diff options
222 files changed, 1885 insertions, 1053 deletions
diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst index f1fc8ae3846a..cc860a0c296b 100644 --- a/Documentation/RCU/lockdep.rst +++ b/Documentation/RCU/lockdep.rst @@ -49,7 +49,7 @@ checking of rcu_dereference() primitives: is invoked by both RCU-sched readers and updaters. srcu_dereference_check(p, c): Use explicit check expression "c" along with - srcu_read_lock_held()(). This is useful in code that + srcu_read_lock_held(). This is useful in code that is invoked by both SRCU readers and updaters. rcu_dereference_raw(p): Don't check. (Use sparingly, if at all.) diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt index d336f3f73a4c..63fd4e6a014b 100644 --- a/Documentation/admin-guide/devices.txt +++ b/Documentation/admin-guide/devices.txt @@ -1662,7 +1662,7 @@ 98 block User-mode virtual block device 0 = /dev/ubda First user-mode block device - 16 = /dev/udbb Second user-mode block device + 16 = /dev/ubdb Second user-mode block device ... Partitions are handled in the same way as for IDE diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 5e477869df18..5fe1ade88c17 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -1434,7 +1434,7 @@ on the feature, restricting the viewing angles. DYTC Lapmode sensor ------------------- +------------------- sysfs: dytc_lapmode diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml index 5887c917d480..58fe9d02a781 100644 --- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml @@ -30,9 +30,13 @@ allOf: then: properties: clock-output-names: - items: - - const: clk_out_sd0 - - const: clk_in_sd0 + oneOf: + - items: + - const: clk_out_sd0 + - const: clk_in_sd0 + - items: + - const: clk_out_sd1 + - const: clk_in_sd1 properties: compatible: diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt index 0c9cf6a8808c..26a8f320a156 100644 --- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt +++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt @@ -50,6 +50,8 @@ Optional properties: error caused by stop clock(fifo full) Valid range = [0:0x7]. if not present, default value is 0. applied to compatible "mediatek,mt2701-mmc". +- resets: Phandle and reset specifier pair to softreset line of MSDC IP. +- reset-names: Should be "hrst". Examples: mmc0: mmc@11230000 { diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt index 2cf3affa1be7..96c0b1440c9c 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt @@ -15,8 +15,15 @@ Required properties: - "nvidia,tegra210-sdhci": for Tegra210 - "nvidia,tegra186-sdhci": for Tegra186 - "nvidia,tegra194-sdhci": for Tegra194 -- clocks : Must contain one entry, for the module clock. - See ../clocks/clock-bindings.txt for details. +- clocks: For Tegra210, Tegra186 and Tegra194 must contain two entries. + One for the module clock and one for the timeout clock. + For all other Tegra devices, must contain a single entry for + the module clock. See ../clocks/clock-bindings.txt for details. +- clock-names: For Tegra210, Tegra186 and Tegra194 must contain the + strings 'sdhci' and 'tmclk' to represent the module and + the timeout clocks, respectively. + For all other Tegra devices must contain the string 'sdhci' + to represent the module clock. - resets : Must contain an entry for each entry in reset-names. See ../reset/reset.txt for details. - reset-names : Must include the following entries: @@ -99,7 +106,7 @@ Optional properties for Tegra210, Tegra186 and Tegra194: Example: sdhci@700b0000 { - compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci"; + compatible = "nvidia,tegra124-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; @@ -115,3 +122,22 @@ sdhci@700b0000 { nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>; status = "disabled"; }; + +sdhci@700b0000 { + compatible = "nvidia,tegra210-sdhci"; + reg = <0x0 0x700b0000 0x0 0x200>; + interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; + resets = <&tegra_car 14>; + reset-names = "sdhci"; + pinctrl-names = "sdmmc-3v3", "sdmmc-1v8"; + pinctrl-0 = <&sdmmc1_3v3>; + pinctrl-1 = <&sdmmc1_1v8>; + nvidia,pad-autocal-pull-up-offset-3v3 = <0x00>; + nvidia,pad-autocal-pull-down-offset-3v3 = <0x7d>; + nvidia,pad-autocal-pull-up-offset-1v8 = <0x7b>; + nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>; + status = "disabled"; +}; diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt index bf7328aba330..dab208b5c7c7 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.txt +++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt @@ -1,4 +1,4 @@ Distributed Switch Architecture Device Tree Bindings ---------------------------------------------------- -See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documenation. +See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documentation. diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 71c5a40da320..ccd677ba7d76 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -6,9 +6,9 @@ API to implement a new FPGA bridge * struct :c:type:`fpga_bridge` — The FPGA Bridge structure * struct :c:type:`fpga_bridge_ops` — Low level Bridge driver ops -* :c:func:`devm_fpga_bridge_create()` — Allocate and init a bridge struct -* :c:func:`fpga_bridge_register()` — Register a bridge -* :c:func:`fpga_bridge_unregister()` — Unregister a bridge +* devm_fpga_bridge_create() — Allocate and init a bridge struct +* fpga_bridge_register() — Register a bridge +* fpga_bridge_unregister() — Unregister a bridge .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 576f1945eacd..af5382af1379 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -104,9 +104,9 @@ API for implementing a new FPGA Manager driver * ``fpga_mgr_states`` — Values for :c:member:`fpga_manager->state`. * struct :c:type:`fpga_manager` — the FPGA manager struct * struct :c:type:`fpga_manager_ops` — Low level FPGA manager driver ops -* :c:func:`devm_fpga_mgr_create` — Allocate and init a manager struct -* :c:func:`fpga_mgr_register` — Register an FPGA manager -* :c:func:`fpga_mgr_unregister` — Unregister an FPGA manager +* devm_fpga_mgr_create() — Allocate and init a manager struct +* fpga_mgr_register() — Register an FPGA manager +* fpga_mgr_unregister() — Unregister an FPGA manager .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_mgr_states diff --git a/Documentation/driver-api/fpga/fpga-programming.rst b/Documentation/driver-api/fpga/fpga-programming.rst index b5484df6ff0f..f487ad64dfb9 100644 --- a/Documentation/driver-api/fpga/fpga-programming.rst +++ b/Documentation/driver-api/fpga/fpga-programming.rst @@ -6,9 +6,9 @@ Overview The in-kernel API for FPGA programming is a combination of APIs from FPGA manager, bridge, and regions. The actual function used to -trigger FPGA programming is :c:func:`fpga_region_program_fpga()`. +trigger FPGA programming is fpga_region_program_fpga(). -:c:func:`fpga_region_program_fpga()` uses functionality supplied by +fpga_region_program_fpga() uses functionality supplied by the FPGA manager and bridges. It will: * lock the region's mutex @@ -20,8 +20,8 @@ the FPGA manager and bridges. It will: * release the locks The struct fpga_image_info specifies what FPGA image to program. It is -allocated/freed by :c:func:`fpga_image_info_alloc()` and freed with -:c:func:`fpga_image_info_free()` +allocated/freed by fpga_image_info_alloc() and freed with +fpga_image_info_free() How to program an FPGA using a region ------------------------------------- @@ -84,10 +84,10 @@ will generate that list. Here's some sample code of what to do next:: API for programming an FPGA --------------------------- -* :c:func:`fpga_region_program_fpga` — Program an FPGA -* :c:type:`fpga_image_info` — Specifies what FPGA image to program -* :c:func:`fpga_image_info_alloc()` — Allocate an FPGA image info struct -* :c:func:`fpga_image_info_free()` — Free an FPGA image info struct +* fpga_region_program_fpga() — Program an FPGA +* fpga_image_info() — Specifies what FPGA image to program +* fpga_image_info_alloc() — Allocate an FPGA image info struct +* fpga_image_info_free() — Free an FPGA image info struct .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_program_fpga diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index 0529b2d2231a..31118a8ba218 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -46,18 +46,18 @@ API to add a new FPGA region ---------------------------- * struct :c:type:`fpga_region` — The FPGA region struct -* :c:func:`devm_fpga_region_create` — Allocate and init a region struct -* :c:func:`fpga_region_register` — Register an FPGA region -* :c:func:`fpga_region_unregister` — Unregister an FPGA region +* devm_fpga_region_create() — Allocate and init a region struct +* fpga_region_register() — Register an FPGA region +* fpga_region_unregister() — Unregister an FPGA region The FPGA region's probe function will need to get a reference to the FPGA Manager it will be using to do the programming. This usually would happen during the region's probe function. -* :c:func:`fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count -* :c:func:`of_fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count, +* fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count +* of_fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count, given a device node. -* :c:func:`fpga_mgr_put` — Put an FPGA manager +* fpga_mgr_put() — Put an FPGA manager The FPGA region will need to specify which bridges to control while programming the FPGA. The region driver can build a list of bridges during probe time @@ -66,11 +66,11 @@ the list of bridges to program just before programming (:c:member:`fpga_region->get_bridges`). The FPGA bridge framework supplies the following APIs to handle building or tearing down that list. -* :c:func:`fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a +* fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a list -* :c:func:`of_fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a +* of_fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a list, given a device node -* :c:func:`fpga_bridges_put` — Given a list of bridges, put them +* fpga_bridges_put() — Given a list of bridges, put them .. kernel-doc:: include/linux/fpga/fpga-region.h :functions: fpga_region diff --git a/Documentation/driver-api/iio/core.rst b/Documentation/driver-api/iio/core.rst index b0bc0c028cc5..51b21e002396 100644 --- a/Documentation/driver-api/iio/core.rst +++ b/Documentation/driver-api/iio/core.rst @@ -11,10 +11,10 @@ Industrial I/O Devices ---------------------- * struct :c:type:`iio_dev` - industrial I/O device -* :c:func:`iio_device_alloc()` - allocate an :c:type:`iio_dev` from a driver -* :c:func:`iio_device_free()` - free an :c:type:`iio_dev` from a driver -* :c:func:`iio_device_register()` - register a device with the IIO subsystem -* :c:func:`iio_device_unregister()` - unregister a device from the IIO +* iio_device_alloc() - allocate an :c:type:`iio_dev` from a driver +* iio_device_free() - free an :c:type:`iio_dev` from a driver +* iio_device_register() - register a device with the IIO subsystem +* iio_device_unregister() - unregister a device from the IIO subsystem An IIO device usually corresponds to a single hardware sensor and it @@ -34,17 +34,17 @@ A typical IIO driver will register itself as an :doc:`I2C <../i2c>` or At probe: -1. Call :c:func:`iio_device_alloc()`, which allocates memory for an IIO device. +1. Call iio_device_alloc(), which allocates memory for an IIO device. 2. Initialize IIO device fields with driver specific information (e.g. device name, device channels). -3. Call :c:func:`iio_device_register()`, this registers the device with the +3. Call iio_device_register(), this registers the device with the IIO core. After this call the device is ready to accept requests from user space applications. At remove, we free the resources allocated in probe in reverse order: -1. :c:func:`iio_device_unregister()`, unregister the device from the IIO core. -2. :c:func:`iio_device_free()`, free the memory allocated for the IIO device. +1. iio_device_unregister(), unregister the device from the IIO core. +2. iio_device_free(), free the memory allocated for the IIO device. IIO device sysfs interface ========================== diff --git a/Documentation/filesystems/affs.rst b/Documentation/filesystems/affs.rst index 7f1a40dce6d3..5776cbd5fa53 100644 --- a/Documentation/filesystems/affs.rst +++ b/Documentation/filesystems/affs.rst @@ -110,13 +110,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows: - R maps to r for user, group and others. On directories, R implies x. - - If both W and D are allowed, w will be set. + - W maps to w. - E maps to x. - - H and P are always retained and ignored under Linux. + - D is ignored. - - A is always reset when a file is written to. + - H, S and P are always retained and ignored under Linux. + + - A is cleared when a file is written to. User id and group id will be used unless set[gu]id are given as mount options. Since most of the Amiga file systems are single user systems @@ -128,11 +130,13 @@ Linux -> Amiga: The Linux rwxrwxrwx file mode is handled as follows: - - r permission will set R for user, group and others. + - r permission will allow R for user, group and others. + + - w permission will allow W for user, group and others. - - w permission will set W and D for user, group and others. + - x permission of the user will allow E for plain files. - - x permission of the user will set E for plain files. + - D will be allowed for user, group and others. - All other flags (suid, sgid, ...) are ignored and will not be retained. diff --git a/Documentation/hwmon/abituguru-datasheet.rst b/Documentation/hwmon/abituguru-datasheet.rst index 6d5253e2223b..0cd61471d2a2 100644 --- a/Documentation/hwmon/abituguru-datasheet.rst +++ b/Documentation/hwmon/abituguru-datasheet.rst @@ -68,7 +68,7 @@ See below for all known bank addresses, numbers of sensors in that bank, number of bytes data per sensor and contents/meaning of those bytes. Although both this document and the kernel driver have kept the sensor -terminoligy for the addressing within a bank this is not 100% correct, in +terminology for the addressing within a bank this is not 100% correct, in bank 0x24 for example the addressing within the bank selects a PWM output not a sensor. @@ -155,7 +155,7 @@ After wider testing of the Linux kernel driver some variants of the uGuru have turned up which do not hold 0x08 at DATA within 250 reads after writing the bank address. With these versions this happens quite frequent, using larger timeouts doesn't help, they just go offline for a second or 2, doing some -internal callibration or whatever. Your code should be prepared to handle +internal calibration or whatever. Your code should be prepared to handle this and in case of no response in this specific case just goto sleep for a while and then retry. @@ -331,6 +331,6 @@ the voltage / clock programming out, I tried reading and only reading banks 0-0x30 with the reading code used for the sensor banks (0x20-0x28) and this resulted in a _permanent_ reprogramming of the voltages, luckily I had the sensors part configured so that it would shutdown my system on any out of spec -voltages which proprably safed my computer (after a reboot I managed to +voltages which probably safed my computer (after a reboot I managed to immediately enter the bios and reload the defaults). This probably means that the read/write cycle for the non sensor part is different from the sensor part. diff --git a/Documentation/hwmon/abituguru.rst b/Documentation/hwmon/abituguru.rst index d8243c827de9..cfda60b757ce 100644 --- a/Documentation/hwmon/abituguru.rst +++ b/Documentation/hwmon/abituguru.rst @@ -17,7 +17,7 @@ Supported chips: Note: The uGuru is a microcontroller with onboard firmware which programs it to behave as a hwmon IC. There are many different revisions of the - firmware and thus effectivly many different revisions of the uGuru. + firmware and thus effectively many different revisions of the uGuru. Below is an incomplete list with which revisions are used for which Motherboards: @@ -33,7 +33,7 @@ Supported chips: sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's this does not always work. For these uGuru's the autodetection can be overridden with the bank1_types module param. For all 3 known - revison 1 motherboards the correct use of this param is: + revision 1 motherboards the correct use of this param is: bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1 You may also need to specify the fan_sensors option for these boards fan_sensors=5 diff --git a/Documentation/hwmon/abituguru3.rst b/Documentation/hwmon/abituguru3.rst index 514f11f41e8b..88046d866385 100644 --- a/Documentation/hwmon/abituguru3.rst +++ b/Documentation/hwmon/abituguru3.rst @@ -13,7 +13,7 @@ Supported chips: Note: The uGuru is a microcontroller with onboard firmware which programs it to behave as a hwmon IC. There are many different revisions of the - firmware and thus effectivly many different revisions of the uGuru. + firmware and thus effectively many different revisions of the uGuru. Below is an incomplete list with which revisions are used for which Motherboards: @@ -24,7 +24,7 @@ Supported chips: - uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X, AW9D-MAX) - The abituguru3 driver is only for revison 3.0.x.x motherboards, + The abituguru3 driver is only for revision 3.0.x.x motherboards, this driver will not work on older motherboards. For older motherboards use the abituguru (without the 3 !) driver. diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst index 4cefed8048ca..ddada4a53749 100644 --- a/Documentation/locking/locktypes.rst +++ b/Documentation/locking/locktypes.rst @@ -164,14 +164,14 @@ by disabling preemption or interrupts. On non-PREEMPT_RT kernels local_lock operations map to the preemption and interrupt disabling and enabling primitives: - =========================== ====================== - local_lock(&llock) preempt_disable() - local_unlock(&llock) preempt_enable() - local_lock_irq(&llock) local_irq_disable() - local_unlock_irq(&llock) local_irq_enable() - local_lock_save(&llock) local_irq_save() - local_lock_restore(&llock) local_irq_save() - =========================== ====================== + =============================== ====================== + local_lock(&llock) preempt_disable() + local_unlock(&llock) preempt_enable() + local_lock_irq(&llock) local_irq_disable() + local_unlock_irq(&llock) local_irq_enable() + local_lock_irqsave(&llock) local_irq_save() + local_unlock_irqrestore(&llock) local_irq_restore() + =============================== ====================== The named scope of local_lock has two advantages over the regular primitives: @@ -353,14 +353,14 @@ protection scope. So the following substitution is wrong:: { local_irq_save(flags); -> local_lock_irqsave(&local_lock_1, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_1, flags); } func2() { local_irq_save(flags); -> local_lock_irqsave(&local_lock_2, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_2, flags); } func3() @@ -379,14 +379,14 @@ PREEMPT_RT-specific semantics of spinlock_t. The correct substitution is:: { local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags); } func2() { local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags); func3(); - local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags); + local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags); } func3() diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst index 227f427118e8..b7a627d6c97d 100644 --- a/Documentation/maintainer/maintainer-entry-profile.rst +++ b/Documentation/maintainer/maintainer-entry-profile.rst @@ -101,3 +101,4 @@ to do something different in the near future. ../doc-guide/maintainer-profile ../nvdimm/maintainer-entry-profile + ../riscv/patch-acceptance diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index af029b3ca2ab..11bd5e6108c0 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -180,7 +180,7 @@ The configuration can only be set up via VLAN tagging and bridge setup. # bring up the slave interfaces ip link set lan1 up - ip link set lan1 up + ip link set lan2 up ip link set lan3 up # create bridge diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 4a9aa4f0681e..918e32d76fc4 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -142,7 +142,7 @@ only NUL-terminated strings. The safe replacement is strscpy(). (Users of strscpy() still needing NUL-padding should instead use strscpy_pad().) -If a caller is using non-NUL-terminated strings, strncpy()() can +If a caller is using non-NUL-terminated strings, strncpy() can still be used, but destinations should be marked with the `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_ attribute to avoid future compiler warnings. diff --git a/Documentation/translations/it_IT/process/deprecated.rst b/Documentation/translations/it_IT/process/deprecated.rst index e108eaf82cf6..a642ff3fdc8b 100644 --- a/Documentation/translations/it_IT/process/deprecated.rst +++ b/Documentation/translations/it_IT/process/deprecated.rst @@ -130,7 +130,7 @@ chi usa solo stringe terminate. La versione sicura da usare è strscpy(). (chi usa strscpy() e necessita di estendere la terminazione con NUL deve aggiungere una chiamata a memset()) -Se il chiamate no usa stringhe terminate con NUL, allore strncpy()() +Se il chiamate no usa stringhe terminate con NUL, allore strncpy() può continuare ad essere usata, ma i buffer di destinazione devono essere marchiati con l'attributo `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_ per evitare avvisi durante la compilazione. diff --git a/MAINTAINERS b/MAINTAINERS index e4647c84c987..dca9bfd8c888 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3389,6 +3389,7 @@ M: Florian Fainelli <[email protected]> L: [email protected] (subscribers-only) S: Supported +F: Documentation/devicetree/bindings/net/dsa/b53.txt F: drivers/net/dsa/b53/* F: include/linux/platform_data/b53.h @@ -3574,13 +3575,28 @@ L: [email protected] S: Maintained F: drivers/phy/broadcom/phy-brcm-usb* +BROADCOM ETHERNET PHY DRIVERS +M: Florian Fainelli <[email protected]> +S: Supported +F: Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt +F: drivers/net/phy/bcm*.