diff options
711 files changed, 19862 insertions, 4510 deletions
@@ -226,6 +226,8 @@ Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Drew Fustini <fustini@kernel.org> <drew@pdp7.com> <duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr> +Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <easwar.hariharan@intel.com> +Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <eahariha@linux.microsoft.com> Ed L. Cashin <ecashin@coraid.com> Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org> Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com> diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 803f578dc023..0ddffc9133d0 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -731,7 +731,7 @@ Contact: linux-block@vger.kernel.org Description: [RW] If the device is registered for writeback throttling, then this file shows the target minimum read latency. If this latency - is exceeded in a given window of time (see wb_window_usec), then + is exceeded in a given window of time (see curr_win_nsec), then the writeback throttling will start scaling back writes. Writing a value of '0' to this file disables the feature. Writing a value of '-1' to this file resets the value to the default diff --git a/Documentation/ABI/testing/sysfs-bus-counter b/Documentation/ABI/testing/sysfs-bus-counter index 3e8259e56d38..3e7eddd8aff3 100644 --- a/Documentation/ABI/testing/sysfs-bus-counter +++ b/Documentation/ABI/testing/sysfs-bus-counter @@ -309,26 +309,26 @@ Description: What: /sys/bus/counter/devices/counterX/cascade_counts_enable_component_id What: /sys/bus/counter/devices/counterX/external_input_phase_clock_select_component_id -What: /sys/bus/counter/devices/counterX/countY/compare_component_id What: /sys/bus/counter/devices/counterX/countY/capture_component_id What: /sys/bus/counter/devices/counterX/countY/ceiling_component_id -What: /sys/bus/counter/devices/counterX/countY/floor_component_id +What: /sys/bus/counter/devices/counterX/countY/compare_component_id What: /sys/bus/counter/devices/counterX/countY/count_mode_component_id What: /sys/bus/counter/devices/counterX/countY/direction_component_id What: /sys/bus/counter/devices/counterX/countY/enable_component_id What: /sys/bus/counter/devices/counterX/countY/error_noise_component_id +What: /sys/bus/counter/devices/counterX/countY/floor_component_id +What: /sys/bus/counter/devices/counterX/countY/num_overflows_component_id What: /sys/bus/counter/devices/counterX/countY/prescaler_component_id What: /sys/bus/counter/devices/counterX/countY/preset_component_id What: /sys/bus/counter/devices/counterX/countY/preset_enable_component_id What: /sys/bus/counter/devices/counterX/countY/signalZ_action_component_id -What: /sys/bus/counter/devices/counterX/countY/num_overflows_component_id What: /sys/bus/counter/devices/counterX/signalY/cable_fault_component_id What: /sys/bus/counter/devices/counterX/signalY/cable_fault_enable_component_id What: /sys/bus/counter/devices/counterX/signalY/filter_clock_prescaler_component_id +What: /sys/bus/counter/devices/counterX/signalY/frequency_component_id What: /sys/bus/counter/devices/counterX/signalY/index_polarity_component_id What: /sys/bus/counter/devices/counterX/signalY/polarity_component_id What: /sys/bus/counter/devices/counterX/signalY/synchronous_mode_component_id -What: /sys/bus/counter/devices/counterX/signalY/frequency_component_id KernelVersion: 5.16 Contact: linux-iio@vger.kernel.org Description: diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-m24lr b/Documentation/ABI/testing/sysfs-bus-i2c-devices-m24lr new file mode 100644 index 000000000000..7c51ce8d38ba --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-m24lr @@ -0,0 +1,100 @@ +What: /sys/bus/i2c/devices/<busnum>-<primary-addr>/unlock +Date: 2025-07-04 +KernelVersion: 6.17 +Contact: Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> +Description: + Write-only attribute used to present a password and unlock + access to protected areas of the M24LR chip, including + configuration registers such as the Sector Security Status + (SSS) bytes. A valid password must be written to enable write + access to these regions via the I2C interface. + + Format: + - Hexadecimal string representing a 32-bit (4-byte) password + - Accepts 1 to 8 hex digits (e.g., "c", "1F", "a1b2c3d4") + - No "0x" prefix, whitespace, or trailing newline + - Case-insensitive + + Behavior: + - If the password matches the internal stored value, + access to protected memory/configuration is granted + - If the password does not match the internally stored value, + it will fail silently + +What: /sys/bus/i2c/devices/<busnum>-<primary-addr>/new_pass +Date: 2025-07-04 +KernelVersion: 6.17 +Contact: Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> +Description: + Write-only attribute used to update the password required to + unlock the M24LR chip. + + Format: + - Hexadecimal string representing a new 32-bit password + - Accepts 1 to 8 hex digits (e.g., "1A", "ffff", "c0ffee00") + - No "0x" prefix, whitespace, or trailing newline + - Case-insensitive + + Behavior: + - Overwrites the current password stored in the I2C password + register + - Requires the device to be unlocked before changing the + password + - If the device is locked, the write silently fails + +What: /sys/bus/i2c/devices/<busnum>-<primary-addr>/uid +Date: 2025-07-04 +KernelVersion: 6.17 +Contact: Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> +Description: + Read-only attribute that exposes the 8-byte unique identifier + programmed into the M24LR chip at the factory. + + Format: + - Lowercase hexadecimal string representing a 64-bit value + - 1 to 16 hex digits (e.g., "e00204f12345678") + - No "0x" prefix + - Includes a trailing newline + +What: /sys/bus/i2c/devices/<busnum>-<primary-addr>/total_sectors +Date: 2025-07-04 +KernelVersion: 6.17 +Contact: Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> +Description: + Read-only attribute that exposes the total number of EEPROM + sectors available in the M24LR chip. + + Format: + - 1 to 2 hex digits (e.g. "F") + - No "0x" prefix + - Includes a trailing newline + + Notes: + - Value is encoded by the chip and corresponds to the EEPROM + size (e.g., 3 = 4 kbit for M24LR04E-R) + +What: /sys/bus/i2c/devices/<busnum>-<primary-addr>/sss +Date: 2025-07-04 +KernelVersion: 6.17 +Contact: Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> +Description: + Read/write binary attribute representing the Sector Security + Status (SSS) bytes for all EEPROM sectors in STMicroelectronics + M24LR chips. + + Each EEPROM sector has one SSS byte, which controls I2C and + RF access through protection bits and optional password + authentication. + + Format: + - The file contains one byte per EEPROM sector + - Byte at offset N corresponds to sector N + - Binary access only; use tools like dd, Python, or C that + support byte-level I/O and offset control. + + Notes: + - The number of valid bytes in this file is equal to the + value exposed by 'total_sectors' file + - Write access requires prior password authentication in + I2C mode + - Refer to the M24LR datasheet for full SSS bit layout diff --git a/Documentation/admin-guide/blockdev/zoned_loop.rst b/Documentation/admin-guide/blockdev/zoned_loop.rst index 9c7aa3b482f3..64dcfde7450a 100644 --- a/Documentation/admin-guide/blockdev/zoned_loop.rst +++ b/Documentation/admin-guide/blockdev/zoned_loop.rst @@ -79,7 +79,7 @@ zone_capacity_mb Device zone capacity (must always be equal to or lower than the zone size. Default: zone size. conv_zones Total number of conventioanl zones starting from sector 0. Default: 8. -base_dir Path to the base directoy where to create the directory +base_dir Path to the base directory where to create the directory containing the zone files of the device. Default=/var/local/zloop. The device directory containing the zone files is always diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index d9d3cc7df348..51c0bc4c2dc5 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -435,8 +435,8 @@ both cgroups. Controlling Controllers ----------------------- -Availablity -~~~~~~~~~~~ +Availability +~~~~~~~~~~~~ A controller is available in a cgroup when it is supported by the kernel (i.e., compiled in, not disabled and not attached to a v1 hierarchy) and listed in the diff --git a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst index b4de16f5ec44..6dd0800146f6 100644 --- a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst +++ b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst @@ -214,7 +214,7 @@ Spectre_v1 X Spectre_v2 X X Spectre_v2_user X X * (Note 1) SRBDS X X X X -SRSO X X +SRSO X X X X SSB (Note 4) TAA X X X X * (Note 2) TSA X X X X diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 32fc73dc5529..034898e81ba2 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -76,20 +76,21 @@ unit as preprocessor statement. The above example would then read:: within the corresponding compilation unit before the #include for <linux/export.h>. Typically it's placed before the first #include statement. -Using the EXPORT_SYMBOL_GPL_FOR_MODULES() macro ------------------------------------------------ +Using the EXPORT_SYMBOL_FOR_MODULES() macro +------------------------------------------- Symbols exported using this macro are put into a module namespace. This -namespace cannot be imported. +namespace cannot be imported. These exports are GPL-only as they are only +intended for in-tree modules. The macro takes a comma separated list of module names, allowing only those modules to access this symbol. Simple tail-globs are supported. For example:: - EXPORT_SYMBOL_GPL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") + EXPORT_SYMBOL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") -will limit usage of this symbol to modules whoes name matches the given +will limit usage of this symbol to modules whose name matches the given patterns. How to use Symbols exported in Namespaces diff --git a/Documentation/devicetree/bindings/eeprom/at25.yaml b/Documentation/devicetree/bindings/eeprom/at25.yaml index c31e5e719525..00e0f07b44f8 100644 --- a/Documentation/devicetree/bindings/eeprom/at25.yaml +++ b/Documentation/devicetree/bindings/eeprom/at25.yaml @@ -56,6 +56,7 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32 description: Total eeprom size in bytes. + Also used for FRAMs without device ID where the size cannot be detected. address-width: $ref: /schemas/types.yaml#/definitions/uint32 @@ -146,4 +147,11 @@ examples: reg = <1>; spi-max-frequency = <40000000>; }; + + fram@2 { + compatible = "cypress,fm25", "atmel,at25"; + reg = <2>; + spi-max-frequency = <20000000>; + size = <2048>; + }; }; diff --git a/Documentation/devicetree/bindings/eeprom/st,m24lr.yaml b/Documentation/devicetree/bindings/eeprom/st,m24lr.yaml new file mode 100644 index 000000000000..0a0820e9d11f --- /dev/null +++ b/Documentation/devicetree/bindings/eeprom/st,m24lr.yaml @@ -0,0 +1,52 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/eeprom/st,m24lr.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: STMicroelectronics M24LR NFC/RFID EEPROM + +maintainers: + - Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> + +description: + STMicroelectronics M24LR series are dual-interface (RF + I2C) + EEPROM chips. These devices support I2C-based access to both + memory and a system area that controls authentication and configuration. + They expose two I2C addresses, one for the system parameter sector and + one for the EEPROM. + +allOf: + - $ref: /schemas/nvmem/nvmem.yaml# + +properties: + compatible: + enum: + - st,m24lr04e-r + - st,m24lr16e-r + - st,m24lr64e-r + + reg: + items: + - description: I2C address used for control/system registers + - description: I2C address used for EEPROM memory access + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + eeprom@57 { + compatible = "st,m24lr04e-r"; + reg = <0x57>, /* primary-device */ + <0x53>; /* secondary-device */ + }; + }; +... diff --git a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt b/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt deleted file mode 100644 index cfcf455ad4de..000000000000 --- a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt +++ /dev/null @@ -1,23 +0,0 @@ - -* Richtek RT8973A - Micro USB Switch device - -The Richtek RT8973A is Micro USB Switch with OVP and I2C interface. The RT8973A -is a USB port accessory detector and switch that is optimized to protect low -voltage system from abnormal high input voltage (up to 28V) and supports high -speed USB operation. Also, RT8973A support 'auto-configuration' mode. -If auto-configuration mode is enabled, RT8973A would control internal h/w patch -for USB D-/D+ switching. - -Required properties: -- compatible: Should be "richtek,rt8973a-muic" -- reg: Specifies the I2C slave address of the MUIC block. It should be 0x14 -- interrupts: Interrupt specifiers for detection interrupt sources. - -Example: - - rt8973a@14 { - compatible = "richtek,rt8973a-muic"; - interrupt-parent = <&gpx1>; - interrupts = <5 0>; - reg = <0x14>; - }; diff --git a/Documentation/devicetree/bindings/extcon/linux,extcon-usb-gpio.yaml b/Documentation/devicetree/bindings/extcon/linux,extcon-usb-gpio.yaml index 8856107bdd33..8f29d333602b 100644 --- a/Documentation/devicetree/bindings/extcon/linux,extcon-usb-gpio.yaml +++ b/Documentation/devicetree/bindings/extcon/linux,extcon-usb-gpio.yaml @@ -25,6 +25,12 @@ properties: required: - compatible +anyOf: + - required: + - id-gpios + - required: + - vbus-gpios + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/extcon/maxim,max14526.yaml b/Documentation/devicetree/bindings/extcon/maxim,max14526.yaml new file mode 100644 index 000000000000..7eb5918df1c2 --- /dev/null +++ b/Documentation/devicetree/bindings/extcon/maxim,max14526.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/extcon/maxim,max14526.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Maxim MAX14526 MicroUSB Integrated Circuit (MUIC) + +maintainers: + - Svyatoslav Ryhel <clamor95@gmail.com> + +properties: + compatible: + const: maxim,max14526 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + connector: + $ref: /schemas/connector/usb-connector.yaml# + + port: + $ref: /schemas/graph.yaml#/properties/port + +required: + - compatible + - reg + - interrupts + - connector + - port + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + muic@44 { + compatible = "maxim,max14526"; + reg = <0x44>; + + interrupt-parent = <&gpio>; + interrupts = <72 IRQ_TYPE_EDGE_FALLING>; + + connector { + compatible = "usb-b-connector"; + label = "micro-USB"; + type = "micro"; + }; + + port { + #address-cells = <1>; + #size-cells = <0>; + + muic_to_charger: endpoint@0 { + reg = <0>; + remote-endpoint = <&charger_input>; + }; + + muic_to_usb: endpoint@1 { + reg = <1>; + remote-endpoint = <&usb_input>; + }; + + muic_to_mhl: endpoint@2 { + reg = <2>; + remote-endpoint = <&mhl_input>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/extcon/richtek,rt8973a-muic.yaml b/Documentation/devicetree/bindings/extcon/richtek,rt8973a-muic.yaml new file mode 100644 index 000000000000..f9e0d816c025 --- /dev/null +++ b/Documentation/devicetree/bindings/extcon/richtek,rt8973a-muic.yaml @@ -0,0 +1,49 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/extcon/richtek,rt8973a-muic.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Richtek RT8973A MUIC + +maintainers: + - Chanwoo Choi <cw00.choi@samsung.com> + +description: + The Richtek RT8973A is Micro USB Switch with OVP and I2C interface. The RT8973A + is a USB port accessory detector and switch that is optimized to protect low + voltage system from abnormal high input voltage (up to 28V) and supports high + speed USB operation. Also, RT8973A support 'auto-configuration' mode. + If auto-configuration mode is enabled, RT8973A would control internal h/w patch + for USB D-/D+ switching. + +properties: + compatible: + const: richtek,rt8973a-muic + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + i2c { + #address-cells = <1>; + #size-cells = <0>; + usb-switch@14 { + compatible = "richtek,rt8973a-muic"; + reg = <0x14>; + interrupt-parent = <&gpio>; + interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + }; + }; diff --git a/Documentation/devicetree/bindings/misc/qcom,fastrpc.yaml b/Documentation/devicetree/bindings/misc/qcom,fastrpc.yaml index 0840a3d92513..3f6199fc9ae6 100644 --- a/Documentation/devicetree/bindings/misc/qcom,fastrpc.yaml +++ b/Documentation/devicetree/bindings/misc/qcom,fastrpc.yaml @@ -27,6 +27,8 @@ properties: - sdsp - cdsp - cdsp1 + - gdsp0 + - gdsp1 memory-region: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml index 6d9de3303762..b3492a9aa4ef 100644 --- a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml +++ b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml @@ -62,11 +62,13 @@ properties: items: - description: GMAC main clock - description: Peripheral registers interface clock + - description: APB glue registers interface clock clock-names: items: - const: stmmaceth - const: pclk + - const: apb interrupts: items: @@ -88,8 +90,8 @@ examples: compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; reg = <0xe7070000 0x2000>, <0xec003000 0x1000>; reg-names = "dwmac", "apb"; - clocks = <&clk 1>, <&clk 2>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk 1>, <&clk 2>, <&clk 3>; + clock-names = "stmmaceth", "pclk", "apb"; interrupts = <66>; interrupt-names = "macirq"; phy-mode = "rgmii-id"; diff --git a/Documentation/devicetree/bindings/nvmem/airoha,an8855-efuse.yaml b/Documentation/devicetree/bindings/nvmem/airoha,an8855-efuse.yaml new file mode 100644 index 000000000000..9802d9ea2176 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/airoha,an8855-efuse.yaml @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/airoha,an8855-efuse.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Airoha AN8855 Switch EFUSE + +maintainers: + - Christian Marangi <ansuelsmth@gmail.com> + +description: + Airoha AN8855 EFUSE used to calibrate internal PHYs and store additional + configuration info. + +$ref: nvmem.yaml# + +properties: + compatible: + const: airoha,an8855-efuse + + '#nvmem-cell-cells': + const: 0 + +required: + - compatible + - '#nvmem-cell-cells' + +unevaluatedProperties: false + +examples: + - | + efuse { + compatible = "airoha,an8855-efuse"; + + #nvmem-cell-cells = <0>; + + nvmem-layout { + compatible = "fixed-layout"; + #address-cells = <1>; + #size-cells = <1>; + + shift_sel_port0_tx_a: shift-sel-port0-tx-a@c { + reg = <0xc 0x4>; + }; + + shift_sel_port0_tx_b: shift-sel-port0-tx-b@10 { + reg = <0x10 0x4>; + }; + + shift_sel_port0_tx_c: shift-sel-port0-tx-c@14 { + reg = <0x14 0x4>; + }; + + shift_sel_port0_tx_d: shift-sel-port0-tx-d@18 { + reg = <0x18 0x4>; + }; + + shift_sel_port1_tx_a: shift-sel-port1-tx-a@1c { + reg = <0x1c 0x4>; + }; + + shift_sel_port1_tx_b: shift-sel-port1-tx-b@20 { + reg = <0x20 0x4>; + }; + + shift_sel_port1_tx_c: shift-sel-port1-tx-c@24 { + reg = <0x24 0x4>; + }; + + shift_sel_port1_tx_d: shift-sel-port1-tx-d@28 { + reg = <0x28 0x4>; + }; + + shift_sel_port2_tx_a: shift-sel-port2-tx-a@2c { + reg = <0x2c 0x4>; + }; + + shift_sel_port2_tx_b: shift-sel-port2-tx-b@30 { + reg = <0x30 0x4>; + }; + + shift_sel_port2_tx_c: shift-sel-port2-tx-c@34 { + reg = <0x34 0x4>; + }; + + shift_sel_port2_tx_d: shift-sel-port2-tx-d@38 { + reg = <0x38 0x4>; + }; + + shift_sel_port3_tx_a: shift-sel-port3-tx-a@4c { + reg = <0x4c 0x4>; + }; + + shift_sel_port3_tx_b: shift-sel-port3-tx-b@50 { + reg = <0x50 0x4>; + }; + + shift_sel_port3_tx_c: shift-sel-port3-tx-c@54 { + reg = <0x54 0x4>; + }; + + shift_sel_port3_tx_d: shift-sel-port3-tx-d@58 { + reg = <0x58 0x4>; + }; + + shift_sel_port4_tx_a: shift-sel-port4-tx-a@5c { + reg = <0x5c 0x4>; + }; + + shift_sel_port4_tx_b: shift-sel-port4-tx-b@60 { + reg = <0x60 0x4>; + }; + + shift_sel_port4_tx_c: shift-sel-port4-tx-c@64 { + reg = <0x64 0x4>; + }; + + shift_sel_port4_tx_d: shift-sel-port4-tx-d@68 { + reg = <0x68 0x4>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml b/Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml index c713e23819f1..afd1919c6b1c 100644 --- a/Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml +++ b/Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml @@ -19,7 +19,12 @@ select: false properties: compatible: - const: kontron,sl28-vpd + oneOf: + - items: + - enum: + - kontron,sa67-vpd + - const: kontron,sl28-vpd + - const: kontron,sl28-vpd serial-number: type: object diff --git a/Documentation/devicetree/bindings/nvmem/nxp,s32g-ocotp-nvmem.yaml b/Documentation/devicetree/bindings/nvmem/nxp,s32g-ocotp-nvmem.yaml new file mode 100644 index 000000000000..8d46e7d28da6 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/nxp,s32g-ocotp-nvmem.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/nxp,s32g-ocotp-nvmem.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP S32G OCOTP NVMEM driver + +maintainers: + - Ciprian Costea <ciprianmarian.costea@nxp.com> + +description: + The drivers provides an interface to access One Time + Programmable memory pages, such as TMU fuse values. + +properties: + compatible: + oneOf: + - enum: + - nxp,s32g2-ocotp + - items: + - enum: + - nxp,s32g3-ocotp + - nxp,s32r45-ocotp + - const: nxp,s32g2-ocotp + reg: + maxItems: 1 + +required: + - compatible + - reg + +unevaluatedProperties: false + +allOf: + - $ref: nvmem.yaml# + +examples: + - | + nvmem@400a4000 { + compatible = "nxp,s32g2-ocotp"; + reg = <0x400a4000 0x400>; + #address-cells = <1>; + #size-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml index e6ffbc2a2298..57ff6bf1e188 100644 --- a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml +++ b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Infineon Buck Regulators with PMBUS interfaces maintainers: - - Not Me. + - Guenter Roeck <linux@roeck-us.net> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/slimbus/qcom,slim.yaml b/Documentation/devicetree/bindings/slimbus/qcom,slim.yaml deleted file mode 100644 index 883bda58ca97..000000000000 --- a/Documentation/devicetree/bindings/slimbus/qcom,slim.yaml +++ /dev/null @@ -1,86 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/slimbus/qcom,slim.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: Qualcomm SoC SLIMbus controller - -maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> - - Srinivas Kandagatla <srinivas.kandagatla@linaro.org> - -description: - SLIMbus controller used when applications processor controls SLIMbus master - component. - -allOf: - - $ref: slimbus.yaml# - -properties: - compatible: - items: - - enum: - - qcom,apq8064-slim - - const: qcom,slim - - reg: - items: - - description: Physical address of controller register blocks - - description: SLEW RATE register - - reg-names: - items: - - const: ctrl - - const: slew - - clocks: - items: - - description: Interface clock for this controller - - description: Interrupt for controller core's BAM - - clock-names: - items: - - const: iface - - const: core - - interrupts: - maxItems: 1 - -required: - - compatible - - reg - - reg-names - - clocks - - clock-names - - interrupts - -unevaluatedProperties: false - -examples: - - | - #include <dt-bindings/clock/qcom,gcc-msm8960.h> - #include <dt-bindings/clock/qcom,lcc-msm8960.h> - #include <dt-bindings/interrupt-controller/arm-gic.h> - - soc { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - slim@28080000 { - compatible = "qcom,apq8064-slim", "qcom,slim"; - reg = <0x28080000 0x2000>, <0x80207c 4>; - reg-names = "ctrl", "slew"; - interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&lcc SLIMBUS_SRC>, <&lcc AUDIO_SLIMBUS_CLK>; - clock-names = "iface", "core"; - #address-cells = <2>; - #size-cells = <0>; - - audio-codec@1,0 { - compatible = "slim217,60"; - reg = <1 0>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/slimbus/slimbus.yaml b/Documentation/devicetree/bindings/slimbus/slimbus.yaml index 3b8cae9d1016..89017d9cda10 100644 --- a/Documentation/devicetree/bindings/slimbus/slimbus.yaml +++ b/Documentation/devicetree/bindings/slimbus/slimbus.yaml @@ -68,8 +68,6 @@ additionalProperties: true examples: - | - #include <dt-bindings/clock/qcom,gcc-msm8960.h> - #include <dt-bindings/clock/qcom,lcc-msm8960.h> #include <dt-bindings/interrupt-controller/arm-gic.h> soc { @@ -78,17 +76,14 @@ examples: ranges; slim@28080000 { - compatible = "qcom,apq8064-slim", "qcom,slim"; - reg = <0x28080000 0x2000>, <0x80207c 4>; - reg-names = "ctrl", "slew"; - interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&lcc SLIMBUS_SRC>, <&lcc AUDIO_SLIMBUS_CLK>; - clock-names = "iface", "core"; + compatible = "qcom,slim-ngd-v1.5.0"; + reg = <0x091c0000 0x2c000>; + interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <2>; #size-cells = <0>; audio-codec@1,0 { - compatible = "slim217,60"; + compatible = "slim217,1a0"; reg = <1 0>; }; }; diff --git a/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml b/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml index 55adea827c34..2c1bbc0eb05a 100644 --- a/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml +++ b/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml @@ -24,6 +24,9 @@ properties: reg: maxItems: 1 + interrupts: + maxItems: 1 + clocks: maxItems: 1 @@ -40,5 +43,6 @@ examples: owire@63fa4000 { compatible = "fsl,imx53-owire", "fsl,imx21-owire"; reg = <0x63fa4000 0x4000>; + interrupts = <88>; clocks = <&clks IMX5_CLK_OWIRE_GATE>; }; diff --git a/Documentation/netlink/specs/binder.yaml b/Documentation/netlink/specs/binder.yaml new file mode 100644 index 000000000000..0f0575ad1265 --- /dev/null +++ b/Documentation/netlink/specs/binder.yaml @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +# +# Copyright 2025 Google LLC +# +--- +name: binder +protocol: genetlink +uapi-header: linux/android/binder_netlink.h +doc: Binder interface over generic netlink + +attribute-sets: + - + name: report + doc: | + Attributes included within a transaction failure report. The elements + correspond directly with the specific transaction that failed, along + with the error returned to the sender e.g. BR_DEAD_REPLY. + + attributes: + - + name: error + type: u32 + doc: The enum binder_driver_return_protocol returned to the sender. + - + name: context + type: string + doc: The binder context where the transaction occurred. + - + name: from-pid + type: u32 + doc: The PID of the sender process. + - + name: from-tid + type: u32 + doc: The TID of the sender thread. + - + name: to-pid + type: u32 + doc: | + The PID of the recipient process. This attribute may not be present + if the target could not be determined. + - + name: to-tid + type: u32 + doc: | + The TID of the recipient thread. This attribute may not be present + if the target could not be determined. + - + name: is-reply + type: flag + doc: When present, indicates the failed transaction is a reply. + - + name: flags + type: u32 + doc: The bitmask of enum transaction_flags from the transaction. + - + name: code + type: u32 + doc: The application-defined code from the transaction. + - + name: data-size + type: u32 + doc: The transaction payload size in bytes. + +operations: + list: + - + name: report + doc: | + A multicast event sent to userspace subscribers to notify them about + binder transaction failures. The generated report provides the full + details of the specific transaction that failed. The intention is for + programs to monitor these events and react to the failures as needed. + + attribute-set: report + mcgrp: report + event: + attributes: + - error + - context + - from-pid + - from-tid + - to-pid + - to-tid + - is-reply + - flags + - code + - data-size + +mcast-groups: + list: + - + name: report diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index bb620f554598..9756d16e3df1 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1420,7 +1420,7 @@ udp_hash_entries - INTEGER A negative value means the networking namespace does not own its hash buckets and shares the initial networking namespace's one. -udp_child_ehash_entries - INTEGER +udp_child_hash_entries - INTEGER Control the number of hash buckets for UDP sockets in the child networking namespace, which must be set before clone() or unshare(). diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 5bfab01eff5a..1683c139821e 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -12,6 +12,8 @@ add_addr_timeout - INTEGER (seconds) resent to an MPTCP peer that has not acknowledged a previous ADD_ADDR message. + Do not retransmit if set to 0. + The default value matches TCP_RTO_MAX. This is a per-namespace sysctl. diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst index 56c560a00b37..84657e7d2e5b 100644 --- a/Documentation/process/security-bugs.rst +++ b/Documentation/process/security-bugs.rst @@ -8,8 +8,22 @@ like to know when a security bug is found so that it can be fixed and disclosed as quickly as possible. Please report security bugs to the Linux kernel security team. -Contact -------- +The security team and maintainers almost always require additional +information beyond what was initially provided in a report and rely on +active and efficient collaboration with the reporter to perform further +testing (e.g., verifying versions, configuration options, mitigations, or +patches). Before contacting the security team, the reporter must ensure +they are available to explain their findings, engage in discussions, and +run additional tests. Reports where the reporter does not respond promptly +or cannot effectively discuss their findings may be abandoned if the +communication does not quickly improve. + +As it is with any bug, the more information provided the easier it +will be to diagnose and fix. Please review the procedure outlined in +'Documentation/admin-guide/reporting-issues.rst' if you are unclear about what +information is helpful. Any exploit code is very helpful and will not +be released without consent from the reporter unless it has already been +made public. The Linux kernel security team can be contacted by email at <security@kernel.org>. This is a private list of security officers @@ -19,13 +33,6 @@ that can speed up the process considerably. It is possible that the security team will bring in extra help from area maintainers to understand and fix the security vulnerability. -As it is with any bug, the more information provided the easier it -will be to diagnose and fix. Please review the procedure outlined in -'Documentation/admin-guide/reporting-issues.rst' if you are unclear about what -information is helpful. Any exploit code is very helpful and will not -be released without consent from the reporter unless it has already been -made public. - Please send plain text emails without attachments where possible. It is much harder to have a context-quoted discussion about a complex issue if all the details are hidden away in attachments. Think of it like a diff --git a/Documentation/userspace-api/iommufd.rst b/Documentation/userspace-api/iommufd.rst index 03f7510384d2..f1c4d21e5c5e 100644 --- a/Documentation/userspace-api/iommufd.rst +++ b/Documentation/userspace-api/iommufd.rst @@ -43,7 +43,7 @@ Following IOMMUFD objects are exposed to userspace: - IOMMUFD_OBJ_HWPT_PAGING, representing an actual hardware I/O page table (i.e. a single struct iommu_domain) managed by the iommu driver. "PAGING" - primarly indicates this type of HWPT should be linked to an IOAS. It also + primarily indicates this type of HWPT should be linked to an IOAS. It also indicates that it is backed by an iommu_domain with __IOMMU_DOMAIN_PAGING feature flag. This can be either an UNMANAGED stage-1 domain for a device running in the user space, or a nesting parent stage-2 domain for mappings @@ -76,7 +76,7 @@ Following IOMMUFD objects are exposed to userspace: * Security namespace for guest owned ID, e.g. guest-controlled cache tags * Non-device-affiliated event reporting, e.g. invalidation queue errors - * Access to a sharable nesting parent pagetable across physical IOMMUs + * Access to a shareable nesting parent pagetable across physical IOMMUs * Virtualization of various platforms IDs, e.g. RIDs and others * Delivery of paravirtualized invalidation * Direct assigned invalidation queues diff --git a/MAINTAINERS b/MAINTAINERS index fe168477caa4..f1fb790a461a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1790,6 +1790,7 @@ M: Suren Baghdasaryan <surenb@google.com> L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git +F: Documentation/netlink/specs/binder.yaml F: drivers/android/ ANDROID GOLDFISH PIC DRIVER @@ -8426,6 +8427,17 @@ T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/scheduler/ F: include/drm/gpu_scheduler.h +DRM GPUVM +M: Danilo Krummrich <dakr@kernel.org> +R: Matthew Brost <matthew.brost@intel.com> +R: Thomas Hellström <thomas.hellstrom@linux.intel.com> +R: Alice Ryhl <aliceryhl@google.com> +L: dri-devel@lists.freedesktop.org +S: Supported +T: git https://gitlab.freedesktop.org/drm/misc/kernel.git +F: drivers/gpu/drm/drm_gpuvm.c +F: include/drm/drm_gpuvm.h + DRM LOG M: Jocelyn Falempe <jfalempe@redhat.com> M: Javier Martinez Canillas <javierm@redhat.com> @@ -10655,7 +10667,8 @@ S: Maintained F: block/partitions/efi.* HABANALABS PCI DRIVER -M: Yaron Avizrat <yaron.avizrat@intel.com> +M: Koby Elbaz <koby.elbaz@intel.com> +M: Konstantin Sinyuk <konstantin.sinyuk@intel.com> L: dri-devel@lists.freedesktop.org S: Supported C: irc://irc.oftc.net/dri-devel @@ -11013,7 +11026,7 @@ F: Documentation/admin-guide/perf/hns3-pmu.rst F: drivers/perf/hisilicon/hns3_pmu.c HISILICON I2C CONTROLLER DRIVER -M: Yicong Yang <yangyicong@hisilicon.com> +M: Devyn Liu <liudingyuan@h-partners.com> L: linux-i2c@vger.kernel.org S: Maintained W: https://www.hisilicon.com @@ -11438,6 +11451,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton <akpm@linux-foundation.org> R: Lance Yang <lance.yang@linux.dev> +R: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/hung_task.h @@ -12280,7 +12294,6 @@ F: include/linux/avf/virtchnl.h F: include/linux/net/intel/*/ INTEL ETHERNET PROTOCOL DRIVER FOR RDMA -M: Mustafa Ismail <mustafa.ismail@intel.com> M: Tatyana Nikolova <tatyana.e.nikolova@intel.com> L: linux-rdma@vger.kernel.org S: Supported @@ -12583,10 +12596,9 @@ S: Supported F: drivers/cpufreq/intel_pstate.c INTEL PTP DFL ToD DRIVER -M: Tianfei Zhang <tianfei.zhang@intel.com> L: linux-fpga@vger.kernel.org L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/ptp/ptp_dfl_tod.c INTEL QUADRATURE ENCODER PERIPHERAL DRIVER @@ -12724,9 +12736,8 @@ S: Maintained F: drivers/platform/x86/intel/wmi/thunderbolt.c INTEL WWAN IOSM DRIVER -M: M Chetan Kumar <m.chetan.kumar@intel.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/wwan/iosm/ INTEL(R) FLEXIBLE RETURN AND EVENT DELIVERY @@ -13686,7 +13697,6 @@ F: scripts/Makefile.kmsan KPROBES M: Naveen N Rao <naveen@kernel.org> -M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org @@ -15674,7 +15684,6 @@ MEDIATEK T7XX 5G WWAN MODEM DRIVER M: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com> R: Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com> R: Liu Haijun <haijun.liu@mediatek.com> -R: M Chetan Kumar <m.chetan.kumar@linux.intel.com> R: Ricardo Martinez <ricardo.martinez@linux.intel.com> L: netdev@vger.kernel.org S: Supported @@ -16061,6 +16070,23 @@ F: mm/mempolicy.c F: mm/migrate.c F: mm/migrate_device.c +MEMORY MANAGEMENT - MGLRU (MULTI-GEN LRU) +M: Andrew Morton <akpm@linux-foundation.org> +M: Axel Rasmussen <axelrasmussen@google.com> +M: Yuanchu Xie <yuanchu@google.com> +R: Wei Xu <weixugc@google.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/admin-guide/mm/multigen_lru.rst +F: Documentation/mm/multigen_lru.rst +F: include/linux/mm_inline.h +F: include/linux/mmzone.h +F: mm/swap.c +F: mm/vmscan.c +F: mm/workingset.c + MEMORY MANAGEMENT - MISC M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@redhat.com> @@ -16251,8 +16277,10 @@ S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm F: rust/helpers/mm.c +F: rust/helpers/page.c F: rust/kernel/mm.rs F: rust/kernel/mm/ +F: rust/kernel/page.rs MEMORY MAPPING M: Andrew Morton <akpm@linux-foundation.org> @@ -17451,6 +17479,7 @@ F: drivers/net/ethernet/neterion/ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> +M: Florian Westphal <fw@strlen.de> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained @@ -22176,7 +22205,7 @@ F: arch/s390/mm S390 NETWORK DRIVERS M: Alexandra Winter <wintera@linux.ibm.com> -M: Thorsten Winkler <twinkler@linux.ibm.com> +R: Aswin Karuvally <aswin@linux.ibm.com> L: linux-s390@vger.kernel.org L: netdev@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index b0703a4e02a2..a3a9759414f4 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -102,7 +102,13 @@ KBUILD_CFLAGS += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma) ifdef CONFIG_OBJTOOL ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP +# The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled. +# Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to +# be passed via '-mllvm' to ld.lld. KBUILD_CFLAGS += -mannotate-tablejump +ifdef CONFIG_LTO_CLANG +KBUILD_LDFLAGS += -mllvm --loongarch-annotate-tablejump +endif else KBUILD_CFLAGS += -fno-jump-tables # keep compatibility with older compilers endif diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 3eda298702b1..5cb568a60cf8 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -58,7 +58,7 @@ .endm .macro STACKLEAK_ERASE -#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#ifdef CONFIG_KSTACK_ERASE bl stackleak_erase_on_task_stack #endif .endm diff --git a/arch/loongarch/include/uapi/asm/setup.h b/arch/loongarch/include/uapi/asm/setup.h new file mode 100644 index 000000000000..d46363ce3e02 --- /dev/null +++ b/arch/loongarch/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_LOONGARCH_SETUP_H +#define _UAPI_ASM_LOONGARCH_SETUP_H + +#define COMMAND_LINE_SIZE 4096 + +#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */ diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index e2f30ff9afde..a43ba7f9f987 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/moduleloader.h> #include <linux/ftrace.h> +#include <linux/sort.h> Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) { @@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v return (Elf_Addr)&plt[nr]; } -static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) -{ - return x->r_info == y->r_info && x->r_addend == y->r_addend; -} +#define cmp_3way(a, b) ((a) < (b) ? -1 : (a) > (b)) -static bool duplicate_rela(const Elf_Rela *rela, int idx) +static int compare_rela(const void *x, const void *y) { - int i; + int ret; + const Elf_Rela *rela_x = x, *rela_y = y; - for (i = 0; i < idx; i++) { - if (is_rela_equal(&rela[i], &rela[idx])) - return true; - } + ret = cmp_3way(rela_x->r_info, rela_y->r_info); + if (ret == 0) + ret = cmp_3way(rela_x->r_addend, rela_y->r_addend); - return false; + return ret; } static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts, unsigned int *gots) { - unsigned int i, type; + unsigned int i; + + sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL); for (i = 0; i < num; i++) { - type = ELF_R_TYPE(relas[i].r_info); - switch (type) { + if (i && !compare_rela(&relas[i-1], &relas[i])) + continue; + + switch (ELF_R_TYPE(relas[i].r_info)) { case R_LARCH_SOP_PUSH_PLT_PCREL: case R_LARCH_B26: - if (!duplicate_rela(relas, i)) - (*plts)++; + (*plts)++; break; case R_LARCH_GOT_PC_HI20: - if (!duplicate_rela(relas, i)) - (*gots)++; + (*gots)++; break; default: break; /* Do nothing. */ diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index 4740cb5b2388..c9f7ca778364 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -677,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, for (i = 1; i < 32; i++) err |= __put_user(regs->regs[i], &sc->sc_regs[i]); +#ifdef CONFIG_CPU_HAS_LBT + if (extctx->lbt.addr) + err |= protected_save_lbt_context(extctx); +#endif + if (extctx->lasx.addr) err |= protected_save_lasx_context(extctx); else if (extctx->lsx.addr) @@ -684,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, else if (extctx->fpu.addr) err |= protected_save_fpu_context(extctx); -#ifdef CONFIG_CPU_HAS_LBT - if (extctx->lbt.addr) - err |= protected_save_lbt_context(extctx); -#endif - /* Set the "end" magic */ info = (struct sctx_info *)extctx->end.addr; err |= __put_user(0, &info->magic); diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 367906b10f81..f3092f2de8b5 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -5,6 +5,7 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/clockchips.h> +#include <linux/cpuhotplug.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev return 0; } +static int arch_timer_starting(unsigned int cpu) +{ + set_csr_ecfg(ECFGF_TIMER); + + return 0; +} + +static int arch_timer_dying(unsigned int cpu) +{ + constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device)); + + /* Clear Timer Interrupt */ + write_csr_tintclear(CSR_TINTCLR_TI); + + return 0; +} + static unsigned long get_loops_per_jiffy(void) { unsigned long lpj = (unsigned long)const_clock_freq; @@ -172,6 +190,10 @@ int constant_clockevent_init(void) lpj_fine = get_loops_per_jiffy(); pr_info("Constant clock event device register\n"); + cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, + "clockevents/loongarch/timer:starting", + arch_timer_starting, arch_timer_dying); + return 0; } diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index a3a12af9ecbf..026b139dcff2 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) } cpu = s->sw_coremap[irq]; - vcpu = kvm_get_vcpu(s->kvm, cpu); + vcpu = kvm_get_vcpu_by_id(s->kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return; + } + if (level) { /* if not enable return false */ if (!test_bit(irq, (unsigned long *)s->enable.reg_u32)) diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index e658d5b37c04..5a8481dda052 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -99,7 +99,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) { int i, idx, ret; - uint32_t val = 0, mask = 0; + uint64_t val = 0, mask = 0; /* * Bit 27-30 is mask for byte writing. @@ -108,7 +108,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) if ((data >> 27) & 0xf) { /* Read the old val */ idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, 4, &val); srcu_read_unlock(&vcpu->kvm->srcu, idx); if (unlikely(ret)) { kvm_err("%s: : read data from addr %llx failed\n", __func__, addr); @@ -124,7 +124,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) } val |= ((uint32_t)(data >> 32) & ~mask); idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, 4, &val); srcu_read_unlock(&vcpu->kvm->srcu, idx); if (unlikely(ret)) kvm_err("%s: : write data to addr %llx failed\n", __func__, addr); @@ -298,7 +298,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev, cpu = (attr->attr >> 16) & 0x3ff; addr = attr->attr & 0xff; - vcpu = kvm_get_vcpu(dev->kvm, cpu); + vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu); if (unlikely(vcpu == NULL)) { kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); return -EINVAL; diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index 6f00ffe05c54..119290bcea79 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -195,6 +195,11 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + /* statistics of pch pic reading */ vcpu->stat.pch_pic_read_exits++; ret = loongarch_pch_pic_read(s, addr, len, val); @@ -302,6 +307,11 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + /* statistics of pch pic writing */ vcpu->stat.pch_pic_write_exits++; ret = loongarch_pch_pic_write(s, addr, len, val); diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index d1b8c50941ca..ce478151466c 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1283,9 +1283,11 @@ int kvm_own_lbt(struct kvm_vcpu *vcpu) return -EINVAL; preempt_disable(); - set_csr_euen(CSR_EUEN_LBTEN); - _restore_lbt(&vcpu->arch.lbt); - vcpu->arch.aux_inuse |= KVM_LARCH_LBT; + if (!(vcpu->arch.aux_inuse & KVM_LARCH_LBT)) { + set_csr_euen(CSR_EUEN_LBTEN); + _restore_lbt(&vcpu->arch.lbt); + vcpu->arch.aux_inuse |= KVM_LARCH_LBT; + } preempt_enable(); return 0; diff --git a/arch/mips/boot/dts/lantiq/danube_easy50712.dts b/arch/mips/boot/dts/lantiq/danube_easy50712.dts index 1ce20b7d05cb..c4d7aa5753b0 100644 --- a/arch/mips/boot/dts/lantiq/danube_easy50712.dts +++ b/arch/mips/boot/dts/lantiq/danube_easy50712.dts @@ -82,13 +82,16 @@ }; }; - etop@e180000 { + ethernet@e180000 { compatible = "lantiq,etop-xway"; reg = <0xe180000 0x40000>; interrupt-parent = <&icu0>; interrupts = <73 78>; + interrupt-names = "tx", "rx"; phy-mode = "rmii"; mac-address = [ 00 11 22 33 44 55 ]; + lantiq,rx-burst-length = <4>; + lantiq,tx-burst-length = <4>; }; stp0: stp@e100bb0 { diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 5a75283d17f1..6031a0272d87 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -497,7 +497,7 @@ void __init ltq_soc_init(void) ifccr = CGU_IFCCR_VR9; pcicr = CGU_PCICR_VR9; } else { - clkdev_add_pmu("1e180000.etop", NULL, 1, 0, PMU_PPE); + clkdev_add_pmu("1e180000.ethernet", NULL, 1, 0, PMU_PPE); } if (!of_machine_is_compatible("lantiq,ase")) @@ -531,9 +531,9 @@ void __init ltq_soc_init(void) CLOCK_133M, CLOCK_133M); clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0); clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P); - clkdev_add_pmu("1e180000.etop", "ppe", 1, 0, PMU_PPE); - clkdev_add_cgu("1e180000.etop", "ephycgu", CGU_EPHY); - clkdev_add_pmu("1e180000.etop", "ephy", 1, 0, PMU_EPHY); + clkdev_add_pmu("1e180000.ethernet", "ppe", 1, 0, PMU_PPE); + clkdev_add_cgu("1e180000.ethernet", "ephycgu", CGU_EPHY); + clkdev_add_pmu("1e180000.ethernet", "ephy", 1, 0, PMU_EPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_ASE_SDIO); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); } else if (of_machine_is_compatible("lantiq,grx390")) { @@ -592,7 +592,7 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM); clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 0, PMU_USB1_P); clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1 | PMU_AHBM); - clkdev_add_pmu("1e180000.etop", "switch", 1, 0, PMU_SWITCH); + clkdev_add_pmu("1e180000.ethernet", "switch", 1, 0, PMU_SWITCH); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index 42724bf7e90e..03f1d7319049 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -297,8 +297,9 @@ reg-names = "dwmac", "apb"; interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; @@ -319,8 +320,9 @@ reg-names = "dwmac", "apb"; interrupts = <66 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 1d073acd05a7..cea3de4dce8c 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -530,6 +530,9 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l lowcore_address + sizeof(struct lowcore), POPULATE_LOWCORE); for_each_physmem_usable_range(i, &start, &end) { + /* Do not map lowcore with identity mapping */ + if (!start) + start = sizeof(struct lowcore); pgtable_populate((unsigned long)__identity_va(start), (unsigned long)__identity_va(end), POPULATE_IDENTITY); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6b33429f1c4d..5e616bc988ac 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -5,6 +5,7 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y @@ -19,6 +20,7 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_SCHED_PROXY_EXEC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y @@ -42,6 +44,7 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DM_CRYPT=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -105,6 +108,7 @@ CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y +CONFIG_ZONE_DEVICE=y CONFIG_PERCPU_STATS=y CONFIG_GUP_TEST=y CONFIG_ANON_VMA_NAME=y @@ -223,17 +227,19 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m CONFIG_NETFILTER_XT_TARGET_CT=m CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HL=m CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m -CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_SECMARK=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m @@ -248,6 +254,7 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m CONFIG_NETFILTER_XT_MATCH_CONNMARK=m CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m @@ -318,16 +325,8 @@ CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -340,15 +339,9 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_IP6_NF_SECURITY=m -CONFIG_IP6_NF_NAT=m -CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_IP_SCTP=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -383,6 +376,7 @@ CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m @@ -504,6 +498,7 @@ CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m +CONFIG_OVPN=m CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m @@ -641,6 +636,7 @@ CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m CONFIG_VHOST_VDPA=m +CONFIG_DEV_DAX=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -665,6 +661,7 @@ CONFIG_NILFS2_FS=m CONFIG_BCACHEFS_FS=y CONFIG_BCACHEFS_QUOTA=y CONFIG_BCACHEFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -755,6 +752,8 @@ CONFIG_HARDENED_USERCOPY=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_SELFTESTS=y +CONFIG_CRYPTO_SELFTESTS_FULL=y +CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_BENCHMARK=m @@ -783,7 +782,6 @@ CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_MD4=m @@ -822,6 +820,7 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CRYPTO_KRB5=m CONFIG_CRYPTO_KRB5_SELFTESTS=y CONFIG_CORDIC=m +CONFIG_TRACE_MMIO_ACCESS=y CONFIG_RANDOM32_SELFTEST=y CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b75eb2775850..094599cdaf4d 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -4,6 +4,7 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y @@ -17,6 +18,7 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_SCHED_PROXY_EXEC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y @@ -40,11 +42,12 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DM_CRYPT=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y -CONFIG_HZ_100=y +CONFIG_HZ_1000=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y @@ -97,6 +100,7 @@ CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y +CONFIG_ZONE_DEVICE=y CONFIG_PERCPU_STATS=y CONFIG_ANON_VMA_NAME=y CONFIG_USERFAULTFD=y @@ -214,17 +218,19 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m CONFIG_NETFILTER_XT_TARGET_CT=m CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HL=m CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m -CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_SECMARK=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m @@ -239,6 +245,7 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m CONFIG_NETFILTER_XT_MATCH_CONNMARK=m CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m @@ -309,16 +316,8 @@ CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -331,15 +330,9 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_IP6_NF_SECURITY=m -CONFIG_IP6_NF_NAT=m -CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_IP_SCTP=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -373,6 +366,7 @@ CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m @@ -494,6 +488,7 @@ CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m +CONFIG_OVPN=m CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m @@ -631,6 +626,7 @@ CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m CONFIG_VHOST_VDPA=m +CONFIG_DEV_DAX=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -652,6 +648,7 @@ CONFIG_NILFS2_FS=m CONFIG_BCACHEFS_FS=m CONFIG_BCACHEFS_QUOTA=y CONFIG_BCACHEFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -683,7 +680,6 @@ CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y -CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m @@ -741,6 +737,7 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_SELFTESTS=y +CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_BENCHMARK=m @@ -769,7 +766,6 @@ CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_MD4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8163c1702720..ed0b137353ad 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,5 +1,6 @@ CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y # CONFIG_CPU_ISOLATION is not set # CONFIG_UTS_NS is not set @@ -11,7 +12,7 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KEXEC=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 -CONFIG_HZ_100=y +CONFIG_HZ_1000=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set # CONFIG_AP is not set diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 5d9effb0867c..41a0d2066fa0 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -6,6 +6,7 @@ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ +#include <linux/security.h> #include <linux/slab.h> #include "hypfs.h" @@ -66,23 +67,27 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) long rc; mutex_lock(&df->lock); - if (df->unlocked_ioctl) - rc = df->unlocked_ioctl(file, cmd, arg); - else - rc = -ENOTTY; + rc = df->unlocked_ioctl(file, cmd, arg); mutex_unlock(&df->lock); return rc; } -static const struct file_operations dbfs_ops = { +static const struct file_operations dbfs_ops_ioctl = { .read = dbfs_read, .unlocked_ioctl = dbfs_ioctl, }; +static const struct file_operations dbfs_ops = { + .read = dbfs_read, +}; + void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df) { - df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, - &dbfs_ops); + const struct file_operations *fops = &dbfs_ops; + + if (df->unlocked_ioctl && !security_locked_down(LOCKDOWN_DEBUGFS)) + fops = &dbfs_ops_ioctl; + df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops); mutex_init(&df->lock); } diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index d44725d37e30..849db20e7165 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -28,7 +28,6 @@ * #define APC_DEBUG_LED */ -#define APC_MINOR MISC_DYNAMIC_MINOR #define APC_OBPNAME "power-management" #define APC_DEVNAME "apc" @@ -138,7 +137,7 @@ static const struct file_operations apc_fops = { .llseek = noop_llseek, }; -static struct miscdevice apc_miscdev = { APC_MINOR, APC_DEVNAME, &apc_fops }; +static struct miscdevice apc_miscdev = { MISC_DYNAMIC_MINOR, APC_DEVNAME, &apc_fops }; static int apc_probe(struct platform_device *op) { diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 916bac09b464..63e037e94e4c 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -106,5 +106,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index 7a706db87b93..a34cd19796f9 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -785,6 +785,7 @@ static void __head svsm_pval_4k_page(unsigned long paddr, bool validate) pc->entry[0].page_size = RMP_PG_SIZE_4K; pc->entry[0].action = validate; pc->entry[0].ignore_cf = 0; + pc->entry[0].rsvd = 0; pc->entry[0].pfn = paddr >> PAGE_SHIFT; /* Protocol 0, Call ID 1 */ @@ -810,6 +811,13 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, if (ret) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } /* diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index fc59ce78c477..14ef5908fb27 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -227,6 +227,7 @@ static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action, pe->page_size = RMP_PG_SIZE_4K; pe->action = action; pe->ignore_cf = 0; + pe->rsvd = 0; pe->pfn = pfn; pe++; @@ -257,6 +258,7 @@ static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int d pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K; pe->action = e->operation == SNP_PAGE_STATE_PRIVATE; pe->ignore_cf = 0; + pe->rsvd = 0; pe->pfn = e->gfn; pe++; @@ -358,10 +360,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/coco/sev/vc-handle.c b/arch/x86/coco/sev/vc-handle.c index faf1fce89ed4..c3b4acbde0d8 100644 --- a/arch/x86/coco/sev/vc-handle.c +++ b/arch/x86/coco/sev/vc-handle.c @@ -371,29 +371,30 @@ static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write) * executing with Secure TSC enabled, so special handling is required for * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ. */ -static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write) +static enum es_result __vc_handle_secure_tsc_msrs(struct es_em_ctxt *ctxt, bool write) { + struct pt_regs *regs = ctxt->regs; u64 tsc; /* - * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled. - * Terminate the SNP guest when the interception is enabled. + * Writing to MSR_IA32_TSC can cause subsequent reads of the TSC to + * return undefined values, and GUEST_TSC_FREQ is read-only. Generate + * a #GP on all writes. */ - if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) - return ES_VMM_ERROR; + if (write) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } /* - * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC - * to return undefined values, so ignore all writes. - * - * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use - * the value returned by rdtsc_ordered(). + * GUEST_TSC_FREQ read should not be intercepted when Secure TSC is + * enabled. Terminate the guest if a read is attempted. */ - if (write) { - WARN_ONCE(1, "TSC MSR writes are verboten!\n"); - return ES_OK; - } + if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) + return ES_VMM_ERROR; + /* Reads of MSR_IA32_TSC should return the current TSC value. */ tsc = rdtsc_ordered(); regs->ax = lower_32_bits(tsc); regs->dx = upper_32_bits(tsc); @@ -416,7 +417,7 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) case MSR_IA32_TSC: case MSR_AMD64_GUEST_TSC_FREQ: if (sev_status & MSR_AMD64_SNP_SECURE_TSC) - return __vc_handle_secure_tsc_msrs(regs, write); + return __vc_handle_secure_tsc_msrs(ctxt, write); break; default: break; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 602957dd2609..06fc0479a23f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -218,6 +218,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h deleted file mode 100644 index d5749b25fa10..000000000000 --- a/arch/x86/include/asm/cpuid.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef _ASM_X86_CPUID_H -#define _ASM_X86_CPUID_H - -#include <asm/cpuid/api.h> - -#endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 89075ff19afa..02236962fdb1 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -619,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); + +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -634,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} +static inline void sev_evict_cache(void *va, int npages) {} #endif #endif diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 59a62c3780a2..a16d4631547c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -94,12 +94,13 @@ DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); #ifdef MODULE #define __ADDRESSABLE_xen_hypercall #else -#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#define __ADDRESSABLE_xen_hypercall \ + __stringify(.global STATIC_CALL_KEY(xen_hypercall);) #endif #define __HYPERCALL \ __ADDRESSABLE_xen_hypercall \ - "call __SCT__xen_hypercall" + __stringify(call STATIC_CALL_TRAMP(xen_hypercall)) #define __HYPERCALL_ENTRY(x) "a" (x) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a5ece6ebe8a7..a6f88ca1a6b4 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1326,8 +1326,8 @@ static const char * const s5_reset_reason_txt[] = { static __init int print_s5_reset_status_mmio(void) { - unsigned long value; void __iomem *addr; + u32 value; int i; if (!cpu_feature_enabled(X86_FEATURE_ZEN)) @@ -1340,12 +1340,16 @@ static __init int print_s5_reset_status_mmio(void) value = ioread32(addr); iounmap(addr); + /* Value with "all bits set" is an error response and should be ignored. */ + if (value == U32_MAX) + return 0; + for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) { if (!(value & BIT(i))) continue; if (s5_reset_reason_txt[i]) { - pr_info("x86/amd: Previous system reset reason [0x%08lx]: %s\n", + pr_info("x86/amd: Previous system reset reason [0x%08x]: %s\n", value, s5_reset_reason_txt[i]); } } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b74bf937cd9f..49ef1b832c1a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -386,7 +386,6 @@ static bool __init should_mitigate_vuln(unsigned int bug) case X86_BUG_SPECTRE_V2: case X86_BUG_RETBLEED: - case X86_BUG_SRSO: case X86_BUG_L1TF: case X86_BUG_ITS: return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) || @@ -1069,10 +1068,8 @@ static void __init gds_select_mitigation(void) if (gds_mitigation == GDS_MITIGATION_AUTO) { if (should_mitigate_vuln(X86_BUG_GDS)) gds_mitigation = GDS_MITIGATION_FULL; - else { + else gds_mitigation = GDS_MITIGATION_OFF; - return; - } } /* No microcode */ @@ -3184,8 +3181,18 @@ static void __init srso_select_mitigation(void) } if (srso_mitigation == SRSO_MITIGATION_AUTO) { - if (should_mitigate_vuln(X86_BUG_SRSO)) { + /* + * Use safe-RET if user->kernel or guest->host protection is + * required. Otherwise the 'microcode' mitigation is sufficient + * to protect the user->user and guest->guest vectors. + */ + if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST) || + (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) && + !boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO))) { srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) || + cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST)) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; } else { srso_mitigation = SRSO_MITIGATION_NONE; return; diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 2154f12766fb..1fda6c3a2b65 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -16,6 +16,7 @@ #include <asm/spec-ctrl.h> #include <asm/delay.h> #include <asm/msr.h> +#include <asm/resctrl.h> #include "cpu.h" @@ -117,6 +118,8 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c) x86_amd_ls_cfg_ssbd_mask = 1ULL << 10; } } + + resctrl_cpu_detect(c); } static void early_init_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b4a1f6732a3a..6b868afb26c3 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -48,6 +48,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 12ed75c1b567..28e4fd65c9da 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1881,19 +1881,20 @@ long fpu_xstate_prctl(int option, unsigned long arg2) #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 - * use in the task. + * use in the task. Report -1 if no AVX-512 usage. