lvl; - struct device_attribute rpm_lvl_attr; - struct device_attribute spm_lvl_attr; int pm_op_in_progress; /* Auto-Hibernate Idle Timer register value */ diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index b2bec19022cd..81099b68bbfb 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -867,12 +867,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) struct ufshpb_region *rgn, *victim_rgn = NULL; list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { - if (!rgn) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "%s: no region allocated\n", - __func__); - return NULL; - } if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; @@ -888,6 +882,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) break; } + if (!victim_rgn) + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: no region allocated\n", + __func__); + return victim_rgn; } diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e6110da69e7..578c4b6d0f7d 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -988,7 +988,7 @@ static struct virtio_driver virtio_scsi_driver = { .remove = virtscsi_remove, }; -static int __init init(void) +static int __init virtio_scsi_init(void) { int ret = -ENOMEM; @@ -1020,14 +1020,14 @@ error: return ret; } -static void __exit fini(void) +static void __exit virtio_scsi_fini(void) { unregister_virtio_driver(&virtio_scsi_driver); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } -module_init(init); -module_exit(fini); +module_init(virtio_scsi_init); +module_exit(virtio_scsi_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio SCSI HBA driver"); diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c index 27b9e2baab1a..7acf9193a9e8 100644 --- a/drivers/scsi/zorro7xx.c +++ b/drivers/scsi/zorro7xx.c @@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z) scsi_remove_host(host); NCR_700_release(host); + if (host->base > 0x01000000) + iounmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); zorro_release_device(z); diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 86c76211b3d3..cad2d55dcd3d 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, addr = op->addr.val; len = op->data.nbytes; - if (bcm_qspi_bspi_ver_three(qspi) == true) { + if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) { /* * The address coming into this function is a raw flash offset. * But for BSPI <= V3, we need to convert it to a remapped BSPI @@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, len < 4) mspi_read = true; - if (mspi_read) + if (!has_bspi(qspi) || mspi_read) return bcm_qspi_mspi_exec_mem_op(spi, op); ret = bcm_qspi_bspi_set_mode(qspi, op, 0); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index b0c9f62ccefb..616ada891974 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -19,6 +19,7 @@ #include <linux/iopoll.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of.h> @@ -102,12 +103,6 @@ struct cqspi_driver_platdata { #define CQSPI_TIMEOUT_MS 500 #define CQSPI_READ_TIMEOUT_MS 10 -/* Instruction type */ -#define CQSPI_INST_TYPE_SINGLE 0 -#define CQSPI_INST_TYPE_DUAL 1 -#define CQSPI_INST_TYPE_QUAD 2 -#define CQSPI_INST_TYPE_OCTAL 3 - #define CQSPI_DUMMY_CLKS_PER_BYTE 8 #define CQSPI_DUMMY_BYTES_MAX 4 #define CQSPI_DUMMY_CLKS_MAX 31 @@ -376,10 +371,6 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, const struct spi_mem_op *op) { - f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - /* * For an op to be DTR, cmd phase along with every other non-empty * phase should have dtr field set to 1. If an op phase has zero @@ -389,32 +380,23 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, (!op->addr.nbytes || op->addr.dtr) && (!op->data.nbytes || op->data.dtr); - switch (op->data.buswidth) { - case 0: - break; - case 1: - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - break; - case 2: - f_pdata->data_width = CQSPI_INST_TYPE_DUAL; - break; - case 4: - f_pdata->data_width = CQSPI_INST_TYPE_QUAD; - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } + f_pdata->inst_width = 0; + if (op->cmd.buswidth) + f_pdata->inst_width = ilog2(op->cmd.buswidth); + + f_pdata->addr_width = 0; + if (op->addr.buswidth) + f_pdata->addr_width = ilog2(op->addr.buswidth); + + f_pdata->data_width = 0; + if (op->data.buswidth) + f_pdata->data_width = ilog2(op->data.buswidth); /* Right now we only support 8-8-8 DTR mode. */ if (f_pdata->dtr) { switch (op->cmd.buswidth) { case 0: - break; case 8: - f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -422,9 +404,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->addr.buswidth) { case 0: - break; case 8: - f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -432,9 +412,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->data.buswidth) { case 0: - break; case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 55c092069301..65be8e085ab8 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -813,6 +813,7 @@ static int mxic_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); pm_runtime_disable(&pdev->dev); + mxic_spi_mem_ecc_remove(mxic); } return ret; diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index fe82f3575df4..24ec1c83f379 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev) error = rpcif_hw_init(rpc, false); if (error) - return error; + goto out_disable_rpm; error = spi_register_controller(ctlr); if (error) { dev_err(&pdev->dev, "spi_register_controller failed\n"); - rpcif_disable_rpm(rpc); + goto out_disable_rpm; } + return 0; + +out_disable_rpm: + rpcif_disable_rpm(rpc); return error; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c4dd1200fe99..2e6d6bbeb784 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1130,11 +1130,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg) if (ctlr->dma_tx) tx_dev = ctlr->dma_tx->device->dev; + else if (ctlr->dma_map_dev) + tx_dev = ctlr->dma_map_dev; else tx_dev = ctlr->dev.parent; if (ctlr->dma_rx) rx_dev = ctlr->dma_rx->device->dev; + else if (ctlr->dma_map_dev) + rx_dev = ctlr->dma_map_dev; else rx_dev = ctlr->dev.parent; @@ -2406,7 +2410,8 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data) } else { struct acpi_device *adev; - if (acpi_bus_get_device(parent_handle, &adev)) + adev = acpi_fetch_acpi_dev(parent_handle); + if (!adev) return -ENODEV; ctlr = acpi_spi_find_controller_by_adev(adev); diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 95d4ca50a605..fd7267baa707 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1821,6 +1821,7 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi) mutex_lock(&udev->cmdr_lock); page = xa_load(&udev->data_pages, dpi); if (likely(page)) { + get_page(page); mutex_unlock(&udev->cmdr_lock); return page; } @@ -1877,6 +1878,7 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) /* For the vmalloc()ed cmd area pages */ addr = (void *)(unsigned long)info->mem[mi].addr + offset; page = vmalloc_to_page(addr); + get_page(page); } else { uint32_t dpi; @@ -1887,7 +1889,6 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - get_page(page); vmf->page = page; return 0; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2f4fb09f1e89..79001301b383 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -163,6 +163,7 @@ struct mlx5_vdpa_net { u32 cur_num_vqs; struct notifier_block nb; struct vdpa_callback config_cb; + struct mlx5_vdpa_wq_ent cvq_ent; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -1658,6 +1659,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) mvdev = wqent->mvdev; ndev = to_mlx5_vdpa_ndev(mvdev); cvq = &mvdev->cvq; + + mutex_lock(&ndev->reslock); + + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) goto out; @@ -1696,9 +1703,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) if (vringh_need_notify_iotlb(&cvq->vring)) vringh_notify(&cvq->vring); + + queue_work(mvdev->wq, &wqent->work); + break; } + out: - kfree(wqent); + mutex_unlock(&ndev->reslock); } static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) @@ -1706,7 +1717,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - struct mlx5_vdpa_wq_ent *wqent; if (!is_index_valid(mvdev, idx)) return; @@ -1715,13 +1725,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) if (!mvdev->wq || !mvdev->cvq.ready) return; - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return; - - wqent->mvdev = mvdev; - INIT_WORK(&wqent->work, mlx5_cvq_kick_handler); - queue_work(mvdev->wq, &wqent->work); + queue_work(mvdev->wq, &ndev->cvq_ent.work); return; } @@ -2180,7 +2184,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb goto err_mr; if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) - return 0; + goto err_mr; restore_channels_info(ndev); err = setup_driver(mvdev); @@ -2195,12 +2199,14 @@ err_mr: return err; } +/* reslock must be held for this function */ static int setup_driver(struct mlx5_vdpa_dev *mvdev) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; - mutex_lock(&ndev->reslock); + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (ndev->setup) { mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n"); err = 0; @@ -2230,7 +2236,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto err_fwd; } ndev->setup = true; - mutex_unlock(&ndev->reslock); return 0; @@ -2241,23 +2246,23 @@ err_tir: err_rqt: teardown_virtqueues(ndev); out: - mutex_unlock(&ndev->reslock); return err; } +/* reslock must be held for this function */ static void teardown_driver(struct mlx5_vdpa_net *ndev) { - mutex_lock(&ndev->reslock); + + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (!ndev->setup) - goto out; + return; remove_fwd_to_tir(ndev); destroy_tir(ndev); destroy_rqt(ndev); teardown_virtqueues(ndev); ndev->setup = false; -out: - mutex_unlock(&ndev->reslock); } static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) @@ -2278,6 +2283,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) print_status(mvdev, status, true); + mutex_lock(&ndev->reslock); + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { err = setup_driver(mvdev); @@ -2287,16 +2294,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); - return; + goto err_clear; } } ndev->mvdev.status = status; + mutex_unlock(&ndev->reslock); return; err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +err_clear: + mutex_unlock(&ndev->reslock); } static int mlx5_vdpa_reset(struct vdpa_device *vdev) @@ -2306,6 +2316,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) print_status(mvdev, 0, true); mlx5_vdpa_info(mvdev, "performing device reset\n"); + + mutex_lock(&ndev->reslock); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2318,6 +2330,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) if (mlx5_vdpa_create_mr(mvdev, NULL)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } + mutex_unlock(&ndev->reslock); return 0; } @@ -2353,19 +2366,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); bool change_map; int err; + mutex_lock(&ndev->reslock); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); - return err; + goto err; } if (change_map) - return mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb); - return 0; +err: + mutex_unlock(&ndev->reslock); + return err; } static void mlx5_vdpa_free(struct vdpa_device *vdev) @@ -2740,6 +2758,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mr; + ndev->cvq_ent.mvdev = mvdev; + INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler); mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq"); if (!mvdev->wq) { err = -ENOMEM; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 34d6bb1bf82e..a6bb0e438216 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1579,7 +1579,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, * If it's not a platform device, at least print a warning. A * fix would add code to remove the device from the system. */ - if (dev_is_platform(device)) { + if (!device) { + /* TODO: Represent each OF framebuffer as its own + * device in the device hierarchy. For now, offb + * doesn't have such a device, so unregister the + * framebuffer as before without warning. + */ + do_unregister_framebuffer(registered_fb[i]); + } else if (dev_is_platform(device)) { registered_fb[i]->forced_out = true; platform_device_unregister(to_platform_device(device)); } else { diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75c8d560bbd3..22f15f444f75 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -526,9 +526,8 @@ int virtio_device_restore(struct virtio_device *dev) goto err; } - /* If restore didn't do it, mark device DRIVER_OK ourselves. */ - if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) - virtio_device_ready(dev); + /* Finally, tell the device we're all set */ + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); virtio_config_enable(dev); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0399cf8e3c32..151e9da5da2d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -118,7 +118,7 @@ struct btrfs_bio_ctrl { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f455c96c974..380054c94e4b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2957,8 +2957,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } + ret = file_modified(file); + if (ret) + goto out_only_mutex; + lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode))); lockend = round_down(offset + len, btrfs_inode_sectorsize(BTRFS_I(inode))) - 1; @@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); + return btrfs_punch_hole(file, offset, len); /* * Only trigger disk allocation, don't trigger qgroup reserve @@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6bfc4343c98d..17d5557f98ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, int ret = 0; if (btrfs_is_free_space_inode(inode)) { - WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; } @@ -4488,6 +4487,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); return -EPERM; } + if (atomic_read(&dest->nr_swapfiles)) { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu with active swapfile", + root->root_key.objectid); + return -EPERM; + } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); @@ -11107,8 +11113,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, * set. We use this counter to prevent snapshots. We must increment it * before walking the extents because we don't want a concurrent * snapshot to run after we've already checked the extents. + * + * It is possible that subvolume is marked for deletion but still not + * removed yet. To prevent this race, we check the root status before + * activating the swapfile. */ + spin_lock(&root->root_item_lock); + if (btrfs_root_dead(root)) { + spin_unlock(&root->root_item_lock); + + btrfs_exclop_finish(fs_info); + btrfs_warn(fs_info, + "cannot activate swapfile because subvolume %llu is being deleted", + root->root_key.objectid); + return -EPERM; + } atomic_inc(&root->nr_swapfiles); + spin_unlock(&root->root_item_lock); isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238cee5b5254..f46e71061942 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em) } static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) + u32 extent_thresh, u64 newer_than, bool locked) { struct extent_map *next; bool ret = false; @@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, return false; /* - * We want to check if the next extent can be merged with the current - * one, which can be an extent created in a past generation, so we pass - * a minimum generation of 0 to defrag_lookup_extent(). + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. */ - next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) goto out; @@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, */ if (next->len >= get_extent_max_capacity(em)) goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; out: free_extent_map(next); @@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); + extent_thresh, newer_than, locked); if (!next_mergeable) { struct defrag_target_range *last; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1be7cb2f955f..2cfbc74a3b4e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path) path_put(&path); } -static int btrfs_rm_dev_item(struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, + struct btrfs_device *device) { struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_trans_handle *trans; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); - } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device) if (ret) { if (ret > 0) ret = -ENOENT; - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - } - out: btrfs_free_path(path); - if (!ret) - ret = btrfs_commit_transaction(trans); return ret; } @@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, struct block_device **bdev, fmode_t *mode) { + struct btrfs_trans_handle *trans; struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) - goto out; + return ret; device = btrfs_find_device(fs_info->fs_devices, args); if (!device) { @@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; else ret = -ENOENT; - goto out; + return ret; } if (btrfs_pinned_by_swapfile(fs_info, device)) { btrfs_warn_in_rcu(fs_info, "cannot remove device %s (devid %llu) due to active swapfile", rcu_str_deref(device->name), device->devid); - ret = -ETXTBSY; - goto out; + return -ETXTBSY; } - if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto out; - } + if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) + return BTRFS_ERROR_DEV_TGT_REPLACE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && - fs_info->fs_devices->rw_devices == 1) { - ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto out; - } + fs_info->fs_devices->rw_devices == 1) + return BTRFS_ERROR_DEV_ONLY_WRITABLE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); @@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, if (ret) goto error_undo; - /* - * TODO: the superblock still includes this device in its num_devices - * counter although write_all_supers() is not locked out. This - * could give a filesystem state which requires a degraded mount. - */ - ret = btrfs_rm_dev_item(device); - if (ret) + trans = btrfs_start_transaction(fs_info->chunk_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); goto error_undo; + } + + ret = btrfs_rm_dev_item(trans, device); + if (ret) { + /* Any error in dev item removal is critical */ + btrfs_crit(fs_info, + "failed to remove device item for devid %llu: %d", + device->devid, ret); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); btrfs_scrub_cancel_dev(device); @@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, free_fs_devices(cur_devices); } -out: + ret = btrfs_commit_transaction(trans); + return ret; error_undo: @@ -2240,7 +2231,7 @@ error_undo: device->fs_devices->rw_devices++; mutex_unlock(&fs_info->chunk_mutex); } - goto out; + return ret; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b7b5fac1c779..1b1b310c3c51 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, map = em->map_lookup; /* We only support single profile for now */ - ASSERT(map->num_stripes == 1); device = map->stripes[0].dev; free_extent_map(em); @@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) { + struct btrfs_fs_info *fs_info = fs_devices->fs_info; struct btrfs_device *device; bool ret = false; - if (!btrfs_is_zoned(fs_devices->fs_info)) + if (!btrfs_is_zoned(fs_info)) return true; - /* Non-single profiles are not supported yet */ - ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0); - /* Check if there is a device with active zones left */ - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) { + mutex_lock(&fs_info->chunk_mutex); + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { struct btrfs_zoned_device_info *zinfo = device->zone_info; if (!device->bdev) @@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) break; } } - mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 15a5c5db038b..c0542bdcd06b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ #define SMB3_PRODUCT_BUILD 35 -#define CIFS_VERSION "2.35" +#define CIFS_VERSION "2.36" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ee3b7c15e884..54155eb4faac 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int -reconnect_dfs_server(struct TCP_Server_Info *server, - bool mark_smb_session) +static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); + /* + * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a + * different server or share during failover. It could be improved by adding some logic to + * only do that in case it connects to a different server or share, though. + */ + cifs_mark_tcp_ses_conns_for_reconnect(server, true); cifs_abort_connection(server); @@ -537,7 +540,7 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server, mark_smb_session); + return reconnect_dfs_server(server); } #else int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) @@ -4465,7 +4468,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - cifs_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } dfs_cache_free_tgts(tl); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index ebe236b9d9f5..235aa1b395eb 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - cifs_reconnect(mid->server, false); + cifs_signal_cifsd_for_reconnect(mid->server, false); } } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index c653beb735b8..3fe47a88f47d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; + struct cifs_ses *iter; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { - if (ses->Suid == le64_to_cpu(thdr->SessionId)) + list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + if (iter->Suid == le64_to_cpu(thdr->SessionId)) { + ses = iter; break; + } } spin_unlock(&cifs_tcp_ses_lock); - if (list_entry_is_head(ses, &srvr->smb_ses_list, - smb_ses_list)) { + if (!ses) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } diff --git a/fs/file_table.c b/fs/file_table.c index 7d2e692b66a9..ada8fe814db9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -412,6 +412,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { diff --git a/fs/io-wq.h b/fs/io-wq.h index dbecd27656c7..04d374e65e54 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; + int fd; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index a8413f006417..659f8ecba5b7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -63,7 +63,6 @@ #include <net/sock.h> #include <net/af_unix.h> #include <net/scm.h> -#include <net/busy_poll.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -112,8 +111,7 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -412,11 +410,6 @@ struct io_ring_ctx { struct list_head sqd_list; unsigned long check_cq_overflow; -#ifdef CONFIG_NET_RX_BUSY_POLL - /* used to track busy poll napi_id */ - struct list_head napi_list; - spinlock_t napi_lock; /* napi_list lock */ -#endif struct { unsigned cached_cq_tail; @@ -500,7 +493,6 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; @@ -592,7 +584,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + u32 flags; }; struct io_connect { @@ -654,10 +647,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -1182,8 +1175,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1313,13 +1309,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(req->fixed_rsrc_refs); + } } } @@ -1424,29 +1427,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1456,24 +1439,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1595,10 +1563,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); -#ifdef CONFIG_NET_RX_BUSY_POLL - INIT_LIST_HEAD(&ctx->napi_list); - spin_lock_init(&ctx->napi_lock); -#endif return ctx; err: kfree(ctx->dummy_ubuf); @@ -1636,14 +1600,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -1687,14 +1643,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - switch (req->opcode) { - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!S_ISREG(file_inode(req->splice.file_in)->i_mode)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } } static void io_prep_async_link(struct io_kiocb *req) @@ -1788,12 +1736,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); - while (!list_empty(&ctx->timeout_list)) { + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; - struct io_kiocb *req = list_first_entry(&ctx->timeout_list, - struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; @@ -1810,7 +1757,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - list_del_init(&req->timeout.list); io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; @@ -2562,6 +2508,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); + spin_lock_irqsave(&tctx->task_lock, flags); if (priority) wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); @@ -3186,42 +3134,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3237,6 +3154,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3367,7 +3285,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3377,7 +3296,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3539,7 +3458,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; @@ -3740,13 +3659,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3834,6 +3746,49 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3869,6 +3824,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3972,13 +3930,6 @@ out_free: return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3999,6 +3950,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -4369,18 +4323,11 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -4395,20 +4342,29 @@ static int io_tee_prep(struct io_kiocb *req, static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4427,15 +4383,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -4444,8 +4409,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4513,9 +4477,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -5757,108 +5718,6 @@ IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ -#ifdef CONFIG_NET_RX_BUSY_POLL - -#define NAPI_TIMEOUT (60 * SEC_CONVERSION) - -struct napi_entry { - struct list_head list; - unsigned int napi_id; - unsigned long timeout; -}; - -/* - * Add busy poll NAPI ID from sk. - */ -static void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ - unsigned int napi_id; - struct socket *sock; - struct sock *sk; - struct napi_entry *ne; - - if (!net_busy_loop_on()) - return; - - sock = sock_from_file(file); - if (!sock) - return; - - sk = sock->sk; - if (!sk) - return; - - napi_id = READ_ONCE(sk->sk_napi_id); - - /* Non-NAPI IDs can be rejected */ - if (napi_id < MIN_NAPI_ID) - return; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(ne, &ctx->napi_list, list) { - if (ne->napi_id == napi_id) { - ne->timeout = jiffies + NAPI_TIMEOUT; - goto out; - } - } - - ne = kmalloc(sizeof(*ne), GFP_NOWAIT); - if (!ne) - goto out; - - ne->napi_id = napi_id; - ne->timeout = jiffies + NAPI_TIMEOUT; - list_add_tail(&ne->list, &ctx->napi_list); -out: - spin_unlock(&ctx->napi_lock); -} - -static inline void io_check_napi_entry_timeout(struct napi_entry *ne) -{ - if (time_after(jiffies, ne->timeout)) { - list_del(&ne->list); - kfree(ne); - } -} - -/* - * Busy poll if globally on and supporting sockets found - */ -static bool io_napi_busy_loop(struct list_head *napi_list) -{ - struct napi_entry *ne, *n; - - list_for_each_entry_safe(ne, n, napi_list, list) { - napi_busy_loop(ne->napi_id, NULL, NULL, true, - BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - } - return !list_empty(napi_list); -} - -static void io_free_napi_list(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->napi_lock); - while (!list_empty(&ctx->napi_list)) { - struct napi_entry *ne = - list_first_entry(&ctx->napi_list, struct napi_entry, - list); - - list_del(&ne->list); - kfree(ne); - } - spin_unlock(&ctx->napi_lock); -} -#else -static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ -} - -static inline void io_free_napi_list(struct io_ring_ctx *ctx) -{ -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; @@ -5972,7 +5831,7 @@ static void io_poll_remove_entries(struct io_kiocb *req) * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; struct io_poll_iocb *poll = io_poll_get_single(req); @@ -5994,7 +5853,10 @@ static int io_poll_check_events(struct io_kiocb *req) if (!req->result) { struct poll_table_struct pt = { ._key = req->cflags }; - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED))) + req->result = -EBADF; + else + req->result = vfs_poll(req->file, &pt) & req->cflags; } /* multishot, just fill an CQE and proceed */ @@ -6010,7 +5872,6 @@ static int io_poll_check_events(struct io_kiocb *req) if (unlikely(!filled)) return -ECANCELED; io_cqring_ev_posted(ctx); - io_add_napi(req->file, ctx); } else if (req->result) { return 0; } @@ -6029,7 +5890,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6054,7 +5915,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6261,7 +6122,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask, poll->events); return 0; } - io_add_napi(req->file, req->ctx); /* * Release