[ch] +F: drivers/net/phy/broadcom.c +F: include/linux/brcmphy.h + BROADCOM GENET ETHERNET DRIVER M: Doug Berger <[email protected]> M: Florian Fainelli <[email protected]> S: Supported +F: Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +F: Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt F: drivers/net/ethernet/broadcom/genet/ +F: drivers/net/mdio/mdio-bcm-unimac.c +F: include/linux/platform_data/bcmgenet.h +F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <[email protected]> @@ -5240,6 +5256,7 @@ DOCUMENTATION M: Jonathan Corbet <[email protected]> S: Maintained +P: Documentation/doc-guide/maintainer-profile.rst T: git git://git.lwn.net/linux.git docs-next F: Documentation/ F: scripts/documentation-file-ref-check @@ -6495,7 +6512,6 @@ F: net/bridge/ ETHERNET PHY LIBRARY M: Andrew Lunn <[email protected]> -M: Florian Fainelli <[email protected]> M: Heiner Kallweit <[email protected]> R: Russell King <[email protected]> @@ -13570,12 +13586,18 @@ F: kernel/events/* F: tools/lib/perf/ F: tools/perf/ -PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS +PERFORMANCE EVENTS TOOLING ARM64 R: John Garry <[email protected]> R: Will Deacon <[email protected]> +R: Mathieu Poirier <[email protected]> +R: Leo Yan <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported +F: tools/build/feature/test-libopencsd.c +F: tools/perf/arch/arm*/ F: tools/perf/pmu-events/arch/arm64/ +F: tools/perf/util/arm-spe* +F: tools/perf/util/cs-etm* PERSONALITY HANDLING M: Christoph Hellwig <[email protected]> diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 1a39e0ef776b..5b9ec032ce8d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -686,6 +686,8 @@ clocks = <&pericfg CLK_PERI_MSDC30_0_PD>, <&topckgen CLK_TOP_MSDC50_0_SEL>; clock-names = "source", "hclk"; + resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>; + reset-names = "hrst"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 34d249d85da7..8eb61dd9921e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -337,8 +337,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03400000 0x0 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC1>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>, @@ -366,8 +367,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03420000 0x0 0x10000>; interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC2>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC2>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>, @@ -390,8 +392,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03440000 0x0 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC3>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>, @@ -416,8 +419,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03460000 0x0 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC4>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>, <&bpmp TEGRA186_CLK_PLLC4_VCO>; assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 48160f48003a..ca5cb6aef5ee 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -460,8 +460,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03400000 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC1>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>, @@ -485,8 +486,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03440000 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC3>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>, @@ -511,8 +513,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03460000 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC4>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>, <&bpmp TEGRA194_CLK_PLLC4>; assigned-clock-parents = diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 829f786af133..8cca2166a446 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -1194,8 +1194,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 14>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1222,8 +1223,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0200 0x0 0x200>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC2>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 9>; reset-names = "sdhci"; pinctrl-names = "sdmmc-1v8-drv"; @@ -1239,8 +1241,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0400 0x0 0x200>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC3>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 69>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1262,8 +1265,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0600 0x0 0x200>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC4>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 15>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv"; diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index b49fe6f618ed..f8150ee74f29 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -3,7 +3,7 @@ * Architecture-specific kernel symbols */ -#ifdef CONFIG_VIRTUAL_MEM_MAP +#if defined(CONFIG_VIRTUAL_MEM_MAP) || defined(CONFIG_DISCONTIGMEM) #include <linux/compiler.h> #include <linux/export.h> #include <linux/memblock.h> diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 0880a003573d..3344d4a1fe89 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -46,6 +46,9 @@ unsigned long memory_size; EXPORT_SYMBOL(memory_size); unsigned long lowmem_size; +EXPORT_SYMBOL(min_low_pfn); +EXPORT_SYMBOL(max_low_pfn); + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; EXPORT_SYMBOL(kmap_pte); diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index c798856e74a4..0ddd611b4277 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -998,6 +998,7 @@ static int fs_open(struct atm_vcc *atm_vcc) error = make_rate (pcr, r, &tmc0, NULL); if (error) { kfree(tc); + kfree(vcc); return error; } } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 2c2bf24140c9..12b30075134a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -596,14 +596,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - /* - * Using __get_user_pages_fast() with a read-only - * access is questionable. A read-only page may be - * COW-broken, and then this might end up giving - * the wrong side of the COW.. - * - * We may or may not care. - */ if (pvec) { /* defer to worker if malloc fails */ if (!i915_gem_object_is_readonly(obj)) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 359616e3efbb..d2ecc9c45255 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1598,6 +1598,17 @@ static void hid_output_field(const struct hid_device *hid, } /* + * Compute the size of a report. + */ +static size_t hid_compute_report_size(struct hid_report *report) +{ + if (report->size) + return ((report->size - 1) >> 3) + 1; + + return 0; +} + +/* * Create a report. 'data' has to be allocated using * hid_alloc_report_buf() so that it has proper size. */ @@ -1609,7 +1620,7 @@ void hid_output_report(struct hid_report *report, __u8 *data) if (report->id > 0) *data++ = report->id; - memset(data, 0, ((report->size - 1) >> 3) + 1); + memset(data, 0, hid_compute_report_size(report)); for (n = 0; n < report->maxfield; n++) hid_output_field(report->device, report->field[n], data); } @@ -1739,7 +1750,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, csize--; } - rsize = ((report->size - 1) >> 3) + 1; + rsize = hid_compute_report_size(report); if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE - 1; diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c index 45c4f888b7c4..dae193749d44 100644 --- a/drivers/hid/hid-elan.c +++ b/drivers/hid/hid-elan.c @@ -188,6 +188,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) ret = input_mt_init_slots(input, ELAN_MAX_FINGERS, INPUT_MT_POINTER); if (ret) { hid_err(hdev, "Failed to init elan MT slots: %d\n", ret); + input_free_device(input); return ret; } @@ -198,6 +199,7 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) if (ret) { hid_err(hdev, "Failed to register elan input device: %d\n", ret); + input_mt_destroy_slots(input); input_free_device(input); return ret; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index a8e3b2796be8..74fc1df6e3c2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -850,6 +850,7 @@ #define USB_DEVICE_ID_MS_POWER_COVER 0x07da #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd #define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb +#define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -1015,6 +1016,8 @@ #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 #define USB_DEVICE_ID_SAITEK_X52 0x075c +#define USB_DEVICE_ID_SAITEK_X52_2 0x0255 +#define USB_DEVICE_ID_SAITEK_X52_PRO 0x0762 #define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index b8eabf206e74..88e19996427e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1132,6 +1132,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel } mapped: + /* Mapping failed, bail out */ + if (!bit) + return; + if (device->driver->input_mapped && device->driver->input_mapped(device, hidinput, field, usage, &bit, &max) < 0) { diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 5576fed7bc15..071fd093a5f4 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -448,6 +448,8 @@ static const struct hid_device_id ms_devices[] = { .driver_data = MS_SURFACE_DIAL }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER), .driver_data = MS_QUIRK_FF }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS), + .driver_data = MS_QUIRK_FF }, { } }; MODULE_DEVICE_TABLE(hid, ms_devices); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 3f94b4954225..e3152155c4b8 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -856,6 +856,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, code = BTN_0 + ((usage->hid - 1) & HID_USAGE); hid_map_usage(hi, usage, bit, max, EV_KEY, code); + if (!*bit) + return -1; input_set_capability(hi->input, EV_KEY, code); return 1; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index a65aef6a322f..7a2be0205dfd 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -150,6 +150,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_2), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52_PRO), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 151aa95775be..af6d4f898e4c 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -537,12 +537,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, CACHE_MAX_CONCURRENT_LOCKS); if (IS_ERR(cmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(cmd->bm); + r = PTR_ERR(cmd->bm); + cmd->bm = NULL; + return r; } r = __open_or_format_metadata(cmd, may_format_device); - if (r) + if (r) { dm_block_manager_destroy(cmd->bm); + cmd->bm = NULL; + } return r; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 238cd80826a6..380386c36921 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -739,7 +739,7 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv, u8 buf[MAX_CIPHER_BLOCKSIZE] __aligned(__alignof__(__le64)); struct skcipher_request *req; struct scatterlist src, dst; - struct crypto_wait wait; + DECLARE_CRYPTO_WAIT(wait); int err; req = skcipher_request_alloc(any_tfm(cc), GFP_NOIO); @@ -936,7 +936,7 @@ static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *d u8 *es, *ks, *data, *data2, *data_offset; struct skcipher_request *req; struct scatterlist *sg, *sg2, src, dst; - struct crypto_wait wait; + DECLARE_CRYPTO_WAIT(wait); int i, r; req = skcipher_request_alloc(elephant->tfm, GFP_NOIO); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 8c8d940e532e..3fc3757def55 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2487,6 +2487,7 @@ next_chunk: range.logical_sector = le64_to_cpu(ic->sb->recalc_sector); if (unlikely(range.logical_sector >= ic->provided_data_sectors)) { if (ic->mode == 'B') { + block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR); DEBUG_print("queue_delayed_work: bitmap_flush_work\n"); queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, 0); } @@ -2564,6 +2565,17 @@ next_chunk: goto err; } + if (ic->mode == 'B') { + sector_t start, end; + start = (range.logical_sector >> + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) << + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); + end = ((range.logical_sector + range.n_sectors) >> + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) << + (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); + block_bitmap_op(ic, ic->recalc_bitmap, start, end - start, BITMAP_OP_CLEAR); + } + advance_and_next: cond_resched(); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index e3283d35c7fd..de4da825ade6 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1287,17 +1287,25 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m) static void flush_multipath_work(struct multipath *m) { if (m->hw_handler_name) { - set_bit(MPATHF_PG_INIT_DISABLED, &m->flags); - smp_mb__after_atomic(); + unsigned long flags; + + if (!atomic_read(&m->pg_init_in_progress)) + goto skip; + + spin_lock_irqsave(&m->lock, flags); + if (atomic_read(&m->pg_init_in_progress) && + !test_and_set_bit(MPATHF_PG_INIT_DISABLED, &m->flags)) { + spin_unlock_irqrestore(&m->lock, flags); - if (atomic_read(&m->pg_init_in_progress)) flush_workqueue(kmpath_handlerd); - multipath_wait_for_pg_init_completion(m); + multipath_wait_for_pg_init_completion(m); - clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags); - smp_mb__after_atomic(); + spin_lock_irqsave(&m->lock, flags); + clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags); + } + spin_unlock_irqrestore(&m->lock, flags); } - +skip: if (m->queue_mode == DM_TYPE_BIO_BASED) flush_work(&m->process_queued_bios); flush_work(&m->trigger_event); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 76b6b323bf4b..b461836b6d26 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -739,12 +739,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f THIN_MAX_CONCURRENT_LOCKS); if (IS_ERR(pmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(pmd->bm); + r = PTR_ERR(pmd->bm); + pmd->bm = NULL; + return r; } r = __open_or_format_metadata(pmd, format_device); - if (r) + if (r) { dm_block_manager_destroy(pmd->bm); + pmd->bm = NULL; + } return r; } @@ -954,7 +958,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd) } pmd_write_lock_in_core(pmd); - if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) { + if (!pmd->fail_io && !dm_bm_is_read_only(pmd->bm)) { r = __commit_transaction(pmd); if (r < 0) DMWARN("%s: __commit_transaction() failed, error = %d", diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 86dbe0c8b45c..6271d1e741cf 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -231,6 +231,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) pfn_t pfn; int id; struct page **pages; + sector_t offset; wc->memory_vmapped = false; @@ -245,9 +246,16 @@ static int persistent_memory_claim(struct dm_writecache *wc) goto err1; } + offset = get_start_sect(wc->ssd_dev->bdev); + if (offset & (PAGE_SIZE / 512 - 1)) { + r = -EINVAL; + goto err1; + } + offset >>= PAGE_SHIFT - 9; + id = dax_read_lock(); - da = dax_direct_access(wc->ssd_dev->dax_dev, 0, p, &wc->memory_map, &pfn); + da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn); if (da < 0) { wc->memory_map = NULL; r = da; @@ -269,7 +277,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) i = 0; do { long daa; - daa = dax_direct_access(wc->ssd_dev->dax_dev, i, p - i, + daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i, NULL, &pfn); if (daa <= 0) { r = daa ? daa : -EINVAL; diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 749ec268d957..54c089a50b15 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -493,7 +493,7 @@ int dm_bm_write_lock(struct dm_block_manager *bm, void *p; int r; - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result); @@ -562,7 +562,7 @@ int dm_bm_write_lock_zero(struct dm_block_manager *bm, struct buffer_aux *aux; void *p; - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; p = dm_bufio_new(bm->bufio, b, (struct dm_buffer **) result); @@ -602,7 +602,7 @@ EXPORT_SYMBOL_GPL(dm_bm_unlock); int dm_bm_flush(struct dm_block_manager *bm) { - if (bm->read_only) + if (dm_bm_is_read_only(bm)) return -EPERM; return dm_bufio_write_dirty_buffers(bm->bufio); @@ -616,19 +616,21 @@ void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b) bool dm_bm_is_read_only(struct dm_block_manager *bm) { - return bm->read_only; + return (bm ? bm->read_only : true); } EXPORT_SYMBOL_GPL(dm_bm_is_read_only); void dm_bm_set_read_only(struct dm_block_manager *bm) { - bm->read_only = true; + if (bm) + bm->read_only = true; } EXPORT_SYMBOL_GPL(dm_bm_set_read_only); void dm_bm_set_read_write(struct dm_block_manager *bm) { - bm->read_only = false; + if (bm) + bm->read_only = false; } EXPORT_SYMBOL_GPL(dm_bm_set_read_write); diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index 48ae60a2c603..c7ba76fee599 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -467,7 +467,7 @@ config VIDEO_VPX3220 config VIDEO_MAX9286 tristate "Maxim MAX9286 GMSL deserializer support" depends on I2C && I2C_MUX - depends on OF + depends on OF_GPIO select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API select MEDIA_CONTROLLER @@ -741,7 +741,7 @@ config VIDEO_HI556 config VIDEO_IMX214 tristate "Sony IMX214 sensor support" depends on GPIOLIB && I2C && VIDEO_V4L2 - depends on V4L2_FWNODE + select V4L2_FWNODE select MEDIA_CONTROLLER select VIDEO_V4L2_SUBDEV_API select REGMAP_I2C diff --git a/drivers/media/platform/ti-vpe/cal.h b/drivers/media/platform/ti-vpe/cal.h index e496083715d2..4123405ee0cf 100644 --- a/drivers/media/platform/ti-vpe/cal.h +++ b/drivers/media/platform/ti-vpe/cal.h @@ -226,7 +226,7 @@ static inline void cal_write_field(struct cal_dev *cal, u32 offset, u32 value, u32 val = cal_read(cal, offset); val &= ~mask; - val |= FIELD_PREP(mask, value); + val |= (value << __ffs(mask)) & mask; cal_write(cal, offset, val); } diff --git a/drivers/media/rc/gpio-ir-tx.c b/drivers/media/rc/gpio-ir-tx.c index f33b443bfa47..c6cd2e6d8e65 100644 --- a/drivers/media/rc/gpio-ir-tx.c +++ b/drivers/media/rc/gpio-ir-tx.c @@ -19,8 +19,6 @@ struct gpio_ir { struct gpio_desc *gpio; unsigned int carrier; unsigned int duty_cycle; - /* we need a spinlock to hold the cpu while transmitting */ - spinlock_t lock; }; static const struct of_device_id gpio_ir_tx_of_match[] = { @@ -53,12 +51,11 @@ static int gpio_ir_tx_set_carrier(struct rc_dev *dev, u32 carrier) static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf, uint count) { - unsigned long flags; ktime_t edge; s32 delta; int i; - spin_lock_irqsave(&gpio_ir->lock, flags); + local_irq_disable(); edge = ktime_get(); @@ -72,14 +69,11 @@ static void gpio_ir_tx_unmodulated(struct gpio_ir *gpio_ir, uint *txbuf, } gpiod_set_value(gpio_ir->gpio, 0); - - spin_unlock_irqrestore(&gpio_ir->lock, flags); } static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, uint count) { - unsigned long flags; ktime_t edge; /* * delta should never exceed 0.5 seconds (IR_MAX_DURATION) and on @@ -95,7 +89,7 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, space = DIV_ROUND_CLOSEST((100 - gpio_ir->duty_cycle) * (NSEC_PER_SEC / 100), gpio_ir->carrier); - spin_lock_irqsave(&gpio_ir->lock, flags); + local_irq_disable(); edge = ktime_get(); @@ -128,19 +122,20 @@ static void gpio_ir_tx_modulated(struct gpio_ir *gpio_ir, uint *txbuf, edge = last; } } - - spin_unlock_irqrestore(&gpio_ir->lock, flags); } static int gpio_ir_tx(struct rc_dev *dev, unsigned int *txbuf, unsigned int count) { struct gpio_ir *gpio_ir = dev->priv; + unsigned long flags; + local_irq_save(flags); if (gpio_ir->carrier) gpio_ir_tx_modulated(gpio_ir, txbuf, count); else gpio_ir_tx_unmodulated(gpio_ir, txbuf, count); + local_irq_restore(flags); return count; } @@ -176,7 +171,6 @@ static int gpio_ir_tx_probe(struct platform_device *pdev) gpio_ir->carrier = 38000; gpio_ir->duty_cycle = 50; - spin_lock_init(&gpio_ir->lock); rc = devm_rc_register_device(&pdev->dev, rcdev); if (rc < 0) diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index f9616158bcf4..98681ba10428 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -1726,7 +1726,7 @@ static int mceusb_dev_probe(struct usb_interface *intf, goto mem_alloc_fail; ir->pipe_in = pipe; - ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_ATOMIC, &ir->dma_in); + ir->buf_in = usb_alloc_coherent(dev, maxp, GFP_KERNEL, &ir->dma_in); if (!ir->buf_in) goto buf_in_alloc_fail; diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 7b53066d9d07..dee8a9f3d80a 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1292,6 +1292,10 @@ static ssize_t store_protocols(struct device *device, } mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } old_protocols = *current_protocols; new_protocols = old_protocols; @@ -1430,6 +1434,10 @@ static ssize_t store_filter(struct device *device, return -EINVAL; mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } new_filter = *filter; if (fattr->mask) @@ -1544,6 +1552,10 @@ static ssize_t store_wakeup_protocols(struct device *device, int i; mutex_lock(&dev->lock); + if (!dev->registered) { + mutex_unlock(&dev->lock); + return -ENODEV; + } allowed = dev->allowed_wakeup_protocols; @@ -1601,25 +1613,25 @@ static void rc_dev_release(struct device *device) kfree(dev); } -#define ADD_HOTPLUG_VAR(fmt, val...) \ - do { \ - int err = add_uevent_var(env, fmt, val); \ - if (err) \ - return err; \ - } while (0) - static int rc_dev_uevent(struct device *device, struct kobj_uevent_env *env) { struct rc_dev *dev = to_rc_dev(device); + int ret = 0; - if (dev->rc_map.name) - ADD_HOTPLUG_VAR("NAME=%s", dev->rc_map.name); - if (dev->driver_name) - ADD_HOTPLUG_VAR("DRV_NAME=%s", dev->driver_name); - if (dev->device_name) - ADD_HOTPLUG_VAR("DEV_NAME=%s", dev->device_name); + mutex_lock(&dev->lock); - return 0; + if (!dev->registered) + ret = -ENODEV; + if (ret == 0 && dev->rc_map.name) + ret = add_uevent_var(env, "NAME=%s", dev->rc_map.name); + if (ret == 0 && dev->driver_name) + ret = add_uevent_var(env, "DRV_NAME=%s", dev->driver_name); + if (ret == 0 && dev->device_name) + ret = add_uevent_var(env, "DEV_NAME=%s", dev->device_name); + + mutex_unlock(&dev->lock); + + return ret; } /* @@ -2011,14 +2023,14 @@ void rc_unregister_device(struct rc_dev *dev) del_timer_sync(&dev->timer_keyup); del_timer_sync(&dev->timer_repeat); - rc_free_rx_device(dev); - mutex_lock(&dev->lock); if (dev->users && dev->close) dev->close(dev); dev->registered = false; mutex_unlock(&dev->lock); + rc_free_rx_device(dev); + /* * lirc device should be freed with dev->registered = false, so * that userspace polling will get notified. diff --git a/drivers/media/test-drivers/vicodec/vicodec-core.c b/drivers/media/test-drivers/vicodec/vicodec-core.c index 8941d73f6611..71928e30dae8 100644 --- a/drivers/media/test-drivers/vicodec/vicodec-core.c +++ b/drivers/media/test-drivers/vicodec/vicodec-core.c @@ -1994,6 +1994,7 @@ static int vicodec_request_validate(struct media_request *req) } ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl, vicodec_ctrl_stateless_state.id); + v4l2_ctrl_request_hdl_put(hdl); if (!ctrl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 2a22e13a6303..f74b42280892 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -3187,14 +3187,16 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd) #ifdef CONFIG_COMPAT_32BIT_TIME case VIDIOC_DQEVENT_TIME32: { struct v4l2_event *ev = parg; - struct v4l2_event_time32 ev32 = { - .type = ev->type, - .pending = ev->pending, - .sequence = ev->sequence, - .timestamp.tv_sec = ev->timestamp.tv_sec, - .timestamp.tv_nsec = ev->timestamp.tv_nsec, - .id = ev->id, - }; + struct v4l2_event_time32 ev32; + + memset(&ev32, 0, sizeof(ev32)); + + ev32.type = ev->type; + ev32.pending = ev->pending; + ev32.sequence = ev->sequence; + ev32.timestamp.tv_sec = ev->timestamp.tv_sec; + ev32.timestamp.tv_nsec = ev->timestamp.tv_nsec; + ev32.id = ev->id; memcpy(&ev32.u, &ev->u, sizeof(ev->u)); memcpy(&ev32.reserved, &ev->reserved, sizeof(ev->reserved)); @@ -3208,21 +3210,23 @@ static int video_put_user(void __user *arg, void *parg, unsigned int cmd) case VIDIOC_DQBUF_TIME32: case VIDIOC_PREPARE_BUF_TIME32: { struct v4l2_buffer *vb = parg; - struct v4l2_buffer_time32 vb32 = { - .index = vb->index, - .type = vb->type, - .bytesused = vb->bytesused, - .flags = vb->flags, - .field = vb->field, - .timestamp.tv_sec = vb->timestamp.tv_sec, - .timestamp.tv_usec = vb->timestamp.tv_usec, - .timecode = vb->timecode, - .sequence = vb->sequence, - .memory = vb->memory, - .m.userptr = vb->m.userptr, - .length = vb->length, - .request_fd = vb->request_fd, - }; + struct v4l2_buffer_time32 vb32; + + memset(&vb32, 0, sizeof(vb32)); + + vb32.index = vb->index; + vb32.type = vb->type; + vb32.bytesused = vb->bytesused; + vb32.flags = vb->flags; + vb32.field = vb->field; + vb32.timestamp.tv_sec = vb->timestamp.tv_sec; + vb32.timestamp.tv_usec = vb->timestamp.tv_usec; + vb32.timecode = vb->timecode; + vb32.sequence = vb->sequence; + vb32.memory = vb->memory; + vb32.m.userptr = vb->m.userptr; + vb32.length = vb->length; + vb32.request_fd = vb->request_fd; if (copy_to_user(arg, &vb32, sizeof(vb32))) return -EFAULT; diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 4e2583f69a63..b0c27944db7f 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> +#include <linux/reset.h> #include <linux/mmc/card.h> #include <linux/mmc/core.h> @@ -419,6 +420,7 @@ struct msdc_host { struct pinctrl_state *pins_uhs; struct delayed_work req_timeout; int irq; /* host interrupt */ + struct reset_control *reset; struct clk *src_clk; /* msdc source clock */ struct clk *h_clk; /* msdc h_clk */ @@ -1592,6 +1594,12 @@ static void msdc_init_hw(struct msdc_host *host) u32 val; u32 tune_reg = host->dev_comp->pad_tune_reg; + if (host->reset) { + reset_control_assert(host->reset); + usleep_range(10, 50); + reset_control_deassert(host->reset); + } + /* Configure to MMC/SD mode, clock free running */ sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_MODE | MSDC_CFG_CKPDN); @@ -2390,6 +2398,11 @@ static int msdc_drv_probe(struct platform_device *pdev) if (IS_ERR(host->src_clk_cg)) host->src_clk_cg = NULL; + host->reset = devm_reset_control_get_optional_exclusive(&pdev->dev, + "hrst"); + if (IS_ERR(host->reset)) + return PTR_ERR(host->reset); + host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { ret = -EINVAL; diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 48ecbd0b180d..962f074ca174 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -535,6 +535,11 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_qcom_sd = { .caps = MMC_CAP_NONREMOVABLE, }; +struct amd_sdhci_host { + bool tuned_clock; + bool dll_enabled; +}; + /* AMD sdhci reset dll register. */ #define SDHCI_AMD_RESET_DLL_REGISTER 0x908 @@ -555,26 +560,66 @@ static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host) } /* - * For AMD Platform it is required to disable the tuning - * bit first controller to bring to HS Mode from HS200 - * mode, later enable to tune to HS400 mode. + * The initialization sequence for HS400 is: + * HS->HS200->Perform Tuning->HS->HS400 + * + * The re-tuning sequence is: + * HS400->DDR52->HS->HS200->Perform Tuning->HS->HS400 + * + * The AMD eMMC Controller can only use the tuned clock while in HS200 and HS400 + * mode. If we switch to a different mode, we need to disable the tuned clock. + * If we have previously performed tuning and switch back to HS200 or + * HS400, we can re-enable the tuned clock. + * */ static void amd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_acpi_host *acpi_host = sdhci_priv(host); + struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host); unsigned int old_timing = host->timing; + u16 val; sdhci_set_ios(mmc, ios); - if (old_timing == MMC_TIMING_MMC_HS200 && - ios->timing == MMC_TIMING_MMC_HS) - sdhci_writew(host, 0x9, SDHCI_HOST_CONTROL2); - if (old_timing != MMC_TIMING_MMC_HS400 && - ios->timing == MMC_TIMING_MMC_HS400) { - sdhci_writew(host, 0x80, SDHCI_HOST_CONTROL2); - sdhci_acpi_amd_hs400_dll(host); + + if (old_timing != host->timing && amd_host->tuned_clock) { + if (host->timing == MMC_TIMING_MMC_HS400 || + host->timing == MMC_TIMING_MMC_HS200) { + val = sdhci_readw(host, SDHCI_HOST_CONTROL2); + val |= SDHCI_CTRL_TUNED_CLK; + sdhci_writew(host, val, SDHCI_HOST_CONTROL2); + } else { + val = sdhci_readw(host, SDHCI_HOST_CONTROL2); + val &= ~SDHCI_CTRL_TUNED_CLK; + sdhci_writew(host, val, SDHCI_HOST_CONTROL2); + } + + /* DLL is only required for HS400 */ + if (host->timing == MMC_TIMING_MMC_HS400 && + !amd_host->dll_enabled) { + sdhci_acpi_amd_hs400_dll(host); + amd_host->dll_enabled = true; + } } } +static int amd_sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + int err; + struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_acpi_host *acpi_host = sdhci_priv(host); + struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host); + + amd_host->tuned_clock = false; + + err = sdhci_execute_tuning(mmc, opcode); + + if (!err && !host->tuning_err) + amd_host->tuned_clock = true; + + return err; +} + static const struct sdhci_ops sdhci_acpi_ops_amd = { .set_clock = sdhci_set_clock, .set_bus_width = sdhci_set_bus_width, @@ -602,6 +647,7 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, host->mmc_host_ops.select_drive_strength = amd_select_drive_strength; host->mmc_host_ops.set_ios = amd_set_ios; + host->mmc_host_ops.execute_tuning = amd_sdhci_execute_tuning; return 0; } @@ -613,6 +659,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = { SDHCI_QUIRK_32BIT_ADMA_SIZE, .quirks2 = SDHCI_QUIRK2_BROKEN_64_BIT_DMA, .probe_slot = sdhci_acpi_emmc_amd_probe_slot, + .priv_size = sizeof(struct amd_sdhci_host), }; struct sdhci_acpi_uid_slot { diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bb6802448b2f..af413805bbf1 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -232,6 +232,14 @@ static void sdhci_pci_dumpregs(struct mmc_host *mmc) sdhci_dumpregs(mmc_priv(mmc)); } +static void sdhci_cqhci_reset(struct sdhci_host *host, u8 mask) +{ + if ((host->mmc->caps2 & MMC_CAP2_CQE) && (mask & SDHCI_RESET_ALL) && + host->mmc->cqe_private) + cqhci_deactivate(host->mmc); + sdhci_reset(host, mask); +} + /*****************************************************************************\ * * * Hardware specific quirk handling * @@ -718,7 +726,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = { .set_power = sdhci_intel_set_power, .