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { - unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); - long delta; + unsigned long timestamp; + long delta = -1; - if (!timestamp) { - /* - * Report -1 if no AVX512 usage - */ - delta = -1; - } else { + /* AVX-512 usage is not tracked for kernel threads. Don't report anything. */ + if (task->flags & (PF_KTHREAD | PF_USER_WORKER)) + return; + + timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); + + if (timestamp) { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3bf76902f07f..50e51047e1fe 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5847,8 +5847,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, goto out; } - bfqq = kmem_cache_alloc_node(bfq_pool, - GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN, + bfqq = kmem_cache_alloc_node(bfq_pool, GFP_NOWAIT | __GFP_ZERO, bfqd->queue->node); if (bfqq) { diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5936db7f8475..fe9ebd6a2e14 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -394,7 +394,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, /* allocate */ if (!new_blkg) { - new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); + new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; @@ -1467,7 +1467,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); - INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); + INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); @@ -1630,7 +1630,7 @@ retry: pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, - GFP_NOWAIT | __GFP_NOWARN); + GFP_NOWAIT); } if (!pd) { diff --git a/block/blk-core.c b/block/blk-core.c index fdac48aec5ef..4201504158a1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -557,7 +557,7 @@ static inline int bio_check_eod(struct bio *bio) sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); - if (nr_sectors && + if (nr_sectors && maxsector && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 7ed3e71f2fc0..32c65efdda46 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(SQ_SCHED), QUEUE_FLAG_NAME(DISABLE_WBT_DEF), QUEUE_FLAG_NAME(NO_ELV_SWITCH), + QUEUE_FLAG_NAME(QOS_ENABLED), }; #undef QUEUE_FLAG_NAME diff --git a/block/blk-mq.c b/block/blk-mq.c index b67d6c02eceb..ba3a4b77f578 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -5033,6 +5033,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, unsigned int memflags; int i; struct xarray elv_tbl, et_tbl; + bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); @@ -5056,9 +5057,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_sysfs_unregister_hctxs(q); } - list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_freeze_queue_nomemsave(q); - /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5068,6 +5066,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (blk_mq_elv_switch_none(q, &elv_tbl)) goto switch_back; + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_freeze_queue_nomemsave(q); + queues_frozen = true; if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) goto switch_back; @@ -5091,8 +5092,12 @@ fallback: } switch_back: /* The blk_mq_elv_switch_back unfreezes queue for us. */ - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { + /* switch_back expects queue to be frozen */ + if (!queues_frozen) + blk_mq_freeze_queue_nomemsave(q); blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl); + } list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 848591fb3c57..654478dfbc20 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -2,8 +2,6 @@ #include "blk-rq-qos.h" -__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos); - /* * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, * false if 'v' + 1 would be bigger than 'below'. @@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q) struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); - static_branch_dec(&block_rq_qos); } + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); mutex_unlock(&q->rq_qos_mutex); } @@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - static_branch_inc(&block_rq_qos); + blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); @@ -377,6 +375,8 @@ void rq_qos_del(struct rq_qos *rqos) break; } } + if (!q->rq_qos) + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 39749f4066fb..1fe22000a379 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -12,7 +12,6 @@ #include "blk-mq-debugfs.h" struct blk_mq_debugfs_attr; -extern struct static_key_false block_rq_qos; enum rq_qos_id { RQ_QOS_WBT, @@ -113,43 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos && - !blk_rq_is_passthrough(rq)) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } static inline void rq_qos_done_bio(struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && - bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) || - bio_flagged(bio, BIO_QOS_MERGED))) { - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (q->rq_qos) - __rq_qos_done_bio(q->rq_qos, bio); - } + struct request_queue *q; + + if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) && + !bio_flagged(bio, BIO_QOS_MERGED))) + return; + + q = bdev_get_queue(bio->bi_bdev); + + /* + * If a bio has BIO_QOS_xxx set, it implicitly implies that + * q->rq_qos is present. So, we skip re-checking q->rq_qos + * here as an extra optimization and directly call + * __rq_qos_done_bio(). + */ + __rq_qos_done_bio(q->rq_qos, bio); } static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } @@ -158,14 +169,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } @@ -173,7 +186,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq, static inline void rq_qos_queue_depth_changed(struct request_queue *q) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 07874e9b609f..d6438e6c276d 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -157,16 +157,14 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: if (bi->pi_tuple_size) { - pr_warn("pi_tuple_size must be 0 when checksum type \ - is none\n"); + pr_warn("pi_tuple_size must be 0 when checksum type is none\n"); return -EINVAL; } break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) { - pr_warn("pi_tuple_size mismatch for T10 PI: expected \ - %zu, got %u\n", + pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n", sizeof(struct t10_pi_tuple), bi->pi_tuple_size); return -EINVAL; @@ -174,8 +172,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) break; case BLK_INTEGRITY_CSUM_CRC64: if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) { - pr_warn("pi_tuple_size mismatch for CRC64 PI: \ - expected %zu, got %u\n", + pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n", sizeof(struct crc64_pi_tuple), bi->pi_tuple_size); return -EINVAL; @@ -972,6 +969,8 @@ bool queue_limits_stack_integrity(struct queue_limits *t, goto incompatible; if (ti->csum_type != bi->csum_type) goto incompatible; + if (ti->pi_tuple_size != bi->pi_tuple_size) + goto incompatible; if ((ti->flags & BLK_INTEGRITY_REF_TAG) != (bi->flags & BLK_INTEGRITY_REF_TAG)) goto incompatible; @@ -980,6 +979,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t, ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) | (bi->flags & BLK_INTEGRITY_REF_TAG); ti->csum_type = bi->csum_type; + ti->pi_tuple_size = bi->pi_tuple_size; ti->metadata_size = bi->metadata_size; ti->pi_offset = bi->pi_offset; ti->interval_exp = bi->interval_exp; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 396cded255ea..4a7f1a349998 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -847,7 +847,7 @@ static void blk_queue_release(struct kobject *kobj) /* nothing to do here, all data is associated with the parent gendisk */ } -static const struct kobj_type blk_queue_ktype = { +const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, @@ -875,15 +875,14 @@ int blk_register_queue(struct gendisk *disk) struct request_queue *q = disk->queue; int ret; - kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) - goto out_put_queue_kobj; + return ret; if (queue_is_mq(q)) { ret = blk_mq_sysfs_register(disk); if (ret) - goto out_put_queue_kobj; + goto out_del_queue_kobj; } mutex_lock(&q->sysfs_lock); @@ -903,9 +902,9 @@ int blk_register_queue(struct gendisk *disk) if (queue_is_mq(q)) elevator_set_default(q); - wbt_enable_default(disk); blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); + wbt_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); @@ -934,8 +933,8 @@ out_debugfs_remove: mutex_unlock(&q->sysfs_lock); if (queue_is_mq(q)) blk_mq_sysfs_unregister(disk); -out_put_queue_kobj: - kobject_put(&disk->queue_kobj); +out_del_queue_kobj: + kobject_del(&disk->queue_kobj); return ret; } @@ -986,5 +985,4 @@ void blk_unregister_queue(struct gendisk *disk) elevator_set_none(q); blk_debugfs_remove(disk); - kobject_put(&disk->queue_kobj); } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index a50d4cd55f41..eb8037bae0bd 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -85,8 +85,8 @@ struct rq_wb { u64 sync_issue; void *sync_cookie; - unsigned long last_issue; /* last non-throttled issue */ - unsigned long last_comp; /* last non-throttled comp */ + unsigned long last_issue; /* issue time of last read rq */ + unsigned long last_comp; /* completion time of last read rq */ unsigned long min_lat_nsec; struct rq_qos rqos; struct rq_wait rq_wait[WBT_NUM_RWQ]; @@ -248,13 +248,14 @@ static void wbt_done(struct rq_qos *rqos, struct request *rq) struct rq_wb *rwb = RQWB(rqos); if (!wbt_is_tracked(rq)) { - if (rwb->sync_cookie == rq) { - rwb->sync_issue = 0; - rwb->sync_cookie = NULL; - } + if (wbt_is_read(rq)) { + if (rwb->sync_cookie == rq) { + rwb->sync_issue = 0; + rwb->sync_cookie = NULL; + } - if (wbt_is_read(rq)) wb_timestamp(rwb, &rwb->last_comp); + } } else { WARN_ON_ONCE(rq == rwb->sync_cookie); __wbt_done(rqos, wbt_flags(rq)); diff --git a/block/blk.h b/block/blk.h index 0a2eccf28ca4..46f566f9b126 100644 --- a/block/blk.h +++ b/block/blk.h @@ -29,6 +29,7 @@ struct elevator_tags; /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) +extern const struct kobj_type blk_queue_ktype; extern struct dentry *blk_debugfs_root; struct blk_flush_queue { diff --git a/block/genhd.c b/block/genhd.c index c26733f6324b..9bbc38d12792 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1303,6 +1303,7 @@ static void disk_release(struct device *dev) disk_free_zone_resources(disk); xa_destroy(&disk->part_tbl); + kobject_put(&disk->queue_kobj); disk->queue->disk = NULL; blk_put_queue(disk->queue); @@ -1486,6 +1487,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, INIT_LIST_HEAD(&disk->slave_bdevs); #endif mutex_init(&disk->rqos_state_mutex); + kobject_init(&disk->queue_kobj, &blk_queue_ktype); return disk; out_erase_part0: diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 601fdbe70179..61472a381904 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -1829,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf) struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv; struct hl_ctx *ctx; - if (!hl_dmabuf) - return; - ctx = hl_dmabuf->ctx; if (hl_dmabuf->memhash_hnode) @@ -1859,7 +1856,12 @@ static int export_dmabuf(struct hl_ctx *ctx, { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct hl_device *hdev = ctx->hdev; - int rc, fd; + CLASS(get_unused_fd, fd)(flags); + + if (fd < 0) { + dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); + return fd; + } exp_info.ops = &habanalabs_dmabuf_ops; exp_info.size = total_size; @@ -1872,13 +1874,6 @@ static int export_dmabuf(struct hl_ctx *ctx, return PTR_ERR(hl_dmabuf->dmabuf); } - fd = dma_buf_fd(hl_dmabuf->dmabuf, flags); - if (fd < 0) { - dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); - rc = fd; - goto err_dma_buf_put; - } - hl_dmabuf->ctx = ctx; hl_ctx_get(hl_dmabuf->ctx); atomic_inc(&ctx->hdev->dmabuf_export_cnt); @@ -1890,13 +1885,9 @@ static int export_dmabuf(struct hl_ctx *ctx, get_file(ctx->hpriv->file_priv->filp); *dmabuf_fd = fd; + fd_install(take_fd(fd), hl_dmabuf->dmabuf->file); return 0; - -err_dma_buf_put: - hl_dmabuf->dmabuf->priv = NULL; - dma_buf_put(hl_dmabuf->dmabuf); - return rc; } static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset) diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c index a38b88baadf2..5722e4128d3c 100644 --- a/drivers/accel/habanalabs/gaudi2/gaudi2.c +++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c @@ -10437,7 +10437,7 @@ end: (u64 *)(lin_dma_pkts_arr), DEBUGFS_WRITE64); WREG32(sob_addr, 0); - kfree(lin_dma_pkts_arr); + kvfree(lin_dma_pkts_arr); return rc; } diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index bf8dc92a373a..2561b045acc7 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -315,7 +315,7 @@ static void __iomem *einj_get_parameter_address(void) memcpy_fromio(&v5param, p, v5param_size); acpi5 = 1; check_vendor_extension(pa_v5, &v5param); - if (available_error_type & ACPI65_EINJV2_SUPP) { + if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) { len = v5param.einjv2_struct.length; offset = offsetof(struct einjv2_extension_struct, component_arr); max_nr_components = (len - offset) / @@ -540,6 +540,9 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, struct set_error_type_with_address *v5param; v5param = kmalloc(v5param_size, GFP_KERNEL); + if (!v5param) + return -ENOMEM; + memcpy_fromio(v5param, einj_param, v5param_size); v5param->type = type; if (type & ACPI5_VENDOR_BIT) { @@ -1091,7 +1094,7 @@ err_put_table: return rc; } -static void __exit einj_remove(struct faux_device *fdev) +static void einj_remove(struct faux_device *fdev) { struct apei_exec_context ctx; @@ -1114,15 +1117,9 @@ static void __exit einj_remove(struct faux_device *fdev) } static struct faux_device *einj_dev; -/* - * einj_remove() lives in .exit.text. For drivers registered via - * platform_driver_probe() this is ok because they cannot get unbound at - * runtime. So mark the driver struct with __refdata to prevent modpost - * triggering a section mismatch warning. - */ -static struct faux_device_ops einj_device_ops __refdata = { +static struct faux_device_ops einj_device_ops = { .probe = einj_probe, - .remove = __exit_p(einj_remove), + .remove = einj_remove, }; static int __init einj_init(void) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 75c7db8b156a..7855bbf752b1 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2033,7 +2033,7 @@ void __init acpi_ec_ecdt_probe(void) goto out; } - if (!strstarts(ecdt_ptr->id, "\\")) { + if (!strlen(ecdt_ptr->id)) { /* * The ECDT table on some MSI notebooks contains invalid data, together * with an empty ID string (""). @@ -2042,9 +2042,13 @@ void __init acpi_ec_ecdt_probe(void) * a "fully qualified reference to the (...) embedded controller device", * so this string always has to start with a backslash. * - * By verifying this we can avoid such faulty ECDT tables in a safe way. + * However some ThinkBook machines have a ECDT table with a valid EC + * description but an invalid ID string ("_SB.PC00.LPCB.EC0"). + * + * Because of this we only check if the ID string is empty in order to + * avoid the obvious cases. */ - pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id); + pr_err(FW_BUG "Ignoring ECDT due to empty ID string\n"); goto out; } diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c index 318683744ed1..11b1c2828005 100644 --- a/drivers/acpi/pfr_update.c +++ b/drivers/acpi/pfr_update.c @@ -329,7 +329,7 @@ static bool applicable_image(const void *data, struct pfru_update_cap_info *cap, if (type == PFRU_CODE_INJECT_TYPE) return payload_hdr->rt_ver >= cap->code_rt_version; - return payload_hdr->rt_ver >= cap->drv_rt_version; + return payload_hdr->svn_ver >= cap->drv_svn; } static void print_update_debug_info(struct pfru_updated_result *result, diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 755003bf3a45..8972446b7162 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -180,7 +180,7 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) struct acpi_processor *pr = per_cpu(processors, cpu); int ret; - if (!pr || !pr->performance) + if (!pr) continue; /* @@ -197,6 +197,9 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, ret); + if (!pr->performance) + continue; + ret = acpi_processor_get_platform_limit(pr); if (ret) pr_err("Failed to update freq constraint for CPU%d (%d)\n", diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index 5b3b8041f827..e2e402c9d175 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -4,6 +4,7 @@ menu "Android" config ANDROID_BINDER_IPC bool "Android Binder IPC Driver" depends on MMU + depends on NET default n help Binder is used in Android for both communication between processes, @@ -13,6 +14,19 @@ config ANDROID_BINDER_IPC Android process, using Binder to identify, invoke and pass arguments between said processes. +config ANDROID_BINDER_IPC_RUST + bool "Rust version of Android Binder IPC Driver" + depends on RUST && MMU && !ANDROID_BINDER_IPC + help + This enables the Rust implementation of the Binder driver. + + Binder is used in Android for both communication between processes, + and remote method invocation. + + This means one Android process can call a method/routine in another + Android process, using Binder to identify, invoke and pass arguments + between said processes. + config ANDROID_BINDERFS bool "Android Binderfs filesystem" depends on ANDROID_BINDER_IPC @@ -27,7 +41,7 @@ config ANDROID_BINDERFS config ANDROID_BINDER_DEVICES string "Android Binder devices" - depends on ANDROID_BINDER_IPC + depends on ANDROID_BINDER_IPC || ANDROID_BINDER_IPC_RUST default "binder,hwbinder,vndbinder" help Default value for the binder.devices parameter. diff --git a/drivers/android/Makefile b/drivers/android/Makefile index c5d47be0276c..e0c650d3898e 100644 --- a/drivers/android/Makefile +++ b/drivers/android/Makefile @@ -2,5 +2,6 @@ ccflags-y += -I$(src) # needed for trace events obj-$(CONFIG_ANDROID_BINDERFS) += binderfs.o -obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o +obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o binder_netlink.o obj-$(CONFIG_ANDROID_BINDER_ALLOC_KUNIT_TEST) += tests/ +obj-$(CONFIG_ANDROID_BINDER_IPC_RUST) += binder/ diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 312b462e349d..8c99ceaa303b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -74,6 +74,7 @@ #include <linux/cacheflush.h> +#include "binder_netlink.h" #include "binder_internal.h" #include "binder_trace.h" @@ -2993,6 +2994,69 @@ static void binder_set_txn_from_error(struct binder_transaction *t, int id, binder_thread_dec_tmpref(from); } +/** + * binder_netlink_report() - report a transaction failure via netlink + * @proc: the binder proc sending the transaction + * @t: the binder transaction that failed + * @data_size: the user provided data size for the transaction + * @error: enum binder_driver_return_protocol returned to sender + */ +static void binder_netlink_report(struct binder_proc *proc, + struct binder_transaction *t, + u32 data_size, + u32 error) +{ + const char *context = proc->context->name; + struct sk_buff *skb; + void *hdr; + + if (!genl_has_listeners(&binder_nl_family, &init_net, + BINDER_NLGRP_REPORT)) + return; + + trace_binder_netlink_report(context, t, data_size, error); + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return; + + hdr = genlmsg_put(skb, 0, 0, &binder_nl_family, 0, BINDER_CMD_REPORT); + if (!hdr) + goto free_skb; + + if (nla_put_u32(skb, BINDER_A_REPORT_ERROR, error) || + nla_put_string(skb, BINDER_A_REPORT_CONTEXT, context) || + nla_put_u32(skb, BINDER_A_REPORT_FROM_PID, t->from_pid) || + nla_put_u32(skb, BINDER_A_REPORT_FROM_TID, t->from_tid)) + goto cancel_skb; + + if (t->to_proc && + nla_put_u32(skb, BINDER_A_REPORT_TO_PID, t->to_proc->pid)) + goto cancel_skb; + + if (t->to_thread && + nla_put_u32(skb, BINDER_A_REPORT_TO_TID, t->to_thread->pid)) + goto cancel_skb; + + if (t->is_reply && nla_put_flag(skb, BINDER_A_REPORT_IS_REPLY)) + goto cancel_skb; + + if (nla_put_u32(skb, BINDER_A_REPORT_FLAGS, t->flags) || + nla_put_u32(skb, BINDER_A_REPORT_CODE, t->code) || + nla_put_u32(skb, BINDER_A_REPORT_DATA_SIZE, data_size)) + goto cancel_skb; + + genlmsg_end(skb, hdr); + genlmsg_multicast(&binder_nl_family, skb, 0, BINDER_NLGRP_REPORT, + GFP_KERNEL); + return; + +cancel_skb: + genlmsg_cancel(skb, hdr); +free_skb: + nlmsg_free(skb); +} + static void binder_transaction(struct binder_proc *proc, struct binder_thread *thread, struct binder_transaction_data *tr, int reply, @@ -3042,6 +3106,32 @@ static void binder_transaction(struct binder_proc *proc, binder_set_extended_error(&thread->ee, t_debug_id, BR_OK, 0); binder_inner_proc_unlock(proc); + t = kzalloc(sizeof(*t), GFP_KERNEL); + if (!t) { + binder_txn_error("%d:%d cannot allocate transaction\n", + thread->pid, proc->pid); + return_error = BR_FAILED_REPLY; + return_error_param = -ENOMEM; + return_error_line = __LINE__; + goto err_alloc_t_failed; + } + INIT_LIST_HEAD(&t->fd_fixups); + binder_stats_created(BINDER_STAT_TRANSACTION); + spin_lock_init(&t->lock); + t->debug_id = t_debug_id; + t->start_time = t_start_time; + t->from_pid = proc->pid; + t->from_tid = thread->pid; + t->sender_euid = task_euid(proc->tsk); + t->code = tr->code; + t->flags = tr->flags; + t->priority = task_nice(current); + t->work.type = BINDER_WORK_TRANSACTION; + t->is_async = !reply && (tr->flags & TF_ONE_WAY); + t->is_reply = reply; + if (!reply && !(tr->flags & TF_ONE_WAY)) + t->from = thread; + if (reply) { binder_inner_proc_lock(proc); in_reply_to = thread->transaction_stack; @@ -3228,24 +3318,13 @@ static void binder_transaction(struct binder_proc *proc, } binder_inner_proc_unlock(proc); } + + t->to_proc = target_proc; + t->to_thread = target_thread; if (target_thread) e->to_thread = target_thread->pid; e->to_proc = target_proc->pid; - /* TODO: reuse incoming transaction for reply */ - t = kzalloc(sizeof(*t), GFP_KERNEL); - if (t == NULL) { - binder_txn_error("%d:%d cannot allocate transaction\n", - thread->pid, proc->pid); - return_error = BR_FAILED_REPLY; - return_error_param = -ENOMEM; - return_error_line = __LINE__; - goto err_alloc_t_failed; - } - INIT_LIST_HEAD(&t->fd_fixups); - binder_stats_created(BINDER_STAT_TRANSACTION); - spin_lock_init(&t->lock); - tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL); if (tcomplete == NULL) { binder_txn_error("%d:%d cannot allocate work for transaction\n", @@ -3257,9 +3336,6 @@ static void binder_transaction(struct binder_proc *proc, } binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE); - t->debug_id = t_debug_id; - t->start_time = t_start_time; - if (reply) binder_debug(BINDER_DEBUG_TRANSACTION, "%d:%d BC_REPLY %d -> %d:%d, data size %lld-%lld-%lld\n", @@ -3275,19 +3351,6 @@ static void binder_transaction(struct binder_proc *proc, (u64)tr->data_size, (u64)tr->offsets_size, (u64)extra_buffers_size); - if (!reply && !(tr->flags & TF_ONE_WAY)) - t->from = thread; - else - t->from = NULL; - t->from_pid = proc->pid; - t->from_tid = thread->pid; - t->sender_euid = task_euid(proc->tsk); - t->to_proc = target_proc; - t->to_thread = target_thread; - t->code = tr->code; - t->flags = tr->flags; - t->priority = task_nice(current); - if (target_node && target_node->txn_security_ctx) { u32 secid; size_t added_size; @@ -3680,11 +3743,13 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_copy_data_failed; } - if (t->buffer->oneway_spam_suspect) + if (t->buffer->oneway_spam_suspect) { tcomplete->type = BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT; - else + binder_netlink_report(proc, t, tr->data_size, + BR_ONEWAY_SPAM_SUSPECT); + } else { tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; - t->work.type = BINDER_WORK_TRANSACTION; + } if (reply) { binder_enqueue_thread_work(thread, tcomplete); @@ -3712,7 +3777,6 @@ static void binder_transaction(struct binder_proc *proc, * the target replies (or there is an error). */ binder_enqueue_deferred_thread_work_ilocked(thread, tcomplete); - t->need_reply = 1; t->from_parent = thread->transaction_stack; thread->transaction_stack = t; binder_inner_proc_unlock(proc); @@ -3733,8 +3797,11 @@ static void binder_transaction(struct binder_proc *proc, * process and is put in a pending queue, waiting for the target * process to be unfrozen. */ - if (return_error == BR_TRANSACTION_PENDING_FROZEN) + if (return_error == BR_TRANSACTION_PENDING_FROZEN) { tcomplete->type = BINDER_WORK_TRANSACTION_PENDING; + binder_netlink_report(proc, t, tr->data_size, + return_error); + } binder_enqueue_thread_work(thread, tcomplete); if (return_error && return_error != BR_TRANSACTION_PENDING_FROZEN) @@ -3783,9 +3850,6 @@ err_get_secctx_failed: err_alloc_tcomplete_failed: if (trace_binder_txn_latency_free_enabled()) binder_txn_latency_free(t); - kfree(t); - binder_stats_deleted(BINDER_STAT_TRANSACTION); -err_alloc_t_failed: err_bad_todo_list: err_bad_call_stack: err_empty_call_stack: @@ -3796,6 +3860,11 @@ err_invalid_target_handle: binder_dec_node_tmpref(target_node); } + binder_netlink_report(proc, t, tr->data_size, return_error); + kfree(t); + binder_stats_deleted(BINDER_STAT_TRANSACTION); +err_alloc_t_failed: + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, "%d:%d transaction %s to %d:%d failed %d/%d/%d, code %u size %lld-%lld line %d\n", proc->pid, thread->pid, reply ? "reply" : @@ -6324,13 +6393,13 @@ static void print_binder_transaction_ilocked(struct seq_file *m, spin_lock(&t->lock); to_proc = t->to_proc; seq_printf(m, - "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d elapsed %lldms", + "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld a%d r%d elapsed %lldms", prefix, t->debug_id, t, t->from_pid, t->from_tid, to_proc ? to_proc->pid : 0, t->to_thread ? t->to_thread->pid : 0, - t->code, t->flags, t->priority, t->need_reply, + t->code, t->flags, t->priority, t->is_async, t->is_reply, ktime_ms_delta(current_time, t->start_time)); spin_unlock(&t->lock); @@ -7062,12 +7131,19 @@ static int __init binder_init(void) } } - ret = init_binderfs(); + ret = genl_register_family(&binder_nl_family); if (ret) goto err_init_binder_device_failed; + ret = init_binderfs(); + if (ret) + goto err_init_binderfs_failed; + return ret; +err_init_binderfs_failed: + genl_unregister_family(&binder_nl_family); + err_init_binder_device_failed: hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) { misc_deregister(&device->miscdev); @@ -7088,5 +7164,3 @@ device_initcall(binder_init); #define CREATE_TRACE_POINTS #include "binder_trace.h" - -MODULE_LICENSE("GPL v2"); diff --git a/drivers/android/binder/Makefile b/drivers/android/binder/Makefile new file mode 100644 index 000000000000..09eabb527fa0 --- /dev/null +++ b/drivers/android/binder/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only +ccflags-y += -I$(src) # needed for trace events + +obj-$(CONFIG_ANDROID_BINDER_IPC_RUST) += rust_binder.o +rust_binder-y := \ + rust_binder_main.o \ + rust_binderfs.o \ + rust_binder_events.o \ + page_range_helper.o diff --git a/drivers/android/binder/allocation.rs b/drivers/android/binder/allocation.rs new file mode 100644 index 000000000000..7f65a9c3a0e5 --- /dev/null +++ b/drivers/android/binder/allocation.rs @@ -0,0 +1,602 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use core::mem::{size_of, size_of_val, MaybeUninit}; +use core::ops::Range; + +use kernel::{ + bindings, + fs::file::{File, FileDescriptorReservation}, + prelude::*, + sync::{aref::ARef, Arc}, + transmute::{AsBytes, FromBytes}, + uaccess::UserSliceReader, + uapi, +}; + +use crate::{ + deferred_close::DeferredFdCloser, + defs::*, + node::{Node, NodeRef}, + process::Process, + DArc, +}; + +#[derive(Default)] +pub(crate) struct AllocationInfo { + /// Range within the allocation where we can find the offsets to the object descriptors. + pub(crate) offsets: Option<Range<usize>>, + /// The target node of the transaction this allocation is associated to. + /// Not set for replies. + pub(crate) target_node: Option<NodeRef>, + /// When this allocation is dropped, call `pending_oneway_finished` on the node. + /// + /// This is used to serialize oneway transaction on the same node. Binder guarantees that + /// oneway transactions to the same node are delivered sequentially in the order they are sent. + pub(crate) oneway_node: Option<DArc<Node>>, + /// Zero the data in the buffer on free. + pub(crate) clear_on_free: bool, + /// List of files embedded in this transaction. + file_list: FileList, +} + +/// Represents an allocation that the kernel is currently using. +/// +/// When allocations are idle, the range allocator holds the data related to them. +/// +/// # Invariants +/// +/// This allocation corresponds to an allocation in the range allocator, so the relevant pages are +/// marked in use in the page range. +pub(crate) struct Allocation { + pub(crate) offset: usize, + size: usize, + pub(crate) ptr: usize, + pub(crate) process: Arc<Process>, + allocation_info: Option<AllocationInfo>, + free_on_drop: bool, + pub(crate) oneway_spam_detected: bool, + #[allow(dead_code)] + pub(crate) debug_id: usize, +} + +impl Allocation { + pub(crate) fn new( + process: Arc<Process>, + debug_id: usize, + offset: usize, + size: usize, + ptr: usize, + oneway_spam_detected: bool, + ) -> Self { + Self { + process, + offset, + size, + ptr, + debug_id, + oneway_spam_detected, + allocation_info: None, + free_on_drop: true, + } + } + + fn size_check(&self, offset: usize, size: usize) -> Result { + let overflow_fail = offset.checked_add(size).is_none(); + let cmp_size_fail = offset.wrapping_add(size) > self.size; + if overflow_fail || cmp_size_fail { + return Err(EFAULT); + } + Ok(()) + } + + pub(crate) fn copy_into( + &self, + reader: &mut UserSliceReader, + offset: usize, + size: usize, + ) -> Result { + self.size_check(offset, size)?; + + // SAFETY: While this object exists, the range allocator will keep the range allocated, and + // in turn, the pages will be marked as in use. + unsafe { + self.process + .pages + .copy_from_user_slice(reader, self.offset + offset, size) + } + } + + pub(crate) fn read<T: FromBytes>(&self, offset: usize) -> Result<T> { + self.size_check(offset, size_of::<T>())?; + + // SAFETY: While this object exists, the range allocator will keep the range allocated, and + // in turn, the pages will be marked as in use. + unsafe { self.process.pages.read(self.offset + offset) } + } + + pub(crate) fn write<T: ?Sized>(&self, offset: usize, obj: &T) -> Result { + self.size_check(offset, size_of_val::<T>(obj))?; + + // SAFETY: While this object exists, the range allocator will keep the range allocated, and + // in turn, the pages will be marked as in use. + unsafe { self.process.pages.write(self.offset + offset, obj) } + } + + pub(crate) fn fill_zero(&self) -> Result { + // SAFETY: While this object exists, the range allocator will keep the range allocated, and + // in turn, the pages will be marked as in use. + unsafe { self.process.pages.fill_zero(self.offset, self.size) } + } + + pub(crate) fn keep_alive(mut self) { + self.process + .buffer_make_freeable(self.offset, self.allocation_info.take()); + self.free_on_drop = false; + } + + pub(crate) fn set_info(&mut self, info: AllocationInfo) { + self.allocation_info = Some(info); + } + + pub(crate) fn get_or_init_info(&mut self) -> &mut AllocationInfo { + self.allocation_info.get_or_insert_with(Default::default) + } + + pub(crate) fn set_info_offsets(&mut self, offsets: Range<usize>) { + self.get_or_init_info().offsets = Some(offsets); + } + + pub(crate) fn set_info_oneway_node(&mut self, oneway_node: DArc<Node>) { + self.get_or_init_info().oneway_node = Some(oneway_node); + } + + pub(crate) fn set_info_clear_on_drop(&mut self) { + self.get_or_init_info().clear_on_free = true; + } + + pub(crate) fn set_info_target_node(&mut self, target_node: NodeRef) { + self.get_or_init_info().target_node = Some(target_node); + } + + /// Reserve enough space to push at least `num_fds` fds. + pub(crate) fn info_add_fd_reserve(&mut self, num_fds: usize) -> Result { + self.get_or_init_info() + .file_list + .files_to_translate + .reserve(num_fds, GFP_KERNEL)?; + + Ok(()) + } + + pub(crate) fn info_add_fd( + &mut self, + file: ARef<File>, + buffer_offset: usize, + close_on_free: bool, + ) -> Result { + self.get_or_init_info().file_list.files_to_translate.push( + FileEntry { + file, + buffer_offset, + close_on_free, + }, + GFP_KERNEL, + )?; + + Ok(()) + } + + pub(crate) fn set_info_close_on_free(&mut self, cof: FdsCloseOnFree) { + self.get_or_init_info().file_list.close_on_free = cof.0; + } + + pub(crate) fn translate_fds(&mut self) -> Result<TranslatedFds> { + let file_list = match self.allocation_info.as_mut() { + Some(info) => &mut info.file_list, + None => return Ok(TranslatedFds::new()), + }; + + let files = core::mem::take(&mut file_list.files_to_translate); + + let num_close_on_free = files.iter().filter(|entry| entry.close_on_free).count(); + let mut close_on_free = KVec::with_capacity(num_close_on_free, GFP_KERNEL)?; + + let mut reservations = KVec::with_capacity(files.len(), GFP_KERNEL)?; + for file_info in files { + let res = FileDescriptorReservation::get_unused_fd_flags(bindings::O_CLOEXEC)?; + let fd = res.reserved_fd(); + self.write::<u32>(file_info.buffer_offset, &fd)?; + + reservations.push( + Reservation { + res, + file: file_info.file, + }, + GFP_KERNEL, + )?; + if file_info.close_on_free { + close_on_free.push(fd, GFP_KERNEL)?; + } + } + + Ok(TranslatedFds { + reservations, + close_on_free: FdsCloseOnFree(close_on_free), + }) + } + + /// Should the looper return to userspace when freeing this allocation? + pub(crate) fn looper_need_return_on_free(&self) -> bool { + // Closing fds involves pushing task_work for execution when we return to userspace. Hence, + // we should return to userspace asap if we are closing fds. + match self.allocation_info { + Some(ref info) => !info.file_list.close_on_free.is_empty(), + None => false, + } + } +} + +impl Drop for Allocation { + fn drop(&mut self) { + if !self.free_on_drop { + return; + } + + if let Some(mut info) = self.allocation_info.take() { + if let Some(oneway_node) = info.oneway_node.as_ref() { + oneway_node.pending_oneway_finished(); + } + + info.target_node = None; + + if let Some(offsets) = info.offsets.clone() { + let view = AllocationView::new(self, offsets.start); + for i in offsets.step_by(size_of::<usize>()) { + if view.cleanup_object(i).is_err() { + pr_warn!("Error cleaning up object at offset {}\n", i) + } + } + } + + for &fd in &info.file_list.close_on_free { + let closer = match DeferredFdCloser::new(GFP_KERNEL) { + Ok(closer) => closer, + Err(kernel::alloc::AllocError) => { + // Ignore allocation failures. + break; + } + }; + + // Here, we ignore errors. The operation can fail if the fd is not valid, or if the + // method is called from a kthread. However, this is always called from a syscall, + // so the latter case cannot happen, and we don't care about the first case. + let _ = closer.close_fd(fd); + } + + if info.clear_on_free { + if let Err(e) = self.fill_zero() { + pr_warn!("Failed to clear data on free: {:?}", e); + } + } + } + + self.process.buffer_raw_free(self.ptr); + } +} + +/// A wrapper around `Allocation` that is being created. +/// +/// If the allocation is destroyed while wrapped in this wrapper, then the allocation will be +/// considered to be part of a failed transaction. Successful transactions avoid that by calling +/// `success`, which skips the destructor. +#[repr(transparent)] +pub(crate) struct NewAllocation(pub(crate) Allocation); + +impl NewAllocation { + pub(crate) fn success(self) -> Allocation { + // This skips the destructor. + // + // SAFETY: This type is `#[repr(transparent)]`, so the layout matches. + unsafe { core::mem::transmute(self) } + } +} + +impl core::ops::Deref for NewAllocation { + type Target = Allocation; + fn deref(&self) -> &Allocation { + &self.0 + } +} + +impl core::ops::DerefMut for NewAllocation { + fn deref_mut(&mut self) -> &mut Allocation { + &mut self.0 + } +} + +/// A view into the beginning of an allocation. +/// +/// All attempts to read or write outside of the view will fail. To intentionally access outside of +/// this view, use the `alloc` field of this struct directly. +pub(crate) struct AllocationView<'a> { + pub(crate) alloc: &'a mut Allocation, + limit: usize, +} + +impl<'a> AllocationView<'a> { + pub(crate) fn new(alloc: &'a mut Allocation, limit: usize) -> Self { + AllocationView { alloc, limit } + } + + pub(crate) fn read<T: FromBytes>(&self, offset: usize) -> Result<T> { + if offset.checked_add(size_of::<T>()).ok_or(EINVAL)? > self.limit { + return Err(EINVAL); + } + self.alloc.read(offset) + } + + pub(crate) fn write<T: AsBytes>(&self, offset: usize, obj: &T) -> Result { + if offset.checked_add(size_of::<T>()).ok_or(EINVAL)? > self.limit { + return Err(EINVAL); + } + self.alloc.write(offset, obj) + } + + pub(crate) fn copy_into( + &self, + reader: &mut UserSliceReader, + offset: usize, + size: usize, + ) -> Result { + if offset.checked_add(size).ok_or(EINVAL)? > self.limit { + return Err(EINVAL); + } + self.alloc.copy_into(reader, offset, size) + } + + pub(crate) fn transfer_binder_object( + &self, + offset: usize, + obj: &uapi::flat_binder_object, + strong: bool, + node_ref: NodeRef, + ) -> Result { + let mut newobj = FlatBinderObject::default(); + let node = node_ref.node.clone(); + if Arc::ptr_eq(&node_ref.node.owner, &self.alloc.process) { + // The receiving process is the owner of the node, so send it a binder object (instead + // of a handle). + let (ptr, cookie) = node.get_id(); + newobj.hdr.type_ = if strong { + BINDER_TYPE_BINDER + } else { + BINDER_TYPE_WEAK_BINDER + }; + newobj.flags = obj.flags; + newobj.__bindgen_anon_1.binder = ptr as _; + newobj.cookie = cookie as _; + self.write(offset, &newobj)?; + // Increment the user ref count on the node. It will be decremented as part of the + // destruction of the buffer, when we see a binder or weak-binder object. + node.update_refcount(true, 1, strong); + } else { + // The receiving process is different from the owner, so we need to insert a handle to + // the binder object. + let handle = self + .alloc + .process + .as_arc_borrow() + .insert_or_update_handle(node_ref, false)?; + newobj.hdr.type_ = if strong { + BINDER_TYPE_HANDLE + } else { + BINDER_TYPE_WEAK_HANDLE + }; + newobj.flags = obj.flags; + newobj.__bindgen_anon_1.handle = handle; + if self.write(offset, &newobj).is_err() { + // Decrement ref count on the handle we just created. + let _ = self + .alloc + .process + .as_arc_borrow() + .update_ref(handle, false, strong); + return Err(EINVAL); + } + } + + Ok(()) + } + + fn cleanup_object(&self, index_offset: usize) -> Result { + let offset = self.alloc.read(index_offset)?; + let header = self.read::<BinderObjectHeader>(offset)?; + match header.type_ { + BINDER_TYPE_WEAK_BINDER | BINDER_TYPE_BINDER => { + let obj = self.read::<FlatBinderObject>(offset)?; + let strong = header.type_ == BINDER_TYPE_BINDER; + // SAFETY: The type is `BINDER_TYPE_{WEAK_}BINDER`, so the `binder` field is + // populated. + let ptr = unsafe { obj.__bindgen_anon_1.binder }; + let cookie = obj.cookie; + self.alloc.process.update_node(ptr, cookie, strong); + Ok(()) + } + BINDER_TYPE_WEAK_HANDLE | BINDER_TYPE_HANDLE => { + let obj = self.read::<FlatBinderObject>(offset)?; + let strong = header.type_ == BINDER_TYPE_HANDLE; + // SAFETY: The type is `BINDER_TYPE_{WEAK_}HANDLE`, so the `handle` field is + // populated. + let handle = unsafe { obj.__bindgen_anon_1.handle }; + self.alloc + .process + .as_arc_borrow() + .update_ref(handle, false, strong) + } + _ => Ok(()), + } + } +} + +/// A binder object as it is serialized. +/// +/// # Invariants +/// +/// All bytes must be initialized, and the value of `self.hdr.type_` must be one of the allowed +/// types. +#[repr(C)] +pub(crate) union BinderObject { + hdr: uapi::binder_object_header, + fbo: uapi::flat_binder_object, + fdo: uapi::binder_fd_object, + bbo: uapi::binder_buffer_object, + fdao: uapi::binder_fd_array_object, +} + +/// A view into a `BinderObject` that can be used in a match statement. +pub(crate) enum BinderObjectRef<'a> { + Binder(&'a mut uapi::flat_binder_object), + Handle(&'a mut uapi::flat_binder_object), + Fd(&'a mut uapi::binder_fd_object), + Ptr(&'a mut uapi::binder_buffer_object), + Fda(&'a mut uapi::binder_fd_array_object), +} + +impl BinderObject { + pub(crate) fn read_from(reader: &mut UserSliceReader) -> Result<BinderObject> { + let object = Self::read_from_inner(|slice| { + let read_len = usize::min(slice.len(), reader.len()); + reader.clone_reader().read_slice(&mut slice[..read_len])?; + Ok(()) + })?; + + // If we used a object type smaller than the largest object size, then we've read more + // bytes than we needed to. However, we used `.clone_reader()` to avoid advancing the + // original reader. Now, we call `skip` so that the caller's reader is advanced by the + // right amount. + // + // The `skip` call fails if the reader doesn't have `size` bytes available. This could + // happen if the type header corresponds to an object type that is larger than the rest of + // the reader. + // + // Any extra bytes beyond the size of the object are inaccessible after this call, so + // reading them again from the `reader` later does not result in TOCTOU bugs. + reader.skip(object.size())?; + + Ok(object) + } + + /// Use the provided reader closure to construct a `BinderObject`. + /// + /// The closure should write the bytes for the object into the provided slice. + pub(crate) fn read_from_inner<R>(reader: R) -> Result<BinderObject> + where + R: FnOnce(&mut [u8; size_of::<BinderObject>()]) -> Result<()>, + { + let mut obj = MaybeUninit::<BinderObject>::zeroed(); + + // SAFETY: The lengths of `BinderObject` and `[u8; size_of::<BinderObject>()]` are equal, + // and the byte array has an alignment requirement of one, so the pointer cast is okay. + // Additionally, `obj` was initialized to zeros, so the byte array will not be + // uninitialized. + (reader)(unsafe { &mut *obj.as_mut_ptr().cast() })?; + + // SAFETY: The entire object is initialized, so accessing this field is safe. + let type_ = unsafe { obj.assume_init_ref().hdr.type_ }; + if Self::type_to_size(type_).is_none() { + // The value of `obj.hdr_type_` was invalid. + return Err(EINVAL); + } + + // SAFETY: All bytes are initialized (since we zeroed them at the start) and we checked + // that `self.hdr.type_` is one of the allowed types, so the type invariants are satisfied. + unsafe { Ok(obj.assume_init()) } + } + + pub(crate) fn as_ref(&mut self) -> BinderObjectRef<'_> { + use BinderObjectRef::*; + // SAFETY: The constructor ensures that all bytes of `self` are initialized, and all + // variants of this union accept all initialized bit patterns. + unsafe { + match self.hdr.type_ { + BINDER_TYPE_WEAK_BINDER | BINDER_TYPE_BINDER => Binder(&mut self.fbo), + BINDER_TYPE_WEAK_HANDLE | BINDER_TYPE_HANDLE => Handle(&mut self.fbo), + BINDER_TYPE_FD => Fd(&mut self.fdo), + BINDER_TYPE_PTR => Ptr(&mut self.bbo), + BINDER_TYPE_FDA => Fda(&mut self.fdao), + // SAFETY: By the type invariant, the value of `self.hdr.type_` cannot have any + // other value than the ones checked above. + _ => core::hint::unreachable_unchecked(), + } + } + } + + pub(crate) fn size(&self) -> usize { + // SAFETY: The entire object is initialized, so accessing this field is safe. + let type_ = unsafe { self.hdr.type_ }; + + // SAFETY: The type invariants guarantee that the type field is correct. + unsafe { Self::type_to_size(type_).unwrap_unchecked() } + } + + fn type_to_size(type_: u32) -> Option<usize> { + match type_ { + BINDER_TYPE_WEAK_BINDER => Some(size_of::<uapi::flat_binder_object>()), + BINDER_TYPE_BINDER => Some(size_of::<uapi::flat_binder_object>()), + BINDER_TYPE_WEAK_HANDLE => Some(size_of::<uapi::flat_binder_object>()), + BINDER_TYPE_HANDLE => Some(size_of::<uapi::flat_binder_object>()), + BINDER_TYPE_FD => Some(size_of::<uapi::binder_fd_object>()), + BINDER_TYPE_PTR => Some(size_of::<uapi::binder_buffer_object>()), + BINDER_TYPE_FDA => Some(size_of::<uapi::binder_fd_array_object>()), + _ => None, + } + } +} + +#[derive(Default)] +struct FileList { + files_to_translate: KVec<FileEntry>, + close_on_free: KVec<u32>, +} + +struct FileEntry { + /// The file for which a descriptor will be created in the recipient process. + file: ARef<File>, + /// The offset in the buffer where the file descriptor is stored. + buffer_offset: usize, + /// Whether this fd should be closed when the allocation is freed. + close_on_free: bool, +} + +pub(crate) struct TranslatedFds { + reservations: KVec<Reservation>, + /// If commit is called, then these fds should be closed. (If commit is not called, then they + /// shouldn't be closed.) + close_on_free: FdsCloseOnFree, +} + +struct Reservation { + res: FileDescriptorReservation, + file: ARef<File>, +} + +impl TranslatedFds { + pub(crate) fn new() -> Self { + Self { + reservations: KVec::new(), + close_on_free: FdsCloseOnFree(KVec::new()), + } + } + + pub(crate) fn commit(self) -> FdsCloseOnFree { + for entry in self.reservations { + entry.res.fd_install(entry.file); + } + + self.close_on_free + } +} + +pub(crate) struct FdsCloseOnFree(KVec<u32>); diff --git a/drivers/android/binder/context.rs b/drivers/android/binder/context.rs new file mode 100644 index 000000000000..3d135ec03ca7 --- /dev/null +++ b/drivers/android/binder/context.rs @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{ + error::Error, + list::{List, ListArc, ListLinks}, + prelude::*, + security, + str::{CStr, CString}, + sync::{Arc, Mutex}, + task::Kuid, +}; + +use crate::{error::BinderError, node::NodeRef, process::Process}; + +kernel::sync::global_lock! { + // SAFETY: We call `init` in the module initializer, so it's initialized before first use. + pub(crate) unsafe(uninit) static CONTEXTS: Mutex<ContextList> = ContextList { + list: List::new(), + }; +} + +pub(crate) struct ContextList { + list: List<Context>, +} + +pub(crate) fn get_all_contexts() -> Result<KVec<Arc<Context>>> { + let lock = CONTEXTS.lock(); + + let count = lock.list.iter().count(); + + let mut ctxs = KVec::with_capacity(count, GFP_KERNEL)?; + for ctx in &lock.list { + ctxs.push(Arc::from(ctx), GFP_KERNEL)?; + } + Ok(ctxs) +} + +/// This struct keeps track of the processes using this context, and which process is the context +/// manager. +struct Manager { + node: Option<NodeRef>, + uid: Option<Kuid>, + all_procs: List<Process>, +} + +/// There is one context per binder file (/dev/binder, /dev/hwbinder, etc) +#[pin_data] +pub(crate) struct Context { + #[pin] + manager: Mutex<Manager>, + pub(crate) name: CString, + #[pin] + links: ListLinks, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for Context { untracked; } +} +kernel::list::impl_list_item! { + impl ListItem<0> for Context { + using ListLinks { self.links }; + } +} + +impl Context { + pub(crate) fn new(name: &CStr) -> Result<Arc<Self>> { + let name = CString::try_from(name)?; + let list_ctx = ListArc::pin_init::<Error>( + try_pin_init!(Context { + name, + links <- ListLinks::new(), + manager <- kernel::new_mutex!(Manager { + all_procs: List::new(), + node: None, + uid: None, + }, "Context::manager"), + }), + GFP_KERNEL, + )?; + + let ctx = list_ctx.clone_arc(); + CONTEXTS.lock().list.push_back(list_ctx); + + Ok(ctx) + } + + /// Called when the file for this context is unlinked. + /// + /// No-op if called twice. + pub(crate) fn deregister(&self) { + // SAFETY: We never add the context to any other linked list than this one, so it is either + // in this list, or not in any list. + unsafe { CONTEXTS.lock().list.remove(self) }; + } + + pub(crate) fn register_process(self: &Arc<Self>, proc: ListArc<Process>) { + if !Arc::ptr_eq(self, &proc.ctx) { + pr_err!("Context::register_process called on the wrong context."); + return; + } + self.manager.lock().all_procs.push_back(proc); + } + + pub(crate) fn deregister_process(self: &Arc<Self>, proc: &Process) { + if !Arc::ptr_eq(self, &proc.ctx) { + pr_err!("Context::deregister_process called on the wrong context."); + return; + } + // SAFETY: We just checked that this is the right list. + unsafe { self.manager.lock().all_procs.remove(proc) }; + } + + pub(crate) fn set_manager_node(&self, node_ref: NodeRef) -> Result { + let mut manager = self.manager.lock(); + if manager.node.is_some() { + pr_warn!("BINDER_SET_CONTEXT_MGR already set"); + return Err(EBUSY); + } + security::binder_set_context_mgr(&node_ref.node.owner.cred)?; + + // If the context manager has been set before, ensure that we use the same euid. + let caller_uid = Kuid::current_euid(); + if let Some(ref uid) = manager.uid { + if *uid != caller_uid { + return Err(EPERM); + } + } + + manager.node = Some(node_ref); + manager.uid = Some(caller_uid); + Ok(()) + } + + pub(crate) fn unset_manager_node(&self) { + let node_ref = self.manager.lock().node.take(); + drop(node_ref); + } + + pub(crate) fn get_manager_node(&self, strong: bool) -> Result<NodeRef, BinderError> { + self.manager + .lock() + .node + .as_ref() + .ok_or_else(BinderError::new_dead)? + .clone(strong) + .map_err(BinderError::from) + } + + pub(crate) fn for_each_proc<F>(&self, mut func: F) + where + F: FnMut(&Process), + { + let lock = self.manager.lock(); + for proc in &lock.all_procs { + func(&proc); + } + } + + pub(crate) fn get_all_procs(&self) -> Result<KVec<Arc<Process>>> { + let lock = self.manager.lock(); + let count = lock.all_procs.iter().count(); + + let mut procs = KVec::with_capacity(count, GFP_KERNEL)?; + for proc in &lock.all_procs { + procs.push(Arc::from(proc), GFP_KERNEL)?; + } + Ok(procs) + } + + pub(crate) fn get_procs_with_pid(&self, pid: i32) -> Result<KVec<Arc<Process>>> { + let orig = self.get_all_procs()?; + let mut backing = KVec::with_capacity(orig.len(), GFP_KERNEL)?; + for proc in orig.into_iter().filter(|proc| proc.task.pid() == pid) { + backing.push(proc, GFP_KERNEL)?; + } + Ok(backing) + } +} diff --git a/drivers/android/binder/deferred_close.rs b/drivers/android/binder/deferred_close.rs new file mode 100644 index 000000000000..ac895c04d0cb --- /dev/null +++ b/drivers/android/binder/deferred_close.rs @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! Logic for closing files in a deferred manner. +//! +//! This file could make sense to have in `kernel::fs`, but it was rejected for being too +//! Binder-specific. + +use core::mem::MaybeUninit; +use kernel::{ + alloc::{AllocError, Flags}, + bindings, + prelude::*, +}; + +/// Helper used for closing file descriptors in a way that is safe even if the file is currently +/// held using `fdget`. +/// +/// Additional motivation can be found in commit 80cd795630d6 ("binder: fix use-after-free due to +/// ksys_close() during fdget()") and in the comments on `binder_do_fd_close`. +pub(crate) struct DeferredFdCloser { + inner: KBox<DeferredFdCloserInner>, +} + +/// SAFETY: This just holds an allocation with no real content, so there's no safety issue with +/// moving it across threads. +unsafe impl Send for DeferredFdCloser {} +/// SAFETY: This just holds an allocation with no real content, so there's no safety issue with +/// moving it across threads. +unsafe impl Sync for DeferredFdCloser {} + +/// # Invariants +/// +/// If the `file` pointer is non-null, then it points at a `struct file` and owns a refcount to +/// that file. +#[repr(C)] +struct DeferredFdCloserInner { + twork: MaybeUninit<bindings::callback_head>, + file: *mut bindings::file, +} + +impl DeferredFdCloser { + /// Create a new [`DeferredFdCloser`]. + pub(crate) fn new(flags: Flags) -> Result<Self, AllocError> { + Ok(Self { + // INVARIANT: The `file` pointer is null, so the type invariant does not apply. + inner: KBox::new( + DeferredFdCloserInner { + twork: MaybeUninit::uninit(), + file: core::ptr::null_mut(), + }, + flags, + )?, + }) + } + + /// Schedule a task work that closes the file descriptor when this task returns to userspace. + /// + /// Fails if this is called from a context where we cannot run work when returning to + /// userspace. (E.g., from a kthread.) + pub(crate) fn close_fd(self, fd: u32) -> Result<(), DeferredFdCloseError> { + use bindings::task_work_notify_mode_TWA_RESUME as TWA_RESUME; + + // In this method, we schedule the task work before closing the file. This is because + // scheduling a task work is fallible, and we need to know whether it will fail before we + // attempt to close the file. + + // Task works are not available on kthreads. + let current = kernel::current!(); + + // Check if this is a kthread. + // SAFETY: Reading `flags` from a task is always okay. + if unsafe { ((*current.as_ptr()).flags & bindings::PF_KTHREAD) != 0 } { + return Err(DeferredFdCloseError::TaskWorkUnavailable); + } + + // Transfer ownership of the box's allocation to a raw pointer. This disables the + // destructor, so we must manually convert it back to a KBox to drop it. + // + // Until we convert it back to a `KBox`, there are no aliasing requirements on this + // pointer. + let inner = KBox::into_raw(self.inner); + + // The `callback_head` field is first in the struct, so this cast correctly gives us a + // pointer to the field. + let callback_head = inner.cast::<bindings::callback_head>(); + // SAFETY: This pointer offset operation does not go out-of-bounds. + let file_field = unsafe { core::ptr::addr_of_mut!((*inner).file) }; + + let current = current.as_ptr(); + + // SAFETY: This function currently has exclusive access to the `DeferredFdCloserInner`, so + // it is okay for us to perform unsynchronized writes to its `callback_head` field. + unsafe { bindings::init_task_work(callback_head, Some(Self::do_close_fd)) }; + + // SAFETY: This inserts the `DeferredFdCloserInner` into the task workqueue for the current + // task. If this operation is successful, then this transfers exclusive ownership of the + // `callback_head` field to the C side until it calls `do_close_fd`, and we don't touch or + // invalidate the field during that time. + // + // When the C side calls `do_close_fd`, the safety requirements of that method are + // satisfied because when a task work is executed, the callback is given ownership of the + // pointer. + // + // The file pointer is currently null. If it is changed to be non-null before `do_close_fd` + // is called, then that change happens due to the write at the end of this function, and + // that write has a safety comment that explains why the refcount can be dropped when + // `do_close_fd` runs. + let res = unsafe { bindings::task_work_add(current, callback_head, TWA_RESUME) }; + + if res != 0 { + // SAFETY: Scheduling the task work failed, so we still have ownership of the box, so + // we may destroy it. + unsafe { drop(KBox::from_raw(inner)) }; + + return Err(DeferredFdCloseError::TaskWorkUnavailable); + } + + // This removes the fd from the fd table in `current`. The file is not fully closed until + // `filp_close` is called. We are given ownership of one refcount to the file. + // + // SAFETY: This is safe no matter what `fd` is. If the `fd` is valid (that is, if the + // pointer is non-null), then we call `filp_close` on the returned pointer as required by + // `file_close_fd`. + let file = unsafe { bindings::file_close_fd(fd) }; + if file.is_null() { + // We don't clean up the task work since that might be expensive if the task work queue + // is long. Just let it execute and let it clean up for itself. + return Err(DeferredFdCloseError::BadFd); + } + + // Acquire a second refcount to the file. + // + // SAFETY: The `file` pointer points at a file with a non-zero refcount. + unsafe { bindings::get_file(file) }; + + // This method closes the fd, consuming one of our two refcounts. There could be active + // light refcounts created from that fd, so we must ensure that the file has a positive + // refcount for the duration of those active light refcounts. We do that by holding on to + // the second refcount until the current task returns to userspace. + // + // SAFETY: The `file` pointer is valid. Passing `current->files` as the file table to close + // it in is correct, since we just got the `fd` from `file_close_fd` which also uses + // `current->files`. + // + // Note: fl_owner_t is currently a void pointer. + unsafe { bindings::filp_close(file, (*current).files as bindings::fl_owner_t) }; + + // We update the file pointer that the task work is supposed to fput. This transfers + // ownership of our last refcount. + // + // INVARIANT: This changes the `file` field of a `DeferredFdCloserInner` from null to + // non-null. This doesn't break the type invariant for `DeferredFdCloserInner` because we + // still own a refcount to the file, so we can pass ownership of that refcount to the + // `DeferredFdCloserInner`. + // + // When `do_close_fd` runs, it must be safe for it to `fput` the refcount. However, this is + // the case because all light refcounts that are associated with the fd we closed + // previously must be dropped when `do_close_fd`, since light refcounts must be dropped + // before returning to userspace. + // + // SAFETY: Task works are executed on the current thread right before we return to + // userspace, so this write is guaranteed to happen before `do_close_fd` is called, which + // means that a race is not possible here. + unsafe { *file_field = file }; + + Ok(()) + } + + /// # Safety + /// + /// The provided pointer must point at the `twork` field of a `DeferredFdCloserInner` stored in + /// a `KBox`, and the caller must pass exclusive ownership of that `KBox`. Furthermore, if the + /// file pointer is non-null, then it must be okay to release the refcount by calling `fput`. + unsafe extern "C" fn do_close_fd(inner: *mut bindings::callback_head) { + // SAFETY: The caller just passed us ownership of this box. + let inner = unsafe { KBox::from_raw(inner.cast::<DeferredFdCloserInner>()) }; + if !inner.file.is_null() { + // SAFETY: By the type invariants, we own a refcount to this file, and the caller + // guarantees that dropping the refcount now is okay. + unsafe { bindings::fput(inner.file) }; + } + // The allocation is freed when `inner` goes out of scope. + } +} + +/// Represents a failure to close an fd in a deferred manner. +#[derive(Copy, Clone, Debug, Eq, PartialEq)] +pub(crate) enum DeferredFdCloseError { + /// Closing the fd failed because we were unable to schedule a task work. + TaskWorkUnavailable, + /// Closing the fd failed because the fd does not exist. + BadFd, +} + +impl From<DeferredFdCloseError> for Error { + fn from(err: DeferredFdCloseError) -> Error { + match err { + DeferredFdCloseError::TaskWorkUnavailable => ESRCH, + DeferredFdCloseError::BadFd => EBADF, + } + } +} diff --git a/drivers/android/binder/defs.rs b/drivers/android/binder/defs.rs new file mode 100644 index 000000000000..33f51b4139c7 --- /dev/null +++ b/drivers/android/binder/defs.rs @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use core::mem::MaybeUninit; +use core::ops::{Deref, DerefMut}; +use kernel::{ + transmute::{AsBytes, FromBytes}, + uapi::{self, *}, +}; + +macro_rules! pub_no_prefix { + ($prefix:ident, $($newname:ident),+ $(,)?) => { + $(pub(crate) const $newname: u32 = kernel::macros::concat_idents!($prefix, $newname);)+ + }; +} + +pub_no_prefix!( + binder_driver_return_protocol_, + BR_TRANSACTION, + BR_TRANSACTION_SEC_CTX, + BR_REPLY, + BR_DEAD_REPLY, + BR_FAILED_REPLY, + BR_FROZEN_REPLY, + BR_NOOP, + BR_SPAWN_LOOPER, + BR_TRANSACTION_COMPLETE, + BR_TRANSACTION_PENDING_FROZEN, + BR_ONEWAY_SPAM_SUSPECT, + BR_OK, + BR_ERROR, + BR_INCREFS, + BR_ACQUIRE, + BR_RELEASE, + BR_DECREFS, + BR_DEAD_BINDER, + BR_CLEAR_DEATH_NOTIFICATION_DONE, + BR_FROZEN_BINDER, + BR_CLEAR_FREEZE_NOTIFICATION_DONE, +); + +pub_no_prefix!( + binder_driver_command_protocol_, + BC_TRANSACTION, + BC_TRANSACTION_SG, + BC_REPLY, + BC_REPLY_SG, + BC_FREE_BUFFER, + BC_ENTER_LOOPER, + BC_EXIT_LOOPER, + BC_REGISTER_LOOPER, + BC_INCREFS, + BC_ACQUIRE, + BC_RELEASE, + BC_DECREFS, + BC_INCREFS_DONE, + BC_ACQUIRE_DONE, + BC_REQUEST_DEATH_NOTIFICATION, + BC_CLEAR_DEATH_NOTIFICATION, + BC_DEAD_BINDER_DONE, + BC_REQUEST_FREEZE_NOTIFICATION, + BC_CLEAR_FREEZE_NOTIFICATION, + BC_FREEZE_NOTIFICATION_DONE, +); + +pub_no_prefix!( + flat_binder_object_flags_, + FLAT_BINDER_FLAG_ACCEPTS_FDS, + FLAT_BINDER_FLAG_TXN_SECURITY_CTX +); + +pub_no_prefix!( + transaction_flags_, + TF_ONE_WAY, + TF_ACCEPT_FDS, + TF_CLEAR_BUF, + TF_UPDATE_TXN +); + +pub(crate) use uapi::{ + BINDER_TYPE_BINDER, BINDER_TYPE_FD, BINDER_TYPE_FDA, BINDER_TYPE_HANDLE, BINDER_TYPE_PTR, + BINDER_TYPE_WEAK_BINDER, BINDER_TYPE_WEAK_HANDLE, +}; + +macro_rules! decl_wrapper { + ($newname:ident, $wrapped:ty) => { + // Define a wrapper around the C type. Use `MaybeUninit` to enforce that the value of + // padding bytes must be preserved. + #[derive(Copy, Clone)] + #[repr(transparent)] + pub(crate) struct $newname(MaybeUninit<$wrapped>); + + // SAFETY: This macro is only used with types where this is ok. + unsafe impl FromBytes for $newname {} + // SAFETY: This macro is only used with types where this is ok. + unsafe impl AsBytes for $newname {} + + impl Deref for $newname { + type Target = $wrapped; + fn deref(&self) -> &Self::Target { + // SAFETY: We use `MaybeUninit` only to preserve padding. The value must still + // always be valid. + unsafe { self.0.assume_init_ref() } + } + } + + impl DerefMut for $newname { + fn deref_mut(&mut self) -> &mut Self::Target { + // SAFETY: We use `MaybeUninit` only to preserve padding. The value must still + // always be valid. + unsafe { self.0.assume_init_mut() } + } + } + + impl Default for $newname { + fn default() -> Self { + // Create a new value of this type where all bytes (including padding) are zeroed. + Self(MaybeUninit::zeroed()) + } + } + }; +} + +decl_wrapper!(BinderNodeDebugInfo, uapi::binder_node_debug_info); +decl_wrapper!(BinderNodeInfoForRef, uapi::binder_node_info_for_ref); +decl_wrapper!(FlatBinderObject, uapi::flat_binder_object); +decl_wrapper!(BinderFdObject, uapi::binder_fd_object); +decl_wrapper!(BinderFdArrayObject, uapi::binder_fd_array_object); +decl_wrapper!(BinderObjectHeader, uapi::binder_object_header); +decl_wrapper!(BinderBufferObject, uapi::binder_buffer_object); +decl_wrapper!(BinderTransactionData, uapi::binder_transaction_data); +decl_wrapper!( + BinderTransactionDataSecctx, + uapi::binder_transaction_data_secctx +); +decl_wrapper!(BinderTransactionDataSg, uapi::binder_transaction_data_sg); +decl_wrapper!(BinderWriteRead, uapi::binder_write_read); +decl_wrapper!(BinderVersion, uapi::binder_version); +decl_wrapper!(BinderFrozenStatusInfo, uapi::binder_frozen_status_info); +decl_wrapper!(BinderFreezeInfo, uapi::binder_freeze_info); +decl_wrapper!(BinderFrozenStateInfo, uapi::binder_frozen_state_info); +decl_wrapper!(BinderHandleCookie, uapi::binder_handle_cookie); +decl_wrapper!(ExtendedError, uapi::binder_extended_error); + +impl BinderVersion { + pub(crate) fn current() -> Self { + Self(MaybeUninit::new(uapi::binder_version { + protocol_version: BINDER_CURRENT_PROTOCOL_VERSION as _, + })) + } +} + +impl BinderTransactionData { + pub(crate) fn with_buffers_size(self, buffers_size: u64) -> BinderTransactionDataSg { + BinderTransactionDataSg(MaybeUninit::new(uapi::binder_transaction_data_sg { + transaction_data: *self, + buffers_size, + })) + } +} + +impl BinderTransactionDataSecctx { + /// View the inner data as wrapped in `BinderTransactionData`. + pub(crate) fn tr_data(&mut self) -> &mut BinderTransactionData { + // SAFETY: Transparent wrapper is safe to transmute. + unsafe { + &mut *(&mut self.transaction_data as *mut uapi::binder_transaction_data + as *mut BinderTransactionData) + } + } +} + +impl ExtendedError { + pub(crate) fn new(id: u32, command: u32, param: i32) -> Self { + Self(MaybeUninit::new(uapi::binder_extended_error { + id, + command, + param, + })) + } +} diff --git a/drivers/android/binder/error.rs b/drivers/android/binder/error.rs new file mode 100644 index 000000000000..9921827267d0 --- /dev/null +++ b/drivers/android/binder/error.rs @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::prelude::*; + +use crate::defs::*; + +pub(crate) type BinderResult<T = ()> = core::result::Result<T, BinderError>; + +/// An error that will be returned to userspace via the `BINDER_WRITE_READ` ioctl rather than via +/// errno. +pub(crate) struct BinderError { + pub(crate) reply: u32, + source: Option<Error>, +} + +impl BinderError { + pub(crate) fn new_dead() -> Self { + Self { + reply: BR_DEAD_REPLY, + source: None, + } + } + + pub(crate) fn new_frozen() -> Self { + Self { + reply: BR_FROZEN_REPLY, + source: None, + } + } + + pub(crate) fn new_frozen_oneway() -> Self { + Self { + reply: BR_TRANSACTION_PENDING_FROZEN, + source: None, + } + } + + pub(crate) fn is_dead(&self) -> bool { + self.reply == BR_DEAD_REPLY + } + + pub(crate) fn as_errno(&self) -> kernel::ffi::c_int { + self.source.unwrap_or(EINVAL).to_errno() + } + + pub(crate) fn should_pr_warn(&self) -> bool { + self.source.is_some() + } +} + +/// Convert an errno into a `BinderError` and store the errno used to construct it. The errno +/// should be stored as the thread's extended error when given to userspace. +impl From<Error> for BinderError { + fn from(source: Error) -> Self { + Self { + reply: BR_FAILED_REPLY, + source: Some(source), + } + } +} + +impl From<kernel::fs::file::BadFdError> for BinderError { + fn from(source: kernel::fs::file::BadFdError) -> Self { + BinderError::from(Error::from(source)) + } +} + +impl From<kernel::alloc::AllocError> for BinderError { + fn from(_: kernel::alloc::AllocError) -> Self { + Self { + reply: BR_FAILED_REPLY, + source: Some(ENOMEM), + } + } +} + +impl core::fmt::Debug for BinderError { + fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { + match self.reply { + BR_FAILED_REPLY => match self.source.as_ref() { + Some(source) => f + .debug_struct("BR_FAILED_REPLY") + .field("source", source) + .finish(), + None => f.pad("BR_FAILED_REPLY"), + }, + BR_DEAD_REPLY => f.pad("BR_DEAD_REPLY"), + BR_FROZEN_REPLY => f.pad("BR_FROZEN_REPLY"), + BR_TRANSACTION_PENDING_FROZEN => f.pad("BR_TRANSACTION_PENDING_FROZEN"), + BR_TRANSACTION_COMPLETE => f.pad("BR_TRANSACTION_COMPLETE"), + _ => f + .debug_struct("BinderError") + .field("reply", &self.reply) + .finish(), + } + } +} diff --git a/drivers/android/binder/freeze.rs b/drivers/android/binder/freeze.rs new file mode 100644 index 000000000000..e68c3c8bc55a --- /dev/null +++ b/drivers/android/binder/freeze.rs @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{ + alloc::AllocError, + list::ListArc, + prelude::*, + rbtree::{self, RBTreeNodeReservation}, + seq_file::SeqFile, + seq_print, + sync::{Arc, UniqueArc}, + uaccess::UserSliceReader, +}; + +use crate::{ + defs::*, node::Node, process::Process, thread::Thread, BinderReturnWriter, DArc, DLArc, + DTRWrap, DeliverToRead, +}; + +#[derive(Clone, Copy, Eq, PartialEq, Ord, PartialOrd)] +pub(crate) struct FreezeCookie(u64); + +/// Represents a listener for changes to the frozen state of a process. +pub(crate) struct FreezeListener { + /// The node we are listening for. + pub(crate) node: DArc<Node>, + /// The cookie of this freeze listener. + cookie: FreezeCookie, + /// What value of `is_frozen` did we most recently tell userspace about? + last_is_frozen: Option<bool>, + /// We sent a `BR_FROZEN_BINDER` and we are waiting for `BC_FREEZE_NOTIFICATION_DONE` before + /// sending any other commands. + is_pending: bool, + /// Userspace sent `BC_CLEAR_FREEZE_NOTIFICATION` and we need to reply with + /// `BR_CLEAR_FREEZE_NOTIFICATION_DONE` as soon as possible. If `is_pending` is set, then we + /// must wait for it to be unset before we can reply. + is_clearing: bool, + /// Number of cleared duplicates that can't be deleted until userspace sends + /// `BC_FREEZE_NOTIFICATION_DONE`. + num_pending_duplicates: u64, + /// Number of cleared duplicates that can be deleted. + num_cleared_duplicates: u64, +} + +impl FreezeListener { + /// Is it okay to create a new listener with the same cookie as this one for the provided node? + /// + /// Under some scenarios, userspace may delete a freeze listener and immediately recreate it + /// with the same cookie. This results in duplicate listeners. To avoid issues with ambiguity, + /// we allow this only if the new listener is for the same node, and we also require that the + /// old listener has already been cleared. + fn allow_duplicate(&self, node: &DArc<Node>) -> bool { + Arc::ptr_eq(&self.node, node) && self.is_clearing + } +} + +type UninitFM = UniqueArc<core::mem::MaybeUninit<DTRWrap<FreezeMessage>>>; + +/// Represents a notification that the freeze state has changed. +pub(crate) struct FreezeMessage { + cookie: FreezeCookie, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for FreezeMessage { + untracked; + } +} + +impl FreezeMessage { + fn new(flags: kernel::alloc::Flags) -> Result<UninitFM, AllocError> { + UniqueArc::new_uninit(flags) + } + + fn init(ua: UninitFM, cookie: FreezeCookie) -> DLArc<FreezeMessage> { + match ua.pin_init_with(DTRWrap::new(FreezeMessage { cookie })) { + Ok(msg) => ListArc::from(msg), + Err(err) => match err {}, + } + } +} + +impl DeliverToRead for FreezeMessage { + fn do_work( + self: DArc<Self>, + thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let _removed_listener; + let mut node_refs = thread.process.node_refs.lock(); + let Some(mut freeze_entry) = node_refs.freeze_listeners.find_mut(&self.cookie) else { + return Ok(true); + }; + let freeze = freeze_entry.get_mut(); + + if freeze.num_cleared_duplicates > 0 { + freeze.num_cleared_duplicates -= 1; + drop(node_refs); + writer.write_code(BR_CLEAR_FREEZE_NOTIFICATION_DONE)?; + writer.write_payload(&self.cookie.0)?; + return Ok(true); + } + + if freeze.is_pending { + return Ok(true); + } + if freeze.is_clearing { + _removed_listener = freeze_entry.remove_node(); + drop(node_refs); + writer.write_code(BR_CLEAR_FREEZE_NOTIFICATION_DONE)?; + writer.write_payload(&self.cookie.0)?; + Ok(true) + } else { + let is_frozen = freeze.node.owner.inner.lock().is_frozen; + if freeze.last_is_frozen == Some(is_frozen) { + return Ok(true); + } + + let mut state_info = BinderFrozenStateInfo::default(); + state_info.is_frozen = is_frozen as u32; + state_info.cookie = freeze.cookie.0; + freeze.is_pending = true; + freeze.last_is_frozen = Some(is_frozen); + drop(node_refs); + + writer.write_code(BR_FROZEN_BINDER)?; + writer.write_payload(&state_info)?; + // BR_FROZEN_BINDER notifications can cause transactions + Ok(false) + } + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + #[inline(never)] + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + seq_print!(m, "{}has frozen binder\n", prefix); + Ok(()) + } +} + +impl FreezeListener { + pub(crate) fn on_process_exit(&self, proc: &Arc<Process>) { + if !self.is_clearing { + self.node.remove_freeze_listener(proc); + } + } +} + +impl Process { + pub(crate) fn request_freeze_notif( + self: &Arc<Self>, + reader: &mut UserSliceReader, + ) -> Result<()> { + let hc = reader.read::<BinderHandleCookie>()?; + let handle = hc.handle; + let cookie = FreezeCookie(hc.cookie); + + let msg = FreezeMessage::new(GFP_KERNEL)?; + let alloc = RBTreeNodeReservation::new(GFP_KERNEL)?; + + let mut node_refs_guard = self.node_refs.lock(); + let node_refs = &mut *node_refs_guard; + let Some(info) = node_refs.by_handle.get_mut(&handle) else { + pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION invalid ref {}\n", handle); + return Err(EINVAL); + }; + if info.freeze().is_some() { + pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION already set\n"); + return Err(EINVAL); + } + let node_ref = info.node_ref(); + let freeze_entry = node_refs.freeze_listeners.entry(cookie); + + if let rbtree::Entry::Occupied(ref dupe) = freeze_entry { + if !dupe.get().allow_duplicate(&node_ref.node) { + pr_warn!("BC_REQUEST_FREEZE_NOTIFICATION duplicate cookie\n"); + return Err(EINVAL); + } + } + + // All failure paths must come before this call, and all modifications must come after this + // call. + node_ref.node.add_freeze_listener(self, GFP_KERNEL)?; + + match freeze_entry { + rbtree::Entry::Vacant(entry) => { + entry.insert( + FreezeListener { + cookie, + node: node_ref.node.clone(), + last_is_frozen: None, + is_pending: false, + is_clearing: false, + num_pending_duplicates: 0, + num_cleared_duplicates: 0, + }, + alloc, + ); + } + rbtree::Entry::Occupied(mut dupe) => { + let dupe = dupe.get_mut(); + if dupe.is_pending { + dupe.num_pending_duplicates += 1; + } else { + dupe.num_cleared_duplicates += 1; + } + dupe.last_is_frozen = None; + dupe.is_pending = false; + dupe.is_clearing = false; + } + } + + *info.freeze() = Some(cookie); + let msg = FreezeMessage::init(msg, cookie); + drop(node_refs_guard); + let _ = self.push_work(msg); + Ok(()) + } + + pub(crate) fn freeze_notif_done(self: &Arc<Self>, reader: &mut UserSliceReader) -> Result<()> { + let cookie = FreezeCookie(reader.read()?); + let alloc = FreezeMessage::new(GFP_KERNEL)?; + let mut node_refs_guard = self.node_refs.lock(); + let node_refs = &mut *node_refs_guard; + let Some(freeze) = node_refs.freeze_listeners.get_mut(&cookie) else { + pr_warn!("BC_FREEZE_NOTIFICATION_DONE {:016x} not found\n", cookie.0); + return Err(EINVAL); + }; + let mut clear_msg = None; + if freeze.num_pending_duplicates > 0 { + clear_msg = Some(FreezeMessage::init(alloc, cookie)); + freeze.num_pending_duplicates -= 1; + freeze.num_cleared_duplicates += 1; + } else { + if !freeze.is_pending { + pr_warn!( + "BC_FREEZE_NOTIFICATION_DONE {:016x} not pending\n", + cookie.0 + ); + return Err(EINVAL); + } + if freeze.is_clearing { + // Immediately send another FreezeMessage for BR_CLEAR_FREEZE_NOTIFICATION_DONE. + clear_msg = Some(FreezeMessage::init(alloc, cookie)); + } + freeze.is_pending = false; + } + drop(node_refs_guard); + if let Some(clear_msg) = clear_msg { + let _ = self.push_work(clear_msg); + } + Ok(()) + } + + pub(crate) fn clear_freeze_notif(self: &Arc<Self>, reader: &mut UserSliceReader) -> Result<()> { + let hc = reader.read::<BinderHandleCookie>()?; + let handle = hc.handle; + let cookie = FreezeCookie(hc.cookie); + + let alloc = FreezeMessage::new(GFP_KERNEL)?; + let mut node_refs_guard = self.node_refs.lock(); + let node_refs = &mut *node_refs_guard; + let Some(info) = node_refs.by_handle.get_mut(&handle) else { + pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION invalid ref {}\n", handle); + return Err(EINVAL); + }; + let Some(info_cookie) = info.freeze() else { + pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION freeze notification not active\n"); + return Err(EINVAL); + }; + if *info_cookie != cookie { + pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION freeze notification cookie mismatch\n"); + return Err(EINVAL); + } + let Some(listener) = node_refs.freeze_listeners.get_mut(&cookie) else { + pr_warn!