ownership. If someone tried to queue a tw while it was @@ -6766,6 +6626,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6992,11 +6853,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: @@ -7179,11 +7039,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(req->splice.file_in); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) @@ -7218,11 +7073,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7232,6 +7082,23 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->work.fd, issue_flags); + else + req->file = io_file_get_normal(req, req->work.fd); + if (req->file) + return true; + + req_set_fail(req); + req->result = -EBADF; + return false; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; @@ -7242,6 +7109,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (!io_op_defs[req->opcode].audit_skip) audit_uring_entry(req->opcode); + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; switch (req->opcode) { case IORING_OP_NOP: @@ -7386,10 +7255,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -7401,14 +7271,18 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + } + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); + io_req_task_queue_fail(req, err); return; } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7465,46 +7339,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); +out: + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->user_data, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; @@ -7744,6 +7628,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->work.fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7753,11 +7639,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); @@ -8032,13 +7913,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); -#ifdef CONFIG_NET_RX_BUSY_POLL - spin_lock(&ctx->napi_lock); - if (!list_empty(&ctx->napi_list) && - io_napi_busy_loop(&ctx->napi_list)) - ++ret; - spin_unlock(&ctx->napi_lock); -#endif + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) @@ -8176,9 +8051,6 @@ struct io_wait_queue { struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned busy_poll_to; -#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) @@ -8240,87 +8112,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return 1; } -#ifdef CONFIG_NET_RX_BUSY_POLL -static void io_adjust_busy_loop_timeout(struct timespec64 *ts, - struct io_wait_queue *iowq) -{ - unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll); - struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to); - - if (timespec64_compare(ts, &pollto) > 0) { - *ts = timespec64_sub(*ts, pollto); - iowq->busy_poll_to = busy_poll_to; - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - iowq->busy_poll_to = to; - ts->tv_sec = 0; - ts->tv_nsec = 0; - } -} - -static inline bool io_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) -{ - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); - - return time_after(now, end_time); - } - return true; -} - -static bool io_busy_loop_end(void *p, unsigned long start_time) -{ - struct io_wait_queue *iowq = p; - - return signal_pending(current) || - io_should_wake(iowq) || - io_busy_loop_timeout(start_time, iowq->busy_poll_to); -} - -static void io_blocking_napi_busy_loop(struct list_head *napi_list, - struct io_wait_queue *iowq) -{ - unsigned long start_time = - list_is_singular(napi_list) ? 0 : - busy_loop_current_time(); - - do { - if (list_is_singular(napi_list)) { - struct napi_entry *ne = - list_first_entry(napi_list, - struct napi_entry, list); - - napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq, - true, BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - break; - } - } while (io_napi_busy_loop(napi_list) && - !io_busy_loop_end(iowq, start_time)); -} - -static void io_putback_napi_list(struct io_ring_ctx *ctx, - struct list_head *napi_list) -{ - struct napi_entry *cne, *lne; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(cne, &ctx->napi_list, list) - list_for_each_entry(lne, napi_list, list) - if (cne->napi_id == lne->napi_id) { - list_del(&lne->list); - kfree(lne); - break; - } - list_splice(napi_list, &ctx->napi_list); - spin_unlock(&ctx->napi_lock); -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -8333,9 +8124,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; -#ifdef CONFIG_NET_RX_BUSY_POLL - LIST_HEAD(local_napi_list); -#endif do { io_cqring_overflow_flush(ctx); @@ -8358,29 +8146,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } -#ifdef CONFIG_NET_RX_BUSY_POLL - iowq.busy_poll_to = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { - spin_lock(&ctx->napi_lock); - list_splice_init(&ctx->napi_list, &local_napi_list); - spin_unlock(&ctx->napi_lock); - } -#endif if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!list_empty(&local_napi_list)) - io_adjust_busy_loop_timeout(&ts, &iowq); -#endif timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } -#ifdef CONFIG_NET_RX_BUSY_POLL - else if (!list_empty(&local_napi_list)) - iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll); -#endif init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; @@ -8390,12 +8162,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); -#ifdef CONFIG_NET_RX_BUSY_POLL - if (iowq.busy_poll_to) - io_blocking_napi_busy_loop(&local_napi_list, &iowq); - if (!list_empty(&local_napi_list)) - io_putback_napi_list(ctx, &local_napi_list); -#endif do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { @@ -8864,8 +8630,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr_files; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (file) + fput(file); + } } else { kfree_skb(skb); free_uid(fpl->user); @@ -9156,13 +8926,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { + u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; - prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->tag = *tag_slot; + *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -9231,7 +9003,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; - int ret, i; + int ret; io_ring_submit_lock(ctx, needs_lock); ret = -ENXIO; @@ -9244,8 +9016,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) if (ret) goto out; - i = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; @@ -9301,8 +9073,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, up->offset + done, - ctx->rsrc_node, file); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; @@ -9327,7 +9098,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, up->offset + done) = tag; + *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { @@ -9411,7 +9182,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -9986,7 +9756,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, offset, + err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); @@ -10181,7 +9951,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); - io_free_napi_list(ctx); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); kfree(ctx->io_buffers); @@ -10604,7 +10373,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } @@ -11707,7 +11476,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (copy_from_user(new_mask, arg, len)) { + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { free_cpumask_var(new_mask); return -EFAULT; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 47a53b3362b6..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,10 +4,6 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC - select CRYPTO - select CRYPTO_HASH - select XXHASH - select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bac4cf1a308e..c6b263b5faf1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,7 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> -#include <linux/xxhash.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -350,10 +350,7 @@ out: * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * - * The xxhash algorithm is chosen because it is fast, and is supposed - * to result in a decent flat distribution of hashes. - * - * We then select only the first 18 bits to avoid issues with excessive + * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a @@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) { if (cookie == 0) return 0; - return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; + return hash_64(cookie, 18); } static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, @@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7eb3b08d702f..b4e46b0ffa2d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 57b0497105c8..7eefa16ed381 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index ad3405c64b9e..e7b34f7e0614 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index d258933cf8c8..7b861e4f0533 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e3f5b380cefe..16106f805ffa 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..6f325e10056c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..c4b78c21d793 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -509,7 +509,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c1fc4af47f69..3a9d2d7cc6b7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; } #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-array.h> + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 761f8f1885c7..