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, - .reset = sdhci_reset, + .reset = sdhci_cqhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, .irq = sdhci_cqhci_irq, diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 0a3f9d024f2a..13fbf70b5fde 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -110,6 +110,12 @@ #define NVQUIRK_DIS_CARD_CLK_CONFIG_TAP BIT(8) #define NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING BIT(9) +/* + * NVQUIRK_HAS_TMCLK is for SoC's having separate timeout clock for Tegra + * SDMMC hardware data timeout. + */ +#define NVQUIRK_HAS_TMCLK BIT(10) + /* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */ #define SDHCI_TEGRA_CQE_BASE_ADDR 0xF000 @@ -140,6 +146,7 @@ struct sdhci_tegra_autocal_offsets { struct sdhci_tegra { const struct sdhci_tegra_soc_data *soc_data; struct gpio_desc *power_gpio; + struct clk *tmclk; bool ddr_signaling; bool pad_calib_required; bool pad_control_available; @@ -1418,7 +1425,6 @@ static const struct sdhci_ops tegra210_sdhci_ops = { static const struct sdhci_pltfm_data sdhci_tegra210_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | @@ -1434,7 +1440,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra210 = { NVQUIRK_HAS_PADCALIB | NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | - NVQUIRK_ENABLE_SDR104, + NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK, .min_tap_delay = 106, .max_tap_delay = 185, }; @@ -1456,7 +1463,6 @@ static const struct sdhci_ops tegra186_sdhci_ops = { static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | @@ -1473,6 +1479,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra186 = { NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK | NVQUIRK_CQHCI_DCMD_R1B_CMD_TIMING, .min_tap_delay = 84, .max_tap_delay = 136, @@ -1485,7 +1492,8 @@ static const struct sdhci_tegra_soc_data soc_data_tegra194 = { NVQUIRK_HAS_PADCALIB | NVQUIRK_DIS_CARD_CLK_CONFIG_TAP | NVQUIRK_ENABLE_SDR50 | - NVQUIRK_ENABLE_SDR104, + NVQUIRK_ENABLE_SDR104 | + NVQUIRK_HAS_TMCLK, .min_tap_delay = 96, .max_tap_delay = 139, }; @@ -1613,6 +1621,43 @@ static int sdhci_tegra_probe(struct platform_device *pdev) goto err_power_req; } + /* + * Tegra210 has a separate SDMMC_LEGACY_TM clock used for host + * timeout clock and SW can choose TMCLK or SDCLK for hardware + * data timeout through the bit USE_TMCLK_FOR_DATA_TIMEOUT of + * the register SDHCI_TEGRA_VENDOR_SYS_SW_CTRL. + * + * USE_TMCLK_FOR_DATA_TIMEOUT bit default is set to 1 and SDMMC uses + * 12Mhz TMCLK which is advertised in host capability register. + * With TMCLK of 12Mhz provides maximum data timeout period that can + * be achieved is 11s better than using SDCLK for data timeout. + * + * So, TMCLK is set to 12Mhz and kept enabled all the time on SoC's + * supporting separate TMCLK. + */ + + if (soc_data->nvquirks & NVQUIRK_HAS_TMCLK) { + clk = devm_clk_get(&pdev->dev, "tmclk"); + if (IS_ERR(clk)) { + rc = PTR_ERR(clk); + if (rc == -EPROBE_DEFER) + goto err_power_req; + + dev_warn(&pdev->dev, "failed to get tmclk: %d\n", rc); + clk = NULL; + } + + clk_set_rate(clk, 12000000); + rc = clk_prepare_enable(clk); + if (rc) { + dev_err(&pdev->dev, + "failed to enable tmclk: %d\n", rc); + goto err_power_req; + } + + tegra_host->tmclk = clk; + } + clk = devm_clk_get(mmc_dev(host->mmc), NULL); if (IS_ERR(clk)) { rc = PTR_ERR(clk); @@ -1656,6 +1701,7 @@ err_add_host: err_rst_get: clk_disable_unprepare(pltfm_host->clk); err_clk_get: + clk_disable_unprepare(tegra_host->tmclk); err_power_req: err_parse_dt: sdhci_pltfm_free(pdev); @@ -1673,6 +1719,7 @@ static int sdhci_tegra_remove(struct platform_device *pdev) reset_control_assert(tegra_host->rst); usleep_range(2000, 4000); clk_disable_unprepare(pltfm_host->clk); + clk_disable_unprepare(tegra_host->tmclk); sdhci_pltfm_free(pdev); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 0c37ddb58c1e..1aaf47a0da2b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1326,14 +1326,17 @@ mt7530_setup(struct dsa_switch *ds) if (phy_node->parent == priv->dev->of_node->parent) { ret = of_get_phy_mode(mac_np, &interface); - if (ret && ret != -ENODEV) + if (ret && ret != -ENODEV) { + of_node_put(mac_np); return ret; + } id = of_mdio_parse_addr(ds->dev, phy_node); if (id == 0) priv->p5_intf_sel = P5_INTF_SEL_PHY_P0; if (id == 4) priv->p5_intf_sel = P5_INTF_SEL_PHY_P4; } + of_node_put(mac_np); of_node_put(phy_node); break; } @@ -1501,7 +1504,7 @@ unsupported: phylink_set(mask, 100baseT_Full); if (state->interface != PHY_INTERFACE_MODE_MII) { - phylink_set(mask, 1000baseT_Half); + /* This switch only supports 1G full-duplex. */ phylink_set(mask, 1000baseT_Full); if (port == 5) phylink_set(mask, 1000baseX_Full); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index c69d9592a2b7..04bfa6e465ff 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -400,6 +400,7 @@ static int felix_parse_ports_node(struct felix *felix, if (err < 0) { dev_err(dev, "Unsupported PHY mode %s on port %d\n", phy_modes(phy_mode), port); + of_node_put(child); return err; } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c3f6f124e5f0..5a28dfb36ec3 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3415,7 +3415,7 @@ static int sja1105_check_device_id(struct sja1105_private *priv) sja1105_unpack(prod_id, &part_no, 19, 4, SJA1105_SIZE_DEVICE_ID); - for (match = sja1105_dt_ids; match->compatible; match++) { + for (match = sja1105_dt_ids; match->compatible[0]; match++) { const struct sja1105_info *info = match->data; /* Is what's been probed in our match table at all? */ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 46c3c1ca38d6..859ded0c06b0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -166,6 +166,7 @@ enum xgbe_port_mode { XGBE_PORT_MODE_10GBASE_T, XGBE_PORT_MODE_10GBASE_R, XGBE_PORT_MODE_SFP, + XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG, XGBE_PORT_MODE_MAX, }; @@ -1634,6 +1635,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) if (ad_reg & 0x80) { switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: mode = XGBE_MODE_KR; break; default: @@ -1643,6 +1645,7 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) } else if (ad_reg & 0x20) { switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: mode = XGBE_MODE_KX_1000; break; case XGBE_PORT_MODE_1000BASE_X: @@ -1782,6 +1785,7 @@ static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata, switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: XGBE_SET_ADV(dlks, 10000baseKR_Full); break; case XGBE_PORT_MODE_BACKPLANE_2500: @@ -1874,6 +1878,7 @@ static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: return XGBE_AN_MODE_CL73; + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: case XGBE_PORT_MODE_BACKPLANE_2500: return XGBE_AN_MODE_NONE; case XGBE_PORT_MODE_1000BASE_T: @@ -2156,6 +2161,7 @@ static enum xgbe_mode xgbe_phy_switch_mode(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_switch_bp_mode(pdata); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_switch_bp_2500_mode(pdata); @@ -2251,6 +2257,7 @@ static enum xgbe_mode xgbe_phy_get_mode(struct xgbe_prv_data *pdata, switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_get_bp_mode(speed); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_get_bp_2500_mode(speed); @@ -2426,6 +2433,7 @@ static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_use_bp_mode(pdata, mode); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_use_bp_2500_mode(pdata, mode); @@ -2515,6 +2523,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: return xgbe_phy_valid_speed_bp_mode(speed); case XGBE_PORT_MODE_BACKPLANE_2500: return xgbe_phy_valid_speed_bp_2500_mode(speed); @@ -2792,6 +2801,7 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)) return false; @@ -2844,6 +2854,7 @@ static bool xgbe_phy_conn_type_mismatch(struct xgbe_prv_data *pdata) switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: case XGBE_PORT_MODE_BACKPLANE_2500: if (phy_data->conn_type == XGBE_CONN_TYPE_BACKPLANE) return false; @@ -3160,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* Backplane support */ case XGBE_PORT_MODE_BACKPLANE: XGBE_SET_SUP(lks, Autoneg); + fallthrough; + case XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG: XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, Backplane); diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 0187dbf3b87d..54cdafdd067d 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -153,6 +153,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) if (IS_ERR(data->reset_gpio)) { error = PTR_ERR(data->reset_gpio); dev_err(priv->dev, "Failed to request gpio: %d\n", error); + mdiobus_free(bus); return error; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index dfed9ade6950..0762d5d1a810 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2491,8 +2491,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->tx_rings = devm_kcalloc(&pdev->dev, txq, sizeof(struct bcm_sysport_tx_ring), GFP_KERNEL); - if (!priv->tx_rings) - return -ENOMEM; + if (!priv->tx_rings) { + ret = -ENOMEM; + goto err_free_netdev; + } priv->is_lite = params->is_lite; priv->num_rx_desc_words = params->num_rx_desc_words; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f92fd8863f48..b167066af450 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1141,6 +1141,9 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay) { + if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))) + return; + if (BNXT_PF(bp)) queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay); else @@ -1157,10 +1160,12 @@ static void bnxt_queue_sp_work(struct bnxt *bp) static void bnxt_cancel_sp_work(struct bnxt *bp) { - if (BNXT_PF(bp)) + if (BNXT_PF(bp)) { flush_workqueue(bnxt_pf_wq); - else + } else { cancel_work_sync(&bp->sp_task); + cancel_delayed_work_sync(&bp->fw_reset_task); + } } static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) @@ -6102,6 +6107,21 @@ static int bnxt_get_func_stat_ctxs(struct bnxt *bp) return cp + ulp_stat; } +/* Check if a default RSS map needs to be setup. This function is only + * used on older firmware that does not require reserving RX rings. + */ +static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp) +{ + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + /* The RSS map is valid for RX rings set to resv_rx_rings */ + if (hw_resc->resv_rx_rings != bp->rx_nr_rings) { + hw_resc->resv_rx_rings = bp->rx_nr_rings; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + } +} + static bool bnxt_need_reserve_rings(struct bnxt *bp) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -6110,22 +6130,28 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) int rx = bp->rx_nr_rings, stat; int vnic = 1, grp = rx; - if (bp->hwrm_spec_code < 0x10601) - return false; - - if (hw_resc->resv_tx_rings != bp->tx_nr_rings) + if (hw_resc->resv_tx_rings != bp->tx_nr_rings && + bp->hwrm_spec_code >= 0x10601) return true; + /* Old firmware does not need RX ring reservations but we still + * need to setup a default RSS map when needed. With new firmware + * we go through RX ring reservations first and then set up the + * RSS map for the successfully reserved RX rings when needed. + */ + if (!BNXT_NEW_RM(bp)) { + bnxt_check_rss_tbl_no_rmgr(bp); + return false; + } if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5)) vnic = rx + 1; if (bp->flags & BNXT_FLAG_AGG_RINGS) rx <<= 1; stat = bnxt_get_func_stat_ctxs(bp); - if (BNXT_NEW_RM(bp) && - (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || - hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || - (hw_resc->resv_hw_ring_grps != grp && - !(bp->flags & BNXT_FLAG_CHIP_P5)))) + if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || + hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || + (hw_resc->resv_hw_ring_grps != grp && + !(bp->flags & BNXT_FLAG_CHIP_P5))) return true; if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) && hw_resc->resv_irqs != nq) @@ -6214,6 +6240,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (!tx || !rx || !cp || !grp || !vnic || !stat) return -ENOMEM; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + return rc; } @@ -8495,9 +8524,6 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) rc = bnxt_init_int_mode(bp); bnxt_ulp_irq_restart(bp, rc); } - if (!netif_is_rxfh_configured(bp->dev)) - bnxt_set_dflt_rss_indir_tbl(bp); - if (rc) { netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; @@ -9284,16 +9310,19 @@ static ssize_t bnxt_show_temp(struct device *dev, struct hwrm_temp_monitor_query_input req = {0}; struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); - u32 temp = 0; + u32 len = 0; resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) - temp = resp->temp * 1000; /* display millidegree */ + if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - return sprintf(buf, "%u\n", temp); + if (len) + return len; + + return sprintf(buf, "unknown\n"); } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); @@ -9475,15 +9504,15 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } } - bnxt_enable_napi(bp); - bnxt_debug_dev_init(bp); - rc = bnxt_init_nic(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); - goto open_err; + goto open_err_irq; } + bnxt_enable_napi(bp); + bnxt_debug_dev_init(bp); + if (link_re_init) { mutex_lock(&bp->link_lock); rc = bnxt_update_phy_setting(bp); @@ -9514,10 +9543,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bnxt_vf_reps_open(bp); return 0; -open_err: - bnxt_debug_dev_exit(bp); - bnxt_disable_napi(bp); - open_err_irq: bnxt_del_napi(bp); @@ -11761,6 +11786,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_cancel_sp_work(bp); bp->sp_event = 0; @@ -12200,6 +12226,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (BNXT_CHIP_P5(bp)) bp->flags |= BNXT_FLAG_CHIP_P5; + rc = bnxt_alloc_rss_indir_tbl(bp); + if (rc) + goto init_err_pci_clean; + rc = bnxt_fw_init_one_p2(bp); if (rc) goto init_err_pci_clean; @@ -12304,11 +12334,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - rc = bnxt_alloc_rss_indir_tbl(bp); - if (rc) - goto init_err_pci_clean; - bnxt_set_dflt_rss_indir_tbl(bp); - if (BNXT_PF(bp)) { if (!bnxt_pf_wq) { bnxt_pf_wq = @@ -12339,6 +12364,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) (long)pci_resource_start(pdev, 0), dev->dev_addr); pcie_print_link_status(pdev); + pci_save_state(pdev); return 0; init_err_cleanup: @@ -12536,6 +12562,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) "Cannot re-enable PCI device after reset.\n"); } else { pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); err = bnxt_hwrm_func_reset(bp); if (!err) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 17934cd87a4a..d0928334bdc8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -472,20 +472,13 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) static int bnxt_get_num_ring_stats(struct bnxt *bp) { int rx, tx, cmn; - bool sh = false; - - if (bp->flags & BNXT_FLAG_SHARED_RINGS) - sh = true; rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS + bnxt_get_num_tpa_ring_stats(bp); tx = NUM_RING_TX_HW_STATS; cmn = NUM_RING_CMN_SW_STATS; - if (sh) - return (rx + tx + cmn) * bp->cp_nr_rings; - else - return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + - cmn * bp->cp_nr_rings; + return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + + cmn * bp->cp_nr_rings; } static int bnxt_get_num_stats(struct bnxt *bp) @@ -806,7 +799,7 @@ static void bnxt_get_channels(struct net_device *dev, int max_tx_sch_inputs; /* Get the most up-to-date max_tx_sch_inputs. */ - if (BNXT_NEW_RM(bp)) + if (netif_running(dev) && BNXT_NEW_RM(bp)) bnxt_hwrm_func_resc_qcaps(bp, false); max_tx_sch_inputs = hw_resc->max_tx_sch_inputs; @@ -2323,6 +2316,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data) if (rc != 0) return rc; + if (!dir_entries || !entry_length) + return -EIO; + /* Insert 2 bytes of directory info (count and size of entries) */ if (len < 2) return -EINVAL; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 0ca8436d2e9d..be85dad2e3bc 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1364,7 +1364,7 @@ static int bcmgenet_validate_flow(struct net_device *dev, case ETHER_FLOW: eth_mask = &cmd->fs.m_u.ether_spec; /* don't allow mask which isn't valid */ - if (VALIDATE_MASK(eth_mask->h_source) || + if (VALIDATE_MASK(eth_mask->h_dest) || VALIDATE_MASK(eth_mask->h_source) || VALIDATE_MASK(eth_mask->h_proto)) { netdev_err(dev, "rxnfc: Unsupported mask\n"); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9894594d957d..5143cdd0eeca 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7221,8 +7221,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp) static inline void tg3_reset_task_cancel(struct tg3 *tp) { - cancel_work_sync(&tp->reset_task); - tg3_flag_clear(tp, RESET_TASK_PENDING); + if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags)) + cancel_work_sync(&tp->reset_task); tg3_flag_clear(tp, TX_RECOVERY_PENDING); } @@ -11209,18 +11209,27 @@ static void tg3_reset_task(struct work_struct *work) tg3_halt(tp, RESET_KIND_SHUTDOWN, 0); err = tg3_init_hw(tp, true); - if (err) + if (err) { + tg3_full_unlock(tp); + tp->irq_sync = 0; + tg3_napi_enable(tp); + /* Clear this flag so that tg3_reset_task_cancel() will not + * call cancel_work_sync() and wait forever. + */ + tg3_flag_clear(tp, RESET_TASK_PENDING); + dev_close(tp->dev); goto out; + } tg3_netif_start(tp); -out: tg3_full_unlock(tp); if (!err) tg3_phy_start(tp); tg3_flag_clear(tp, RESET_TASK_PENDING); +out: rtnl_unlock(); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c index e3510e9b21f3..9a6d65243334 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c @@ -62,6 +62,7 @@ static struct thermal_zone_device_ops cxgb4_thermal_ops = { int cxgb4_thermal_init(struct adapter *adap) { struct ch_thermal *ch_thermal = &adap->ch_thermal; + char ch_tz_name[THERMAL_NAME_LENGTH]; int num_trip = CXGB4_NUM_TRIPS; u32 param, val; int ret; @@ -82,7 +83,8 @@ int cxgb4_thermal_init(struct adapter *adap) ch_thermal->trip_type = THERMAL_TRIP_CRITICAL; } - ch_thermal->tzdev = thermal_zone_device_register("cxgb4", num_trip, + snprintf(ch_tz_name, sizeof(ch_tz_name), "cxgb4_%s", adap->name); + ch_thermal->tzdev = thermal_zone_device_register(ch_tz_name, num_trip, 0, adap, &cxgb4_thermal_ops, NULL, 0, 0); @@ -105,7 +107,9 @@ int cxgb4_thermal_init(struct adapter *adap) int cxgb4_thermal_remove(struct adapter *adap) { - if (adap->ch_thermal.tzdev) + if (adap->ch_thermal.tzdev) { thermal_zone_device_unregister(adap->ch_thermal.tzdev); + adap->ch_thermal.tzdev = NULL; + } return 0; } diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 62e271aea4a5..ffec0f3dd957 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2446,8 +2446,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); - clk_disable_unprepare(port->pclk); - return PTR_ERR(port->reset); + ret = PTR_ERR(port->reset); + goto unprepare; } reset_control_reset(port->reset); usleep_range(100, 500); @@ -2502,25 +2502,25 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); - if (ret) { - clk_disable_unprepare(port->pclk); - return ret; - } + if (ret) + goto unprepare; ret = register_netdev(netdev); - if (!ret) { + if (ret) + goto unprepare; + + netdev_info(netdev, + "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n", + port->irq, &dmares->start, + &gmacres->start); + ret = gmac_setup_phy(netdev); + if (ret) netdev_info(netdev, - "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n", - port->irq, &dmares->start, - &gmacres->start); - ret = gmac_setup_phy(netdev); - if (ret) - netdev_info(netdev, - "PHY init failed, deferring to ifup time\n"); - return 0; - } + "PHY init failed, deferring to ifup time\n"); + return 0; - port->netdev = NULL; +unprepare: + clk_disable_unprepare(port->pclk); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 23f278e46975..22522f8a5299 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2282,8 +2282,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev) priv->enet_ver = AE_VERSION_1; else if (acpi_dev_found(hns_enet_acpi_match[1].id)) priv->enet_ver = AE_VERSION_2; - else - return -ENXIO; + else { + ret = -ENXIO; + goto out_read_prop_fail; + } /* try to find port-idx-in-ae first */ ret = acpi_node_get_property_reference(dev->fwnode, @@ -2299,7 +2301,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) priv->fwnode = args.fwnode; } else { dev_err(dev, "cannot read cfg data from OF or acpi\n"); - return -ENXIO; + ret = -ENXIO; + goto out_read_prop_fail; } ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index c2ea0348b2f7..a4f1d515e5e0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -21,6 +21,7 @@ #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/vxlan.h> +#include <net/geneve.h> #include "hnae3.h" #include "hns3_enet.h" @@ -780,7 +781,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, * and it is udp packet, which has a dest port as the IANA assigned. * the hardware is expected to do the checksum offload, but the * hardware will not do the checksum offload when udp dest port is - * 4789. + * 4789 or 6081. */ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) { @@ -789,7 +790,8 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.hdr = skb_transport_header(skb); if (!