("BC_CLEAR_FREEZE_NOTIFICATION invalid cookie {}\n", handle); + return Err(EINVAL); + }; + listener.is_clearing = true; + listener.node.remove_freeze_listener(self); + *info.freeze() = None; + let mut msg = None; + if !listener.is_pending { + msg = Some(FreezeMessage::init(alloc, cookie)); + } + drop(node_refs_guard); + + if let Some(msg) = msg { + let _ = self.push_work(msg); + } + Ok(()) + } + + fn get_freeze_cookie(&self, node: &DArc<Node>) -> Option<FreezeCookie> { + let node_refs = &mut *self.node_refs.lock(); + let handle = node_refs.by_node.get(&node.global_id())?; + let node_ref = node_refs.by_handle.get_mut(handle)?; + *node_ref.freeze() + } + + /// Creates a vector of every freeze listener on this process. + /// + /// Returns pairs of the remote process listening for notifications and the local node it is + /// listening on. + #[expect(clippy::type_complexity)] + fn find_freeze_recipients(&self) -> Result<KVVec<(DArc<Node>, Arc<Process>)>, AllocError> { + // Defined before `inner` to drop after releasing spinlock if `push_within_capacity` fails. + let mut node_proc_pair; + + // We pre-allocate space for up to 8 recipients before we take the spinlock. However, if + // the allocation fails, use a vector with a capacity of zero instead of failing. After + // all, there might not be any freeze listeners, in which case this operation could still + // succeed. + let mut recipients = + KVVec::with_capacity(8, GFP_KERNEL).unwrap_or_else(|_err| KVVec::new()); + + let mut inner = self.lock_with_nodes(); + let mut curr = inner.nodes.cursor_front(); + while let Some(cursor) = curr { + let (key, node) = cursor.current(); + let key = *key; + let list = node.freeze_list(&inner.inner); + let len = list.len(); + + if recipients.spare_capacity_mut().len() < len { + drop(inner); + recipients.reserve(len, GFP_KERNEL)?; + inner = self.lock_with_nodes(); + // Find the node we were looking at and try again. If the set of nodes was changed, + // then just proceed to the next node. This is ok because we don't guarantee the + // inclusion of nodes that are added or removed in parallel with this operation. + curr = inner.nodes.cursor_lower_bound(&key); + continue; + } + + for proc in list { + node_proc_pair = (node.clone(), proc.clone()); + recipients + .push_within_capacity(node_proc_pair) + .map_err(|_| { + pr_err!( + "push_within_capacity failed even though we checked the capacity\n" + ); + AllocError + })?; + } + + curr = cursor.move_next(); + } + Ok(recipients) + } + + /// Prepare allocations for sending freeze messages. + pub(crate) fn prepare_freeze_messages(&self) -> Result<FreezeMessages, AllocError> { + let recipients = self.find_freeze_recipients()?; + let mut batch = KVVec::with_capacity(recipients.len(), GFP_KERNEL)?; + for (node, proc) in recipients { + let Some(cookie) = proc.get_freeze_cookie(&node) else { + // If the freeze listener was removed in the meantime, just discard the + // notification. + continue; + }; + let msg_alloc = FreezeMessage::new(GFP_KERNEL)?; + let msg = FreezeMessage::init(msg_alloc, cookie); + batch.push((proc, msg), GFP_KERNEL)?; + } + + Ok(FreezeMessages { batch }) + } +} + +pub(crate) struct FreezeMessages { + batch: KVVec<(Arc<Process>, DLArc<FreezeMessage>)>, +} + +impl FreezeMessages { + pub(crate) fn send_messages(self) { + for (proc, msg) in self.batch { + let _ = proc.push_work(msg); + } + } +} diff --git a/drivers/android/binder/node.rs b/drivers/android/binder/node.rs new file mode 100644 index 000000000000..ade895ef791e --- /dev/null +++ b/drivers/android/binder/node.rs @@ -0,0 +1,1131 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{ + list::{AtomicTracker, List, ListArc, ListLinks, TryNewListArc}, + prelude::*, + seq_file::SeqFile, + seq_print, + sync::lock::{spinlock::SpinLockBackend, Guard}, + sync::{Arc, LockedBy, SpinLock}, +}; + +use crate::{ + defs::*, + error::BinderError, + process::{NodeRefInfo, Process, ProcessInner}, + thread::Thread, + transaction::Transaction, + BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead, +}; + +use core::mem; + +mod wrapper; +pub(crate) use self::wrapper::CritIncrWrapper; + +#[derive(Debug)] +pub(crate) struct CouldNotDeliverCriticalIncrement; + +/// Keeps track of how this node is scheduled. +/// +/// There are two ways to schedule a node to a work list. Just schedule the node itself, or +/// allocate a wrapper that references the node and schedule the wrapper. These wrappers exists to +/// make it possible to "move" a node from one list to another - when `do_work` is called directly +/// on the `Node`, then it's a no-op if there's also a pending wrapper. +/// +/// Wrappers are generally only needed for zero-to-one refcount increments, and there are two cases +/// of this: weak increments and strong increments. We call such increments "critical" because it +/// is critical that they are delivered to the thread doing the increment. Some examples: +/// +/// * One thread makes a zero-to-one strong increment, and another thread makes a zero-to-one weak +/// increment. Delivering the node to the thread doing the weak increment is wrong, since the +/// thread doing the strong increment may have ended a long time ago when the command is actually +/// processed by userspace. +/// +/// * We have a weak reference and are about to drop it on one thread. But then another thread does +/// a zero-to-one strong increment. If the strong increment gets sent to the thread that was +/// about to drop the weak reference, then the strong increment could be processed after the +/// other thread has already exited, which would be too late. +/// +/// Note that trying to create a `ListArc` to the node can succeed even if `has_normal_push` is +/// set. This is because another thread might just have popped the node from a todo list, but not +/// yet called `do_work`. However, if `has_normal_push` is false, then creating a `ListArc` should +/// always succeed. +/// +/// Like the other fields in `NodeInner`, the delivery state is protected by the process lock. +struct DeliveryState { + /// Is the `Node` currently scheduled? + has_pushed_node: bool, + + /// Is a wrapper currently scheduled? + /// + /// The wrapper is used only for strong zero2one increments. + has_pushed_wrapper: bool, + + /// Is the currently scheduled `Node` scheduled due to a weak zero2one increment? + /// + /// Weak zero2one operations are always scheduled using the `Node`. + has_weak_zero2one: bool, + + /// Is the currently scheduled wrapper/`Node` scheduled due to a strong zero2one increment? + /// + /// If `has_pushed_wrapper` is set, then the strong zero2one increment was scheduled using the + /// wrapper. Otherwise, `has_pushed_node` must be set and it was scheduled using the `Node`. + has_strong_zero2one: bool, +} + +impl DeliveryState { + fn should_normal_push(&self) -> bool { + !self.has_pushed_node && !self.has_pushed_wrapper + } + + fn did_normal_push(&mut self) { + assert!(self.should_normal_push()); + self.has_pushed_node = true; + } + + fn should_push_weak_zero2one(&self) -> bool { + !self.has_weak_zero2one && !self.has_strong_zero2one + } + + fn can_push_weak_zero2one_normally(&self) -> bool { + !self.has_pushed_node + } + + fn did_push_weak_zero2one(&mut self) { + assert!(self.should_push_weak_zero2one()); + assert!(self.can_push_weak_zero2one_normally()); + self.has_pushed_node = true; + self.has_weak_zero2one = true; + } + + fn should_push_strong_zero2one(&self) -> bool { + !self.has_strong_zero2one + } + + fn can_push_strong_zero2one_normally(&self) -> bool { + !self.has_pushed_node + } + + fn did_push_strong_zero2one(&mut self) { + assert!(self.should_push_strong_zero2one()); + assert!(self.can_push_strong_zero2one_normally()); + self.has_pushed_node = true; + self.has_strong_zero2one = true; + } + + fn did_push_strong_zero2one_wrapper(&mut self) { + assert!(self.should_push_strong_zero2one()); + assert!(!self.can_push_strong_zero2one_normally()); + self.has_pushed_wrapper = true; + self.has_strong_zero2one = true; + } +} + +struct CountState { + /// The reference count. + count: usize, + /// Whether the process that owns this node thinks that we hold a refcount on it. (Note that + /// even if count is greater than one, we only increment it once in the owning process.) + has_count: bool, +} + +impl CountState { + fn new() -> Self { + Self { + count: 0, + has_count: false, + } + } +} + +struct NodeInner { + /// Strong refcounts held on this node by `NodeRef` objects. + strong: CountState, + /// Weak refcounts held on this node by `NodeRef` objects. + weak: CountState, + delivery_state: DeliveryState, + /// The binder driver guarantees that oneway transactions sent to the same node are serialized, + /// that is, userspace will not be given the next one until it has finished processing the + /// previous oneway transaction. This is done to avoid the case where two oneway transactions + /// arrive in opposite order from the order in which they were sent. (E.g., they could be + /// delivered to two different threads, which could appear as-if they were sent in opposite + /// order.) + /// + /// To fix that, we store pending oneway transactions in a separate list in the node, and don't + /// deliver the next oneway transaction until userspace signals that it has finished processing + /// the previous oneway transaction by calling the `BC_FREE_BUFFER` ioctl. + oneway_todo: List<DTRWrap<Transaction>>, + /// Keeps track of whether this node has a pending oneway transaction. + /// + /// When this is true, incoming oneway transactions are stored in `oneway_todo`, instead of + /// being delivered directly to the process. + has_oneway_transaction: bool, + /// List of processes to deliver a notification to when this node is destroyed (usually due to + /// the process dying). + death_list: List<DTRWrap<NodeDeath>, 1>, + /// List of processes to deliver freeze notifications to. + freeze_list: KVVec<Arc<Process>>, + /// The number of active BR_INCREFS or BR_ACQUIRE operations. (should be maximum two) + /// + /// If this is non-zero, then we postpone any BR_RELEASE or BR_DECREFS notifications until the + /// active operations have ended. This avoids the situation an increment and decrement get + /// reordered from userspace's perspective. + active_inc_refs: u8, + /// List of `NodeRefInfo` objects that reference this node. + refs: List<NodeRefInfo, { NodeRefInfo::LIST_NODE }>, +} + +#[pin_data] +pub(crate) struct Node { + pub(crate) debug_id: usize, + ptr: u64, + pub(crate) cookie: u64, + pub(crate) flags: u32, + pub(crate) owner: Arc<Process>, + inner: LockedBy<NodeInner, ProcessInner>, + #[pin] + links_track: AtomicTracker, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for Node { + tracked_by links_track: AtomicTracker; + } +} + +// Make `oneway_todo` work. +kernel::list::impl_list_item! { + impl ListItem<0> for DTRWrap<Transaction> { + using ListLinks { self.links.inner }; + } +} + +impl Node { + pub(crate) fn new( + ptr: u64, + cookie: u64, + flags: u32, + owner: Arc<Process>, + ) -> impl PinInit<Self> { + pin_init!(Self { + inner: LockedBy::new( + &owner.inner, + NodeInner { + strong: CountState::new(), + weak: CountState::new(), + delivery_state: DeliveryState { + has_pushed_node: false, + has_pushed_wrapper: false, + has_weak_zero2one: false, + has_strong_zero2one: false, + }, + death_list: List::new(), + oneway_todo: List::new(), + freeze_list: KVVec::new(), + has_oneway_transaction: false, + active_inc_refs: 0, + refs: List::new(), + }, + ), + debug_id: super::next_debug_id(), + ptr, + cookie, + flags, + owner, + links_track <- AtomicTracker::new(), + }) + } + + pub(crate) fn has_oneway_transaction(&self, owner_inner: &mut ProcessInner) -> bool { + let inner = self.inner.access_mut(owner_inner); + inner.has_oneway_transaction + } + + #[inline(never)] + pub(crate) fn full_debug_print( + &self, + m: &SeqFile, + owner_inner: &mut ProcessInner, + ) -> Result<()> { + let inner = self.inner.access_mut(owner_inner); + seq_print!( + m, + " node {}: u{:016x} c{:016x} hs {} hw {} cs {} cw {}", + self.debug_id, + self.ptr, + self.cookie, + inner.strong.has_count, + inner.weak.has_count, + inner.strong.count, + inner.weak.count, + ); + if !inner.refs.is_empty() { + seq_print!(m, " proc"); + for node_ref in &inner.refs { + seq_print!(m, " {}", node_ref.process.task.pid()); + } + } + seq_print!(m, "\n"); + for t in &inner.oneway_todo { + t.debug_print_inner(m, " pending async transaction "); + } + Ok(()) + } + + /// Insert the `NodeRef` into this `refs` list. + /// + /// # Safety + /// + /// It must be the case that `info.node_ref.node` is this node. + pub(crate) unsafe fn insert_node_info( + &self, + info: ListArc<NodeRefInfo, { NodeRefInfo::LIST_NODE }>, + ) { + self.inner + .access_mut(&mut self.owner.inner.lock()) + .refs + .push_front(info); + } + + /// Insert the `NodeRef` into this `refs` list. + /// + /// # Safety + /// + /// It must be the case that `info.node_ref.node` is this node. + pub(crate) unsafe fn remove_node_info( + &self, + info: &NodeRefInfo, + ) -> Option<ListArc<NodeRefInfo, { NodeRefInfo::LIST_NODE }>> { + // SAFETY: We always insert `NodeRefInfo` objects into the `refs` list of the node that it + // references in `info.node_ref.node`. That is this node, so `info` cannot possibly be in + // the `refs` list of another node. + unsafe { + self.inner + .access_mut(&mut self.owner.inner.lock()) + .refs + .remove(info) + } + } + + /// An id that is unique across all binder nodes on the system. Used as the key in the + /// `by_node` map. + pub(crate) fn global_id(&self) -> usize { + self as *const Node as usize + } + + pub(crate) fn get_id(&self) -> (u64, u64) { + (self.ptr, self.cookie) + } + + pub(crate) fn add_death( + &self, + death: ListArc<DTRWrap<NodeDeath>, 1>, + guard: &mut Guard<'_, ProcessInner, SpinLockBackend>, + ) { + self.inner.access_mut(guard).death_list.push_back(death); + } + + pub(crate) fn inc_ref_done_locked( + self: &DArc<Node>, + _strong: bool, + owner_inner: &mut ProcessInner, + ) -> Option<DLArc<Node>> { + let inner = self.inner.access_mut(owner_inner); + if inner.active_inc_refs == 0 { + pr_err!("inc_ref_done called when no active inc_refs"); + return None; + } + + inner.active_inc_refs -= 1; + if inner.active_inc_refs == 0 { + // Having active inc_refs can inhibit dropping of ref-counts. Calculate whether we + // would send a refcount decrement, and if so, tell the caller to schedule us. + let strong = inner.strong.count > 0; + let has_strong = inner.strong.has_count; + let weak = strong || inner.weak.count > 0; + let has_weak = inner.weak.has_count; + + let should_drop_weak = !weak && has_weak; + let should_drop_strong = !strong && has_strong; + + // If we want to drop the ref-count again, tell the caller to schedule a work node for + // that. + let need_push = should_drop_weak || should_drop_strong; + + if need_push && inner.delivery_state.should_normal_push() { + let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap(); + inner.delivery_state.did_normal_push(); + Some(list_arc) + } else { + None + } + } else { + None + } + } + + pub(crate) fn update_refcount_locked( + self: &DArc<Node>, + inc: bool, + strong: bool, + count: usize, + owner_inner: &mut ProcessInner, + ) -> Option<DLArc<Node>> { + let is_dead = owner_inner.is_dead; + let inner = self.inner.access_mut(owner_inner); + + // Get a reference to the state we'll update. + let state = if strong { + &mut inner.strong + } else { + &mut inner.weak + }; + + // Update the count and determine whether we need to push work. + let need_push = if inc { + state.count += count; + // TODO: This method shouldn't be used for zero-to-one increments. + !is_dead && !state.has_count + } else { + if state.count < count { + pr_err!("Failure: refcount underflow!"); + return None; + } + state.count -= count; + !is_dead && state.count == 0 && state.has_count + }; + + if need_push && inner.delivery_state.should_normal_push() { + let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap(); + inner.delivery_state.did_normal_push(); + Some(list_arc) + } else { + None + } + } + + pub(crate) fn incr_refcount_allow_zero2one( + self: &DArc<Self>, + strong: bool, + owner_inner: &mut ProcessInner, + ) -> Result<Option<DLArc<Node>>, CouldNotDeliverCriticalIncrement> { + let is_dead = owner_inner.is_dead; + let inner = self.inner.access_mut(owner_inner); + + // Get a reference to the state we'll update. + let state = if strong { + &mut inner.strong + } else { + &mut inner.weak + }; + + // Update the count and determine whether we need to push work. + state.count += 1; + if is_dead || state.has_count { + return Ok(None); + } + + // Userspace needs to be notified of this. + if !strong && inner.delivery_state.should_push_weak_zero2one() { + assert!(inner.delivery_state.can_push_weak_zero2one_normally()); + let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap(); + inner.delivery_state.did_push_weak_zero2one(); + Ok(Some(list_arc)) + } else if strong && inner.delivery_state.should_push_strong_zero2one() { + if inner.delivery_state.can_push_strong_zero2one_normally() { + let list_arc = ListArc::try_from_arc(self.clone()).ok().unwrap(); + inner.delivery_state.did_push_strong_zero2one(); + Ok(Some(list_arc)) + } else { + state.count -= 1; + Err(CouldNotDeliverCriticalIncrement) + } + } else { + // Work is already pushed, and we don't need to push again. + Ok(None) + } + } + + pub(crate) fn incr_refcount_allow_zero2one_with_wrapper( + self: &DArc<Self>, + strong: bool, + wrapper: CritIncrWrapper, + owner_inner: &mut ProcessInner, + ) -> Option<DLArc<dyn DeliverToRead>> { + match self.incr_refcount_allow_zero2one(strong, owner_inner) { + Ok(Some(node)) => Some(node as _), + Ok(None) => None, + Err(CouldNotDeliverCriticalIncrement) => { + assert!(strong); + let inner = self.inner.access_mut(owner_inner); + inner.strong.count += 1; + inner.delivery_state.did_push_strong_zero2one_wrapper(); + Some(wrapper.init(self.clone())) + } + } + } + + pub(crate) fn update_refcount(self: &DArc<Self>, inc: bool, count: usize, strong: bool) { + self.owner + .inner + .lock() + .update_node_refcount(self, inc, strong, count, None); + } + + pub(crate) fn populate_counts( + &self, + out: &mut BinderNodeInfoForRef, + guard: &Guard<'_, ProcessInner, SpinLockBackend>, + ) { + let inner = self.inner.access(guard); + out.strong_count = inner.strong.count as _; + out.weak_count = inner.weak.count as _; + } + + pub(crate) fn populate_debug_info( + &self, + out: &mut BinderNodeDebugInfo, + guard: &Guard<'_, ProcessInner, SpinLockBackend>, + ) { + out.ptr = self.ptr as _; + out.cookie = self.cookie as _; + let inner = self.inner.access(guard); + if inner.strong.has_count { + out.has_strong_ref = 1; + } + if inner.weak.has_count { + out.has_weak_ref = 1; + } + } + + pub(crate) fn force_has_count(&self, guard: &mut Guard<'_, ProcessInner, SpinLockBackend>) { + let inner = self.inner.access_mut(guard); + inner.strong.has_count = true; + inner.weak.has_count = true; + } + + fn write(&self, writer: &mut BinderReturnWriter<'_>, code: u32) -> Result { + writer.write_code(code)?; + writer.write_payload(&self.ptr)?; + writer.write_payload(&self.cookie)?; + Ok(()) + } + + pub(crate) fn submit_oneway( + &self, + transaction: DLArc<Transaction>, + guard: &mut Guard<'_, ProcessInner, SpinLockBackend>, + ) -> Result<(), (BinderError, DLArc<dyn DeliverToRead>)> { + if guard.is_dead { + return Err((BinderError::new_dead(), transaction)); + } + + let inner = self.inner.access_mut(guard); + if inner.has_oneway_transaction { + inner.oneway_todo.push_back(transaction); + } else { + inner.has_oneway_transaction = true; + guard.push_work(transaction)?; + } + Ok(()) + } + + pub(crate) fn release(&self) { + let mut guard = self.owner.inner.lock(); + while let Some(work) = self.inner.access_mut(&mut guard).oneway_todo.pop_front() { + drop(guard); + work.into_arc().cancel(); + guard = self.owner.inner.lock(); + } + + let death_list = core::mem::take(&mut self.inner.access_mut(&mut guard).death_list); + drop(guard); + for death in death_list { + death.into_arc().set_dead(); + } + } + + pub(crate) fn pending_oneway_finished(&self) { + let mut guard = self.owner.inner.lock(); + if guard.is_dead { + // Cleanup will happen in `Process::deferred_release`. + return; + } + + let inner = self.inner.access_mut(&mut guard); + + let transaction = inner.oneway_todo.pop_front(); + inner.has_oneway_transaction = transaction.is_some(); + if let Some(transaction) = transaction { + match guard.push_work(transaction) { + Ok(()) => {} + Err((_err, work)) => { + // Process is dead. + // This shouldn't happen due to the `is_dead` check, but if it does, just drop + // the transaction and return. + drop(guard); + drop(work); + } + } + } + } + + /// Finds an outdated transaction that the given transaction can replace. + /// + /// If one is found, it is removed from the list and returned. + pub(crate) fn take_outdated_transaction( + &self, + new: &Transaction, + guard: &mut Guard<'_, ProcessInner, SpinLockBackend>, + ) -> Option<DLArc<Transaction>> { + let inner = self.inner.access_mut(guard); + let mut cursor = inner.oneway_todo.cursor_front(); + while let Some(next) = cursor.peek_next() { + if new.can_replace(&next) { + return Some(next.remove()); + } + cursor.move_next(); + } + None + } + + /// This is split into a separate function since it's called by both `Node::do_work` and + /// `NodeWrapper::do_work`. + fn do_work_locked( + &self, + writer: &mut BinderReturnWriter<'_>, + mut guard: Guard<'_, ProcessInner, SpinLockBackend>, + ) -> Result<bool> { + let inner = self.inner.access_mut(&mut guard); + let strong = inner.strong.count > 0; + let has_strong = inner.strong.has_count; + let weak = strong || inner.weak.count > 0; + let has_weak = inner.weak.has_count; + + if weak && !has_weak { + inner.weak.has_count = true; + inner.active_inc_refs += 1; + } + + if strong && !has_strong { + inner.strong.has_count = true; + inner.active_inc_refs += 1; + } + + let no_active_inc_refs = inner.active_inc_refs == 0; + let should_drop_weak = no_active_inc_refs && (!weak && has_weak); + let should_drop_strong = no_active_inc_refs && (!strong && has_strong); + if should_drop_weak { + inner.weak.has_count = false; + } + if should_drop_strong { + inner.strong.has_count = false; + } + if no_active_inc_refs && !weak { + // Remove the node if there are no references to it. + guard.remove_node(self.ptr); + } + drop(guard); + + if weak && !has_weak { + self.write(writer, BR_INCREFS)?; + } + if strong && !has_strong { + self.write(writer, BR_ACQUIRE)?; + } + if should_drop_strong { + self.write(writer, BR_RELEASE)?; + } + if should_drop_weak { + self.write(writer, BR_DECREFS)?; + } + + Ok(true) + } + + pub(crate) fn add_freeze_listener( + &self, + process: &Arc<Process>, + flags: kernel::alloc::Flags, + ) -> Result { + let mut vec_alloc = KVVec::<Arc<Process>>::new(); + loop { + let mut guard = self.owner.inner.lock(); + // Do not check for `guard.dead`. The `dead` flag that matters here is the owner of the + // listener, no the target. + let inner = self.inner.access_mut(&mut guard); + let len = inner.freeze_list.len(); + if len >= inner.freeze_list.capacity() { + if len >= vec_alloc.capacity() { + drop(guard); + vec_alloc = KVVec::with_capacity((1 + len).next_power_of_two(), flags)?; + continue; + } + mem::swap(&mut inner.freeze_list, &mut vec_alloc); + for elem in vec_alloc.drain_all() { + inner.freeze_list.push_within_capacity(elem)?; + } + } + inner.freeze_list.push_within_capacity(process.clone())?; + return Ok(()); + } + } + + pub(crate) fn remove_freeze_listener(&self, p: &Arc<Process>) { + let _unused_capacity; + let mut guard = self.owner.inner.lock(); + let inner = self.inner.access_mut(&mut guard); + let len = inner.freeze_list.len(); + inner.freeze_list.retain(|proc| !Arc::ptr_eq(proc, p)); + if len == inner.freeze_list.len() { + pr_warn!( + "Could not remove freeze listener for {}\n", + p.pid_in_current_ns() + ); + } + if inner.freeze_list.is_empty() { + _unused_capacity = mem::replace(&mut inner.freeze_list, KVVec::new()); + } + } + + pub(crate) fn freeze_list<'a>(&'a self, guard: &'a ProcessInner) -> &'a [Arc<Process>] { + &self.inner.access(guard).freeze_list + } +} + +impl DeliverToRead for Node { + fn do_work( + self: DArc<Self>, + _thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let mut owner_inner = self.owner.inner.lock(); + let inner = self.inner.access_mut(&mut owner_inner); + + assert!(inner.delivery_state.has_pushed_node); + if inner.delivery_state.has_pushed_wrapper { + // If the wrapper is scheduled, then we are either a normal push or weak zero2one + // increment, and the wrapper is a strong zero2one increment, so the wrapper always + // takes precedence over us. + assert!(inner.delivery_state.has_strong_zero2one); + inner.delivery_state.has_pushed_node = false; + inner.delivery_state.has_weak_zero2one = false; + return Ok(true); + } + + inner.delivery_state.has_pushed_node = false; + inner.delivery_state.has_weak_zero2one = false; + inner.delivery_state.has_strong_zero2one = false; + + self.do_work_locked(writer, owner_inner) + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + #[inline(never)] + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + seq_print!( + m, + "{}node work {}: u{:016x} c{:016x}\n", + prefix, + self.debug_id, + self.ptr, + self.cookie, + ); + Ok(()) + } +} + +/// Represents something that holds one or more ref-counts to a `Node`. +/// +/// Whenever process A holds a refcount to a node owned by a different process B, then process A +/// will store a `NodeRef` that refers to the `Node` in process B. When process A releases the +/// refcount, we destroy the NodeRef, which decrements the ref-count in process A. +/// +/// This type is also used for some other cases. For example, a transaction allocation holds a +/// refcount on the target node, and this is implemented by storing a `NodeRef` in the allocation +/// so that the destructor of the allocation will drop a refcount of the `Node`. +pub(crate) struct NodeRef { + pub(crate) node: DArc<Node>, + /// How many times does this NodeRef hold a refcount on the Node? + strong_node_count: usize, + weak_node_count: usize, + /// How many times does userspace hold a refcount on this NodeRef? + strong_count: usize, + weak_count: usize, +} + +impl NodeRef { + pub(crate) fn new(node: DArc<Node>, strong_count: usize, weak_count: usize) -> Self { + Self { + node, + strong_node_count: strong_count, + weak_node_count: weak_count, + strong_count, + weak_count, + } + } + + pub(crate) fn absorb(&mut self, mut other: Self) { + assert!( + Arc::ptr_eq(&self.node, &other.node), + "absorb called with differing nodes" + ); + self.strong_node_count += other.strong_node_count; + self.weak_node_count += other.weak_node_count; + self.strong_count += other.strong_count; + self.weak_count += other.weak_count; + other.strong_count = 0; + other.weak_count = 0; + other.strong_node_count = 0; + other.weak_node_count = 0; + + if self.strong_node_count >= 2 || self.weak_node_count >= 2 { + let mut guard = self.node.owner.inner.lock(); + let inner = self.node.inner.access_mut(&mut guard); + + if self.strong_node_count >= 2 { + inner.strong.count -= self.strong_node_count - 1; + self.strong_node_count = 1; + assert_ne!(inner.strong.count, 0); + } + if self.weak_node_count >= 2 { + inner.weak.count -= self.weak_node_count - 1; + self.weak_node_count = 1; + assert_ne!(inner.weak.count, 0); + } + } + } + + pub(crate) fn get_count(&self) -> (usize, usize) { + (self.strong_count, self.weak_count) + } + + pub(crate) fn clone(&self, strong: bool) -> Result<NodeRef> { + if strong && self.strong_count == 0 { + return Err(EINVAL); + } + Ok(self + .node + .owner + .inner + .lock() + .new_node_ref(self.node.clone(), strong, None)) + } + + /// Updates (increments or decrements) the number of references held against the node. If the + /// count being updated transitions from 0 to 1 or from 1 to 0, the node is notified by having + /// its `update_refcount` function called. + /// + /// Returns whether `self` should be removed (when both counts are zero). + pub(crate) fn update(&mut self, inc: bool, strong: bool) -> bool { + if strong && self.strong_count == 0 { + return false; + } + let (count, node_count, other_count) = if strong { + ( + &mut self.strong_count, + &mut self.strong_node_count, + self.weak_count, + ) + } else { + ( + &mut self.weak_count, + &mut self.weak_node_count, + self.strong_count, + ) + }; + if inc { + if *count == 0 { + *node_count = 1; + self.node.update_refcount(true, 1, strong); + } + *count += 1; + } else { + if *count == 0 { + pr_warn!( + "pid {} performed invalid decrement on ref\n", + kernel::current!().pid() + ); + return false; + } + *count -= 1; + if *count == 0 { + self.node.update_refcount(false, *node_count, strong); + *node_count = 0; + return other_count == 0; + } + } + false + } +} + +impl Drop for NodeRef { + // This destructor is called conditionally from `Allocation::drop`. That branch is often + // mispredicted. Inlining this method call reduces the cost of those branch mispredictions. + #[inline(always)] + fn drop(&mut self) { + if self.strong_node_count > 0 { + self.node + .update_refcount(false, self.strong_node_count, true); + } + if self.weak_node_count > 0 { + self.node + .update_refcount(false, self.weak_node_count, false); + } + } +} + +struct NodeDeathInner { + dead: bool, + cleared: bool, + notification_done: bool, + /// Indicates whether the normal flow was interrupted by removing the handle. In this case, we + /// need behave as if the death notification didn't exist (i.e., we don't deliver anything to + /// the user. + aborted: bool, +} + +/// Used to deliver notifications when a process dies. +/// +/// A process can request to be notified when a process dies using `BC_REQUEST_DEATH_NOTIFICATION`. +/// This will make the driver send a `BR_DEAD_BINDER` to userspace when the process dies (or +/// immediately if it is already dead). Userspace is supposed to respond with `BC_DEAD_BINDER_DONE` +/// once it has processed the notification. +/// +/// Userspace can unregister from death notifications using the `BC_CLEAR_DEATH_NOTIFICATION` +/// command. In this case, the kernel will respond with `BR_CLEAR_DEATH_NOTIFICATION_DONE` once the +/// notification has been removed. Note that if the remote process dies before the kernel has +/// responded with `BR_CLEAR_DEATH_NOTIFICATION_DONE`, then the kernel will still send a +/// `BR_DEAD_BINDER`, which userspace must be able to process. In this case, the kernel will wait +/// for the `BC_DEAD_BINDER_DONE` command before it sends `BR_CLEAR_DEATH_NOTIFICATION_DONE`. +/// +/// Note that even if the kernel sends a `BR_DEAD_BINDER`, this does not remove the death +/// notification. Userspace must still remove it manually using `BC_CLEAR_DEATH_NOTIFICATION`. +/// +/// If a process uses `BC_RELEASE` to destroy its last refcount on a node that has an active death +/// registration, then the death registration is immediately deleted (we implement this using the +/// `aborted` field). However, userspace is not supposed to delete a `NodeRef` without first +/// deregistering death notifications, so this codepath is not executed under normal circumstances. +#[pin_data] +pub(crate) struct NodeDeath { + node: DArc<Node>, + process: Arc<Process>, + pub(crate) cookie: u64, + #[pin] + links_track: AtomicTracker<0>, + /// Used by the owner `Node` to store a list of registered death notifications. + /// + /// # Invariants + /// + /// Only ever used with the `death_list` list of `self.node`. + #[pin] + death_links: ListLinks<1>, + /// Used by the process to keep track of the death notifications for which we have sent a + /// `BR_DEAD_BINDER` but not yet received a `BC_DEAD_BINDER_DONE`. + /// + /// # Invariants + /// + /// Only ever used with the `delivered_deaths` list of `self.process`. + #[pin] + delivered_links: ListLinks<2>, + #[pin] + delivered_links_track: AtomicTracker<2>, + #[pin] + inner: SpinLock<NodeDeathInner>, +} + +impl NodeDeath { + /// Constructs a new node death notification object. + pub(crate) fn new( + node: DArc<Node>, + process: Arc<Process>, + cookie: u64, + ) -> impl PinInit<DTRWrap<Self>> { + DTRWrap::new(pin_init!( + Self { + node, + process, + cookie, + links_track <- AtomicTracker::new(), + death_links <- ListLinks::new(), + delivered_links <- ListLinks::new(), + delivered_links_track <- AtomicTracker::new(), + inner <- kernel::new_spinlock!(NodeDeathInner { + dead: false, + cleared: false, + notification_done: false, + aborted: false, + }, "NodeDeath::inner"), + } + )) + } + + /// Sets the cleared flag to `true`. + /// + /// It removes `self` from the node's death notification list if needed. + /// + /// Returns whether it needs to be queued. + pub(crate) fn set_cleared(self: &DArc<Self>, abort: bool) -> bool { + let (needs_removal, needs_queueing) = { + // Update state and determine if we need to queue a work item. We only need to do it + // when the node is not dead or if the user already completed the death notification. + let mut inner = self.inner.lock(); + if abort { + inner.aborted = true; + } + if inner.cleared { + // Already cleared. + return false; + } + inner.cleared = true; + (!inner.dead, !inner.dead || inner.notification_done) + }; + + // Remove death notification from node. + if needs_removal { + let mut owner_inner = self.node.owner.inner.lock(); + let node_inner = self.node.inner.access_mut(&mut owner_inner); + // SAFETY: A `NodeDeath` is never inserted into the death list of any node other than + // its owner, so it is either in this death list or in no death list. + unsafe { node_inner.death_list.remove(self) }; + } + needs_queueing + } + + /// Sets the 'notification done' flag to `true`. + pub(crate) fn set_notification_done(self: DArc<Self>, thread: &Thread) { + let needs_queueing = { + let mut inner = self.inner.lock(); + inner.notification_done = true; + inner.cleared + }; + if needs_queueing { + if let Some(death) = ListArc::try_from_arc_or_drop(self) { + let _ = thread.push_work_if_looper(death); + } + } + } + + /// Sets the 'dead' flag to `true` and queues work item if needed. + pub(crate) fn set_dead(self: DArc<Self>) { + let needs_queueing = { + let mut inner = self.inner.lock(); + if inner.cleared { + false + } else { + inner.dead = true; + true + } + }; + if needs_queueing { + // Push the death notification to the target process. There is nothing else to do if + // it's already dead. + if let Some(death) = ListArc::try_from_arc_or_drop(self) { + let process = death.process.clone(); + let _ = process.push_work(death); + } + } + } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for NodeDeath { + tracked_by links_track: AtomicTracker; + } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<1> for DTRWrap<NodeDeath> { untracked; } +} +kernel::list::impl_list_item! { + impl ListItem<1> for DTRWrap<NodeDeath> { + using ListLinks { self.wrapped.death_links }; + } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<2> for DTRWrap<NodeDeath> { + tracked_by wrapped: NodeDeath; + } +} +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<2> for NodeDeath { + tracked_by delivered_links_track: AtomicTracker<2>; + } +} +kernel::list::impl_list_item! { + impl ListItem<2> for DTRWrap<NodeDeath> { + using ListLinks { self.wrapped.delivered_links }; + } +} + +impl DeliverToRead for NodeDeath { + fn do_work( + self: DArc<Self>, + _thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let done = { + let inner = self.inner.lock(); + if inner.aborted { + return Ok(true); + } + inner.cleared && (!inner.dead || inner.notification_done) + }; + + let cookie = self.cookie; + let cmd = if done { + BR_CLEAR_DEATH_NOTIFICATION_DONE + } else { + let process = self.process.clone(); + let mut process_inner = process.inner.lock(); + let inner = self.inner.lock(); + if inner.aborted { + return Ok(true); + } + // We're still holding the inner lock, so it cannot be aborted while we insert it into + // the delivered list. + process_inner.death_delivered(self.clone()); + BR_DEAD_BINDER + }; + + writer.write_code(cmd)?; + writer.write_payload(&cookie)?; + // DEAD_BINDER notifications can cause transactions, so stop processing work items when we + // get to a death notification. + Ok(cmd != BR_DEAD_BINDER) + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + #[inline(never)] + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + let inner = self.inner.lock(); + + let dead_binder = inner.dead && !inner.notification_done; + + if dead_binder { + if inner.cleared { + seq_print!(m, "{}has cleared dead binder\n", prefix); + } else { + seq_print!(m, "{}has dead binder\n", prefix); + } + } else { + seq_print!(m, "{}has cleared death notification\n", prefix); + } + + Ok(()) + } +} diff --git a/drivers/android/binder/node/wrapper.rs b/drivers/android/binder/node/wrapper.rs new file mode 100644 index 000000000000..43294c050502 --- /dev/null +++ b/drivers/android/binder/node/wrapper.rs @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{list::ListArc, prelude::*, seq_file::SeqFile, seq_print, sync::UniqueArc}; + +use crate::{node::Node, thread::Thread, BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead}; + +use core::mem::MaybeUninit; + +pub(crate) struct CritIncrWrapper { + inner: UniqueArc<MaybeUninit<DTRWrap<NodeWrapper>>>, +} + +impl CritIncrWrapper { + pub(crate) fn new() -> Result<Self> { + Ok(CritIncrWrapper { + inner: UniqueArc::new_uninit(GFP_KERNEL)?, + }) + } + + pub(super) fn init(self, node: DArc<Node>) -> DLArc<dyn DeliverToRead> { + match self.inner.pin_init_with(DTRWrap::new(NodeWrapper { node })) { + Ok(initialized) => ListArc::from(initialized) as _, + Err(err) => match err {}, + } + } +} + +struct NodeWrapper { + node: DArc<Node>, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for NodeWrapper { + untracked; + } +} + +impl DeliverToRead for NodeWrapper { + fn do_work( + self: DArc<Self>, + _thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let node = &self.node; + let mut owner_inner = node.owner.inner.lock(); + let inner = node.inner.access_mut(&mut owner_inner); + + let ds = &mut inner.delivery_state; + + assert!(ds.has_pushed_wrapper); + assert!(ds.has_strong_zero2one); + ds.has_pushed_wrapper = false; + ds.has_strong_zero2one = false; + + node.do_work_locked(writer, owner_inner) + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + #[inline(never)] + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + seq_print!( + m, + "{}node work {}: u{:016x} c{:016x}\n", + prefix, + self.node.debug_id, + self.node.ptr, + self.node.cookie, + ); + Ok(()) + } +} diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs new file mode 100644 index 000000000000..9379038f61f5 --- /dev/null +++ b/drivers/android/binder/page_range.rs @@ -0,0 +1,734 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! This module has utilities for managing a page range where unused pages may be reclaimed by a +//! vma shrinker. + +// To avoid deadlocks, locks are taken in the order: +// +// 1. mmap lock +// 2. spinlock +// 3. lru spinlock +// +// The shrinker will use trylock methods because it locks them in a different order. + +use core::{ + marker::PhantomPinned, + mem::{size_of, size_of_val, MaybeUninit}, + ptr, +}; + +use kernel::{ + bindings, + error::Result, + ffi::{c_ulong, c_void}, + mm::{virt, Mm, MmWithUser}, + new_mutex, new_spinlock, + page::{Page, PAGE_SHIFT, PAGE_SIZE}, + prelude::*, + str::CStr, + sync::{aref::ARef, Mutex, SpinLock}, + task::Pid, + transmute::FromBytes, + types::Opaque, + uaccess::UserSliceReader, +}; + +/// Represents a shrinker that can be registered with the kernel. +/// +/// Each shrinker can be used by many `ShrinkablePageRange` objects. +#[repr(C)] +pub(crate) struct Shrinker { + inner: Opaque<*mut bindings::shrinker>, + list_lru: Opaque<bindings::list_lru>, +} + +// SAFETY: The shrinker and list_lru are thread safe. +unsafe impl Send for Shrinker {} +// SAFETY: The shrinker and list_lru are thread safe. +unsafe impl Sync for Shrinker {} + +impl Shrinker { + /// Create a new shrinker. + /// + /// # Safety + /// + /// Before using this shrinker with a `ShrinkablePageRange`, the `register` method must have + /// been called exactly once, and it must not have returned an error. + pub(crate) const unsafe fn new() -> Self { + Self { + inner: Opaque::uninit(), + list_lru: Opaque::uninit(), + } + } + + /// Register this shrinker with the kernel. + pub(crate) fn register(&'static self, name: &CStr) -> Result<()> { + // SAFETY: These fields are not yet used, so it's okay to zero them. + unsafe { + self.inner.get().write(ptr::null_mut()); + self.list_lru.get().write_bytes(0, 1); + } + + // SAFETY: The field is not yet used, so we can initialize it. + let ret = unsafe { bindings::__list_lru_init(self.list_lru.get(), false, ptr::null_mut()) }; + if ret != 0 { + return Err(Error::from_errno(ret)); + } + + // SAFETY: The `name` points at a valid c string. + let shrinker = unsafe { bindings::shrinker_alloc(0, name.as_char_ptr()) }; + if shrinker.is_null() { + // SAFETY: We initialized it, so its okay to destroy it. + unsafe { bindings::list_lru_destroy(self.list_lru.get()) }; + return Err(Error::from_errno(ret)); + } + + // SAFETY: We're about to register the shrinker, and these are the fields we need to + // initialize. (All other fields are already zeroed.) + unsafe { + (&raw mut (*shrinker).count_objects).write(Some(rust_shrink_count)); + (&raw mut (*shrinker).scan_objects).write(Some(rust_shrink_scan)); + (&raw mut (*shrinker).private_data).write(self.list_lru.get().cast()); + } + + // SAFETY: The new shrinker has been fully initialized, so we can register it. + unsafe { bindings::shrinker_register(shrinker) }; + + // SAFETY: This initializes the pointer to the shrinker so that we can use it. + unsafe { self.inner.get().write(shrinker) }; + + Ok(()) + } +} + +/// A container that manages a page range in a vma. +/// +/// The pages can be thought of as an array of booleans of whether the pages are usable. The +/// methods `use_range` and `stop_using_range` set all booleans in a range to true or false +/// respectively. Initially, no pages are allocated. When a page is not used, it is not freed +/// immediately. Instead, it is made available to the memory shrinker to free it if the device is +/// under memory pressure. +/// +/// It's okay for `use_range` and `stop_using_range` to race with each other, although there's no +/// way to know whether an index ends up with true or false if a call to `use_range` races with +/// another call to `stop_using_range` on a given index. +/// +/// It's also okay for the two methods to race with themselves, e.g. if two threads call +/// `use_range` on the same index, then that's fine and neither call will return until the page is +/// allocated and mapped. +/// +/// The methods that read or write to a range require that the page is marked as in use. So it is +/// _not_ okay to call `stop_using_range` on a page that is in use by the methods that read or +/// write to the page. +#[pin_data(PinnedDrop)] +pub(crate) struct ShrinkablePageRange { + /// Shrinker object registered with the kernel. + shrinker: &'static Shrinker, + /// Pid using this page range. Only used as debugging information. + pid: Pid, + /// The mm for the relevant process. + mm: ARef<Mm>, + /// Used to synchronize calls to `vm_insert_page` and `zap_page_range_single`. + #[pin] + mm_lock: Mutex<()>, + /// Spinlock protecting changes to pages. + #[pin] + lock: SpinLock<Inner>, + + /// Must not move, since page info has pointers back. + #[pin] + _pin: PhantomPinned, +} + +struct Inner { + /// Array of pages. + /// + /// Since this is also accessed by the shrinker, we can't use a `Box`, which asserts exclusive + /// ownership. To deal with that, we manage it using raw pointers. + pages: *mut PageInfo, + /// Length of the `pages` array. + size: usize, + /// The address of the vma to insert the pages into. + vma_addr: usize, +} + +// SAFETY: proper locking is in place for `Inner` +unsafe impl Send for Inner {} + +type StableMmGuard = + kernel::sync::lock::Guard<'static, (), kernel::sync::lock::mutex::MutexBackend>; + +/// An array element that describes the current state of a page. +/// +/// There are three states: +/// +/// * Free. The page is None. The `lru` element is not queued. +/// * Available. The page is Some. The `lru` element is queued to the shrinker's lru. +/// * Used. The page is Some. The `lru` element is not queued. +/// +/// When an element is available, the shrinker is able to free the page. +#[repr(C)] +struct PageInfo { + lru: bindings::list_head, + page: Option<Page>, + range: *const ShrinkablePageRange, +} + +impl PageInfo { + /// # Safety + /// + /// The caller ensures that writing to `me.page` is ok, and that the page is not currently set. + unsafe fn set_page(me: *mut PageInfo, page: Page) { + // SAFETY: This pointer offset is in bounds. + let ptr = unsafe { &raw mut (*me).page }; + + // SAFETY: The pointer is valid for writing, so also valid for reading. + if unsafe { (*ptr).is_some() } { + pr_err!("set_page called when there is already a page"); + // SAFETY: We will initialize the page again below. + unsafe { ptr::drop_in_place(ptr) }; + } + + // SAFETY: The pointer is valid for writing. + unsafe { ptr::write(ptr, Some(page)) }; + } + + /// # Safety + /// + /// The caller ensures that reading from `me.page` is ok for the duration of 'a. + unsafe fn get_page<'a>(me: *const PageInfo) -> Option<&'a Page> { + // SAFETY: This pointer offset is in bounds. + let ptr = unsafe { &raw const (*me).page }; + + // SAFETY: The pointer is valid for reading. + unsafe { (*ptr).as_ref() } + } + + /// # Safety + /// + /// The caller ensures that writing to `me.page` is ok for the duration of 'a. + unsafe fn take_page(me: *mut PageInfo) -> Option<Page> { + // SAFETY: This pointer offset is in bounds. + let ptr = unsafe { &raw mut (*me).page }; + + // SAFETY: The pointer is valid for reading. + unsafe { (*ptr).take() } + } + + /// Add this page to the lru list, if not already in the list. + /// + /// # Safety + /// + /// The pointer must be valid, and it must be the right shrinker and nid. + unsafe fn list_lru_add(me: *mut PageInfo, nid: i32, shrinker: &'static Shrinker) { + // SAFETY: This pointer offset is in bounds. + let lru_ptr = unsafe { &raw mut (*me).lru }; + // SAFETY: The lru pointer is valid, and we're not using it with any other lru list. + unsafe { bindings::list_lru_add(shrinker.list_lru.get(), lru_ptr, nid, ptr::null_mut()) }; + } + + /// Remove this page from the lru list, if it is in the list. + /// + /// # Safety + /// + /// The pointer must be valid, and it must be the right shrinker and nid. + unsafe fn list_lru_del(me: *mut PageInfo, nid: i32, shrinker: &'static Shrinker) { + // SAFETY: This pointer offset is in bounds. + let lru_ptr = unsafe { &raw mut (*me).lru }; + // SAFETY: The lru pointer is valid, and we're not using it with any other lru list. + unsafe { bindings::list_lru_del(shrinker.list_lru.get(), lru_ptr, nid, ptr::null_mut()) }; + } +} + +impl ShrinkablePageRange { + /// Create a new `ShrinkablePageRange` using the given shrinker. + pub(crate) fn new(shrinker: &'static Shrinker) -> impl PinInit<Self, Error> { + try_pin_init!(Self { + shrinker, + pid: kernel::current!().pid(), + mm: ARef::from(&**kernel::current!().mm().ok_or(ESRCH)?), + mm_lock <- new_mutex!((), "ShrinkablePageRange::mm"), + lock <- new_spinlock!(Inner { + pages: ptr::null_mut(), + size: 0, + vma_addr: 0, + }, "ShrinkablePageRange"), + _pin: PhantomPinned, + }) + } + + pub(crate) fn stable_trylock_mm(&self) -> Option<StableMmGuard> { + // SAFETY: This extends the duration of the reference. Since this call happens before + // `mm_lock` is taken in the destructor of `ShrinkablePageRange`, the destructor will block + // until the returned guard is dropped. This ensures that the guard is valid until dropped. + let mm_lock = unsafe { &*ptr::from_ref(&self.mm_lock) }; + + mm_lock.try_lock() + } + + /// Register a vma with this page range. Returns the size of the region. + pub(crate) fn register_with_vma(&self, vma: &virt::VmaNew) -> Result<usize> { + let num_bytes = usize::min(vma.end() - vma.start(), bindings::SZ_4M as usize); + let num_pages = num_bytes >> PAGE_SHIFT; + + if !ptr::eq::<Mm>(&*self.mm, &**vma.mm()) { + pr_debug!("Failed to register with vma: invalid vma->vm_mm"); + return Err(EINVAL); + } + if num_pages == 0 { + pr_debug!("Failed to register with vma: size zero"); + return Err(EINVAL); + } + + let mut pages = KVVec::<PageInfo>::with_capacity(num_pages, GFP_KERNEL)?; + + // SAFETY: This just initializes the pages array. + unsafe { + let self_ptr = self as *const ShrinkablePageRange; + for i in 0..num_pages { + let info = pages.as_mut_ptr().add(i); + (&raw mut (*info).range).write(self_ptr); + (&raw mut (*info).page).write(None); + let lru = &raw mut (*info).lru; + (&raw mut (*lru).next).write(lru); + (&raw mut (*lru).prev).write(lru); + } + } + + let mut inner = self.lock.lock(); + if inner.size > 0 { + pr_debug!("Failed to register with vma: already registered"); + drop(inner); + return Err(EBUSY); + } + + inner.pages = pages.into_raw_parts().0; + inner.size = num_pages; + inner.vma_addr = vma.start(); + + Ok(num_pages) + } + + /// Make sure that the given pages are allocated and mapped. + /// + /// Must not be called from an atomic context. + pub(crate) fn use_range(&self, start: usize, end: usize) -> Result<()> { + if start >= end { + return Ok(()); + } + let mut inner = self.lock.lock(); + assert!(end <= inner.size); + + for i in start..end { + // SAFETY: This pointer offset is in bounds. + let page_info = unsafe { inner.pages.add(i) }; + + // SAFETY: The pointer is valid, and we hold the lock so reading from the page is okay. + if let Some(page) = unsafe { PageInfo::get_page(page_info) } { + // Since we're going to use the page, we should remove it from the lru list so that + // the shrinker will not free it. + // + // SAFETY: The pointer is valid, and this is the right shrinker. + // + // The shrinker can't free the page between the check and this call to + // `list_lru_del` because we hold the lock. + unsafe { PageInfo::list_lru_del(page_info, page.nid(), self.shrinker) }; + } else { + // We have to allocate a new page. Use the slow path. + drop(inner); + // SAFETY: `i < end <= inner.size` so `i` is in bounds. + match unsafe { self.use_page_slow(i) } { + Ok(()) => {} + Err(err) => { + pr_warn!("Error in use_page_slow: {:?}", err); + return Err(err); + } + } + inner = self.lock.lock(); + } + } + Ok(()) + } + + /// Mark the given page as in use, slow path. + /// + /// Must not be called from an atomic context. + /// + /// # Safety + /// + /// Assumes that `i` is in bounds. + #[cold] + unsafe fn use_page_slow(&self, i: usize) -> Result<()> { + let new_page = Page::alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO)?; + + let mm_mutex = self.mm_lock.lock(); + let inner = self.lock.lock(); + + // SAFETY: This pointer offset is in bounds. + let page_info = unsafe { inner.pages.add(i) }; + + // SAFETY: The pointer is valid, and we hold the lock so reading from the page is okay. + if let Some(page) = unsafe { PageInfo::get_page(page_info) } { + // The page was already there, or someone else added the page while we didn't hold the + // spinlock. + // + // SAFETY: The pointer is valid, and this is the right shrinker. + // + // The shrinker can't free the page between the check and this call to + // `list_lru_del` because we hold the lock. + unsafe { PageInfo::list_lru_del(page_info, page.nid(), self.shrinker) }; + return Ok(()); + } + + let vma_addr = inner.vma_addr; + // Release the spinlock while we insert the page into the vma. + drop(inner); + + // No overflow since we stay in bounds of the vma. + let user_page_addr = vma_addr + (i << PAGE_SHIFT); + + // We use `mmput_async` when dropping the `mm` because `use_page_slow` is usually used from + // a remote process. If the call to `mmput` races with the process shutting down, then the + // caller of `use_page_slow` becomes responsible for cleaning up the `mm`, which doesn't + // happen until it returns to userspace. However, the caller might instead go to sleep and + // wait for the owner of the `mm` to wake it up, which doesn't happen because it's in the + // middle of a shutdown process that won't complete until the `mm` is dropped. This can + // amount to a deadlock. + // + // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a + // workqueue. + MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?) + .mmap_read_lock() + .vma_lookup(vma_addr) + .ok_or(ESRCH)? + .as_mixedmap_vma() + .ok_or(ESRCH)? + .vm_insert_page(user_page_addr, &new_page) + .inspect_err(|err| { + pr_warn!( + "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}", + user_page_addr, + vma_addr, + i, + err + ) + })?; + + let inner = self.lock.lock(); + + // SAFETY: The `page_info` pointer is valid and currently does not have a page. The page + // can be written to since we hold the lock. + // + // We released and reacquired the spinlock since we checked that the page is null, but we + // always hold the mm_lock mutex when setting the page to a non-null value, so it's not + // possible for someone else to have changed it since our check. + unsafe { PageInfo::set_page(page_info, new_page) }; + + drop(inner); + drop(mm_mutex); + + Ok(()) + } + + /// If the given page is in use, then mark it as available so that the shrinker can free it. + /// + /// May be called from an atomic context. + pub(crate) fn stop_using_range(&self, start: usize, end: usize) { + if start >= end { + return; + } + let inner = self.lock.lock(); + assert!(end <= inner.size); + + for i in (start..end).rev() { + // SAFETY: The pointer is in bounds. + let page_info = unsafe { inner.pages.add(i) }; + + // SAFETY: Okay for reading since we have the lock. + if let Some(page) = unsafe { PageInfo::get_page(page_info) } { + // SAFETY: The pointer is valid, and it's the right shrinker. + unsafe { PageInfo::list_lru_add(page_info, page.nid(), self.shrinker) }; + } + } + } + + /// Helper for reading or writing to a range of bytes that may overlap with several pages. + /// + /// # Safety + /// + /// All pages touched by this operation must be in use for the duration of this call. + unsafe fn iterate<T>(&self, mut offset: usize, mut size: usize, mut cb: T) -> Result + where + T: FnMut(&Page, usize, usize) -> Result, + { + if size == 0 { + return Ok(()); + } + + let (pages, num_pages) = { + let inner = self.lock.lock(); + (inner.pages, inner.size) + }; + let num_bytes = num_pages << PAGE_SHIFT; + + // Check that the request is within the buffer. + if offset.checked_add(size).ok_or(EFAULT)? > num_bytes { + return Err(EFAULT); + } + + let mut page_index = offset >> PAGE_SHIFT; + offset &= PAGE_SIZE - 1; + while size > 0 { + let available = usize::min(size, PAGE_SIZE - offset); + // SAFETY: The pointer is in bounds. + let page_info = unsafe { pages.add(page_index) }; + // SAFETY: The caller guarantees that this page is in the "in use" state for the + // duration of this call to `iterate`, so nobody will change the page. + let page = unsafe { PageInfo::get_page(page_info) }; + if page.is_none() { + pr_warn!("Page is null!"); + } + let page = page.ok_or(EFAULT)?; + cb(page, offset, available)?; + size -= available; + page_index += 1; + offset = 0; + } + Ok(()) + } + + /// Copy from userspace into this page range. + /// + /// # Safety + /// + /// All pages touched by this operation must be in use for the duration of this call. + pub(crate) unsafe fn copy_from_user_slice( + &self, + reader: &mut UserSliceReader, + offset: usize, + size: usize, + ) -> Result { + // SAFETY: `self.iterate` has the same safety requirements as `copy_from_user_slice`. + unsafe { + self.iterate(offset, size, |page, offset, to_copy| { + page.copy_from_user_slice_raw(reader, offset, to_copy) + }) + } + } + + /// Copy from this page range into kernel space. + /// + /// # Safety + /// + /// All pages touched by this operation must be in use for the duration of this call. + pub(crate) unsafe fn read<T: FromBytes>(&self, offset: usize) -> Result<T> { + let mut out = MaybeUninit::<T>::uninit(); + let mut out_offset = 0; + // SAFETY: `self.iterate` has the same safety requirements as `read`. + unsafe { + self.iterate(offset, size_of::<T>(), |page, offset, to_copy| { + // SAFETY: The sum of `offset` and `to_copy` is bounded by the size of T. + let obj_ptr = (out.as_mut_ptr() as *mut u8).add(out_offset); + // SAFETY: The pointer points is in-bounds of the `out` variable, so it is valid. + page.read_raw(obj_ptr, offset, to_copy)?; + out_offset += to_copy; + Ok(()) + })?; + } + // SAFETY: We just initialised the data. + Ok(unsafe { out.assume_init() }) + } + + /// Copy from kernel space into this page range. + /// + /// # Safety + /// + /// All pages touched by this operation must be in use for the duration of this call. + pub(crate) unsafe fn write<T: ?Sized>(&self, offset: usize, obj: &T) -> Result { + let mut obj_offset = 0; + // SAFETY: `self.iterate` has the same safety requirements as `write`. + unsafe { + self.iterate(offset, size_of_val(obj), |page, offset, to_copy| { + // SAFETY: The sum of `offset` and `to_copy` is bounded by the size of T. + let obj_ptr = (obj as *const T as *const u8).add(obj_offset); + // SAFETY: We have a reference to the object, so the pointer is valid. + page.write_raw(obj_ptr, offset, to_copy)?; + obj_offset += to_copy; + Ok(()) + }) + } + } + + /// Write zeroes to the given range. + /// + /// # Safety + /// + /// All pages touched by this operation must be in use for the duration of this call. + pub(crate) unsafe fn fill_zero(&self, offset: usize, size: usize) -> Result { + // SAFETY: `self.iterate` has the same safety requirements as `copy_into`. + unsafe { + self.iterate(offset, size, |page, offset, len| { + page.fill_zero_raw(offset, len) + }) + } + } +} + +#[pinned_drop] +impl PinnedDrop for ShrinkablePageRange { + fn drop(self: Pin<&mut Self>) { + let (pages, size) = { + let lock = self.lock.lock(); + (lock.pages, lock.size) + }; + + if size == 0 { + return; + } + + // Note: This call is also necessary for the safety of `stable_trylock_mm`. + let mm_lock = self.mm_lock.lock(); + + // This is the destructor, so unlike the other methods, we only need to worry about races + // with the shrinker here. Since we hold the `mm_lock`, we also can't race with the + // shrinker, and after this loop, the shrinker will not access any of our pages since we + // removed them from the lru list. + for i in 0..size { + // SAFETY: Loop is in-bounds of the size. + let p_ptr = unsafe { pages.add(i) }; + // SAFETY: No other readers, so we can read. + if let Some(p) = unsafe { PageInfo::get_page(p_ptr) } { + // SAFETY: The pointer is valid and it's the right shrinker. + unsafe { PageInfo::list_lru_del(p_ptr, p.nid(), self.shrinker) }; + } + } + + drop(mm_lock); + + // SAFETY: `pages` was allocated as an `KVVec<PageInfo>` with capacity `size`. Furthermore, + // all `size` elements are initialized. Also, the array is no longer shared with the + // shrinker due to the above loop. + drop(unsafe { KVVec::from_raw_parts(pages, size, size) }); + } +} + +/// # Safety +/// Called by the shrinker. +#[no_mangle] +unsafe extern "C" fn rust_shrink_count( + shrink: *mut bindings::shrinker, + _sc: *mut bindings::shrink_control, +) -> c_ulong { + // SAFETY: We can access our own private data. + let list_lru = unsafe { (*shrink).private_data.cast::<bindings::list_lru>() }; + // SAFETY: Accessing the lru list is okay. Just an FFI call. + unsafe { bindings::list_lru_count(list_lru) } +} + +/// # Safety +/// Called by the shrinker. +#[no_mangle] +unsafe extern "C" fn rust_shrink_scan( + shrink: *mut bindings::shrinker, + sc: *mut bindings::shrink_control, +) -> c_ulong { + // SAFETY: We can access our own private data. + let list_lru = unsafe { (*shrink).private_data.cast::<bindings::list_lru>() }; + // SAFETY: Caller guarantees that it is safe to read this field. + let nr_to_scan = unsafe { (*sc).nr_to_scan }; + // SAFETY: Accessing the lru list is okay. Just an FFI call. + unsafe { + bindings::list_lru_walk( + list_lru, + Some(bindings::rust_shrink_free_page_wrap), + ptr::null_mut(), + nr_to_scan, + ) + } +} + +const LRU_SKIP: bindings::lru_status = bindings::lru_status_LRU_SKIP; +const LRU_REMOVED_ENTRY: bindings::lru_status = bindings::lru_status_LRU_REMOVED_RETRY; + +/// # Safety +/// Called by the shrinker. +#[no_mangle] +unsafe extern "C" fn rust_shrink_free_page( + item: *mut bindings::list_head, + lru: *mut bindings::list_lru_one, + _cb_arg: *mut c_void, +) -> bindings::lru_status { + // Fields that should survive after unlocking the lru lock. + let page; + let page_index; + let mm; + let mmap_read; + let mm_mutex; + let vma_addr; + + { + // CAST: The `list_head` field is first in `PageInfo`. + let info = item as *mut PageInfo; + // SAFETY: The `range` field of `PageInfo` is immutable. + let range = unsafe { &*((*info).range) }; + + mm = match range.mm.mmget_not_zero() { + Some(mm) => MmWithUser::into_mmput_async(mm), + None => return LRU_SKIP, + }; + + mm_mutex = match range.stable_trylock_mm() { + Some(guard) => guard, + None => return LRU_SKIP, + }; + + mmap_read = match mm.mmap_read_trylock() { + Some(guard) => guard, + None => return LRU_SKIP, + }; + + // We can't lock it normally here, since we hold the lru lock. + let inner = match range.lock.try_lock() { + Some(inner) => inner, + None => return LRU_SKIP, + }; + + // SAFETY: The item is in this lru list, so it's okay to remove it. + unsafe { bindings::list_lru_isolate(lru, item) }; + + // SAFETY: Both pointers are in bounds of the same allocation. + page_index = unsafe { info.offset_from(inner.pages) } as usize; + + // SAFETY: We hold the spinlock, so we can take the page. + // + // This sets the page pointer to zero before we unmap it from the vma. However, we call + // `zap_page_range` before we release the mmap lock, so `use_page_slow` will not be able to + // insert a new page until after our call to `zap_page_range`. + page = unsafe { PageInfo::take_page(info) }; + vma_addr = inner.vma_addr; + + // From this point on, we don't access this PageInfo or ShrinkablePageRange again, because + // they can be freed at any point after we unlock `lru_lock`. This is with the exception of + // `mm_mutex` which is kept alive by holding the lock. + } + + // SAFETY: The lru lock is locked when this method is called. + unsafe { bindings::spin_unlock(&raw mut (*lru).lock) }; + + if let Some(vma) = mmap_read.vma_lookup(vma_addr) { + let user_page_addr = vma_addr + (page_index << PAGE_SHIFT); + vma.zap_page_range_single(user_page_addr, PAGE_SIZE); + } + + drop(mmap_read); + drop(mm_mutex); + drop(mm); + drop(page); + + // SAFETY: We just unlocked the lru lock, but it should be locked when we return. + unsafe { bindings::spin_lock(&raw mut (*lru).lock) }; + + LRU_REMOVED_ENTRY +} diff --git a/drivers/android/binder/page_range_helper.c b/drivers/android/binder/page_range_helper.c new file mode 100644 index 000000000000..496887723ee0 --- /dev/null +++ b/drivers/android/binder/page_range_helper.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* C helper for page_range.rs to work around a CFI violation. + * + * Bindgen currently pretends that `enum lru_status` is the same as an integer. + * This assumption is fine ABI-wise, but once you add CFI to the mix, it + * triggers a CFI violation because `enum lru_status` gets a different CFI tag. + * + * This file contains a workaround until bindgen can be fixed. + * + * Copyright (C) 2025 Google LLC. + */ +#include "page_range_helper.h" + +unsigned int rust_shrink_free_page(struct list_head *item, + struct list_lru_one *list, + void *cb_arg); + +enum lru_status +rust_shrink_free_page_wrap(struct list_head *item, struct list_lru_one *list, + void *cb_arg) +{ + return rust_shrink_free_page(item, list, cb_arg); +} diff --git a/drivers/android/binder/page_range_helper.h b/drivers/android/binder/page_range_helper.h new file mode 100644 index 000000000000..18dd2dd117b2 --- /dev/null +++ b/drivers/android/binder/page_range_helper.