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -627,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..874aabd270c9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -222,6 +222,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..de5c64bbdb72 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,7 +175,7 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 45a9530d3839..522bbf937957 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -358,10 +358,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } diff --git a/include/net/mctp.h b/include/net/mctp.h index d37268fe6825..82800d521c3d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -36,8 +36,6 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) -#define MCTP_HEADER_MAXLEN 4 - #define MCTP_INITIAL_DEFAULT_NET 1 static inline bool mctp_address_unicast(mctp_eid_t eid) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0f34f13ebd55..5337acfe1e9c 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e57a224d6b79..93c3b86e781c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -392,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..23bb19716ad3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..51efaabac3e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..ecb0d7052877 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..8dccb34eb190 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7fa2ebc07f60..d8553f46caa2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, } static int -kprobe_multi_resolve_syms(const void *usyms, u32 cnt, +kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt, unsigned long *addrs) { unsigned long addr, size; - const char **syms; + const char __user **syms; int err = -ENOMEM; unsigned int i; char *func; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index ab463a4d2b23..b56833700d23 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head) */ void rethook_free(struct rethook *rh) { - rcu_assign_pointer(rh->handler, NULL); + WRITE_ONCE(rh->handler, NULL); call_rcu(&rh->rcu, rethook_free_rcu); } diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 926f4823d5ea..fd1728d94bab 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic( ip += length; op += length; - /* Necessarily EOF, due to parsing restrictions */ - if (!partialDecoding || (cpy == oend)) + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ diff --git a/mm/highmem.c b/mm/highmem.c index 0cc0c4da7ed9..1a692997fac4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -624,7 +624,7 @@ void __kmap_local_sched_out(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) @@ -661,7 +661,7 @@ void __kmap_local_sched_in(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fe38212e07c..c468fee595ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); - if (folio) { - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio != page_folio(pmd_page(*pmd))) - goto out; - } + VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) + is_pmd_migration_entry(*pmd)) { + if (folio && folio != page_folio(pmd_page(*pmd))) + goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); + } out: spin_unlock(ptl); diff --git a/mm/list_lru.c b/mm/list_lru.c index c669d87001a6..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, struct list_lru_one *src, *dst; /* - * If there is no lru entry in this nlru, we can skip it immediately. - */ - if (!READ_ONCE(nlru->nr_items)) - return; - - /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a2516d31db6c..8c74107a2b15 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, */ static struct page *new_page(struct page *page, unsigned long start) { + struct folio *dst, *src = page_folio(page); struct vm_area_struct *vma; unsigned long address; + gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; vma = find_vma(current->mm, start); while (vma) { @@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start) vma = vma->vm_next; } - if (PageHuge(page)) { - return alloc_huge_page_vma(page_hstate(compound_head(page)), + if (folio_test_hugetlb(src)) + return alloc_huge_page_vma(page_hstate(&src->page), vma, address); - } else if (PageTransHuge(page)) { - struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } + if (folio_test_large(src)) + gfp = GFP_TRANSHUGE; + /* - * if !vma, alloc_page_vma() will use task or system default policy + * if !vma, vma_alloc_folio() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, - vma, address); + dst = vma_alloc_folio(gfp, folio_order(src), vma, address, + folio_test_large(src)); + return &dst->page; } #else @@ -2227,6 +2224,19 @@ out: } EXPORT_SYMBOL(alloc_pages_vma); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage) +{ + struct folio *folio; + + folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, + hugepage); + if (folio && order > 1) + prep_transhuge_page(&folio->page); + + return folio; +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2733,6 +2743,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index de175e2fdba5..6c31ee1e1c9b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1520,10 +1520,11 @@ out: struct page *alloc_migration_target(struct page *page, unsigned long private) { + struct folio *folio = page_folio(page); struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; + struct folio *new_folio = NULL; int nid; int zidx; @@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(folio); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = page_hstate(&folio->page); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); } - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(folio); } - zidx = zone_idx(page_zone(page)); + zidx = zone_idx(folio_zone(folio)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); + new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask); - return new_page; + return &new_folio->page; } #ifdef CONFIG_NUMA @@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); + int order = compound_order(page); + gfp_t gfp = __GFP_THISNODE; + struct folio *new; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + new = __folio_alloc_node(gfp, order, nid); -out: - return newpage; + return &new->page; } static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) @@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - new_page_t *new; - bool compound; int nr_pages = thp_nr_pages(page); /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ @@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, - &nr_succeeded); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mremap.c b/mm/mremap.c index 9d76da79594d..303d3290b938 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, pmd_t *old_pmd, *new_pmd; pud_t *old_pud, *new_pud; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2db95780e003..6e5b4488a0c5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock); struct pagesets { local_lock_t lock; }; -static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = { +static DEFINE_PER_CPU(struct pagesets, pagesets) = { .lock = INIT_LOCAL_LOCK(lock), }; diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 1187f9c1ec5b..14a5cda73dee 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { - unsigned long size = pvmw->nr_pages * PAGE_SIZE; + struct hstate *hstate = hstate_vma(vma); + unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); @@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, - pvmw->pte); + pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); diff --git a/net/core/filter.c b/net/core/filter.c index a7044e98765e..64470a727ef7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 10bde7c6db44..30b523fa4ad2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5276,11 +5276,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* The page pool signature of struct page will eventually figure out - * which pages can be recycled or not but for now let's prohibit slab - * allocated and page_pool allocated SKBs from being coalesced. + /* In general, avoid mixing slab allocated and page_pool allocated + * pages within the same SKB. However when @to is not pp_recycle and + * @from is cloned, we can transition frag pages from page_pool to + * reference counted. + * + * On the other hand, don't allow coalescing two pp_recycle SKBs if + * @from is cloned, in case the SKB is using page_pool fragment + * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references for cloned SKBs at the moment that would result in + * inconsistent reference counts. */ - if (to->pp_recycle != from->pp_recycle) + if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/dsa/master.c b/net/dsa/master.c index 991c2930d631..2851e44c4cf0 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = { .attrs = dsa_slave_attrs, }; +static void dsa_master_reset_mtu(struct net_device *dev) +{ + int err; + + err = dev_set_mtu(dev, ETH_DATA_LEN); + if (err) + netdev_dbg(dev, + "Unable to reset MTU to exclude DSA overheads\n"); +} + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, @@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) "Failed to create a device link to DSA switch %s\n", dev_name(ds->dev)); + /* The switch driver may not implement ->port_change_mtu(), case in + * which dsa_slave_change_mtu() will not update the master MTU either, + * so we need to do that here. + */ + ret = dev_set_mtu(dev, mtu); + if (ret) + netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n", + ret, mtu); + /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev) sysfs_remove_group(&dev->dev.kobj, &dsa_group); dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); + dsa_master_reset_mtu(dev); dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index cc8e84ef2ae4..ccb62038f6a4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (cfg->fc_oif || cfg->fc_gw_family) { - struct fib_nh *nh = fib_info_nh(fi, 0); + struct fib_nh *nh; + + /* cannot match on nexthop object attributes */ + if (fi->nh) + return 1; + nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { if (fib_encap_match(net, cfg->fc_encap_type, cfg->fc_encap, nh, cfg, extack)) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a9775c830194..4e74bc61a3db 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; - bool do_wrmifwhole; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { + bool do_wrmifwhole; int v; if (optlen != sizeof(v)) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fa10e60cccd..169e9df6d172 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4484,7 +4484,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) struct inet6_dev *idev; int type; - if (netif_is_l3_master(skb->dev) && + if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index f0702d920d8d..e22b0cbb2f35 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -93,13 +93,13 @@ out_release: static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); - const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + int hlen; if (addr) { const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | @@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + struct net_device *dev; + + rc = -EINVAL; + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex); + /* check for correct halen */ + if (dev && extaddr->smctp_halen == dev->addr_len) { + hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr); + rc = 0; + } + rcu_read_unlock(); + if (rc) + goto err_free; + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr); + } + skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) cb = __mctp_cb(skb); cb->net = addr->smctp_network; - /* direct addressing */ - if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + if (!rt) { + /* fill extended address in cb */ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); @@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } cb->ifindex = extaddr->smctp_ifindex; + /* smctp_halen is checked above */ cb->halen = extaddr->smctp_halen; memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); - - rt = NULL; - } else { - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) { - rc = -EHOSTUNREACH; - goto err_free; - } } rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, diff --git a/net/mctp/route.c b/net/mctp/route.c index d5e7db83fe9d..3b24b8d18b5b 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) if (cb->ifindex) { /* direct route; use the hwaddr we stashed in sendmsg */ + if (cb->halen != skb->dev->addr_len) { + /* sanity check, sendmsg should have already caught this */ + kfree_skb(skb); + return -EMSGSIZE; + } daddr = cb->haddr; } else { /* If lookup fails let the device handle daddr==NULL */ @@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); - if (rc) { + if (rc < 0) { kfree_skb(skb); return -EHOSTUNREACH; } @@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, { const unsigned int hlen = sizeof(struct mctp_hdr); struct mctp_hdr *hdr, *hdr2; - unsigned int pos, size; + unsigned int pos, size, headroom; struct sk_buff *skb2; int rc; u8 seq; @@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, return -EMSGSIZE; } + /* keep same headroom as the original skb */ + headroom = skb_headroom(skb); + /* we've got the header */ skb_pull(skb, hlen); @@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* size of message payload */ size = min(mtu - hlen, skb->len - pos); - skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL); + skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL); if (!skb2) { rc = -ENOMEM; break; @@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, skb_set_owner_w(skb2, skb->sk); /* establish packet */ - skb_reserve(skb2, MCTP_HEADER_MAXLEN); + skb_reserve(skb2, headroom); skb_reset_network_header(skb2); skb_put(skb2, hlen + size); skb2->transport_header = skb2->network_header + hlen; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5ddfdb2adaf1..128ee3b300d6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, int err, i, k; for (i = 0; i < set->num_exprs; i++) { - expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL); + expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 38caa66632b4..f590ee1c8a1b 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->sreg].num_reg == 0 && track->regs[priv->dreg].bitwise && @@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->dreg].bitwise && track->regs[priv->dreg].bitwise->ops == expr->ops && diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 9de1462e4ac4..d657f999a11b 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, invert = true; } - priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL); + priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT); if (!priv->list) return -ENOMEM; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index da9083605a61..f4d3573e8782 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[], struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - cpu_stats = alloc_percpu(struct nft_counter); + cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT); if (cpu_stats == NULL) return -ENOMEM; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 43d0d4aadb1f..bb15a55dad5c 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, u64 last_jiffies; int err; - last = kzalloc(sizeof(*last), GFP_KERNEL); + last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT); if (!last) return -ENOMEM; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index d4a6cf3cd697..04ea8b9bf202 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } - priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL); + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index d7db57ed3bc1..e6b0df68feea 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return -EOPNOTSUPP; } - priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL); + priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT); if (!priv->consumed) return -ENOMEM; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7056cb1b8ba0..1b5d73079dc9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb, int rem = nla_len(attr); bool dont_clone_flow_key; - /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */ clone_arg = nla_data(attr); dont_clone_flow_key = nla_get_u32(clone_arg); actions = nla_next(clone_arg, &rem); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index cc282a58b75b..7176156d3844 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) return sfa; } +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); + +static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action) +{ + const struct nlattr *a; + int rem; + + nla_for_each_nested(a, action, rem) { + switch (nla_type(a)) { + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL: + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } + } +} + +static void ovs_nla_free_clone_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_CLONE_ATTR_EXEC: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + +static void ovs_nla_free_dec_ttl_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } +} + +static void ovs_nla_free_sample_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_SAMPLE_ATTR_ARG: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); @@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a) } } -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; - if (!sf_acts) + /* Whenever new actions are added, the need to update this + * function should be considered. + */ + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + + if (!actions) return; - nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { - case OVS_ACTION_ATTR_SET: - ovs_nla_free_set_action(a); + case OVS_ACTION_ATTR_CHECK_PKT_LEN: + ovs_nla_free_check_pkt_len_action(a); + break; + + case OVS_ACTION_ATTR_CLONE: + ovs_nla_free_clone_action(a); break; + case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; + + case OVS_ACTION_ATTR_DEC_TTL: + ovs_nla_free_dec_ttl_action(a); + break; + + case OVS_ACTION_ATTR_SAMPLE: + ovs_nla_free_sample_action(a); + break; + + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; } } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + if (!sf_acts) + return; + ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } @@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr, if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); + /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ + attr = nla_next(nla_data(attr), &rem); + err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 25bbc4cc8b13..f15d6942da45 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -113,8 +113,8 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net); rxnet->live = false; - del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); rxrpc_destroy_all_peers(rxnet); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a18609f608fb..e213aaf45d67 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) ctx->asoc->base.sk->sk_err = -error; return; } + ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: @@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { - sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + error = sctp_packet_singleton(ctx->transport, + chunk, ctx->gfp); + if (!error) + ctx->asoc->stats.octrlchunks++; break; } fallthrough; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8bf2af8546d2..af0174d7ce5a 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1127,6 +1127,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) struct rpc_task *task; task = rpc_new_task(task_setup_data); + if (IS_ERR(task)) + return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; @@ -1227,6 +1229,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); + if (IS_ERR(task)) { + xprt_free_bc_request(req); + return