(!skb->encapsulation && - l4.udp->dest == htons(IANA_VXLAN_UDP_PORT))) + (l4.udp->dest == htons(IANA_VXLAN_UDP_PORT) || + l4.udp->dest == htons(GENEVE_UDP_PORT)))) return false; skb_checksum_help(skb); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5afb3c9c52d2..d3a774331afc 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -479,6 +479,9 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) int i, j, rc; u64 *size_array; + if (!adapter->rx_pool) + return -1; + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); @@ -649,6 +652,9 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) int tx_scrqs; int i, rc; + if (!adapter->tx_pool) + return -1; + tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); for (i = 0; i < tx_scrqs; i++) { rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); @@ -2011,7 +2017,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->req_rx_add_entries_per_subcrq != old_num_rx_slots || adapter->req_tx_entries_per_subcrq != - old_num_tx_slots) { + old_num_tx_slots || + !adapter->rx_pool || + !adapter->tso_pool || + !adapter->tx_pool) { release_rx_pools(adapter); release_tx_pools(adapter); release_napi(adapter); @@ -2024,10 +2033,14 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", + rc); goto out; rc = reset_rx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", + rc); goto out; } ibmvnic_disable_irqs(adapter); diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index d2986f1f2db0..d7444782bfdd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -114,7 +114,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order) goto err_out; for (i = 0; i <= buddy->max_order; ++i) { - s = BITS_TO_LONGS(1 << (buddy->max_order - i)); + s = BITS_TO_LONGS(1UL << (buddy->max_order - i)); buddy->bits[i] = kvmalloc_array(s, sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!buddy->bits[i]) goto err_out_free; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 2df3deedf9fd..7248d248f604 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -61,6 +61,7 @@ struct nfp_tun_active_tuns { * @flags: options part of the request * @tun_info.ipv6: dest IPv6 address of active route * @tun_info.egress_port: port the encapsulated packet egressed + * @tun_info.extra: reserved for future use * @tun_info: tunnels that have sent traffic in reported period */ struct nfp_tun_active_tuns_v6 { @@ -70,6 +71,7 @@ struct nfp_tun_active_tuns_v6 { struct route_ip_info_v6 { struct in6_addr ipv6; __be32 egress_port; + __be32 extra[2]; } tun_info[]; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 8107d32c2767..def65fee27b5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -496,9 +496,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) struct ionic_cq *txcq; u32 rx_work_done = 0; u32 tx_work_done = 0; - u32 work_done = 0; u32 flags = 0; - bool unmask; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; @@ -512,17 +510,12 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) if (rx_work_done) ionic_rx_fill_cb(rxcq->bound_q); - unmask = (rx_work_done < budget) && (tx_work_done < lif->tx_budget); - - if (unmask && napi_complete_done(napi, rx_work_done)) { + if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { flags |= IONIC_INTR_CRED_UNMASK; DEBUG_STATS_INTR_REARM(rxcq->bound_intr); - work_done = rx_work_done; - } else { - work_done = budget; } - if (work_done || flags) { + if (rx_work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, tx_work_done + rx_work_done, flags); @@ -531,7 +524,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) DEBUG_STATS_NAPI_POLL(qcq, rx_work_done); DEBUG_STATS_NAPI_POLL(qcq, tx_work_done); - return work_done; + return rx_work_done; } static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 99f7aae102ce..df89d09b253e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1342,6 +1342,51 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, return error; } +/* MDIO bus init function */ +static int ravb_mdio_init(struct ravb_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + int error; + + /* Bitbang init */ + priv->mdiobb.ops = &bb_ops; + + /* MII controller setting */ + priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); + if (!priv->mii_bus) + return -ENOMEM; + + /* Hook up MII support for ethtool */ + priv->mii_bus->name = "ravb_mii"; + priv->mii_bus->parent = dev; + snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + + /* Register MDIO bus */ + error = of_mdiobus_register(priv->mii_bus, dev->of_node); + if (error) + goto out_free_bus; + + return 0; + +out_free_bus: + free_mdio_bitbang(priv->mii_bus); + return error; +} + +/* MDIO bus release function */ +static int ravb_mdio_release(struct ravb_private *priv) +{ + /* Unregister mdio bus */ + mdiobus_unregister(priv->mii_bus); + + /* Free bitbang info */ + free_mdio_bitbang(priv->mii_bus); + + return 0; +} + /* Network device open function for Ethernet AVB */ static int ravb_open(struct net_device *ndev) { @@ -1350,6 +1395,13 @@ static int ravb_open(struct net_device *ndev) struct device *dev = &pdev->dev; int error; + /* MDIO bus init */ + error = ravb_mdio_init(priv); + if (error) { + netdev_err(ndev, "failed to initialize MDIO\n"); + return error; + } + napi_enable(&priv->napi[RAVB_BE]); napi_enable(&priv->napi[RAVB_NC]); @@ -1427,6 +1479,7 @@ out_free_irq: out_napi_off: napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); return error; } @@ -1736,6 +1789,8 @@ static int ravb_close(struct net_device *ndev) ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); + ravb_mdio_release(priv); + return 0; } @@ -1887,51 +1942,6 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_features = ravb_set_features, }; -/* MDIO bus init function */ -static int ravb_mdio_init(struct ravb_private *priv) -{ - struct platform_device *pdev = priv->pdev; - struct device *dev = &pdev->dev; - int error; - - /* Bitbang init */ - priv->mdiobb.ops = &bb_ops; - - /* MII controller setting */ - priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); - if (!priv->mii_bus) - return -ENOMEM; - - /* Hook up MII support for ethtool */ - priv->mii_bus->name = "ravb_mii"; - priv->mii_bus->parent = dev; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); - - /* Register MDIO bus */ - error = of_mdiobus_register(priv->mii_bus, dev->of_node); - if (error) - goto out_free_bus; - - return 0; - -out_free_bus: - free_mdio_bitbang(priv->mii_bus); - return error; -} - -/* MDIO bus release function */ -static int ravb_mdio_release(struct ravb_private *priv) -{ - /* Unregister mdio bus */ - mdiobus_unregister(priv->mii_bus); - - /* Free bitbang info */ - free_mdio_bitbang(priv->mii_bus); - - return 0; -} - static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 }, { .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 }, @@ -2174,13 +2184,6 @@ static int ravb_probe(struct platform_device *pdev) eth_hw_addr_random(ndev); } - /* MDIO bus init */ - error = ravb_mdio_init(priv); - if (error) { - dev_err(&pdev->dev, "failed to initialize MDIO\n"); - goto out_dma_free; - } - netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); @@ -2202,8 +2205,6 @@ static int ravb_probe(struct platform_device *pdev) out_napi_del: netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); -out_dma_free: dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); @@ -2235,7 +2236,6 @@ static int ravb_remove(struct platform_device *pdev) unregister_netdev(ndev); netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); free_netdev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c index 012925e878f4..85207acf7dee 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.c +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -36,7 +36,7 @@ bool ef100_rx_buf_hash_valid(const u8 *prefix) return PREFIX_FIELD(prefix, RSS_HASH_VALID); } -static bool check_fcs(struct efx_channel *channel, u32 *prefix) +static bool ef100_has_fcs_error(struct efx_channel *channel, u32 *prefix) { u16 rxclass; u8 l2status; @@ -46,11 +46,11 @@ static bool check_fcs(struct efx_channel *channel, u32 *prefix) if (likely(l2status == ESE_GZ_RH_HCLASS_L2_STATUS_OK)) /* Everything is ok */ - return 0; + return false; if (l2status == ESE_GZ_RH_HCLASS_L2_STATUS_FCS_ERR) channel->n_rx_eth_crc_err++; - return 1; + return true; } void __ef100_rx_packet(struct efx_channel *channel) @@ -63,7 +63,7 @@ void __ef100_rx_packet(struct efx_channel *channel) prefix = (u32 *)(eh - ESE_GZ_RX_PKT_PREFIX_LEN); - if (check_fcs(channel, prefix) && + if (ef100_has_fcs_error(channel, prefix) && unlikely(!(efx->net_dev->features & NETIF_F_RXALL))) goto out; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index cb994f66c3be..9baf3f3da91e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -174,6 +174,8 @@ void am65_cpsw_nuss_adjust_link(struct net_device *ndev) if (phy->speed == 10 && phy_interface_is_rgmii(phy)) /* Can be used with in band mode only */ mac_control |= CPSW_SL_CTL_EXT_EN; + if (phy->speed == 100 && phy->interface == PHY_INTERFACE_MODE_RMII) + mac_control |= CPSW_SL_CTL_IFCTL_A; if (phy->duplex) mac_control |= CPSW_SL_CTL_FULLDUPLEX; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9b17bbbe102f..4a65edc5a375 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1116,7 +1116,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, HOST_PORT_NUM, ALE_VLAN, vid); ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, 0, ALE_VLAN, vid); - ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret |= cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 1247d35d42ef..8ed78577cded 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1032,19 +1032,34 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, return ret; } + /* reset the return code as pm_runtime_get_sync() can return + * non zero values as well. + */ + ret = 0; for (i = 0; i < cpsw->data.slaves; i++) { if (cpsw->slaves[i].ndev && - vid == cpsw->slaves[i].port_vlan) + vid == cpsw->slaves[i].port_vlan) { + ret = -EINVAL; goto err; + } } dev_dbg(priv->dev, "removing vlanid %d from vlan filter\n", vid); - cpsw_ale_del_vlan(cpsw->ale, vid, 0); - cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, - HOST_PORT_NUM, ALE_VLAN, vid); - cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, - 0, ALE_VLAN, vid); - cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_vlan() failed: ret %d\n", ret); + ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, + HOST_PORT_NUM, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_ucast() failed: ret %d\n", + ret); + ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, + 0, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_mcast failed. ret %d\n", + ret); + cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); + ret = 0; err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 21640a035d7d..8e47d0112e5d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1179,6 +1179,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, goto nlmsg_failure; if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) || + nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) || nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) || nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr)) goto nla_put_failure; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index f3c04981b8da..cd7032628a28 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -215,9 +215,9 @@ static int dp83867_set_wol(struct phy_device *phydev, if (wol->wolopts & WAKE_MAGICSECURE) { phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, (wol->sopass[1] << 8) | wol->sopass[0]); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP2, (wol->sopass[3] << 8) | wol->sopass[2]); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP1, + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RXFSOP3, (wol->sopass[5] << 8) | wol->sopass[4]); val_rxcfg |= DP83867_WOL_SEC_EN; diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 58103152c601..6b98d74b5102 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -427,18 +427,18 @@ static int dp83869_config_init(struct phy_device *phydev) return ret; val = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL); - val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val |= (DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) - val |= (DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) - val |= DP83869_RGMII_TX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_TX_CLK_DELAY_EN; if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) - val |= DP83869_RGMII_RX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_RX_CLK_DELAY_EN; ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL, val); diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index a7fbc3ccd29e..c7bcfca7d70b 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -252,6 +252,7 @@ config USB_NET_CDC_EEM config USB_NET_CDC_NCM tristate "CDC NCM support" depends on USB_USBNET + select USB_NET_CDCETHER default y help This driver provides support for CDC NCM (Network Control Model diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index e39f41efda3e..7bc6e8f856fe 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -296,7 +296,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal) netdev_dbg(dev->net, "asix_get_phy_addr()\n"); - if (ret < 0) { + if (ret < 2) { netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret); goto out; } diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index b91f92e4e5f2..915ac75b55fc 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -625,6 +625,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0a46, 0x1269), /* DM9621A USB to Fast Ethernet Adapter */ .driver_info = (unsigned long)&dm9601_info, }, + { + USB_DEVICE(0x0586, 0x3427), /* ZyXEL Keenetic Plus DSL xDSL modem */ + .driver_info = (unsigned long)&dm9601_info, + }, {}, // END }; diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index 386ed2aa31fd..9b00708676cf 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -229,7 +229,7 @@ static void hdlc_setup_dev(struct net_device *dev) dev->min_mtu = 68; dev->max_mtu = HDLC_MAX_MTU; dev->type = ARPHRD_RAWHDLC; - dev->hard_header_len = 16; + dev->hard_header_len = 0; dev->needed_headroom = 0; dev->addr_len = 0; dev->header_ops = &hdlc_null_ops; diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index d8cba3625c18..444130655d8e 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -370,6 +370,7 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) memcpy(&state(hdlc)->settings, &new_settings, size); spin_lock_init(&state(hdlc)->lock); dev->header_ops = &cisco_header_ops; + dev->hard_header_len = sizeof(struct hdlc_header); dev->type = ARPHRD_CISCO; call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_on(dev); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 8ccd086e06cb..732a6c1851f5 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -210,6 +210,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) skb->dev = dev = lapbeth->ethdev; + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); @@ -340,6 +342,7 @@ static int lapbeth_new_device(struct net_device *dev) */ ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + dev->needed_headroom; + ndev->needed_tailroom = dev->needed_tailroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 9642971e89ce..457854765983 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -966,7 +966,7 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev, rc = down_killable(&stcontext->exchange_lock); if (rc) { WARN(1, "Semaphore is not found up in st95hf_in_send_cmd\n"); - return rc; + goto free_skb_resp; } rc = st95hf_spi_send(&stcontext->spicontext, skb->data, diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 71aebaf533ea..0e8621a6956d 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -2457,10 +2457,10 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task) return err; } - __kfree_skb(skb); log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, "itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n", task->itt, skb, skb->len, skb->data_len, err); + __kfree_skb(skb); iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err); iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED); return err; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 3f04f2c81366..5ca424df355c 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3863,7 +3863,7 @@ void qedf_stag_change_work(struct work_struct *work) container_of(work, struct qedf_ctx, stag_work.work); if (!qedf) { - QEDF_ERR(&qedf->dbg_ctx, "qedf is NULL"); + QEDF_ERR(NULL, "qedf is NULL"); return; } QEDF_ERR(&qedf->dbg_ctx, "Performing software context reset.\n"); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 139f0073da37..1ad7260d4758 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4482,8 +4482,6 @@ static int resp_open_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) goto fini; } - if (zc == ZC2_IMPLICIT_OPEN) - zbc_close_zone(devip, zsp); zbc_open_zone(devip, zsp, true); fini: write_unlock(macc_lckp); diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index bc27f9430eeb..7c6b91f0e780 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -199,6 +199,7 @@ static int cedrus_request_validate(struct media_request *req) struct v4l2_ctrl *ctrl_test; unsigned int count; unsigned int i; + int ret = 0; list_for_each_entry(obj, &req->objects, list) { struct vb2_buffer *vb; @@ -243,12 +244,16 @@ static int cedrus_request_validate(struct media_request *req) if (!ctrl_test) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); - return -ENOENT; + ret = -ENOENT; + break; } } v4l2_ctrl_request_hdl_put(hdl); + if (ret) + return ret; + return vb2_request_validate(req); } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5857d4eec9d7..b45519ca66a7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2537,7 +2537,7 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) { r = vhost_update_used_flags(vq); if (r) - vq_err(vq, "Failed to enable notification at %p: %d\n", + vq_err(vq, "Failed to disable notification at %p: %d\n", &vq->used->flags, r); } } diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index f708c45d5f66..29f11e10a7c7 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -420,24 +420,51 @@ affs_mode_to_prot(struct inode *inode) u32 prot = AFFS_I(inode)->i_protect; umode_t mode = inode->i_mode; + /* + * First, clear all RWED bits for owner, group, other. + * Then, recalculate them afresh. + * + * We'll always clear the delete-inhibit bit for the owner, as that is + * the classic single-user mode AmigaOS protection bit and we need to + * stay compatible with all scenarios. + * + * Since multi-user AmigaOS is an extension, we'll only set the + * delete-allow bit if any of the other bits in the same user class + * (group/other) are used. + */ + prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD + | FIBF_NOWRITE | FIBF_NODELETE + | FIBF_GRP_EXECUTE | FIBF_GRP_READ + | FIBF_GRP_WRITE | FIBF_GRP_DELETE + | FIBF_OTR_EXECUTE | FIBF_OTR_READ + | FIBF_OTR_WRITE | FIBF_OTR_DELETE); + + /* Classic single-user AmigaOS flags. These are inverted. */ if (!(mode & 0100)) prot |= FIBF_NOEXECUTE; if (!(mode & 0400)) prot |= FIBF_NOREAD; if (!(mode & 0200)) prot |= FIBF_NOWRITE; + + /* Multi-user extended flags. Not inverted. */ if (mode & 0010) prot |= FIBF_GRP_EXECUTE; if (mode & 0040) prot |= FIBF_GRP_READ; if (mode & 0020) prot |= FIBF_GRP_WRITE; + if (mode & 0070) + prot |= FIBF_GRP_DELETE; + if (mode & 0001) prot |= FIBF_OTR_EXECUTE; if (mode & 0004) prot |= FIBF_OTR_READ; if (mode & 0002) prot |= FIBF_OTR_WRITE; + if (mode & 0007) + prot |= FIBF_OTR_DELETE; AFFS_I(inode)->i_protect = prot; } diff --git a/fs/affs/file.c b/fs/affs/file.c index a26a0f96c119..d91b0133d95d 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -429,6 +429,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, return ret; } +static int affs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + + return ret; +} + static sector_t _affs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,affs_get_block); @@ -438,7 +456,7 @@ const struct address_space_operations affs_aops = { .readpage = affs_readpage, .writepage = affs_writepage, .write_begin = affs_write_begin, - .write_end = generic_write_end, + .write_end = affs_write_end, .direct_IO = affs_direct_IO, .bmap = _affs_bmap }; @@ -795,6 +813,12 @@ done: if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; + /* Clear Archived bit on file writes, as AmigaOS would do */ + if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { + AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; + mark_inode_dirty(inode); + } + err_first_bh: unlock_page(page); put_page(page); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 5d9ef517cf81..e7e98ad63a91 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -161,8 +161,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 792ac711985e..18042b7dab6a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -401,22 +401,24 @@ struct afs_vlserver { #define AFS_VLSERVER_FL_PROBED 0 /* The VL server has been probed */ #define AFS_VLSERVER_FL_PROBING 1 /* VL server is being probed */ #define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ +#define AFS_VLSERVER_FL_RESPONDING 3 /* VL server is responding */ rwlock_t lock; /* Lock on addresses */ atomic_t usage; + unsigned int rtt; /* Server's current RTT in uS */ /* Probe state */ wait_queue_head_t probe_wq; atomic_t probe_outstanding; spinlock_t probe_lock; struct { - unsigned int rtt; /* RTT as ktime/64 */ + unsigned int rtt; /* RTT in uS */ u32 abort_code; short error; - bool have_result; - bool responded:1; - bool is_yfs:1; - bool not_yfs:1; - bool local_failure:1; + unsigned short flags; +#define AFS_VLSERVER_PROBE_RESPONDED 0x01 /* At least once response (may be abort) */ +#define AFS_VLSERVER_PROBE_IS_YFS 0x02 /* The peer appears to be YFS */ +#define AFS_VLSERVER_PROBE_NOT_YFS 0x04 /* The peer appears not to be YFS */ +#define AFS_VLSERVER_PROBE_LOCAL_FAILURE 0x08 /* A local failure prevented a probe */ } probe; u16 port; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e817fc740ba0..e8babb62ed44 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -310,6 +310,11 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) alist->preferred == i ? '>' : '-', &alist->addrs[i].transport); } + seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt); + seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n", + vlserver->probe.flags, vlserver->probe.error, + vlserver->probe.abort_code, + atomic_read(&vlserver->probe_outstanding)); return 0; } diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index 8fea54eba0c2..38b2ba1d9ec0 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -21,6 +21,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len, rwlock_init(&vlserver->lock); init_waitqueue_head(&vlserver->probe_wq); spin_lock_init(&vlserver->probe_lock); + vlserver->rtt = UINT_MAX; vlserver->name_len = name_len; vlserver->port = port; memcpy(vlserver->name, name, name_len); diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index e3aa013c2177..d1c7068b4346 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -11,15 +11,33 @@ #include "internal.h" #include "protocol_yfs.h" -static bool afs_vl_probe_done(struct afs_vlserver *server) + +/* + * Handle the completion of a set of probes. + */ +static void afs_finished_vl_probe(struct afs_vlserver *server) { - if (!atomic_dec_and_test(&server->probe_outstanding)) - return false; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { + server->rtt = UINT_MAX; + clear_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + } - wake_up_var(&server->probe_outstanding); clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags); wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING); - return true; +} + +/* + * Handle the completion of a probe RPC call. + */ +static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up) +{ + if (atomic_dec_and_test(&server->probe_outstanding)) { + afs_finished_vl_probe(server); + wake_up = true; + } + + if (wake_up) + wake_up_all(&server->probe_wq); } /* @@ -45,15 +63,20 @@ void afs_vlserver_probe_result(struct afs_call *call) server->probe.error = 0; goto responded; case -ECONNABORTED: - if (!server->probe.responded) { + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { server->probe.abort_code = call->abort_code; server->probe.error = ret; } goto responded; case -ENOMEM: case -ENONET: - server->probe.local_failure = true; - afs_io_error(call, afs_io_error_vl_probe_fail); + case -EKEYEXPIRED: + case -EKEYREVOKED: + case -EKEYREJECTED: + server->probe.flags |= AFS_VLSERVER_PROBE_LOCAL_FAILURE; + if (server->probe.error == 0) + server->probe.error = ret; + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ case -ERFKILL: @@ -67,12 +90,12 @@ void afs_vlserver_probe_result(struct afs_call *call) default: clear_bit(index, &alist->responded); set_bit(index, &alist->failed); - if (!server->probe.responded && + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) && (server->probe.error == 0 || server->probe.error == -ETIMEDOUT || server->probe.error == -ETIME)) server->probe.error = ret; - afs_io_error(call, afs_io_error_vl_probe_fail); + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; } @@ -81,39 +104,36 @@ responded: clear_bit(index, &alist->failed); if (call->service_id == YFS_VL_SERVICE) { - server->probe.is_yfs = true; + server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS; set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } else { - server->probe.not_yfs = true; - if (!server->probe.is_yfs) { + server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) { clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; + server->rtt = rtt_us; alist->preferred = index; - have_result = true; } smp_wmb(); /* Set rtt before responded. */ - server->probe.responded = true; + server->probe.flags |= AFS_VLSERVER_PROBE_RESPONDED; set_bit(AFS_VLSERVER_FL_PROBED, &server->flags); + set_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + have_result = true; out: spin_unlock(&server->probe_lock); _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", server_index, index, &alist->addrs[index].transport, rtt_us, ret); - have_result |= afs_vl_probe_done(server); - if (have_result) { - server->probe.have_result = true; - wake_up_var(&server->probe.have_result); - wake_up_all(&server->probe_wq); - } + afs_done_one_vl_probe(server, have_result); } /* @@ -151,11 +171,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net, in_progress = true; } else { afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); + afs_done_one_vl_probe(server, false); } } - if (!in_progress) - afs_vl_probe_done(server); return in_progress; } @@ -193,7 +212,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, { struct wait_queue_entry *waits; struct afs_vlserver *server; - unsigned int rtt = UINT_MAX; + unsigned int rtt = UINT_MAX, rtt_s; bool have_responders = false; int pref = -1, i; @@ -205,7 +224,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, server = vllist->servers[i].server; if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) __clear_bit(i, &untried); - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) have_responders = true; } } @@ -231,7 +250,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) goto stop; if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) still_probing = true; @@ -249,10 +268,11 @@ stop: for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded && - server->probe.rtt < rtt) { + rtt_s = READ_ONCE(server->rtt); + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags) && + rtt_s < rtt) { pref = i; - rtt = server->probe.rtt; + rtt = rtt_s; } remove_wait_queue(&server->probe_wq, &waits[i]); diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index f405ca8b240a..c0458c903b31 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -192,7 +192,8 @@ pick_server: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; - if (!test_bit(i, &vc->untried) || !s->probe.responded) + if (!test_bit(i, &vc->untried) || + !