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Google, Inc. + */ + +#ifndef _LINUX_PAGE_RANGE_HELPER_H +#define _LINUX_PAGE_RANGE_HELPER_H + +#include <linux/list_lru.h> + +enum lru_status +rust_shrink_free_page_wrap(struct list_head *item, struct list_lru_one *list, + void *cb_arg); + +#endif /* _LINUX_PAGE_RANGE_HELPER_H */ diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs new file mode 100644 index 000000000000..f13a747e784c --- /dev/null +++ b/drivers/android/binder/process.rs @@ -0,0 +1,1696 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! This module defines the `Process` type, which represents a process using a particular binder +//! context. +//! +//! The `Process` object keeps track of all of the resources that this process owns in the binder +//! context. +//! +//! There is one `Process` object for each binder fd that a process has opened, so processes using +//! several binder contexts have several `Process` objects. This ensures that the contexts are +//! fully separated. + +use core::mem::take; + +use kernel::{ + bindings, + cred::Credential, + error::Error, + fs::file::{self, File}, + list::{List, ListArc, ListArcField, ListLinks}, + mm, + prelude::*, + rbtree::{self, RBTree, RBTreeNode, RBTreeNodeReservation}, + seq_file::SeqFile, + seq_print, + sync::poll::PollTable, + sync::{ + lock::{spinlock::SpinLockBackend, Guard}, + Arc, ArcBorrow, CondVar, CondVarTimeoutResult, Mutex, SpinLock, UniqueArc, + }, + task::Task, + types::ARef, + uaccess::{UserSlice, UserSliceReader}, + uapi, + workqueue::{self, Work}, +}; + +use crate::{ + allocation::{Allocation, AllocationInfo, NewAllocation}, + context::Context, + defs::*, + error::{BinderError, BinderResult}, + node::{CouldNotDeliverCriticalIncrement, CritIncrWrapper, Node, NodeDeath, NodeRef}, + page_range::ShrinkablePageRange, + range_alloc::{RangeAllocator, ReserveNew, ReserveNewArgs}, + stats::BinderStats, + thread::{PushWorkRes, Thread}, + BinderfsProcFile, DArc, DLArc, DTRWrap, DeliverToRead, +}; + +#[path = "freeze.rs"] +mod freeze; +use self::freeze::{FreezeCookie, FreezeListener}; + +struct Mapping { + address: usize, + alloc: RangeAllocator<AllocationInfo>, +} + +impl Mapping { + fn new(address: usize, size: usize) -> Self { + Self { + address, + alloc: RangeAllocator::new(size), + } + } +} + +// bitflags for defer_work. +const PROC_DEFER_FLUSH: u8 = 1; +const PROC_DEFER_RELEASE: u8 = 2; + +/// The fields of `Process` protected by the spinlock. +pub(crate) struct ProcessInner { + is_manager: bool, + pub(crate) is_dead: bool, + threads: RBTree<i32, Arc<Thread>>, + /// INVARIANT: Threads pushed to this list must be owned by this process. + ready_threads: List<Thread>, + nodes: RBTree<u64, DArc<Node>>, + mapping: Option<Mapping>, + work: List<DTRWrap<dyn DeliverToRead>>, + delivered_deaths: List<DTRWrap<NodeDeath>, 2>, + + /// The number of requested threads that haven't registered yet. + requested_thread_count: u32, + /// The maximum number of threads used by the process thread pool. + max_threads: u32, + /// The number of threads the started and registered with the thread pool. + started_thread_count: u32, + + /// Bitmap of deferred work to do. + defer_work: u8, + + /// Number of transactions to be transmitted before processes in freeze_wait + /// are woken up. + outstanding_txns: u32, + /// Process is frozen and unable to service binder transactions. + pub(crate) is_frozen: bool, + /// Process received sync transactions since last frozen. + pub(crate) sync_recv: bool, + /// Process received async transactions since last frozen. + pub(crate) async_recv: bool, + pub(crate) binderfs_file: Option<BinderfsProcFile>, + /// Check for oneway spam + oneway_spam_detection_enabled: bool, +} + +impl ProcessInner { + fn new() -> Self { + Self { + is_manager: false, + is_dead: false, + threads: RBTree::new(), + ready_threads: List::new(), + mapping: None, + nodes: RBTree::new(), + work: List::new(), + delivered_deaths: List::new(), + requested_thread_count: 0, + max_threads: 0, + started_thread_count: 0, + defer_work: 0, + outstanding_txns: 0, + is_frozen: false, + sync_recv: false, + async_recv: false, + binderfs_file: None, + oneway_spam_detection_enabled: false, + } + } + + /// Schedule the work item for execution on this process. + /// + /// If any threads are ready for work, then the work item is given directly to that thread and + /// it is woken up. Otherwise, it is pushed to the process work list. + /// + /// This call can fail only if the process is dead. In this case, the work item is returned to + /// the caller so that the caller can drop it after releasing the inner process lock. This is + /// necessary since the destructor of `Transaction` will take locks that can't necessarily be + /// taken while holding the inner process lock. + pub(crate) fn push_work( + &mut self, + work: DLArc<dyn DeliverToRead>, + ) -> Result<(), (BinderError, DLArc<dyn DeliverToRead>)> { + // Try to find a ready thread to which to push the work. + if let Some(thread) = self.ready_threads.pop_front() { + // Push to thread while holding state lock. This prevents the thread from giving up + // (for example, because of a signal) when we're about to deliver work. + match thread.push_work(work) { + PushWorkRes::Ok => Ok(()), + PushWorkRes::FailedDead(work) => Err((BinderError::new_dead(), work)), + } + } else if self.is_dead { + Err((BinderError::new_dead(), work)) + } else { + let sync = work.should_sync_wakeup(); + + // Didn't find a thread waiting for proc work; this can happen + // in two scenarios: + // 1. All threads are busy handling transactions + // In that case, one of those threads should call back into + // the kernel driver soon and pick up this work. + // 2. Threads are using the (e)poll interface, in which case + // they may be blocked on the waitqueue without having been + // added to waiting_threads. For this case, we just iterate + // over all threads not handling transaction work, and + // wake them all up. We wake all because we don't know whether + // a thread that called into (e)poll is handling non-binder + // work currently. + self.work.push_back(work); + + // Wake up polling threads, if any. + for thread in self.threads.values() { + thread.notify_if_poll_ready(sync); + } + + Ok(()) + } + } + + pub(crate) fn remove_node(&mut self, ptr: u64) { + self.nodes.remove(&ptr); + } + + /// Updates the reference count on the given node. + pub(crate) fn update_node_refcount( + &mut self, + node: &DArc<Node>, + inc: bool, + strong: bool, + count: usize, + othread: Option<&Thread>, + ) { + let push = node.update_refcount_locked(inc, strong, count, self); + + // If we decided that we need to push work, push either to the process or to a thread if + // one is specified. + if let Some(node) = push { + if let Some(thread) = othread { + thread.push_work_deferred(node); + } else { + let _ = self.push_work(node); + // Nothing to do: `push_work` may fail if the process is dead, but that's ok as in + // that case, it doesn't care about the notification. + } + } + } + + pub(crate) fn new_node_ref( + &mut self, + node: DArc<Node>, + strong: bool, + thread: Option<&Thread>, + ) -> NodeRef { + self.update_node_refcount(&node, true, strong, 1, thread); + let strong_count = if strong { 1 } else { 0 }; + NodeRef::new(node, strong_count, 1 - strong_count) + } + + pub(crate) fn new_node_ref_with_thread( + &mut self, + node: DArc<Node>, + strong: bool, + thread: &Thread, + wrapper: Option<CritIncrWrapper>, + ) -> Result<NodeRef, CouldNotDeliverCriticalIncrement> { + let push = match wrapper { + None => node + .incr_refcount_allow_zero2one(strong, self)? + .map(|node| node as _), + Some(wrapper) => node.incr_refcount_allow_zero2one_with_wrapper(strong, wrapper, self), + }; + if let Some(node) = push { + thread.push_work_deferred(node); + } + let strong_count = if strong { 1 } else { 0 }; + Ok(NodeRef::new(node, strong_count, 1 - strong_count)) + } + + /// Returns an existing node with the given pointer and cookie, if one exists. + /// + /// Returns an error if a node with the given pointer but a different cookie exists. + fn get_existing_node(&self, ptr: u64, cookie: u64) -> Result<Option<DArc<Node>>> { + match self.nodes.get(&ptr) { + None => Ok(None), + Some(node) => { + let (_, node_cookie) = node.get_id(); + if node_cookie == cookie { + Ok(Some(node.clone())) + } else { + Err(EINVAL) + } + } + } + } + + fn register_thread(&mut self) -> bool { + if self.requested_thread_count == 0 { + return false; + } + + self.requested_thread_count -= 1; + self.started_thread_count += 1; + true + } + + /// Finds a delivered death notification with the given cookie, removes it from the thread's + /// delivered list, and returns it. + fn pull_delivered_death(&mut self, cookie: u64) -> Option<DArc<NodeDeath>> { + let mut cursor = self.delivered_deaths.cursor_front(); + while let Some(next) = cursor.peek_next() { + if next.cookie == cookie { + return Some(next.remove().into_arc()); + } + cursor.move_next(); + } + None + } + + pub(crate) fn death_delivered(&mut self, death: DArc<NodeDeath>) { + if let Some(death) = ListArc::try_from_arc_or_drop(death) { + self.delivered_deaths.push_back(death); + } else { + pr_warn!("Notification added to `delivered_deaths` twice."); + } + } + + pub(crate) fn add_outstanding_txn(&mut self) { + self.outstanding_txns += 1; + } + + fn txns_pending_locked(&self) -> bool { + if self.outstanding_txns > 0 { + return true; + } + for thread in self.threads.values() { + if thread.has_current_transaction() { + return true; + } + } + false + } +} + +/// Used to keep track of a node that this process has a handle to. +#[pin_data] +pub(crate) struct NodeRefInfo { + debug_id: usize, + /// The refcount that this process owns to the node. + node_ref: ListArcField<NodeRef, { Self::LIST_PROC }>, + death: ListArcField<Option<DArc<NodeDeath>>, { Self::LIST_PROC }>, + /// Cookie of the active freeze listener for this node. + freeze: ListArcField<Option<FreezeCookie>, { Self::LIST_PROC }>, + /// Used to store this `NodeRefInfo` in the node's `refs` list. + #[pin] + links: ListLinks<{ Self::LIST_NODE }>, + /// The handle for this `NodeRefInfo`. + handle: u32, + /// The process that has a handle to the node. + pub(crate) process: Arc<Process>, +} + +impl NodeRefInfo { + /// The id used for the `Node::refs` list. + pub(crate) const LIST_NODE: u64 = 0x2da16350fb724a10; + /// The id used for the `ListArc` in `ProcessNodeRefs`. + const LIST_PROC: u64 = 0xd703a5263dcc8650; + + fn new(node_ref: NodeRef, handle: u32, process: Arc<Process>) -> impl PinInit<Self> { + pin_init!(Self { + debug_id: super::next_debug_id(), + node_ref: ListArcField::new(node_ref), + death: ListArcField::new(None), + freeze: ListArcField::new(None), + links <- ListLinks::new(), + handle, + process, + }) + } + + kernel::list::define_list_arc_field_getter! { + pub(crate) fn death(&mut self<{Self::LIST_PROC}>) -> &mut Option<DArc<NodeDeath>> { death } + pub(crate) fn freeze(&mut self<{Self::LIST_PROC}>) -> &mut Option<FreezeCookie> { freeze } + pub(crate) fn node_ref(&mut self<{Self::LIST_PROC}>) -> &mut NodeRef { node_ref } + pub(crate) fn node_ref2(&self<{Self::LIST_PROC}>) -> &NodeRef { node_ref } + } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<{Self::LIST_NODE}> for NodeRefInfo { untracked; } + impl ListArcSafe<{Self::LIST_PROC}> for NodeRefInfo { untracked; } +} +kernel::list::impl_list_item! { + impl ListItem<{Self::LIST_NODE}> for NodeRefInfo { + using ListLinks { self.links }; + } +} + +/// Keeps track of references this process has to nodes owned by other processes. +/// +/// TODO: Currently, the rbtree requires two allocations per node reference, and two tree +/// traversals to look up a node by `Node::global_id`. Once the rbtree is more powerful, these +/// extra costs should be eliminated. +struct ProcessNodeRefs { + /// Used to look up nodes using the 32-bit id that this process knows it by. + by_handle: RBTree<u32, ListArc<NodeRefInfo, { NodeRefInfo::LIST_PROC }>>, + /// Used to look up nodes without knowing their local 32-bit id. The usize is the address of + /// the underlying `Node` struct as returned by `Node::global_id`. + by_node: RBTree<usize, u32>, + /// Used to look up a `FreezeListener` by cookie. + /// + /// There might be multiple freeze listeners for the same node, but at most one of them is + /// active. + freeze_listeners: RBTree<FreezeCookie, FreezeListener>, +} + +impl ProcessNodeRefs { + fn new() -> Self { + Self { + by_handle: RBTree::new(), + by_node: RBTree::new(), + freeze_listeners: RBTree::new(), + } + } +} + +/// A process using binder. +/// +/// Strictly speaking, there can be multiple of these per process. There is one for each binder fd +/// that a process has opened, so processes using several binder contexts have several `Process` +/// objects. This ensures that the contexts are fully separated. +#[pin_data] +pub(crate) struct Process { + pub(crate) ctx: Arc<Context>, + + // The task leader (process). + pub(crate) task: ARef<Task>, + + // Credential associated with file when `Process` is created. + pub(crate) cred: ARef<Credential>, + + #[pin] + pub(crate) inner: SpinLock<ProcessInner>, + + #[pin] + pub(crate) pages: ShrinkablePageRange, + + // Waitqueue of processes waiting for all outstanding transactions to be + // processed. + #[pin] + freeze_wait: CondVar, + + // Node references are in a different lock to avoid recursive acquisition when + // incrementing/decrementing a node in another process. + #[pin] + node_refs: Mutex<ProcessNodeRefs>, + + // Work node for deferred work item. + #[pin] + defer_work: Work<Process>, + + // Links for process list in Context. + #[pin] + links: ListLinks, + + pub(crate) stats: BinderStats, +} + +kernel::impl_has_work! { + impl HasWork<Process> for Process { self.defer_work } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for Process { untracked; } +} +kernel::list::impl_list_item! { + impl ListItem<0> for Process { + using ListLinks { self.links }; + } +} + +impl workqueue::WorkItem for Process { + type Pointer = Arc<Process>; + + fn run(me: Arc<Self>) { + let defer; + { + let mut inner = me.inner.lock(); + defer = inner.defer_work; + inner.defer_work = 0; + } + + if defer & PROC_DEFER_FLUSH != 0 { + me.deferred_flush(); + } + if defer & PROC_DEFER_RELEASE != 0 { + me.deferred_release(); + } + } +} + +impl Process { + fn new(ctx: Arc<Context>, cred: ARef<Credential>) -> Result<Arc<Self>> { + let current = kernel::current!(); + let list_process = ListArc::pin_init::<Error>( + try_pin_init!(Process { + ctx, + cred, + inner <- kernel::new_spinlock!(ProcessInner::new(), "Process::inner"), + pages <- ShrinkablePageRange::new(&super::BINDER_SHRINKER), + node_refs <- kernel::new_mutex!(ProcessNodeRefs::new(), "Process::node_refs"), + freeze_wait <- kernel::new_condvar!("Process::freeze_wait"), + task: current.group_leader().into(), + defer_work <- kernel::new_work!("Process::defer_work"), + links <- ListLinks::new(), + stats: BinderStats::new(), + }), + GFP_KERNEL, + )?; + + let process = list_process.clone_arc(); + process.ctx.register_process(list_process); + + Ok(process) + } + + pub(crate) fn pid_in_current_ns(&self) -> kernel::task::Pid { + self.task.tgid_nr_ns(None) + } + + #[inline(never)] + pub(crate) fn debug_print_stats(&self, m: &SeqFile, ctx: &Context) -> Result<()> { + seq_print!(m, "proc {}\n", self.pid_in_current_ns()); + seq_print!(m, "context {}\n", &*ctx.name); + + let inner = self.inner.lock(); + seq_print!(m, " threads: {}\n", inner.threads.iter().count()); + seq_print!( + m, + " requested threads: {}+{}/{}\n", + inner.requested_thread_count, + inner.started_thread_count, + inner.max_threads, + ); + if let Some(mapping) = &inner.mapping { + seq_print!( + m, + " free oneway space: {}\n", + mapping.alloc.free_oneway_space() + ); + seq_print!(m, " buffers: {}\n", mapping.alloc.count_buffers()); + } + seq_print!( + m, + " outstanding transactions: {}\n", + inner.outstanding_txns + ); + seq_print!(m, " nodes: {}\n", inner.nodes.iter().count()); + drop(inner); + + { + let mut refs = self.node_refs.lock(); + let (mut count, mut weak, mut strong) = (0, 0, 0); + for r in refs.by_handle.values_mut() { + let node_ref = r.node_ref(); + let (nstrong, nweak) = node_ref.get_count(); + count += 1; + weak += nweak; + strong += nstrong; + } + seq_print!(m, " refs: {count} s {strong} w {weak}\n"); + } + + self.stats.debug_print(" ", m); + + Ok(()) + } + + #[inline(never)] + pub(crate) fn debug_print(&self, m: &SeqFile, ctx: &Context, print_all: bool) -> Result<()> { + seq_print!(m, "proc {}\n", self.pid_in_current_ns()); + seq_print!(m, "context {}\n", &*ctx.name); + + let mut all_threads = KVec::new(); + let mut all_nodes = KVec::new(); + loop { + let inner = self.inner.lock(); + let num_threads = inner.threads.iter().count(); + let num_nodes = inner.nodes.iter().count(); + + if all_threads.capacity() < num_threads || all_nodes.capacity() < num_nodes { + drop(inner); + all_threads.reserve(num_threads, GFP_KERNEL)?; + all_nodes.reserve(num_nodes, GFP_KERNEL)?; + continue; + } + + for thread in inner.threads.values() { + assert!(all_threads.len() < all_threads.capacity()); + let _ = all_threads.push(thread.clone(), GFP_ATOMIC); + } + + for node in inner.nodes.values() { + assert!(all_nodes.len() < all_nodes.capacity()); + let _ = all_nodes.push(node.clone(), GFP_ATOMIC); + } + + break; + } + + for thread in all_threads { + thread.debug_print(m, print_all)?; + } + + let mut inner = self.inner.lock(); + for node in all_nodes { + if print_all || node.has_oneway_transaction(&mut inner) { + node.full_debug_print(m, &mut inner)?; + } + } + drop(inner); + + if print_all { + let mut refs = self.node_refs.lock(); + for r in refs.by_handle.values_mut() { + let node_ref = r.node_ref(); + let dead = node_ref.node.owner.inner.lock().is_dead; + let (strong, weak) = node_ref.get_count(); + let debug_id = node_ref.node.debug_id; + + seq_print!( + m, + " ref {}: desc {} {}node {debug_id} s {strong} w {weak}", + r.debug_id, + r.handle, + if dead { "dead " } else { "" }, + ); + } + } + + let inner = self.inner.lock(); + for work in &inner.work { + work.debug_print(m, " ", " pending transaction ")?; + } + for _death in &inner.delivered_deaths { + seq_print!(m, " has delivered dead binder\n"); + } + if let Some(mapping) = &inner.mapping { + mapping.alloc.debug_print(m)?; + } + drop(inner); + + Ok(()) + } + + /// Attempts to fetch a work item from the process queue. + pub(crate) fn get_work(&self) -> Option<DLArc<dyn DeliverToRead>> { + self.inner.lock().work.pop_front() + } + + /// Attempts to fetch a work item from the process queue. If none is available, it registers the + /// given thread as ready to receive work directly. + /// + /// This must only be called when the thread is not participating in a transaction chain; when + /// it is, work will always be delivered directly to the thread (and not through the process + /// queue). + pub(crate) fn get_work_or_register<'a>( + &'a self, + thread: &'a Arc<Thread>, + ) -> GetWorkOrRegister<'a> { + let mut inner = self.inner.lock(); + // Try to get work from the process queue. + if let Some(work) = inner.work.pop_front() { + return GetWorkOrRegister::Work(work); + } + + // Register the thread as ready. + GetWorkOrRegister::Register(Registration::new(thread, &mut inner)) + } + + fn get_current_thread(self: ArcBorrow<'_, Self>) -> Result<Arc<Thread>> { + let id = { + let current = kernel::current!(); + if !core::ptr::eq(current.group_leader(), &*self.task) { + pr_err!("get_current_thread was called from the wrong process."); + return Err(EINVAL); + } + current.pid() + }; + + { + let inner = self.inner.lock(); + if let Some(thread) = inner.threads.get(&id) { + return Ok(thread.clone()); + } + } + + // Allocate a new `Thread` without holding any locks. + let reservation = RBTreeNodeReservation::new(GFP_KERNEL)?; + let ta: Arc<Thread> = Thread::new(id, self.into())?; + + let mut inner = self.inner.lock(); + match inner.threads.entry(id) { + rbtree::Entry::Vacant(entry) => { + entry.insert(ta.clone(), reservation); + Ok(ta) + } + rbtree::Entry::Occupied(_entry) => { + pr_err!("Cannot create two threads with the same id."); + Err(EINVAL) + } + } + } + + pub(crate) fn push_work(&self, work: DLArc<dyn DeliverToRead>) -> BinderResult { + // If push_work fails, drop the work item outside the lock. + let res = self.inner.lock().push_work(work); + match res { + Ok(()) => Ok(()), + Err((err, work)) => { + drop(work); + Err(err) + } + } + } + + fn set_as_manager( + self: ArcBorrow<'_, Self>, + info: Option<FlatBinderObject>, + thread: &Thread, + ) -> Result { + let (ptr, cookie, flags) = if let Some(obj) = info { + ( + // SAFETY: The object type for this ioctl is implicitly `BINDER_TYPE_BINDER`, so it + // is safe to access the `binder` field. + unsafe { obj.__bindgen_anon_1.binder }, + obj.cookie, + obj.flags, + ) + } else { + (0, 0, 0) + }; + let node_ref = self.get_node(ptr, cookie, flags as _, true, thread)?; + let node = node_ref.node.clone(); + self.ctx.set_manager_node(node_ref)?; + self.inner.lock().is_manager = true; + + // Force the state of the node to prevent the delivery of acquire/increfs. + let mut owner_inner = node.owner.inner.lock(); + node.force_has_count(&mut owner_inner); + Ok(()) + } + + fn get_node_inner( + self: ArcBorrow<'_, Self>, + ptr: u64, + cookie: u64, + flags: u32, + strong: bool, + thread: &Thread, + wrapper: Option<CritIncrWrapper>, + ) -> Result<Result<NodeRef, CouldNotDeliverCriticalIncrement>> { + // Try to find an existing node. + { + let mut inner = self.inner.lock(); + if let Some(node) = inner.get_existing_node(ptr, cookie)? { + return Ok(inner.new_node_ref_with_thread(node, strong, thread, wrapper)); + } + } + + // Allocate the node before reacquiring the lock. + let node = DTRWrap::arc_pin_init(Node::new(ptr, cookie, flags, self.into()))?.into_arc(); + let rbnode = RBTreeNode::new(ptr, node.clone(), GFP_KERNEL)?; + let mut inner = self.inner.lock(); + if let Some(node) = inner.get_existing_node(ptr, cookie)? { + return Ok(inner.new_node_ref_with_thread(node, strong, thread, wrapper)); + } + + inner.nodes.insert(rbnode); + // This can only fail if someone has already pushed the node to a list, but we just created + // it and still hold the lock, so it can't fail right now. + let node_ref = inner + .new_node_ref_with_thread(node, strong, thread, wrapper) + .unwrap(); + + Ok(Ok(node_ref)) + } + + pub(crate) fn get_node( + self: ArcBorrow<'_, Self>, + ptr: u64, + cookie: u64, + flags: u32, + strong: bool, + thread: &Thread, + ) -> Result<NodeRef> { + let mut wrapper = None; + for _ in 0..2 { + match self.get_node_inner(ptr, cookie, flags, strong, thread, wrapper) { + Err(err) => return Err(err), + Ok(Ok(node_ref)) => return Ok(node_ref), + Ok(Err(CouldNotDeliverCriticalIncrement)) => { + wrapper = Some(CritIncrWrapper::new()?); + } + } + } + // We only get a `CouldNotDeliverCriticalIncrement` error if `wrapper` is `None`, so the + // loop should run at most twice. + unreachable!() + } + + pub(crate) fn insert_or_update_handle( + self: ArcBorrow<'_, Process>, + node_ref: NodeRef, + is_mananger: bool, + ) -> Result<u32> { + { + let mut refs = self.node_refs.lock(); + + // Do a lookup before inserting. + if let Some(handle_ref) = refs.by_node.get(&node_ref.node.global_id()) { + let handle = *handle_ref; + let info = refs.by_handle.get_mut(&handle).unwrap(); + info.node_ref().absorb(node_ref); + return Ok(handle); + } + } + + // Reserve memory for tree nodes. + let reserve1 = RBTreeNodeReservation::new(GFP_KERNEL)?; + let reserve2 = RBTreeNodeReservation::new(GFP_KERNEL)?; + let info = UniqueArc::new_uninit(GFP_KERNEL)?; + + let mut refs = self.node_refs.lock(); + + // Do a lookup again as node may have been inserted before the lock was reacquired. + if let Some(handle_ref) = refs.by_node.get(&node_ref.node.global_id()) { + let handle = *handle_ref; + let info = refs.by_handle.get_mut(&handle).unwrap(); + info.node_ref().absorb(node_ref); + return Ok(handle); + } + + // Find id. + let mut target: u32 = if is_mananger { 0 } else { 1 }; + for handle in refs.by_handle.keys() { + if *handle > target { + break; + } + if *handle == target { + target = target.checked_add(1).ok_or(ENOMEM)?; + } + } + + let gid = node_ref.node.global_id(); + let (info_proc, info_node) = { + let info_init = NodeRefInfo::new(node_ref, target, self.into()); + match info.pin_init_with(info_init) { + Ok(info) => ListArc::pair_from_pin_unique(info), + // error is infallible + Err(err) => match err {}, + } + }; + + // Ensure the process is still alive while we insert a new reference. + // + // This releases the lock before inserting the nodes, but since `is_dead` is set as the + // first thing in `deferred_release`, process cleanup will not miss the items inserted into + // `refs` below. + if self.inner.lock().is_dead { + return Err(ESRCH); + } + + // SAFETY: `info_proc` and `info_node` reference the same node, so we are inserting + // `info_node` into the right node's `refs` list. + unsafe { info_proc.node_ref2().node.insert_node_info(info_node) }; + + refs.by_node.insert(reserve1.into_node(gid, target)); + refs.by_handle.insert(reserve2.into_node(target, info_proc)); + Ok(target) + } + + pub(crate) fn get_transaction_node(&self, handle: u32) -> BinderResult<NodeRef> { + // When handle is zero, try to get the context manager. + if handle == 0 { + Ok(self.ctx.get_manager_node(true)?) + } else { + Ok(self.get_node_from_handle(handle, true)?) + } + } + + pub(crate) fn get_node_from_handle(&self, handle: u32, strong: bool) -> Result<NodeRef> { + self.node_refs + .lock() + .by_handle + .get_mut(&handle) + .ok_or(ENOENT)? + .node_ref() + .clone(strong) + } + + pub(crate) fn remove_from_delivered_deaths(&self, death: &DArc<NodeDeath>) { + let mut inner = self.inner.lock(); + // SAFETY: By the invariant on the `delivered_links` field, this is the right linked list. + let removed = unsafe { inner.delivered_deaths.remove(death) }; + drop(inner); + drop(removed); + } + + pub(crate) fn update_ref( + self: ArcBorrow<'_, Process>, + handle: u32, + inc: bool, + strong: bool, + ) -> Result { + if inc && handle == 0 { + if let Ok(node_ref) = self.ctx.get_manager_node(strong) { + if core::ptr::eq(&*self, &*node_ref.node.owner) { + return Err(EINVAL); + } + let _ = self.insert_or_update_handle(node_ref, true); + return Ok(()); + } + } + + // To preserve original binder behaviour, we only fail requests where the manager tries to + // increment references on itself. + let mut refs = self.node_refs.lock(); + if let Some(info) = refs.by_handle.get_mut(&handle) { + if info.node_ref().update(inc, strong) { + // Clean up death if there is one attached to this node reference. + if let Some(death) = info.death().take() { + death.set_cleared(true); + self.remove_from_delivered_deaths(&death); + } + + // Remove reference from process tables, and from the node's `refs` list. + + // SAFETY: We are removing the `NodeRefInfo` from the right node. + unsafe { info.node_ref2().node.remove_node_info(info) }; + + let id = info.node_ref().node.global_id(); + refs.by_handle.remove(&handle); + refs.by_node.remove(&id); + } + } else { + // All refs are cleared in process exit, so this warning is expected in that case. + if !self.inner.lock().is_dead { + pr_warn!("{}: no such ref {handle}\n", self.pid_in_current_ns()); + } + } + Ok(()) + } + + /// Decrements the refcount of the given node, if one exists. + pub(crate) fn update_node(&self, ptr: u64, cookie: u64, strong: bool) { + let mut inner = self.inner.lock(); + if let Ok(Some(node)) = inner.get_existing_node(ptr, cookie) { + inner.update_node_refcount(&node, false, strong, 1, None); + } + } + + pub(crate) fn inc_ref_done(&self, reader: &mut UserSliceReader, strong: bool) -> Result { + let ptr = reader.read::<u64>()?; + let cookie = reader.read::<u64>()?; + let mut inner = self.inner.lock(); + if let Ok(Some(node)) = inner.get_existing_node(ptr, cookie) { + if let Some(node) = node.inc_ref_done_locked(strong, &mut inner) { + // This only fails if the process is dead. + let _ = inner.push_work(node); + } + } + Ok(()) + } + + pub(crate) fn buffer_alloc( + self: &Arc<Self>, + debug_id: usize, + size: usize, + is_oneway: bool, + from_pid: i32, + ) -> BinderResult<NewAllocation> { + use kernel::page::PAGE_SIZE; + + let mut reserve_new_args = ReserveNewArgs { + debug_id, + size, + is_oneway, + pid: from_pid, + ..ReserveNewArgs::default() + }; + + let (new_alloc, addr) = loop { + let mut inner = self.inner.lock(); + let mapping = inner.mapping.as_mut().ok_or_else(BinderError::new_dead)?; + let alloc_request = match mapping.alloc.reserve_new(reserve_new_args)? { + ReserveNew::Success(new_alloc) => break (new_alloc, mapping.address), + ReserveNew::NeedAlloc(request) => request, + }; + drop(inner); + // We need to allocate memory and then call `reserve_new` again. + reserve_new_args = alloc_request.make_alloc()?; + }; + + let res = Allocation::new( + self.clone(), + debug_id, + new_alloc.offset, + size, + addr + new_alloc.offset, + new_alloc.oneway_spam_detected, + ); + + // This allocation will be marked as in use until the `Allocation` is used to free it. + // + // This method can't be called while holding a lock, so we release the lock first. It's + // okay for several threads to use the method on the same index at the same time. In that + // case, one of the calls will allocate the given page (if missing), and the other call + // will wait for the other call to finish allocating the page. + // + // We will not call `stop_using_range` in parallel with this on the same page, because the + // allocation can only be removed via the destructor of the `Allocation` object that we + // currently own. + match self.pages.use_range( + new_alloc.offset / PAGE_SIZE, + (new_alloc.offset + size).div_ceil(PAGE_SIZE), + ) { + Ok(()) => {} + Err(err) => { + pr_warn!("use_range failure {:?}", err); + return Err(err.into()); + } + } + + Ok(NewAllocation(res)) + } + + pub(crate) fn buffer_get(self: &Arc<Self>, ptr: usize) -> Option<Allocation> { + let mut inner = self.inner.lock(); + let mapping = inner.mapping.as_mut()?; + let offset = ptr.checked_sub(mapping.address)?; + let (size, debug_id, odata) = mapping.alloc.reserve_existing(offset).ok()?; + let mut alloc = Allocation::new(self.clone(), debug_id, offset, size, ptr, false); + if let Some(data) = odata { + alloc.set_info(data); + } + Some(alloc) + } + + pub(crate) fn buffer_raw_free(&self, ptr: usize) { + let mut inner = self.inner.lock(); + if let Some(ref mut mapping) = &mut inner.mapping { + let offset = match ptr.checked_sub(mapping.address) { + Some(offset) => offset, + None => return, + }; + + let freed_range = match mapping.alloc.reservation_abort(offset) { + Ok(freed_range) => freed_range, + Err(_) => { + pr_warn!( + "Pointer {:x} failed to free, base = {:x}\n", + ptr, + mapping.address + ); + return; + } + }; + + // No more allocations in this range. Mark them as not in use. + // + // Must be done before we release the lock so that `use_range` is not used on these + // indices until `stop_using_range` returns. + self.pages + .stop_using_range(freed_range.start_page_idx, freed_range.end_page_idx); + } + } + + pub(crate) fn buffer_make_freeable(&self, offset: usize, mut data: Option<AllocationInfo>) { + let mut inner = self.inner.lock(); + if let Some(ref mut mapping) = &mut inner.mapping { + if mapping.alloc.reservation_commit(offset, &mut data).is_err() { + pr_warn!("Offset {} failed to be marked freeable\n", offset); + } + } + } + + fn create_mapping(&self, vma: &mm::virt::VmaNew) -> Result { + use kernel::page::PAGE_SIZE; + let size = usize::min(vma.end() - vma.start(), bindings::SZ_4M as usize); + let mapping = Mapping::new(vma.start(), size); + let page_count = self.pages.register_with_vma(vma)?; + if page_count * PAGE_SIZE != size { + return Err(EINVAL); + } + + // Save range allocator for later. + self.inner.lock().mapping = Some(mapping); + + Ok(()) + } + + fn version(&self, data: UserSlice) -> Result { + data.writer().write(&BinderVersion::current()) + } + + pub(crate) fn register_thread(&self) -> bool { + self.inner.lock().register_thread() + } + + fn remove_thread(&self, thread: Arc<Thread>) { + self.inner.lock().threads.remove(&thread.id); + thread.release(); + } + + fn set_max_threads(&self, max: u32) { + self.inner.lock().max_threads = max; + } + + fn set_oneway_spam_detection_enabled(&self, enabled: u32) { + self.inner.lock().oneway_spam_detection_enabled = enabled != 0; + } + + pub(crate) fn is_oneway_spam_detection_enabled(&self) -> bool { + self.inner.lock().oneway_spam_detection_enabled + } + + fn get_node_debug_info(&self, data: UserSlice) -> Result { + let (mut reader, mut writer) = data.reader_writer(); + + // Read the starting point. + let ptr = reader.read::<BinderNodeDebugInfo>()?.ptr; + let mut out = BinderNodeDebugInfo::default(); + + { + let inner = self.inner.lock(); + for (node_ptr, node) in &inner.nodes { + if *node_ptr > ptr { + node.populate_debug_info(&mut out, &inner); + break; + } + } + } + + writer.write(&out) + } + + fn get_node_info_from_ref(&self, data: UserSlice) -> Result { + let (mut reader, mut writer) = data.reader_writer(); + let mut out = reader.read::<BinderNodeInfoForRef>()?; + + if out.strong_count != 0 + || out.weak_count != 0 + || out.reserved1 != 0 + || out.reserved2 != 0 + || out.reserved3 != 0 + { + return Err(EINVAL); + } + + // Only the context manager is allowed to use this ioctl. + if !self.inner.lock().is_manager { + return Err(EPERM); + } + + { + let mut node_refs = self.node_refs.lock(); + let node_info = node_refs.by_handle.get_mut(&out.handle).ok_or(ENOENT)?; + let node_ref = node_info.node_ref(); + let owner_inner = node_ref.node.owner.inner.lock(); + node_ref.node.populate_counts(&mut out, &owner_inner); + } + + // Write the result back. + writer.write(&out) + } + + pub(crate) fn needs_thread(&self) -> bool { + let mut inner = self.inner.lock(); + let ret = inner.requested_thread_count == 0 + && inner.ready_threads.is_empty() + && inner.started_thread_count < inner.max_threads; + if ret { + inner.requested_thread_count += 1 + } + ret + } + + pub(crate) fn request_death( + self: &Arc<Self>, + reader: &mut UserSliceReader, + thread: &Thread, + ) -> Result { + let handle: u32 = reader.read()?; + let cookie: u64 = reader.read()?; + + // Queue BR_ERROR if we can't allocate memory for the death notification. + let death = UniqueArc::new_uninit(GFP_KERNEL).inspect_err(|_| { + thread.push_return_work(BR_ERROR); + })?; + let mut refs = self.node_refs.lock(); + let Some(info) = refs.by_handle.get_mut(&handle) else { + pr_warn!("BC_REQUEST_DEATH_NOTIFICATION invalid ref {handle}\n"); + return Ok(()); + }; + + // Nothing to do if there is already a death notification request for this handle. + if info.death().is_some() { + pr_warn!("BC_REQUEST_DEATH_NOTIFICATION death notification already set\n"); + return Ok(()); + } + + let death = { + let death_init = NodeDeath::new(info.node_ref().node.clone(), self.clone(), cookie); + match death.pin_init_with(death_init) { + Ok(death) => death, + // error is infallible + Err(err) => match err {}, + } + }; + + // Register the death notification. + { + let owner = info.node_ref2().node.owner.clone(); + let mut owner_inner = owner.inner.lock(); + if owner_inner.is_dead { + let death = Arc::from(death); + *info.death() = Some(death.clone()); + drop(owner_inner); + death.set_dead(); + } else { + let death = ListArc::from(death); + *info.death() = Some(death.clone_arc()); + info.node_ref().node.add_death(death, &mut owner_inner); + } + } + Ok(()) + } + + pub(crate) fn clear_death(&self, reader: &mut UserSliceReader, thread: &Thread) -> Result { + let handle: u32 = reader.read()?; + let cookie: u64 = reader.read()?; + + let mut refs = self.node_refs.lock(); + let Some(info) = refs.by_handle.get_mut(&handle) else { + pr_warn!("BC_CLEAR_DEATH_NOTIFICATION invalid ref {handle}\n"); + return Ok(()); + }; + + let Some(death) = info.death().take() else { + pr_warn!("BC_CLEAR_DEATH_NOTIFICATION death notification not active\n"); + return Ok(()); + }; + if death.cookie != cookie { + *info.death() = Some(death); + pr_warn!("BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch\n"); + return Ok(()); + } + + // Update state and determine if we need to queue a work item. We only need to do it when + // the node is not dead or if the user already completed the death notification. + if death.set_cleared(false) { + if let Some(death) = ListArc::try_from_arc_or_drop(death) { + let _ = thread.push_work_if_looper(death); + } + } + + Ok(()) + } + + pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) { + if let Some(death) = self.inner.lock().pull_delivered_death(cookie) { + death.set_notification_done(thread); + } + } + + /// Locks the spinlock and move the `nodes` rbtree out. + /// + /// This allows you to iterate through `nodes` while also allowing you to give other parts of + /// the codebase exclusive access to `ProcessInner`. + pub(crate) fn lock_with_nodes(&self) -> WithNodes<'_> { + let mut inner = self.inner.lock(); + WithNodes { + nodes: take(&mut inner.nodes), + inner, + } + } + + fn deferred_flush(&self) { + let inner = self.inner.lock(); + for thread in inner.threads.values() { + thread.exit_looper(); + } + } + + fn deferred_release(self: Arc<Self>) { + let is_manager = { + let mut inner = self.inner.lock(); + inner.is_dead = true; + inner.is_frozen = false; + inner.sync_recv = false; + inner.async_recv = false; + inner.is_manager + }; + + if is_manager { + self.ctx.unset_manager_node(); + } + + self.ctx.deregister_process(&self); + + let binderfs_file = self.inner.lock().binderfs_file.take(); + drop(binderfs_file); + + // Release threads. + let threads = { + let mut inner = self.inner.lock(); + let threads = take(&mut inner.threads); + let ready = take(&mut inner.ready_threads); + drop(inner); + drop(ready); + + for thread in threads.values() { + thread.release(); + } + threads + }; + + // Release nodes. + { + while let Some(node) = { + let mut lock = self.inner.lock(); + lock.nodes.cursor_front().map(|c| c.remove_current().1) + } { + node.to_key_value().1.release(); + } + } + + // Clean up death listeners and remove nodes from external node info lists. + for info in self.node_refs.lock().by_handle.values_mut() { + // SAFETY: We are removing the `NodeRefInfo` from the right node. + unsafe { info.node_ref2().node.remove_node_info(info) }; + + // Remove all death notifications from the nodes (that belong to a different process). + let death = if let Some(existing) = info.death().take() { + existing + } else { + continue; + }; + death.set_cleared(false); + } + + // Clean up freeze listeners. + let freeze_listeners = take(&mut self.node_refs.lock().freeze_listeners); + for listener in freeze_listeners.values() { + listener.on_process_exit(&self); + } + drop(freeze_listeners); + + // Release refs on foreign nodes. + { + let mut refs = self.node_refs.lock(); + let by_handle = take(&mut refs.by_handle); + let by_node = take(&mut refs.by_node); + drop(refs); + drop(by_node); + drop(by_handle); + } + + // Cancel all pending work items. + while let Some(work) = self.get_work() { + work.into_arc().cancel(); + } + + let delivered_deaths = take(&mut self.inner.lock().delivered_deaths); + drop(delivered_deaths); + + // Free any resources kept alive by allocated buffers. + let omapping = self.inner.lock().mapping.take(); + if let Some(mut mapping) = omapping { + let address = mapping.address; + mapping + .alloc + .take_for_each(|offset, size, debug_id, odata| { + let ptr = offset + address; + pr_warn!( + "{}: removing orphan mapping {offset}:{size}\n", + self.pid_in_current_ns() + ); + let mut alloc = + Allocation::new(self.clone(), debug_id, offset, size, ptr, false); + if let Some(data) = odata { + alloc.set_info(data); + } + drop(alloc) + }); + } + + // calls to synchronize_rcu() in thread drop will happen here + drop(threads); + } + + pub(crate) fn drop_outstanding_txn(&self) { + let wake = { + let mut inner = self.inner.lock(); + if inner.outstanding_txns == 0 { + pr_err!("outstanding_txns underflow"); + return; + } + inner.outstanding_txns -= 1; + inner.is_frozen && inner.outstanding_txns == 0 + }; + + if wake { + self.freeze_wait.notify_all(); + } + } + + pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result { + if info.enable == 0 { + let msgs = self.prepare_freeze_messages()?; + let mut inner = self.inner.lock(); + inner.sync_recv = false; + inner.async_recv = false; + inner.is_frozen = false; + drop(inner); + msgs.send_messages(); + return Ok(()); + } + + let mut inner = self.inner.lock(); + inner.sync_recv = false; + inner.async_recv = false; + inner.is_frozen = true; + + if info.timeout_ms > 0 { + let mut jiffies = kernel::time::msecs_to_jiffies(info.timeout_ms); + while jiffies > 0 { + if inner.outstanding_txns == 0 { + break; + } + + match self + .freeze_wait + .wait_interruptible_timeout(&mut inner, jiffies) + { + CondVarTimeoutResult::Signal { .. } => { + inner.is_frozen = false; + return Err(ERESTARTSYS); + } + CondVarTimeoutResult::Woken { jiffies: remaining } => { + jiffies = remaining; + } + CondVarTimeoutResult::Timeout => { + jiffies = 0; + } + } + } + } + + if inner.txns_pending_locked() { + inner.is_frozen = false; + Err(EAGAIN) + } else { + drop(inner); + match self.prepare_freeze_messages() { + Ok(batch) => { + batch.send_messages(); + Ok(()) + } + Err(kernel::alloc::AllocError) => { + self.inner.lock().is_frozen = false; + Err(ENOMEM) + } + } + } + } +} + +fn get_frozen_status(data: UserSlice) -> Result { + let (mut reader, mut writer) = data.reader_writer(); + + let mut info = reader.read::<BinderFrozenStatusInfo>()?; + info.sync_recv = 0; + info.async_recv = 0; + let mut found = false; + + for ctx in crate::context::get_all_contexts()? { + ctx.for_each_proc(|proc| { + if proc.task.pid() == info.pid as _ { + found = true; + let inner = proc.inner.lock(); + let txns_pending = inner.txns_pending_locked(); + info.async_recv |= inner.async_recv as u32; + info.sync_recv |= inner.sync_recv as u32; + info.sync_recv |= (txns_pending as u32) << 1; + } + }); + } + + if found { + writer.write(&info)?; + Ok(()) + } else { + Err(EINVAL) + } +} + +fn ioctl_freeze(reader: &mut UserSliceReader) -> Result { + let info = reader.read::<BinderFreezeInfo>()?; + + // Very unlikely for there to be more than 3, since a process normally uses at most binder and + // hwbinder. + let mut procs = KVec::with_capacity(3, GFP_KERNEL)?; + + let ctxs = crate::context::get_all_contexts()?; + for ctx in ctxs { + for proc in ctx.get_procs_with_pid(info.pid as i32)? { + procs.push(proc, GFP_KERNEL)?; + } + } + + for proc in procs { + proc.ioctl_freeze(&info)?; + } + Ok(()) +} + +/// The ioctl handler. +impl Process { + /// Ioctls that are write-only from the perspective of userspace. + /// + /// The kernel will only read from the pointer that userspace provided to us. + fn ioctl_write_only( + this: ArcBorrow<'_, Process>, + _file: &File, + cmd: u32, + reader: &mut UserSliceReader, + ) -> Result { + let thread = this.get_current_thread()?; + match cmd { + uapi::BINDER_SET_MAX_THREADS => this.set_max_threads(reader.read()?), + uapi::BINDER_THREAD_EXIT => this.remove_thread(thread), + uapi::BINDER_SET_CONTEXT_MGR => this.set_as_manager(None, &thread)?, + uapi::BINDER_SET_CONTEXT_MGR_EXT => { + this.set_as_manager(Some(reader.read()?), &thread)? + } + uapi::BINDER_ENABLE_ONEWAY_SPAM_DETECTION => { + this.set_oneway_spam_detection_enabled(reader.read()?) + } + uapi::BINDER_FREEZE => ioctl_freeze(reader)?, + _ => return Err(EINVAL), + } + Ok(()) + } + + /// Ioctls that are read/write from the perspective of userspace. + /// + /// The kernel will both read from and write to the pointer that userspace provided to us. + fn ioctl_write_read( + this: ArcBorrow<'_, Process>, + file: &File, + cmd: u32, + data: UserSlice, + ) -> Result { + let thread = this.get_current_thread()?; + let blocking = (file.flags() & file::flags::O_NONBLOCK) == 0; + match cmd { + uapi::BINDER_WRITE_READ => thread.write_read(data, blocking)?, + uapi::BINDER_GET_NODE_DEBUG_INFO => this.get_node_debug_info(data)?, + uapi::BINDER_GET_NODE_INFO_FOR_REF => this.get_node_info_from_ref(data)?, + uapi::BINDER_VERSION => this.version(data)?, + uapi::BINDER_GET_FROZEN_INFO => get_frozen_status(data)?, + uapi::BINDER_GET_EXTENDED_ERROR => thread.get_extended_error(data)?, + _ => return Err(EINVAL), + } + Ok(()) + } +} + +/// The file operations supported by `Process`. +impl Process { + pub(crate) fn open(ctx: ArcBorrow<'_, Context>, file: &File) -> Result<Arc<Process>> { + Self::new(ctx.into(), ARef::from(file.cred())) + } + + pub(crate) fn release(this: Arc<Process>, _file: &File) { + let binderfs_file; + let should_schedule; + { + let mut inner = this.inner.lock(); + should_schedule = inner.defer_work == 0; + inner.defer_work |= PROC_DEFER_RELEASE; + binderfs_file = inner.binderfs_file.take(); + } + + if should_schedule { + // Ignore failures to schedule to the workqueue. Those just mean that we're already + // scheduled for execution. + let _ = workqueue::system().enqueue(this); + } + + drop(binderfs_file); + } + + pub(crate) fn flush(this: ArcBorrow<'_, Process>) -> Result { + let should_schedule; + { + let mut inner = this.inner.lock(); + should_schedule = inner.defer_work == 0; + inner.defer_work |= PROC_DEFER_FLUSH; + } + + if should_schedule { + // Ignore failures to schedule to the workqueue. Those just mean that we're already + // scheduled for execution. + let _ = workqueue::system().enqueue(Arc::from(this)); + } + Ok(()) + } + + pub(crate) fn ioctl(this: ArcBorrow<'_, Process>, file: &File, cmd: u32, arg: usize) -> Result { + use kernel::ioctl::{_IOC_DIR, _IOC_SIZE}; + use kernel::uapi::{_IOC_READ, _IOC_WRITE}; + + crate::trace::trace_ioctl(cmd, arg); + + let user_slice = UserSlice::new(UserPtr::from_addr(arg), _IOC_SIZE(cmd)); + + const _IOC_READ_WRITE: u32 = _IOC_READ | _IOC_WRITE; + + match _IOC_DIR(cmd) { + _IOC_WRITE => Self::ioctl_write_only(this, file, cmd, &mut user_slice.reader()), + _IOC_READ_WRITE => Self::ioctl_write_read(this, file, cmd, user_slice), + _ => Err(EINVAL), + } + } + + pub(crate) fn compat_ioctl( + this: ArcBorrow<'_, Process>, + file: &File, + cmd: u32, + arg: usize, + ) -> Result { + Self::ioctl(this, file, cmd, arg) + } + + pub(crate) fn mmap( + this: ArcBorrow<'_, Process>, + _file: &File, + vma: &mm::virt::VmaNew, + ) -> Result { + // We don't allow mmap to be used in a different process. + if !core::ptr::eq(kernel::current!().group_leader(), &*this.task) { + return Err(EINVAL); + } + if vma.start() == 0 { + return Err(EINVAL); + } + + vma.try_clear_maywrite().map_err(|_| EPERM)?; + vma.set_dontcopy(); + vma.set_mixedmap(); + + // TODO: Set ops. We need to learn when the user unmaps so that we can stop using it. + this.create_mapping(vma) + } + + pub(crate) fn poll( + this: ArcBorrow<'_, Process>, + file: &File, + table: PollTable<'_>, + ) -> Result<u32> { + let thread = this.get_current_thread()?; + let (from_proc, mut mask) = thread.poll(file, table); + if mask == 0 && from_proc && !this.inner.lock().work.is_empty() { + mask |= bindings::POLLIN; + } + Ok(mask) + } +} + +/// Represents that a thread has registered with the `ready_threads` list of its process. +/// +/// The destructor of this type will unregister the thread from the list of ready threads. +pub(crate) struct Registration<'a> { + thread: &'a Arc<Thread>, +} + +impl<'a> Registration<'a> { + fn new(thread: &'a Arc<Thread>, guard: &mut Guard<'_, ProcessInner, SpinLockBackend>) -> Self { + assert!(core::ptr::eq(&thread.process.inner, guard.lock_ref())); + // INVARIANT: We are pushing this thread to the right `ready_threads` list. + if let Ok(list_arc) = ListArc::try_from_arc(thread.clone()) { + guard.ready_threads.push_front(list_arc); + } else { + // It is an error to hit this branch, and it should not be reachable. We try to do + // something reasonable when the failure path happens. Most likely, the thread in + // question will sleep forever. + pr_err!("Same thread registered with `ready_threads` twice."); + } + Self { thread } + } +} + +impl Drop for Registration<'_> { + fn drop(&mut self) { + let mut inner = self.thread.process.inner.lock(); + // SAFETY: The thread has the invariant that we never push it to any other linked list than + // the `ready_threads` list of its parent process. Therefore, the thread is either in that + // list, or in no list. + unsafe { inner.ready_threads.remove(self.thread) }; + } +} + +pub(crate) struct WithNodes<'a> { + pub(crate) inner: Guard<'a, ProcessInner, SpinLockBackend>, + pub(crate) nodes: RBTree<u64, DArc<Node>>, +} + +impl Drop for WithNodes<'_> { + fn drop(&mut self) { + core::mem::swap(&mut self.nodes, &mut self.inner.nodes); + if self.nodes.iter().next().is_some() { + pr_err!("nodes array was modified while using lock_with_nodes\n"); + } + } +} + +pub(crate) enum GetWorkOrRegister<'a> { + Work(DLArc<dyn DeliverToRead>), + Register(Registration<'a>), +} diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs new file mode 100644 index 000000000000..07e1dec2ce63 --- /dev/null +++ b/drivers/android/binder/range_alloc/array.rs @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{ + page::{PAGE_MASK, PAGE_SIZE}, + prelude::*, + seq_file::SeqFile, + seq_print, + task::Pid, +}; + +use crate::range_alloc::{DescriptorState, FreedRange, Range}; + +/// Keeps track of allocations in a process' mmap. +/// +/// Each process has an mmap where the data for incoming transactions will be placed. This struct +/// keeps track of allocations made in the mmap. For each allocation, we store a descriptor that +/// has metadata related to the allocation. We also keep track of available free space. +pub(super) struct ArrayRangeAllocator<T> { + /// This stores all ranges that are allocated. Unlike the tree based allocator, we do *not* + /// store the free ranges. + /// + /// Sorted by offset. + pub(super) ranges: KVec<Range<T>>, + size: usize, + free_oneway_space: usize, +} + +struct FindEmptyRes { + /// Which index in `ranges` should we insert the new range at? + /// + /// Inserting the new range at this index keeps `ranges` sorted. + insert_at_idx: usize, + /// Which offset should we insert the new range at? + insert_at_offset: usize, +} + +impl<T> ArrayRangeAllocator<T> { + pub(crate) fn new(size: usize, alloc: EmptyArrayAlloc<T>) -> Self { + Self { + ranges: alloc.ranges, + size, + free_oneway_space: size / 2, + } + } + + pub(crate) fn free_oneway_space(&self) -> usize { + self.free_oneway_space + } + + pub(crate) fn count_buffers(&self) -> usize { + self.ranges.len() + } + + pub(crate) fn total_size(&self) -> usize { + self.size + } + + pub(crate) fn is_full(&self) -> bool { + self.ranges.len() == self.ranges.capacity() + } + + pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> { + for range in &self.ranges { + seq_print!( + m, + " buffer {}: {} size {} pid {} oneway {}", + 0, + range.offset, + range.size, + range.state.pid(), + range.state.is_oneway(), + ); + if let DescriptorState::Reserved(_) = range.state { + seq_print!(m, " reserved\n"); + } else { + seq_print!(m, " allocated\n"); + } + } + Ok(()) + } + + /// Find somewhere to put a new range. + /// + /// Unlike the tree implementation, we do not bother to find the smallest gap. The idea is that + /// fragmentation isn't a big issue when we don't have many ranges. + /// + /// Returns the index that the new range should have in `self.ranges` after insertion. + fn find_empty_range(&self, size: usize) -> Option<FindEmptyRes> { + let after_last_range = self.ranges.last().map(Range::endpoint).unwrap_or(0); + + if size <= self.total_size() - after_last_range { + // We can put the range at the end, so just do that. + Some(FindEmptyRes { + insert_at_idx: self.ranges.len(), + insert_at_offset: after_last_range, + }) + } else { + let mut end_of_prev = 0; + for (i, range) in self.ranges.iter().enumerate() { + // Does it fit before the i'th range? + if size <= range.offset - end_of_prev { + return Some(FindEmptyRes { + insert_at_idx: i, + insert_at_offset: end_of_prev, + }); + } + end_of_prev = range.endpoint(); + } + None + } + } + + pub(crate) fn reserve_new( + &mut self, + debug_id: usize, + size: usize, + is_oneway: bool, + pid: Pid, + ) -> Result<usize> { + // Compute new value of free_oneway_space, which is set only on success. + let new_oneway_space = if is_oneway { + match self.free_oneway_space.checked_sub(size) { + Some(new_oneway_space) => new_oneway_space, + None => return Err(ENOSPC), + } + } else { + self.free_oneway_space + }; + + let FindEmptyRes { + insert_at_idx, + insert_at_offset, + } = self.find_empty_range(size).ok_or(ENOSPC)?; + self.free_oneway_space = new_oneway_space; + + let new_range = Range { + offset: insert_at_offset, + size, + state: DescriptorState::new(is_oneway, debug_id, pid), + }; + // Insert the value at the given index to keep the array sorted. + self.ranges + .insert_within_capacity(insert_at_idx, new_range) + .ok() + .unwrap(); + + Ok(insert_at_offset) + } + + pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> { + // This could use a binary search, but linear scans are usually faster for small arrays. + let i = self + .ranges + .iter() + .position(|range| range.offset == offset) + .ok_or(EINVAL)?; + let range = &self.ranges[i]; + + if let DescriptorState::Allocated(_) = range.state { + return Err(EPERM); + } + + let size = range.size; + let offset = range.offset; + + if range.state.is_oneway() { + self.free_oneway_space += size; + } + + // This computes the range of pages that are no longer used by *any* allocated range. The + // caller will mark them as unused, which means that they can be freed if the system comes + // under memory pressure. + let mut freed_range = FreedRange::interior_pages(offset, size); + #[expect(clippy::collapsible_if)] // reads better like this + if offset % PAGE_SIZE != 0 { + if i == 0 || self.ranges[i - 1].endpoint() <= (offset & PAGE_MASK) { + freed_range.start_page_idx -= 1; + } + } + if range.endpoint() % PAGE_SIZE != 0 { + let page_after = (range.endpoint() & PAGE_MASK) + PAGE_SIZE; + if i + 1 == self.ranges.len() || page_after <= self.ranges[i + 1].offset { + freed_range.end_page_idx += 1; + } + } + + self.ranges.remove(i)?; + Ok(freed_range) + } + + pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result { + // This could use a binary search, but linear scans are usually faster for small arrays. + let range = self + .ranges + .iter_mut() + .find(|range| range.offset == offset) + .ok_or(ENOENT)?; + + let DescriptorState::Reserved(reservation) = &range.state else { + return Err(ENOENT); + }; + + range.state = DescriptorState::Allocated(reservation.clone().allocate(data.take())); + Ok(()) + } + + pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> { + // This could use a binary search, but linear scans are usually faster for small arrays. + let range = self + .ranges + .iter_mut() + .find(|range| range.offset == offset) + .ok_or(ENOENT)?; + + let DescriptorState::Allocated(allocation) = &mut range.state else { + return Err(ENOENT); + }; + + let data = allocation.take(); + let debug_id = allocation.reservation.debug_id; + range.state = DescriptorState::Reserved(allocation.reservation.clone()); + Ok((range.size, debug_id, data)) + } + + pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) { + for range in self.ranges.iter_mut() { + if let DescriptorState::Allocated(allocation) = &mut range.state { + callback( + range.offset, + range.size, + allocation.reservation.debug_id, + allocation.data.take(), + ); + } + } + } +} + +pub(crate) struct EmptyArrayAlloc<T> { + ranges: KVec<Range<T>>, +} + +impl<T> EmptyArrayAlloc<T> { + pub(crate) fn try_new(capacity: usize) -> Result<Self> { + Ok(Self { + ranges: KVec::with_capacity(capacity, GFP_KERNEL)?, + }) + } +} diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs new file mode 100644 index 000000000000..2301e2bc1a1f --- /dev/null +++ b/drivers/android/binder/range_alloc/mod.rs @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{page::PAGE_SIZE, prelude::*, seq_file::SeqFile, task::Pid}; + +mod tree; +use self::tree::{FromArrayAllocs, ReserveNewTreeAlloc, TreeRangeAllocator}; + +mod array; +use self::array::{ArrayRangeAllocator, EmptyArrayAlloc}; + +enum DescriptorState<T> { + Reserved(Reservation), + Allocated(Allocation<T>), +} + +impl<T> DescriptorState<T> { + fn new(is_oneway: bool, debug_id: usize, pid: Pid) -> Self { + DescriptorState::Reserved(Reservation { + debug_id, + is_oneway, + pid, + }) + } + + fn pid(&self) -> Pid { + match self { + DescriptorState::Reserved(inner) => inner.pid, + DescriptorState::Allocated(inner) => inner.reservation.pid, + } + } + + fn is_oneway(&self) -> bool { + match self { + DescriptorState::Reserved(inner) => inner.is_oneway, + DescriptorState::Allocated(inner) => inner.reservation.is_oneway, + } + } +} + +#[derive(Clone)] +struct Reservation { + debug_id: usize, + is_oneway: bool, + pid: Pid, +} + +impl Reservation { + fn allocate<T>(self, data: Option<T>) -> Allocation<T> { + Allocation { + data, + reservation: self, + } + } +} + +struct Allocation<T> { + reservation: Reservation, + data: Option<T>, +} + +impl<T> Allocation<T> { + fn deallocate(self) -> (Reservation, Option<T>) { + (self.reservation, self.data) + } + + fn debug_id(&self) -> usize { + self.reservation.debug_id + } + + fn take(&mut self) -> Option<T> { + self.data.take() + } +} + +/// The array implementation must switch to the tree if it wants to go beyond this number of +/// ranges. +const TREE_THRESHOLD: usize = 8; + +/// Represents a range of pages that have just become completely free. +#[derive(Copy, Clone)] +pub(crate) struct FreedRange { + pub(crate) start_page_idx: usize, + pub(crate) end_page_idx: usize, +} + +impl FreedRange { + fn interior_pages(offset: usize, size: usize) -> FreedRange { + FreedRange { + // Divide round up + start_page_idx: offset.div_ceil(PAGE_SIZE), + // Divide round down + end_page_idx: (offset + size) / PAGE_SIZE, + } + } +} + +struct Range<T> { + offset: usize, + size: usize, + state: DescriptorState<T>, +} + +impl<T> Range<T> { + fn endpoint(&self) -> usize { + self.offset + self.size + } +} + +pub(crate) struct RangeAllocator<T> { + inner: Impl<T>, +} + +enum Impl<T> { + Empty(usize), + Array(ArrayRangeAllocator<T>), + Tree(TreeRangeAllocator<T>), +} + +impl<T> RangeAllocator<T> { + pub(crate) fn new(size: usize) -> Self { + Self { + inner: Impl::Empty(size), + } + } + + pub(crate) fn free_oneway_space(&self) -> usize { + match &self.inner { + Impl::Empty(size) => size / 2, + Impl::Array(array) => array.free_oneway_space(), + Impl::Tree(tree) => tree.free_oneway_space(), + } + } + + pub(crate) fn count_buffers(&self) -> usize { + match &self.inner { + Impl::Empty(_size) => 0, + Impl::Array(array) => array.count_buffers(), + Impl::Tree(tree) => tree.count_buffers(), + } + } + + pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> { + match &self.inner { + Impl::Empty(_size) => Ok(()), + Impl::Array(array) => array.debug_print(m), + Impl::Tree(tree) => tree.debug_print(m), + } + } + + /// Try to reserve a new buffer, using the provided allocation if necessary. + pub(crate) fn reserve_new(&mut self, mut args: ReserveNewArgs<T>) -> Result<ReserveNew<T>> { + match &mut self.inner { + Impl::Empty(size) => { + let empty_array = match args.empty_array_alloc.take() { + Some(empty_array) => ArrayRangeAllocator::new(*size, empty_array), + None => { + return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc { + args, + need_empty_array_alloc: true, + need_new_tree_alloc: false, + need_tree_alloc: false, + })) + } + }; + + self.inner = Impl::Array(empty_array); + self.reserve_new(args) + } + Impl::Array(array) if array.is_full() => { + let allocs = match args.new_tree_alloc { + Some(ref mut allocs) => allocs, + None => { + return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc { + args, + need_empty_array_alloc: false, + need_new_tree_alloc: true, + need_tree_alloc: true, + })) + } + }; + + let new_tree = + TreeRangeAllocator::from_array(array.total_size(), &mut array.ranges, allocs); + + self.inner = Impl::Tree(new_tree); + self.reserve_new(args) + } + Impl::Array(array) => { + let offset = + array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?; + Ok(ReserveNew::Success(ReserveNewSuccess { + offset, + oneway_spam_detected: false, + _empty_array_alloc: args.empty_array_alloc, + _new_tree_alloc: args.new_tree_alloc, + _tree_alloc: args.tree_alloc, + })) + } + Impl::Tree(tree) => { + let alloc = match args.tree_alloc { + Some(alloc) => alloc, + None => { + return Ok(ReserveNew::NeedAlloc(ReserveNewNeedAlloc { + args, + need_empty_array_alloc: false, + need_new_tree_alloc: false, + need_tree_alloc: true, + })); + } + }; + let (offset, oneway_spam_detected) = + tree.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid, alloc)?; + Ok(ReserveNew::Success(ReserveNewSuccess { + offset, + oneway_spam_detected, + _empty_array_alloc: args.empty_array_alloc, + _new_tree_alloc: args.new_tree_alloc, + _tree_alloc: None, + })) + } + } + } + + /// Deletes the allocations at `offset`. + pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> { + match &mut self.inner { + Impl::Empty(_size) => Err(EINVAL), + Impl::Array(array) => array.reservation_abort(offset), + Impl::Tree(tree) => { + let freed_range = tree.reservation_abort(offset)?; + if tree.is_empty() { + self.inner = Impl::Empty(tree.total_size()); + } + Ok(freed_range) + } + } + } + + /// Called when an allocation is no longer in use by the kernel. + /// + /// The value in `data` will be stored, if any. A mutable reference is used to avoid dropping + /// the `T` when an error is returned. + pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result { + match &mut self.inner { + Impl::Empty(_size) => Err(EINVAL), + Impl::Array(array) => array.reservation_commit(offset, data), + Impl::Tree(tree) => tree.reservation_commit(offset, data), + } + } + + /// Called when the kernel starts using an allocation. + /// + /// Returns the size of the existing entry and the data associated with it. + pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> { + match &mut self.inner { + Impl::Empty(_size) => Err(EINVAL), + Impl::Array(array) => array.reserve_existing(offset), + Impl::Tree(tree) => tree.reserve_existing(offset), + } + } + + /// Call the provided callback at every allocated region. + /// + /// This destroys the range allocator. Used only during shutdown. + pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) { + match &mut self.inner { + Impl::Empty(_size) => {} + Impl::Array(array) => array.take_for_each(callback), + Impl::Tree(tree) => tree.take_for_each(callback), + } + } +} + +/// The arguments for `reserve_new`. +#[derive(Default)] +pub(crate) struct ReserveNewArgs<T> { + pub(crate) size: usize, + pub(crate) is_oneway: bool, + pub(crate) debug_id: usize, + pub(crate) pid: Pid, + pub(crate) empty_array_alloc: Option<EmptyArrayAlloc<T>>, + pub(crate) new_tree_alloc: Option<FromArrayAllocs<T>>, + pub(crate) tree_alloc: Option<ReserveNewTreeAlloc<T>>, +} + +/// The return type of `ReserveNew`. +pub(crate) enum ReserveNew<T> { + Success(ReserveNewSuccess<T>), + NeedAlloc(ReserveNewNeedAlloc<T>), +} + +/// Returned by `reserve_new` when the reservation was successul. +pub(crate) struct ReserveNewSuccess<T> { + pub(crate) offset: usize, + pub(crate) oneway_spam_detected: bool, + + // If the user supplied an allocation that we did not end up using, then we return it here. + // The caller will kfree it outside of the lock. + _empty_array_alloc: Option<EmptyArrayAlloc<T>>, + _new_tree_alloc: Option<FromArrayAllocs<T>>, + _tree_alloc: Option<ReserveNewTreeAlloc<T>>, +} + +/// Returned by `reserve_new` to request the caller to make an allocation before calling the method +/// again. +pub(crate) struct ReserveNewNeedAlloc<T> { + args: ReserveNewArgs<T>, + need_empty_array_alloc: bool, + need_new_tree_alloc: bool, + need_tree_alloc: bool, +} + +impl<T> ReserveNewNeedAlloc<T> { + /// Make the necessary allocations for another call to `reserve_new`. + pub(crate) fn make_alloc(mut self) -> Result<ReserveNewArgs<T>> { + if self.need_empty_array_alloc && self.args.empty_array_alloc.is_none() { + self.args.empty_array_alloc = Some(EmptyArrayAlloc::try_new(TREE_THRESHOLD)?); + } + if self.need_new_tree_alloc && self.args.new_tree_alloc.is_none() { + self.args.new_tree_alloc = Some(FromArrayAllocs::try_new(TREE_THRESHOLD)?); + } + if self.need_tree_alloc && self.args.tree_alloc.is_none() { + self.args.tree_alloc = Some(ReserveNewTreeAlloc::try_new()?); + } + Ok(self.args) + } +} diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs new file mode 100644 index 000000000000..7b1a248fcb02 --- /dev/null +++ b/drivers/android/binder/range_alloc/tree.rs @@ -0,0 +1,488 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::{ + page::PAGE_SIZE, + prelude::*, + rbtree::{RBTree, RBTreeNode, RBTreeNodeReservation}, + seq_file::SeqFile, + seq_print, + task::Pid, +}; + +use crate::range_alloc::{DescriptorState, FreedRange, Range}; + +/// Keeps track of allocations in a process' mmap. +/// +/// Each process has an mmap where the data for incoming transactions will be placed. This struct +/// keeps track of allocations made in the mmap. For each allocation, we store a descriptor that +/// has metadata related to the allocation. We also keep track of available free space. +pub(super) struct TreeRangeAllocator<T> { + /// This collection contains descriptors for *both* ranges containing an allocation, *and* free + /// ranges between allocations. The free ranges get merged, so there are never two free ranges + /// next to each other. + tree: RBTree<usize, Descriptor<T>>, + /// Contains an entry for every free range in `self.tree`. This tree sorts the ranges by size, + /// letting us look up the smallest range whose size is at least some lower bound. + free_tree: RBTree<FreeKey, ()>, + size: usize, + free_oneway_space: usize, +} + +impl<T> TreeRangeAllocator<T> { + pub(crate) fn from_array( + size: usize, + ranges: &mut KVec<Range<T>>, + alloc: &mut FromArrayAllocs<T>, + ) -> Self { + let mut tree = TreeRangeAllocator { + tree: RBTree::new(), + free_tree: RBTree::new(), + size, + free_oneway_space: size / 2, + }; + + let mut free_offset = 0; + for range in ranges.drain_all() { + let free_size = range.offset - free_offset; + if free_size > 0 { + let free_node = alloc.free_tree.pop().unwrap(); + tree.free_tree + .insert(free_node.into_node((free_size, free_offset), ())); + let tree_node = alloc.tree.pop().unwrap(); + tree.tree.insert( + tree_node.into_node(free_offset, Descriptor::new(free_offset, free_size)), + ); + } + free_offset = range.endpoint(); + + if range.state.is_oneway() { + tree.free_oneway_space = tree.free_oneway_space.saturating_sub(range.size); + } + + let free_res = alloc.free_tree.pop().unwrap(); + let tree_node = alloc.tree.pop().unwrap(); + let mut desc = Descriptor::new(range.offset, range.size); + desc.state = Some((range.state, free_res)); + tree.tree.insert(tree_node.into_node(range.offset, desc)); + } + + // After the last range, we may need a free range. + if free_offset < size { + let free_size = size - free_offset; + let free_node = alloc.free_tree.pop().unwrap(); + tree.free_tree + .insert(free_node.into_node((free_size, free_offset), ())); + let tree_node = alloc.tree.pop().unwrap(); + tree.tree + .insert(tree_node.into_node(free_offset, Descriptor::new(free_offset, free_size))); + } + + tree + } + + pub(crate) fn is_empty(&self) -> bool { + let mut tree_iter = self.tree.values(); + // There's always at least one range, because index zero is either the start of a free or + // allocated range. + let first_value = tree_iter.next().unwrap(); + if tree_iter.next().is_some() { + // There are never two free ranges next to each other, so if there is more than one + // descriptor, then at least one of them must hold an allocated range. + return false; + } + // There is only one descriptor. Return true if it is for a free range. + first_value.state.is_none() + } + + pub(crate) fn total_size(&self) -> usize { + self.size + } + + pub(crate) fn free_oneway_space(&self) -> usize { + self.free_oneway_space + } + + pub(crate) fn count_buffers(&self) -> usize { + self.tree + .values() + .filter(|desc| desc.state.is_some()) + .count() + } + + pub(crate) fn debug_print(&self, m: &SeqFile) -> Result<()> { + for desc in self.tree.values() { + let state = match &desc.state { + Some(state) => &state.0, + None => continue, + }; + seq_print!( + m, + " buffer: {} size {} pid {}", + desc.offset, + desc.size, + state.pid(), + ); + if state.is_oneway() { + seq_print!(m, " oneway"); + } + match state { + DescriptorState::Reserved(_res) => { + seq_print!(m, " reserved\n"); + } + DescriptorState::Allocated(_alloc) => { + seq_print!(m, " allocated\n"); + } + } + } + Ok(()) + } + + fn find_best_match(&mut self, size: usize) -> Option<&mut Descriptor<T>> { + let free_cursor = self.free_tree.cursor_lower_bound(&(size, 0))?; + let ((_, offset), ()) = free_cursor.current(); + self.tree.get_mut(offset) + } + + /// Try to reserve a new buffer, using the provided allocation if necessary. + pub(crate) fn reserve_new( + &mut self, + debug_id: usize, + size: usize, + is_oneway: bool, + pid: Pid, + alloc: ReserveNewTreeAlloc<T>, + ) -> Result<(usize, bool)> { + // Compute new value of free_oneway_space, which is set only on success. + let new_oneway_space = if is_oneway { + match self.free_oneway_space.checked_sub(size) { + Some(new_oneway_space) => new_oneway_space, + None => return Err(ENOSPC), + } + } else { + self.free_oneway_space + }; + + // Start detecting spammers once we have less than 20% + // of async space left (which is less than 10% of total + // buffer size). + // + // (This will short-circut, so `low_oneway_space` is + // only called when necessary.) + let oneway_spam_detected = + is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); + + let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) { + None => { + pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size); + return Err(ENOSPC); + } + Some(desc) => { + let found_size = desc.size; + let found_offset = desc.offset; + + // In case we need to break up the descriptor + let new_desc = Descriptor::new(found_offset + size, found_size - size); + let (tree_node, free_tree_node, desc_node_res) = alloc.initialize(new_desc); + + desc.state = Some(( + DescriptorState::new(is_oneway, debug_id, pid), + desc_node_res, + )); + desc.size = size; + + (found_size, found_offset, tree_node, free_tree_node) + } + }; + self.free_oneway_space = new_oneway_space; + self.free_tree.remove(&(found_size, found_off)); + + if found_size != size { + self.tree.insert(tree_node); + self.free_tree.insert(free_tree_node); + } + + Ok((found_off, oneway_spam_detected)) + } + + pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> { + let mut cursor = self.tree.cursor_lower_bound(&offset).ok_or_else(|| { + pr_warn!( + "EINVAL from range_alloc.reservation_abort - offset: {}", + offset + ); + EINVAL + })?; + + let (_, desc) = cursor.current_mut(); + + if desc.offset != offset { + pr_warn!( + "EINVAL from range_alloc.reservation_abort - offset: {}", + offset + ); + return Err(EINVAL); + } + + let (reservation, free_node_res) = desc.try_change_state(|state| match state { + Some((DescriptorState::Reserved(reservation), free_node_res)) => { + (None, Ok((reservation, free_node_res))) + } + None => { + pr_warn!