task; + } + xprt_init_bc_request(req, task); task->tk_action = call_bc_encode; @@ -1858,6 +1865,9 @@ call_encode(struct rpc_task *task) xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); + /* Add task to reply queue before transmission to avoid races */ + if (task->tk_status == 0 && rpc_reply_expected(task)) + task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ @@ -1881,9 +1891,6 @@ call_encode(struct rpc_task *task) return; } - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; @@ -2200,6 +2207,7 @@ call_transmit_status(struct rpc_task *task) * socket just returned a connection error, * then hold onto the transport lock. */ + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2283,6 +2291,7 @@ call_bc_transmit_status(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2365,6 +2374,11 @@ call_status(struct rpc_task *task) case -EPIPE: case -EAGAIN: break; + case -ENFILE: + case -ENOBUFS: + case -ENOMEM: + rpc_delay(task, HZ>>2); + break; case -EIO: /* shutdown or soft timeout */ goto out_exit; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b258b87a3ec2..7f70c1e608b7 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) if (task == NULL) { task = rpc_alloc_task(); + if (task == NULL) { + rpc_release_calldata(setup_data->callback_ops, + setup_data->callback_data); + return ERR_PTR(-ENOMEM); + } flags = RPC_TASK_DYNAMIC; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 05b38bf68316..71ba4cf513bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg, static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) { - int err; - - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); - if (err < 0) - return err; - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr), xdr->page_len + xdr->page_base); return xprt_sendmsg(sock, msg, base + xdr->page_base); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 478f857cdaed..cc35ec433400 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + goto out_unlock; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); } + xdr_free_bvec(xdr); trace_svcsock_udp_send(xprt, err); - +out_unlock: mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; @@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, int ret; *sentp = 0; - xdr_alloc_bvec(xdr, GFP_KERNEL); + ret = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (ret < 0) + return ret; ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 515501f79290..86d62cffba0d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -69,10 +69,11 @@ /* * Local functions */ -static void xprt_init(struct rpc_xprt *xprt, struct net *net); +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_destroy(struct rpc_xprt *xprt); -static void xprt_request_init(struct rpc_task *task); +static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); +static int xprt_request_prepare(struct rpc_rqst *req); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return; - if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - trace_xprt_disconnect_cleanup(xprt); - xprt->ops->close(xprt); - } - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); @@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) * @task: RPC task * */ -void +int xprt_request_enqueue_receive(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + int ret; if (!xprt_request_need_enqueue_receive(task, req)) - return; + return 0; - xprt_request_prepare(task->tk_rqstp); + ret = xprt_request_prepare(task->tk_rqstp); + if (ret) + return ret; spin_lock(&xprt->queue_lock); /* Update the softirq receive buffer */ @@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); + return 0; } /** @@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task) * * Calls into the transport layer to do whatever is needed to prepare * the request for transmission or receive. + * Returns error, or zero. */ -void +static int xprt_request_prepare(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; if (xprt->ops->prepare_request) - xprt->ops->prepare_request(req); + return xprt->ops->prepare_request(req); + return 0; } /** diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 78af7518f263..8ab64ea46870 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) return ret; } -static void +static int xs_stream_prepare_request(struct rpc_rqst *req) { + gfp_t gfp = rpc_task_gfp_mask(); + int ret; + + ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp); + if (ret < 0) + return ret; xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec( - &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + return xdr_alloc_bvec(&req->rq_rcv_buf, gfp); } /* @@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req) /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } @@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); @@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -2544,6 +2562,9 @@ static int bc_sendto(struct rpc_rqst *req) int err; req->rq_xtime = ktime_get(); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0024a692f0f8..a8976ef95528 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (prot->version == TLS_1_3_VERSION || prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) memcpy(iv + iv_offset, tls_ctx->rx.iv, - crypto_aead_ivsize(ctx->aead_recv)); + prot->iv_size + prot->salt_size); else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 9afcc6467a09..e09d6908a21d 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 91af2850b505..7678af364793 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", map_cnt ); @@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", prog_cnt ); @@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv) %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ - if (!s) \n\ + if (!s) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv) return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ + return err; \n\ } \n\ \n\ static inline const void *%2$s__elf_bytes(size_t *sz) \n\ @@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv) \n\ obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ if (!s) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s->sz = sizeof(*s); \n\ @@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv) s->var_cnt = %2$d; \n\ s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ if (!s->vars) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ ", @@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv) return obj; \n\ err: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 1480910c792e..de66e1cc0734 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1)) PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) +ifeq ($(CC_NO_CLANG), 0) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro +endif + $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 86e2e926aa0e..af4d63af8072 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..cc6df49a65a1 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +198,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +207,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..45a30040ec8d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 65dbdda3a054..1da76ccde448 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t) return 0; } -static void security_init(struct nfit_test *t) +static void nfit_security_init(struct nfit_test *t) { int i; @@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t) if (nfit_test_dimm_init(t)) return -ENOMEM; smart_init(t); - security_init(t); + nfit_security_init(t); return ars_state_init(&t->pdev.dev, &t->ars_state); } diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index 5aa52cc31dc2..c11832657d2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ #include <test_progs.h> #include "dummy_st_ops.skel.h" +#include "trace_dummy_st_ops.skel.h" /* Need to keep consistent with definition in include/linux/bpf.h */ struct bpf_dummy_ops_state { @@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); + struct trace_dummy_st_ops *trace_skel; struct dummy_st_ops *skel; int fd, err; @@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); + + trace_skel = trace_dummy_st_ops__open(); + if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open")) + goto done; + + err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1, + fd, "test_1"); + if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)")) + goto done; + + err = trace_dummy_st_ops__load(trace_skel); + if (!ASSERT_OK(err, "load(trace_skel)")) + goto done; + + err = trace_dummy_st_ops__attach(trace_skel); + if (!ASSERT_OK(err, "attach(trace_skel)")) + goto done; + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); + ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val"); +done: dummy_st_ops__destroy(skel); + trace_dummy_st_ops__destroy(trace_skel); } static void test_dummy_multiple_args(void) diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index b64df94ec476..db388f593d0a 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -367,7 +367,7 @@ static inline int check_array_of_maps(void) VERIFY(check_default(&array_of_maps->map, map)); inner_map = bpf_map_lookup_elem(array_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; @@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void) VERIFY(check_default(&hash_of_maps->map, map)); inner_map = bpf_map_lookup_elem(hash_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c new file mode 100644 index 000000000000..00a4be9d3074 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int val = 0; + +SEC("fentry/test_1") +int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx) +{ + __u64 state; + + /* Read the traced st_ops arg1 which is a pointer */ + bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx); + /* Read state->val */ + bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index b9e991d43155..e7775d3bbe08 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -18,8 +18,9 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" -static int start_server(const struct sockaddr *addr, socklen_t len) +static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) { + int mode = !dual; int fd; fd = socket(addr->sa_family, SOCK_STREAM, 0); @@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len) goto out; } + if (addr->sa_family == AF_INET6) { + if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, + sizeof(mode)) == -1) { + log_err("Failed to set the dual-stack mode"); + goto close_out; + } + } + if (bind(fd, addr, len) == -1) { log_err("Failed to bind server socket"); goto close_out; @@ -47,24 +56,17 @@ out: return fd; } -static int connect_to_server(int server_fd) +static int connect_to_server(const struct sockaddr *addr, socklen_t len) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); int fd = -1; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - fd = socket(addr.ss_family, SOCK_STREAM, 0); + fd = socket(addr->sa_family, SOCK_STREAM, 0); if (fd == -1) { log_err("Failed to create client socket"); goto out; } - if (connect(fd, (const struct sockaddr *)&addr, len) == -1) { + if (connect(fd, (const struct sockaddr *)addr, len) == -1) { log_err("Fail to connect to server"); goto close_out; } @@ -116,7 +118,8 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp) +static int run_test(int server_fd, int results_fd, bool xdp, + const struct sockaddr *addr, socklen_t len) { int client = -1, srv_client = -1; int ret = 0; @@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp) goto err; } - client = connect_to_server(server_fd); + client = connect_to_server(addr, len); if (client == -1) goto err; @@ -199,12 +202,30 @@ out: return ret; } +static bool get_port(int server_fd, in_port_t *port) +{ + struct sockaddr_in addr; + socklen_t len = sizeof(addr); + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return false; + } + + /* sin_port and sin6_port are located at the same offset. */ + *port = addr.sin_port; + return true; +} + int main(int argc, char **argv) { struct sockaddr_in addr4; struct sockaddr_in6 addr6; + struct sockaddr_in addr4dual; + struct sockaddr_in6 addr6dual; int server = -1; int server_v6 = -1; + int server_dual = -1; int results = -1; int err = 0; bool xdp; @@ -224,25 +245,43 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); addr4.sin_port = 0; + memcpy(&addr4dual, &addr4, sizeof(addr4dual)); memset(&addr6, 0, sizeof(addr6)); addr6.sin6_family = AF_INET6; addr6.sin6_addr = in6addr_loopback; addr6.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4)); - if (server == -1) + memset(&addr6dual, 0, sizeof(addr6dual)); + addr6dual.sin6_family = AF_INET6; + addr6dual.sin6_addr = in6addr_any; + addr6dual.sin6_port = 0; + + server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), + false); + if (server == -1 || !get_port(server, &addr4.sin_port)) goto err; server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6)); - if (server_v6 == -1) + sizeof(addr6), false); + if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + goto err; + + server_dual = start_server((const struct sockaddr *)&addr6dual, + sizeof(addr6dual), true); + if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + goto err; + + if (run_test(server, results, xdp, + (const struct sockaddr *)&addr4, sizeof(addr4))) goto err; - if (run_test(server, results, xdp)) + if (run_test(server_v6, results, xdp, + (const struct sockaddr *)&addr6, sizeof(addr6))) goto err; - if (run_test(server_v6, results, xdp)) + if (run_test(server_dual, results, xdp, + (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) goto err; printf("ok\n"); @@ -252,6 +291,7 @@ err: out: close(server); close(server_v6); + close(server_dual); close(results); return err; } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 11779405dc80..25f4d54067c0 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -64,6 +64,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <setjmp.h> #include "kselftest.h" @@ -183,7 +184,10 @@ struct __test_metadata *_metadata, \ struct __fixture_variant_metadata *variant) \ { \ - test_name(_metadata); \ + _metadata->setup_completed = true; \ + if (setjmp(_metadata->env) == 0) \ + test_name(_metadata); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata _##test_name##_object = \ { .name = #test_name, \ @@ -287,7 +291,9 @@ #define FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * FIXTURE_VARIANT() - Optionally called once per fixture @@ -302,9 +308,9 @@ * ... * }; * - * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() - * as *variant*. Variants allow the same tests to be run with different - * arguments. + * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and + * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with + * different arguments. */ #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name @@ -356,10 +362,7 @@ * Defines a test that depends on a fixture (e.g., is part of a test case). * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. - * - * Warning: use of ASSERT_* here will skip TEARDOWN. */ -/* TODO(wad) register fixtures on dedicated test lists. */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -381,12 +384,17 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ - fixture_name##_teardown(_metadata, &self); \ + if (setjmp(_metadata->env) == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + _metadata->setup_completed = true; \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ + } \ + if (_metadata->setup_completed) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ @@ -683,7 +691,7 @@ */ #define OPTIONAL_HANDLER(_assert) \ for (; _metadata->trigger; _metadata->trigger = \ - __bail(_assert, _metadata->no_print, _metadata->step)) + __bail(_assert, _metadata)) #define __INC_STEP(_metadata) \ /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ @@ -830,6 +838,9 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + bool aborted; /* stopped test due to failed ASSERT */ + bool setup_completed; /* did setup finish? */ + jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t) __LIST_APPEND(t->fixture->tests, t); } -static inline int __bail(int for_realz, bool no_print, __u8 step) +static inline int __bail(int for_realz, struct __test_metadata *t) { + /* if this is ASSERT, return immediately. */ if (for_realz) { - if (no_print) - _exit(step); - abort(); + t->aborted = true; + longjmp(t->env, 1); } + /* otherwise, end the for loop and continue. */ return 0; } +static inline void __test_check_assert(struct __test_metadata *t) +{ + if (t->aborted) { + if (t->no_print) + _exit(t->step); + abort(); + } +} + struct __test_metadata *__active_test; static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) { diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index d444ee6aa3cb..b3bf5319bb0e 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1208,6 +1208,20 @@ ipv4_fcnal() set +e check_nexthop "dev veth1" "" log_test $? 0 "Nexthops removed on admin down" + + # nexthop route delete warning: route add with nhid and delete + # using device + run_cmd "$IP li set dev veth1 up" + run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1" + out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + run_cmd "$IP route add 172.16.101.1/32 nhid 12" + run_cmd "$IP route delete 172.16.101.1/32 dev veth1" + out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + [ $out1 -eq $out2 ] + rc=$? + log_test $rc 0 "Delete nexthop route warning" + run_cmd "$IP route delete 172.16.101.1/32 nhid 12" + run_cmd "$IP nexthop del id 12" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index dcaefa224ca0..edafaca1aeb3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ -TEST_GEN_PROGS := regression_enomem +TEST_GEN_PROGS = regression_enomem -include ../lib.mk +LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h -$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h +include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 17999e082aa7..070c1c876df1 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,7 +95,6 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 18a3bde8bc96..28604c9f805c 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -46,6 +46,8 @@ #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" + static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags); @@ -368,7 +370,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } @@ -417,7 +419,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index c4aea794725a..e691a3cf1491 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "../kselftest.h" static const char **name; @@ -306,10 +307,8 @@ static void test_clock_gettime(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime(-1, "invalid"); @@ -370,10 +369,8 @@ static void test_clock_gettime64(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime64(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime64(-1, "invalid"); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 53df7d3893d3..0388c4d60af0 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -92,6 +92,10 @@ warn_32bit_failure: echo "If you are using a Fedora-like distribution, try:"; \ echo ""; \ echo " yum install glibc-devel.*i686"; \ + echo ""; \ + echo "If you are using a SUSE-like distribution, try:"; \ + echo ""; \ + echo " zypper install gcc-32bit glibc-devel-static-32bit"; \ exit 0; endif |