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) continue; if (s->probe.rtt < rtt) { vc->index = i; @@ -262,10 +263,14 @@ no_more_servers: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) + e.responded = true; afs_prioritise_error(&e, READ_ONCE(s->probe.error), s->probe.abort_code); } + error = e.error; + failed_set_error: vc->error = error; failed: diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 613920c17ac1..ea8aaf36647e 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1798,7 +1798,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( cache->fs_info = fs_info; cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); - set_free_space_tree_thresholds(cache); cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED; @@ -1912,6 +1911,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (ret < 0) goto error; + set_free_space_tree_thresholds(cache); + if (need_clear) { /* * When we mount with old space cache, we need to @@ -2132,6 +2133,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, return -ENOMEM; cache->length = size; + set_free_space_tree_thresholds(cache); cache->used = bytes_used; cache->flags = type; cache->last_byte_to_unpin = (u64)-1; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cd1cd673bc0b..cd392da69b81 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1297,6 +1297,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), + eb_rewin, btrfs_header_level(eb_rewin)); btrfs_tree_read_lock(eb_rewin); __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm); WARN_ON(btrfs_header_nritems(eb_rewin) > @@ -1370,7 +1372,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (!eb) return NULL; - btrfs_tree_read_lock(eb); if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); @@ -1378,6 +1379,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, + btrfs_header_level(eb)); + btrfs_tree_read_lock(eb); if (tm) __tree_mod_log_rewind(fs_info, eb, time_seq, tm); else diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5871ef78edba..e9eedc053fc5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4527,7 +4527,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, return ERR_PTR(-EUCLEAN); } - btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); + btrfs_set_buffer_lockdep_class(owner, buf, level); btrfs_tree_lock(buf); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6def411b2eba..a940edb1e64f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5655,9 +5655,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, } } -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dstv, - unsigned long start, unsigned long len) +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5677,7 +5677,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb, cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); - if (copy_to_user(dst, kaddr + offset, cur)) { + if (copy_to_user_nofault(dst, kaddr + offset, cur)) { ret = -EFAULT; break; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 00a88f2eb5ab..30794ae58498 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -241,9 +241,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dst, unsigned long start, - unsigned long len); +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dst, unsigned long start, + unsigned long len); void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src); void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb, const void *src); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 8b1f5c8897b7..6b9faf3b0e96 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -22,6 +22,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group *cache) size_t bitmap_size; u64 num_bitmaps, total_bitmap_size; + if (WARN_ON(cache->length == 0)) + btrfs_warn(cache->fs_info, "block group %llu length is zero", + cache->start); + /* * We convert to bitmaps when the disk space required for using extents * exceeds that required for using bitmaps. diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bd3511c5ca81..ac45f022b495 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2086,9 +2086,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, sh.len = item_len; sh.transid = found_transid; - /* copy search result header */ - if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { - ret = -EFAULT; + /* + * Copy search result header. If we fault then loop again so we + * can fault in the pages and -EFAULT there if there's a + * problem. Otherwise we'll fault and then copy the buffer in + * properly this next time through + */ + if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = 0; goto out; } @@ -2096,10 +2101,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, if (item_len) { char __user *up = ubuf + *sk_offset; - /* copy the item */ - if (read_extent_buffer_to_user(leaf, up, - item_off, item_len)) { - ret = -EFAULT; + /* + * Copy the item, same behavior as above, but reset the + * * sk_offset so we copy the full thing again. + */ + if (read_extent_buffer_to_user_nofault(leaf, up, + item_off, item_len)) { + ret = 0; + *sk_offset -= sizeof(sh); goto out; } @@ -2184,6 +2193,10 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { + ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset); + if (ret) + break; + ret = btrfs_search_forward(root, &key, path, sk->min_transid); if (ret != 0) { if (ret > 0) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 5a6cb9db512e..354ab9985a34 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3716,50 +3716,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, return 0; } +static void scrub_workers_put(struct btrfs_fs_info *fs_info) +{ + if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, + &fs_info->scrub_lock)) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; + + scrub_workers = fs_info->scrub_workers; + scrub_wr_comp = fs_info->scrub_wr_completion_workers; + scrub_parity = fs_info->scrub_parity_workers; + + fs_info->scrub_workers = NULL; + fs_info->scrub_wr_completion_workers = NULL; + fs_info->scrub_parity_workers = NULL; + mutex_unlock(&fs_info->scrub_lock); + + btrfs_destroy_workqueue(scrub_workers); + btrfs_destroy_workqueue(scrub_wr_comp); + btrfs_destroy_workqueue(scrub_parity); + } +} + /* * get a reference count on fs_info->scrub_workers. start worker if necessary */ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; + int ret = -ENOMEM; - lockdep_assert_held(&fs_info->scrub_lock); + if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) + return 0; - if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { - ASSERT(fs_info->scrub_workers == NULL); - fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", - flags, is_dev_replace ? 1 : max_active, 4); - if (!fs_info->scrub_workers) - goto fail_scrub_workers; - - ASSERT(fs_info->scrub_wr_completion_workers == NULL); - fs_info->scrub_wr_completion_workers = - btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, - max_active, 2); - if (!fs_info->scrub_wr_completion_workers) - goto fail_scrub_wr_completion_workers; + scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags, + is_dev_replace ? 1 : max_active, 4); + if (!scrub_workers) + goto fail_scrub_workers; - ASSERT(fs_info->scrub_parity_workers == NULL); - fs_info->scrub_parity_workers = - btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, max_active, 2); - if (!fs_info->scrub_parity_workers) - goto fail_scrub_parity_workers; + if (!scrub_wr_comp) + goto fail_scrub_wr_completion_workers; + scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + max_active, 2); + if (!scrub_parity) + goto fail_scrub_parity_workers; + + mutex_lock(&fs_info->scrub_lock); + if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { + ASSERT(fs_info->scrub_workers == NULL && + fs_info->scrub_wr_completion_workers == NULL && + fs_info->scrub_parity_workers == NULL); + fs_info->scrub_workers = scrub_workers; + fs_info->scrub_wr_completion_workers = scrub_wr_comp; + fs_info->scrub_parity_workers = scrub_parity; refcount_set(&fs_info->scrub_workers_refcnt, 1); - } else { - refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + return 0; } - return 0; + /* Other thread raced in and created the workers for us */ + refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + ret = 0; + btrfs_destroy_workqueue(scrub_parity); fail_scrub_parity_workers: - btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers); + btrfs_destroy_workqueue(scrub_wr_comp); fail_scrub_wr_completion_workers: - btrfs_destroy_workqueue(fs_info->scrub_workers); + btrfs_destroy_workqueue(scrub_workers); fail_scrub_workers: - return -ENOMEM; + return ret; } int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, @@ -3770,9 +3804,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, int ret; struct btrfs_device *dev; unsigned int nofs_flag; - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3819,13 +3850,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (IS_ERR(sctx)) return PTR_ERR(sctx); + ret = scrub_workers_get(fs_info, is_dev_replace); + if (ret) + goto out_free_ctx; + mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -ENODEV; - goto out_free_ctx; + goto out; } if (!is_dev_replace && !readonly && @@ -3834,7 +3869,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", rcu_str_deref(dev->name)); ret = -EROFS; - goto out_free_ctx; + goto out; } mutex_lock(&fs_info->scrub_lock); @@ -3843,7 +3878,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EIO; - goto out_free_ctx; + goto out; } down_read(&fs_info->dev_replace.rwsem); @@ -3854,17 +3889,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EINPROGRESS; - goto out_free_ctx; + goto out; } up_read(&fs_info->dev_replace.rwsem); - ret = scrub_workers_get(fs_info, is_dev_replace); - if (ret) { - mutex_unlock(&fs_info->scrub_lock); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - goto out_free_ctx; - } - sctx->readonly = readonly; dev->scrub_ctx = sctx; mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3917,24 +3945,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_lock(&fs_info->scrub_lock); dev->scrub_ctx = NULL; - if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) { - scrub_workers = fs_info->scrub_workers; - scrub_wr_comp = fs_info->scrub_wr_completion_workers; - scrub_parity = fs_info->scrub_parity_workers; - - fs_info->scrub_workers = NULL; - fs_info->scrub_wr_completion_workers = NULL; - fs_info->scrub_parity_workers = NULL; - } mutex_unlock(&fs_info->scrub_lock); - btrfs_destroy_workqueue(scrub_workers); - btrfs_destroy_workqueue(scrub_wr_comp); - btrfs_destroy_workqueue(scrub_parity); + scrub_workers_put(fs_info); scrub_put_ctx(sctx); return ret; - +out: + scrub_workers_put(fs_info); out_free_ctx: scrub_free_ctx(sctx); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 517b44300a05..7b1fee630f97 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -984,7 +984,7 @@ static int check_inode_item(struct extent_buffer *leaf, /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { inode_item_err(leaf, slot, - "invalid inode generation: has %llu expect [0, %llu]", + "invalid inode transid: has %llu expect [0, %llu]", btrfs_inode_transid(leaf, iitem), super_gen + 1); return -EUCLEAN; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ee96c5869f57..214856c4ccb1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4462,6 +4462,7 @@ int btrfs_uuid_scan_kthread(void *data) goto skip; } update_tree: + btrfs_release_path(path); if (!btrfs_is_empty_uuid(root_item.uuid)) { ret = btrfs_uuid_tree_add(trans, root_item.uuid, BTRFS_UUID_KEY_SUBVOL, @@ -4486,6 +4487,7 @@ update_tree: } skip: + btrfs_release_path(path); if (trans) { ret = btrfs_end_transaction(trans); trans = NULL; @@ -4493,7 +4495,6 @@ skip: break; } - btrfs_release_path(path); if (key.offset < (u64)-1) { key.offset++; } else if (key.type < BTRFS_ROOT_ITEM_KEY) { diff --git a/fs/eventpoll.c b/fs/eventpoll.c index e0decff22ae2..8107e06d7f6f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1995,9 +1995,9 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) * during ep_insert(). */ if (list_empty(&epi->ffd.file->f_tfile_llink)) { - get_file(epi->ffd.file); - list_add(&epi->ffd.file->f_tfile_llink, - &tfile_check_list); + if (get_file_rcu(epi->ffd.file)) + list_add(&epi->ffd.file->f_tfile_llink, + &tfile_check_list); } } } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 8623c815164a..305d4bc07337 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -653,8 +653,8 @@ xfs_attr_shortform_create( ASSERT(ifp->if_flags & XFS_IFINLINE); } xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); - hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data; - hdr->count = 0; + hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data; + memset(hdr, 0, sizeof(*hdr)); hdr->totsize = cpu_to_be16(sizeof(*hdr)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } @@ -1036,8 +1036,10 @@ xfs_attr_shortform_verify( * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. + * xfs_attr_sf_entry is defined with a 1-byte variable + * array at the end, so we must subtract that off. */ - if (((char *)sfep + sizeof(*sfep)) >= endp) + if (((char *)sfep + sizeof(*sfep) - 1) >= endp) return __this_address; /* Don't allow names with known bad length. */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index f742a96a2fe1..a6b37db55169 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -688,7 +688,7 @@ xfs_ialloc_ag_alloc( args.minalignslop = igeo->cluster_align - 1; /* Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; @@ -736,7 +736,7 @@ xfs_ialloc_ag_alloc( /* * Allow space for the inode btree to split. */ - args.minleft = igeo->inobt_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels; if ((error = xfs_alloc_vextent(&args))) return error; } diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index c6df01a2a158..7ad3659c5d2a 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -58,7 +58,7 @@ #define XFS_IALLOC_SPACE_RES(mp) \ (M_IGEO(mp)->ialloc_blks + \ ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \ - (M_IGEO(mp)->inobt_maxlevels - 1))) + M_IGEO(mp)->inobt_maxlevels)) /* * Space reservation values for various transactions. diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 73cafc843cd7..5123f82f2477 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1165,7 +1165,7 @@ xfs_insert_file_space( goto out_trans_cancel; do { - error = xfs_trans_roll_inode(&tp, ip); + error = xfs_defer_finish(&tp); if (error) goto out_trans_cancel; diff --git a/include/linux/hid.h b/include/linux/hid.h index 875f71132b14..c7044a14200e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -959,34 +959,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type + * + * The value pointed to by @bit will be set to NULL if either @type is + * an unhandled event type, or if @c is out of range for @type. This + * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, - __u8 type, __u16 c) + __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; - - usage->type = type; - usage->code = c; + unsigned long *bmap = NULL; + unsigned int limit = 0; switch (type) { case EV_ABS: - *bit = input->absbit; - *max = ABS_MAX; + bmap = input->absbit; + limit = ABS_MAX; break; case EV_REL: - *bit = input->relbit; - *max = REL_MAX; + bmap = input->relbit; + limit = REL_MAX; break; case EV_KEY: - *bit = input->keybit; - *max = KEY_MAX; + bmap = input->keybit; + limit = KEY_MAX; break; case EV_LED: - *bit = input->ledbit; - *max = LED_MAX; + bmap = input->ledbit; + limit = LED_MAX; break; } + + if (unlikely(c > limit || !bmap)) { + pr_warn_ratelimited("%s: Invalid code %d type %d\n", + input->name, c, type); + *bit = NULL; + return; + } + + usage->type = type; + usage->code = c; + *max = limit; + *bit = bmap; } /** @@ -1000,7 +1015,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); - clear_bit(c, *bit); + if (*bit) + clear_bit(usage->code, *bit); } /** diff --git a/include/linux/ksm.h b/include/linux/ksm.h index e48b1e453ff5..161e8164abcf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -53,8 +53,6 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address); #else /* !CONFIG_KSM */ @@ -88,11 +86,6 @@ static inline void rmap_walk_ksm(struct page *page, static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) { } -static inline bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - return false; -} #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 9a33f171aa82..625f491b95de 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,8 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 last_dir; + u8 flags; }; #endif /* _NF_CONNTRACK_SCTP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 851425c3178f..89016d08f6a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -43,8 +43,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags); +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid); static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ab57cf787c1f..ed9bea924dc3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -71,7 +71,7 @@ * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or - * IPv4|UDP where the Next Header field in the IPv6 + * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with @@ -1056,7 +1056,16 @@ void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); + +#ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); +#else +static inline void consume_skb(struct sk_buff *skb) +{ + return kfree_skb(skb); +} +#endif + void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; @@ -2658,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. - * get_rps_cpus() for example only access one 64 bytes aligned block : + * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 2e6ca53b9bbd..18e75974d4e3 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFAULT, PGMAJFAULT, PGLAZYFREED, PGREFILL, + PGREUSE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSCAN_KSWAPD, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 91eacbdcf33d..f6abcc0bbd6e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 9205a76d967a..38e4094960ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -494,7 +494,7 @@ int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bf9491b77d16..224d194ad29d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -143,6 +143,8 @@ static inline u64 nft_reg_load64(const u32 *sreg) static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { + if (len % NFT_REG32_SIZE) + dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 059b6e45a028..c33079b986e8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -138,11 +138,16 @@ enum rxrpc_recvmsg_trace { }; enum rxrpc_rtt_tx_trace { + rxrpc_rtt_tx_cancel, rxrpc_rtt_tx_data, + rxrpc_rtt_tx_no_slot, rxrpc_rtt_tx_ping, }; enum rxrpc_rtt_rx_trace { + rxrpc_rtt_rx_cancel, + rxrpc_rtt_rx_lost, + rxrpc_rtt_rx_obsolete, rxrpc_rtt_rx_ping_response, rxrpc_rtt_rx_requested_ack, }; @@ -339,10 +344,15 @@ enum rxrpc_tx_point { E_(rxrpc_recvmsg_wait, "WAIT") #define rxrpc_rtt_tx_traces \ + EM(rxrpc_rtt_tx_cancel, "CNCE") \ EM(rxrpc_rtt_tx_data, "DATA") \ + EM(rxrpc_rtt_tx_no_slot, "FULL") \ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ + EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_obsolete, "OBSL") \ + EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ E_(rxrpc_rtt_rx_requested_ack, "RACK") @@ -1087,38 +1097,43 @@ TRACE_EVENT(rxrpc_recvmsg, TRACE_EVENT(rxrpc_rtt_tx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_tx_trace why, - rxrpc_serial_t send_serial), + int slot, rxrpc_serial_t send_serial), - TP_ARGS(call, why, send_serial), + TP_ARGS(call, why, slot, send_serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_tx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; ), - TP_printk("c=%08x %s sr=%08x", + TP_printk("c=%08x [%d] %s sr=%08x", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_tx_traces), __entry->send_serial) ); TRACE_EVENT(rxrpc_rtt_rx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, u32 rtt, u32 rto), - TP_ARGS(call, why, send_serial, resp_serial, rtt, rto), + TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_rx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) __field(rxrpc_serial_t, resp_serial ) __field(u32, rtt ) @@ -1128,14 +1143,16 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; __entry->resp_serial = resp_serial; __entry->rtt = rtt; __entry->rto = rto; ), - TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u", + TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_rx_traces), __entry->send_serial, __entry->resp_serial, diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 3d0d8231dc19..7d6687618d80 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -135,7 +135,7 @@ struct in_addr { * this socket to prevent accepting spoofed ones. */ #define IP_PMTUDISC_INTERFACE 4 -/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get +/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get * fragmented if they exeed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 42f351c1f5c5..2b8e12f7a4a6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -133,7 +133,7 @@ enum nf_tables_msg_types { * @NFTA_LIST_ELEM: list element (NLA_NESTED) */ enum nft_list_attributes { - NFTA_LIST_UNPEC, + NFTA_LIST_UNSPEC, NFTA_LIST_ELEM, __NFTA_LIST_MAX }; diff --git a/init/initramfs.c b/init/initramfs.c index e6dbfb767057..1f97c0328a7a 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -297,7 +297,7 @@ static void __init clean_path(char *path, umode_t fmode) { struct kstat st; - if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && + if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && (st.mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.mode)) init_rmdir(path); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1bf960aa615c..b999e7ff2583 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2634,7 +2634,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); - if (ulen && !ubuf) + if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 3110c77230c7..bb4b680e8455 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,6 +4,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS + depends on !CC_IS_GCC || GCC_VERSION < 100000 select CONSTRUCTORS if !UML default n help diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 287862f91717..09e70ee2332e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -204,8 +204,7 @@ static int max_extfrag_threshold = 1000; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL) static int bpf_stats_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; @@ -381,22 +381,13 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, } /* - * FOLL_FORCE or a forced COW break can write even to unwritable pte's, - * but only after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) { - return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte)); -} - -/* - * A (separate) COW fault might break the page the other way and - * get_user_pages() would return the page from what is now the wrong - * VM. So we need to force a COW break at GUP time even for reads. - */ -static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags) -{ - return is_cow_mapping(vma->vm_flags) && (flags & (FOLL_GET | FOLL_PIN)); + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -843,7 +834,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(*pte); } - if (unlikely(!try_get_page(*page))) { + if (unlikely(!try_grab_page(*page, gup_flags))) { ret = -ENOMEM; goto unmap; } @@ -1067,11 +1058,9 @@ static long __get_user_pages(struct mm_struct *mm, goto out; } if (is_vm_hugetlb_page(vma)) { - if (should_force_cow_break(vma, foll_flags)) - foll_flags |= FOLL_WRITE; i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, - foll_flags, locked); + gup_flags, locked); if (locked && *locked == 0) { /* * We've got a VM_FAULT_RETRY @@ -1085,10 +1074,6 @@ static long __get_user_pages(struct mm_struct *mm, continue; } } - - if (should_force_cow_break(vma, foll_flags)) - foll_flags |= FOLL_WRITE; - retry: /* * If we have a pending SIGKILL, don't keep faulting pages and @@ -2689,19 +2674,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, return -EFAULT; /* - * The FAST_GUP case requires FOLL_WRITE even for pure reads, - * because get_user_pages() may need to cause an early COW in - * order to avoid confusing the normal COW routines. So only - * targets that are already writable are safe to do by just - * looking at the page tables. - * - * NOTE! With FOLL_FAST_ONLY we allow read-only gup_fast() here, - * because there is no slow path to fall back on. But you'd - * better be careful about possible COW pages - you'll get _a_ - * COW page, but not necessarily the one you intended to get - * depending on what COW event happens after this. COW may break - * the page copy in a random direction. - * * Disable interrupts. The nested form is used, in order to allow * full, general purpose use of this routine. * @@ -2714,8 +2686,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, */ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) { unsigned long fast_flags = gup_flags; - if (!