( + "EINVAL from range_alloc.reservation_abort - offset: {}", + offset + ); + (None, Err(EINVAL)) + } + allocated => { + pr_warn!( + "EPERM from range_alloc.reservation_abort - offset: {}", + offset + ); + (allocated, Err(EPERM)) + } + })?; + + let mut size = desc.size; + let mut offset = desc.offset; + let free_oneway_space_add = if reservation.is_oneway { size } else { 0 }; + + self.free_oneway_space += free_oneway_space_add; + + let mut freed_range = FreedRange::interior_pages(offset, size); + // Compute how large the next free region needs to be to include one more page in + // the newly freed range. + let add_next_page_needed = match (offset + size) % PAGE_SIZE { + 0 => usize::MAX, + unalign => PAGE_SIZE - unalign, + }; + // Compute how large the previous free region needs to be to include one more page + // in the newly freed range. + let add_prev_page_needed = match offset % PAGE_SIZE { + 0 => usize::MAX, + unalign => unalign, + }; + + // Merge next into current if next is free + let remove_next = match cursor.peek_next() { + Some((_, next)) if next.state.is_none() => { + if next.size >= add_next_page_needed { + freed_range.end_page_idx += 1; + } + self.free_tree.remove(&(next.size, next.offset)); + size += next.size; + true + } + _ => false, + }; + + if remove_next { + let (_, desc) = cursor.current_mut(); + desc.size = size; + cursor.remove_next(); + } + + // Merge current into prev if prev is free + match cursor.peek_prev_mut() { + Some((_, prev)) if prev.state.is_none() => { + if prev.size >= add_prev_page_needed { + freed_range.start_page_idx -= 1; + } + // merge previous with current, remove current + self.free_tree.remove(&(prev.size, prev.offset)); + offset = prev.offset; + size += prev.size; + prev.size = size; + cursor.remove_current(); + } + _ => {} + }; + + self.free_tree + .insert(free_node_res.into_node((size, offset), ())); + + Ok(freed_range) + } + + pub(crate) fn reservation_commit(&mut self, offset: usize, data: &mut Option<T>) -> Result { + let desc = self.tree.get_mut(&offset).ok_or(ENOENT)?; + + desc.try_change_state(|state| match state { + Some((DescriptorState::Reserved(reservation), free_node_res)) => ( + Some(( + DescriptorState::Allocated(reservation.allocate(data.take())), + free_node_res, + )), + Ok(()), + ), + other => (other, Err(ENOENT)), + }) + } + + /// Takes an entry at the given offset from [`DescriptorState::Allocated`] to + /// [`DescriptorState::Reserved`]. + /// + /// Returns the size of the existing entry and the data associated with it. + pub(crate) fn reserve_existing(&mut self, offset: usize) -> Result<(usize, usize, Option<T>)> { + let desc = self.tree.get_mut(&offset).ok_or_else(|| { + pr_warn!( + "ENOENT from range_alloc.reserve_existing - offset: {}", + offset + ); + ENOENT + })?; + + let (debug_id, data) = desc.try_change_state(|state| match state { + Some((DescriptorState::Allocated(allocation), free_node_res)) => { + let (reservation, data) = allocation.deallocate(); + let debug_id = reservation.debug_id; + ( + Some((DescriptorState::Reserved(reservation), free_node_res)), + Ok((debug_id, data)), + ) + } + other => { + pr_warn!( + "ENOENT from range_alloc.reserve_existing - offset: {}", + offset + ); + (other, Err(ENOENT)) + } + })?; + + Ok((desc.size, debug_id, data)) + } + + /// Call the provided callback at every allocated region. + /// + /// This destroys the range allocator. Used only during shutdown. + pub(crate) fn take_for_each<F: Fn(usize, usize, usize, Option<T>)>(&mut self, callback: F) { + for (_, desc) in self.tree.iter_mut() { + if let Some((DescriptorState::Allocated(allocation), _)) = &mut desc.state { + callback( + desc.offset, + desc.size, + allocation.debug_id(), + allocation.take(), + ); + } + } + } + + /// Find the amount and size of buffers allocated by the current caller. + /// + /// The idea is that once we cross the threshold, whoever is responsible + /// for the low async space is likely to try to send another async transaction, + /// and at some point we'll catch them in the act. This is more efficient + /// than keeping a map per pid. + fn low_oneway_space(&self, calling_pid: Pid) -> bool { + let mut total_alloc_size = 0; + let mut num_buffers = 0; + for (_, desc) in self.tree.iter() { + if let Some((state, _)) = &desc.state { + if state.is_oneway() && state.pid() == calling_pid { + total_alloc_size += desc.size; + num_buffers += 1; + } + } + } + + // Warn if this pid has more than 50 transactions, or more than 50% of + // async space (which is 25% of total buffer size). Oneway spam is only + // detected when the threshold is exceeded. + num_buffers > 50 || total_alloc_size > self.size / 4 + } +} + +type TreeDescriptorState<T> = (DescriptorState<T>, FreeNodeRes); +struct Descriptor<T> { + size: usize, + offset: usize, + state: Option<TreeDescriptorState<T>>, +} + +impl<T> Descriptor<T> { + fn new(offset: usize, size: usize) -> Self { + Self { + size, + offset, + state: None, + } + } + + fn try_change_state<F, Data>(&mut self, f: F) -> Result<Data> + where + F: FnOnce(Option<TreeDescriptorState<T>>) -> (Option<TreeDescriptorState<T>>, Result<Data>), + { + let (new_state, result) = f(self.state.take()); + self.state = new_state; + result + } +} + +// (Descriptor.size, Descriptor.offset) +type FreeKey = (usize, usize); +type FreeNodeRes = RBTreeNodeReservation<FreeKey, ()>; + +/// An allocation for use by `reserve_new`. +pub(crate) struct ReserveNewTreeAlloc<T> { + tree_node_res: RBTreeNodeReservation<usize, Descriptor<T>>, + free_tree_node_res: FreeNodeRes, + desc_node_res: FreeNodeRes, +} + +impl<T> ReserveNewTreeAlloc<T> { + pub(crate) fn try_new() -> Result<Self> { + let tree_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?; + let free_tree_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?; + let desc_node_res = RBTreeNodeReservation::new(GFP_KERNEL)?; + Ok(Self { + tree_node_res, + free_tree_node_res, + desc_node_res, + }) + } + + fn initialize( + self, + desc: Descriptor<T>, + ) -> ( + RBTreeNode<usize, Descriptor<T>>, + RBTreeNode<FreeKey, ()>, + FreeNodeRes, + ) { + let size = desc.size; + let offset = desc.offset; + ( + self.tree_node_res.into_node(offset, desc), + self.free_tree_node_res.into_node((size, offset), ()), + self.desc_node_res, + ) + } +} + +/// An allocation for creating a tree from an `ArrayRangeAllocator`. +pub(crate) struct FromArrayAllocs<T> { + tree: KVec<RBTreeNodeReservation<usize, Descriptor<T>>>, + free_tree: KVec<RBTreeNodeReservation<FreeKey, ()>>, +} + +impl<T> FromArrayAllocs<T> { + pub(crate) fn try_new(len: usize) -> Result<Self> { + let num_descriptors = 2 * len + 1; + + let mut tree = KVec::with_capacity(num_descriptors, GFP_KERNEL)?; + for _ in 0..num_descriptors { + tree.push(RBTreeNodeReservation::new(GFP_KERNEL)?, GFP_KERNEL)?; + } + + let mut free_tree = KVec::with_capacity(num_descriptors, GFP_KERNEL)?; + for _ in 0..num_descriptors { + free_tree.push(RBTreeNodeReservation::new(GFP_KERNEL)?, GFP_KERNEL)?; + } + + Ok(Self { tree, free_tree }) + } +} diff --git a/drivers/android/binder/rust_binder.h b/drivers/android/binder/rust_binder.h new file mode 100644 index 000000000000..31806890ed1a --- /dev/null +++ b/drivers/android/binder/rust_binder.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Google, Inc. + */ + +#ifndef _LINUX_RUST_BINDER_H +#define _LINUX_RUST_BINDER_H + +#include <uapi/linux/android/binder.h> +#include <uapi/linux/android/binderfs.h> + +/* + * These symbols are exposed by `rust_binderfs.c` and exist here so that Rust + * Binder can call them. + */ +int init_rust_binderfs(void); + +struct dentry; +struct inode; +struct dentry *rust_binderfs_create_proc_file(struct inode *nodp, int pid); +void rust_binderfs_remove_file(struct dentry *dentry); + +#endif diff --git a/drivers/android/binder/rust_binder_events.c b/drivers/android/binder/rust_binder_events.c new file mode 100644 index 000000000000..488b1470060c --- /dev/null +++ b/drivers/android/binder/rust_binder_events.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* rust_binder_events.c + * + * Rust Binder tracepoints. + * + * Copyright 2025 Google LLC + */ + +#include "rust_binder.h" + +const char * const binder_command_strings[] = { + "BC_TRANSACTION", + "BC_REPLY", + "BC_ACQUIRE_RESULT", + "BC_FREE_BUFFER", + "BC_INCREFS", + "BC_ACQUIRE", + "BC_RELEASE", + "BC_DECREFS", + "BC_INCREFS_DONE", + "BC_ACQUIRE_DONE", + "BC_ATTEMPT_ACQUIRE", + "BC_REGISTER_LOOPER", + "BC_ENTER_LOOPER", + "BC_EXIT_LOOPER", + "BC_REQUEST_DEATH_NOTIFICATION", + "BC_CLEAR_DEATH_NOTIFICATION", + "BC_DEAD_BINDER_DONE", + "BC_TRANSACTION_SG", + "BC_REPLY_SG", +}; + +const char * const binder_return_strings[] = { + "BR_ERROR", + "BR_OK", + "BR_TRANSACTION", + "BR_REPLY", + "BR_ACQUIRE_RESULT", + "BR_DEAD_REPLY", + "BR_TRANSACTION_COMPLETE", + "BR_INCREFS", + "BR_ACQUIRE", + "BR_RELEASE", + "BR_DECREFS", + "BR_ATTEMPT_ACQUIRE", + "BR_NOOP", + "BR_SPAWN_LOOPER", + "BR_FINISHED", + "BR_DEAD_BINDER", + "BR_CLEAR_DEATH_NOTIFICATION_DONE", + "BR_FAILED_REPLY", + "BR_FROZEN_REPLY", + "BR_ONEWAY_SPAM_SUSPECT", + "BR_TRANSACTION_PENDING_FROZEN" +}; + +#define CREATE_TRACE_POINTS +#define CREATE_RUST_TRACE_POINTS +#include "rust_binder_events.h" diff --git a/drivers/android/binder/rust_binder_events.h b/drivers/android/binder/rust_binder_events.h new file mode 100644 index 000000000000..2f3efbf9dba6 --- /dev/null +++ b/drivers/android/binder/rust_binder_events.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 Google, Inc. + */ + +#undef TRACE_SYSTEM +#undef TRACE_INCLUDE_FILE +#undef TRACE_INCLUDE_PATH +#define TRACE_SYSTEM rust_binder +#define TRACE_INCLUDE_FILE rust_binder_events +#define TRACE_INCLUDE_PATH ../drivers/android/binder + +#if !defined(_RUST_BINDER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _RUST_BINDER_TRACE_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(rust_binder_ioctl, + TP_PROTO(unsigned int cmd, unsigned long arg), + TP_ARGS(cmd, arg), + + TP_STRUCT__entry( + __field(unsigned int, cmd) + __field(unsigned long, arg) + ), + TP_fast_assign( + __entry->cmd = cmd; + __entry->arg = arg; + ), + TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg) +); + +#endif /* _RUST_BINDER_TRACE_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/drivers/android/binder/rust_binder_internal.h b/drivers/android/binder/rust_binder_internal.h new file mode 100644 index 000000000000..78288fe7964d --- /dev/null +++ b/drivers/android/binder/rust_binder_internal.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* rust_binder_internal.h + * + * This file contains internal data structures used by Rust Binder. Mostly, + * these are type definitions used only by binderfs or things that Rust Binder + * define and export to binderfs. + * + * It does not include things exported by binderfs to Rust Binder since this + * file is not included as input to bindgen. + * + * Copyright (C) 2025 Google LLC. + */ + +#ifndef _LINUX_RUST_BINDER_INTERNAL_H +#define _LINUX_RUST_BINDER_INTERNAL_H + +#define RUST_BINDERFS_SUPER_MAGIC 0x6c6f6f71 + +#include <linux/seq_file.h> +#include <uapi/linux/android/binder.h> +#include <uapi/linux/android/binderfs.h> + +/* + * The internal data types in the Rust Binder driver are opaque to C, so we use + * void pointer typedefs for these types. + */ +typedef void *rust_binder_context; + +/** + * struct binder_device - information about a binder device node + * @minor: the minor number used by this device + * @ctx: the Rust Context used by this device, or null for binder-control + * + * This is used as the private data for files directly in binderfs, but not + * files in the binder_logs subdirectory. This struct owns a refcount on `ctx` + * and the entry for `minor` in `binderfs_minors`. For binder-control `ctx` is + * null. + */ +struct binder_device { + int minor; + rust_binder_context ctx; +}; + +int rust_binder_stats_show(struct seq_file *m, void *unused); +int rust_binder_state_show(struct seq_file *m, void *unused); +int rust_binder_transactions_show(struct seq_file *m, void *unused); +int rust_binder_proc_show(struct seq_file *m, void *pid); + +extern const struct file_operations rust_binder_fops; +rust_binder_context rust_binder_new_context(char *name); +void rust_binder_remove_context(rust_binder_context device); + +/** + * binderfs_mount_opts - mount options for binderfs + * @max: maximum number of allocatable binderfs binder devices + * @stats_mode: enable binder stats in binderfs. + */ +struct binderfs_mount_opts { + int max; + int stats_mode; +}; + +/** + * binderfs_info - information about a binderfs mount + * @ipc_ns: The ipc namespace the binderfs mount belongs to. + * @control_dentry: This records the dentry of this binderfs mount + * binder-control device. + * @root_uid: uid that needs to be used when a new binder device is + * created. + * @root_gid: gid that needs to be used when a new binder device is + * created. + * @mount_opts: The mount options in use. + * @device_count: The current number of allocated binder devices. + * @proc_log_dir: Pointer to the directory dentry containing process-specific + * logs. + */ +struct binderfs_info { + struct ipc_namespace *ipc_ns; + struct dentry *control_dentry; + kuid_t root_uid; + kgid_t root_gid; + struct binderfs_mount_opts mount_opts; + int device_count; + struct dentry *proc_log_dir; +}; + +#endif /* _LINUX_RUST_BINDER_INTERNAL_H */ diff --git a/drivers/android/binder/rust_binder_main.rs b/drivers/android/binder/rust_binder_main.rs new file mode 100644 index 000000000000..6773b7c273ec --- /dev/null +++ b/drivers/android/binder/rust_binder_main.rs @@ -0,0 +1,627 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! Binder -- the Android IPC mechanism. +#![recursion_limit = "256"] +#![allow( + clippy::as_underscore, + clippy::ref_as_ptr, + clippy::ptr_as_ptr, + clippy::cast_lossless +)] + +use kernel::{ + bindings::{self, seq_file}, + fs::File, + list::{ListArc, ListArcSafe, ListLinksSelfPtr, TryNewListArc}, + prelude::*, + seq_file::SeqFile, + seq_print, + sync::poll::PollTable, + sync::Arc, + task::Pid, + transmute::AsBytes, + types::ForeignOwnable, + uaccess::UserSliceWriter, +}; + +use crate::{context::Context, page_range::Shrinker, process::Process, thread::Thread}; + +use core::{ + ptr::NonNull, + sync::atomic::{AtomicBool, AtomicUsize, Ordering}, +}; + +mod allocation; +mod context; +mod deferred_close; +mod defs; +mod error; +mod node; +mod page_range; +mod process; +mod range_alloc; +mod stats; +mod thread; +mod trace; +mod transaction; + +#[allow(warnings)] // generated bindgen code +mod binderfs { + use kernel::bindings::{dentry, inode}; + + extern "C" { + pub fn init_rust_binderfs() -> kernel::ffi::c_int; + } + extern "C" { + pub fn rust_binderfs_create_proc_file( + nodp: *mut inode, + pid: kernel::ffi::c_int, + ) -> *mut dentry; + } + extern "C" { + pub fn rust_binderfs_remove_file(dentry: *mut dentry); + } + pub type rust_binder_context = *mut kernel::ffi::c_void; + #[repr(C)] + #[derive(Copy, Clone)] + pub struct binder_device { + pub minor: kernel::ffi::c_int, + pub ctx: rust_binder_context, + } + impl Default for binder_device { + fn default() -> Self { + let mut s = ::core::mem::MaybeUninit::<Self>::uninit(); + unsafe { + ::core::ptr::write_bytes(s.as_mut_ptr(), 0, 1); + s.assume_init() + } + } + } +} + +module! { + type: BinderModule, + name: "rust_binder", + authors: ["Wedson Almeida Filho", "Alice Ryhl"], + description: "Android Binder", + license: "GPL", +} + +fn next_debug_id() -> usize { + static NEXT_DEBUG_ID: AtomicUsize = AtomicUsize::new(0); + + NEXT_DEBUG_ID.fetch_add(1, Ordering::Relaxed) +} + +/// Provides a single place to write Binder return values via the +/// supplied `UserSliceWriter`. +pub(crate) struct BinderReturnWriter<'a> { + writer: UserSliceWriter, + thread: &'a Thread, +} + +impl<'a> BinderReturnWriter<'a> { + fn new(writer: UserSliceWriter, thread: &'a Thread) -> Self { + BinderReturnWriter { writer, thread } + } + + /// Write a return code back to user space. + /// Should be a `BR_` constant from [`defs`] e.g. [`defs::BR_TRANSACTION_COMPLETE`]. + fn write_code(&mut self, code: u32) -> Result { + stats::GLOBAL_STATS.inc_br(code); + self.thread.process.stats.inc_br(code); + self.writer.write(&code) + } + + /// Write something *other than* a return code to user space. + fn write_payload<T: AsBytes>(&mut self, payload: &T) -> Result { + self.writer.write(payload) + } + + fn len(&self) -> usize { + self.writer.len() + } +} + +/// Specifies how a type should be delivered to the read part of a BINDER_WRITE_READ ioctl. +/// +/// When a value is pushed to the todo list for a process or thread, it is stored as a trait object +/// with the type `Arc<dyn DeliverToRead>`. Trait objects are a Rust feature that lets you +/// implement dynamic dispatch over many different types. This lets us store many different types +/// in the todo list. +trait DeliverToRead: ListArcSafe + Send + Sync { + /// Performs work. Returns true if remaining work items in the queue should be processed + /// immediately, or false if it should return to caller before processing additional work + /// items. + fn do_work( + self: DArc<Self>, + thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool>; + + /// Cancels the given work item. This is called instead of [`DeliverToRead::do_work`] when work + /// won't be delivered. + fn cancel(self: DArc<Self>); + + /// Should we use `wake_up_interruptible_sync` or `wake_up_interruptible` when scheduling this + /// work item? + /// + /// Generally only set to true for non-oneway transactions. + fn should_sync_wakeup(&self) -> bool; + + fn debug_print(&self, m: &SeqFile, prefix: &str, transaction_prefix: &str) -> Result<()>; +} + +// Wrapper around a `DeliverToRead` with linked list links. +#[pin_data] +struct DTRWrap<T: ?Sized> { + #[pin] + links: ListLinksSelfPtr<DTRWrap<dyn DeliverToRead>>, + #[pin] + wrapped: T, +} +kernel::list::impl_list_arc_safe! { + impl{T: ListArcSafe + ?Sized} ListArcSafe<0> for DTRWrap<T> { + tracked_by wrapped: T; + } +} +kernel::list::impl_list_item! { + impl ListItem<0> for DTRWrap<dyn DeliverToRead> { + using ListLinksSelfPtr { self.links }; + } +} + +impl<T: ?Sized> core::ops::Deref for DTRWrap<T> { + type Target = T; + fn deref(&self) -> &T { + &self.wrapped + } +} + +type DArc<T> = kernel::sync::Arc<DTRWrap<T>>; +type DLArc<T> = kernel::list::ListArc<DTRWrap<T>>; + +impl<T: ListArcSafe> DTRWrap<T> { + fn new(val: impl PinInit<T>) -> impl PinInit<Self> { + pin_init!(Self { + links <- ListLinksSelfPtr::new(), + wrapped <- val, + }) + } + + fn arc_try_new(val: T) -> Result<DLArc<T>, kernel::alloc::AllocError> { + ListArc::pin_init( + try_pin_init!(Self { + links <- ListLinksSelfPtr::new(), + wrapped: val, + }), + GFP_KERNEL, + ) + .map_err(|_| kernel::alloc::AllocError) + } + + fn arc_pin_init(init: impl PinInit<T>) -> Result<DLArc<T>, kernel::error::Error> { + ListArc::pin_init( + try_pin_init!(Self { + links <- ListLinksSelfPtr::new(), + wrapped <- init, + }), + GFP_KERNEL, + ) + } +} + +struct DeliverCode { + code: u32, + skip: AtomicBool, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for DeliverCode { untracked; } +} + +impl DeliverCode { + fn new(code: u32) -> Self { + Self { + code, + skip: AtomicBool::new(false), + } + } + + /// Disable this DeliverCode and make it do nothing. + /// + /// This is used instead of removing it from the work list, since `LinkedList::remove` is + /// unsafe, whereas this method is not. + fn skip(&self) { + self.skip.store(true, Ordering::Relaxed); + } +} + +impl DeliverToRead for DeliverCode { + fn do_work( + self: DArc<Self>, + _thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + if !self.skip.load(Ordering::Relaxed) { + writer.write_code(self.code)?; + } + Ok(true) + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + seq_print!(m, "{}", prefix); + if self.skip.load(Ordering::Relaxed) { + seq_print!(m, "(skipped) "); + } + if self.code == defs::BR_TRANSACTION_COMPLETE { + seq_print!(m, "transaction complete\n"); + } else { + seq_print!(m, "transaction error: {}\n", self.code); + } + Ok(()) + } +} + +fn ptr_align(value: usize) -> Option<usize> { + let size = core::mem::size_of::<usize>() - 1; + Some(value.checked_add(size)? & !size) +} + +// SAFETY: We call register in `init`. +static BINDER_SHRINKER: Shrinker = unsafe { Shrinker::new() }; + +struct BinderModule {} + +impl kernel::Module for BinderModule { + fn init(_module: &'static kernel::ThisModule) -> Result<Self> { + // SAFETY: The module initializer never runs twice, so we only call this once. + unsafe { crate::context::CONTEXTS.init() }; + + pr_warn!("Loaded Rust Binder."); + + BINDER_SHRINKER.register(kernel::c_str!("android-binder"))?; + + // SAFETY: The module is being loaded, so we can initialize binderfs. + unsafe { kernel::error::to_result(binderfs::init_rust_binderfs())? }; + + Ok(Self {}) + } +} + +/// Makes the inner type Sync. +#[repr(transparent)] +pub struct AssertSync<T>(T); +// SAFETY: Used only to insert `file_operations` into a global, which is safe. +unsafe impl<T> Sync for AssertSync<T> {} + +/// File operations that rust_binderfs.c can use. +#[no_mangle] +#[used] +pub static rust_binder_fops: AssertSync<kernel::bindings::file_operations> = { + // SAFETY: All zeroes is safe for the `file_operations` type. + let zeroed_ops = unsafe { core::mem::MaybeUninit::zeroed().assume_init() }; + + let ops = kernel::bindings::file_operations { + owner: THIS_MODULE.as_ptr(), + poll: Some(rust_binder_poll), + unlocked_ioctl: Some(rust_binder_unlocked_ioctl), + compat_ioctl: Some(rust_binder_compat_ioctl), + mmap: Some(rust_binder_mmap), + open: Some(rust_binder_open), + release: Some(rust_binder_release), + flush: Some(rust_binder_flush), + ..zeroed_ops + }; + AssertSync(ops) +}; + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_new_context( + name: *const kernel::ffi::c_char, +) -> *mut kernel::ffi::c_void { + // SAFETY: The caller will always provide a valid c string here. + let name = unsafe { kernel::str::CStr::from_char_ptr(name) }; + match Context::new(name) { + Ok(ctx) => Arc::into_foreign(ctx), + Err(_err) => core::ptr::null_mut(), + } +} + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_remove_context(device: *mut kernel::ffi::c_void) { + if !device.is_null() { + // SAFETY: The caller ensures that the `device` pointer came from a previous call to + // `rust_binder_new_device`. + let ctx = unsafe { Arc::<Context>::from_foreign(device) }; + ctx.deregister(); + drop(ctx); + } +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_open( + inode: *mut bindings::inode, + file_ptr: *mut bindings::file, +) -> kernel::ffi::c_int { + // SAFETY: The `rust_binderfs.c` file ensures that `i_private` is set to a + // `struct binder_device`. + let device = unsafe { (*inode).i_private } as *const binderfs::binder_device; + + assert!(!device.is_null()); + + // SAFETY: The `rust_binderfs.c` file ensures that `device->ctx` holds a binder context when + // using the rust binder fops. + let ctx = unsafe { Arc::<Context>::borrow((*device).ctx) }; + + // SAFETY: The caller provides a valid file pointer to a new `struct file`. + let file = unsafe { File::from_raw_file(file_ptr) }; + let process = match Process::open(ctx, file) { + Ok(process) => process, + Err(err) => return err.to_errno(), + }; + + // SAFETY: This is an `inode` for a newly created binder file. + match unsafe { BinderfsProcFile::new(inode, process.task.pid()) } { + Ok(Some(file)) => process.inner.lock().binderfs_file = Some(file), + Ok(None) => { /* pid already exists */ } + Err(err) => return err.to_errno(), + } + + // SAFETY: This file is associated with Rust binder, so we own the `private_data` field. + unsafe { (*file_ptr).private_data = process.into_foreign() }; + 0 +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_release( + _inode: *mut bindings::inode, + file: *mut bindings::file, +) -> kernel::ffi::c_int { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let process = unsafe { Arc::<Process>::from_foreign((*file).private_data) }; + // SAFETY: The caller ensures that the file is valid. + let file = unsafe { File::from_raw_file(file) }; + Process::release(process, file); + 0 +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_compat_ioctl( + file: *mut bindings::file, + cmd: kernel::ffi::c_uint, + arg: kernel::ffi::c_ulong, +) -> kernel::ffi::c_long { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let f = unsafe { Arc::<Process>::borrow((*file).private_data) }; + // SAFETY: The caller ensures that the file is valid. + match Process::compat_ioctl(f, unsafe { File::from_raw_file(file) }, cmd as _, arg as _) { + Ok(()) => 0, + Err(err) => err.to_errno() as isize, + } +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_unlocked_ioctl( + file: *mut bindings::file, + cmd: kernel::ffi::c_uint, + arg: kernel::ffi::c_ulong, +) -> kernel::ffi::c_long { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let f = unsafe { Arc::<Process>::borrow((*file).private_data) }; + // SAFETY: The caller ensures that the file is valid. + match Process::ioctl(f, unsafe { File::from_raw_file(file) }, cmd as _, arg as _) { + Ok(()) => 0, + Err(err) => err.to_errno() as isize, + } +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_mmap( + file: *mut bindings::file, + vma: *mut bindings::vm_area_struct, +) -> kernel::ffi::c_int { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let f = unsafe { Arc::<Process>::borrow((*file).private_data) }; + // SAFETY: The caller ensures that the vma is valid. + let area = unsafe { kernel::mm::virt::VmaNew::from_raw(vma) }; + // SAFETY: The caller ensures that the file is valid. + match Process::mmap(f, unsafe { File::from_raw_file(file) }, area) { + Ok(()) => 0, + Err(err) => err.to_errno(), + } +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_poll( + file: *mut bindings::file, + wait: *mut bindings::poll_table_struct, +) -> bindings::__poll_t { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let f = unsafe { Arc::<Process>::borrow((*file).private_data) }; + // SAFETY: The caller ensures that the file is valid. + let fileref = unsafe { File::from_raw_file(file) }; + // SAFETY: The caller ensures that the `PollTable` is valid. + match Process::poll(f, fileref, unsafe { PollTable::from_raw(wait) }) { + Ok(v) => v, + Err(_) => bindings::POLLERR, + } +} + +/// # Safety +/// Only called by binderfs. +unsafe extern "C" fn rust_binder_flush( + file: *mut bindings::file, + _id: bindings::fl_owner_t, +) -> kernel::ffi::c_int { + // SAFETY: We previously set `private_data` in `rust_binder_open`. + let f = unsafe { Arc::<Process>::borrow((*file).private_data) }; + match Process::flush(f) { + Ok(()) => 0, + Err(err) => err.to_errno(), + } +} + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_stats_show( + ptr: *mut seq_file, + _: *mut kernel::ffi::c_void, +) -> kernel::ffi::c_int { + // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which + // this method is called. + let m = unsafe { SeqFile::from_raw(ptr) }; + if let Err(err) = rust_binder_stats_show_impl(m) { + seq_print!(m, "failed to generate state: {:?}\n", err); + } + 0 +} + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_state_show( + ptr: *mut seq_file, + _: *mut kernel::ffi::c_void, +) -> kernel::ffi::c_int { + // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which + // this method is called. + let m = unsafe { SeqFile::from_raw(ptr) }; + if let Err(err) = rust_binder_state_show_impl(m) { + seq_print!(m, "failed to generate state: {:?}\n", err); + } + 0 +} + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_proc_show( + ptr: *mut seq_file, + _: *mut kernel::ffi::c_void, +) -> kernel::ffi::c_int { + // SAFETY: Accessing the private field of `seq_file` is okay. + let pid = (unsafe { (*ptr).private }) as usize as Pid; + // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which + // this method is called. + let m = unsafe { SeqFile::from_raw(ptr) }; + if let Err(err) = rust_binder_proc_show_impl(m, pid) { + seq_print!(m, "failed to generate state: {:?}\n", err); + } + 0 +} + +/// # Safety +/// Only called by binderfs. +#[no_mangle] +unsafe extern "C" fn rust_binder_transactions_show( + ptr: *mut seq_file, + _: *mut kernel::ffi::c_void, +) -> kernel::ffi::c_int { + // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which + // this method is called. + let m = unsafe { SeqFile::from_raw(ptr) }; + if let Err(err) = rust_binder_transactions_show_impl(m) { + seq_print!(m, "failed to generate state: {:?}\n", err); + } + 0 +} + +fn rust_binder_transactions_show_impl(m: &SeqFile) -> Result<()> { + seq_print!(m, "binder transactions:\n"); + let contexts = context::get_all_contexts()?; + for ctx in contexts { + let procs = ctx.get_all_procs()?; + for proc in procs { + proc.debug_print(m, &ctx, false)?; + seq_print!(m, "\n"); + } + } + Ok(()) +} + +fn rust_binder_stats_show_impl(m: &SeqFile) -> Result<()> { + seq_print!(m, "binder stats:\n"); + stats::GLOBAL_STATS.debug_print("", m); + let contexts = context::get_all_contexts()?; + for ctx in contexts { + let procs = ctx.get_all_procs()?; + for proc in procs { + proc.debug_print_stats(m, &ctx)?; + seq_print!(m, "\n"); + } + } + Ok(()) +} + +fn rust_binder_state_show_impl(m: &SeqFile) -> Result<()> { + seq_print!(m, "binder state:\n"); + let contexts = context::get_all_contexts()?; + for ctx in contexts { + let procs = ctx.get_all_procs()?; + for proc in procs { + proc.debug_print(m, &ctx, true)?; + seq_print!(m, "\n"); + } + } + Ok(()) +} + +fn rust_binder_proc_show_impl(m: &SeqFile, pid: Pid) -> Result<()> { + seq_print!(m, "binder proc state:\n"); + let contexts = context::get_all_contexts()?; + for ctx in contexts { + let procs = ctx.get_procs_with_pid(pid)?; + for proc in procs { + proc.debug_print(m, &ctx, true)?; + seq_print!(m, "\n"); + } + } + Ok(()) +} + +struct BinderfsProcFile(NonNull<bindings::dentry>); + +// SAFETY: Safe to drop any thread. +unsafe impl Send for BinderfsProcFile {} + +impl BinderfsProcFile { + /// # Safety + /// + /// Takes an inode from a newly created binder file. + unsafe fn new(nodp: *mut bindings::inode, pid: i32) -> Result<Option<Self>> { + // SAFETY: The caller passes an `inode` for a newly created binder file. + let dentry = unsafe { binderfs::rust_binderfs_create_proc_file(nodp, pid) }; + match kernel::error::from_err_ptr(dentry) { + Ok(dentry) => Ok(NonNull::new(dentry).map(Self)), + Err(err) if err == EEXIST => Ok(None), + Err(err) => Err(err), + } + } +} + +impl Drop for BinderfsProcFile { + fn drop(&mut self) { + // SAFETY: This is a dentry from `rust_binderfs_remove_file` that has not been deleted yet. + unsafe { binderfs::rust_binderfs_remove_file(self.0.as_ptr()) }; + } +} diff --git a/drivers/android/binder/rust_binderfs.c b/drivers/android/binder/rust_binderfs.c new file mode 100644 index 000000000000..6b497146b698 --- /dev/null +++ b/drivers/android/binder/rust_binderfs.c @@ -0,0 +1,850 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/compiler_types.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/fsnotify.h> +#include <linux/gfp.h> +#include <linux/idr.h> +#include <linux/init.h> +#include <linux/ipc_namespace.h> +#include <linux/kdev_t.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/namei.h> +#include <linux/magic.h> +#include <linux/major.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/mount.h> +#include <linux/fs_parser.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/spinlock_types.h> +#include <linux/stddef.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <linux/user_namespace.h> +#include <linux/xarray.h> +#include <uapi/asm-generic/errno-base.h> +#include <uapi/linux/android/binder.h> +#include <uapi/linux/android/binderfs.h> + +#include "rust_binder.h" +#include "rust_binder_internal.h" + +#define FIRST_INODE 1 +#define SECOND_INODE 2 +#define INODE_OFFSET 3 +#define BINDERFS_MAX_MINOR (1U << MINORBITS) +/* Ensure that the initial ipc namespace always has devices available. */ +#define BINDERFS_MAX_MINOR_CAPPED (BINDERFS_MAX_MINOR - 4) + +DEFINE_SHOW_ATTRIBUTE(rust_binder_stats); +DEFINE_SHOW_ATTRIBUTE(rust_binder_state); +DEFINE_SHOW_ATTRIBUTE(rust_binder_transactions); +DEFINE_SHOW_ATTRIBUTE(rust_binder_proc); + +char *rust_binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES; +module_param_named(rust_devices, rust_binder_devices_param, charp, 0444); + +static dev_t binderfs_dev; +static DEFINE_MUTEX(binderfs_minors_mutex); +static DEFINE_IDA(binderfs_minors); + +enum binderfs_param { + Opt_max, + Opt_stats_mode, +}; + +enum binderfs_stats_mode { + binderfs_stats_mode_unset, + binderfs_stats_mode_global, +}; + +struct binder_features { + bool oneway_spam_detection; + bool extended_error; + bool freeze_notification; +}; + +static const struct constant_table binderfs_param_stats[] = { + { "global", binderfs_stats_mode_global }, + {} +}; + +static const struct fs_parameter_spec binderfs_fs_parameters[] = { + fsparam_u32("max", Opt_max), + fsparam_enum("stats", Opt_stats_mode, binderfs_param_stats), + {} +}; + +static struct binder_features binder_features = { + .oneway_spam_detection = true, + .extended_error = true, + .freeze_notification = true, +}; + +static inline struct binderfs_info *BINDERFS_SB(const struct super_block *sb) +{ + return sb->s_fs_info; +} + +/** + * binderfs_binder_device_create - allocate inode from super block of a + * binderfs mount + * @ref_inode: inode from wich the super block will be taken + * @userp: buffer to copy information about new device for userspace to + * @req: struct binderfs_device as copied from userspace + * + * This function allocates a new binder_device and reserves a new minor + * number for it. + * Minor numbers are limited and tracked globally in binderfs_minors. The + * function will stash a struct binder_device for the specific binder + * device in i_private of the inode. + * It will go on to allocate a new inode from the super block of the + * filesystem mount, stash a struct binder_device in its i_private field + * and attach a dentry to that inode. + * + * Return: 0 on success, negative errno on failure + */ +static int binderfs_binder_device_create(struct inode *ref_inode, + struct binderfs_device __user *userp, + struct binderfs_device *req) +{ + int minor, ret; + struct dentry *dentry, *root; + struct binder_device *device = NULL; + rust_binder_context ctx = NULL; + struct inode *inode = NULL; + struct super_block *sb = ref_inode->i_sb; + struct binderfs_info *info = sb->s_fs_info; +#if defined(CONFIG_IPC_NS) + bool use_reserve = (info->ipc_ns == &init_ipc_ns); +#else + bool use_reserve = true; +#endif + + /* Reserve new minor number for the new device. */ + mutex_lock(&binderfs_minors_mutex); + if (++info->device_count <= info->mount_opts.max) + minor = ida_alloc_max(&binderfs_minors, + use_reserve ? BINDERFS_MAX_MINOR : + BINDERFS_MAX_MINOR_CAPPED, + GFP_KERNEL); + else + minor = -ENOSPC; + if (minor < 0) { + --info->device_count; + mutex_unlock(&binderfs_minors_mutex); + return minor; + } + mutex_unlock(&binderfs_minors_mutex); + + ret = -ENOMEM; + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + goto err; + + req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */ + + ctx = rust_binder_new_context(req->name); + if (!ctx) + goto err; + + inode = new_inode(sb); + if (!inode) + goto err; + + inode->i_ino = minor + INODE_OFFSET; + simple_inode_init_ts(inode); + init_special_inode(inode, S_IFCHR | 0600, + MKDEV(MAJOR(binderfs_dev), minor)); + inode->i_fop = &rust_binder_fops; + inode->i_uid = info->root_uid; + inode->i_gid = info->root_gid; + + req->major = MAJOR(binderfs_dev); + req->minor = minor; + device->ctx = ctx; + device->minor = minor; + + if (userp && copy_to_user(userp, req, sizeof(*req))) { + ret = -EFAULT; + goto err; + } + + root = sb->s_root; + inode_lock(d_inode(root)); + + /* look it up */ + dentry = lookup_noperm(&QSTR(req->name), root); + if (IS_ERR(dentry)) { + inode_unlock(d_inode(root)); + ret = PTR_ERR(dentry); + goto err; + } + + if (d_really_is_positive(dentry)) { + /* already exists */ + dput(dentry); + inode_unlock(d_inode(root)); + ret = -EEXIST; + goto err; + } + + inode->i_private = device; + d_instantiate(dentry, inode); + fsnotify_create(root->d_inode, dentry); + inode_unlock(d_inode(root)); + + return 0; + +err: + kfree(device); + rust_binder_remove_context(ctx); + mutex_lock(&binderfs_minors_mutex); + --info->device_count; + ida_free(&binderfs_minors, minor); + mutex_unlock(&binderfs_minors_mutex); + iput(inode); + + return ret; +} + +/** + * binder_ctl_ioctl - handle binder device node allocation requests + * + * The request handler for the binder-control device. All requests operate on + * the binderfs mount the binder-control device resides in: + * - BINDER_CTL_ADD + * Allocate a new binder device. + * + * Return: %0 on success, negative errno on failure. + */ +static long binder_ctl_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret = -EINVAL; + struct inode *inode = file_inode(file); + struct binderfs_device __user *device = (struct binderfs_device __user *)arg; + struct binderfs_device device_req; + + switch (cmd) { + case BINDER_CTL_ADD: + ret = copy_from_user(&device_req, device, sizeof(device_req)); + if (ret) { + ret = -EFAULT; + break; + } + + ret = binderfs_binder_device_create(inode, device, &device_req); + break; + default: + break; + } + + return ret; +} + +static void binderfs_evict_inode(struct inode *inode) +{ + struct binder_device *device = inode->i_private; + struct binderfs_info *info = BINDERFS_SB(inode->i_sb); + + clear_inode(inode); + + if (!S_ISCHR(inode->i_mode) || !device) + return; + + mutex_lock(&binderfs_minors_mutex); + --info->device_count; + ida_free(&binderfs_minors, device->minor); + mutex_unlock(&binderfs_minors_mutex); + + /* ctx is null for binder-control, but this function ignores null pointers */ + rust_binder_remove_context(device->ctx); + + kfree(device); +} + +static int binderfs_fs_context_parse_param(struct fs_context *fc, + struct fs_parameter *param) +{ + int opt; + struct binderfs_mount_opts *ctx = fc->fs_private; + struct fs_parse_result result; + + opt = fs_parse(fc, binderfs_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_max: + if (result.uint_32 > BINDERFS_MAX_MINOR) + return invalfc(fc, "Bad value for '%s'", param->key); + + ctx->max = result.uint_32; + break; + case Opt_stats_mode: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + ctx->stats_mode = result.uint_32; + break; + default: + return invalfc(fc, "Unsupported parameter '%s'", param->key); + } + + return 0; +} + +static int binderfs_fs_context_reconfigure(struct fs_context *fc) +{ + struct binderfs_mount_opts *ctx = fc->fs_private; + struct binderfs_info *info = BINDERFS_SB(fc->root->d_sb); + + if (info->mount_opts.stats_mode != ctx->stats_mode) + return invalfc(fc, "Binderfs stats mode cannot be changed during a remount"); + + info->mount_opts.stats_mode = ctx->stats_mode; + info->mount_opts.max = ctx->max; + return 0; +} + +static int binderfs_show_options(struct seq_file *seq, struct dentry *root) +{ + struct binderfs_info *info = BINDERFS_SB(root->d_sb); + + if (info->mount_opts.max <= BINDERFS_MAX_MINOR) + seq_printf(seq, ",max=%d", info->mount_opts.max); + + switch (info->mount_opts.stats_mode) { + case binderfs_stats_mode_unset: + break; + case binderfs_stats_mode_global: + seq_puts(seq, ",stats=global"); + break; + } + + return 0; +} + +static const struct super_operations binderfs_super_ops = { + .evict_inode = binderfs_evict_inode, + .show_options = binderfs_show_options, + .statfs = simple_statfs, +}; + +static inline bool is_binderfs_control_device(const struct dentry *dentry) +{ + struct binderfs_info *info = dentry->d_sb->s_fs_info; + + return info->control_dentry == dentry; +} + +static int binderfs_rename(struct mnt_idmap *idmap, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + if (is_binderfs_control_device(old_dentry) || + is_binderfs_control_device(new_dentry)) + return -EPERM; + + return simple_rename(idmap, old_dir, old_dentry, new_dir, + new_dentry, flags); +} + +static int binderfs_unlink(struct inode *dir, struct dentry *dentry) +{ + if (is_binderfs_control_device(dentry)) + return -EPERM; + + return simple_unlink(dir, dentry); +} + +static const struct file_operations binder_ctl_fops = { + .owner = THIS_MODULE, + .open = nonseekable_open, + .unlocked_ioctl = binder_ctl_ioctl, + .compat_ioctl = binder_ctl_ioctl, + .llseek = noop_llseek, +}; + +/** + * binderfs_binder_ctl_create - create a new binder-control device + * @sb: super block of the binderfs mount + * + * This function creates a new binder-control device node in the binderfs mount + * referred to by @sb. + * + * Return: 0 on success, negative errno on failure + */ +static int binderfs_binder_ctl_create(struct super_block *sb) +{ + int minor, ret; + struct dentry *dentry; + struct binder_device *device; + struct inode *inode = NULL; + struct dentry *root = sb->s_root; + struct binderfs_info *info = sb->s_fs_info; +#if defined(CONFIG_IPC_NS) + bool use_reserve = (info->ipc_ns == &init_ipc_ns); +#else + bool use_reserve = true; +#endif + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + return -ENOMEM; + + /* If we have already created a binder-control node, return. */ + if (info->control_dentry) { + ret = 0; + goto out; + } + + ret = -ENOMEM; + inode = new_inode(sb); + if (!inode) + goto out; + + /* Reserve a new minor number for the new device. */ + mutex_lock(&binderfs_minors_mutex); + minor = ida_alloc_max(&binderfs_minors, + use_reserve ? BINDERFS_MAX_MINOR : + BINDERFS_MAX_MINOR_CAPPED, + GFP_KERNEL); + mutex_unlock(&binderfs_minors_mutex); + if (minor < 0) { + ret = minor; + goto out; + } + + inode->i_ino = SECOND_INODE; + simple_inode_init_ts(inode); + init_special_inode(inode, S_IFCHR | 0600, + MKDEV(MAJOR(binderfs_dev), minor)); + inode->i_fop = &binder_ctl_fops; + inode->i_uid = info->root_uid; + inode->i_gid = info->root_gid; + + device->minor = minor; + device->ctx = NULL; + + dentry = d_alloc_name(root, "binder-control"); + if (!dentry) + goto out; + + inode->i_private = device; + info->control_dentry = dentry; + d_add(dentry, inode); + + return 0; + +out: + kfree(device); + iput(inode); + + return ret; +} + +static const struct inode_operations binderfs_dir_inode_operations = { + .lookup = simple_lookup, + .rename = binderfs_rename, + .unlink = binderfs_unlink, +}; + +static struct inode *binderfs_make_inode(struct super_block *sb, int mode) +{ + struct inode *ret; + + ret = new_inode(sb); + if (ret) { + ret->i_ino = iunique(sb, BINDERFS_MAX_MINOR + INODE_OFFSET); + ret->i_mode = mode; + simple_inode_init_ts(ret); + } + return ret; +} + +static struct dentry *binderfs_create_dentry(struct dentry *parent, + const char *name) +{ + struct dentry *dentry; + + dentry = lookup_noperm(&QSTR(name), parent); + if (IS_ERR(dentry)) + return dentry; + + /* Return error if the file/dir already exists. */ + if (d_really_is_positive(dentry)) { + dput(dentry); + return ERR_PTR(-EEXIST); + } + + return dentry; +} + +void rust_binderfs_remove_file(struct dentry *dentry) +{ + struct inode *parent_inode; + + parent_inode = d_inode(dentry->d_parent); + inode_lock(parent_inode); + if (simple_positive(dentry)) { + dget(dentry); + simple_unlink(parent_inode, dentry); + d_delete(dentry); + dput(dentry); + } + inode_unlock(parent_inode); +} + +static struct dentry *rust_binderfs_create_file(struct dentry *parent, const char *name, + const struct file_operations *fops, + void *data) +{ + struct dentry *dentry; + struct inode *new_inode, *parent_inode; + struct super_block *sb; + + parent_inode = d_inode(parent); + inode_lock(parent_inode); + + dentry = binderfs_create_dentry(parent, name); + if (IS_ERR(dentry)) + goto out; + + sb = parent_inode->i_sb; + new_inode = binderfs_make_inode(sb, S_IFREG | 0444); + if (!new_inode) { + dput(dentry); + dentry = ERR_PTR(-ENOMEM); + goto out; + } + + new_inode->i_fop = fops; + new_inode->i_private = data; + d_instantiate(dentry, new_inode); + fsnotify_create(parent_inode, dentry); + +out: + inode_unlock(parent_inode); + return dentry; +} + +struct dentry *rust_binderfs_create_proc_file(struct inode *nodp, int pid) +{ + struct binderfs_info *info = nodp->i_sb->s_fs_info; + struct dentry *dir = info->proc_log_dir; + char strbuf[20 + 1]; + void *data = (void *)(unsigned long) pid; + + if (!dir) + return NULL; + + snprintf(strbuf, sizeof(strbuf), "%u", pid); + return rust_binderfs_create_file(dir, strbuf, &rust_binder_proc_fops, data); +} + +static struct dentry *binderfs_create_dir(struct dentry *parent, + const char *name) +{ + struct dentry *dentry; + struct inode *new_inode, *parent_inode; + struct super_block *sb; + + parent_inode = d_inode(parent); + inode_lock(parent_inode); + + dentry = binderfs_create_dentry(parent, name); + if (IS_ERR(dentry)) + goto out; + + sb = parent_inode->i_sb; + new_inode = binderfs_make_inode(sb, S_IFDIR | 0755); + if (!new_inode) { + dput(dentry); + dentry = ERR_PTR(-ENOMEM); + goto out; + } + + new_inode->i_fop = &simple_dir_operations; + new_inode->i_op = &simple_dir_inode_operations; + + set_nlink(new_inode, 2); + d_instantiate(dentry, new_inode); + inc_nlink(parent_inode); + fsnotify_mkdir(parent_inode, dentry); + +out: + inode_unlock(parent_inode); + return dentry; +} + +static int binder_features_show(struct seq_file *m, void *unused) +{ + bool *feature = m->private; + + seq_printf(m, "%d\n", *feature); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(binder_features); + +static int init_binder_features(struct super_block *sb) +{ + struct dentry *dentry, *dir; + + dir = binderfs_create_dir(sb->s_root, "features"); + if (IS_ERR(dir)) + return PTR_ERR(dir); + + dentry = rust_binderfs_create_file(dir, "oneway_spam_detection", + &binder_features_fops, + &binder_features.oneway_spam_detection); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + dentry = rust_binderfs_create_file(dir, "extended_error", + &binder_features_fops, + &binder_features.extended_error); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + dentry = rust_binderfs_create_file(dir, "freeze_notification", + &binder_features_fops, + &binder_features.freeze_notification); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + return 0; +} + +static int init_binder_logs(struct super_block *sb) +{ + struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir; + struct binderfs_info *info; + int ret = 0; + + binder_logs_root_dir = binderfs_create_dir(sb->s_root, + "binder_logs"); + if (IS_ERR(binder_logs_root_dir)) { + ret = PTR_ERR(binder_logs_root_dir); + goto out; + } + + dentry = rust_binderfs_create_file(binder_logs_root_dir, "stats", + &rust_binder_stats_fops, NULL); + if (IS_ERR(dentry)) { + ret = PTR_ERR(dentry); + goto out; + } + + dentry = rust_binderfs_create_file(binder_logs_root_dir, "state", + &rust_binder_state_fops, NULL); + if (IS_ERR(dentry)) { + ret = PTR_ERR(dentry); + goto out; + } + + dentry = rust_binderfs_create_file(binder_logs_root_dir, "transactions", + &rust_binder_transactions_fops, NULL); + if (IS_ERR(dentry)) { + ret = PTR_ERR(dentry); + goto out; + } + + proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc"); + if (IS_ERR(proc_log_dir)) { + ret = PTR_ERR(proc_log_dir); + goto out; + } + info = sb->s_fs_info; + info->proc_log_dir = proc_log_dir; + +out: + return ret; +} + +static int binderfs_fill_super(struct super_block *sb, struct fs_context *fc) +{ + int ret; + struct binderfs_info *info; + struct binderfs_mount_opts *ctx = fc->fs_private; + struct inode *inode = NULL; + struct binderfs_device device_info = {}; + const char *name; + size_t len; + + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; + + /* + * The binderfs filesystem can be mounted by userns root in a + * non-initial userns. By default such mounts have the SB_I_NODEV flag + * set in s_iflags to prevent security issues where userns root can + * just create random device nodes via mknod() since it owns the + * filesystem mount. But binderfs does not allow to create any files + * including devices nodes. The only way to create binder devices nodes + * is through the binder-control device which userns root is explicitly + * allowed to do. So removing the SB_I_NODEV flag from s_iflags is both + * necessary and safe. + */ + sb->s_iflags &= ~SB_I_NODEV; + sb->s_iflags |= SB_I_NOEXEC; + sb->s_magic = RUST_BINDERFS_SUPER_MAGIC; + sb->s_op = &binderfs_super_ops; + sb->s_time_gran = 1; + + sb->s_fs_info = kzalloc(sizeof(struct binderfs_info), GFP_KERNEL); + if (!sb->s_fs_info) + return -ENOMEM; + info = sb->s_fs_info; + + info->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns); + + info->root_gid = make_kgid(sb->s_user_ns, 0); + if (!gid_valid(info->root_gid)) + info->root_gid = GLOBAL_ROOT_GID; + info->root_uid = make_kuid(sb->s_user_ns, 0); + if (!uid_valid(info->root_uid)) + info->root_uid = GLOBAL_ROOT_UID; + info->mount_opts.max = ctx->max; + info->mount_opts.stats_mode = ctx->stats_mode; + + inode = new_inode(sb); + if (!inode) + return -ENOMEM; + + inode->i_ino = FIRST_INODE; + inode->i_fop = &simple_dir_operations; + inode->i_mode = S_IFDIR | 0755; + simple_inode_init_ts(inode); + inode->i_op = &binderfs_dir_inode_operations; + set_nlink(inode, 2); + + sb->s_root = d_make_root(inode); + if (!sb->s_root) + return -ENOMEM; + + ret = binderfs_binder_ctl_create(sb); + if (ret) + return ret; + + name = rust_binder_devices_param; + for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) { + strscpy(device_info.name, name, len + 1); + ret = binderfs_binder_device_create(inode, NULL, &device_info); + if (ret) + return ret; + name += len; + if (*name == ',') + name++; + } + + ret = init_binder_features(sb); + if (ret) + return ret; + + if (info->mount_opts.stats_mode == binderfs_stats_mode_global) + return init_binder_logs(sb); + + return 0; +} + +static int binderfs_fs_context_get_tree(struct fs_context *fc) +{ + return get_tree_nodev(fc, binderfs_fill_super); +} + +static void binderfs_fs_context_free(struct fs_context *fc) +{ + struct binderfs_mount_opts *ctx = fc->fs_private; + + kfree(ctx); +} + +static const struct fs_context_operations binderfs_fs_context_ops = { + .free = binderfs_fs_context_free, + .get_tree = binderfs_fs_context_get_tree, + .parse_param = binderfs_fs_context_parse_param, + .reconfigure = binderfs_fs_context_reconfigure, +}; + +static int binderfs_init_fs_context(struct fs_context *fc) +{ + struct binderfs_mount_opts *ctx; + + ctx = kzalloc(sizeof(struct binderfs_mount_opts), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->max = BINDERFS_MAX_MINOR; + ctx->stats_mode = binderfs_stats_mode_unset; + + fc->fs_private = ctx; + fc->ops = &binderfs_fs_context_ops; + + return 0; +} + +static void binderfs_kill_super(struct super_block *sb) +{ + struct binderfs_info *info = sb->s_fs_info; + + /* + * During inode eviction struct binderfs_info is needed. + * So first wipe the super_block then free struct binderfs_info. + */ + kill_litter_super(sb); + + if (info && info->ipc_ns) + put_ipc_ns(info->ipc_ns); + + kfree(info); +} + +static struct file_system_type binder_fs_type = { + .name = "binder", + .init_fs_context = binderfs_init_fs_context, + .parameters = binderfs_fs_parameters, + .kill_sb = binderfs_kill_super, + .fs_flags = FS_USERNS_MOUNT, +}; + +int init_rust_binderfs(void) +{ + int ret; + const char *name; + size_t len; + + /* Verify that the default binderfs device names are valid. */ + name = rust_binder_devices_param; + for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) { + if (len > BINDERFS_MAX_NAME) + return -E2BIG; + name += len; + if (*name == ',') + name++; + } + + /* Allocate new major number for binderfs. */ + ret = alloc_chrdev_region(&binderfs_dev, 0, BINDERFS_MAX_MINOR, + "rust_binder"); + if (ret) + return ret; + + ret = register_filesystem(&binder_fs_type); + if (ret) { + unregister_chrdev_region(binderfs_dev, BINDERFS_MAX_MINOR); + return ret; + } + + return ret; +} diff --git a/drivers/android/binder/stats.rs b/drivers/android/binder/stats.rs new file mode 100644 index 000000000000..a83ec111d2cb --- /dev/null +++ b/drivers/android/binder/stats.rs @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! Keep track of statistics for binder_logs. + +use crate::defs::*; +use core::sync::atomic::{AtomicU32, Ordering::Relaxed}; +use kernel::{ioctl::_IOC_NR, seq_file::SeqFile, seq_print}; + +const BC_COUNT: usize = _IOC_NR(BC_REPLY_SG) as usize + 1; +const BR_COUNT: usize = _IOC_NR(BR_TRANSACTION_PENDING_FROZEN) as usize + 1; + +pub(crate) static GLOBAL_STATS: BinderStats = BinderStats::new(); + +pub(crate) struct BinderStats { + bc: [AtomicU32; BC_COUNT], + br: [AtomicU32; BR_COUNT], +} + +impl BinderStats { + pub(crate) const fn new() -> Self { + #[expect(clippy::declare_interior_mutable_const)] + const ZERO: AtomicU32 = AtomicU32::new(0); + + Self { + bc: [ZERO; BC_COUNT], + br: [ZERO; BR_COUNT], + } + } + + pub(crate) fn inc_bc(&self, bc: u32) { + let idx = _IOC_NR(bc) as usize; + if let Some(bc_ref) = self.bc.get(idx) { + bc_ref.fetch_add(1, Relaxed); + } + } + + pub(crate) fn inc_br(&self, br: u32) { + let idx = _IOC_NR(br) as usize; + if let Some(br_ref) = self.br.get(idx) { + br_ref.fetch_add(1, Relaxed); + } + } + + pub(crate) fn debug_print(&self, prefix: &str, m: &SeqFile) { + for (i, cnt) in self.bc.iter().enumerate() { + let cnt = cnt.load(Relaxed); + if cnt > 0 { + seq_print!(m, "{}{}: {}\n", prefix, command_string(i), cnt); + } + } + for (i, cnt) in self.br.iter().enumerate() { + let cnt = cnt.load(Relaxed); + if cnt > 0 { + seq_print!(m, "{}{}: {}\n", prefix, return_string(i), cnt); + } + } + } +} + +mod strings { + use core::str::from_utf8_unchecked; + use kernel::str::CStr; + + extern "C" { + static binder_command_strings: [*const u8; super::BC_COUNT]; + static binder_return_strings: [*const u8; super::BR_COUNT]; + } + + pub(super) fn command_string(i: usize) -> &'static str { + // SAFETY: Accessing `binder_command_strings` is always safe. + let c_str_ptr = unsafe { binder_command_strings[i] }; + // SAFETY: The `binder_command_strings` array only contains nul-terminated strings. + let bytes = unsafe { CStr::from_char_ptr(c_str_ptr) }.as_bytes(); + // SAFETY: The `binder_command_strings` array only contains strings with ascii-chars. + unsafe { from_utf8_unchecked(bytes) } + } + + pub(super) fn return_string(i: usize) -> &'static str { + // SAFETY: Accessing `binder_return_strings` is always safe. + let c_str_ptr = unsafe { binder_return_strings[i] }; + // SAFETY: The `binder_command_strings` array only contains nul-terminated strings. + let bytes = unsafe { CStr::from_char_ptr(c_str_ptr) }.as_bytes(); + // SAFETY: The `binder_command_strings` array only contains strings with ascii-chars. + unsafe { from_utf8_unchecked(bytes) } + } +} +use strings::{command_string, return_string}; diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs new file mode 100644 index 000000000000..7e34ccd394f8 --- /dev/null +++ b/drivers/android/binder/thread.rs @@ -0,0 +1,1596 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! This module defines the `Thread` type, which represents a userspace thread that is using +//! binder. +//! +//! The `Process` object stores all of the threads in an rb tree. + +use kernel::{ + bindings, + fs::{File, LocalFile}, + list::{AtomicTracker, List, ListArc, ListLinks, TryNewListArc}, + prelude::*, + security, + seq_file::SeqFile, + seq_print, + sync::poll::{PollCondVar, PollTable}, + sync::{Arc, SpinLock}, + task::Task, + types::ARef, + uaccess::UserSlice, + uapi, +}; + +use crate::{ + allocation::{Allocation, AllocationView, BinderObject, BinderObjectRef, NewAllocation}, + defs::*, + error::BinderResult, + process::{GetWorkOrRegister, Process}, + ptr_align, + stats::GLOBAL_STATS, + transaction::Transaction, + BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverCode, DeliverToRead, +}; + +use core::{ + mem::size_of, + sync::atomic::{AtomicU32, Ordering}, +}; + +/// Stores the layout of the scatter-gather entries. This is used during the `translate_objects` +/// call and is discarded when it returns. +struct ScatterGatherState { + /// A struct that tracks the amount of unused buffer space. + unused_buffer_space: UnusedBufferSpace, + /// Scatter-gather entries to copy. + sg_entries: KVec<ScatterGatherEntry>, + /// Indexes into `sg_entries` corresponding to the last binder_buffer_object that + /// was processed and all of its ancestors. The array is in sorted order. + ancestors: KVec<usize>, +} + +/// This entry specifies an additional buffer that should be copied using the scatter-gather +/// mechanism. +struct ScatterGatherEntry { + /// The index in the offset array of the BINDER_TYPE_PTR that this entry originates from. + obj_index: usize, + /// Offset in target buffer. + offset: usize, + /// User address in source buffer. + sender_uaddr: usize, + /// Number of bytes to copy. + length: usize, + /// The minimum offset of the next fixup in this buffer. + fixup_min_offset: usize, + /// The offsets within this buffer that contain pointers which should be translated. + pointer_fixups: KVec<PointerFixupEntry>, +} + +/// This entry specifies that a fixup should happen at `target_offset` of the +/// buffer. If `skip` is nonzero, then the fixup is a `binder_fd_array_object` +/// and is applied later. Otherwise if `skip` is zero, then the size of the +/// fixup is `sizeof::<u64>()` and `pointer_value` is written to the buffer. +struct PointerFixupEntry { + /// The number of bytes to skip, or zero for a `binder_buffer_object` fixup. + skip: usize, + /// The translated pointer to write when `skip` is zero. + pointer_value: u64, + /// The offset at which the value should be written. The offset is relative + /// to the original buffer. + target_offset: usize, +} + +/// Return type of `apply_and_validate_fixup_in_parent`. +struct ParentFixupInfo { + /// The index of the parent buffer in `sg_entries`. + parent_sg_index: usize, + /// The number of ancestors of the buffer. + /// + /// The buffer is considered an ancestor of itself, so this is always at + /// least one. + num_ancestors: usize, + /// New value of `fixup_min_offset` if this fixup is applied. + new_min_offset: usize, + /// The offset of the fixup in the target buffer. + target_offset: usize, +} + +impl ScatterGatherState { + /// Called when a `binder_buffer_object` or `binder_fd_array_object` tries + /// to access a region in its parent buffer. These accesses have various + /// restrictions, which this method verifies. + /// + /// The `parent_offset` and `length` arguments describe the offset and + /// length of the access in the parent buffer. + /// + /// # Detailed restrictions + /// + /// Obviously the fixup must be in-bounds for the parent buffer. + /// + /// For safety reasons, we only allow fixups inside a buffer to happen + /// at increasing offsets; additionally, we only allow fixup on the last + /// buffer object that was verified, or one of its parents. + /// + /// Example of what is allowed: + /// + /// A + /// B (parent = A, offset = 0) + /// C (parent = A, offset = 16) + /// D (parent = C, offset = 0) + /// E (parent = A, offset = 32) // min_offset is 16 (C.parent_offset) + /// + /// Examples of what is not allowed: + /// + /// Decreasing offsets within the same parent: + /// A + /// C (parent = A, offset = 16) + /// B (parent = A, offset = 0) // decreasing offset within A + /// + /// Arcerring to a parent that wasn't the last object or any of its parents: + /// A + /// B (parent = A, offset = 0) + /// C (parent = A, offset = 0) + /// C (parent = A, offset = 16) + /// D (parent = B, offset = 0) // B is not A or any of A's parents + fn validate_parent_fixup( + &self, + parent: usize, + parent_offset: usize, + length: usize, + ) -> Result<ParentFixupInfo> { + // Using `position` would also be correct, but `rposition` avoids + // quadratic running times. + let ancestors_i = self + .ancestors + .iter() + .copied() + .rposition(|sg_idx| self.sg_entries[sg_idx].obj_index == parent) + .ok_or(EINVAL)?; + let sg_idx = self.ancestors[ancestors_i]; + let sg_entry = match self.sg_entries.get(sg_idx) { + Some(sg_entry) => sg_entry, + None => { + pr_err!( + "self.ancestors[{}] is {}, but self.sg_entries.len() is {}", + ancestors_i, + sg_idx, + self.sg_entries.len() + ); + return Err(EINVAL); + } + }; + if sg_entry.fixup_min_offset > parent_offset { + pr_warn!( + "validate_parent_fixup: fixup_min_offset={}, parent_offset={}", + sg_entry.fixup_min_offset, + parent_offset + ); + return Err(EINVAL); + } + let new_min_offset = parent_offset.checked_add(length).ok_or(EINVAL)?; + if new_min_offset > sg_entry.length { + pr_warn!( + "validate_parent_fixup: new_min_offset={}, sg_entry.length={}", + new_min_offset, + sg_entry.length + ); + return Err(EINVAL); + } + let target_offset = sg_entry.offset.checked_add(parent_offset).ok_or(EINVAL)?; + // The `ancestors_i + 1` operation can't overflow since the output of the addition is at + // most `self.ancestors.len()`, which also fits in a usize. + Ok(ParentFixupInfo { + parent_sg_index: sg_idx, + num_ancestors: ancestors_i + 1, + new_min_offset, + target_offset, + }) + } +} + +/// Keeps track of how much unused buffer space is left. The initial amount is the number of bytes +/// requested by the user using the `buffers_size` field of `binder_transaction_data_sg`. Each time +/// we translate an object of type `BINDER_TYPE_PTR`, some of the unused buffer space is consumed. +struct UnusedBufferSpace { + /// The start of the remaining space. + offset: usize, + /// The end of the remaining space. + limit: usize, +} +impl UnusedBufferSpace { + /// Claim the next `size` bytes from the unused buffer space. The offset for the claimed chunk + /// into the buffer is returned. + fn claim_next(&mut self, size: usize) -> Result<usize> { + // We require every chunk to be aligned. + let size = ptr_align(size).ok_or(EINVAL)?; + let new_offset = self.offset.checked_add(size).ok_or(EINVAL)?; + + if new_offset <= self.limit { + let offset = self.offset; + self.offset = new_offset; + Ok(offset) + } else { + Err(EINVAL) + } + } +} + +pub(crate) enum PushWorkRes { + Ok, + FailedDead(DLArc<dyn DeliverToRead>), +} + +impl PushWorkRes { + fn is_ok(&self) -> bool { + match self { + PushWorkRes::Ok => true, + PushWorkRes::FailedDead(_) => false, + } + } +} + +/// The fields of `Thread` protected by the spinlock. +struct InnerThread { + /// Determines the looper state of the thread. It is a bit-wise combination of the constants + /// prefixed with `LOOPER_`. + looper_flags: u32, + + /// Determines whether the looper should return. + looper_need_return: bool, + + /// Determines if thread is dead. + is_dead: bool, + + /// Work item used to deliver error codes to the thread that started a transaction. Stored here + /// so that it can be reused. + reply_work: DArc<ThreadError>, + + /// Work item used to deliver error codes to the current thread. Stored here so that it can be + /// reused. + return_work: DArc<ThreadError>, + + /// Determines whether the work list below should be processed. When set to false, `work_list` + /// is treated as if it were empty. + process_work_list: bool, + /// List of work items to deliver to userspace. + work_list: List<DTRWrap<dyn DeliverToRead>>, + current_transaction: Option<DArc<Transaction>>, + + /// Extended error information for this thread. + extended_error: ExtendedError, +} + +const LOOPER_REGISTERED: u32 = 0x01; +const LOOPER_ENTERED: u32 = 0x02; +const LOOPER_EXITED: u32 = 0x04; +const LOOPER_INVALID: u32 = 0x08; +const LOOPER_WAITING: u32 = 0x10; +const LOOPER_WAITING_PROC: u32 = 0x20; +const LOOPER_POLL: u32 = 0x40; + +impl InnerThread { + fn new() -> Result<Self> { + fn next_err_id() -> u32 { + static EE_ID: AtomicU32 = AtomicU32::new(0); + EE_ID.fetch_add(1, Ordering::Relaxed) + } + + Ok(Self { + looper_flags: 0, + looper_need_return: false, + is_dead: false, + process_work_list: false, + reply_work: ThreadError::try_new()?, + return_work: ThreadError::try_new()?, + work_list: List::new(), + current_transaction: None, + extended_error: ExtendedError::new(next_err_id(), BR_OK, 0), + }) + } + + fn pop_work(&mut self) -> Option<DLArc<dyn DeliverToRead>> { + if !self.process_work_list { + return None; + } + + let ret = self.work_list.pop_front(); + self.process_work_list = !self.work_list.is_empty(); + ret + } + + fn push_work(&mut self, work: DLArc<dyn DeliverToRead>) -> PushWorkRes { + if self.is_dead { + PushWorkRes::FailedDead(work) + } else { + self.work_list.push_back(work); + self.process_work_list = true; + PushWorkRes::Ok + } + } + + fn push_reply_work(&mut self, code: u32) { + if let Ok(work) = ListArc::try_from_arc(self.reply_work.clone()) { + work.set_error_code(code); + self.push_work(work); + } else { + pr_warn!("Thread reply work is already in use."); + } + } + + fn push_return_work(&mut self, reply: u32) { + if let Ok(work) = ListArc::try_from_arc(self.return_work.clone()) { + work.set_error_code(reply); + self.push_work(work); + } else { + pr_warn!("Thread return work is already in use."); + } + } + + /// Used to push work items that do not need to be processed immediately and can wait until the + /// thread gets another work item. + fn push_work_deferred(&mut self, work: DLArc<dyn DeliverToRead>) { + self.work_list.push_back(work); + } + + /// Fetches the transaction this thread can reply to. If the thread has a pending transaction + /// (that it could respond to) but it has also issued a transaction, it must first wait for the + /// previously-issued transaction to complete. + /// + /// The `thread` parameter should be the thread containing this `ThreadInner`. + fn pop_transaction_to_reply(&mut self, thread: &Thread) -> Result<DArc<Transaction>> { + let transaction = self.current_transaction.take().ok_or(EINVAL)?; + if core::ptr::eq(thread, transaction.from.as_ref()) { + self.current_transaction = Some(transaction); + return Err(EINVAL); + } + // Find a new current transaction for this thread. + self.current_transaction = transaction.find_from(thread).cloned(); + Ok(transaction) + } + + fn pop_transaction_replied(&mut self, transaction: &DArc<Transaction>) -> bool { + match self.current_transaction.take() { + None => false, + Some(old) => { + if !Arc::ptr_eq(transaction, &old) { + self.current_transaction = Some(old); + return false; + } + self.current_transaction = old.clone_next(); + true + } + } + } + + fn looper_enter(&mut self) { + self.looper_flags |= LOOPER_ENTERED; + if self.looper_flags & LOOPER_REGISTERED != 0 { + self.looper_flags |= LOOPER_INVALID; + } + } + + fn looper_register(&mut self, valid: bool) { + self.looper_flags |= LOOPER_REGISTERED; + if !valid || self.looper_flags & LOOPER_ENTERED != 0 { + self.looper_flags |= LOOPER_INVALID; + } + } + + fn looper_exit(&mut self) { + self.looper_flags |= LOOPER_EXITED; + } + + /// Determines whether the thread is part of a pool, i.e., if it is a looper. + fn is_looper(&self) -> bool { + self.looper_flags & (LOOPER_ENTERED | LOOPER_REGISTERED) != 0 + } + + /// Determines whether the thread should attempt to fetch work items from the process queue. + /// This is generally case when the thread is registered as a looper and not part of a + /// transaction stack. But if there is local work, we want to return to userspace before we + /// deliver any remote work. + fn should_use_process_work_queue(&self) -> bool { + self.current_transaction.is_none() && !self.process_work_list && self.is_looper() + } + + fn poll(&mut self) -> u32 { + self.looper_flags |= LOOPER_POLL; + if self.process_work_list || self.looper_need_return { + bindings::POLLIN + } else { + 0 + } + } +} + +/// This represents a thread that's used with binder. +#[pin_data] +pub(crate) struct Thread { + pub(crate) id: i32, + pub(crate) process: Arc<Process>, + pub(crate) task: ARef<Task>, + #[pin] + inner: SpinLock<InnerThread>, + #[pin] + work_condvar: PollCondVar, + /// Used to insert this thread into the process' `ready_threads` list. + /// + /// INVARIANT: May never be used for any other list than the `self.process.ready_threads`. + #[pin] + links: ListLinks, + #[pin] + links_track: AtomicTracker, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for Thread { + tracked_by links_track: AtomicTracker; + } +} +kernel::list::impl_list_item! { + impl ListItem<0> for Thread { + using ListLinks { self.links }; + } +} + +impl Thread { + pub(crate) fn new(id: i32, process: Arc<Process>) -> Result<Arc<Self>> { + let inner = InnerThread::new()?; + + Arc::pin_init( + try_pin_init!