(gup_flags & FOLL_FAST_ONLY)) - fast_flags |= FOLL_WRITE; local_irq_save(flags); gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2ccff8472cd4..7ff29cc3d55c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1291,12 +1291,13 @@ fallback: } /* - * FOLL_FORCE or a forced COW break can write even to unwritable pmd's, - * but only after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) { - return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd)); + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -2661,31 +2661,6 @@ again: goto again; } -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, - unsigned long address) -{ -#ifdef CONFIG_DEBUG_VM - if (WARN_ON(is_zero_pfn(page_to_pfn(page))) || - WARN_ON(!page_mapped(page)) || - WARN_ON(!PageLocked(page))) { - dump_page(page, "reuse_ksm_page"); - return false; - } -#endif - - if (PageSwapCache(page) || !page_stable_node(page)) - return false; - /* Prohibit parallel get_ksm_page() */ - if (!page_ref_freeze(page, 1)) - return false; - - page_move_anon_rmap(page, vma); - page->index = linear_page_index(vma, address); - page_ref_unfreeze(page, 1); - - return true; -} #ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { diff --git a/mm/memory.c b/mm/memory.c index 602f4283122f..148eafb8cbb1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2622,6 +2622,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf) if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); + count_vm_event(PGREUSE); } /* @@ -2927,50 +2928,25 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * not dirty accountable. */ if (PageAnon(vmf->page)) { - int total_map_swapcount; - if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) || - page_count(vmf->page) != 1)) + struct page *page = vmf->page; + + /* PageKsm() doesn't necessarily raise the page refcount */ + if (PageKsm(page) || page_count(page) != 1) + goto copy; + if (!trylock_page(page)) + goto copy; + if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { + unlock_page(page); goto copy; - if (!trylock_page(vmf->page)) { - get_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - lock_page(vmf->page); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (!pte_same(*vmf->pte, vmf->orig_pte)) { - update_mmu_tlb(vma, vmf->address, vmf->pte); - unlock_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - put_page(vmf->page); - return 0; - } - put_page(vmf->page); - } - if (PageKsm(vmf->page)) { - bool reused = reuse_ksm_page(vmf->page, vmf->vma, - vmf->address); - unlock_page(vmf->page); - if (!reused) - goto copy; - wp_page_reuse(vmf); - return VM_FAULT_WRITE; - } - if (reuse_swap_page(vmf->page, &total_map_swapcount)) { - if (total_map_swapcount == 1) { - /* - * The page is all ours. Move it to - * our anon_vma so the rmap code will - * not search our parent or siblings. - * Protected against the rmap code by - * the page lock. - */ - page_move_anon_rmap(vmf->page, vma); - } - unlock_page(vmf->page); - wp_page_reuse(vmf); - return VM_FAULT_WRITE; } - unlock_page(vmf->page); + /* + * Ok, we've got the only map reference, and the only + * page count reference, and the page is locked, + * it's dark out, and we're wearing sunglasses. Hit it. + */ + wp_page_reuse(vmf); + unlock_page(page); + return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); diff --git a/mm/vmstat.c b/mm/vmstat.c index e670f910cd2f..4f7b4ee6aa12 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1241,6 +1241,7 @@ const char * const vmstat_text[] = { "pglazyfreed", "pgrefill", + "pgreuse", "pgsteal_kswapd", "pgsteal_direct", "pgscan_kswapd", diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 0f8495b9eeb1..717fe657561d 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -881,6 +881,12 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl, ogm_packet->version, ntohs(ogm_packet->tvlv_len)); + if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from ourself\n"); + return; + } + /* If the throughput metric is 0, immediately drop the packet. No need * to create orig_node / neigh_node for an unusable route. */ @@ -1008,11 +1014,6 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; - ogm_packet = (struct batadv_ogm2_packet *)skb->data; - - if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) - goto free_skb; - batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 91a04ca373dc..8500f56cbd10 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -437,7 +437,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); - netif_rx(skb); + if (in_interrupt()) + netif_rx(skb); + else + netif_rx_ni(skb); out: if (primary_if) batadv_hardif_put(primary_if); diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index a18dcc686dc3..ef3f85b576c4 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -703,8 +703,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET; /* store the client address if the message is going to a client */ - if (ret == BATADV_DHCP_TO_CLIENT && - pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) { + if (ret == BATADV_DHCP_TO_CLIENT) { + if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) + return BATADV_DHCP_NO; + /* check if the DHCP packet carries an Ethernet DHCP */ p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET; if (*p != BATADV_DHCP_HTYPE_ETHERNET) diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index ce2767e9cec6..7b0af33bdb97 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -116,7 +116,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) if (segmented) { if (rfml->incomplete_frm == NULL) { /* Initial Segment */ - if (cfpkt_peek_head(pkt, rfml->seghead, 6) < 0) + if (cfpkt_peek_head(pkt, rfml->seghead, 6) != 0) goto out; rfml->pdu_size = get_unaligned_le16(rfml->seghead+4); @@ -233,7 +233,7 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > rfml->fragment_size + RFM_HEAD_SIZE) err = cfpkt_peek_head(pkt, head, 6); - if (err < 0) + if (err != 0) goto out; while (cfpkt_getlen(frontpkt) > rfml->fragment_size + RFM_HEAD_SIZE) { diff --git a/net/core/dev.c b/net/core/dev.c index b9c6f31ae96e..4086d335978c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6612,12 +6612,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; - list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + set_bit(NAPI_STATE_NPSVC, &napi->state); + list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); } EXPORT_SYMBOL(netif_napi_add); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 093e90e52bc2..2338753e936b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ static void poll_napi(struct net_device *dev) struct napi_struct *napi; int cpu = smp_processor_id(); - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 95f4c6b8f51a..44fdbb9c6e53 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3699,7 +3699,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) cpu_to_node(cpu), "kpktgend_%d", cpu); if (IS_ERR(p)) { - pr_err("kernel_thread() failed for cpu %d\n", t->cpu); + pr_err("kthread_create_on_node() failed for cpu %d\n", t->cpu); list_del(&t->th_list); kfree(t); return PTR_ERR(p); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e18184ffa9c3..6faf73d6a0f7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -820,6 +820,7 @@ void skb_tx_error(struct sk_buff *skb) } EXPORT_SYMBOL(skb_tx_error); +#ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free @@ -837,6 +838,7 @@ void consume_skb(struct sk_buff *skb) __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); +#endif /** * consume_stateless_skb - free an skbuff, assuming it is stateless diff --git a/net/core/sock.c b/net/core/sock.c index f8e5ccc45272..6c5c6b18eff4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3254,7 +3254,7 @@ void sk_common_release(struct sock *sk) sk->sk_prot->destroy(sk); /* - * Observation: when sock_common_release is called, processes have + * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c89b46fec153..ffc5332f1390 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2121,7 +2121,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist) + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 7afde8828b4c..3f248a19faa3 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -3,7 +3,7 @@ * nf_nat_pptp.c * * NAT support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6fd4330287c2..407956be7deb 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { - /* oif is set, packet is to local broadcast and + /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index fac2135aa47b..5b60a4bdd36a 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -21,6 +21,7 @@ #include <net/calipso.h> #endif +static int two = 2; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; @@ -150,7 +151,7 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "seg6_flowlabel", diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index e71ca5aec684..864326f150e2 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** - * l3mdev_fib_table - get FIB table id associated with an L3 + * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 366f76c9003d..314973033d03 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -405,18 +405,14 @@ ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre, return duration; } -u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, - struct ieee80211_rx_status *status, - int len) +static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + u32 *overhead) { - struct ieee80211_supported_band *sband; - const struct ieee80211_rate *rate; bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI; - bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; int bw, streams; int group, idx; u32 duration; - bool cck; switch (status->bw) { case RATE_INFO_BW_20: @@ -437,20 +433,6 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, } switch (status->encoding) { - case RX_ENC_LEGACY: - if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) - return 0; - - sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx >= sband->n_bitrates) - return 0; - - rate = &sband->bitrates[status->rate_idx]; - cck = rate->flags & IEEE80211_RATE_MANDATORY_B; - - return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, - cck, len); - case RX_ENC_VHT: streams = status->nss; idx = status->rate_idx; @@ -477,51 +459,144 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; + *overhead = 36 + (streams << 2); + + return duration; +} + + +u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + int len) +{ + struct ieee80211_supported_band *sband; + u32 duration, overhead = 0; + + if (status->encoding == RX_ENC_LEGACY) { + const struct ieee80211_rate *rate; + bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; + bool cck; + + if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) + return 0; + + sband = hw->wiphy->bands[status->band]; + if (!sband || status->rate_idx >= sband->n_bitrates) + return 0; + + rate = &sband->bitrates[status->rate_idx]; + cck = rate->flags & IEEE80211_RATE_MANDATORY_B; + + return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, + cck, len); + } + + duration = ieee80211_get_rate_duration(hw, status, &overhead); + if (!duration) + return 0; + duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; - duration += 36 + (streams << 2); - - return duration; + return duration + overhead; } EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime); -static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, - struct ieee80211_tx_rate *rate, - u8 band, int len) +static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, + struct ieee80211_rx_status *stat, u8 band, + struct rate_info *ri) { - struct ieee80211_rx_status stat = { - .band = band, - }; + struct ieee80211_supported_band *sband = hw->wiphy->bands[band]; + int i; - if (rate->idx < 0 || !rate->count) + if (!ri || !sband) + return false; + + stat->bw = ri->bw; + stat->nss = ri->nss; + stat->rate_idx = ri->mcs; + + if (ri->flags & RATE_INFO_FLAGS_HE_MCS) + stat->encoding = RX_ENC_HE; + else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS) + stat->encoding = RX_ENC_VHT; + else if (ri->flags & RATE_INFO_FLAGS_MCS) + stat->encoding = RX_ENC_HT; + else + stat->encoding = RX_ENC_LEGACY; + + if (ri->flags & RATE_INFO_FLAGS_SHORT_GI) + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; + + stat->he_gi = ri->he_gi; + + if (stat->encoding != RX_ENC_LEGACY) + return true; + + stat->rate_idx = 0; + for (i = 0; i < sband->n_bitrates; i++) { + if (ri->legacy != sband->bitrates[i].bitrate) + continue; + + stat->rate_idx = i; + return true; + } + + return false; +} + +static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, + struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, u8 band, int len) +{ + memset(stat, 0, sizeof(*stat)); + stat->band = band; + + if (ieee80211_fill_rate_info(hw, stat, band, ri)) return 0; + if (rate->idx < 0 || !rate->count) + return -1; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_80; + stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_40; + stat->bw = RATE_INFO_BW_40; else - stat.bw = RATE_INFO_BW_20; + stat->bw = RATE_INFO_BW_20; - stat.enc_flags = 0; + stat->enc_flags = 0; if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) - stat.enc_flags |= RX_ENC_FLAG_SHORTPRE; + stat->enc_flags |= RX_ENC_FLAG_SHORTPRE; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) - stat.enc_flags |= RX_ENC_FLAG_SHORT_GI; + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; - stat.rate_idx = rate->idx; + stat->rate_idx = rate->idx; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { - stat.encoding = RX_ENC_VHT; - stat.rate_idx = ieee80211_rate_get_vht_mcs(rate); - stat.nss = ieee80211_rate_get_vht_nss(rate); + stat->encoding = RX_ENC_VHT; + stat->rate_idx = ieee80211_rate_get_vht_mcs(rate); + stat->nss = ieee80211_rate_get_vht_nss(rate); } else if (rate->flags & IEEE80211_TX_RC_MCS) { - stat.encoding = RX_ENC_HT; + stat->encoding = RX_ENC_HT; } else { - stat.encoding = RX_ENC_LEGACY; + stat->encoding = RX_ENC_LEGACY; } + return 0; +} + +static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, + u8 band, int len) +{ + struct ieee80211_rx_status stat; + + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + return ieee80211_calc_rx_airtime(hw, &stat, len); } @@ -536,7 +611,7 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_rate *rate = &info->status.rates[i]; u32 cur_duration; - cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, + cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, NULL, info->band, len); if (!cur_duration) break; @@ -572,26 +647,41 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, if (pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_rx_status stat; struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; - u32 airtime; + struct rate_info *ri = &sta->tx_stats.last_rate_info; + u32 duration, overhead; + u8 agg_shift; - if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS | - IEEE80211_TX_RC_MCS))) - ampdu = false; + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + if (stat.encoding == RX_ENC_LEGACY || !ampdu) + return ieee80211_calc_rx_airtime(hw, &stat, len); + + duration = ieee80211_get_rate_duration(hw, &stat, &overhead); /* * Assume that HT/VHT transmission on any AC except VO will * use aggregation. Since we don't have reliable reporting - * of aggregation length, assume an average of 16. + * of aggregation length, assume an average size based on the + * tx rate. * This will not be very accurate, but much better than simply - * assuming un-aggregated tx. + * assuming un-aggregated tx in all cases. */ - airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band, - ampdu ? len * 16 : len); - if (ampdu) - airtime /= 16; - - return airtime; + if (duration > 400) /* <= VHT20 MCS2 1S */ + agg_shift = 1; + else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + agg_shift = 2; + else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + agg_shift = 3; + else + agg_shift = 4; + + duration *= len; + duration /= AVG_PKT_SIZE; + duration /= 1024; + + return duration + (overhead >> agg_shift); } if (!conf) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9d398c9daa4c..d5010116cf4d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -524,7 +524,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.retry_failed: # of frames that failed after retry * @status_stats.retry_count: # of retries attempted * @status_stats.lost_packets: # of lost packets - * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.last_pkt_time: timestamp of last ACKed packet * @status_stats.msdu_retries: # of MSDU retries * @status_stats.msdu_failed: # of failed MSDUs * @status_stats.last_ack: last ack timestamp (jiffies) @@ -597,7 +597,7 @@ struct sta_info { unsigned long filtered; unsigned long retry_failed, retry_count; unsigned int lost_packets; - unsigned long last_tdls_pkt_time; + unsigned long last_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; @@ -611,6 +611,7 @@ struct sta_info { u64 packets[IEEE80211_NUM_ACS]; u64 bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_rate; + struct rate_info last_rate_info; u64 msdu[IEEE80211_NUM_TIDS + 1]; } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index adb1d30ce06e..0794396a7988 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -755,12 +755,16 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, * - current throughput (higher value for higher tpt)? */ #define STA_LOST_PKT_THRESHOLD 50 +#define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ #define STA_LOST_TDLS_PKT_THRESHOLD 10 #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { + unsigned long pkt_time = STA_LOST_PKT_TIME; + unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD; + /* If driver relies on its own algorithm for station kickout, skip * mac80211 packet loss mechanism. */ @@ -773,21 +777,20 @@ static void ieee80211_lost_packet(struct sta_info *sta, return; sta->status_stats.lost_packets++; - if (!sta->sta.tdls && - sta->status_stats.lost_packets < STA_LOST_PKT_THRESHOLD) - return; + if (sta->sta.tdls) { + pkt_time = STA_LOST_TDLS_PKT_TIME; + pkt_thr = STA_LOST_PKT_THRESHOLD; + } /* * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. + * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME */ - if (sta->sta.tdls && - (sta->status_stats.lost_packets < STA_LOST_TDLS_PKT_THRESHOLD || - time_before(jiffies, - sta->status_stats.last_tdls_pkt_time + - STA_LOST_TDLS_PKT_TIME))) + if (sta->status_stats.lost_packets < pkt_thr || + !time_after(jiffies, sta->status_stats.last_pkt_time + pkt_time)) return; cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, @@ -1033,9 +1036,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, sta->status_stats.lost_packets = 0; /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = - jiffies; + sta->status_stats.last_pkt_time = jiffies; } else if (noack_success) { /* nothing to do here, do not account as lost */ } else { @@ -1137,9 +1138,17 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; struct ieee80211_supported_band *sband; + struct sta_info *sta; int retry_count; bool acked, noack_success; + if (pubsta) { + sta = container_of(pubsta, struct sta_info, sta); + + if (status->rate) + sta->tx_stats.last_rate_info = *status->rate; + } + if (status->skb) return __ieee80211_tx_status(hw, status); @@ -1154,10 +1163,6 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); if (pubsta) { - struct sta_info *sta; - - sta = container_of(pubsta, struct sta_info, sta); - if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1168,9 +1173,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + /* Track when last packet was ACKed */ + sta->status_stats.last_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; } else if (noack_success) { @@ -1259,8 +1263,7 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + sta->status_stats.last_pkt_time = jiffies; } else { ieee80211_lost_packet(sta, info); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 49b815023986..365ba96c84b0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -891,7 +891,6 @@ restart: goto out; } -wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); while (!sk_stream_memory_free(sk) || @@ -981,7 +980,7 @@ wait_for_sndbuf: */ mptcp_set_timeout(sk, ssk); release_sock(ssk); - goto wait_for_sndbuf; + goto restart; } } } diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 1f44d523b512..5105d4250012 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Connection tracking support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 4f897b14b606..810cca24b399 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -62,6 +62,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; +#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 + #define sNO SCTP_CONNTRACK_NONE #define sCL SCTP_CONNTRACK_CLOSED #define sCW SCTP_CONNTRACK_COOKIE_WAIT @@ -369,6 +371,7 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; + bool ignore = false; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -427,15 +430,39 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* Sec 8.5.1 (D) */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; - } else if (sch->type == SCTP_CID_HEARTBEAT || - sch->type == SCTP_CID_HEARTBEAT_ACK) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + ct->proto.sctp.flags |= SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.last_dir = dir; + ignore = true; + continue; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + } + } else if (sch->type == SCTP_CID_HEARTBEAT_ACK) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); ct->proto.sctp.vtag[dir] = sh->vtag; } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out_unlock; + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + if ((ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) == 0 || + ct->proto.sctp.last_dir == dir) + goto out_unlock; + + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.vtag[dir] = sh->vtag; + ct->proto.sctp.vtag[!dir] = 0; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } } @@ -470,6 +497,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); + /* allow but do not refresh timeout */ + if (ignore) + return NF_ACCEPT; + timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 6892e497781c..e8c86ee4c1c4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1152,7 +1152,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { - /* Set ASSURED if we see see valid ack in ESTABLISHED + /* Set ASSURED if we see valid ack in ESTABLISHED after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 760ca2422816..af402f458ee0 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,18 +81,6 @@ static bool udp_error(struct sk_buff *skb, return false; } -static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, - struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - u32 extra_jiffies) -{ - if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && - ct->status & IPS_NAT_CLASH)) - nf_ct_kill(ct); - else - nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); -} - /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -124,12 +112,15 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, extra); + /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -206,12 +197,15 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_REPLIED]); + + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd814e514f94..b7dc1cbf40ea 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -815,11 +815,11 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, family, table); if (err < 0) - goto err; + goto err_fill_table_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_table_info: kfree_skb(skb2); return err; } @@ -1563,11 +1563,11 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, family, table, chain); if (err < 0) - goto err; + goto err_fill_chain_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_chain_info: kfree_skb(skb2); return