(Thread { + id, + process, + task: ARef::from(&**kernel::current!()), + inner <- kernel::new_spinlock!(inner, "Thread::inner"), + work_condvar <- kernel::new_poll_condvar!("Thread::work_condvar"), + links <- ListLinks::new(), + links_track <- AtomicTracker::new(), + }), + GFP_KERNEL, + ) + } + + #[inline(never)] + pub(crate) fn debug_print(self: &Arc<Self>, m: &SeqFile, print_all: bool) -> Result<()> { + let inner = self.inner.lock(); + + if print_all || inner.current_transaction.is_some() || !inner.work_list.is_empty() { + seq_print!( + m, + " thread {}: l {:02x} need_return {}\n", + self.id, + inner.looper_flags, + inner.looper_need_return, + ); + } + + let mut t_opt = inner.current_transaction.as_ref(); + while let Some(t) = t_opt { + if Arc::ptr_eq(&t.from, self) { + t.debug_print_inner(m, " outgoing transaction "); + t_opt = t.from_parent.as_ref(); + } else if Arc::ptr_eq(&t.to, &self.process) { + t.debug_print_inner(m, " incoming transaction "); + t_opt = t.find_from(self); + } else { + t.debug_print_inner(m, " bad transaction "); + t_opt = None; + } + } + + for work in &inner.work_list { + work.debug_print(m, " ", " pending transaction ")?; + } + Ok(()) + } + + pub(crate) fn get_extended_error(&self, data: UserSlice) -> Result { + let mut writer = data.writer(); + let ee = self.inner.lock().extended_error; + writer.write(&ee)?; + Ok(()) + } + + pub(crate) fn set_current_transaction(&self, transaction: DArc<Transaction>) { + self.inner.lock().current_transaction = Some(transaction); + } + + pub(crate) fn has_current_transaction(&self) -> bool { + self.inner.lock().current_transaction.is_some() + } + + /// Attempts to fetch a work item from the thread-local queue. The behaviour if the queue is + /// empty depends on `wait`: if it is true, the function waits for some work to be queued (or a + /// signal); otherwise it returns indicating that none is available. + fn get_work_local(self: &Arc<Self>, wait: bool) -> Result<Option<DLArc<dyn DeliverToRead>>> { + { + let mut inner = self.inner.lock(); + if inner.looper_need_return { + return Ok(inner.pop_work()); + } + } + + // Try once if the caller does not want to wait. + if !wait { + return self.inner.lock().pop_work().ok_or(EAGAIN).map(Some); + } + + // Loop waiting only on the local queue (i.e., not registering with the process queue). + let mut inner = self.inner.lock(); + loop { + if let Some(work) = inner.pop_work() { + return Ok(Some(work)); + } + + inner.looper_flags |= LOOPER_WAITING; + let signal_pending = self.work_condvar.wait_interruptible_freezable(&mut inner); + inner.looper_flags &= !LOOPER_WAITING; + + if signal_pending { + return Err(EINTR); + } + if inner.looper_need_return { + return Ok(None); + } + } + } + + /// Attempts to fetch a work item from the thread-local queue, falling back to the process-wide + /// queue if none is available locally. + /// + /// This must only be called when the thread is not participating in a transaction chain. If it + /// is, the local version (`get_work_local`) should be used instead. + fn get_work(self: &Arc<Self>, wait: bool) -> Result<Option<DLArc<dyn DeliverToRead>>> { + // Try to get work from the thread's work queue, using only a local lock. + { + let mut inner = self.inner.lock(); + if let Some(work) = inner.pop_work() { + return Ok(Some(work)); + } + if inner.looper_need_return { + drop(inner); + return Ok(self.process.get_work()); + } + } + + // If the caller doesn't want to wait, try to grab work from the process queue. + // + // We know nothing will have been queued directly to the thread queue because it is not in + // a transaction and it is not in the process' ready list. + if !wait { + return self.process.get_work().ok_or(EAGAIN).map(Some); + } + + // Get work from the process queue. If none is available, atomically register as ready. + let reg = match self.process.get_work_or_register(self) { + GetWorkOrRegister::Work(work) => return Ok(Some(work)), + GetWorkOrRegister::Register(reg) => reg, + }; + + let mut inner = self.inner.lock(); + loop { + if let Some(work) = inner.pop_work() { + return Ok(Some(work)); + } + + inner.looper_flags |= LOOPER_WAITING | LOOPER_WAITING_PROC; + let signal_pending = self.work_condvar.wait_interruptible_freezable(&mut inner); + inner.looper_flags &= !(LOOPER_WAITING | LOOPER_WAITING_PROC); + + if signal_pending || inner.looper_need_return { + // We need to return now. We need to pull the thread off the list of ready threads + // (by dropping `reg`), then check the state again after it's off the list to + // ensure that something was not queued in the meantime. If something has been + // queued, we just return it (instead of the error). + drop(inner); + drop(reg); + + let res = match self.inner.lock().pop_work() { + Some(work) => Ok(Some(work)), + None if signal_pending => Err(EINTR), + None => Ok(None), + }; + return res; + } + } + } + + /// Push the provided work item to be delivered to user space via this thread. + /// + /// Returns whether the item was successfully pushed. This can only fail if the thread is dead. + pub(crate) fn push_work(&self, work: DLArc<dyn DeliverToRead>) -> PushWorkRes { + let sync = work.should_sync_wakeup(); + + let res = self.inner.lock().push_work(work); + + if res.is_ok() { + if sync { + self.work_condvar.notify_sync(); + } else { + self.work_condvar.notify_one(); + } + } + + res + } + + /// Attempts to push to given work item to the thread if it's a looper thread (i.e., if it's + /// part of a thread pool) and is alive. Otherwise, push the work item to the process instead. + pub(crate) fn push_work_if_looper(&self, work: DLArc<dyn DeliverToRead>) -> BinderResult { + let mut inner = self.inner.lock(); + if inner.is_looper() && !inner.is_dead { + inner.push_work(work); + Ok(()) + } else { + drop(inner); + self.process.push_work(work) + } + } + + pub(crate) fn push_work_deferred(&self, work: DLArc<dyn DeliverToRead>) { + self.inner.lock().push_work_deferred(work); + } + + pub(crate) fn push_return_work(&self, reply: u32) { + self.inner.lock().push_return_work(reply); + } + + fn translate_object( + &self, + obj_index: usize, + offset: usize, + object: BinderObjectRef<'_>, + view: &mut AllocationView<'_>, + allow_fds: bool, + sg_state: &mut ScatterGatherState, + ) -> BinderResult { + match object { + BinderObjectRef::Binder(obj) => { + let strong = obj.hdr.type_ == BINDER_TYPE_BINDER; + // SAFETY: `binder` is a `binder_uintptr_t`; any bit pattern is a valid + // representation. + let ptr = unsafe { obj.__bindgen_anon_1.binder } as _; + let cookie = obj.cookie as _; + let flags = obj.flags as _; + let node = self + .process + .as_arc_borrow() + .get_node(ptr, cookie, flags, strong, self)?; + security::binder_transfer_binder(&self.process.cred, &view.alloc.process.cred)?; + view.transfer_binder_object(offset, obj, strong, node)?; + } + BinderObjectRef::Handle(obj) => { + let strong = obj.hdr.type_ == BINDER_TYPE_HANDLE; + // SAFETY: `handle` is a `u32`; any bit pattern is a valid representation. + let handle = unsafe { obj.__bindgen_anon_1.handle } as _; + let node = self.process.get_node_from_handle(handle, strong)?; + security::binder_transfer_binder(&self.process.cred, &view.alloc.process.cred)?; + view.transfer_binder_object(offset, obj, strong, node)?; + } + BinderObjectRef::Fd(obj) => { + if !allow_fds { + return Err(EPERM.into()); + } + + // SAFETY: `fd` is a `u32`; any bit pattern is a valid representation. + let fd = unsafe { obj.__bindgen_anon_1.fd }; + let file = LocalFile::fget(fd)?; + // SAFETY: The binder driver never calls `fdget_pos` and this code runs from an + // ioctl, so there are no active calls to `fdget_pos` on this thread. + let file = unsafe { LocalFile::assume_no_fdget_pos(file) }; + security::binder_transfer_file( + &self.process.cred, + &view.alloc.process.cred, + &file, + )?; + + let mut obj_write = BinderFdObject::default(); + obj_write.hdr.type_ = BINDER_TYPE_FD; + // This will be overwritten with the actual fd when the transaction is received. + obj_write.__bindgen_anon_1.fd = u32::MAX; + obj_write.cookie = obj.cookie; + view.write::<BinderFdObject>(offset, &obj_write)?; + + const FD_FIELD_OFFSET: usize = + core::mem::offset_of!(uapi::binder_fd_object, __bindgen_anon_1.fd); + + let field_offset = offset + FD_FIELD_OFFSET; + + view.alloc.info_add_fd(file, field_offset, false)?; + } + BinderObjectRef::Ptr(obj) => { + let obj_length = obj.length.try_into().map_err(|_| EINVAL)?; + let alloc_offset = match sg_state.unused_buffer_space.claim_next(obj_length) { + Ok(alloc_offset) => alloc_offset, + Err(err) => { + pr_warn!( + "Failed to claim space for a BINDER_TYPE_PTR. (offset: {}, limit: {}, size: {})", + sg_state.unused_buffer_space.offset, + sg_state.unused_buffer_space.limit, + obj_length, + ); + return Err(err.into()); + } + }; + + let sg_state_idx = sg_state.sg_entries.len(); + sg_state.sg_entries.push( + ScatterGatherEntry { + obj_index, + offset: alloc_offset, + sender_uaddr: obj.buffer as _, + length: obj_length, + pointer_fixups: KVec::new(), + fixup_min_offset: 0, + }, + GFP_KERNEL, + )?; + + let buffer_ptr_in_user_space = (view.alloc.ptr + alloc_offset) as u64; + + if obj.flags & uapi::BINDER_BUFFER_FLAG_HAS_PARENT == 0 { + sg_state.ancestors.clear(); + sg_state.ancestors.push(sg_state_idx, GFP_KERNEL)?; + } else { + // Another buffer also has a pointer to this buffer, and we need to fixup that + // pointer too. + + let parent_index = usize::try_from(obj.parent).map_err(|_| EINVAL)?; + let parent_offset = usize::try_from(obj.parent_offset).map_err(|_| EINVAL)?; + + let info = sg_state.validate_parent_fixup( + parent_index, + parent_offset, + size_of::<u64>(), + )?; + + sg_state.ancestors.truncate(info.num_ancestors); + sg_state.ancestors.push(sg_state_idx, GFP_KERNEL)?; + + let parent_entry = match sg_state.sg_entries.get_mut(info.parent_sg_index) { + Some(parent_entry) => parent_entry, + None => { + pr_err!( + "validate_parent_fixup returned index out of bounds for sg.entries" + ); + return Err(EINVAL.into()); + } + }; + + parent_entry.fixup_min_offset = info.new_min_offset; + parent_entry.pointer_fixups.push( + PointerFixupEntry { + skip: 0, + pointer_value: buffer_ptr_in_user_space, + target_offset: info.target_offset, + }, + GFP_KERNEL, + )?; + } + + let mut obj_write = BinderBufferObject::default(); + obj_write.hdr.type_ = BINDER_TYPE_PTR; + obj_write.flags = obj.flags; + obj_write.buffer = buffer_ptr_in_user_space; + obj_write.length = obj.length; + obj_write.parent = obj.parent; + obj_write.parent_offset = obj.parent_offset; + view.write::<BinderBufferObject>(offset, &obj_write)?; + } + BinderObjectRef::Fda(obj) => { + if !allow_fds { + return Err(EPERM.into()); + } + let parent_index = usize::try_from(obj.parent).map_err(|_| EINVAL)?; + let parent_offset = usize::try_from(obj.parent_offset).map_err(|_| EINVAL)?; + let num_fds = usize::try_from(obj.num_fds).map_err(|_| EINVAL)?; + let fds_len = num_fds.checked_mul(size_of::<u32>()).ok_or(EINVAL)?; + + let info = sg_state.validate_parent_fixup(parent_index, parent_offset, fds_len)?; + view.alloc.info_add_fd_reserve(num_fds)?; + + sg_state.ancestors.truncate(info.num_ancestors); + let parent_entry = match sg_state.sg_entries.get_mut(info.parent_sg_index) { + Some(parent_entry) => parent_entry, + None => { + pr_err!( + "validate_parent_fixup returned index out of bounds for sg.entries" + ); + return Err(EINVAL.into()); + } + }; + + parent_entry.fixup_min_offset = info.new_min_offset; + parent_entry + .pointer_fixups + .push( + PointerFixupEntry { + skip: fds_len, + pointer_value: 0, + target_offset: info.target_offset, + }, + GFP_KERNEL, + ) + .map_err(|_| ENOMEM)?; + + let fda_uaddr = parent_entry + .sender_uaddr + .checked_add(parent_offset) + .ok_or(EINVAL)?; + let mut fda_bytes = KVec::new(); + UserSlice::new(UserPtr::from_addr(fda_uaddr as _), fds_len) + .read_all(&mut fda_bytes, GFP_KERNEL)?; + + if fds_len != fda_bytes.len() { + pr_err!("UserSlice::read_all returned wrong length in BINDER_TYPE_FDA"); + return Err(EINVAL.into()); + } + + for i in (0..fds_len).step_by(size_of::<u32>()) { + let fd = { + let mut fd_bytes = [0u8; size_of::<u32>()]; + fd_bytes.copy_from_slice(&fda_bytes[i..i + size_of::<u32>()]); + u32::from_ne_bytes(fd_bytes) + }; + + let file = LocalFile::fget(fd)?; + // SAFETY: The binder driver never calls `fdget_pos` and this code runs from an + // ioctl, so there are no active calls to `fdget_pos` on this thread. + let file = unsafe { LocalFile::assume_no_fdget_pos(file) }; + security::binder_transfer_file( + &self.process.cred, + &view.alloc.process.cred, + &file, + )?; + + // The `validate_parent_fixup` call ensuers that this addition will not + // overflow. + view.alloc.info_add_fd(file, info.target_offset + i, true)?; + } + drop(fda_bytes); + + let mut obj_write = BinderFdArrayObject::default(); + obj_write.hdr.type_ = BINDER_TYPE_FDA; + obj_write.num_fds = obj.num_fds; + obj_write.parent = obj.parent; + obj_write.parent_offset = obj.parent_offset; + view.write::<BinderFdArrayObject>(offset, &obj_write)?; + } + } + Ok(()) + } + + fn apply_sg(&self, alloc: &mut Allocation, sg_state: &mut ScatterGatherState) -> BinderResult { + for sg_entry in &mut sg_state.sg_entries { + let mut end_of_previous_fixup = sg_entry.offset; + let offset_end = sg_entry.offset.checked_add(sg_entry.length).ok_or(EINVAL)?; + + let mut reader = + UserSlice::new(UserPtr::from_addr(sg_entry.sender_uaddr), sg_entry.length).reader(); + for fixup in &mut sg_entry.pointer_fixups { + let fixup_len = if fixup.skip == 0 { + size_of::<u64>() + } else { + fixup.skip + }; + + let target_offset_end = fixup.target_offset.checked_add(fixup_len).ok_or(EINVAL)?; + if fixup.target_offset < end_of_previous_fixup || offset_end < target_offset_end { + pr_warn!( + "Fixups oob {} {} {} {}", + fixup.target_offset, + end_of_previous_fixup, + offset_end, + target_offset_end + ); + return Err(EINVAL.into()); + } + + let copy_off = end_of_previous_fixup; + let copy_len = fixup.target_offset - end_of_previous_fixup; + if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) { + pr_warn!("Failed copying into alloc: {:?}", err); + return Err(err.into()); + } + if fixup.skip == 0 { + let res = alloc.write::<u64>(fixup.target_offset, &fixup.pointer_value); + if let Err(err) = res { + pr_warn!("Failed copying ptr into alloc: {:?}", err); + return Err(err.into()); + } + } + if let Err(err) = reader.skip(fixup_len) { + pr_warn!("Failed skipping {} from reader: {:?}", fixup_len, err); + return Err(err.into()); + } + end_of_previous_fixup = target_offset_end; + } + let copy_off = end_of_previous_fixup; + let copy_len = offset_end - end_of_previous_fixup; + if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) { + pr_warn!("Failed copying remainder into alloc: {:?}", err); + return Err(err.into()); + } + } + Ok(()) + } + + /// This method copies the payload of a transaction into the target process. + /// + /// The resulting payload will have several different components, which will be stored next to + /// each other in the allocation. Furthermore, various objects can be embedded in the payload, + /// and those objects have to be translated so that they make sense to the target transaction. + pub(crate) fn copy_transaction_data( + &self, + to_process: Arc<Process>, + tr: &BinderTransactionDataSg, + debug_id: usize, + allow_fds: bool, + txn_security_ctx_offset: Option<&mut usize>, + ) -> BinderResult<NewAllocation> { + let trd = &tr.transaction_data; + let is_oneway = trd.flags & TF_ONE_WAY != 0; + let mut secctx = if let Some(offset) = txn_security_ctx_offset { + let secid = self.process.cred.get_secid(); + let ctx = match security::SecurityCtx::from_secid(secid) { + Ok(ctx) => ctx, + Err(err) => { + pr_warn!("Failed to get security ctx for id {}: {:?}", secid, err); + return Err(err.into()); + } + }; + Some((offset, ctx)) + } else { + None + }; + + let data_size = trd.data_size.try_into().map_err(|_| EINVAL)?; + let aligned_data_size = ptr_align(data_size).ok_or(EINVAL)?; + let offsets_size = trd.offsets_size.try_into().map_err(|_| EINVAL)?; + let aligned_offsets_size = ptr_align(offsets_size).ok_or(EINVAL)?; + let buffers_size = tr.buffers_size.try_into().map_err(|_| EINVAL)?; + let aligned_buffers_size = ptr_align(buffers_size).ok_or(EINVAL)?; + let aligned_secctx_size = match secctx.as_ref() { + Some((_offset, ctx)) => ptr_align(ctx.len()).ok_or(EINVAL)?, + None => 0, + }; + + // This guarantees that at least `sizeof(usize)` bytes will be allocated. + let len = usize::max( + aligned_data_size + .checked_add(aligned_offsets_size) + .and_then(|sum| sum.checked_add(aligned_buffers_size)) + .and_then(|sum| sum.checked_add(aligned_secctx_size)) + .ok_or(ENOMEM)?, + size_of::<usize>(), + ); + let secctx_off = aligned_data_size + aligned_offsets_size + aligned_buffers_size; + let mut alloc = + match to_process.buffer_alloc(debug_id, len, is_oneway, self.process.task.pid()) { + Ok(alloc) => alloc, + Err(err) => { + pr_warn!( + "Failed to allocate buffer. len:{}, is_oneway:{}", + len, + is_oneway + ); + return Err(err); + } + }; + + // SAFETY: This accesses a union field, but it's okay because the field's type is valid for + // all bit-patterns. + let trd_data_ptr = unsafe { &trd.data.ptr }; + let mut buffer_reader = + UserSlice::new(UserPtr::from_addr(trd_data_ptr.buffer as _), data_size).reader(); + let mut end_of_previous_object = 0; + let mut sg_state = None; + + // Copy offsets if there are any. + if offsets_size > 0 { + { + let mut reader = + UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size) + .reader(); + alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?; + } + + let offsets_start = aligned_data_size; + let offsets_end = aligned_data_size + aligned_offsets_size; + + // This state is used for BINDER_TYPE_PTR objects. + let sg_state = sg_state.insert(ScatterGatherState { + unused_buffer_space: UnusedBufferSpace { + offset: offsets_end, + limit: len, + }, + sg_entries: KVec::new(), + ancestors: KVec::new(), + }); + + // Traverse the objects specified. + let mut view = AllocationView::new(&mut alloc, data_size); + for (index, index_offset) in (offsets_start..offsets_end) + .step_by(size_of::<usize>()) + .enumerate() + { + let offset = view.alloc.read(index_offset)?; + + if offset < end_of_previous_object { + pr_warn!("Got transaction with invalid offset."); + return Err(EINVAL.into()); + } + + // Copy data between two objects. + if end_of_previous_object < offset { + view.copy_into( + &mut buffer_reader, + end_of_previous_object, + offset - end_of_previous_object, + )?; + } + + let mut object = BinderObject::read_from(&mut buffer_reader)?; + + match self.translate_object( + index, + offset, + object.as_ref(), + &mut view, + allow_fds, + sg_state, + ) { + Ok(()) => end_of_previous_object = offset + object.size(), + Err(err) => { + pr_warn!("Error while translating object."); + return Err(err); + } + } + + // Update the indexes containing objects to clean up. + let offset_after_object = index_offset + size_of::<usize>(); + view.alloc + .set_info_offsets(offsets_start..offset_after_object); + } + } + + // Copy remaining raw data. + alloc.copy_into( + &mut buffer_reader, + end_of_previous_object, + data_size - end_of_previous_object, + )?; + + if let Some(sg_state) = sg_state.as_mut() { + if let Err(err) = self.apply_sg(&mut alloc, sg_state) { + pr_warn!("Failure in apply_sg: {:?}", err); + return Err(err); + } + } + + if let Some((off_out, secctx)) = secctx.as_mut() { + if let Err(err) = alloc.write(secctx_off, secctx.as_bytes()) { + pr_warn!("Failed to write security context: {:?}", err); + return Err(err.into()); + } + **off_out = secctx_off; + } + Ok(alloc) + } + + fn unwind_transaction_stack(self: &Arc<Self>) { + let mut thread = self.clone(); + while let Ok(transaction) = { + let mut inner = thread.inner.lock(); + inner.pop_transaction_to_reply(thread.as_ref()) + } { + let reply = Err(BR_DEAD_REPLY); + if !transaction.from.deliver_single_reply(reply, &transaction) { + break; + } + + thread = transaction.from.clone(); + } + } + + pub(crate) fn deliver_reply( + &self, + reply: Result<DLArc<Transaction>, u32>, + transaction: &DArc<Transaction>, + ) { + if self.deliver_single_reply(reply, transaction) { + transaction.from.unwind_transaction_stack(); + } + } + + /// Delivers a reply to the thread that started a transaction. The reply can either be a + /// reply-transaction or an error code to be delivered instead. + /// + /// Returns whether the thread is dead. If it is, the caller is expected to unwind the + /// transaction stack by completing transactions for threads that are dead. + fn deliver_single_reply( + &self, + reply: Result<DLArc<Transaction>, u32>, + transaction: &DArc<Transaction>, + ) -> bool { + if let Ok(transaction) = &reply { + transaction.set_outstanding(&mut self.process.inner.lock()); + } + + { + let mut inner = self.inner.lock(); + if !inner.pop_transaction_replied(transaction) { + return false; + } + + if inner.is_dead { + return true; + } + + match reply { + Ok(work) => { + inner.push_work(work); + } + Err(code) => inner.push_reply_work(code), + } + } + + // Notify the thread now that we've released the inner lock. + self.work_condvar.notify_sync(); + false + } + + /// Determines if the given transaction is the current transaction for this thread. + fn is_current_transaction(&self, transaction: &DArc<Transaction>) -> bool { + let inner = self.inner.lock(); + match &inner.current_transaction { + None => false, + Some(current) => Arc::ptr_eq(current, transaction), + } + } + + /// Determines the current top of the transaction stack. It fails if the top is in another + /// thread (i.e., this thread belongs to a stack but it has called another thread). The top is + /// [`None`] if the thread is not currently participating in a transaction stack. + fn top_of_transaction_stack(&self) -> Result<Option<DArc<Transaction>>> { + let inner = self.inner.lock(); + if let Some(cur) = &inner.current_transaction { + if core::ptr::eq(self, cur.from.as_ref()) { + pr_warn!("got new transaction with bad transaction stack"); + return Err(EINVAL); + } + Ok(Some(cur.clone())) + } else { + Ok(None) + } + } + + fn transaction<T>(self: &Arc<Self>, tr: &BinderTransactionDataSg, inner: T) + where + T: FnOnce(&Arc<Self>, &BinderTransactionDataSg) -> BinderResult, + { + if let Err(err) = inner(self, tr) { + if err.should_pr_warn() { + let mut ee = self.inner.lock().extended_error; + ee.command = err.reply; + ee.param = err.as_errno(); + pr_warn!( + "Transaction failed: {:?} my_pid:{}", + err, + self.process.pid_in_current_ns() + ); + } + + self.push_return_work(err.reply); + } + } + + fn transaction_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult { + // SAFETY: Handle's type has no invalid bit patterns. + let handle = unsafe { tr.transaction_data.target.handle }; + let node_ref = self.process.get_transaction_node(handle)?; + security::binder_transaction(&self.process.cred, &node_ref.node.owner.cred)?; + // TODO: We need to ensure that there isn't a pending transaction in the work queue. How + // could this happen? + let top = self.top_of_transaction_stack()?; + let list_completion = DTRWrap::arc_try_new(DeliverCode::new(BR_TRANSACTION_COMPLETE))?; + let completion = list_completion.clone_arc(); + let transaction = Transaction::new(node_ref, top, self, tr)?; + + // Check that the transaction stack hasn't changed while the lock was released, then update + // it with the new transaction. + { + let mut inner = self.inner.lock(); + if !transaction.is_stacked_on(&inner.current_transaction) { + pr_warn!("Transaction stack changed during transaction!"); + return Err(EINVAL.into()); + } + inner.current_transaction = Some(transaction.clone_arc()); + // We push the completion as a deferred work so that we wait for the reply before + // returning to userland. + inner.push_work_deferred(list_completion); + } + + if let Err(e) = transaction.submit() { + completion.skip(); + // Define `transaction` first to drop it after `inner`. + let transaction; + let mut inner = self.inner.lock(); + transaction = inner.current_transaction.take().unwrap(); + inner.current_transaction = transaction.clone_next(); + Err(e) + } else { + Ok(()) + } + } + + fn reply_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult { + let orig = self.inner.lock().pop_transaction_to_reply(self)?; + if !orig.from.is_current_transaction(&orig) { + return Err(EINVAL.into()); + } + + // We need to complete the transaction even if we cannot complete building the reply. + let out = (|| -> BinderResult<_> { + let completion = DTRWrap::arc_try_new(DeliverCode::new(BR_TRANSACTION_COMPLETE))?; + let process = orig.from.process.clone(); + let allow_fds = orig.flags & TF_ACCEPT_FDS != 0; + let reply = Transaction::new_reply(self, process, tr, allow_fds)?; + self.inner.lock().push_work(completion); + orig.from.deliver_reply(Ok(reply), &orig); + Ok(()) + })() + .map_err(|mut err| { + // At this point we only return `BR_TRANSACTION_COMPLETE` to the caller, and we must let + // the sender know that the transaction has completed (with an error in this case). + pr_warn!( + "Failure {:?} during reply - delivering BR_FAILED_REPLY to sender.", + err + ); + let reply = Err(BR_FAILED_REPLY); + orig.from.deliver_reply(reply, &orig); + err.reply = BR_TRANSACTION_COMPLETE; + err + }); + + out + } + + fn oneway_transaction_inner(self: &Arc<Self>, tr: &BinderTransactionDataSg) -> BinderResult { + // SAFETY: The `handle` field is valid for all possible byte values, so reading from the + // union is okay. + let handle = unsafe { tr.transaction_data.target.handle }; + let node_ref = self.process.get_transaction_node(handle)?; + security::binder_transaction(&self.process.cred, &node_ref.node.owner.cred)?; + let transaction = Transaction::new(node_ref, None, self, tr)?; + let code = if self.process.is_oneway_spam_detection_enabled() + && transaction.oneway_spam_detected + { + BR_ONEWAY_SPAM_SUSPECT + } else { + BR_TRANSACTION_COMPLETE + }; + let list_completion = DTRWrap::arc_try_new(DeliverCode::new(code))?; + let completion = list_completion.clone_arc(); + self.inner.lock().push_work(list_completion); + match transaction.submit() { + Ok(()) => Ok(()), + Err(err) => { + completion.skip(); + Err(err) + } + } + } + + fn write(self: &Arc<Self>, req: &mut BinderWriteRead) -> Result { + let write_start = req.write_buffer.wrapping_add(req.write_consumed); + let write_len = req.write_size.saturating_sub(req.write_consumed); + let mut reader = + UserSlice::new(UserPtr::from_addr(write_start as _), write_len as _).reader(); + + while reader.len() >= size_of::<u32>() && self.inner.lock().return_work.is_unused() { + let before = reader.len(); + let cmd = reader.read::<u32>()?; + GLOBAL_STATS.inc_bc(cmd); + self.process.stats.inc_bc(cmd); + match cmd { + BC_TRANSACTION => { + let tr = reader.read::<BinderTransactionData>()?.with_buffers_size(0); + if tr.transaction_data.flags & TF_ONE_WAY != 0 { + self.transaction(&tr, Self::oneway_transaction_inner); + } else { + self.transaction(&tr, Self::transaction_inner); + } + } + BC_TRANSACTION_SG => { + let tr = reader.read::<BinderTransactionDataSg>()?; + if tr.transaction_data.flags & TF_ONE_WAY != 0 { + self.transaction(&tr, Self::oneway_transaction_inner); + } else { + self.transaction(&tr, Self::transaction_inner); + } + } + BC_REPLY => { + let tr = reader.read::<BinderTransactionData>()?.with_buffers_size(0); + self.transaction(&tr, Self::reply_inner) + } + BC_REPLY_SG => { + let tr = reader.read::<BinderTransactionDataSg>()?; + self.transaction(&tr, Self::reply_inner) + } + BC_FREE_BUFFER => { + let buffer = self.process.buffer_get(reader.read()?); + if let Some(buffer) = &buffer { + if buffer.looper_need_return_on_free() { + self.inner.lock().looper_need_return = true; + } + } + drop(buffer); + } + BC_INCREFS => { + self.process + .as_arc_borrow() + .update_ref(reader.read()?, true, false)? + } + BC_ACQUIRE => { + self.process + .as_arc_borrow() + .update_ref(reader.read()?, true, true)? + } + BC_RELEASE => { + self.process + .as_arc_borrow() + .update_ref(reader.read()?, false, true)? + } + BC_DECREFS => { + self.process + .as_arc_borrow() + .update_ref(reader.read()?, false, false)? + } + BC_INCREFS_DONE => self.process.inc_ref_done(&mut reader, false)?, + BC_ACQUIRE_DONE => self.process.inc_ref_done(&mut reader, true)?, + BC_REQUEST_DEATH_NOTIFICATION => self.process.request_death(&mut reader, self)?, + BC_CLEAR_DEATH_NOTIFICATION => self.process.clear_death(&mut reader, self)?, + BC_DEAD_BINDER_DONE => self.process.dead_binder_done(reader.read()?, self), + BC_REGISTER_LOOPER => { + let valid = self.process.register_thread(); + self.inner.lock().looper_register(valid); + } + BC_ENTER_LOOPER => self.inner.lock().looper_enter(), + BC_EXIT_LOOPER => self.inner.lock().looper_exit(), + BC_REQUEST_FREEZE_NOTIFICATION => self.process.request_freeze_notif(&mut reader)?, + BC_CLEAR_FREEZE_NOTIFICATION => self.process.clear_freeze_notif(&mut reader)?, + BC_FREEZE_NOTIFICATION_DONE => self.process.freeze_notif_done(&mut reader)?, + + // Fail if given an unknown error code. + // BC_ATTEMPT_ACQUIRE and BC_ACQUIRE_RESULT are no longer supported. + _ => return Err(EINVAL), + } + // Update the number of write bytes consumed. + req.write_consumed += (before - reader.len()) as u64; + } + + Ok(()) + } + + fn read(self: &Arc<Self>, req: &mut BinderWriteRead, wait: bool) -> Result { + let read_start = req.read_buffer.wrapping_add(req.read_consumed); + let read_len = req.read_size.saturating_sub(req.read_consumed); + let mut writer = BinderReturnWriter::new( + UserSlice::new(UserPtr::from_addr(read_start as _), read_len as _).writer(), + self, + ); + let (in_pool, use_proc_queue) = { + let inner = self.inner.lock(); + (inner.is_looper(), inner.should_use_process_work_queue()) + }; + + let getter = if use_proc_queue { + Self::get_work + } else { + Self::get_work_local + }; + + // Reserve some room at the beginning of the read buffer so that we can send a + // BR_SPAWN_LOOPER if we need to. + let mut has_noop_placeholder = false; + if req.read_consumed == 0 { + if let Err(err) = writer.write_code(BR_NOOP) { + pr_warn!("Failure when writing BR_NOOP at beginning of buffer."); + return Err(err); + } + has_noop_placeholder = true; + } + + // Loop doing work while there is room in the buffer. + let initial_len = writer.len(); + while writer.len() >= size_of::<uapi::binder_transaction_data_secctx>() + 4 { + match getter(self, wait && initial_len == writer.len()) { + Ok(Some(work)) => match work.into_arc().do_work(self, &mut writer) { + Ok(true) => {} + Ok(false) => break, + Err(err) => { + return Err(err); + } + }, + Ok(None) => { + break; + } + Err(err) => { + // Propagate the error if we haven't written anything else. + if err != EINTR && err != EAGAIN { + pr_warn!("Failure in work getter: {:?}", err); + } + if initial_len == writer.len() { + return Err(err); + } else { + break; + } + } + } + } + + req.read_consumed += read_len - writer.len() as u64; + + // Write BR_SPAWN_LOOPER if the process needs more threads for its pool. + if has_noop_placeholder && in_pool && self.process.needs_thread() { + let mut writer = + UserSlice::new(UserPtr::from_addr(req.read_buffer as _), req.read_size as _) + .writer(); + writer.write(&BR_SPAWN_LOOPER)?; + } + Ok(()) + } + + pub(crate) fn write_read(self: &Arc<Self>, data: UserSlice, wait: bool) -> Result { + let (mut reader, mut writer) = data.reader_writer(); + let mut req = reader.read::<BinderWriteRead>()?; + + // Go through the write buffer. + let mut ret = Ok(()); + if req.write_size > 0 { + ret = self.write(&mut req); + if let Err(err) = ret { + pr_warn!( + "Write failure {:?} in pid:{}", + err, + self.process.pid_in_current_ns() + ); + req.read_consumed = 0; + writer.write(&req)?; + self.inner.lock().looper_need_return = false; + return ret; + } + } + + // Go through the work queue. + if req.read_size > 0 { + ret = self.read(&mut req, wait); + if ret.is_err() && ret != Err(EINTR) { + pr_warn!( + "Read failure {:?} in pid:{}", + ret, + self.process.pid_in_current_ns() + ); + } + } + + // Write the request back so that the consumed fields are visible to the caller. + writer.write(&req)?; + + self.inner.lock().looper_need_return = false; + + ret + } + + pub(crate) fn poll(&self, file: &File, table: PollTable<'_>) -> (bool, u32) { + table.register_wait(file, &self.work_condvar); + let mut inner = self.inner.lock(); + (inner.should_use_process_work_queue(), inner.poll()) + } + + /// Make the call to `get_work` or `get_work_local` return immediately, if any. + pub(crate) fn exit_looper(&self) { + let mut inner = self.inner.lock(); + let should_notify = inner.looper_flags & LOOPER_WAITING != 0; + if should_notify { + inner.looper_need_return = true; + } + drop(inner); + + if should_notify { + self.work_condvar.notify_one(); + } + } + + pub(crate) fn notify_if_poll_ready(&self, sync: bool) { + // Determine if we need to notify. This requires the lock. + let inner = self.inner.lock(); + let notify = inner.looper_flags & LOOPER_POLL != 0 && inner.should_use_process_work_queue(); + drop(inner); + + // Now that the lock is no longer held, notify the waiters if we have to. + if notify { + if sync { + self.work_condvar.notify_sync(); + } else { + self.work_condvar.notify_one(); + } + } + } + + pub(crate) fn release(self: &Arc<Self>) { + self.inner.lock().is_dead = true; + + //self.work_condvar.clear(); + self.unwind_transaction_stack(); + + // Cancel all pending work items. + while let Ok(Some(work)) = self.get_work_local(false) { + work.into_arc().cancel(); + } + } +} + +#[pin_data] +struct ThreadError { + error_code: AtomicU32, + #[pin] + links_track: AtomicTracker, +} + +impl ThreadError { + fn try_new() -> Result<DArc<Self>> { + DTRWrap::arc_pin_init(pin_init!(Self { + error_code: AtomicU32::new(BR_OK), + links_track <- AtomicTracker::new(), + })) + .map(ListArc::into_arc) + } + + fn set_error_code(&self, code: u32) { + self.error_code.store(code, Ordering::Relaxed); + } + + fn is_unused(&self) -> bool { + self.error_code.load(Ordering::Relaxed) == BR_OK + } +} + +impl DeliverToRead for ThreadError { + fn do_work( + self: DArc<Self>, + _thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let code = self.error_code.load(Ordering::Relaxed); + self.error_code.store(BR_OK, Ordering::Relaxed); + writer.write_code(code)?; + Ok(true) + } + + fn cancel(self: DArc<Self>) {} + + fn should_sync_wakeup(&self) -> bool { + false + } + + fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { + seq_print!( + m, + "{}transaction error: {}\n", + prefix, + self.error_code.load(Ordering::Relaxed) + ); + Ok(()) + } +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for ThreadError { + tracked_by links_track: AtomicTracker; + } +} diff --git a/drivers/android/binder/trace.rs b/drivers/android/binder/trace.rs new file mode 100644 index 000000000000..af0e4392805e --- /dev/null +++ b/drivers/android/binder/trace.rs @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use kernel::ffi::{c_uint, c_ulong}; +use kernel::tracepoint::declare_trace; + +declare_trace! { + unsafe fn rust_binder_ioctl(cmd: c_uint, arg: c_ulong); +} + +#[inline] +pub(crate) fn trace_ioctl(cmd: u32, arg: usize) { + // SAFETY: Always safe to call. + unsafe { rust_binder_ioctl(cmd, arg as c_ulong) } +} diff --git a/drivers/android/binder/transaction.rs b/drivers/android/binder/transaction.rs new file mode 100644 index 000000000000..02512175d622 --- /dev/null +++ b/drivers/android/binder/transaction.rs @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +use core::sync::atomic::{AtomicBool, Ordering}; +use kernel::{ + prelude::*, + seq_file::SeqFile, + seq_print, + sync::{Arc, SpinLock}, + task::Kuid, + time::{Instant, Monotonic}, + types::ScopeGuard, +}; + +use crate::{ + allocation::{Allocation, TranslatedFds}, + defs::*, + error::{BinderError, BinderResult}, + node::{Node, NodeRef}, + process::{Process, ProcessInner}, + ptr_align, + thread::{PushWorkRes, Thread}, + BinderReturnWriter, DArc, DLArc, DTRWrap, DeliverToRead, +}; + +#[pin_data(PinnedDrop)] +pub(crate) struct Transaction { + pub(crate) debug_id: usize, + target_node: Option<DArc<Node>>, + pub(crate) from_parent: Option<DArc<Transaction>>, + pub(crate) from: Arc<Thread>, + pub(crate) to: Arc<Process>, + #[pin] + allocation: SpinLock<Option<Allocation>>, + is_outstanding: AtomicBool, + code: u32, + pub(crate) flags: u32, + data_size: usize, + offsets_size: usize, + data_address: usize, + sender_euid: Kuid, + txn_security_ctx_off: Option<usize>, + pub(crate) oneway_spam_detected: bool, + start_time: Instant<Monotonic>, +} + +kernel::list::impl_list_arc_safe! { + impl ListArcSafe<0> for Transaction { untracked; } +} + +impl Transaction { + pub(crate) fn new( + node_ref: NodeRef, + from_parent: Option<DArc<Transaction>>, + from: &Arc<Thread>, + tr: &BinderTransactionDataSg, + ) -> BinderResult<DLArc<Self>> { + let debug_id = super::next_debug_id(); + let trd = &tr.transaction_data; + let allow_fds = node_ref.node.flags & FLAT_BINDER_FLAG_ACCEPTS_FDS != 0; + let txn_security_ctx = node_ref.node.flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX != 0; + let mut txn_security_ctx_off = if txn_security_ctx { Some(0) } else { None }; + let to = node_ref.node.owner.clone(); + let mut alloc = match from.copy_transaction_data( + to.clone(), + tr, + debug_id, + allow_fds, + txn_security_ctx_off.as_mut(), + ) { + Ok(alloc) => alloc, + Err(err) => { + if !err.is_dead() { + pr_warn!("Failure in copy_transaction_data: {:?}", err); + } + return Err(err); + } + }; + let oneway_spam_detected = alloc.oneway_spam_detected; + if trd.flags & TF_ONE_WAY != 0 { + if from_parent.is_some() { + pr_warn!("Oneway transaction should not be in a transaction stack."); + return Err(EINVAL.into()); + } + alloc.set_info_oneway_node(node_ref.node.clone()); + } + if trd.flags & TF_CLEAR_BUF != 0 { + alloc.set_info_clear_on_drop(); + } + let target_node = node_ref.node.clone(); + alloc.set_info_target_node(node_ref); + let data_address = alloc.ptr; + + Ok(DTRWrap::arc_pin_init(pin_init!(Transaction { + debug_id, + target_node: Some(target_node), + from_parent, + sender_euid: from.process.task.euid(), + from: from.clone(), + to, + code: trd.code, + flags: trd.flags, + data_size: trd.data_size as _, + offsets_size: trd.offsets_size as _, + data_address, + allocation <- kernel::new_spinlock!(Some(alloc.success()), "Transaction::new"), + is_outstanding: AtomicBool::new(false), + txn_security_ctx_off, + oneway_spam_detected, + start_time: Instant::now(), + }))?) + } + + pub(crate) fn new_reply( + from: &Arc<Thread>, + to: Arc<Process>, + tr: &BinderTransactionDataSg, + allow_fds: bool, + ) -> BinderResult<DLArc<Self>> { + let debug_id = super::next_debug_id(); + let trd = &tr.transaction_data; + let mut alloc = match from.copy_transaction_data(to.clone(), tr, debug_id, allow_fds, None) + { + Ok(alloc) => alloc, + Err(err) => { + pr_warn!("Failure in copy_transaction_data: {:?}", err); + return Err(err); + } + }; + let oneway_spam_detected = alloc.oneway_spam_detected; + if trd.flags & TF_CLEAR_BUF != 0 { + alloc.set_info_clear_on_drop(); + } + Ok(DTRWrap::arc_pin_init(pin_init!(Transaction { + debug_id, + target_node: None, + from_parent: None, + sender_euid: from.process.task.euid(), + from: from.clone(), + to, + code: trd.code, + flags: trd.flags, + data_size: trd.data_size as _, + offsets_size: trd.offsets_size as _, + data_address: alloc.ptr, + allocation <- kernel::new_spinlock!(Some(alloc.success()), "Transaction::new"), + is_outstanding: AtomicBool::new(false), + txn_security_ctx_off: None, + oneway_spam_detected, + start_time: Instant::now(), + }))?) + } + + #[inline(never)] + pub(crate) fn debug_print_inner(&self, m: &SeqFile, prefix: &str) { + seq_print!( + m, + "{}{}: from {}:{} to {} code {:x} flags {:x} elapsed {}ms", + prefix, + self.debug_id, + self.from.process.task.pid(), + self.from.id, + self.to.task.pid(), + self.code, + self.flags, + self.start_time.elapsed().as_millis(), + ); + if let Some(target_node) = &self.target_node { + seq_print!(m, " node {}", target_node.debug_id); + } + seq_print!(m, " size {}:{}\n", self.data_size, self.offsets_size); + } + + /// Determines if the transaction is stacked on top of the given transaction. + pub(crate) fn is_stacked_on(&self, onext: &Option<DArc<Self>>) -> bool { + match (&self.from_parent, onext) { + (None, None) => true, + (Some(from_parent), Some(next)) => Arc::ptr_eq(from_parent, next), + _ => false, + } + } + + /// Returns a pointer to the next transaction on the transaction stack, if there is one. + pub(crate) fn clone_next(&self) -> Option<DArc<Self>> { + Some(self.from_parent.as_ref()?.clone()) + } + + /// Searches in the transaction stack for a thread that belongs to the target process. This is + /// useful when finding a target for a new transaction: if the node belongs to a process that + /// is already part of the transaction stack, we reuse the thread. + fn find_target_thread(&self) -> Option<Arc<Thread>> { + let mut it = &self.from_parent; + while let Some(transaction) = it { + if Arc::ptr_eq(&transaction.from.process, &self.to) { + return Some(transaction.from.clone()); + } + it = &transaction.from_parent; + } + None + } + + /// Searches in the transaction stack for a transaction originating at the given thread. + pub(crate) fn find_from(&self, thread: &Thread) -> Option<&DArc<Transaction>> { + let mut it = &self.from_parent; + while let Some(transaction) = it { + if core::ptr::eq(thread, transaction.from.as_ref()) { + return Some(transaction); + } + + it = &transaction.from_parent; + } + None + } + + pub(crate) fn set_outstanding(&self, to_process: &mut ProcessInner) { + // No race because this method is only called once. + if !self.is_outstanding.load(Ordering::Relaxed) { + self.is_outstanding.store(true, Ordering::Relaxed); + to_process.add_outstanding_txn(); + } + } + + /// Decrement `outstanding_txns` in `to` if it hasn't already been decremented. + fn drop_outstanding_txn(&self) { + // No race because this is called at most twice, and one of the calls are in the + // destructor, which is guaranteed to not race with any other operations on the + // transaction. It also cannot race with `set_outstanding`, since submission happens + // before delivery. + if self.is_outstanding.load(Ordering::Relaxed) { + self.is_outstanding.store(false, Ordering::Relaxed); + self.to.drop_outstanding_txn(); + } + } + + /// Submits the transaction to a work queue. Uses a thread if there is one in the transaction + /// stack, otherwise uses the destination process. + /// + /// Not used for replies. + pub(crate) fn submit(self: DLArc<Self>) -> BinderResult { + // Defined before `process_inner` so that the destructor runs after releasing the lock. + let mut _t_outdated; + + let oneway = self.flags & TF_ONE_WAY != 0; + let process = self.to.clone(); + let mut process_inner = process.inner.lock(); + + self.set_outstanding(&mut process_inner); + + if oneway { + if let Some(target_node) = self.target_node.clone() { + if process_inner.is_frozen { + process_inner.async_recv = true; + if self.flags & TF_UPDATE_TXN != 0 { + if let Some(t_outdated) = + target_node.take_outdated_transaction(&self, &mut process_inner) + { + // Save the transaction to be dropped after locks are released. + _t_outdated = t_outdated; + } + } + } + match target_node.submit_oneway(self, &mut process_inner) { + Ok(()) => {} + Err((err, work)) => { + drop(process_inner); + // Drop work after releasing process lock. + drop(work); + return Err(err); + } + } + + if process_inner.is_frozen { + return Err(BinderError::new_frozen_oneway()); + } else { + return Ok(()); + } + } else { + pr_err!("Failed to submit oneway transaction to node."); + } + } + + if process_inner.is_frozen { + process_inner.sync_recv = true; + return Err(BinderError::new_frozen()); + } + + let res = if let Some(thread) = self.find_target_thread() { + match thread.push_work(self) { + PushWorkRes::Ok => Ok(()), + PushWorkRes::FailedDead(me) => Err((BinderError::new_dead(), me)), + } + } else { + process_inner.push_work(self) + }; + drop(process_inner); + + match res { + Ok(()) => Ok(()), + Err((err, work)) => { + // Drop work after releasing process lock. + drop(work); + Err(err) + } + } + } + + /// Check whether one oneway transaction can supersede another. + pub(crate) fn can_replace(&self, old: &Transaction) -> bool { + if self.from.process.task.pid() != old.from.process.task.pid() { + return false; + } + + if self.flags & old.flags & (TF_ONE_WAY | TF_UPDATE_TXN) != (TF_ONE_WAY | TF_UPDATE_TXN) { + return false; + } + + let target_node_match = match (self.target_node.as_ref(), old.target_node.as_ref()) { + (None, None) => true, + (Some(tn1), Some(tn2)) => Arc::ptr_eq(tn1, tn2), + _ => false, + }; + + self.code == old.code && self.flags == old.flags && target_node_match + } + + fn prepare_file_list(&self) -> Result<TranslatedFds> { + let mut alloc = self.allocation.lock().take().ok_or(ESRCH)?; + + match alloc.translate_fds() { + Ok(translated) => { + *self.allocation.lock() = Some(alloc); + Ok(translated) + } + Err(err) => { + // Free the allocation eagerly. + drop(alloc); + Err(err) + } + } + } +} + +impl DeliverToRead for Transaction { + fn do_work( + self: DArc<Self>, + thread: &Thread, + writer: &mut BinderReturnWriter<'_>, + ) -> Result<bool> { + let send_failed_reply = ScopeGuard::new(|| { + if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 { + let reply = Err(BR_FAILED_REPLY); + self.from.deliver_reply(reply, &self); + } + self.drop_outstanding_txn(); + }); + + let files = if let Ok(list) = self.prepare_file_list() { + list + } else { + // On failure to process the list, we send a reply back to the sender and ignore the + // transaction on the recipient. + return Ok(true); + }; + + let mut tr_sec = BinderTransactionDataSecctx::default(); + let tr = tr_sec.tr_data(); + if let Some(target_node) = &self.target_node { + let (ptr, cookie) = target_node.get_id(); + tr.target.ptr = ptr as _; + tr.cookie = cookie as _; + }; + tr.code = self.code; + tr.flags = self.flags; + tr.data_size = self.data_size as _; + tr.data.ptr.buffer = self.data_address as _; + tr.offsets_size = self.offsets_size as _; + if tr.offsets_size > 0 { + tr.data.ptr.offsets = (self.data_address + ptr_align(self.data_size).unwrap()) as _; + } + tr.sender_euid = self.sender_euid.into_uid_in_current_ns(); + tr.sender_pid = 0; + if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 { + // Not a reply and not one-way. + tr.sender_pid = self.from.process.pid_in_current_ns(); + } + let code = if self.target_node.is_none() { + BR_REPLY + } else if self.txn_security_ctx_off.is_some() { + BR_TRANSACTION_SEC_CTX + } else { + BR_TRANSACTION + }; + + // Write the transaction code and data to the user buffer. + writer.write_code(code)?; + if let Some(off) = self.txn_security_ctx_off { + tr_sec.secctx = (self.data_address + off) as u64; + writer.write_payload(&tr_sec)?; + } else { + writer.write_payload(&*tr)?; + } + + let mut alloc = self.allocation.lock().take().ok_or(ESRCH)?; + + // Dismiss the completion of transaction with a failure. No failure paths are allowed from + // here on out. + send_failed_reply.dismiss(); + + // Commit files, and set FDs in FDA to be closed on buffer free. + let close_on_free = files.commit(); + alloc.set_info_close_on_free(close_on_free); + + // It is now the user's responsibility to clear the allocation. + alloc.keep_alive(); + + self.drop_outstanding_txn(); + + // When this is not a reply and not a oneway transaction, update `current_transaction`. If + // it's a reply, `current_transaction` has already been updated appropriately. + if self.target_node.is_some() && tr_sec.transaction_data.flags & TF_ONE_WAY == 0 { + thread.set_current_transaction(self); + } + + Ok(false) + } + + fn cancel(self: DArc<Self>) { + let allocation = self.allocation.lock().take(); + drop(allocation); + + // If this is not a reply or oneway transaction, then send a dead reply. + if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 { + let reply = Err(BR_DEAD_REPLY); + self.from.deliver_reply(reply, &self); + } + + self.drop_outstanding_txn(); + } + + fn should_sync_wakeup(&self) -> bool { + self.flags & TF_ONE_WAY == 0 + } + + fn debug_print(&self, m: &SeqFile, _prefix: &str, tprefix: &str) -> Result<()> { + self.debug_print_inner(m, tprefix); + Ok(()) + } +} + +#[pinned_drop] +impl PinnedDrop for Transaction { + fn drop(self: Pin<&mut Self>) { + self.drop_outstanding_txn(); + } +} diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 8b08976146ba..342574bfd28a 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -537,8 +537,8 @@ struct binder_transaction { struct binder_proc *to_proc; struct binder_thread *to_thread; struct binder_transaction *to_parent; - unsigned need_reply:1; - /* unsigned is_dead:1; */ /* not used at the moment */ + unsigned is_async:1; + unsigned is_reply:1; struct binder_buffer *buffer; unsigned int code; diff --git a/drivers/android/binder_netlink.c b/drivers/android/binder_netlink.c new file mode 100644 index 000000000000..d05397a50ca6 --- /dev/null +++ b/drivers/android/binder_netlink.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/binder.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "binder_netlink.h" + +#include <uapi/linux/android/binder_netlink.h> + +/* Ops table for binder */ +static const struct genl_split_ops binder_nl_ops[] = { +}; + +static const struct genl_multicast_group binder_nl_mcgrps[] = { + [BINDER_NLGRP_REPORT] = { "report", }, +}; + +struct genl_family binder_nl_family __ro_after_init = { + .name = BINDER_FAMILY_NAME, + .version = BINDER_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = binder_nl_ops, + .n_split_ops = ARRAY_SIZE(binder_nl_ops), + .mcgrps = binder_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(binder_nl_mcgrps), +}; diff --git a/drivers/android/binder_netlink.h b/drivers/android/binder_netlink.h new file mode 100644 index 000000000000..882c7a6b537e --- /dev/null +++ b/drivers/android/binder_netlink.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/binder.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_BINDER_GEN_H +#define _LINUX_BINDER_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/android/binder_netlink.h> + +enum { + BINDER_NLGRP_REPORT, +}; + +extern struct genl_family binder_nl_family; + +#endif /* _LINUX_BINDER_GEN_H */ diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index 97a78e5623db..fa5eb61cf580 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -402,6 +402,43 @@ TRACE_EVENT(binder_return, "unknown") ); +TRACE_EVENT(binder_netlink_report, + TP_PROTO(const char *context, + struct binder_transaction *t, + u32 data_size, + u32 error), + TP_ARGS(context, t, data_size, error), + TP_STRUCT__entry( + __field(const char *, context) + __field(u32, error) + __field(int, from_pid) + __field(int, from_tid) + __field(int, to_pid) + __field(int, to_tid) + __field(bool, is_reply) + __field(unsigned int, flags) + __field(unsigned int, code) + __field(size_t, data_size) + ), + TP_fast_assign( + __entry->context = context; + __entry->error = error; + __entry->from_pid = t->from_pid; + __entry->from_tid = t->from_tid; + __entry->to_pid = t->to_proc ? t->to_proc->pid : 0; + __entry->to_tid = t->to_thread ? t->to_thread->pid : 0; + __entry->is_reply = t->is_reply; + __entry->flags = t->flags; + __entry->code = t->code; + __entry->data_size = data_size; + ), + TP_printk("from %d:%d to %d:%d context=%s error=%d is_reply=%d flags=0x%x code=0x%x size=%zu", + __entry->from_pid, __entry->from_tid, + __entry->to_pid, __entry->to_tid, + __entry->context, __entry->error, __entry->is_reply, + __entry->flags, __entry->code, __entry->data_size) +); + #endif /* _BINDER_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 0d9d95a7fb60..be8e64eb39ec 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -59,6 +59,7 @@ struct binder_features { bool oneway_spam_detection; bool extended_error; bool freeze_notification; + bool transaction_report; }; static const struct constant_table binderfs_param_stats[] = { @@ -76,6 +77,7 @@ static struct binder_features binder_features = { .oneway_spam_detection = true, .extended_error = true, .freeze_notification = true, + .transaction_report = true, }; static inline struct binderfs_info *BINDERFS_SB(const struct super_block *sb) @@ -601,6 +603,12 @@ static int init_binder_features(struct super_block *sb) if (IS_ERR(dentry)) return PTR_ERR(dentry); + dentry = binderfs_create_file(dir, "transaction_report", + &binder_features_fops, + &binder_features.transaction_report); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + return 0; } diff --git a/drivers/android/dbitmap.h b/drivers/android/dbitmap.h index 956f1bd087d1..c7299ce8b374 100644 --- a/drivers/android/dbitmap.h +++ b/drivers/android/dbitmap.h @@ -37,6 +37,7 @@ static inline void dbitmap_free(struct dbitmap *dmap) { dmap->nbits = 0; kfree(dmap->map); + dmap->map = NULL; } /* Returns the nbits that a dbitmap can shrink to, 0 if not possible. */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 2946ae6d4b2c..2586e77ebf45 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2075,7 +2075,7 @@ out: * Check if a link is established. This is a relaxed version of * ata_phys_link_online() which accounts for the fact that this is potentially * called after changing the link power management policy, which may not be - * reflected immediately in the SSTAUS register (e.g., we may still be seeing + * reflected immediately in the SStatus register (e.g., we may still be seeing * the PHY in partial, slumber or devsleep Partial power management state. * So check that: * - A device is still present, that is, DET is 1h (Device presence detected @@ -2089,8 +2089,13 @@ static bool ata_eh_link_established(struct ata_link *link) u32 sstatus; u8 det, ipm; + /* + * For old IDE/PATA adapters that do not have a valid scr_read method, + * or if reading the SStatus register fails, assume that the device is + * present. Device probe will determine if that is really the case. + */ if (sata_scr_read(link, SCR_STATUS, &sstatus)) - return false; + return true; det = sstatus & 0x0f; ipm = (sstatus >> 8) & 0x0f; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 57f674f51b0c..2ded5e476d6e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3904,21 +3904,16 @@ static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc, /* Check cdl_ctrl */ switch (buf[0] & 0x03) { case 0: - /* Disable CDL if it is enabled */ - if (!(dev->flags & ATA_DFLAG_CDL_ENABLED)) - return 0; + /* Disable CDL */ ata_dev_dbg(dev, "Disabling CDL\n"); cdl_action = 0; dev->flags &= ~ATA_DFLAG_CDL_ENABLED; break; case 0x02: /* - * Enable CDL if not already enabled. Since this is mutually - * exclusive with NCQ priority, allow this only if NCQ priority - * is disabled. + * Enable CDL. Since CDL is mutually exclusive with NCQ + * priority, allow this only if NCQ priority is disabled. */ - if (dev->flags & ATA_DFLAG_CDL_ENABLED) - return 0; if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) { ata_dev_err(dev, "NCQ priority must be disabled to enable CDL\n"); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index e21492981f7d..f6d6276974ee 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -380,6 +380,9 @@ enum { /* this is/was a write request */ __EE_WRITE, + /* hand back using mempool_free(e, drbd_buffer_page_pool) */ + __EE_RELEASE_TO_MEMPOOL, + /* this is/was a write same request */ __EE_WRITE_SAME, @@ -402,6 +405,7 @@ enum { #define EE_IN_INTERVAL_TREE (1<<__EE_IN_INTERVAL_TREE) #define EE_SUBMITTED (1<<__EE_SUBMITTED) #define EE_WRITE (1<<__EE_WRITE) +#define EE_RELEASE_TO_MEMPOOL (1<<__EE_RELEASE_TO_MEMPOOL) #define EE_WRITE_SAME (1<<__EE_WRITE_SAME) #define EE_APPLICATION (1<<__EE_APPLICATION) #define EE_RS_THIN_REQ (1<<__EE_RS_THIN_REQ) @@ -858,7 +862,6 @@ struct drbd_device { struct list_head sync_ee; /* IO in progress (P_RS_DATA_REPLY gets written to disk) */ struct list_head done_ee; /* need to send P_WRITE_ACK */ struct list_head read_ee; /* [RS]P_DATA_REQUEST being read */ - struct list_head net_ee; /* zero-copy network send in progress */ struct list_head resync_reads; atomic_t pp_in_use; /* allocated from page pool */ @@ -1329,24 +1332,6 @@ extern struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ extern mempool_t drbd_request_mempool; extern mempool_t drbd_ee_mempool; -/* drbd's page pool, used to buffer data received from the peer, - * or data requested by the peer. - * - * This does not have an emergency reserve. - * - * When allocating from this pool, it first takes pages from the pool. - * Only if the pool is depleted will try to allocate from the system. - * - * The assumption is that pages taken from this pool will be processed, - * and given back, "quickly", and then can be recycled, so we can avoid - * frequent calls to alloc_page(), and still will be able to make progress even - * under memory pressure. - */ -extern struct page *drbd_pp_pool; -extern spinlock_t drbd_pp_lock; -extern int drbd_pp_vacant; -extern wait_queue_head_t drbd_pp_wait; - /* We also need a standard (emergency-reserve backed) page pool * for meta data IO (activity log, bitmap). * We can keep it global, as long as it is used as "N pages at a time". @@ -1354,6 +1339,7 @@ extern wait_queue_head_t drbd_pp_wait; */ #define DRBD_MIN_POOL_PAGES 128 extern mempool_t drbd_md_io_page_pool; +extern mempool_t drbd_buffer_page_pool; /* We also need to make sure we get a bio * when we need it for housekeeping purposes */ @@ -1488,10 +1474,7 @@ extern struct drbd_peer_request *drbd_alloc_peer_req(struct drbd_peer_device *, sector_t, unsigned int, unsigned int, gfp_t) __must_hold(local); -extern void __drbd_free_peer_req(struct drbd_device *, struct drbd_peer_request *, - int); -#define drbd_free_peer_req(m,e) __drbd_free_peer_req(m, e, 0) -#define drbd_free_net_peer_req(m,e) __drbd_free_peer_req(m, e, 1) +extern void drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *req); extern struct page *drbd_alloc_pages(struct drbd_peer_device *, unsigned int, bool); extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed); extern int drbd_connected(struct drbd_peer_device *); @@ -1610,16 +1593,6 @@ static inline struct page *page_chain_next(struct page *page) for (; page && ({ n = page_chain_next(page); 1; }); page = n) -static inline int drbd_peer_req_has_active_page(struct drbd_peer_request *peer_req) -{ - struct page *page = peer_req->pages; - page_chain_for_each(page) { - if (page_count(page) > 1) - return 1; - } - return 0; -} - static inline union drbd_state drbd_read_state(struct drbd_device *device) { struct drbd_resource *resource = device->resource; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 52724b79be30..c73376886e7a 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -114,20 +114,10 @@ struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ mempool_t drbd_request_mempool; mempool_t drbd_ee_mempool; mempool_t drbd_md_io_page_pool; +mempool_t drbd_buffer_page_pool; struct bio_set drbd_md_io_bio_set; struct bio_set drbd_io_bio_set; -/* I do not use a standard mempool, because: - 1) I want to hand out the pre-allocated objects first. - 2) I want to be able to interrupt sleeping allocation with a signal. - Note: This is a single linked list, the next pointer is the private - member of struct page. - */ -struct page *drbd_pp_pool; -DEFINE_SPINLOCK(drbd_pp_lock); -int drbd_pp_vacant; -wait_queue_head_t drbd_pp_wait; - DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5); static const struct block_device_operations drbd_ops = { @@ -1611,6 +1601,7 @@ static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *b static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, struct drbd_peer_request *peer_req) { + bool use_sendpage = !(peer_req->flags & EE_RELEASE_TO_MEMPOOL); struct page *page = peer_req->pages; unsigned len = peer_req->i.size; int err; @@ -1619,8 +1610,13 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, page_chain_for_each(page) { unsigned l = min_t(unsigned, len, PAGE_SIZE); - err = _drbd_send_page(peer_device, page, 0, l, - page_chain_next(page) ? MSG_MORE : 0); + if (likely(use_sendpage)) + err = _drbd_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + else + err = _drbd_no_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + if (err) return err; len -= l; @@ -1962,7 +1958,6 @@ void drbd_init_set_defaults(struct drbd_device *device) INIT_LIST_HEAD(&device->sync_ee); INIT_LIST_HEAD(&device->done_ee); INIT_LIST_HEAD(&device->read_ee); - INIT_LIST_HEAD(&device->net_ee); INIT_LIST_HEAD(&device->resync_reads); INIT_LIST_HEAD(&device->resync_work.list); INIT_LIST_HEAD(&device->unplug_work.list); @@ -2043,7 +2038,6 @@ void drbd_device_cleanup(struct drbd_device *device) D_ASSERT(device, list_empty(&device->sync_ee)); D_ASSERT(device, list_empty(&device->done_ee)); D_ASSERT(device, list_empty(&device->read_ee)); - D_ASSERT(device, list_empty(&device->net_ee)); D_ASSERT(device, list_empty(&device->resync_reads)); D_ASSERT(device, list_empty(&first_peer_device(device)->connection->sender_work.q)); D_ASSERT(device, list_empty(&device->resync_work.list)); @@ -2055,19 +2049,11 @@ void drbd_device_cleanup(struct drbd_device *device) static void drbd_destroy_mempools(void) { - struct page *page; - - while (drbd_pp_pool) { - page = drbd_pp_pool; - drbd_pp_pool = (struct page *)page_private(page); - __free_page(page); - drbd_pp_vacant--; - } - /* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */ bioset_exit(&drbd_io_bio_set); bioset_exit(&drbd_md_io_bio_set); + mempool_exit(&drbd_buffer_page_pool); mempool_exit(&drbd_md_io_page_pool); mempool_exit(&drbd_ee_mempool); mempool_exit(&drbd_request_mempool); @@ -2086,9 +2072,8 @@ static void drbd_destroy_mempools(void) static int drbd_create_mempools(void) { - struct page *page; const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count; - int i, ret; + int ret; /* caches */ drbd_request_cache = kmem_cache_create( @@ -2125,6 +2110,10 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; + ret = mempool_init_page_pool(&drbd_buffer_page_pool, number, 0); + if (ret) + goto Enomem; + ret = mempool_init_slab_pool(&drbd_request_mempool, number, drbd_request_cache); if (ret) @@ -2134,15 +2123,6 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; - for (i = 0; i < number; i++) { - page = alloc_page(GFP_HIGHUSER); - if (!page) - goto Enomem; - set_page_private(page, (unsigned long)drbd_pp_pool); - drbd_pp_pool = page; - } - drbd_pp_vacant = number; - return 0; Enomem: @@ -2169,10 +2149,6 @@ static void drbd_release_all_peer_reqs(struct drbd_device *device) rr = drbd_free_peer_reqs(device, &device->done_ee); if (rr) drbd_err(device, "%d EEs in done list found!\n", rr); - - rr = drbd_free_peer_reqs(device, &device->net_ee); - if (rr) - drbd_err(device, "%d EEs in net list found!\n", rr); } /* caution. no locking. */ @@ -2863,11 +2839,6 @@ static int __init drbd_init(void) return err; } - /* - * allocate all necessary structs - */ - init_waitqueue_head(&drbd_pp_wait); - drbd_proc = NULL; /* play safe for drbd_cleanup */ idr_init(&drbd_devices); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 975024cf03c5..caaf2781136d 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/scatterlist.h> #include <linux/part_stat.h> +#include <linux/mempool.h> #include "drbd_int.h" #include "drbd_protocol.h" #include "drbd_req.h" @@ -63,182 +64,31 @@ static int e_end_block(struct drbd_work *, int); #define GFP_TRY (__GFP_HIGHMEM | __GFP_NOWARN) -/* - * some helper functions to deal with single linked page lists, - * page->private being our "next" pointer. - */ - -/* If at least n pages are linked at head, get n pages off. - * Otherwise, don't modify head, and return NULL. - * Locking is the responsibility of the caller. - */ -static struct page *page_chain_del(struct page **head, int n) -{ - struct page *page; - struct page *tmp; - - BUG_ON(!n); - BUG_ON(!head); - - page = *head; - - if (!page) - return NULL; - - while (page) { - tmp = page_chain_next(page); - if (--n == 0) - break; /* found sufficient pages */ - if (tmp == NULL) - /* insufficient pages, don't use any of them. */ - return NULL; - page = tmp; - } - - /* add end of list marker for the returned list */ - set_page_private(page, 0); - /* actual return value, and adjustment of head */ - page = *head; - *head = tmp; - return page; -} - -/* may be used outside of locks to find the tail of a (usually short) - * "private" page chain, before adding it back to a global chain head - * with page_chain_add() under a spinlock. */ -static struct page *page_chain_tail(struct page *page, int *len) -{ - struct page *tmp; - int i = 1; - while ((tmp = page_chain_next(page))) { - ++i; - page = tmp; - } - if (len) - *len = i; - return page; -} - -static int page_chain_free(struct page *page) -{ - struct page *tmp; - int i = 0; - page_chain_for_each_safe(page, tmp) { - put_page(page); - ++i; - } - return i; -} - -static void page_chain_add(struct page **head, - struct page *chain_first, struct page *chain_last) -{ -#if 1 - struct page *tmp; - tmp = page_chain_tail(chain_first, NULL); - BUG_ON(tmp != chain_last); -#endif - - /* add chain to head */ - set_page_private(chain_last, (unsigned long)*head); - *head = chain_first; -} - -static struct page *__drbd_alloc_pages(struct drbd_device *device, - unsigned int number) +static struct page *__drbd_alloc_pages(unsigned int number) { struct page *page = NULL; struct page *tmp = NULL; unsigned int i = 0; - /* Yes, testing drbd_pp_vacant outside the lock is racy. - * So what. It saves a spin_lock. */ - if (drbd_pp_vacant >= number) { - spin_lock(&drbd_pp_lock); - page = page_chain_del(&drbd_pp_pool, number); - if (page) - drbd_pp_vacant -= number; - spin_unlock(&drbd_pp_lock); - if (page) - return page; - } - /* GFP_TRY, because we must not cause arbitrary write-out: in a DRBD * "criss-cross" setup, that might cause write-out on some other DRBD, * which in turn might block on the other node at this very place. */ for (i = 0; i < number; i++) { - tmp = alloc_page(GFP_TRY); + tmp = mempool_alloc(&drbd_buffer_page_pool, GFP_TRY); if (!tmp) - break; + goto fail; set_page_private(tmp, (unsigned long)page); page = tmp; } - - if (i == number) - return page; - - /* Not enough pages immediately available this time. - * No need to jump around here, drbd_alloc_pages will retry this - * function "soon". */ - if (page) { - tmp = page_chain_tail(page, NULL); - spin_lock(&drbd_pp_lock); - page_chain_add(&drbd_pp_pool, page, tmp); - drbd_pp_vacant += i; - spin_unlock(&drbd_pp_lock); + return page; +fail: + page_chain_for_each_safe(page, tmp) { + set_page_private(page, 0); + mempool_free(page, &drbd_buffer_page_pool); } return NULL; } -static void reclaim_finished_net_peer_reqs(struct drbd_device *device, - struct list_head *to_be_freed) -{ - struct drbd_peer_request *peer_req, *tmp; - - /* The EEs are always appended to the end of the list. Since - they are sent in order over the wire, they have to finish - in order. As soon as we see the first not finished we can - stop to examine the list... */ - - list_for_each_entry_safe(peer_req, tmp, &device->net_ee, w.list) { - if (drbd_peer_req_has_active_page(peer_req)) - break; - list_move(&peer_req->w.list, to_be_freed); - } -} - -static void drbd_reclaim_net_peer_reqs(struct drbd_device *device) -{ - LIST_HEAD(reclaimed); - struct drbd_peer_request *peer_req, *t; - - spin_lock_irq(&device->resource->req_lock); - reclaim_finished_net_peer_reqs(device, &reclaimed); - spin_unlock_irq(&device->resource->req_lock); - list_for_each_entry_safe(peer_req, t, &reclaimed, w.list) - drbd_free_net_peer_req(device, peer_req); -} - -static void conn_reclaim_net_peer_reqs(struct drbd_connection *connection) -{ - struct drbd_peer_device *peer_device; - int vnr; - - rcu_read_lock(); - idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { - struct drbd_device *device = peer_device->device; - if (!atomic_read(&device->pp_in_use_by_net)) - continue; - - kref_get(&device->kref); - rcu_read_unlock(); - drbd_reclaim_net_peer_reqs(device); - kref_put(&device->kref, drbd_destroy_device); - rcu_read_lock(); - } - rcu_read_unlock(); -} - /** * drbd_alloc_pages() - Returns @number pages, retries forever (or until signalled) * @peer_device: DRBD device. @@ -263,9 +113,8 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int bool retry) { struct drbd_device *device = peer_device->device; - struct page *page = NULL; + struct page *page; struct net_conf *nc; - DEFINE_WAIT(wait); unsigned int mxb; rcu_read_lock(); @@ -273,37 +122,9 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int mxb = nc ? nc->max_buffers : 1000000; rcu_read_unlock(); - if (atomic_read(&device->pp_in_use) < mxb) - page = __drbd_alloc_pages(device, number); - - /* Try to keep the fast path fast, but occasionally we need - * to reclaim the pages we lended to the network stack. */ - if (page && atomic_read(&device->pp_in_use_by_net) > 512) - drbd_reclaim_net_peer_reqs(device); - - while (page == NULL) { - prepare_to_wait(&drbd_pp_wait, &wait, TASK_INTERRUPTIBLE); - - drbd_reclaim_net_peer_reqs(device); - - if (atomic_read(&device->pp_in_use) < mxb) { - page = __drbd_alloc_pages(device, number); - if (page) - break; - } - - if (!retry) - break; - - if (signal_pending(current)) { - drbd_warn(device, "drbd_alloc_pages interrupted!