err; } @@ -3008,11 +3008,11 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, NULL); if (err < 0) - goto err; + goto err_fill_rule_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_rule_info: kfree_skb(skb2); return err; } @@ -3770,7 +3770,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } - if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) + if (set->udata && + nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); @@ -3967,11 +3968,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) - goto err; + goto err_fill_set_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_set_info: kfree_skb(skb2); return err; } @@ -4859,24 +4860,18 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) - goto err1; + return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, &elem); if (err < 0) - goto err2; + goto err_fill_setelem; - err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT); - /* This avoids a loop in nfnetlink. */ - if (err < 0) - goto err1; + return nfnetlink_unicast(skb, ctx->net, ctx->portid); - return 0; -err2: +err_fill_setelem: kfree_skb(skb); -err1: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return err; } /* called with rcu_read_lock held */ @@ -6181,10 +6176,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) - goto err; + goto err_fill_obj_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_obj_info: kfree_skb(skb2); return err; } @@ -7044,10 +7040,11 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, &flowtable->hook_list); if (err < 0) - goto err; + goto err_fill_flowtable_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_flowtable_info: kfree_skb(skb2); return err; } @@ -7233,10 +7230,11 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq); if (err < 0) - goto err; + goto err_fill_gen_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_gen_info: kfree_skb(skb2); return err; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 5f24edf95830..3a2e64e13b22 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -149,10 +149,15 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) } EXPORT_SYMBOL_GPL(nfnetlink_set_err); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags) +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { - return netlink_unicast(net->nfnl, skb, portid, flags); + int err; + + err = nlmsg_unicast(net->nfnl, skb, portid); + if (err == -EAGAIN) + err = -ENOBUFS; + + return err; } EXPORT_SYMBOL_GPL(nfnetlink_unicast); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f02992419850..b35e8d9a5b37 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -356,8 +356,7 @@ __nfulnl_send(struct nfulnl_instance *inst) goto out; } } - nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index dadfc06245a3..d1d8bca03b4f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -681,7 +681,7 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3b9b97aa4b32..3a6c84fb2c90 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -102,7 +102,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || - ct->status & IPS_SEQ_ADJUST) + ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index ed7cb9f747f6..7a2e59638499 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -87,7 +87,9 @@ void nft_payload_eval(const struct nft_expr *expr, u32 *dest = ®s->data[priv->dreg]; int offset; - dest[priv->len / NFT_REG32_SIZE] = 0; + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 4b2834fd17b2..217ab3644c25 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -218,11 +218,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { + bool overlap = false, dup_end_left = false, dup_end_right = false; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; - bool overlap = false; int d; /* Detect overlaps as we descend the tree. Set the flag in these cases: @@ -238,24 +238,44 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * * b1. _ _ __>| !_ _ __| (insert end before existing start) * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end) + * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) + * '--' no nodes falling in this range + * b4. >|_ _ ! (insert start before existing start) * * Case a3. resolves to b3.: * - if the inserted start element is the leftmost, because the '0' * element in the tree serves as end element - * - otherwise, if an existing end is found. Note that end elements are - * always inserted after corresponding start elements. + * - otherwise, if an existing end is found immediately to the left. If + * there are existing nodes in between, we need to further descend the + * tree before we can conclude the new start isn't causing an overlap + * + * or to b4., which, preceded by a3., means we already traversed one or + * more existing intervals entirely, from the right. * * For a new, rightmost pair of elements, we'll hit cases b3. and b2., * in that order. * * The flag is also cleared in two special cases: * - * b4. |__ _ _!|<_ _ _ (insert start right before existing end) - * b5. |__ _ >|!__ _ _ (insert end right after existing start) + * b5. |__ _ _!|<_ _ _ (insert start right before existing end) + * b6. |__ _ >|!__ _ _ (insert end right after existing start) * * which always happen as last step and imply that no further * overlapping is possible. + * + * Another special case comes from the fact that start elements matching + * an already existing start element are allowed: insertion is not + * performed but we return -EEXIST in that case, and the error will be + * cleared by the caller if NLM_F_EXCL is not present in the request. + * This way, request for insertion of an exact overlap isn't reported as + * error to userspace if not desired. + * + * However, if the existing start matches a pre-existing start, but the + * end element doesn't match the corresponding pre-existing end element, + * we need to report a partial overlap. This is a local condition that + * can be noticed without need for a tracking flag, by checking for a + * local duplicated end for a corresponding start, from left and right, + * separately. */ parent = NULL; @@ -272,26 +292,41 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) + !nft_set_elem_expired(&rbe->ext) && !*p) overlap = false; } else { + if (dup_end_left && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); + + if (overlap) { + dup_end_right = true; + continue; + } } } else if (d > 0) { p = &parent->rb_right; if (nft_rbtree_interval_end(new)) { + if (dup_end_right && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); - } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && + + if (overlap) { + dup_end_left = true; + continue; + } + } else if (nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext)) { - overlap = true; + overlap = nft_rbtree_interval_end(rbe); } } else { if (nft_rbtree_interval_end(rbe) && @@ -316,6 +351,8 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_left; } } + + dup_end_left = dup_end_right = false; } if (overlap) diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 19bef176145e..606411869698 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -640,7 +640,7 @@ static void __net_exit recent_proc_net_exit(struct net *net) struct recent_table *t; /* recent_net_exit() is called before recent_mt_destroy(). Make sure - * that the parent xt_recent proc entry is is empty before trying to + * that the parent xt_recent proc entry is empty before trying to * remove it. */ spin_lock_bh(&recent_lock); diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d07de2c0fbc7..f73a8382c275 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -85,6 +85,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) kfree(netlbl_domhsh_addr6_entry(iter6)); } #endif /* IPv6 */ + kfree(ptr->def.addrsel); } kfree(ptr->domain); kfree(ptr); @@ -537,6 +538,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, goto add_return; } #endif /* IPv6 */ + /* cleanup the new entry since we've moved everything over */ + netlbl_domhsh_free_entry(&entry->rcu); } else ret_val = -EINVAL; @@ -580,6 +583,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, { int ret_val = 0; struct audit_buffer *audit_buf; + struct netlbl_af4list *iter4; + struct netlbl_domaddr4_map *map4; +#if IS_ENABLED(CONFIG_IPV6) + struct netlbl_af6list *iter6; + struct netlbl_domaddr6_map *map6; +#endif /* IPv6 */ if (entry == NULL) return -ENOENT; @@ -597,6 +606,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, ret_val = -ENOENT; spin_unlock(&netlbl_domhsh_lock); + if (ret_val) + return ret_val; + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, @@ -606,40 +618,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, audit_log_end(audit_buf); } - if (ret_val == 0) { - struct netlbl_af4list *iter4; - struct netlbl_domaddr4_map *map4; -#if IS_ENABLED(CONFIG_IPV6) - struct netlbl_af6list *iter6; - struct netlbl_domaddr6_map *map6; -#endif /* IPv6 */ - - switch (entry->def.type) { - case NETLBL_NLTYPE_ADDRSELECT: - netlbl_af4list_foreach_rcu(iter4, - &entry->def.addrsel->list4) { - map4 = netlbl_domhsh_addr4_entry(iter4); - cipso_v4_doi_putdef(map4->def.cipso); - } + switch (entry->def.type) { + case NETLBL_NLTYPE_ADDRSELECT: + netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) { + map4 = netlbl_domhsh_addr4_entry(iter4); + cipso_v4_doi_putdef(map4->def.cipso); + } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, - &entry->def.addrsel->list6) { - map6 = netlbl_domhsh_addr6_entry(iter6); - calipso_doi_putdef(map6->def.calipso); - } + netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { + map6 = netlbl_domhsh_addr6_entry(iter6); + calipso_doi_putdef(map6->def.calipso); + } #endif /* IPv6 */ - break; - case NETLBL_NLTYPE_CIPSOV4: - cipso_v4_doi_putdef(entry->def.cipso); - break; + break; + case NETLBL_NLTYPE_CIPSOV4: + cipso_v4_doi_putdef(entry->def.cipso); + break; #if IS_ENABLED(CONFIG_IPV6) - case NETLBL_NLTYPE_CALIPSO: - calipso_doi_putdef(entry->def.calipso); - break; + case NETLBL_NLTYPE_CALIPSO: + calipso_doi_putdef(entry->def.calipso); + break; #endif /* IPv6 */ - } - call_rcu(&entry->rcu, netlbl_domhsh_free_entry); } + call_rcu(&entry->rcu, netlbl_domhsh_free_entry); return ret_val; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b5f30d7d30d0..d2d1448274f5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -353,7 +353,7 @@ static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index da8254e680f9..2b33e977a905 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2170,7 +2170,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; @@ -2239,6 +2240,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6d29a3603a3e..884cff7bb169 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -488,7 +488,6 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ - RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ @@ -673,9 +672,13 @@ struct rxrpc_call { rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - /* ping management */ - rxrpc_serial_t ping_serial; /* Last ping sent */ - ktime_t ping_time; /* Time last ping sent */ + /* RTT management */ + rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ + ktime_t rtt_sent_at[4]; /* Time packet sent */ + unsigned long rtt_avail; /* Mask of available slots in bits 0-3, + * Mask of pending samples in 8-11 */ +#define RXRPC_CALL_RTT_AVAIL_MASK 0xf +#define RXRPC_CALL_RTT_PEND_SHIFT 8 /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -1037,7 +1040,7 @@ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, /* * rtt.c */ -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); void rxrpc_peer_init_rtt(struct rxrpc_peer *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 38a46167523f..a40fae013942 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -153,6 +153,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; call->rxnet = rxnet; + call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index fbde8b824e23..667c44aa5a63 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -608,36 +608,57 @@ unlock: } /* - * Process a requested ACK. + * See if there's a cached RTT probe to complete. */ -static void rxrpc_input_requested_ack(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t acked_serial, + rxrpc_serial_t ack_serial, + enum rxrpc_rtt_rx_trace type) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + rxrpc_serial_t orig_serial; + unsigned long avail; ktime_t sent_at; - int ix; + bool matched = false; + int i; - for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; + avail = READ_ONCE(call->rtt_avail); + smp_rmb(); /* Read avail bits before accessing data. */ - sent_at = skb->tstamp; - smp_rmb(); /* Read timestamp before serial. */ - sp = rxrpc_skb(skb); - if (sp->hdr.serial != orig_serial) + for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) { + if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail)) continue; - goto found; - } - return; + sent_at = call->rtt_sent_at[i]; + orig_serial = call->rtt_serial[i]; + + if (orig_serial == acked_serial) { + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_mb(); /* Read data before setting avail bit */ + set_bit(i, &call->rtt_avail); + if (type != rxrpc_rtt_rx_cancel) + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); + else + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, + orig_serial, acked_serial, 0, 0); + matched = true; + } + + /* If a later serial is being acked, then mark this slot as + * being available. + */ + if (after(acked_serial, orig_serial)) { + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, + orig_serial, acked_serial, 0, 0); + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); + set_bit(i, &call->rtt_avail); + } + } -found: - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, - orig_serial, ack_serial, sent_at, resp_time); + if (!matched) + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } /* @@ -682,27 +703,11 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) */ static void rxrpc_input_ping_response(struct rxrpc_call *call, ktime_t resp_time, - rxrpc_serial_t orig_serial, + rxrpc_serial_t acked_serial, rxrpc_serial_t ack_serial) { - rxrpc_serial_t ping_serial; - ktime_t ping_time; - - ping_time = call->ping_time; - smp_rmb(); - ping_serial = READ_ONCE(call->ping_serial); - - if (orig_serial == call->acks_lost_ping) + if (acked_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - - if (before(orig_serial, ping_serial) || - !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) - return; - if (after(orig_serial, ping_serial)) - return; - - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, - orig_serial, ack_serial, ping_time, resp_time); } /* @@ -843,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackinfo info; u8 acks[RXRPC_MAXACKS]; } buf; - rxrpc_serial_t acked_serial; + rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -856,6 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } offset += sizeof(buf.ack); + ack_serial = sp->hdr.serial; acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); prev_pkt = ntohl(buf.ack.previousPacket); @@ -864,31 +870,42 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); - trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, + trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) + switch (buf.ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - sp->hdr.serial); - if (buf.ack.reason == RXRPC_ACK_REQUESTED) - rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + if (acked_serial != 0) + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_cancel); + break; + } if (buf.ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", sp->hdr.serial); + _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ack); } /* Discard any out-of-order or duplicate ACKs (outside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); return; @@ -904,7 +921,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) /* Discard any out-of-order or duplicate ACKs (inside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); goto out; @@ -964,7 +981,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 1ba43c3df4ad..3cfff7922ba8 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,6 +124,49 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, } /* + * Record the beginning of an RTT probe. + */ +static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_rtt_tx_trace why) +{ + unsigned long avail = call->rtt_avail; + int rtt_slot = 9; + + if (!(avail & RXRPC_CALL_RTT_AVAIL_MASK)) + goto no_slot; + + rtt_slot = __ffs(avail & RXRPC_CALL_RTT_AVAIL_MASK); + if (!test_and_clear_bit(rtt_slot, &call->rtt_avail)) + goto no_slot; + + call->rtt_serial[rtt_slot] = serial; + call->rtt_sent_at[rtt_slot] = ktime_get_real(); + smp_wmb(); /* Write data before avail bit */ + set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + + trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); + return rtt_slot; + +no_slot: + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); + return -1; +} + +/* + * Cancel an RTT probe. + */ +static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, + rxrpc_serial_t serial, int rtt_slot) +{ + if (rtt_slot != -1) { + clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); /* Clear pending bit before setting slot */ + set_bit(rtt_slot, &call->rtt_avail); + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); + } +} + +/* * Send an ACK call packet. */ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, @@ -136,7 +179,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - int ret; + int ret, rtt_slot = -1; u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -196,18 +239,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (_serial) *_serial = serial; - if (ping) { - call->ping_serial = serial; - smp_wmb(); - /* We need to stick a time in before we send the packet in case - * the reply gets back before kernel_sendmsg() completes - but - * asking UDP to send the packet can take a relatively long - * time. - */ - call->ping_time = ktime_get_real(); - set_bit(RXRPC_CALL_PINGING, &call->flags); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); - } + if (ping) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); conn->params.peer->last_tx_at = ktime_get_seconds(); @@ -221,8 +254,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - if (ping) - clear_bit(RXRPC_CALL_PINGING, &call->flags); + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_propose_ACK(call, pkt->ack.reason, ntohl(pkt->ack.serial), false, true, @@ -321,7 +353,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, struct kvec iov[2]; rxrpc_serial_t serial; size_t len; - int ret; + int ret, rtt_slot = -1; _enter(",{%d}", skb->len); @@ -397,6 +429,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet @@ -408,12 +442,15 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + } + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -422,7 +459,6 @@ done: if (ret >= 0) { if (whdr.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = skb->tstamp; - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -469,6 +505,8 @@ send_fragmentable: sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: @@ -487,12 +525,14 @@ send_fragmentable: BUG(); } - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + } rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index ca29976bb193..68396d052052 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -502,11 +502,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer); * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer smoothed RTT. + * Get the call's peer smoothed RTT in uS. */ -u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->srtt_us >> 3; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index 928d8b34a3ee..1221b0637a7e 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -146,6 +146,7 @@ static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) * exclusive access to the peer RTT data. */ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { @@ -162,7 +163,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_count++; spin_unlock(&peer->rtt_input_lock); - trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, + trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, peer->srtt_us >> 3, peer->rto_j); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 52a24d4ef5d8..e08130e5746b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1137,7 +1137,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = -ENOMEM; ticket = kmalloc(ticket_len, GFP_NOFS); if (!ticket) - goto temporary_error; + goto temporary_error_free_resp; eproto = tracepoint_string("rxkad_tkt_short"); abort_code = RXKADPACKETSHORT; @@ -1230,6 +1230,7 @@ protocol_error: temporary_error_free_ticket: kfree(ticket); +temporary_error_free_resp: kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index deac82f3ad7b..e89fab6ccb34 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -353,23 +353,11 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) - goto err_early_drop_init; - - err = tcf_qevent_init(&q->qe_mark, sch, - FLOW_BLOCK_BINDER_TYPE_RED_MARK, - tb[TCA_RED_MARK_BLOCK], extack); - if (err) - goto err_mark_init; - - return 0; + return err; -err_mark_init: - tcf_qevent_destroy(&q->qe_early_drop, sch); -err_early_drop_init: - del_timer_sync(&q->adapt_timer); - red_offload(sch, false); - qdisc_put(q->qdisc); - return err; + return tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); } static int red_change(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e981992634dd..fe53c1e38c7d 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1176,9 +1176,27 @@ static void taprio_offload_config_changed(struct taprio_sched *q) spin_unlock(&q->current_entry_lock); } -static void taprio_sched_to_offload(struct taprio_sched *q, +static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) +{ + u32 i, queue_mask = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(tc_mask & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + + queue_mask |= GENMASK(offset + count - 1, offset); + } + + return queue_mask; +} + +static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - const struct tc_mqprio_qopt *mqprio, struct tc_taprio_qopt_offload *offload) { struct sched_entry *entry; @@ -1193,7 +1211,8 @@ static void taprio_sched_to_offload(struct taprio_sched *q, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = entry->gate_mask; + e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + i++; } @@ -1201,7 +1220,6 @@ static void taprio_sched_to_offload(struct taprio_sched *q, } static int taprio_enable_offload(struct net_device *dev, - struct tc_mqprio_qopt *mqprio, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) @@ -1223,7 +1241,7 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(q, sched, mqprio, offload); + taprio_sched_to_offload(dev, sched, offload); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { @@ -1485,7 +1503,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } if (FULL_OFFLOAD_IS_ENABLED(q->flags)) - err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ec1fba1fbe71..836615f71a7d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8060,8 +8060,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) pr_debug("%s: begins, snum:%d\n", __func__, snum); - local_bh_disable(); - if (snum == 0) { /* Search for an available port. */ int low, high, remaining, index; @@ -8079,20 +8077,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) continue; index = sctp_phashfn(net, rover); head = &sctp_port_hashtable[index]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(net, pp->net)) goto next; break; next: - spin_unlock(&head->lock); + spin_unlock_bh(&head->lock); + cond_resched(); } while (--remaining > 0); /* Exhausted local port range during search? */ ret = 1; if (remaining <= 0) - goto fail; + return ret; /* OK, here is the one we will use. HEAD (the port * hash table list entry) is non-NULL and we hold it's @@ -8107,7 +8106,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(net, snum)]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, net)) goto pp_found; @@ -8207,10 +8206,7 @@ success: ret = 0; fail_unlock: - spin_unlock(&head->lock); - -fail: - local_bh_enable(); + spin_unlock_bh(&head->lock); return ret; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 3b5c374c6d2c..0e7409e469c0 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -116,7 +116,6 @@ static void smc_close_cancel_work(struct smc_sock *smc) cancel_work_sync(&smc->conn.close_work); cancel_delayed_work_sync(&smc->conn.tx_work); lock_sock(sk); - sk->sk_state = SMC_CLOSED; } /* terminate smc socket abnormally - active abort @@ -134,22 +133,22 @@ void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_ACTIVE: - sk->sk_state = SMC_PEERABORTWAIT; - smc_close_cancel_work(smc); - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: + sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; - sock_put(sk); /* postponed passive closing */ + sock_put(sk); /* (postponed) passive closing */ break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; @@ -159,6 +158,8 @@ void smc_close_active_abort(struct smc_sock *smc) case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index b42fa3b00d00..a406627b1d55 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1356,6 +1356,8 @@ create: if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ + } else { + conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); @@ -1777,6 +1779,7 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) list_del(&smc->conn.sndbuf_desc->list); mutex_unlock(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); + smc->conn.sndbuf_desc = NULL; } return rc; } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index df5b0a6ea848..3ea33466ebe9 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -841,6 +841,9 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) struct smc_init_info ini; int lnk_idx, rc = 0; + if (!llc->qp_mtu) + goto out_reject; + ini.vlan_id = lgr->vlan_id; smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && @@ -917,10 +920,20 @@ out: kfree(qentry); } +static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(llc->raw.data); i++) + if (llc->raw.data[i]) + return false; + return true; +} + static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) { if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && - !llc->add_link.qp_mtu && !llc->add_link.link_num) + smc_llc_is_empty_llc_message(llc)) return true; return false; } diff --git a/net/socket.c b/net/socket.c index dbbe8ea7d395..0c0144604f81 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3610,7 +3610,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getsockname); /** - * kernel_peername - get the address which the socket is connected (kernel space) + * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * @@ -3671,7 +3671,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, EXPORT_SYMBOL(kernel_sendpage_locked); /** - * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c38babaa4e57..7c523dc81575 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -326,7 +326,8 @@ static void tipc_aead_free(struct rcu_head *rp) if (aead->cloned) { tipc_aead_put(aead->cloned); } else { - head = *this_cpu_ptr(aead->tfm_entry); + head = *get_cpu_ptr(aead->tfm_entry); + put_cpu_ptr(aead->tfm_entry); list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) { crypto_free_aead(tfm_entry->tfm); list_del(&tfm_entry->list); @@ -399,10 +400,15 @@ static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val) */ static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead) { - struct tipc_tfm **tfm_entry = this_cpu_ptr(aead->tfm_entry); + struct tipc_tfm **tfm_entry; + struct crypto_aead *tfm; + tfm_entry = get_cpu_ptr(aead->tfm_entry); *tfm_entry = list_next_entry(*tfm_entry, list); - return (*tfm_entry)->tfm; + tfm = (*tfm_entry)->tfm; + put_cpu_ptr(tfm_entry); + + return tfm; } /** diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 2679e97e0389..ebd280e767bd 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2771,18 +2771,21 @@ static int tipc_shutdown(struct socket *sock, int how) trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " "); __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN); - sk->sk_shutdown = SEND_SHUTDOWN; + if (tipc_sk_type_connectionless(sk)) + sk->sk_shutdown = SHUTDOWN_MASK; + else + sk->sk_shutdown = SEND_SHUTDOWN; if (sk->sk_state == TIPC_DISCONNECTING) { /* Discard any unreceived messages */ __skb_queue_purge(&sk->sk_receive_queue); - /* Wake up anyone sleeping in poll */ - sk->sk_state_change(sk); res = 0; } else { res = -ENOTCONN; } + /* Wake up anyone sleeping in poll. */ + sk->sk_state_change(sk); release_sock(sk); return res; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index e97a4f0c32a3..6a6f2f214c10 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -10,6 +10,7 @@ */ #include <linux/export.h> +#include <linux/bitfield.