\n"); - break; - } - - if (schedule_timeout(HZ/10) == 0) - mxb = UINT_MAX; - } - finish_wait(&drbd_pp_wait, &wait); + if (atomic_read(&device->pp_in_use) >= mxb) + schedule_timeout_interruptible(HZ / 10); + page = __drbd_alloc_pages(number); if (page) atomic_add(number, &device->pp_in_use); @@ -314,29 +135,25 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int * Is also used from inside an other spin_lock_irq(&resource->req_lock); * Either links the page chain back to the global pool, * or returns all pages to the system. */ -static void drbd_free_pages(struct drbd_device *device, struct page *page, int is_net) +static void drbd_free_pages(struct drbd_device *device, struct page *page) { - atomic_t *a = is_net ? &device->pp_in_use_by_net : &device->pp_in_use; - int i; + struct page *tmp; + int i = 0; if (page == NULL) return; - if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count) - i = page_chain_free(page); - else { - struct page *tmp; - tmp = page_chain_tail(page, &i); - spin_lock(&drbd_pp_lock); - page_chain_add(&drbd_pp_pool, page, tmp); - drbd_pp_vacant += i; - spin_unlock(&drbd_pp_lock); - } - i = atomic_sub_return(i, a); + page_chain_for_each_safe(page, tmp) { + set_page_private(page, 0); + if (page_count(page) == 1) + mempool_free(page, &drbd_buffer_page_pool); + else + put_page(page); + i++; + } + i = atomic_sub_return(i, &device->pp_in_use); if (i < 0) - drbd_warn(device, "ASSERTION FAILED: %s: %d < 0\n", - is_net ? "pp_in_use_by_net" : "pp_in_use", i); - wake_up(&drbd_pp_wait); + drbd_warn(device, "ASSERTION FAILED: pp_in_use: %d < 0\n", i); } /* @@ -380,6 +197,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto gfpflags_allow_blocking(gfp_mask)); if (!page) goto fail; + if (!mempool_is_saturated(&drbd_buffer_page_pool)) + peer_req->flags |= EE_RELEASE_TO_MEMPOOL; } memset(peer_req, 0, sizeof(*peer_req)); @@ -403,13 +222,12 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto return NULL; } -void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *peer_req, - int is_net) +void drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *peer_req) { might_sleep(); if (peer_req->flags & EE_HAS_DIGEST) kfree(peer_req->digest); - drbd_free_pages(device, peer_req->pages, is_net); + drbd_free_pages(device, peer_req->pages); D_ASSERT(device, atomic_read(&peer_req->pending_bios) == 0); D_ASSERT(device, drbd_interval_empty(&peer_req->i)); if (!expect(device, !(peer_req->flags & EE_CALL_AL_COMPLETE_IO))) { @@ -424,14 +242,13 @@ int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list) LIST_HEAD(work_list); struct drbd_peer_request *peer_req, *t; int count = 0; - int is_net = list == &device->net_ee; spin_lock_irq(&device->resource->req_lock); list_splice_init(list, &work_list); spin_unlock_irq(&device->resource->req_lock); list_for_each_entry_safe(peer_req, t, &work_list, w.list) { - __drbd_free_peer_req(device, peer_req, is_net); + drbd_free_peer_req(device, peer_req); count++; } return count; @@ -443,18 +260,13 @@ int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list) static int drbd_finish_peer_reqs(struct drbd_device *device) { LIST_HEAD(work_list); - LIST_HEAD(reclaimed); struct drbd_peer_request *peer_req, *t; int err = 0; spin_lock_irq(&device->resource->req_lock); - reclaim_finished_net_peer_reqs(device, &reclaimed); list_splice_init(&device->done_ee, &work_list); spin_unlock_irq(&device->resource->req_lock); - list_for_each_entry_safe(peer_req, t, &reclaimed, w.list) - drbd_free_net_peer_req(device, peer_req); - /* possible callbacks here: * e_end_block, and e_end_resync_block, e_send_superseded. * all ignore the last argument. @@ -1975,7 +1787,7 @@ static int drbd_drain_block(struct drbd_peer_device *peer_device, int data_size) data_size -= len; } kunmap(page); - drbd_free_pages(peer_device->device, page, 0); + drbd_free_pages(peer_device->device, page); return err; } @@ -5224,16 +5036,6 @@ static int drbd_disconnected(struct drbd_peer_device *peer_device) put_ldev(device); } - /* tcp_close and release of sendpage pages can be deferred. I don't - * want to use SO_LINGER, because apparently it can be deferred for - * more than 20 seconds (longest time I checked). - * - * Actually we don't care for exactly when the network stack does its - * put_page(), but release our reference on these pages right here. - */ - i = drbd_free_peer_reqs(device, &device->net_ee); - if (i) - drbd_info(device, "net_ee not empty, killed %u entries\n", i); i = atomic_read(&device->pp_in_use_by_net); if (i) drbd_info(device, "pp_in_use_by_net = %d, expected 0\n", i); @@ -5980,8 +5782,6 @@ int drbd_ack_receiver(struct drbd_thread *thi) while (get_t_state(thi) == RUNNING) { drbd_thread_current_set_cpu(thi); - conn_reclaim_net_peer_reqs(connection); - if (test_and_clear_bit(SEND_PING, &connection->flags)) { if (drbd_send_ping(connection)) { drbd_err(connection, "drbd_send_ping has failed\n"); diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index a6ea737b3b71..dea3e79d044f 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1030,22 +1030,6 @@ out: return 1; } -/* helper */ -static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_request *peer_req) -{ - if (drbd_peer_req_has_active_page(peer_req)) { - /* This might happen if sendpage() has not finished */ - int i = PFN_UP(peer_req->i.size); - atomic_add(i, &device->pp_in_use_by_net); - atomic_sub(i, &device->pp_in_use); - spin_lock_irq(&device->resource->req_lock); - list_add_tail(&peer_req->w.list, &device->net_ee); - spin_unlock_irq(&device->resource->req_lock); - wake_up(&drbd_pp_wait); - } else - drbd_free_peer_req(device, peer_req); -} - /** * w_e_end_data_req() - Worker callback, to send a P_DATA_REPLY packet in response to a P_DATA_REQUEST * @w: work object. @@ -1059,9 +1043,8 @@ int w_e_end_data_req(struct drbd_work *w, int cancel) int err; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (likely((peer_req->flags & EE_WAS_ERROR) == 0)) { @@ -1074,12 +1057,12 @@ int w_e_end_data_req(struct drbd_work *w, int cancel) err = drbd_send_ack(peer_device, P_NEG_DREPLY, peer_req); } - dec_unacked(device); - - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } @@ -1120,9 +1103,8 @@ int w_e_end_rsdata_req(struct drbd_work *w, int cancel) int err; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (get_ldev_if_state(device, D_FAILED)) { @@ -1155,13 +1137,12 @@ int w_e_end_rsdata_req(struct drbd_work *w, int cancel) /* update resync data with failure */ drbd_rs_failed_io(peer_device, peer_req->i.sector, peer_req->i.size); } - - dec_unacked(device); - - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } @@ -1176,9 +1157,8 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel) int err, eq = 0; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (get_ldev(device)) { @@ -1220,12 +1200,12 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel) if (drbd_ratelimit()) drbd_err(device, "Sending NegDReply. I guess it gets messy.\n"); } - - dec_unacked(device); - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block/ack() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1b6ee91f8eb9..57263c273f0f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -137,20 +137,29 @@ static void loop_global_unlock(struct loop_device *lo, bool global) static int max_part; static int part_shift; -static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) +static loff_t lo_calculate_size(struct loop_device *lo, struct file *file) { + struct kstat stat; loff_t loopsize; + int ret; - /* Compute loopsize in bytes */ - loopsize = i_size_read(file->f_mapping->host); - if (offset > 0) - loopsize -= offset; + /* + * Get the accurate file size. This provides better results than + * cached inode data, particularly for network filesystems where + * metadata may be stale. + */ + ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0); + if (ret) + return 0; + + loopsize = stat.size; + if (lo->lo_offset > 0) + loopsize -= lo->lo_offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; - - if (sizelimit > 0 && sizelimit < loopsize) - loopsize = sizelimit; + if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize) + loopsize = lo->lo_sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. @@ -158,11 +167,6 @@ static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) return loopsize >> 9; } -static loff_t get_loop_size(struct loop_device *lo, struct file *file) -{ - return get_size(lo->lo_offset, lo->lo_sizelimit, file); -} - /* * We support direct I/O only if lo_offset is aligned with the logical I/O size * of backing device, and the logical block size of loop is bigger than that of @@ -569,7 +573,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, error = -EINVAL; /* size of the new backing store needs to be the same */ - if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) + if (lo_calculate_size(lo, file) != lo_calculate_size(lo, old_file)) goto out_err; /* @@ -1063,7 +1067,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, loop_update_dio(lo); loop_sysfs_init(lo); - size = get_loop_size(lo, file); + size = lo_calculate_size(lo, file); loop_set_size(lo, size); /* Order wrt reading lo_state in loop_validate_file(). */ @@ -1255,8 +1259,7 @@ out_unfreeze: if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); if (!err && size_changed) { - loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, - lo->lo_backing_file); + loff_t new_size = lo_calculate_size(lo, lo->lo_backing_file); loop_set_size(lo, new_size); } out_unlock: @@ -1399,7 +1402,7 @@ static int loop_set_capacity(struct loop_device *lo) if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; - size = get_loop_size(lo, lo->lo_backing_file); + size = lo_calculate_size(lo, lo->lo_backing_file); loop_set_size(lo, size); return 0; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6561d2a561fa..99abd67b708b 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -235,7 +235,7 @@ struct ublk_device { struct completion completion; unsigned int nr_queues_ready; - unsigned int nr_privileged_daemon; + bool unprivileged_daemons; struct mutex cancel_mutex; bool canceling; pid_t ublksrv_tgid; @@ -1389,7 +1389,7 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq, { blk_status_t res; - if (unlikely(ubq->fail_io)) + if (unlikely(READ_ONCE(ubq->fail_io))) return BLK_STS_TARGET; /* With recovery feature enabled, force_abort is set in @@ -1401,7 +1401,8 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq, * Note: force_abort is guaranteed to be seen because it is set * before request queue is unqiuesced. */ - if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort)) + if (ublk_nosrv_should_queue_io(ubq) && + unlikely(READ_ONCE(ubq->force_abort))) return BLK_STS_IOERR; if (check_cancel && unlikely(ubq->canceling)) @@ -1550,7 +1551,7 @@ static void ublk_reset_ch_dev(struct ublk_device *ub) /* set to NULL, otherwise new tasks cannot mmap io_cmd_buf */ ub->mm = NULL; ub->nr_queues_ready = 0; - ub->nr_privileged_daemon = 0; + ub->unprivileged_daemons = false; ub->ublksrv_tgid = -1; } @@ -1644,7 +1645,6 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) * Transition the device to the nosrv state. What exactly this * means depends on the recovery flags */ - blk_mq_quiesce_queue(disk->queue); if (ublk_nosrv_should_stop_dev(ub)) { /* * Allow any pending/future I/O to pass through quickly @@ -1652,8 +1652,7 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) * waits for all pending I/O to complete */ for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_get_queue(ub, i)->force_abort = true; - blk_mq_unquiesce_queue(disk->queue); + WRITE_ONCE(ublk_get_queue(ub, i)->force_abort, true); ublk_stop_dev_unlocked(ub); } else { @@ -1663,9 +1662,8 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) } else { ub->dev_info.state = UBLK_S_DEV_FAIL_IO; for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_get_queue(ub, i)->fail_io = true; + WRITE_ONCE(ublk_get_queue(ub, i)->fail_io, true); } - blk_mq_unquiesce_queue(disk->queue); } unlock: mutex_unlock(&ub->mutex); @@ -1980,12 +1978,10 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) __must_hold(&ub->mutex) { ubq->nr_io_ready++; - if (ublk_queue_ready(ubq)) { + if (ublk_queue_ready(ubq)) ub->nr_queues_ready++; - - if (capable(CAP_SYS_ADMIN)) - ub->nr_privileged_daemon++; - } + if (!ub->unprivileged_daemons && !capable(CAP_SYS_ADMIN)) + ub->unprivileged_daemons = true; if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) { /* now we are ready for handling ublk io request */ @@ -2880,8 +2876,8 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, ublk_apply_params(ub); - /* don't probe partitions if any one ubq daemon is un-trusted */ - if (ub->nr_privileged_daemon != ub->nr_queues_ready) + /* don't probe partitions if any daemon task is un-trusted */ + if (ub->unprivileged_daemons) set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); ublk_get_device(ub); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 4390fd571dbd..a8c520dc09e1 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -642,12 +642,7 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, * WMT command. */ err = wait_on_bit_timeout(&data->flags, BTMTK_TX_WAIT_VND_EVT, - TASK_INTERRUPTIBLE, HCI_INIT_TIMEOUT); - if (err == -EINTR) { - bt_dev_err(hdev, "Execution of wmt command interrupted"); - clear_bit(BTMTK_TX_WAIT_VND_EVT, &data->flags); - goto err_free_wc; - } + TASK_UNINTERRUPTIBLE, HCI_INIT_TIMEOUT); if (err) { bt_dev_err(hdev, "Execution of wmt command timed out"); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 73a4a325c867..76e7f857fb7d 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -543,10 +543,10 @@ static int ps_setup(struct hci_dev *hdev) } if (psdata->wakeup_source) { - ret = devm_request_irq(&serdev->dev, psdata->irq_handler, - ps_host_wakeup_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, - dev_name(&serdev->dev), nxpdev); + ret = devm_request_threaded_irq(&serdev->dev, psdata->irq_handler, + NULL, ps_host_wakeup_irq_handler, + IRQF_ONESHOT, + dev_name(&serdev->dev), nxpdev); if (ret) bt_dev_info(hdev, "error setting wakeup IRQ handler, ignoring\n"); disable_irq(psdata->irq_handler); diff --git a/drivers/cdx/cdx_msi.c b/drivers/cdx/cdx_msi.c index 3388a5d1462c..91b95422b263 100644 --- a/drivers/cdx/cdx_msi.c +++ b/drivers/cdx/cdx_msi.c @@ -174,6 +174,7 @@ struct irq_domain *cdx_msi_domain_init(struct device *dev) } parent = irq_find_matching_fwnode(of_fwnode_handle(parent_node), DOMAIN_BUS_NEXUS); + of_node_put(parent_node); if (!parent || !msi_get_domain_info(parent)) { dev_err(dev, "unable to locate ITS domain\n"); return NULL; diff --git a/drivers/cdx/controller/cdx_rpmsg.c b/drivers/cdx/controller/cdx_rpmsg.c index 04b578a0be17..61f1a290ff08 100644 --- a/drivers/cdx/controller/cdx_rpmsg.c +++ b/drivers/cdx/controller/cdx_rpmsg.c @@ -129,8 +129,7 @@ static int cdx_rpmsg_probe(struct rpmsg_device *rpdev) chinfo.src = RPMSG_ADDR_ANY; chinfo.dst = rpdev->dst; - strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, - strlen(cdx_rpmsg_id_table[0].name)); + strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, sizeof(chinfo.name)); cdx_mcdi->ept = rpmsg_create_ept(rpdev, cdx_rpmsg_cb, NULL, chinfo); if (!cdx_mcdi->ept) { diff --git a/drivers/char/Makefile b/drivers/char/Makefile index e9b360cdc99a..1291369b9126 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -6,6 +6,7 @@ obj-y += mem.o random.o obj-$(CONFIG_TTY_PRINTK) += ttyprintk.o obj-y += misc.o +obj-$(CONFIG_TEST_MISC_MINOR) += misc_minor_kunit.o obj-$(CONFIG_ATARI_DSP56K) += dsp56k.o obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o obj-$(CONFIG_UV_MMTIMER) += uv_mmtimer.o diff --git a/drivers/char/adi.c b/drivers/char/adi.c index f9bec10a6064..4312b0cc391c 100644 --- a/drivers/char/adi.c +++ b/drivers/char/adi.c @@ -131,7 +131,7 @@ static ssize_t adi_write(struct file *file, const char __user *buf, ssize_t ret; int i; - if (count <= 0) + if (count == 0) return -EINVAL; ver_buf_sz = min_t(size_t, count, MAX_BUF_SZ); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 0713ea2b2a51..4f5ccd3a1f56 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -867,7 +867,7 @@ int hpet_alloc(struct hpet_data *hdp) printk(KERN_INFO "hpet%u: at MMIO 0x%lx, IRQ%s", hpetp->hp_which, hdp->hd_phys_address, - hpetp->hp_ntimer > 1 ? "s" : ""); + str_plural(hpetp->hp_ntimer)); for (i = 0; i < hpetp->hp_ntimer; i++) printk(KERN_CONT "%s %u", i > 0 ? "," : "", hdp->hd_irq[i]); printk(KERN_CONT "\n"); diff --git a/drivers/char/misc.c b/drivers/char/misc.c index 558302a64dd9..726516fb0a3b 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -132,7 +132,8 @@ static int misc_open(struct inode *inode, struct file *file) break; } - if (!new_fops) { + /* Only request module for fixed minor code */ + if (!new_fops && minor < MISC_DYNAMIC_MINOR) { mutex_unlock(&misc_mtx); request_module("char-major-%d-%d", MISC_MAJOR, minor); mutex_lock(&misc_mtx); @@ -144,10 +145,11 @@ static int misc_open(struct inode *inode, struct file *file) new_fops = fops_get(iter->fops); break; } - if (!new_fops) - goto fail; } + if (!new_fops) + goto fail; + /* * Place the miscdevice in the file's * private_data so it can be used by the @@ -210,6 +212,12 @@ int misc_register(struct miscdevice *misc) int err = 0; bool is_dynamic = (misc->minor == MISC_DYNAMIC_MINOR); + if (misc->minor > MISC_DYNAMIC_MINOR) { + pr_err("Invalid fixed minor %d for miscdevice '%s'\n", + misc->minor, misc->name); + return -EINVAL; + } + INIT_LIST_HEAD(&misc->list); mutex_lock(&misc_mtx); @@ -275,13 +283,12 @@ EXPORT_SYMBOL(misc_register); void misc_deregister(struct miscdevice *misc) { - if (WARN_ON(list_empty(&misc->list))) - return; - mutex_lock(&misc_mtx); - list_del(&misc->list); + list_del_init(&misc->list); device_destroy(&misc_class, MKDEV(MISC_MAJOR, misc->minor)); misc_minor_free(misc->minor); + if (misc->minor > MISC_DYNAMIC_MINOR) + misc->minor = MISC_DYNAMIC_MINOR; mutex_unlock(&misc_mtx); } EXPORT_SYMBOL(misc_deregister); diff --git a/drivers/misc/misc_minor_kunit.c b/drivers/char/misc_minor_kunit.c index 30eceac5f1b6..6fc8b05169c5 100644 --- a/drivers/misc/misc_minor_kunit.c +++ b/drivers/char/misc_minor_kunit.c @@ -7,12 +7,6 @@ #include <linux/file.h> #include <linux/init_syscalls.h> -/* dynamic minor (2) */ -static struct miscdevice dev_dynamic_minor = { - .minor = 2, - .name = "dev_dynamic_minor", -}; - /* static minor (LCD_MINOR) */ static struct miscdevice dev_static_minor = { .minor = LCD_MINOR, @@ -25,16 +19,6 @@ static struct miscdevice dev_misc_dynamic_minor = { .name = "dev_misc_dynamic_minor", }; -static void kunit_dynamic_minor(struct kunit *test) -{ - int ret; - - ret = misc_register(&dev_dynamic_minor); - KUNIT_EXPECT_EQ(test, 0, ret); - KUNIT_EXPECT_EQ(test, 2, dev_dynamic_minor.minor); - misc_deregister(&dev_dynamic_minor); -} - static void kunit_static_minor(struct kunit *test) { int ret; @@ -157,13 +141,7 @@ static bool is_valid_dynamic_minor(int minor) { if (minor < 0) return false; - if (minor == MISC_DYNAMIC_MINOR) - return false; - if (minor >= 0 && minor <= 15) - return false; - if (minor >= 128 && minor < MISC_DYNAMIC_MINOR) - return false; - return true; + return minor > MISC_DYNAMIC_MINOR; } static int miscdev_test_open(struct inode *inode, struct file *file) @@ -557,7 +535,7 @@ static void __init miscdev_test_conflict(struct kunit *test) */ miscstat.minor = miscdyn.minor; ret = misc_register(&miscstat); - KUNIT_EXPECT_EQ(test, ret, -EBUSY); + KUNIT_EXPECT_EQ(test, ret, -EINVAL); if (ret == 0) misc_deregister(&miscstat); @@ -590,8 +568,9 @@ static void __init miscdev_test_conflict_reverse(struct kunit *test) misc_deregister(&miscdyn); ret = misc_register(&miscstat); - KUNIT_EXPECT_EQ(test, ret, 0); - KUNIT_EXPECT_EQ(test, miscstat.minor, miscdyn.minor); + KUNIT_EXPECT_EQ(test, ret, -EINVAL); + if (ret == 0) + misc_deregister(&miscstat); /* * Try to register a dynamic minor after registering a static minor @@ -601,25 +580,81 @@ static void __init miscdev_test_conflict_reverse(struct kunit *test) miscdyn.minor = MISC_DYNAMIC_MINOR; ret = misc_register(&miscdyn); KUNIT_EXPECT_EQ(test, ret, 0); - KUNIT_EXPECT_NE(test, miscdyn.minor, miscstat.minor); + KUNIT_EXPECT_EQ(test, miscdyn.minor, miscstat.minor); KUNIT_EXPECT_TRUE(test, is_valid_dynamic_minor(miscdyn.minor)); if (ret == 0) misc_deregister(&miscdyn); +} - miscdev_test_can_open(test, &miscstat); +/* Take minor(> MISC_DYNAMIC_MINOR) as invalid when register miscdevice */ +static void miscdev_test_invalid_input(struct kunit *test) +{ + struct miscdevice misc_test = { + .minor = MISC_DYNAMIC_MINOR + 1, + .name = "misc_test", + .fops = &miscdev_test_fops, + }; + int ret; - misc_deregister(&miscstat); + ret = misc_register(&misc_test); + KUNIT_EXPECT_EQ(test, ret, -EINVAL); + if (ret == 0) + misc_deregister(&misc_test); +} + +/* + * Verify if @miscdyn_a can still be registered successfully without + * reinitialization even if its minor ever owned was requested by + * another miscdevice such as @miscdyn_b. + */ +static void miscdev_test_dynamic_reentry(struct kunit *test) +{ + struct miscdevice miscdyn_a = { + .name = "miscdyn_a", + .minor = MISC_DYNAMIC_MINOR, + .fops = &miscdev_test_fops, + }; + struct miscdevice miscdyn_b = { + .name = "miscdyn_b", + .minor = MISC_DYNAMIC_MINOR, + .fops = &miscdev_test_fops, + }; + int ret, minor_a; + + ret = misc_register(&miscdyn_a); + KUNIT_ASSERT_EQ(test, ret, 0); + KUNIT_EXPECT_TRUE(test, is_valid_dynamic_minor(miscdyn_a.minor)); + minor_a = miscdyn_a.minor; + if (ret != 0) + return; + misc_deregister(&miscdyn_a); + + ret = misc_register(&miscdyn_b); + KUNIT_ASSERT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, miscdyn_b.minor, minor_a); + if (ret != 0) + return; + + ret = misc_register(&miscdyn_a); + KUNIT_ASSERT_EQ(test, ret, 0); + KUNIT_EXPECT_TRUE(test, is_valid_dynamic_minor(miscdyn_a.minor)); + KUNIT_EXPECT_NE(test, miscdyn_a.minor, miscdyn_b.minor); + if (ret == 0) + misc_deregister(&miscdyn_a); + + misc_deregister(&miscdyn_b); } static struct kunit_case test_cases[] = { - KUNIT_CASE(kunit_dynamic_minor), KUNIT_CASE(kunit_static_minor), KUNIT_CASE(kunit_misc_dynamic_minor), + KUNIT_CASE(miscdev_test_invalid_input), KUNIT_CASE_PARAM(miscdev_test_twice, miscdev_gen_params), KUNIT_CASE_PARAM(miscdev_test_duplicate_minor, miscdev_gen_params), KUNIT_CASE(miscdev_test_duplicate_name), KUNIT_CASE(miscdev_test_duplicate_name_leak), KUNIT_CASE_PARAM(miscdev_test_duplicate_error, miscdev_gen_params), + KUNIT_CASE(miscdev_test_dynamic_reentry), {} }; diff --git a/drivers/comedi/Kconfig b/drivers/comedi/Kconfig index 93c68a40a17b..6dcc2567de6d 100644 --- a/drivers/comedi/Kconfig +++ b/drivers/comedi/Kconfig @@ -705,6 +705,15 @@ config COMEDI_ADL_PCI6208 To compile this driver as a module, choose M here: the module will be called adl_pci6208. +config COMEDI_ADL_PCI7250 + tristate "ADLink PCI-7250 support" + help + Enable support for ADLink PCI-7250/LPCI-7250/LPCIe-7250 relay output + and isolated digital input boards. + + To compile this driver as a module, choose M here: the module will be + called adl_pci7250. + config COMEDI_ADL_PCI7X3X tristate "ADLink PCI-723X/743X isolated digital i/o board support" depends on HAS_IOPORT diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 23b7178522ae..7e2f2b1a1c36 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -1587,6 +1587,9 @@ static int do_insnlist_ioctl(struct comedi_device *dev, memset(&data[n], 0, (MIN_SAMPLES - n) * sizeof(unsigned int)); } + } else { + memset(data, 0, max_t(unsigned int, n, MIN_SAMPLES) * + sizeof(unsigned int)); } ret = parse_insn(dev, insns + i, data, file); if (ret < 0) @@ -1670,6 +1673,8 @@ static int do_insn_ioctl(struct comedi_device *dev, memset(&data[insn->n], 0, (MIN_SAMPLES - insn->n) * sizeof(unsigned int)); } + } else { + memset(data, 0, n_data * sizeof(unsigned int)); } ret = parse_insn(dev, insn, data, file); if (ret < 0) diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c index f1dc854928c1..c9ebaadc5e82 100644 --- a/drivers/comedi/drivers.c +++ b/drivers/comedi/drivers.c @@ -620,11 +620,9 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, unsigned int chan = CR_CHAN(insn->chanspec); unsigned int base_chan = (chan < 32) ? 0 : chan; unsigned int _data[2]; + unsigned int i; int ret; - if (insn->n == 0) - return 0; - memset(_data, 0, sizeof(_data)); memset(&_insn, 0, sizeof(_insn)); _insn.insn = INSN_BITS; @@ -635,18 +633,21 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, if (insn->insn == INSN_WRITE) { if (!(s->subdev_flags & SDF_WRITABLE)) return -EINVAL; - _data[0] = 1U << (chan - base_chan); /* mask */ - _data[1] = data[0] ? (1U << (chan - base_chan)) : 0; /* bits */ + _data[0] = 1U << (chan - base_chan); /* mask */ } + for (i = 0; i < insn->n; i++) { + if (insn->insn == INSN_WRITE) + _data[1] = data[i] ? _data[0] : 0; /* bits */ - ret = s->insn_bits(dev, s, &_insn, _data); - if (ret < 0) - return ret; + ret = s->insn_bits(dev, s, &_insn, _data); + if (ret < 0) + return ret; - if (insn->insn == INSN_READ) - data[0] = (_data[1] >> (chan - base_chan)) & 1; + if (insn->insn == INSN_READ) + data[i] = (_data[1] >> (chan - base_chan)) & 1; + } - return 1; + return insn->n; } static int __comedi_device_postconfig_async(struct comedi_device *dev, diff --git a/drivers/comedi/drivers/Makefile b/drivers/comedi/drivers/Makefile index b24ac00cab73..7b99a431330d 100644 --- a/drivers/comedi/drivers/Makefile +++ b/drivers/comedi/drivers/Makefile @@ -73,6 +73,7 @@ obj-$(CONFIG_COMEDI_ADDI_APCI_3120) += addi_apci_3120.o obj-$(CONFIG_COMEDI_ADDI_APCI_3501) += addi_apci_3501.o obj-$(CONFIG_COMEDI_ADDI_APCI_3XXX) += addi_apci_3xxx.o obj-$(CONFIG_COMEDI_ADL_PCI6208) += adl_pci6208.o +obj-$(CONFIG_COMEDI_ADL_PCI7250) += adl_pci7250.o obj-$(CONFIG_COMEDI_ADL_PCI7X3X) += adl_pci7x3x.o obj-$(CONFIG_COMEDI_ADL_PCI8164) += adl_pci8164.o obj-$(CONFIG_COMEDI_ADL_PCI9111) += adl_pci9111.o diff --git a/drivers/comedi/drivers/adl_pci7250.c b/drivers/comedi/drivers/adl_pci7250.c new file mode 100644 index 000000000000..78c85a402435 --- /dev/null +++ b/drivers/comedi/drivers/adl_pci7250.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * adl_pci7250.c + * + * Comedi driver for ADLink PCI-7250 series cards. + * + * Copyright (C) 2015, 2025 Ian Abbott <abbotti@mev.co.uk> + */ + +/* + * Driver: adl_pci7250 + * Description: Driver for the ADLINK PCI-7250 relay output & digital input card + * Devices: [ADLINK] PCI-7250 (adl_pci7250) LPCI-7250 LPCIe-7250 + * Author: Ian Abbott <abbotti@mev.co.uk> + * Status: works + * Updated: Mon, 02 Jun 2025 13:54:11 +0100 + * + * The driver assumes that 3 PCI-7251 modules are fitted to the PCI-7250, + * giving 32 channels of relay outputs and 32 channels of isolated digital + * inputs. That is also the case for the LPCI-7250 and older LPCIe-7250 + * cards although they do not physically support the PCI-7251 modules. + * Newer LPCIe-7250 cards have a different PCI subsystem device ID, so + * set the number of channels to 8 for these cards. + * + * Not fitting the PCI-7251 modules shouldn't do any harm, but the extra + * inputs and relay outputs won't work! + * + * Configuration Options: not applicable, uses PCI auto config + */ + +#include <linux/module.h> +#include <linux/comedi/comedi_pci.h> + +static unsigned char adl_pci7250_read8(struct comedi_device *dev, + unsigned int offset) +{ +#ifdef CONFIG_HAS_IOPORT + if (!dev->mmio) + return inb(dev->iobase + offset); +#endif + return readb(dev->mmio + offset); +} + +static void adl_pci7250_write8(struct comedi_device *dev, unsigned int offset, + unsigned char val) +{ +#ifdef CONFIG_HAS_IOPORT + if (!dev->mmio) { + outb(val, dev->iobase + offset); + return; + } +#endif + writeb(val, dev->mmio + offset); +} + +static int adl_pci7250_do_insn_bits(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data) +{ + unsigned int mask = comedi_dio_update_state(s, data); + + if (mask) { + unsigned int state = s->state; + unsigned int i; + + for (i = 0; i * 8 < s->n_chan; i++) { + if ((mask & 0xffu) != 0) { + /* write relay data to even offset registers */ + adl_pci7250_write8(dev, i * 2, state & 0xffu); + } + state >>= 8; + mask >>= 8; + } + } + + data[1] = s->state; + + return 2; +} + +static int adl_pci7250_di_insn_bits(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data) +{ + unsigned int value = 0; + unsigned int i; + + for (i = 0; i * 8 < s->n_chan; i++) { + /* read DI value from odd offset registers */ + value |= (unsigned int)adl_pci7250_read8(dev, i * 2 + 1) << + (i * 8); + } + + data[1] = value; + + return 2; +} + +static int pci7250_auto_attach(struct comedi_device *dev, + unsigned long context_unused) +{ + struct pci_dev *pcidev = comedi_to_pci_dev(dev); + struct comedi_subdevice *s; + unsigned int max_chans; + unsigned int i; + int ret; + + ret = comedi_pci_enable(dev); + if (ret) + return ret; + + if (pci_resource_len(pcidev, 2) < 8) + return -ENXIO; + + /* + * Newer LPCIe-7250 boards use MMIO. Older LPCIe-7250, LPCI-7250, and + * PCI-7250 boards use Port I/O. + */ + if (pci_resource_flags(pcidev, 2) & IORESOURCE_MEM) { + dev->mmio = pci_ioremap_bar(pcidev, 2); + if (!dev->mmio) + return -ENOMEM; + } else if (IS_ENABLED(CONFIG_HAS_IOPORT)) { + dev->iobase = pci_resource_start(pcidev, 2); + } else { + dev_err(dev->class_dev, + "error! need I/O port support\n"); + return -ENXIO; + } + + if (pcidev->subsystem_device == 0x7000) { + /* + * This is a newer LPCIe-7250 variant and cannot possibly + * have PCI-7251 modules fitted, so limit the number of + * channels to 8. + */ + max_chans = 8; + } else { + /* + * It is unknown whether the board is a PCI-7250, an LPCI-7250, + * or an older LPCIe-7250 variant, so treat it as a PCI-7250 + * and assume it can have PCI-7251 modules fitted to increase + * the number of channels to a maximum of 32. + */ + max_chans = 32; + } + + ret = comedi_alloc_subdevices(dev, 2); + if (ret) + return ret; + + /* Relay digital output. */ + s = &dev->subdevices[0]; + s->type = COMEDI_SUBD_DO; + s->subdev_flags = SDF_WRITABLE; + s->n_chan = max_chans; + s->maxdata = 1; + s->range_table = &range_digital; + s->insn_bits = adl_pci7250_do_insn_bits; + /* Read initial state of relays from the even offset registers. */ + s->state = 0; + for (i = 0; i * 8 < max_chans; i++) { + s->state |= (unsigned int)adl_pci7250_read8(dev, i * 2) << + (i * 8); + } + + /* Isolated digital input. */ + s = &dev->subdevices[1]; + s->type = COMEDI_SUBD_DI; + s->subdev_flags = SDF_READABLE; + s->n_chan = max_chans; + s->maxdata = 1; + s->range_table = &range_digital; + s->insn_bits = adl_pci7250_di_insn_bits; + + return 0; +} + +static struct comedi_driver adl_pci7250_driver = { + .driver_name = "adl_pci7250", + .module = THIS_MODULE, + .auto_attach = pci7250_auto_attach, + .detach = comedi_pci_detach, +}; + +static int adl_pci7250_pci_probe(struct pci_dev *dev, + const struct pci_device_id *id) +{ + return comedi_pci_auto_config(dev, &adl_pci7250_driver, + id->driver_data); +} + +static const struct pci_device_id adl_pci7250_pci_table[] = { +#ifdef CONFIG_HAS_IOPORT + { PCI_DEVICE_SUB(PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, + 0x9999, 0x7250) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADLINK, 0x7250, + 0x9999, 0x7250) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADLINK, 0x7250, + PCI_VENDOR_ID_ADLINK, 0x7250) }, +#endif + { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADLINK, 0x7250, + PCI_VENDOR_ID_ADLINK, 0x7000) }, /* newer LPCIe-7250 */ + { 0 } +}; +MODULE_DEVICE_TABLE(pci, adl_pci7250_pci_table); + +static struct pci_driver adl_pci7250_pci_driver = { + .name = "adl_pci7250", + .id_table = adl_pci7250_pci_table, + .probe = adl_pci7250_pci_probe, + .remove = comedi_pci_auto_unconfig, +}; +module_comedi_pci_driver(adl_pci7250_driver, adl_pci7250_pci_driver); + +MODULE_AUTHOR("Comedi https://www.comedi.org"); +MODULE_DESCRIPTION("Comedi driver for ADLink PCI-7250 series boards"); +MODULE_LICENSE("GPL"); diff --git a/drivers/comedi/drivers/pcl726.c b/drivers/comedi/drivers/pcl726.c index 0430630e6ebb..b542896fa0e4 100644 --- a/drivers/comedi/drivers/pcl726.c +++ b/drivers/comedi/drivers/pcl726.c @@ -328,7 +328,8 @@ static int pcl726_attach(struct comedi_device *dev, * Hook up the external trigger source interrupt only if the * user config option is valid and the board supports interrupts. */ - if (it->options[1] && (board->irq_mask & (1 << it->options[1]))) { + if (it->options[1] > 0 && it->options[1] < 16 && + (board->irq_mask & (1U << it->options[1]))) { ret = request_irq(it->options[1], pcl726_interrupt, 0, dev->board_name, dev); if (ret == 0) { diff --git a/drivers/counter/ti-ecap-capture.c b/drivers/counter/ti-ecap-capture.c index 3faaf7f60539..3586a7ab9887 100644 --- a/drivers/counter/ti-ecap-capture.c +++ b/drivers/counter/ti-ecap-capture.c @@ -465,11 +465,6 @@ static irqreturn_t ecap_cnt_isr(int irq, void *dev_id) return IRQ_HANDLED; } -static void ecap_cnt_pm_disable(void *dev) -{ - pm_runtime_disable(dev); -} - static int ecap_cnt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -523,12 +518,9 @@ static int ecap_cnt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, counter_dev); - pm_runtime_enable(dev); - - /* Register a cleanup callback to care for disabling PM */ - ret = devm_add_action_or_reset(dev, ecap_cnt_pm_disable, dev); + ret = devm_pm_runtime_enable(dev); if (ret) - return dev_err_probe(dev, ret, "failed to add pm disable action\n"); + return ret; ret = devm_counter_add(dev, counter_dev); if (ret) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 06a1c7dd081f..f366d35c5840 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2793,6 +2793,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT_X, core_funcs), + X86_MATCH(INTEL_ATOM_DARKMONT_X, core_funcs), {} }; #endif diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 52d5d26fc7c6..b2e3d0b0a116 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -97,6 +97,14 @@ static inline int which_bucket(u64 duration_ns) static DEFINE_PER_CPU(struct menu_device, menu_devices); +static void menu_update_intervals(struct menu_device *data, unsigned int interval_us) +{ + /* Update the repeating-pattern data. */ + data->intervals[data->interval_ptr++] = interval_us; + if (data->interval_ptr >= INTERVALS) + data->interval_ptr = 0; +} + static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); /* @@ -222,6 +230,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (data->needs_update) { menu_update(drv, dev); data->needs_update = 0; + } else if (!dev->last_residency_ns) { + /* + * This happens when the driver rejects the previously selected + * idle state and returns an error, so update the recent + * intervals table to prevent invalid information from being + * used going forward. + */ + menu_update_intervals(data, UINT_MAX); } /* Find the shortest expected idle interval. */ @@ -271,20 +287,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return 0; } - if (tick_nohz_tick_stopped()) { - /* - * If the tick is already stopped, the cost of possible short - * idle duration misprediction is much higher, because the CPU - * may be stuck in a shallow idle state for a long time as a - * result of it. In that case say we might mispredict and use - * the known time till the closest timer event for the idle - * state selection. - */ - if (predicted_ns < TICK_NSEC) - predicted_ns = data->next_timer_ns; - } else if (latency_req > predicted_ns) { - latency_req = predicted_ns; - } + /* + * If the tick is already stopped, the cost of possible short idle + * duration misprediction is much higher, because the CPU may be stuck + * in a shallow idle state for a long time as a result of it. In that + * case, say we might mispredict and use the known time till the closest + * timer event for the idle state selection. + */ + if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC) + predicted_ns = data->next_timer_ns; /* * Find the idle state with the lowest power while satisfying @@ -300,13 +311,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (idx == -1) idx = i; /* first enabled state */ + if (s->exit_latency_ns > latency_req) + break; + if (s->target_residency_ns > predicted_ns) { /* * Use a physical idle state, not busy polling, unless * a timer is going to trigger soon enough. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && - s->exit_latency_ns <= latency_req && s->target_residency_ns <= data->next_timer_ns) { predicted_ns = s->target_residency_ns; idx = i; @@ -338,8 +351,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return idx; } - if (s->exit_latency_ns > latency_req) - break; idx = i; } @@ -482,10 +493,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->correction_factor[data->bucket] = new_factor; - /* update the repeating-pattern data */ - data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns); - if (data->interval_ptr >= INTERVALS) - data->interval_ptr = 0; + menu_update_intervals(data, ktime_to_us(measured_ns)); } /** diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index a6f6d467aacf..aec46bf03302 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -134,6 +134,19 @@ config EXTCON_MAX8997 Maxim MAX8997 PMIC. The MAX8997 MUIC is a USB port accessory detector and switch. +config EXTCON_MAX14526 + tristate "Maxim MAX14526 EXTCON Support" + depends on I2C + select IRQ_DOMAIN + select REGMAP_I2C + help + If you say yes here you get support for the Maxim MAX14526 + MUIC device. The MAX14526 MUIC is a USB port accessory + detector and switch. The MAX14526 is designed to simplify + interface requirements on portable devices by multiplexing + common inputs (USB, UART, Microphone, Stereo Audio and + Composite Video) on a single micro/mini USB connector. + config EXTCON_PALMAS tristate "Palmas USB EXTCON support" depends on MFD_PALMAS diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile index 0d6d23faf748..6482f2bfd661 100644 --- a/drivers/extcon/Makefile +++ b/drivers/extcon/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_EXTCON_MAX3355) += extcon-max3355.o obj-$(CONFIG_EXTCON_MAX77693) += extcon-max77693.o obj-$(CONFIG_EXTCON_MAX77843) += extcon-max77843.o obj-$(CONFIG_EXTCON_MAX8997) += extcon-max8997.o +obj-$(CONFIG_EXTCON_MAX14526) += extcon-max14526.o obj-$(CONFIG_EXTCON_PALMAS) += extcon-palmas.o obj-$(CONFIG_EXTCON_PTN5150) += extcon-ptn5150.o obj-$(CONFIG_EXTCON_QCOM_SPMI_MISC) += extcon-qcom-spmi-misc.o diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c index 46c40d85c2ac..7e3c9f38297b 100644 --- a/drivers/extcon/extcon-adc-jack.c +++ b/drivers/extcon/extcon-adc-jack.c @@ -164,6 +164,8 @@ static void adc_jack_remove(struct platform_device *pdev) { struct adc_jack_data *data = platform_get_drvdata(pdev); + if (data->wakeup_source) + device_init_wakeup(&pdev->dev, false); free_irq(data->irq, data); cancel_work_sync(&data->handler.work); } diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c index d3bcbe839c09..19856dddade6 100644 --- a/drivers/extcon/extcon-axp288.c +++ b/drivers/extcon/extcon-axp288.c @@ -470,7 +470,7 @@ static int axp288_extcon_probe(struct platform_device *pdev) if (ret < 0) return ret; - device_init_wakeup(dev, true); + devm_device_init_wakeup(dev); platform_set_drvdata(pdev, info); return 0; diff --git a/drivers/extcon/extcon-fsa9480.c b/drivers/extcon/extcon-fsa9480.c index b11b43171063..a031eb0914a0 100644 --- a/drivers/extcon/extcon-fsa9480.c +++ b/drivers/extcon/extcon-fsa9480.c @@ -317,7 +317,7 @@ static int fsa9480_probe(struct i2c_client *client) return ret; } - device_init_wakeup(info->dev, true); + devm_device_init_wakeup(info->dev); fsa9480_detect_dev(info); return 0; diff --git a/drivers/extcon/extcon-max14526.c b/drivers/extcon/extcon-max14526.c new file mode 100644 index 000000000000..3750a5c20612 --- /dev/null +++ b/drivers/extcon/extcon-max14526.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/device.h> +#include <linux/devm-helpers.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/extcon-provider.h> +#include <linux/i2c.h> +#include <linux/mod_devicetable.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pm.h> +#include <linux/regmap.h> + +/* I2C addresses of MUIC internal registers */ +#define MAX14526_DEVICE_ID 0x00 +#define MAX14526_ID 0x02 + +/* CONTROL_1 register masks */ +#define MAX14526_CONTROL_1 0x01 +#define ID_2P2 BIT(6) +#define ID_620 BIT(5) +#define ID_200 BIT(4) +#define VLDO BIT(3) +#define SEMREN BIT(2) +#define ADC_EN BIT(1) +#define CP_EN BIT(0) + +/* CONTROL_2 register masks */ +#define MAX14526_CONTROL_2 0x02 +#define INTPOL BIT(7) +#define INT_EN BIT(6) +#define MIC_LP BIT(5) +#define CP_AUD BIT(4) +#define CHG_TYPE BIT(1) +#define USB_DET_DIS BIT(0) + +/* SW_CONTROL register masks */ +#define MAX14526_SW_CONTROL 0x03 +#define SW_DATA 0x00 +#define SW_UART 0x01 +#define SW_AUDIO 0x02 +#define SW_OPEN 0x07 + +/* INT_STATUS register masks */ +#define MAX14526_INT_STAT 0x04 +#define CHGDET BIT(7) +#define MR_COMP BIT(6) +#define SENDEND BIT(5) +#define V_VBUS BIT(4) + +/* STATUS register masks */ +#define MAX14526_STATUS 0x05 +#define CPORT BIT(7) +#define CHPORT BIT(6) +#define C1COMP BIT(0) + +enum max14526_idno_resistance { + MAX14526_GND, + MAX14526_24KOHM, + MAX14526_56KOHM, + MAX14526_100KOHM, + MAX14526_130KOHM, + MAX14526_180KOHM, + MAX14526_240KOHM, + MAX14526_330KOHM, + MAX14526_430KOHM, + MAX14526_620KOHM, + MAX14526_910KOHM, + MAX14526_OPEN +}; + +enum max14526_field_idx { + VENDOR_ID, CHIP_REV, /* DEVID */ + DM, DP, /* SW_CONTROL */ + MAX14526_N_REGMAP_FIELDS +}; + +static const struct reg_field max14526_reg_field[MAX14526_N_REGMAP_FIELDS] = { + [VENDOR_ID] = REG_FIELD(MAX14526_DEVICE_ID, 4, 7), + [CHIP_REV] = REG_FIELD(MAX14526_DEVICE_ID, 0, 3), + [DM] = REG_FIELD(MAX14526_SW_CONTROL, 0, 2), + [DP] = REG_FIELD(MAX14526_SW_CONTROL, 3, 5), +}; + +struct max14526_data { + struct i2c_client *client; + struct extcon_dev *edev; + + struct regmap *regmap; + struct regmap_field *rfield[MAX14526_N_REGMAP_FIELDS]; + + int last_state; + int cable; +}; + +enum max14526_muic_modes { + MAX14526_OTG = MAX14526_GND, /* no power */ + MAX14526_MHL = MAX14526_56KOHM, /* no power */ + MAX14526_OTG_Y = MAX14526_GND | V_VBUS, + MAX14526_MHL_CHG = MAX14526_GND | V_VBUS | CHGDET, + MAX14526_NONE = MAX14526_OPEN, + MAX14526_USB = MAX14526_OPEN | V_VBUS, + MAX14526_CHG = MAX14526_OPEN | V_VBUS | CHGDET, +}; + +static const unsigned int max14526_extcon_cable[] = { + EXTCON_USB, + EXTCON_USB_HOST, + EXTCON_CHG_USB_FAST, + EXTCON_DISP_MHL, + EXTCON_NONE, +}; + +static int max14526_ap_usb_mode(struct max14526_data *priv) +{ + struct device *dev = &priv->client->dev; + int ret; + + /* Enable USB Path */ + ret = regmap_field_write(priv->rfield[DM], SW_DATA); + if (ret) + return ret; + + ret = regmap_field_write(priv->rfield[DP], SW_DATA); + if (ret) + return ret; + + /* Enable 200K, Charger Pump and ADC */ + ret = regmap_write(priv->regmap, MAX14526_CONTROL_1, + ID_200 | ADC_EN | CP_EN); + if (ret) + return ret; + + dev_dbg(dev, "AP USB mode set\n"); + + return 0; +} + +static irqreturn_t max14526_interrupt(int irq, void *dev_id) +{ + struct max14526_data *priv = dev_id; + struct device *dev = &priv->client->dev; + int state, ret; + + /* + * Upon an MUIC IRQ (MUIC_INT_N falls), wait at least 70ms + * before reading INT_STAT and STATUS. After the reads, + * MUIC_INT_N returns to high (but the INT_STAT and STATUS + * contents will be held). + */ + msleep(100); + + ret = regmap_read(priv->regmap, MAX14526_INT_STAT, &state); + if (ret) + dev_err(dev, "failed to read MUIC state %d\n", ret); + + if (state == priv->last_state) + return IRQ_HANDLED; + + /* Detach previous device */ + extcon_set_state_sync(priv->edev, priv->cable, false); + + switch (state) { + case MAX14526_USB: + priv->cable = EXTCON_USB; + break; + + case MAX14526_CHG: + priv->cable = EXTCON_CHG_USB_FAST; + break; + + case MAX14526_OTG: + case MAX14526_OTG_Y: + priv->cable = EXTCON_USB_HOST; + break; + + case MAX14526_MHL: + case MAX14526_MHL_CHG: + priv->cable = EXTCON_DISP_MHL; + break; + + case MAX14526_NONE: + default: + priv->cable = EXTCON_NONE; + break; + } + + extcon_set_state_sync(priv->edev, priv->cable, true); + + priv->last_state = state; + + return IRQ_HANDLED; +} + +static const struct regmap_config max14526_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = MAX14526_STATUS, +}; + +static int max14526_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct max14526_data *priv; + int ret, dev_id, rev, i; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->client = client; + i2c_set_clientdata(client, priv); + + priv->regmap = devm_regmap_init_i2c(client, &max14526_regmap_config); + if (IS_ERR(priv->regmap)) + return dev_err_probe(dev, PTR_ERR(priv->regmap), "cannot allocate regmap\n"); + + for (i = 0; i < MAX14526_N_REGMAP_FIELDS; i++) { + priv->rfield[i] = devm_regmap_field_alloc(dev, priv->regmap, + max14526_reg_field[i]); + if (IS_ERR(priv->rfield[i])) + return dev_err_probe(dev, PTR_ERR(priv->rfield[i]), + "cannot allocate regmap field\n"); + } + + /* Detect if MUIC version is supported */ + ret = regmap_field_read(priv->rfield[VENDOR_ID], &dev_id); + if (ret) + return dev_err_probe(dev, ret, "failed to read MUIC ID\n"); + + regmap_field_read(priv->rfield[CHIP_REV], &rev); + + if (dev_id == MAX14526_ID) + dev_info(dev, "detected MAX14526 MUIC with id 0x%x, rev 0x%x\n", dev_id, rev); + else + dev_err_probe(dev, -EINVAL, "MUIC vendor id 0x%X is not recognized\n", dev_id); + + priv->edev = devm_extcon_dev_allocate(dev, max14526_extcon_cable); + if (IS_ERR(priv->edev)) + return dev_err_probe(dev, (IS_ERR(priv->edev)), + "failed to allocate extcon device\n"); + + ret = devm_extcon_dev_register(dev, priv->edev); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to register extcon device\n"); + + ret = max14526_ap_usb_mode(priv); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to set AP USB mode\n"); + + regmap_write_bits(priv->regmap, MAX14526_CONTROL_2, INT_EN, INT_EN); + regmap_write_bits(priv->regmap, MAX14526_CONTROL_2, USB_DET_DIS, (u32)~USB_DET_DIS); + + ret = devm_request_threaded_irq(dev, client->irq, NULL, &max14526_interrupt, + IRQF_ONESHOT | IRQF_SHARED, client->name, priv); + if (ret) + return dev_err_probe(dev, ret, "failed to register IRQ\n"); + + irq_wake_thread(client->irq, priv); + + return 0; +} + +static int max14526_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct max14526_data *priv = i2c_get_clientdata(client); + + irq_wake_thread(client->irq, priv); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(max14526_pm_ops, NULL, max14526_resume); + +static const struct of_device_id max14526_match[] = { + { .compatible = "maxim,max14526" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, max14526_match); + +static const struct i2c_device_id max14526_id[] = { + { "max14526" }, + { } +}; +MODULE_DEVICE_TABLE(i2c, max14526_id); + +static struct i2c_driver max14526_driver = { + .driver = { + .name = "max14526", + .of_match_table = max14526_match, + .pm = &max14526_pm_ops, + }, + .probe = max14526_probe, + .id_table = max14526_id, +}; +module_i2c_driver(max14526_driver); + +MODULE_AUTHOR("Svyatoslav Ryhel <clamor95@gmail.com>"); +MODULE_DESCRIPTION("MAX14526 extcon driver to support MUIC"); +MODULE_LICENSE("GPL"); diff --git a/drivers/extcon/extcon-qcom-spmi-misc.c b/drivers/extcon/extcon-qcom-spmi-misc.c index 53de581a393a..afaba5685c3d 100644 --- a/drivers/extcon/extcon-qcom-spmi-misc.c +++ b/drivers/extcon/extcon-qcom-spmi-misc.c @@ -155,7 +155,7 @@ static int qcom_usb_extcon_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, info); - device_init_wakeup(dev, 1); + devm_device_init_wakeup(dev); /* Perform initial detection */ qcom_usb_extcon_detect_cable(&info->wq_detcable.work); diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index d28477d84697..1d1c2d8f85ae 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -550,6 +550,23 @@ const struct fw_address_region fw_unit_space_region = { .start = 0xfffff0000900ULL, .end = 0x1000000000000ULL, }; #endif /* 0 */ +static void complete_address_handler(struct kref *kref) +{ + struct fw_address_handler *handler = container_of(kref, struct fw_address_handler, kref); + + complete(&handler->done); +} + +static void get_address_handler(struct fw_address_handler *handler) +{ + kref_get(&handler->kref); +} + +static int put_address_handler(struct fw_address_handler *handler) +{ + return kref_put(&handler->kref, complete_address_handler); +} + /** * fw_core_add_address_handler() - register for incoming requests * @handler: callback @@ -596,6 +613,8 @@ int fw_core_add_address_handler(struct fw_address_handler *handler, if (other != NULL) { handler->offset += other->length; } else { + init_completion(&handler->done); + kref_init(&handler->kref); list_add_tail_rcu(&handler->link, &address_handler_list); ret = 0; break; @@ -621,6 +640,9 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler) list_del_rcu(&handler->link); synchronize_rcu(); + + if (!put_address_handler(handler)) + wait_for_completion(&handler->done); } EXPORT_SYMBOL(fw_core_remove_address_handler); @@ -914,22 +936,31 @@ static void handle_exclusive_region_request(struct fw_card *card, handler = lookup_enclosing_address_handler(&address_handler_list, offset, request->length); if (handler) - handler->address_callback(card, request, tcode, destination, source, - p->generation, offset, request->data, - request->length, handler->callback_data); + get_address_handler(handler); } - if (!handler) + if (!handler) { fw_send_response(card, request, RCODE_ADDRESS_ERROR); + return; + } + + // Outside the RCU read-side critical section. Without spinlock. With reference count. + handler->address_callback(card, request, tcode, destination, source, p->generation, offset, + request->data, request->length, handler->callback_data); + put_address_handler(handler); } +// To use kmalloc allocator efficiently, this should be power of two. +#define BUFFER_ON_KERNEL_STACK_SIZE 4 + static void handle_fcp_region_request(struct fw_card *card, struct fw_packet *p, struct fw_request *request, unsigned long long offset) { - struct fw_address_handler *handler; - int tcode, destination, source; + struct fw_address_handler *buffer_on_kernel_stack[BUFFER_ON_KERNEL_STACK_SIZE]; + struct fw_address_handler *handler, **handlers; + int tcode, destination, source, i, count, buffer_size; if ((offset != (CSR_REGISTER_BASE | CSR_FCP_COMMAND) && offset != (CSR_REGISTER_BASE | CSR_FCP_RESPONSE)) || @@ -950,15 +981,55 @@ static void handle_fcp_region_request(struct fw_card *card, return; } + count = 0; + handlers = buffer_on_kernel_stack; + buffer_size = ARRAY_SIZE(buffer_on_kernel_stack); scoped_guard(rcu) { list_for_each_entry_rcu(handler, &address_handler_list, link) { - if (is_enclosing_handler(handler, offset, request->length)) - handler->address_callback(card, request, tcode, destination, source, - p->generation, offset, request->data, - request->length, handler->callback_data); + if (is_enclosing_handler(handler, offset, request->length)) { + if (count >= buffer_size) { + int next_size = buffer_size * 2; + struct fw_address_handler **buffer_on_kernel_heap; + + if (handlers == buffer_on_kernel_stack) + buffer_on_kernel_heap = NULL; + else + buffer_on_kernel_heap = handlers; + + buffer_on_kernel_heap = + krealloc_array(buffer_on_kernel_heap, next_size, + sizeof(*buffer_on_kernel_heap), GFP_ATOMIC); + // FCP is used for purposes unrelated to significant system + // resources (e.g. storage or networking), so allocation + // failures are not considered so critical. + if (!buffer_on_kernel_heap) + break; + + if (handlers == buffer_on_kernel_stack) { + memcpy(buffer_on_kernel_heap, buffer_on_kernel_stack, + sizeof(buffer_on_kernel_stack)); + } + + handlers = buffer_on_kernel_heap; + buffer_size = next_size; + } + get_address_handler(handler); + handlers[count++] = handler; + } } } + for (i = 0; i < count; ++i) { + handler = handlers[i]; + handler->address_callback(card, request, tcode, destination, source, + p->generation, offset, request->data, + request->length, handler->callback_data); + put_address_handler(handler); + } + + if (handlers != buffer_on_kernel_stack) + kfree(handlers); + fw_send_response(card, request, RCODE_COMPLETE); } diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c index 0be0d569589d..b7629a0e4813 100644 --- a/drivers/fpga/zynq-fpga.c +++ b/drivers/fpga/zynq-fpga.c @@ -405,12 +405,12 @@ static int zynq_fpga_ops_write(struct fpga_manager *mgr, struct sg_table *sgt) } } - priv->dma_nelms = - dma_map_sgtable(mgr->dev.parent, sgt, DMA_TO_DEVICE, 0); - if (priv->dma_nelms == 0) { + err = dma_map_sgtable(mgr->dev.parent, sgt, DMA_TO_DEVICE, 0); + if (err) { dev_err(&mgr->dev, "Unable to DMA map (TO_DEVICE)\n"); - return -ENOMEM; + return err; } + priv->dma_nelms = sgt->nents; /* enable clock */ err = clk_enable(priv->clk); diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index 9875e34bde72..ed29b07d16c1 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -190,9 +190,7 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) struct mlxbf3_gpio_context *gs; struct gpio_irq_chip *girq; struct gpio_chip *gc; - char *colon_ptr; int ret, irq; - long num; gs = devm_kzalloc(dev, sizeof(*gs), GFP_KERNEL); if (!gs) @@ -229,39 +227,25 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) gc->owner = THIS_MODULE; gc->add_pin_ranges = mlxbf3_gpio_add_pin_ranges; - colon_ptr = strchr(dev_name(dev), ':'); - if (!colon_ptr) { - dev_err(dev, "invalid device name format\n"); - return -EINVAL; - } - - ret = kstrtol(++colon_ptr, 16, &num); - if (ret) { - dev_err(dev, "invalid device instance\n"); - return ret; - } - - if (!num) { - irq = platform_get_irq(pdev, 0); - if (irq >= 0) { - girq = &gs->gc.irq; - gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip); - girq->default_type = IRQ_TYPE_NONE; - /* This will let us handle the parent IRQ in the driver */ - girq->num_parents = 0; - girq->parents = NULL; - girq->parent_handler = NULL; - girq->handler = handle_bad_irq; - - /* - * Directly request the irq here instead of passing - * a flow-handler because the irq is shared. - */ - ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler, - IRQF_SHARED, dev_name(dev), gs); - if (ret) - return dev_err_probe(dev, ret, "failed to request IRQ"); - } + irq = platform_get_irq_optional(pdev, 0); + if (irq >= 0) { + girq = &gs->gc.irq; + gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip); + girq->default_type = IRQ_TYPE_NONE; + /* This will let us handle the parent IRQ in the driver */ + girq->num_parents = 0; + girq->parents = NULL; + girq->parent_handler = NULL; + girq->handler = handle_bad_irq; + + /* + * Directly request the irq here instead of passing + * a flow-handler because the irq is shared. + */ + ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler, + IRQF_SHARED, dev_name(dev), gs); + if (ret) + return dev_err_probe(dev, ret, "failed to request IRQ"); } platform_set_drvdata(pdev, gs); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index a2adaacf6adb..d3f220be2ef9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1139,6 +1139,9 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) } } + if (!amdgpu_vm_ready(vm)) + return -EINVAL; + r = amdgpu_vm_clear_freed(adev, vm, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index 02138aa55793..dfb6cfd83760 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, - AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE | - AMDGPU_PTE_EXECUTABLE); + AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE | + AMDGPU_VM_PAGE_EXECUTABLE); if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index ff98c87b2e0b..5743ebb2f1b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -514,7 +514,7 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev, return false; if (drm_gem_is_imported(obj)) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; if (dma_buf->ops != &amdgpu_dmabuf_ops) /* No XGMI with non AMD GPUs */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 6626a6e64ff5..d1ccbfcf21fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -317,7 +317,8 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj, */ if (!vm->is_compute_context || !vm->process_info) return 0; - if (!drm_gem_is_imported(obj) || !dma_buf_is_dynamic(obj->dma_buf)) + if (!drm_gem_is_imported(obj) || + !dma_buf_is_dynamic(obj->import_attach->dmabuf)) return 0; mutex_lock_nested(&vm->process_info->lock, 1); if (!WARN_ON(!vm->process_info->eviction_fence)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 0bd51a04be79..23484317a5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1039,15 +1039,28 @@ int psp_update_fw_reservation(struct psp_context *psp) { int ret; uint64_t reserv_addr, reserv_addr_ext; - uint32_t reserv_size, reserv_size_ext; + uint32_t reserv_size, reserv_size_ext, mp0_ip_ver; struct amdgpu_device *adev = psp->adev; + mp0_ip_ver = amdgpu_ip_version(adev, MP0_HWIP, 0); + if (amdgpu_sriov_vf(psp->adev)) return 0; - if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 2)) && - (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 3))) + switch (mp0_ip_ver) { + case IP_VERSION(14, 0, 2): + if (adev->psp.sos.fw_version < 0x3b0e0d) + return 0; + break; + + case IP_VERSION(14, 0, 3): + if (adev->psp.sos.fw_version < 0x3a0e14) + return 0; + break; + + default: return 0; + } ret = psp_get_fw_reservation_info(psp, GFX_CMD_ID_FB_FW_RESERV_ADDR, &reserv_addr, &reserv_size); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 5cacf5717016..c39bb06ebda1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -654,11 +654,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, * Check if all VM PDs/PTs are ready for updates * * Returns: - * True if VM is not evicting. + * True if VM is not evicting and all VM entities are not stopped */ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { - bool empty; bool ret; amdgpu_vm_eviction_lock(vm); @@ -666,10 +665,18 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) amdgpu_vm_eviction_unlock(vm); spin_lock(&vm->status_lock); - empty = list_empty(&vm->evicted); + ret &= list_empty(&vm->evicted); spin_unlock(&vm->status_lock); - return ret && empty; + spin_lock(&vm->immediate.lock); + ret &= !vm->immediate.stopped; + spin_unlock(&vm->immediate.lock); + + spin_lock(&vm->delayed.lock); + ret &= !vm->delayed.stopped; + spin_unlock(&vm->delayed.lock); + + return ret; } /** @@ -1276,7 +1283,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *obj = &bo->tbo.base; if (drm_gem_is_imported(obj) && bo_va->is_xgmi) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 07c936e90d8e..78f9e86ccc09 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -648,9 +648,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, list_for_each_entry(block, &vres->blocks, link) vis_usage += amdgpu_vram_mgr_vis_size(adev, block); - amdgpu_vram_mgr_do_reserve(man); - drm_buddy_free_list(mm, &vres->blocks, vres->flags); + amdgpu_vram_mgr_do_reserve(man); mutex_unlock(&mgr->lock); atomic64_sub(vis_usage, &mgr->vis_usage); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index cd0e2976e268..a0ca3b2c6bd8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7792,6 +7792,9 @@ amdgpu_dm_connector_atomic_check(struct drm_connector *conn, struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(conn); int ret; + if (WARN_ON(unlikely(!old_con_state || !new_con_state))) + return -EINVAL; + trace_amdgpu_dm_connector_atomic_check(new_con_state); if (conn->connector_type == DRM_MODE_CONNECTOR_DisplayPort) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 010172f930ae..45feb404b097 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -299,6 +299,25 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable) irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, acrtc->crtc_id); if (enable) { + struct dc *dc = adev->dm.dc; + struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); + struct psr_settings *psr = &acrtc_state->stream->link->psr_settings; + struct replay_settings *pr = &acrtc_state->stream->link->replay_settings; + bool sr_supported = (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED) || + pr->config.replay_supported; + + /* + * IPS & self-refresh feature can cause vblank counter resets between + * vblank disable and enable. + * It may cause system stuck due to waiting for the vblank counter. + * Call this function to estimate missed vblanks by using timestamps and + * update the vblank counter in DRM. + */ + if (dc->caps.ips_support && + dc->config.disable_ips != DMUB_IPS_DISABLE_ALL && + sr_supported && vblank->config.disable_immediate) + drm_crtc_vblank_restore(crtc); + /* vblank irq on -> Only need vupdate irq in vrr mode */ if (amdgpu_dm_crtc_vrr_active(acrtc_state)) rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, true); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index 67f08495b7e6..154fd2c18e88 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -174,11 +174,8 @@ static struct graphics_object_id bios_parser_get_connector_id( return object_id; } - if (tbl->ucNumberOfObjects <= i) { - dm_error("Can't find connector id %d in connector table of size %d.\n", - i, tbl->ucNumberOfObjects); + if (tbl->ucNumberOfObjects <= i) return object_id; - } id = le16_to_cpu(tbl->asObjects[i].usObjectID); object_id = object_id_from_bios_object_id(id); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c index 2bcae0643e61..58e88778da7f 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c @@ -993,7 +993,7 @@ static enum bp_result set_pixel_clock_v3( allocation.sPCLKInput.usFbDiv = cpu_to_le16((uint16_t)bp_params->feedback_divider); allocation.sPCLKInput.ucFracFbDiv = - (uint8_t)bp_params->fractional_feedback_divider; + (uint8_t)(bp_params->fractional_feedback_divider / 100000); allocation.sPCLKInput.ucPostDiv = (uint8_t)bp_params->pixel_clock_post_divider; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c index f5ad0a177038..dbd6ef1b60a0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c @@ -72,9 +72,9 @@ static const struct state_dependent_clocks dce80_max_clks_by_state[] = { /* ClocksStateLow */ { .display_clk_khz = 352000, .pixel_clk_khz = 330000}, /* ClocksStateNominal */ -{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 }, +{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 }, /* ClocksStatePerformance */ -{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 } }; +{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 } }; int dentist_get_divider_from_did(int did) { @@ -391,8 +391,6 @@ static void dce_pplib_apply_display_requirements( { struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg; - pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context); - dce110_fill_display_configs(context, pp_display_cfg); if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) != 0) @@ -405,11 +403,9 @@ static void dce_update_clocks(struct clk_mgr *clk_mgr_base, { struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base); struct dm_pp_power_level_change_request level_change_req; - int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz; - - /*TODO: W/A for dal3 linux, investigate why this works */ - if (!clk_mgr_dce->dfs_bypass_active) - patched_disp_clk = patched_disp_clk * 115 / 100; + const int max_disp_clk = + clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz; + int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz); level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context); /* get max clock state from PPLIB */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index f8409453434c..13cf415e38e5 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -120,9 +120,15 @@ void dce110_fill_display_configs( const struct dc_state *context, struct dm_pp_display_configuration *pp_display_cfg) { + struct dc *dc = context->clk_mgr->ctx->dc; int j; int num_cfgs = 0; + pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context); + pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz; + pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0; + pp_display_cfg->crtc_index = dc->res_pool->res_cap->num_timing_generator; + for (j = 0; j < context->stream_count; j++) { int k; @@ -164,6 +170,23 @@ void dce110_fill_display_configs( cfg->v_refresh /= stream->timing.h_total; cfg->v_refresh = (cfg->v_refresh + stream->timing.v_total / 2) / stream->timing.v_total; + + /* Find first CRTC index and calculate its line time. + * This is necessary for DPM on SI GPUs. + */ + if (cfg->pipe_idx < pp_display_cfg->crtc_index) { + const struct dc_crtc_timing *timing = + &context->streams[0]->timing; + + pp_display_cfg->crtc_index = cfg->pipe_idx; + pp_display_cfg->line_time_in_us = + timing->h_total * 10000 / timing->pix_clk_100hz; + } + } + + if (!num_cfgs) { + pp_display_cfg->crtc_index = 0; + pp_display_cfg->line_time_in_us = 0; } pp_display_cfg->display_count = num_cfgs; @@ -223,25 +246,8 @@ void dce11_pplib_apply_display_requirements( pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw_ctx.bw.dce.sclk_deep_sleep_khz; - pp_display_cfg->avail_mclk_switch_time_us = - dce110_get_min_vblank_time_us(context); - /* TODO: dce11.2*/ - pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0; - - pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz; - dce110_fill_display_configs(context, pp_display_cfg); - /* TODO: is this still applicable?*/ - if (pp_display_cfg->display_count == 1) { - const struct dc_crtc_timing *timing = - &context->streams[0]->timing; - - pp_display_cfg->crtc_index = - pp_display_cfg->disp_configs[0].pipe_idx; - pp_display_cfg->line_time_in_us = timing->h_total * 10000 / timing->pix_clk_100hz; - } - if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) != 0) dm_pp_apply_display_requirements(dc->ctx, pp_display_cfg); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c index 0267644717b2..a39641a0ff09 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c @@ -83,22 +83,13 @@ static const struct state_dependent_clocks dce60_max_clks_by_state[] = { static int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); - int dprefclk_wdivider; - int dp_ref_clk_khz; - int target_div; + struct dc_context *ctx = clk_mgr_base->ctx; + int dp_ref_clk_khz = 0; - /* DCE6 has no DPREFCLK_CNTL to read DP Reference Clock source */ - - /* Read the mmDENTIST_DISPCLK_CNTL to get the currently - * programmed DID DENTIST_DPREFCLK_WDIVIDER*/ - REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider); - - /* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/ - target_div = dentist_get_divider_from_did(dprefclk_wdivider); - - /* Calculate the current DFS clock, in kHz.