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" @@ -912,6 +913,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; + bool support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -979,9 +981,13 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - if (chandef->chan->band != NL80211_BAND_6GHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap = vht_cap->cap; + support_80_80 = + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; fallthrough; case NL80211_CHAN_WIDTH_80: @@ -1001,7 +1007,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && + !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) return false; break; default: diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fde420af3f00..2c9e9a2d1688 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6011,7 +6011,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) params.he_6ghz_capa = - nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) params.airtime_weight = diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 35b8847a2f6d..d8a90d397423 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2946,6 +2946,9 @@ int regulatory_hint_user(const char *alpha2, if (WARN_ON(!alpha2)) return -EINVAL; + if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) + return -EINVAL; + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; diff --git a/net/wireless/util.c b/net/wireless/util.c index 7c5d5365a5eb..4a9ff9ef513f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -123,11 +123,13 @@ int ieee80211_freq_khz_to_channel(u32 freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else if (freq < 5945) + else if (freq < 5925) return (freq - 5000) / 5; + else if (freq == 5935) + return 2; else if (freq <= 45000) /* DMG band lower limit */ - /* see 802.11ax D4.1 27.3.22.2 */ - return (freq - 5940) / 5; + /* see 802.11ax D6.1 27.3.22.2 */ + return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 077e7ee69e3d..3e5dcdd48a49 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1196,7 +1196,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ /* 1 free */ -#define PERF_MEM_SNOOPX_SHIFT 37 +#define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 3ba566de821c..5acc18b32606 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -5259,7 +5259,7 @@ static int print_arg_pointer(struct trace_seq *s, const char *format, int plen, default: ret = 0; val = eval_num_arg(data, size, event, arg); - trace_seq_printf(s, "%p", (void *)val); + trace_seq_printf(s, "%p", (void *)(intptr_t)val); break; } diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3f72d8e261f3..bd50cdff08a8 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,6 +33,10 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where 'param1', 'param2', etc are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/*. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index c9bfefc051fb..db420dd75e43 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -39,6 +39,10 @@ report:: - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed event like 'pmu/param1=0x3,param2/' where param1 and param2 are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/* @@ -416,6 +420,9 @@ counts for all hardware threads in a core but show the sum counts per hardware thread. This is essentially a replacement for the any bit and convenient for post processing. +--summary:: +Print summary for interval mode (-I). + EXAMPLES -------- diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 8d624aea1c5e..b2924e3181dc 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target, init_stats(&event_stats); for (i = 0; i < multi_iterations; i++) { session = perf_session__new(NULL, false, NULL); - if (!session) - return -ENOMEM; + if (IS_ERR(session)) + return PTR_ERR(session); atomic_set(&event_count, 0); gettimeofday(&start, NULL); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f91352f847c0..772f1057647f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2452,7 +2452,7 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), - OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"), + OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"), OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, "Fail if the specified frequency can't be used"), OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ece1cddfcd7c..3c74c9c0f3c3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1332,6 +1332,9 @@ int cmd_report(int argc, const char **argv) if (report.mmaps_mode) report.tasks_mode = true; + if (dump_trace) + report.tool.ordered_events = false; + if (quiet) perf_quiet_option(); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 0c7d599fa555..e6fc297cee91 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2584,7 +2584,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->idle_hist || thread->tid == 0) { - timehist_update_runtime_stats(tr, t, tprev); + if (!cpu_list || test_bit(sample->cpu, cpu_bitmap)) + timehist_update_runtime_stats(tr, t, tprev); if (sched->idle_hist) { struct idle_thread_runtime *itr = (void *)tr; @@ -2857,6 +2858,9 @@ static void timehist_print_summary(struct perf_sched *sched, printf("\nIdle stats:\n"); for (i = 0; i < idle_max_cpu; ++i) { + if (cpu_list && !test_bit(i, cpu_bitmap)) + continue; + t = idle_threads[i]; if (!t) continue; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 483a28ef4ec4..fddc97cac984 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs) { struct evsel *counter; - if (!stat_config.summary && (read_affinity_counters(rs) < 0)) + if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0)) return; evlist__for_each_entry(evsel_list, counter) { @@ -897,9 +897,9 @@ try_again_reset: if (stat_config.walltime_run_table) stat_config.walltime_run[run_idx] = t1 - t0; - if (interval) { + if (interval && stat_config.summary) { stat_config.interval = 0; - stat_config.summary = true; + stat_config.stop_read_counter = true; init_stats(&walltime_nsecs_stats); update_stats(&walltime_nsecs_stats, t1 - t0); @@ -1164,6 +1164,8 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), + OPT_BOOLEAN(0, "summary", &stat_config.summary, + "print summary for interval mode"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 994c230027bb..7c64134472c7 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1746,6 +1746,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } +#ifdef HAVE_LIBBPF_SUPPORT if (!top.record_opts.no_bpf_event) { top.sb_evlist = evlist__new(); @@ -1759,6 +1760,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } } +#endif if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fa86c5f997cc..fc9c158bfa13 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -137,7 +137,7 @@ static char *fixregex(char *s) return s; /* allocate space for a new string */ - fixed = (char *) malloc(len + 1); + fixed = (char *) malloc(len + esc_count + 1); if (!fixed) return NULL; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 5d20bf8397f0..cd77e334e577 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_mmap__read_done(&md->core); } - if (count != expect) { + if (count != expect * evlist->core.nr_entries) { pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count); goto out_delete_evlist; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f9f87a470c3..aae0fd9045c1 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); @@ -842,7 +842,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index fc0838a7abc2..23db8acc492d 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -70,6 +70,9 @@ static struct pmu_event pme_test[] = { { .metric_expr = "1/m3", .metric_name = "M3", +}, +{ + .name = NULL, } }; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index be9c4c0549bc..a07626f07208 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3629,8 +3629,8 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, { int nr_entries = evlist->core.nr_entries; -single_entry: if (perf_evlist__single_entry(evlist)) { +single_entry: { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, @@ -3638,6 +3638,7 @@ single_entry: env, warn_lost_event, annotation_opts); } + } if (symbol_conf.event_group) { struct evsel *pos; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 302a14d0aca9..93e063f22be5 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -182,15 +182,15 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_TLB_ACCESS)) decoder->record.type |= ARM_SPE_TLB_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_MISS))) decoder->record.type |= ARM_SPE_LLC_MISS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_ACCESS))) decoder->record.type |= ARM_SPE_LLC_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_REMOTE_ACCESS))) decoder->record.type |= ARM_SPE_REMOTE_ACCESS; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index c283223fb31f..a2a369e2fbb6 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1344,8 +1344,15 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; } - if (etm->synth_opts.last_branch) + if (etm->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (etm->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 2a8d245351e7..0af4e81c46e2 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3017,8 +3017,15 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (pt->synth_opts.callchain) attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) + if (pt->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 208b813e00ea..85587de027a5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } -static int is_bpf_image(const char *name) -{ - return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || - strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; -} - static int machine__process_ksymbol_register(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 1d7210804639..cc0faf8f1321 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map) return name && (strstr(name, "bpf_prog_") == name); } +bool __map__is_bpf_image(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) + return true; + + /* + * If PERF_RECORD_KSYMBOL is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && is_bpf_image(name); +} + bool __map__is_ool(const struct map *map) { return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9e312ae2d656..c2f5d28fe73a 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); bool __map__is_bpf_prog(const struct map *map); +bool __map__is_bpf_image(const struct map *map); bool __map__is_ool(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && - !__map__is_bpf_prog(map) && !__map__is_ool(map); + !__map__is_bpf_prog(map) && !__map__is_ool(map) && + !__map__is_bpf_image(map); } bool map__has_symbols(const struct map *map); @@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name) return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } +static inline bool is_bpf_image(const char *name) +{ + return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || + strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; +} #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9f7260e69113..c4d2394e2b2d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -37,6 +37,7 @@ #include "util/evsel_config.h" #include "util/event.h" #include "util/pfm.h" +#include "perf.h" #define MAX_NAME_LEN 100 @@ -1533,19 +1534,23 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, true, get_config_name(head_config), pmu, &config_terms, auto_merge_stats, NULL); - if (evsel) { - evsel->unit = info.unit; - evsel->scale = info.scale; - evsel->per_pkg = info.per_pkg; - evsel->snapshot = info.snapshot; - evsel->metric_expr = info.metric_expr; - evsel->metric_name = info.metric_name; - evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; - evsel->percore = config_term_percore(&evsel->config_terms); - } + if (!evsel) + return -ENOMEM; + + evsel->pmu_name = name ? strdup(name) : NULL; + evsel->use_uncore_alias = use_uncore_alias; + evsel->percore = config_term_percore(&evsel->config_terms); - return evsel ? 0 : -ENOMEM; + if (parse_state->fake_pmu) + return 0; + + evsel->unit = info.unit; + evsel->scale = info.scale; + evsel->per_pkg = info.per_pkg; + evsel->snapshot = info.snapshot; + evsel->metric_expr = info.metric_expr; + evsel->metric_name = info.metric_name; + return 0; } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, @@ -1794,6 +1799,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, if (*str == 'u') { if (!exclude) exclude = eu = ek = eh = 1; + if (!exclude_GH && !perf_guest) + eG = 1; eu = 0; } else if (*str == 'k') { if (!exclude) diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index b9fb91fdc5de..645bf4f1859f 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4); + (void *)(uintptr_t) $2, $6, $4); free($6); if (err) { free(list); @@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)) { + (void *)(uintptr_t) $2, NULL, $4)) { free(list); YYABORT; } @@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0); + (void *)(uintptr_t) $2, $4, 0); free($4); if (err) { free(list); @@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)) { + (void *)(uintptr_t) $2, NULL, 0)) { free(list); YYABORT; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ffbc9d35a383..7a5f03764702 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -87,7 +87,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, session->decomp_last = decomp; } - pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size); + pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size); return 0; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 57d0706e1330..493ec372fdec 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -117,7 +117,7 @@ static void aggr_printout(struct perf_stat_config *config, cpu_map__id_to_die(id), config->csv_output ? 0 : -3, cpu_map__id_to_cpu(id), config->csv_sep); - } else { + } else if (id > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, evsel__cpus(evsel)->map[id], diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index f8778cffd941..aa3bed48511b 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -113,6 +113,7 @@ struct perf_stat_config { bool summary; bool metric_no_group; bool metric_no_merge; + bool stop_read_counter; FILE *output; unsigned int interval; unsigned int timeout; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1f5fcb828a21..5151a8c0b791 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -663,6 +663,7 @@ static bool symbol__is_idle(const char *name) "exit_idle", "mwait_idle", "mwait_idle_with_hints", + "mwait_idle_with_hints.constprop.0", "poll_idle", "ppc64_runlatch_off", "pseries_dedicated_idle_sleep", diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index d2202392ffdb..48dd2b018c47 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -99,7 +99,7 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { - pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n", + pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n", src_size, output.size, dst_size, ZSTD_getErrorName(ret)); break; } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 754cf611723e..0d92ebcb335d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1274,6 +1274,8 @@ static void __run_parallel(unsigned int tasks, pid_t pid[tasks]; int i; + fflush(stdout); + for (i = 0; i < tasks; i++) { pid[i] = fork(); if (pid[i] == 0) { diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b1e4dadacd9b..22943b58d752 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -618,7 +618,9 @@ int cd_flavor_subdir(const char *exec_name) if (!flavor) return 0; flavor++; - fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor); + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor); + return chdir(flavor); } diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index a47d1d832210..431296c0f91c 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -11,7 +11,7 @@ # result in fragmentation and/or PMTU discovery. # # You can check with different Orgininator/Link/Responder MTU eg: -# sh nft_flowtable.sh -o1000 -l500 -r100 +# nft_flowtable.sh -o8000 -l1500 -r2000 # @@ -27,8 +27,7 @@ ns2out="" log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) checktool (){ - $1 > /dev/null 2>&1 - if [ $? -ne 0 ];then + if ! $1 > /dev/null 2>&1; then echo "SKIP: Could not $2" exit $ksft_skip fi @@ -87,19 +86,36 @@ omtu=9000 lmtu=1500 rmtu=2000 +usage(){ + echo "nft_flowtable.sh [OPTIONS]" + echo + echo "MTU options" + echo " -o originator" + echo " -l link" + echo " -r responder" + exit 1 +} + while getopts "o:l:r:" o do case $o in o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; + *) usage;; esac done -ip -net nsr1 link set veth0 mtu $omtu +if ! ip -net nsr1 link set veth0 mtu $omtu; then + exit 1 +fi + ip -net ns1 link set eth0 mtu $omtu -ip -net nsr2 link set veth1 mtu $rmtu +if ! ip -net nsr2 link set veth1 mtu $rmtu; then + exit 1 +fi + ip -net ns2 link set eth0 mtu $rmtu # transfer-net between nsr1 and nsr2. @@ -120,7 +136,10 @@ for i in 1 2; do ip -net ns$i route add default via 10.0.$i.1 ip -net ns$i addr add dead:$i::99/64 dev eth0 ip -net ns$i route add default via dead:$i::1 - ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null + if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then + echo "ERROR: Check Originator/Responder values (problem during address addition)" + exit 1 + fi # don't set ip DF bit for first two tests ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null @@ -178,15 +197,13 @@ if [ $? -ne 0 ]; then fi # test basic connectivity -ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null -if [ $? -ne 0 ];then +if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 bash exit 1 fi -ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null -if [ $? -ne 0 ];then +if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then echo "ERROR: ns2 cannot reach ns1" 1>&2 exit 1 fi @@ -203,7 +220,6 @@ ns2out=$(mktemp) make_file() { name=$1 - who=$2 SIZE=$((RANDOM % (1024 * 8))) TSIZE=$((SIZE * 1024)) @@ -222,8 +238,7 @@ check_transfer() out=$2 what=$3 - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then + if ! cmp "$in" "$out" > /dev/null 2>&1; then echo "FAIL: file mismatch for $what" 1>&2 ls -l "$in" ls -l "$out" @@ -260,13 +275,11 @@ test_tcp_forwarding_ip() wait - check_transfer "$ns1in" "$ns2out" "ns1 -> ns2" - if [ $? -ne 0 ];then + if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then lret=1 fi - check_transfer "$ns2in" "$ns1out" "ns1 <- ns2" - if [ $? -ne 0 ];then + if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then lret=1 fi @@ -295,13 +308,12 @@ test_tcp_forwarding_nat() return $lret } -make_file "$ns1in" "ns1" -make_file "$ns2in" "ns2" +make_file "$ns1in" +make_file "$ns2in" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. -test_tcp_forwarding ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -332,9 +344,7 @@ table ip nat { } EOF -test_tcp_forwarding_nat ns1 ns2 - -if [ $? -eq 0 ] ;then +if test_tcp_forwarding_nat ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2 with NAT" else echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2 @@ -346,8 +356,7 @@ fi # Same as second test, but with PMTU discovery enabled. handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2) -ip netns exec nsr1 nft delete rule inet filter forward $handle -if [ $? -ne 0 ] ;then +if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then echo "FAIL: Could not delete large-packet accept rule" exit 1 fi @@ -355,8 +364,7 @@ fi ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null -test_tcp_forwarding_nat ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding_nat ns1 ns2; then echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery" else echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2 @@ -402,8 +410,7 @@ ip -net ns2 route del 192.168.10.1 via 10.0.2.1 ip -net ns2 route add default via 10.0.2.1 ip -net ns2 route add default via dead:2::1 -test_tcp_forwarding ns1 ns2 -if [ $? -eq 0 ] ;then +if test_tcp_forwarding ns1 ns2; then echo "PASS: ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index c41f24b517f4..65c141ebfbbd 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -462,6 +462,17 @@ static int test_vsys_x(void) return 0; } +/* + * Debuggers expect ptrace() to be able to peek at the vsyscall page. + * Use process_vm_readv() as a proxy for ptrace() to test this. We + * want it to work in the vsyscall=emulate case and to fail in the + * vsyscall=xonly case. + * + * It's worth noting that this ABI is a bit nutty. write(2) can't + * read from the vsyscall page on any kernel version or mode. The + * fact that ptrace() ever worked was a nice courtesy of old kernels, + * but the code to support it is fairly gross. + */ static int test_process_vm_readv(void) { #ifdef __x86_64__ @@ -477,8 +488,12 @@ static int test_process_vm_readv(void) remote.iov_len = 4096; ret = process_vm_readv(getpid(), &local, 1, &remote, 1, 0); if (ret != 4096) { - printf("[OK]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", ret, errno); - return 0; + /* + * We expect process_vm_readv() to work if and only if the + * vsyscall page is readable. + */ + printf("[%s]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", vsyscall_map_r ? "FAIL" : "OK", ret, errno); + return vsyscall_map_r ? 1 : 0; } if (vsyscall_map_r) { @@ -488,6 +503,9 @@ static int test_process_vm_readv(void) printf("[FAIL]\tIt worked but returned incorrect data\n"); return 1; } + } else { + printf("[FAIL]\tprocess_rm_readv() succeeded, but it should have failed in this configuration\n"); + return 1; } #endif |