*/ - dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR - * clk_mgr->base.dentist_vco_freq_khz) / target_div; + if (ASIC_REV_IS_TAHITI_P(ctx->asic_id.hw_internal_rev)) + dp_ref_clk_khz = ctx->dc_bios->fw_info.default_display_engine_pll_frequency; + else + dp_ref_clk_khz = clk_mgr_base->clks.dispclk_khz; return dce_adjust_dp_ref_freq_for_ss(clk_mgr, dp_ref_clk_khz); } @@ -109,8 +100,6 @@ static void dce60_pplib_apply_display_requirements( { struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg; - pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context); - dce110_fill_display_configs(context, pp_display_cfg); if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) != 0) @@ -123,11 +112,9 @@ static void dce60_update_clocks(struct clk_mgr *clk_mgr_base, { struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base); struct dm_pp_power_level_change_request level_change_req; - int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz; - - /*TODO: W/A for dal3 linux, investigate why this works */ - if (!clk_mgr_dce->dfs_bypass_active) - patched_disp_clk = patched_disp_clk * 115 / 100; + const int max_disp_clk = + clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz; + int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz); level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context); /* get max clock state from PPLIB */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 9ab0ee20ca6f..dcc48b5238e5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -217,11 +217,24 @@ static bool create_links( connectors_num, num_virtual_links); - // condition loop on link_count to allow skipping invalid indices + /* When getting the number of connectors, the VBIOS reports the number of valid indices, + * but it doesn't say which indices are valid, and not every index has an actual connector. + * So, if we don't find a connector on an index, that is not an error. + * + * - There is no guarantee that the first N indices will be valid + * - VBIOS may report a higher amount of valid indices than there are actual connectors + * - Some VBIOS have valid configurations for more connectors than there actually are + * on the card. This may be because the manufacturer used the same VBIOS for different + * variants of the same card. + */ for (i = 0; dc->link_count < connectors_num && i < MAX_LINKS; i++) { + struct graphics_object_id connector_id = bios->funcs->get_connector_id(bios, i); struct link_init_data link_init_params = {0}; struct dc_link *link; + if (connector_id.id == CONNECTOR_ID_UNKNOWN) + continue; + DC_LOG_DC("BIOS object table - printing link object info for connector number: %d, link_index: %d", i, dc->link_count); link_init_params.ctx = dc->ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index 4a9d07c31bc5..0c50fe266c8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -896,13 +896,13 @@ void dce110_link_encoder_construct( enc110->base.id, &bp_cap_info); /* Override features with DCE-specific values */ - if (BP_RESULT_OK == result) { + if (result == BP_RESULT_OK) { enc110->base.features.flags.bits.IS_HBR2_CAPABLE = bp_cap_info.DP_HBR2_EN; enc110->base.features.flags.bits.IS_HBR3_CAPABLE = bp_cap_info.DP_HBR3_EN; enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN; - } else { + } else if (result != BP_RESULT_NORECORD) { DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n", __func__, result); @@ -1798,13 +1798,13 @@ void dce60_link_encoder_construct( enc110->base.id, &bp_cap_info); /* Override features with DCE-specific values */ - if (BP_RESULT_OK == result) { + if (result == BP_RESULT_OK) { enc110->base.features.flags.bits.IS_HBR2_CAPABLE = bp_cap_info.DP_HBR2_EN; enc110->base.features.flags.bits.IS_HBR3_CAPABLE = bp_cap_info.DP_HBR3_EN; enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN; - } else { + } else if (result != BP_RESULT_NORECORD) { DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n", __func__, result); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c index e7a318e26d38..fcd3d86ad517 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c @@ -4,7 +4,6 @@ #include "dc.h" #include "dc_dmub_srv.h" -#include "dc_dp_types.h" #include "dmub/dmub_srv.h" #include "core_types.h" #include "dmub_replay.h" @@ -44,45 +43,21 @@ static void dmub_replay_get_state(struct dmub_replay *dmub, enum replay_state *s /* * Enable/Disable Replay. */ -static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst, - struct dc_link *link) +static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst) { union dmub_rb_cmd cmd; struct dc_context *dc = dmub->ctx; uint32_t retry_count; enum replay_state state = REPLAY_STATE_0; - struct pipe_ctx *pipe_ctx = NULL; - struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx; - uint8_t i; memset(&cmd, 0, sizeof(cmd)); cmd.replay_enable.header.type = DMUB_CMD__REPLAY; cmd.replay_enable.data.panel_inst = panel_inst; cmd.replay_enable.header.sub_type = DMUB_CMD__REPLAY_ENABLE; - if (enable) { + if (enable) cmd.replay_enable.data.enable = REPLAY_ENABLE; - // hpo stream/link encoder assignments are not static, need to update everytime we try to enable replay - if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) { - for (i = 0; i < MAX_PIPES; i++) { - if (res_ctx && - res_ctx->pipe_ctx[i].stream && - res_ctx->pipe_ctx[i].stream->link && - res_ctx->pipe_ctx[i].stream->link == link && - res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) { - pipe_ctx = &res_ctx->pipe_ctx[i]; - //TODO: refactor for multi edp support - break; - } - } - - if (!pipe_ctx) - return; - - cmd.replay_enable.data.hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; - cmd.replay_enable.data.hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst; - } - } else + else cmd.replay_enable.data.enable = REPLAY_DISABLE; cmd.replay_enable.header.payload_bytes = sizeof(struct dmub_rb_cmd_replay_enable_data); @@ -174,17 +149,6 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub, copy_settings_data->digbe_inst = replay_context->digbe_inst; copy_settings_data->digfe_inst = replay_context->digfe_inst; - if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) { - if (pipe_ctx->stream_res.hpo_dp_stream_enc) - copy_settings_data->hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; - else - copy_settings_data->hpo_stream_enc_inst = 0; - if (pipe_ctx->link_res.hpo_dp_link_enc) - copy_settings_data->hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst; - else - copy_settings_data->hpo_link_enc_inst = 0; - } - if (pipe_ctx->plane_res.dpp) copy_settings_data->dpp_inst = pipe_ctx->plane_res.dpp->inst; else @@ -247,7 +211,6 @@ static void dmub_replay_set_coasting_vtotal(struct dmub_replay *dmub, pCmd->header.type = DMUB_CMD__REPLAY; pCmd->header.sub_type = DMUB_CMD__REPLAY_SET_COASTING_VTOTAL; pCmd->header.payload_bytes = sizeof(struct dmub_cmd_replay_set_coasting_vtotal_data); - pCmd->replay_set_coasting_vtotal_data.panel_inst = panel_inst; pCmd->replay_set_coasting_vtotal_data.coasting_vtotal = (coasting_vtotal & 0xFFFF); pCmd->replay_set_coasting_vtotal_data.coasting_vtotal_high = (coasting_vtotal & 0xFFFF0000) >> 16; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h index ccbe385e132c..e6346c0ffc0e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h @@ -19,7 +19,7 @@ struct dmub_replay_funcs { void (*replay_get_state)(struct dmub_replay *dmub, enum replay_state *state, uint8_t panel_inst); void (*replay_enable)(struct dmub_replay *dmub, bool enable, bool wait, - uint8_t panel_inst, struct dc_link *link); + uint8_t panel_inst); bool (*replay_copy_settings)(struct dmub_replay *dmub, struct dc_link *link, struct replay_context *replay_context, uint8_t panel_inst); void (*replay_set_power_opt)(struct dmub_replay *dmub, unsigned int power_opt, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index e7927b8f5ba3..98ec9b5a559c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -944,7 +944,7 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active, // TODO: Handle mux change case if force_static is set // If force_static is set, just change the replay_allow_active state directly if (replay != NULL && link->replay_settings.replay_feature_enabled) - replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst, link); + replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst); link->replay_settings.replay_allow_active = *allow_active; } diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index c587b3441e07..6a69a788abe8 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -4048,14 +4048,6 @@ struct dmub_cmd_replay_copy_settings_data { */ uint8_t digbe_inst; /** - * @hpo_stream_enc_inst: HPO stream encoder instance - */ - uint8_t hpo_stream_enc_inst; - /** - * @hpo_link_enc_inst: HPO link encoder instance - */ - uint8_t hpo_link_enc_inst; - /** * AUX HW instance. */ uint8_t aux_inst; @@ -4159,18 +4151,6 @@ struct dmub_rb_cmd_replay_enable_data { * This does not support HDMI/DP2 for now. */ uint8_t phy_rate; - /** - * @hpo_stream_enc_inst: HPO stream encoder instance - */ - uint8_t hpo_stream_enc_inst; - /** - * @hpo_link_enc_inst: HPO link encoder instance - */ - uint8_t hpo_link_enc_inst; - /** - * @pad: Align structure to 4 byte boundary. - */ - uint8_t pad[2]; }; /** diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index e58e7b93810b..6b7db8ec9a53 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -260,6 +260,9 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp) return MOD_HDCP_STATUS_FAILURE; } + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf; mutex_lock(&psp->hdcp_context.mutex); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 3aea32baea3d..f32474af90b3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1697,9 +1697,11 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, uint32_t *min_power_limit) { struct smu_table_context *table_context = &smu->smu_table; + struct smu_14_0_2_powerplay_table *powerplay_table = + table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - uint32_t power_limit; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; if (smu_v14_0_get_current_power_limit(smu, &power_limit)) @@ -1712,11 +1714,29 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (max_power_limit) - *max_power_limit = msg_limit; + if (powerplay_table) { + if (smu->od_enabled && + smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) { + od_percent_upper = pptable->SkuTable.OverDriveLimitsBasicMax.Ppt; + od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt; + } else if (smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) { + od_percent_upper = 0; + od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt; + } + } + + dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", + od_percent_upper, od_percent_lower, power_limit); + + if (max_power_limit) { + *max_power_limit = msg_limit * (100 + od_percent_upper); + *max_power_limit /= 100; + } - if (min_power_limit) - *min_power_limit = 0; + if (min_power_limit) { + *min_power_limit = power_limit * (100 + od_percent_lower); + *min_power_limit /= 100; + } return 0; } diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index ed35e567d117..efe534977d12 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1474,8 +1474,8 @@ analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data) dp = devm_drm_bridge_alloc(dev, struct analogix_dp_device, bridge, &analogix_dp_bridge_funcs); - if (!dp) - return ERR_PTR(-ENOMEM); + if (IS_ERR(dp)) + return ERR_CAST(dp); dp->dev = &pdev->dev; dp->dpms_mode = DRM_MODE_DPMS_OFF; diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c index b63304d3a80f..b3e4cdff61d6 100644 --- a/drivers/gpu/drm/bridge/aux-bridge.c +++ b/drivers/gpu/drm/bridge/aux-bridge.c @@ -18,6 +18,7 @@ static void drm_aux_bridge_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); + of_node_put(dev->of_node); ida_free(&drm_aux_bridge_ida, adev->id); kfree(adev); @@ -65,6 +66,7 @@ int drm_aux_bridge_register(struct device *parent) ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.of_node); ida_free(&drm_aux_bridge_ida, adev->id); kfree(adev); return ret; diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index dd45d9b504d8..4bde00083047 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -1227,6 +1227,7 @@ EXPORT_SYMBOL(drm_atomic_bridge_chain_check); /** * drm_bridge_detect - check if anything is attached to the bridge output * @bridge: bridge control structure + * @connector: attached connector * * If the bridge supports output detection, as reported by the * DRM_BRIDGE_OP_DETECT bridge ops flag, call &drm_bridge_funcs.detect for the diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index bbc7fecb6f4a..74d949995a72 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -2432,6 +2432,8 @@ static const struct drm_gpuvm_ops lock_ops = { * * The expected usage is: * + * .. code-block:: c + * * vm_bind { * struct drm_exec exec; * diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 09a9b452e8b7..50c286c5cee8 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -381,6 +381,26 @@ struct DecFifo { len: usize, } +// On arm32 architecture, dividing an `u64` by a constant will generate a call +// to `__aeabi_uldivmod` which is not present in the kernel. +// So use the multiply by inverse method for this architecture. +fn div10(val: u64) -> u64 { + if cfg!(target_arch = "arm") { + let val_h = val >> 32; + let val_l = val & 0xFFFFFFFF; + let b_h: u64 = 0x66666666; + let b_l: u64 = 0x66666667; + + let tmp1 = val_h * b_l + ((val_l * b_l) >> 32); + let tmp2 = val_l * b_h + (tmp1 & 0xffffffff); + let tmp3 = val_h * b_h + (tmp1 >> 32) + (tmp2 >> 32); + + tmp3 >> 2 + } else { + val / 10 + } +} + impl DecFifo { fn push(&mut self, data: u64, len: usize) { let mut chunk = data; @@ -389,7 +409,7 @@ impl DecFifo { } for i in 0..len { self.decimals[i] = (chunk % 10) as u8; - chunk /= 10; + chunk = div10(chunk); } self.len += len; } diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c index 74f7832ea53e..0726cb5b736e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c @@ -325,6 +325,17 @@ static int hibmc_dp_link_downgrade_training_eq(struct hibmc_dp_dev *dp) return hibmc_dp_link_reduce_rate(dp); } +static void hibmc_dp_update_caps(struct hibmc_dp_dev *dp) +{ + dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; + if (dp->link.cap.link_rate > DP_LINK_BW_8_1 || !dp->link.cap.link_rate) + dp->link.cap.link_rate = DP_LINK_BW_8_1; + + dp->link.cap.lanes = dp->dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; + if (dp->link.cap.lanes > HIBMC_DP_LANE_NUM_MAX) + dp->link.cap.lanes = HIBMC_DP_LANE_NUM_MAX; +} + int hibmc_dp_link_training(struct hibmc_dp_dev *dp) { struct hibmc_dp_link *link = &dp->link; @@ -334,8 +345,7 @@ int hibmc_dp_link_training(struct hibmc_dp_dev *dp) if (ret) drm_err(dp->dev, "dp aux read dpcd failed, ret: %d\n", ret); - dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; - dp->link.cap.lanes = 0x2; + hibmc_dp_update_caps(dp); ret = hibmc_dp_get_serdes_rate_cfg(dp); if (ret < 0) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 768b97f9e74a..289304500ab0 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -32,7 +32,7 @@ DEFINE_DRM_GEM_FOPS(hibmc_fops); -static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "vblank", "hpd" }; +static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "hibmc-vblank", "hibmc-hpd" }; static irqreturn_t hibmc_interrupt(int irq, void *arg) { @@ -115,6 +115,8 @@ static const struct drm_mode_config_funcs hibmc_mode_funcs = { static int hibmc_kms_init(struct hibmc_drm_private *priv) { struct drm_device *dev = &priv->dev; + struct drm_encoder *encoder; + u32 clone_mask = 0; int ret; ret = drmm_mode_config_init(dev); @@ -154,6 +156,12 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv) return ret; } + drm_for_each_encoder(encoder, dev) + clone_mask |= drm_encoder_mask(encoder); + + drm_for_each_encoder(encoder, dev) + encoder->possible_clones = clone_mask; + return 0; } @@ -277,7 +285,6 @@ static void hibmc_unload(struct drm_device *dev) static int hibmc_msi_init(struct drm_device *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); - char name[32] = {0}; int valid_irq_num; int irq; int ret; @@ -292,9 +299,6 @@ static int hibmc_msi_init(struct drm_device *dev) valid_irq_num = ret; for (int i = 0; i < valid_irq_num; i++) { - snprintf(name, ARRAY_SIZE(name) - 1, "%s-%s-%s", - dev->driver->name, pci_name(pdev), g_irqs_names_map[i]); - irq = pci_irq_vector(pdev, i); if (i) @@ -302,10 +306,10 @@ static int hibmc_msi_init(struct drm_device *dev) ret = devm_request_threaded_irq(&pdev->dev, irq, hibmc_dp_interrupt, hibmc_dp_hpd_isr, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); else ret = devm_request_irq(&pdev->dev, irq, hibmc_interrupt, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); if (ret) { drm_err(dev, "install irq failed: %d\n", ret); return ret; @@ -323,13 +327,13 @@ static int hibmc_load(struct drm_device *dev) ret = hibmc_hw_init(priv); if (ret) - goto err; + return ret; ret = drmm_vram_helper_init(dev, pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); if (ret) { drm_err(dev, "Error initializing VRAM MM; %d\n", ret); - goto err; + return ret; } ret = hibmc_kms_init(priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 274feabe7df0..ca8502e2760c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -69,6 +69,7 @@ int hibmc_de_init(struct hibmc_drm_private *priv); int hibmc_vdac_init(struct hibmc_drm_private *priv); int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *connector); +void hibmc_ddc_del(struct hibmc_vdac *vdac); int hibmc_dp_init(struct hibmc_drm_private *priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c index 99b3b77b5445..44860011855e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -95,3 +95,8 @@ int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *vdac) return i2c_bit_add_bus(&vdac->adapter); } + +void hibmc_ddc_del(struct hibmc_vdac *vdac) +{ + i2c_del_adapter(&vdac->adapter); +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index e8a527ede854..841e81f47b68 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -53,7 +53,7 @@ static void hibmc_connector_destroy(struct drm_connector *connector) { struct hibmc_vdac *vdac = to_hibmc_vdac(connector); - i2c_del_adapter(&vdac->adapter); + hibmc_ddc_del(vdac); drm_connector_cleanup(connector); } @@ -110,7 +110,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_DAC, NULL); if (ret) { drm_err(dev, "failed to init encoder: %d\n", ret); - return ret; + goto err; } drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs); @@ -121,7 +121,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) &vdac->adapter); if (ret) { drm_err(dev, "failed to init connector: %d\n", ret); - return ret; + goto err; } drm_connector_helper_add(connector, &hibmc_connector_helper_funcs); @@ -131,4 +131,9 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; return 0; + +err: + hibmc_ddc_del(vdac); + + return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c index fb25ec8adae3..68157f177b6a 100644 --- a/drivers/gpu/drm/i915/display/intel_display_irq.c +++ b/drivers/gpu/drm/i915/display/intel_display_irq.c @@ -1506,10 +1506,14 @@ u32 gen11_gu_misc_irq_ack(struct intel_display *display, const u32 master_ctl) if (!(master_ctl & GEN11_GU_MISC_IRQ)) return 0; + intel_display_rpm_assert_block(display); + iir = intel_de_read(display, GEN11_GU_MISC_IIR); if (likely(iir)) intel_de_write(display, GEN11_GU_MISC_IIR, iir); + intel_display_rpm_assert_unblock(display); + return iir; } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 6e26cb4c5724..685ac98bd001 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -552,10 +552,6 @@ static void ilk_fbc_deactivate(struct intel_fbc *fbc) if (dpfc_ctl & DPFC_CTL_EN) { dpfc_ctl &= ~DPFC_CTL_EN; intel_de_write(display, ILK_DPFC_CONTROL(fbc->id), dpfc_ctl); - - /* wa_18038517565 Enable DPFC clock gating after FBC disable */ - if (display->platform.dg2 || DISPLAY_VER(display) >= 14) - fbc_compressor_clkgate_disable_wa(fbc, false); } } @@ -1710,6 +1706,10 @@ static void __intel_fbc_disable(struct intel_fbc *fbc) __intel_fbc_cleanup_cfb(fbc); + /* wa_18038517565 Enable DPFC clock gating after FBC disable */ + if (display->platform.dg2 || DISPLAY_VER(display) >= 14) + fbc_compressor_clkgate_disable_wa(fbc, false); + fbc->state.plane = NULL; fbc->flip_pending = false; fbc->busy_bits = 0; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index ae9053919211..41988e193a41 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -3275,7 +3275,9 @@ static void intel_psr_configure_full_frame_update(struct intel_dp *intel_dp) static void _psr_invalidate_handle(struct intel_dp *intel_dp) { - if (intel_dp->psr.psr2_sel_fetch_enabled) { + struct intel_display *display = to_intel_display(intel_dp); + + if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) { if (!intel_dp->psr.psr2_sel_fetch_cff_enabled) { intel_dp->psr.psr2_sel_fetch_cff_enabled = true; intel_psr_configure_full_frame_update(intel_dp); @@ -3361,7 +3363,7 @@ static void _psr_flush_handle(struct intel_dp *intel_dp) { struct intel_display *display = to_intel_display(intel_dp); - if (intel_dp->psr.psr2_sel_fetch_enabled) { + if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) { if (intel_dp->psr.psr2_sel_fetch_cff_enabled) { /* can we turn CFF off? */ if (intel_dp->psr.busy_frontbuffer_bits == 0) @@ -3378,11 +3380,13 @@ static void _psr_flush_handle(struct intel_dp *intel_dp) * existing SU configuration */ intel_psr_configure_full_frame_update(intel_dp); - } - intel_psr_force_update(intel_dp); + intel_psr_force_update(intel_dp); + } else { + intel_psr_exit(intel_dp); + } - if (!intel_dp->psr.psr2_sel_fetch_enabled && !intel_dp->psr.active && + if ((!intel_dp->psr.psr2_sel_fetch_enabled || DISPLAY_VER(display) >= 20) && !intel_dp->psr.busy_frontbuffer_bits) queue_work(display->wq.unordered, &intel_dp->psr.work); } diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 3bc57579fe53..668ef139391b 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -23,6 +23,7 @@ #include "intel_modeset_lock.h" #include "intel_tc.h" +#define DP_PIN_ASSIGNMENT_NONE 0x0 #define DP_PIN_ASSIGNMENT_C 0x3 #define DP_PIN_ASSIGNMENT_D 0x4 #define DP_PIN_ASSIGNMENT_E 0x5 @@ -66,6 +67,7 @@ struct intel_tc_port { enum tc_port_mode init_mode; enum phy_fia phy_fia; u8 phy_fia_idx; + u8 max_lane_count; }; static enum intel_display_power_domain @@ -307,6 +309,8 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port) REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val); switch (pin_assignment) { + case DP_PIN_ASSIGNMENT_NONE: + return 0; default: MISSING_CASE(pin_assignment); fallthrough; @@ -365,12 +369,12 @@ static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port) } } -int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port) +static int get_max_lane_count(struct intel_tc_port *tc) { - struct intel_display *display = to_intel_display(dig_port); - struct intel_tc_port *tc = to_tc_port(dig_port); + struct intel_display *display = to_intel_display(tc->dig_port); + struct intel_digital_port *dig_port = tc->dig_port; - if (!intel_encoder_is_tc(&dig_port->base) || tc->mode != TC_PORT_DP_ALT) + if (tc->mode != TC_PORT_DP_ALT) return 4; assert_tc_cold_blocked(tc); @@ -384,6 +388,25 @@ int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port) return intel_tc_port_get_max_lane_count(dig_port); } +static void read_pin_configuration(struct intel_tc_port *tc) +{ + tc->max_lane_count = get_max_lane_count(tc); +} + +int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port) +{ + struct intel_display *display = to_intel_display(dig_port); + struct intel_tc_port *tc = to_tc_port(dig_port); + + if (!intel_encoder_is_tc(&dig_port->base)) + return 4; + + if (DISPLAY_VER(display) < 20) + return get_max_lane_count(tc); + + return tc->max_lane_count; +} + void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port, int required_lanes) { @@ -596,9 +619,12 @@ static void icl_tc_phy_get_hw_state(struct intel_tc_port *tc) tc_cold_wref = __tc_cold_block(tc, &domain); tc->mode = tc_phy_get_current_mode(tc); - if (tc->mode != TC_PORT_DISCONNECTED) + if (tc->mode != TC_PORT_DISCONNECTED) { tc->lock_wakeref = tc_cold_block(tc); + read_pin_configuration(tc); + } + __tc_cold_unblock(tc, domain, tc_cold_wref); } @@ -656,8 +682,11 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc, tc->lock_wakeref = tc_cold_block(tc); - if (tc->mode == TC_PORT_TBT_ALT) + if (tc->mode == TC_PORT_TBT_ALT) { + read_pin_configuration(tc); + return true; + } if ((!tc_phy_is_ready(tc) || !icl_tc_phy_take_ownership(tc, true)) && @@ -668,6 +697,7 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc, goto out_unblock_tc_cold; } + read_pin_configuration(tc); if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes)) goto out_release_phy; @@ -858,9 +888,12 @@ static void adlp_tc_phy_get_hw_state(struct intel_tc_port *tc) port_wakeref = intel_display_power_get(display, port_power_domain); tc->mode = tc_phy_get_current_mode(tc); - if (tc->mode != TC_PORT_DISCONNECTED) + if (tc->mode != TC_PORT_DISCONNECTED) { tc->lock_wakeref = tc_cold_block(tc); + read_pin_configuration(tc); + } + intel_display_power_put(display, port_power_domain, port_wakeref); } @@ -873,6 +906,9 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes) if (tc->mode == TC_PORT_TBT_ALT) { tc->lock_wakeref = tc_cold_block(tc); + + read_pin_configuration(tc); + return true; } @@ -894,6 +930,8 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes) tc->lock_wakeref = tc_cold_block(tc); + read_pin_configuration(tc); + if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes)) goto out_unblock_tc_cold; @@ -1124,9 +1162,18 @@ static void xelpdp_tc_phy_get_hw_state(struct intel_tc_port *tc) tc_cold_wref = __tc_cold_block(tc, &domain); tc->mode = tc_phy_get_current_mode(tc); - if (tc->mode != TC_PORT_DISCONNECTED) + if (tc->mode != TC_PORT_DISCONNECTED) { tc->lock_wakeref = tc_cold_block(tc); + read_pin_configuration(tc); + /* + * Set a valid lane count value for a DP-alt sink which got + * disconnected. The driver can only disable the output on this PHY. + */ + if (tc->max_lane_count == 0) + tc->max_lane_count = 4; + } + drm_WARN_ON(display->drm, (tc->mode == TC_PORT_DP_ALT || tc->mode == TC_PORT_LEGACY) && !xelpdp_tc_phy_tcss_power_is_enabled(tc)); @@ -1138,14 +1185,19 @@ static bool xelpdp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes) { tc->lock_wakeref = tc_cold_block(tc); - if (tc->mode == TC_PORT_TBT_ALT) + if (tc->mode == TC_PORT_TBT_ALT) { + read_pin_configuration(tc); + return true; + } if (!xelpdp_tc_phy_enable_tcss_power(tc, true)) goto out_unblock_tccold; xelpdp_tc_phy_take_ownership(tc, true); + read_pin_configuration(tc); + if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes)) goto out_release_phy; @@ -1226,14 +1278,19 @@ static void tc_phy_get_hw_state(struct intel_tc_port *tc) tc->phy_ops->get_hw_state(tc); } -static bool tc_phy_is_ready_and_owned(struct intel_tc_port *tc, - bool phy_is_ready, bool phy_is_owned) +/* Is the PHY owned by display i.e. is it in legacy or DP-alt mode? */ +static bool tc_phy_owned_by_display(struct intel_tc_port *tc, + bool phy_is_ready, bool phy_is_owned) { struct intel_display *display = to_intel_display(tc->dig_port); - drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready); + if (DISPLAY_VER(display) < 20) { + drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready); - return phy_is_ready && phy_is_owned; + return phy_is_ready && phy_is_owned; + } else { + return phy_is_owned; + } } static bool tc_phy_is_connected(struct intel_tc_port *tc, @@ -1244,7 +1301,7 @@ static bool tc_phy_is_connected(struct intel_tc_port *tc, bool phy_is_owned = tc_phy_is_owned(tc); bool is_connected; - if (tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned)) + if (tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned)) is_connected = port_pll_type == ICL_PORT_DPLL_MG_PHY; else is_connected = port_pll_type == ICL_PORT_DPLL_DEFAULT; @@ -1352,7 +1409,7 @@ tc_phy_get_current_mode(struct intel_tc_port *tc) phy_is_ready = tc_phy_is_ready(tc); phy_is_owned = tc_phy_is_owned(tc); - if (!tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned)) { + if (!tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned)) { mode = get_tc_mode_in_phy_not_owned_state(tc, live_mode); } else { drm_WARN_ON(display->drm, live_mode == TC_PORT_TBT_ALT); @@ -1441,11 +1498,11 @@ static void intel_tc_port_reset_mode(struct intel_tc_port *tc, intel_display_power_flush_work(display); if (!intel_tc_cold_requires_aux_pw(dig_port)) { enum intel_display_power_domain aux_domain; - bool aux_powered; aux_domain = intel_aux_power_domain(dig_port); - aux_powered = intel_display_power_is_enabled(display, aux_domain); - drm_WARN_ON(display->drm, aux_powered); + if (intel_display_power_is_enabled(display, aux_domain)) + drm_dbg_kms(display->drm, "Port %s: AUX unexpectedly powered\n", + tc->port_name); } tc_phy_disconnect(tc); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index b37e400f74e5..5a95f06900b5 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -634,6 +634,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine, static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = engine->i915; + /* Wa_1406697149 (WaDisableBankHangMode:icl) */ wa_write(wal, GEN8_L3CNTLREG, GEN8_ERRDETBCTRL); @@ -669,6 +671,15 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_1406306137:icl,ehl */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); + + if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) { + /* + * Disable Repacking for Compression (masked R/W access) + * before rendering compressed surfaces for display. + */ + wa_masked_en(wal, CACHE_MODE_0_GEN7, + DISABLE_REPACKING_FOR_COMPRESSION); + } } /* @@ -2306,15 +2317,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN8_RC_SEMA_IDLE_MSG_DISABLE); } - if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) { - /* - * "Disable Repacking for Compression (masked R/W access) - * before rendering compressed surfaces for display." - */ - wa_masked_en(wal, CACHE_MODE_0_GEN7, - DISABLE_REPACKING_FOR_COMPRESSION); - } - if (GRAPHICS_VER(i915) == 11) { /* This is not an Wa. Enable for better image quality */ wa_masked_en(wal, diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index e1e542126310..805d0a87aa54 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -253,6 +253,7 @@ nouveau_check_bl_size(struct nouveau_drm *drm, struct nouveau_bo *nvbo, int nouveau_framebuffer_new(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *gem, struct drm_framebuffer **pfb) @@ -260,7 +261,6 @@ nouveau_framebuffer_new(struct drm_device *dev, struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct drm_framebuffer *fb; - const struct drm_format_info *info; unsigned int height, i; uint32_t tile_mode; uint8_t kind; @@ -295,9 +295,6 @@ nouveau_framebuffer_new(struct drm_device *dev, kind = nvbo->kind; } - info = drm_get_format_info(dev, mode_cmd->pixel_format, - mode_cmd->modifier[0]); - for (i = 0; i < info->num_planes; i++) { height = drm_format_info_plane_height(info, mode_cmd->height, @@ -321,7 +318,7 @@ nouveau_framebuffer_new(struct drm_device *dev, if (!(fb = *pfb = kzalloc(sizeof(*fb), GFP_KERNEL))) return -ENOMEM; - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); fb->obj[0] = gem; ret = drm_framebuffer_init(dev, fb, &nouveau_framebuffer_funcs); @@ -344,7 +341,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, if (!gem) return ERR_PTR(-ENOENT); - ret = nouveau_framebuffer_new(dev, mode_cmd, gem, &fb); + ret = nouveau_framebuffer_new(dev, info, mode_cmd, gem, &fb); if (ret == 0) return fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index e45f211501f6..470e0910d484 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -8,8 +8,11 @@ #include <drm/drm_framebuffer.h> +struct drm_format_info; + int nouveau_framebuffer_new(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *gem, struct drm_framebuffer **pfb); diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index edbbda78bac9..c4949e815eb3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -60,14 +60,14 @@ * virtual address in the GPU's VA space there is no guarantee that the actual * mappings are created in the GPU's MMU. If the given memory is swapped out * at the time the bind operation is executed the kernel will stash the mapping - * details into it's internal alloctor and create the actual MMU mappings once + * details into it's internal allocator and create the actual MMU mappings once * the memory is swapped back in. While this is transparent for userspace, it is * guaranteed that all the backing memory is swapped back in and all the memory * mappings, as requested by userspace previously, are actually mapped once the * DRM_NOUVEAU_EXEC ioctl is called to submit an exec job. * * A VM_BIND job can be executed either synchronously or asynchronously. If - * exectued asynchronously, userspace may provide a list of syncobjs this job + * executed asynchronously, userspace may provide a list of syncobjs this job * will wait for and/or a list of syncobj the kernel will signal once the * VM_BIND job finished execution. If executed synchronously the ioctl will * block until the bind job is finished. For synchronous jobs the kernel will @@ -82,7 +82,7 @@ * Since VM_BIND jobs update the GPU's VA space on job submit, EXEC jobs do have * an up to date view of the VA space. However, the actual mappings might still * be pending. Hence, EXEC jobs require to have the particular fences - of - * the corresponding VM_BIND jobs they depent on - attached to them. + * the corresponding VM_BIND jobs they depend on - attached to them. */ static int diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c index 99296f03371a..07c1ebc2a941 100644 --- a/drivers/gpu/drm/nouveau/nvif/vmm.c +++ b/drivers/gpu/drm/nouveau/nvif/vmm.c @@ -219,7 +219,8 @@ nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, case RAW: args->type = NVIF_VMM_V0_TYPE_RAW; break; default: WARN_ON(1); - return -EINVAL; + ret = -EINVAL; + goto done; } memcpy(args->data, argv, argc); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c index 9d06ff722fea..0dc4782df8c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c @@ -325,7 +325,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_peek(gsp, sizeof(*rpc), info.retries); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } @@ -334,7 +334,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_recv_one_elem(gsp, &info); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } diff --git a/drivers/gpu/drm/nova/file.rs b/drivers/gpu/drm/nova/file.rs index 7e59a34b830d..4fe62cf98a23 100644 --- a/drivers/gpu/drm/nova/file.rs +++ b/drivers/gpu/drm/nova/file.rs @@ -39,7 +39,8 @@ impl File { _ => return Err(EINVAL), }; - getparam.set_value(value); + #[allow(clippy::useless_conversion)] + getparam.set_value(value.into()); Ok(0) } diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c index 30c81e2e5d6b..bb3105556f19 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.c +++ b/drivers/gpu/drm/omapdrm/omap_fb.c @@ -351,7 +351,7 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev, } } - fb = omap_framebuffer_init(dev, mode_cmd, bos); + fb = omap_framebuffer_init(dev, info, mode_cmd, bos); if (IS_ERR(fb)) goto error; @@ -365,9 +365,9 @@ error: } struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos) { - const struct drm_format_info *format = NULL; struct omap_framebuffer *omap_fb = NULL; struct drm_framebuffer *fb = NULL; unsigned int pitch = mode_cmd->pitches[0]; @@ -377,15 +377,12 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, dev, mode_cmd, mode_cmd->width, mode_cmd->height, (char *)&mode_cmd->pixel_format); - format = drm_get_format_info(dev, mode_cmd->pixel_format, - mode_cmd->modifier[0]); - for (i = 0; i < ARRAY_SIZE(formats); i++) { if (formats[i] == mode_cmd->pixel_format) break; } - if (!format || i == ARRAY_SIZE(formats)) { + if (i == ARRAY_SIZE(formats)) { dev_dbg(dev->dev, "unsupported pixel format: %4.4s\n", (char *)&mode_cmd->pixel_format); ret = -EINVAL; @@ -399,7 +396,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, } fb = &omap_fb->base; - omap_fb->format = format; + omap_fb->format = info; mutex_init(&omap_fb->lock); /* @@ -407,23 +404,23 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, * that the two planes of multiplane formats need the same number of * bytes per pixel. */ - if (format->num_planes == 2 && pitch != mode_cmd->pitches[1]) { + if (info->num_planes == 2 && pitch != mode_cmd->pitches[1]) { dev_dbg(dev->dev, "pitches differ between planes 0 and 1\n"); ret = -EINVAL; goto fail; } - if (pitch % format->cpp[0]) { + if (pitch % info->cpp[0]) { dev_dbg(dev->dev, "buffer pitch (%u bytes) is not a multiple of pixel size (%u bytes)\n", - pitch, format->cpp[0]); + pitch, info->cpp[0]); ret = -EINVAL; goto fail; } - for (i = 0; i < format->num_planes; i++) { + for (i = 0; i < info->num_planes; i++) { struct plane *plane = &omap_fb->planes[i]; - unsigned int vsub = i == 0 ? 1 : format->vsub; + unsigned int vsub = i == 0 ? 1 : info->vsub; unsigned int size; size = pitch * mode_cmd->height / vsub; @@ -440,7 +437,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, plane->dma_addr = 0; } - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); ret = drm_framebuffer_init(dev, fb, &omap_framebuffer_funcs); if (ret) { diff --git a/drivers/gpu/drm/omapdrm/omap_fb.h b/drivers/gpu/drm/omapdrm/omap_fb.h index 0873f953cf1d..e6010302a22b 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.h +++ b/drivers/gpu/drm/omapdrm/omap_fb.h @@ -13,6 +13,7 @@ struct drm_connector; struct drm_device; struct drm_file; struct drm_framebuffer; +struct drm_format_info; struct drm_gem_object; struct drm_mode_fb_cmd2; struct drm_plane_state; @@ -23,6 +24,7 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd); struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos); int omap_framebuffer_pin(struct drm_framebuffer *fb); void omap_framebuffer_unpin(struct drm_framebuffer *fb); diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 7b6396890681..948af7ec1130 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -197,7 +197,10 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fb = omap_framebuffer_init(dev, &mode_cmd, &bo); + fb = omap_framebuffer_init(dev, + drm_get_format_info(dev, mode_cmd.pixel_format, + mode_cmd.modifier[0]), + &mode_cmd, &bo); if (IS_ERR(fb)) { dev_err(dev->dev, "failed to allocate fb\n"); /* note: if fb creation failed, we can't rely on fb destroy diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index bb73f2a68a12..85d6289a6eda 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -432,7 +432,7 @@ static void panfrost_gem_debugfs_bo_print(struct panfrost_gem_object *bo, if (!refcount) return; - resident_size = bo->base.pages ? bo->base.base.size : 0; + resident_size = panfrost_gem_rss(&bo->base.base); snprintf(creator_info, sizeof(creator_info), "%s/%d", bo->debugfs.creator.process_name, bo->debugfs.creator.tgid); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b4bf5dfeea2d..4dc77c398617 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1297,12 +1297,13 @@ static const struct drm_framebuffer_funcs radeon_fb_funcs = { int radeon_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj) { int ret; fb->obj[0] = obj; - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); ret = drm_framebuffer_init(dev, fb, &radeon_fb_funcs); if (ret) { fb->obj[0] = NULL; @@ -1341,7 +1342,7 @@ radeon_user_framebuffer_create(struct drm_device *dev, return ERR_PTR(-ENOMEM); } - ret = radeon_framebuffer_init(dev, fb, mode_cmd, obj); + ret = radeon_framebuffer_init(dev, fb, info, mode_cmd, obj); if (ret) { kfree(fb); drm_gem_object_put(obj); diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c index e3a481bbee7b..dc81b0c2dbff 100644 --- a/drivers/gpu/drm/radeon/radeon_fbdev.c +++ b/drivers/gpu/drm/radeon/radeon_fbdev.c @@ -53,10 +53,10 @@ static void radeon_fbdev_destroy_pinned_object(struct drm_gem_object *gobj) } static int radeon_fbdev_create_pinned_object(struct drm_fb_helper *fb_helper, + const struct drm_format_info *info, struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **gobj_p) { - const struct drm_format_info *info; struct radeon_device *rdev = fb_helper->dev->dev_private; struct drm_gem_object *gobj = NULL; struct radeon_bo *rbo = NULL; @@ -67,8 +67,6 @@ static int radeon_fbdev_create_pinned_object(struct drm_fb_helper *fb_helper, int height = mode_cmd->height; u32 cpp; - info = drm_get_format_info(rdev_to_drm(rdev), mode_cmd->pixel_format, - mode_cmd->modifier[0]); cpp = info->cpp[0]; /* need to align pitch with crtc limits */ @@ -206,6 +204,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct radeon_device *rdev = fb_helper->dev->dev_private; + const struct drm_format_info *format_info; struct drm_mode_fb_cmd2 mode_cmd = { }; struct fb_info *info; struct drm_gem_object *gobj; @@ -224,7 +223,9 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); - ret = radeon_fbdev_create_pinned_object(fb_helper, &mode_cmd, &gobj); + format_info = drm_get_format_info(rdev_to_drm(rdev), mode_cmd.pixel_format, + mode_cmd.modifier[0]); + ret = radeon_fbdev_create_pinned_object(fb_helper, format_info, &mode_cmd, &gobj); if (ret) { DRM_ERROR("failed to create fbcon object %d\n", ret); return ret; @@ -236,7 +237,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, ret = -ENOMEM; goto err_radeon_fbdev_destroy_pinned_object; } - ret = radeon_framebuffer_init(rdev_to_drm(rdev), fb, &mode_cmd, gobj); + ret = radeon_framebuffer_init(rdev_to_drm(rdev), fb, format_info, &mode_cmd, gobj); if (ret) { DRM_ERROR("failed to initialize framebuffer %d\n", ret); goto err_kfree; diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 3102f6c2d055..9e34da2cacef 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -40,6 +40,7 @@ struct drm_fb_helper; struct drm_fb_helper_surface_size; +struct drm_format_info; struct edid; struct drm_edid; @@ -890,6 +891,7 @@ extern void radeon_combios_encoder_dpms_scratch_regs(struct drm_encoder *encoder, bool on); int radeon_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *rfb, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index ab525668939a..faf50d872be3 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -53,6 +53,7 @@ config ROCKCHIP_CDN_DP bool "Rockchip cdn DP" depends on EXTCON=y || (EXTCON=m && DRM_ROCKCHIP=m) select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR select DRM_DISPLAY_DP_HELPER help This selects support for Rockchip SoC specific extensions diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 186f6452a7d3..b50927a824b4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -2579,12 +2579,13 @@ static int vop2_win_init(struct vop2 *vop2) } /* - * The window registers are only updated when config done is written. - * Until that they read back the old value. As we read-modify-write - * these registers mark them as non-volatile. This makes sure we read - * the new values from the regmap register cache. + * The window and video port registers are only updated when config + * done is written. Until that they read back the old value. As we + * read-modify-write these registers mark them as non-volatile. This + * makes sure we read the new values from the regmap register cache. */ static const struct regmap_range vop2_nonvolatile_range[] = { + regmap_reg_range(RK3568_VP0_CTRL_BASE, RK3588_VP3_CTRL_BASE + 255), regmap_reg_range(0x1000, 0x23ff), }; diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c index 7299fa8971ce..981dada8f3a8 100644 --- a/drivers/gpu/drm/tests/drm_format_helper_test.c +++ b/drivers/gpu/drm/tests/drm_format_helper_test.c @@ -1033,13 +1033,14 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test) NULL : &result->dst_pitch; drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); - buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32)); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); buf = dst.vaddr; /* restore original value of buf */ memset(buf, 0, dst_size); drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } diff --git a/drivers/gpu/drm/xe/regs/xe_bars.h b/drivers/gpu/drm/xe/regs/xe_bars.h index ce05b6ae832f..880140d6ccdc 100644 --- a/drivers/gpu/drm/xe/regs/xe_bars.h +++ b/drivers/gpu/drm/xe/regs/xe_bars.h @@ -7,5 +7,6 @@ #define GTTMMADR_BAR 0 /* MMIO + GTT */ #define LMEM_BAR 2 /* VRAM */ +#define VF_LMEM_BAR 9 /* VF VRAM */ #endif diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index f08fc4377d25..c17ed1ae8649 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -332,6 +332,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe int ret = 0; u32 reg_val, max; struct xe_reg rapl_limit; + u64 max_supp_power_limit = 0; mutex_lock(&hwmon->hwmon_lock); @@ -356,6 +357,20 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe goto unlock; } + /* + * If the sysfs value exceeds the maximum pcode supported power limit value, clamp it to + * the supported maximum (U12.3 format). + * This is to avoid truncation during reg_val calculation below and ensure the valid + * power limit is sent for pcode which would clamp it to card-supported value. + */ + max_supp_power_limit = ((PWR_LIM_VAL) >> hwmon->scl_shift_power) * SF_POWER; + if (value > max_supp_power_limit) { + value = max_supp_power_limit; + drm_info(&hwmon->xe->drm, + "Power limit clamped as selected %s exceeds channel %d limit\n", + PWR_ATTR_TO_STR(attr), channel); + } + /* Computation in 64-bits to avoid overflow. Round to nearest. */ reg_val = DIV_ROUND_CLOSEST_ULL((u64)value << hwmon->scl_shift_power, SF_POWER); @@ -739,9 +754,23 @@ static int xe_hwmon_power_curr_crit_write(struct xe_hwmon *hwmon, int channel, { int ret; u32 uval; + u64 max_crit_power_curr = 0; mutex_lock(&hwmon->hwmon_lock); + /* + * If the sysfs value exceeds the pcode mailbox cmd POWER_SETUP_SUBCOMMAND_WRITE_I1 + * max supported value, clamp it to the command's max (U10.6 format). + * This is to avoid truncation during uval calculation below and ensure the valid power + * limit is sent for pcode which would clamp it to card-supported value. + */ + max_crit_power_curr = (POWER_SETUP_I1_DATA_MASK >> POWER_SETUP_I1_SHIFT) * scale_factor; + if (value > max_crit_power_curr) { + value = max_crit_power_curr; + drm_info(&hwmon->xe->drm, + "Power limit clamped as selected exceeds channel %d limit\n", + channel); + } uval = DIV_ROUND_CLOSEST_ULL(value << POWER_SETUP_I1_SHIFT, scale_factor); ret = xe_hwmon_pcode_write_i1(hwmon, uval); diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index ba1cff2e4cda..84f412fd3c5d 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -408,7 +408,7 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile) /* Special layout, prepared below.. */ vm = xe_vm_create(xe, XE_VM_FLAG_MIGRATION | - XE_VM_FLAG_SET_TILE_ID(tile)); + XE_VM_FLAG_SET_TILE_ID(tile), NULL); if (IS_ERR(vm)) return ERR_CAST(vm); @@ -1820,15 +1820,19 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) || !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) { int buf_offset = 0; + void *bounce; + int err; + + BUILD_BUG_ON(!is_power_of_2(XE_CACHELINE_BYTES)); + bounce = kmalloc(XE_CACHELINE_BYTES, GFP_KERNEL); + if (!bounce) + return -ENOMEM; /* * Less than ideal for large unaligned access but this should be * fairly rare, can fixup if this becomes common. */ do { - u8 bounce[XE_CACHELINE_BYTES]; - void *ptr = (void *)bounce; - int err; int copy_bytes = min_t(int, bytes_left, XE_CACHELINE_BYTES - (offset & XE_CACHELINE_MASK)); @@ -1837,22 +1841,22 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, - (void *)ptr, - sizeof(bounce), 0); + bounce, + XE_CACHELINE_BYTES, 0); if (err) - return err; + break; if (write) { - memcpy(ptr + ptr_offset, buf + buf_offset, copy_bytes); + memcpy(bounce + ptr_offset, buf + buf_offset, copy_bytes); err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, - (void *)ptr, - sizeof(bounce), write); + bounce, + XE_CACHELINE_BYTES, write); if (err) - return err; + break; } else { - memcpy(buf + buf_offset, ptr + ptr_offset, + memcpy(buf + buf_offset, bounce + ptr_offset, copy_bytes); } @@ -1861,7 +1865,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, offset += copy_bytes; } while (bytes_left); - return 0; + kfree(bounce); + return err; } dma_addr = xe_migrate_dma_map(xe, buf, len + page_offset, write); @@ -1882,8 +1887,11 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, else current_bytes = min_t(int, bytes_left, cursor.size); - if (fence) - dma_fence_put(fence); + if (current_bytes & ~PAGE_MASK) { + int pitch = 4; + + current_bytes = min_t(int, current_bytes, S16_MAX * pitch); + } __fence = xe_migrate_vram(m, current_bytes, (unsigned long)buf & ~PAGE_MASK, @@ -1892,11 +1900,15 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, XE_MIGRATE_COPY_TO_VRAM : XE_MIGRATE_COPY_TO_SRAM); if (IS_ERR(__fence)) { - if (fence) + if (fence) { dma_fence_wait(fence, false); + dma_fence_put(fence); + } fence = __fence; goto out_err; } + + dma_fence_put(fence); fence = __fence; buf += current_bytes; diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c index 447a7867eecb..af05db07162e 100644 --- a/drivers/gpu/drm/xe/xe_pci_sriov.c +++ b/drivers/gpu/drm/xe/xe_pci_sriov.c @@ -3,6 +3,10 @@ * Copyright © 2023-2024 Intel Corporation */ +#include <linux/bitops.h> +#include <linux/pci.h> + +#include "regs/xe_bars.h" #include "xe_assert.h" #include "xe_device.h" #include "xe_gt_sriov_pf_config.h" @@ -128,6 +132,18 @@ static void pf_engine_activity_stats(struct xe_device *xe, unsigned int num_vfs, } } +static int resize_vf_vram_bar(struct xe_device *xe, int num_vfs) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + u32 sizes; + + sizes = pci_iov_vf_bar_get_sizes(pdev, VF_LMEM_BAR, num_vfs); + if (!sizes) + return 0; + + return pci_iov_vf_bar_set_size(pdev, VF_LMEM_BAR, __fls(sizes)); +} + static int pf_enable_vfs(struct xe_device *xe, int num_vfs) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); @@ -158,6 +174,12 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs) if (err < 0) goto failed; + if (IS_DGFX(xe)) { + err = resize_vf_vram_bar(xe, num_vfs); + if (err) + xe_sriov_info(xe, "Failed to set VF LMEM BAR size: %d\n", err); + } + err = pci_enable_sriov(pdev, num_vfs); if (err < 0) goto failed; diff --git a/drivers/gpu/drm/xe/xe_pxp_submit.c b/drivers/gpu/drm/xe/xe_pxp_submit.c index d92ec0f515b0..ca95f2a4d4ef 100644 --- a/drivers/gpu/drm/xe/xe_pxp_submit.c +++ b/drivers/gpu/drm/xe/xe_pxp_submit.c @@ -101,7 +101,7 @@ static int allocate_gsc_client_resources(struct xe_gt *gt, xe_assert(xe, hwe); /* PXP instructions must be issued from PPGTT */ - vm = xe_vm_create(xe, XE_VM_FLAG_GSC); + vm = xe_vm_create(xe, XE_VM_FLAG_GSC, NULL); if (IS_ERR(vm)) return PTR_ERR(vm); diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c index 1c3c04d52f55..90244fe59b59 100644 --- a/drivers/gpu/drm/xe/xe_shrinker.c +++ b/drivers/gpu/drm/xe/xe_shrinker.c @@ -54,10 +54,10 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea write_unlock(&shrinker->lock); } -static s64 xe_shrinker_walk(struct xe_device *xe, - struct ttm_operation_ctx *ctx, - const struct xe_bo_shrink_flags flags, - unsigned long to_scan, unsigned long *scanned) +static s64 __xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) { unsigned int mem_type; s64 freed = 0, lret; @@ -93,6 +93,48 @@ static s64 xe_shrinker_walk(struct xe_device *xe, return freed; } +/* + * Try shrinking idle objects without writeback first, then if not sufficient, + * try also non-idle objects and finally if that's not sufficient either, + * add writeback. This avoids stalls and explicit writebacks with light or + * moderate memory pressure. + */ +static s64 xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) +{ + bool no_wait_gpu = true; + struct xe_bo_shrink_flags save_flags = flags; + s64 lret, freed; + + swap(no_wait_gpu, ctx->no_wait_gpu); + save_flags.writeback = false; + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + swap(no_wait_gpu, ctx->no_wait_gpu); + if (lret < 0 || *scanned >= to_scan) + return lret; + + freed = lret; + if (!ctx->no_wait_gpu) { + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + if (*scanned >= to_scan) + return freed; + } + + if (flags.writeback) { + lret = __xe_shrinker_walk(xe, ctx, flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + } + + return freed; +} + static unsigned long xe_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -199,6 +241,7 @@ static unsigned long xe_shrinker_scan(struct shrinker *shrink, struct shrink_con runtime_pm = xe_shrinker_runtime_pm_get(shrinker, true, 0, can_backup); shrink_flags.purge = false; + lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags, nr_to_scan, &nr_scanned); if (lret >= 0) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 2035604121e6..ec04bef8ae40 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1640,7 +1640,7 @@ static void xe_vm_free_scratch(struct xe_vm *vm) } } -struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) +struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) { struct drm_gem_object *vm_resv_obj; struct xe_vm *vm; @@ -1661,9 +1661,10 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) vm->xe = xe; vm->size = 1ull << xe->info.va_bits; - vm->flags = flags; + if (xef) + vm->xef = xe_file_get(xef); /** * GSC VMs are kernel-owned, only used for PXP ops and can sometimes be * manipulated under the PXP mutex. However, the PXP mutex can be taken @@ -1794,6 +1795,20 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) if (number_tiles > 1) vm->composite_fence_ctx = dma_fence_context_alloc(1); + if (xef && xe->info.has_asid) { + u32 asid; + + down_write(&xe->usm.lock); + err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm, + XA_LIMIT(1, XE_MAX_ASID - 1), + &xe->usm.next_asid, GFP_KERNEL); + up_write(&xe->usm.lock); + if (err < 0) + goto err_unlock_close; + + vm->usm.asid = asid; + } + trace_xe_vm_create(vm); return vm; @@ -1814,6 +1829,8 @@ err_no_resv: for_each_tile(tile, xe, id) xe_range_fence_tree_fini(&vm->rftree[id]); ttm_lru_bulk_move_fini(&xe->ttm, &vm->lru_bulk_move); + if (vm->xef) + xe_file_put(vm->xef); kfree(vm); if (flags & XE_VM_FLAG_LR_MODE) xe_pm_runtime_put(xe); @@ -2059,9 +2076,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, struct xe_device *xe = to_xe_device(dev); struct xe_file *xef = to_xe_file(file); struct drm_xe_vm_create *args = data; - struct xe_tile *tile; struct xe_vm *vm; - u32 id, asid; + u32 id; int err; u32 flags = 0; @@ -2097,29 +2113,10 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, if (args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE) flags |= XE_VM_FLAG_FAULT_MODE; - vm = xe_vm_create(xe, flags); + vm = xe_vm_create(xe, flags, xef); if (IS_ERR(vm)) return PTR_ERR(vm); - if (xe->info.has_asid) { - down_write(&xe->usm.lock); - err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm, - XA_LIMIT(1, XE_MAX_ASID - 1), - &xe->usm.next_asid, GFP_KERNEL); - up_write(&xe->usm.lock); - if (err < 0) - goto err_close_and_put; - - vm->usm.asid = asid; - } - - vm->xef = xe_file_get(xef); - - /* Record BO memory for VM pagetable created against client */ - for_each_tile(tile, xe, id) - if (vm->pt_root[id]) - xe_drm_client_add_bo(vm->xef->client, vm->pt_root[id]->bo); - #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_MEM) /* Warning: Security issue - never enable by default */ args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE); @@ -3421,6 +3418,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, free_bind_ops: if (args->num_binds > 1) kvfree(*bind_ops); + *bind_ops = NULL; return err; } @@ -3527,7 +3525,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct xe_exec_queue *q = NULL; u32 num_syncs, num_ufence = 0; struct xe_sync_entry *syncs = NULL; - struct drm_xe_vm_bind_op *bind_ops; + struct drm_xe_vm_bind_op *bind_ops = NULL; struct xe_vma_ops vops; struct dma_fence *fence; int err; diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 3475a118f666..2f213737c7e5 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -26,7 +26,7 @@ struct xe_sync_entry; struct xe_svm_range; struct drm_exec; -struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags); +struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef); struct xe_vm *xe_vm_lookup(struct xe_file *xef, u32 id); int xe_vma_cmp_vma_cb(const void *key, const struct rb_node *node); diff --git a/drivers/greybus/svc.c b/drivers/greybus/svc.c index 4256467fcd35..35ea7147dca6 100644 --- a/drivers/greybus/svc.c +++ b/drivers/greybus/svc.c @@ -10,6 +10,7 @@ #include <linux/kstrtox.h> #include <linux/workqueue.h> #include <linux/greybus.h> +#include <linux/string_choices.h> #define SVC_INTF_EJECT_TIMEOUT 9000 #define SVC_INTF_ACTIVATE_TIMEOUT 6000 @@ -73,7 +74,7 @@ static ssize_t watchdog_show(struct device *dev, struct device_attribute *attr, struct gb_svc *svc = to_gb_svc(dev); return sprintf(buf, "%s\n", - gb_svc_watchdog_enabled(svc) ? "enabled" : "disabled"); + str_enabled_disabled(gb_svc_watchdog_enabled(svc))); } static ssize_t watchdog_store(struct device *dev, diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c index e064e8a4a1f0..cfafe089102a 100644 --- a/drivers/i2c/busses/i2c-rtl9300.c +++ b/drivers/i2c/busses/i2c-rtl9300.c @@ -143,10 +143,10 @@ static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len) return -EIO; for (i = 0; i < len; i++) { - if (i % 4 == 0) - vals[i/4] = 0; - vals[i/4] <<= 8; - vals[i/4] |= buf[i]; + unsigned int shift = (i % 4) * 8; + unsigned int reg = i / 4; + + vals[reg] |= buf[i] << shift; } return regmap_bulk_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, @@ -175,7 +175,7 @@ static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write, return ret; ret = regmap_read_poll_timeout(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, - val, !(val & RTL9300_I2C_MST_CTRL1_I2C_TRIG), 100, 2000); + val, !(val & RTL9300_I2C_MST_CTRL1_I2C_TRIG), 100, 100000); if (ret) return ret; @@ -281,15 +281,19 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s ret = rtl9300_i2c_reg_addr_set(i2c, command, 1); if (ret) goto out_unlock; - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0]); + if (data->block[0] < 1 || data->block[0] > I2C_SMBUS_BLOCK_MAX) { + ret = -EINVAL; + goto out_unlock; + } + ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0] + 1); if (ret) goto out_unlock; if (read_write == I2C_SMBUS_WRITE) { - ret = rtl9300_i2c_write(i2c, &data->block[1], data->block[0]); + ret = rtl9300_i2c_write(i2c, &data->block[0], data->block[0] + 1); if (ret) goto out_unlock; } - len = data->block[0]; + len = data->block[0] + 1; break; default: diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 73747d20df85..91a7b7e7c0c8 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1679,7 +1679,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { }; static const struct x86_cpu_id intel_mwait_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL), + X86_MATCH_VENDOR_FAM_FEATURE(INTEL, X86_FAMILY_ANY, X86_FEATURE_MWAIT, NULL), {} }; diff --git a/drivers/iio/accel/sca3300.c b/drivers/iio/accel/sca3300.c index bda370c0f660..8380b237831c 100644 --- a/drivers/iio/accel/sca3300.c +++ b/drivers/iio/accel/sca3300.c @@ -477,7 +477,7 @@ static irqreturn_t sca3300_trigger_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct sca3300_data *data = iio_priv(indio_dev); int bit, ret, val, i = 0; - IIO_DECLARE_BUFFER_WITH_TS(s16, channels, SCA3300_SCAN_MAX); + IIO_DECLARE_BUFFER_WITH_TS(s16, channels, SCA3300_SCAN_MAX) = { }; iio_for_each_active_channel(indio_dev, bit) { ret = sca3300_read_reg(data, indio_dev->channels[bit].address, &val); diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 6de2abad0197..24f2572c487e 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -1300,7 +1300,7 @@ config RN5T618_ADC config ROHM_BD79124 tristate "Rohm BD79124 ADC driver" - depends on I2C + depends on I2C && GPIOLIB select REGMAP_I2C select IIO_ADC_HELPER help diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 9808df2e9242..4d8c6bafd1c3 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -849,7 +849,7 @@ enum { static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan_spec *chan) { struct device *dev = &st->sd.spi->dev; - struct ad7124_channel *ch = &st->channels[chan->channel]; + struct ad7124_channel *ch = &st->channels[chan->address]; int ret; if (ch->syscalib_mode == AD7124_SYSCALIB_ZERO_SCALE) { @@ -865,8 +865,8 @@ static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan if (ret < 0) return ret; - dev_dbg(dev, "offset for channel %d after zero-scale calibration: 0x%x\n", - chan->channel, ch->cfg.calibration_offset); + dev_dbg(dev, "offset for channel %lu after zero-scale calibration: 0x%x\n", + chan->address, ch->cfg.calibration_offset); } else { ch->cfg.calibration_gain = st->gain_default; @@ -880,8 +880,8 @@ static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan if (ret < 0) return ret; - dev_dbg(dev, "gain for channel %d after full-scale calibration: 0x%x\n", - chan->channel, ch->cfg.calibration_gain); + dev_dbg(dev, "gain for channel %lu after full-scale calibration: 0x%x\n", + chan->address, ch->cfg.calibration_gain); } return 0; @@ -924,7 +924,7 @@ static int ad7124_set_syscalib_mode(struct iio_dev *indio_dev, { struct ad7124_state *st = iio_priv(indio_dev); - st->channels[chan->channel].syscalib_mode = mode; + st->channels[chan->address].syscalib_mode = mode; return 0; } @@ -934,7 +934,7 @@ static int ad7124_get_syscalib_mode(struct iio_dev *indio_dev, { struct ad7124_state *st = iio_priv(indio_dev); - return st->channels[chan->channel].syscalib_mode; + return st->channels[chan->address].syscalib_mode; } static const struct iio_enum ad7124_syscalib_mode_enum = { diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index 4413207be28f..683146e83ab2 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -200,7 +200,7 @@ struct ad7173_channel_config { /* * Following fields are used to compare equality. If you * make adaptations in it, you most likely also have to adapt - * ad7173_find_live_config(), too. + * ad7173_is_setup_equal(), too. */ struct_group(config_props, bool bipolar; @@ -561,12 +561,19 @@ static void ad7173_reset_usage_cnts(struct ad7173_state *st) st->config_usage_counter = 0; } -static struct ad7173_channel_config * -ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *cfg) +/** + * ad7173_is_setup_equal - Compare two channel setups + * @cfg1: First channel configuration + * @cfg2: Second channel configuration + * + * Compares all configuration options that affect the registers connected to + * SETUP_SEL, namely CONFIGx, FILTERx, GAINx and OFFSETx. + * + * Returns: true if the setups are identical, false otherwise + */ +static bool ad7173_is_setup_equal(const struct ad7173_channel_config *cfg1, + const struct ad7173_channel_config *cfg2) { - struct ad7173_channel_config *cfg_aux; - int i; - /* * This is just to make sure that the comparison is adapted after * struct ad7173_channel_config was changed. @@ -579,14 +586,22 @@ ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *c u8 ref_sel; })); + return cfg1->bipolar == cfg2->bipolar && + cfg1->input_buf == cfg2->input_buf && + cfg1->odr == cfg2->odr && + cfg1->ref_sel == cfg2->ref_sel; +} + +static struct ad7173_channel_config * +ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *cfg) +{ + struct ad7173_channel_config *cfg_aux; + int i; + for (i = 0; i < st->num_channels; i++) { cfg_aux = &st->channels[i].cfg; - if (cfg_aux->live && - cfg->bipolar == cfg_aux->bipolar && - cfg->input_buf == cfg_aux->input_buf && - cfg->odr == cfg_aux->odr && - cfg->ref_sel == cfg_aux->ref_sel) + if (cfg_aux->live && ad7173_is_setup_equal(cfg, cfg_aux)) return cfg_aux; } return NULL; @@ -1228,7 +1243,7 @@ static int ad7173_update_scan_mode(struct iio_dev *indio_dev, const unsigned long *scan_mask) { struct ad7173_state *st = iio_priv(indio_dev); - int i, ret; + int i, j, k, ret; for (i = 0; i < indio_dev->num_channels; i++) { if (test_bit(i, scan_mask)) @@ -1239,6 +1254,54 @@ static int ad7173_update_scan_mode(struct iio_dev *indio_dev, return ret; } + /* + * On some chips, there are more channels that setups, so if there were + * more unique setups requested than the number of available slots, + * ad7173_set_channel() will have written over some of the slots. We + * can detect this by making sure each assigned cfg_slot matches the + * requested configuration. If it doesn't, we know that the slot was + * overwritten by a different channel. + */ + for_each_set_bit(i, scan_mask, indio_dev->num_channels) { + const struct ad7173_channel_config *cfg1, *cfg2; + + cfg1 = &st->channels[i].cfg; + + for_each_set_bit(j, scan_mask, indio_dev->num_channels) { + cfg2 = &st->channels[j].cfg; + + /* + * Only compare configs that are assigned to the same + * SETUP_SEL slot and don't compare channel to itself. + */ + if (i == j || cfg1->cfg_slot != cfg2->cfg_slot) + continue; + + /* + * If we find two different configs trying to use the + * same SETUP_SEL slot, then we know that the that we + * have too many unique configurations requested for + * the available slots and at least one was overwritten. + */ + if (!ad7173_is_setup_equal(cfg1, cfg2)) { + /* + * At this point, there isn't a way to tell + * which setups are actually programmed in the + * ADC anymore, so we could read them back to + * see, but it is simpler to just turn off all + * of the live flags so that everything gets + * reprogramed on the next attempt read a sample. + */ + for (k = 0; k < st->num_channels; k++) + st->channels[k].cfg.live = false; + + dev_err(&st->sd.spi->dev, + "Too many unique channel configurations requested for scan\n"); + return -EINVAL; + } + } + } + return 0; } diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index 6f7034b6c266..fa251dc1aae6 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -873,6 +873,7 @@ static const struct ad7380_chip_info adaq4381_4_chip_info = { .has_hardware_gain = true, .available_scan_masks = ad7380_4_channel_scan_masks, .timing_specs = &ad7380_4_timing, + .max_conversion_rate_hz = 4 * MEGA, }; static const struct spi_offload_config ad7380_offload_config = { diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c index 09fe88eb3fb0..2e442e46f679 100644 --- a/drivers/iio/adc/pac1934.c +++ b/drivers/iio/adc/pac1934.c @@ -88,6 +88,7 @@ #define PAC1934_VPOWER_3_ADDR 0x19 #define PAC1934_VPOWER_4_ADDR 0x1A #define PAC1934_REFRESH_V_REG_ADDR 0x1F +#define PAC1934_SLOW_REG_ADDR 0x20 #define PAC1934_CTRL_STAT_REGS_ADDR 0x1C #define PAC1934_PID_REG_ADDR 0xFD #define PAC1934_MID_REG_ADDR 0xFE @@ -1265,8 +1266,23 @@ static int pac1934_chip_configure(struct pac1934_chip_info *info) /* no SLOW triggered REFRESH, clear POR */ regs[PAC1934_SLOW_REG_OFF] = 0; - ret = i2c_smbus_write_block_data(client, PAC1934_CTRL_STAT_REGS_ADDR, - ARRAY_SIZE(regs), (u8 *)regs); + /* + * Write the three bytes sequentially, as the device does not support + * block write. + */ + ret = i2c_smbus_write_byte_data(client, PAC1934_CTRL_STAT_REGS_ADDR, + regs[PAC1934_CHANNEL_DIS_REG_OFF]); + if (ret) + return ret; + + ret = i2c_smbus_write_byte_data(client, + PAC1934_CTRL_STAT_REGS_ADDR + PAC1934_NEG_PWR_REG_OFF, + regs[PAC1934_NEG_PWR_REG_OFF]); + if (ret) + return ret; + + ret = i2c_smbus_write_byte_data(client, PAC1934_SLOW_REG_ADDR, + regs[PAC1934_SLOW_REG_OFF]); if (ret) return ret; diff --git a/drivers/iio/adc/rzg2l_adc.c b/drivers/iio/adc/rzg2l_adc.c index 9674d48074c9..cadb0446bc29 100644 --- a/drivers/iio/adc/rzg2l_adc.c +++ b/drivers/iio/adc/rzg2l_adc.c @@ -89,7 +89,6 @@ struct rzg2l_adc { struct completion completion; struct mutex lock; u16 last_val[RZG2L_ADC_MAX_CHANNELS]; - bool was_rpm_active; }; /** @@ -428,6 +427,8 @@ static int rzg2l_adc_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; + platform_set_drvdata(pdev, indio_dev); + adc = iio_priv(indio_dev); adc->hw_params = device_get_match_data(dev); @@ -460,8 +461,6 @@ static int rzg2l_adc_probe(struct platform_device *pdev) if (ret) return ret; - platform_set_drvdata(pdev, indio_dev); - ret = rzg2l_adc_hw_init(dev, adc); if (ret) return dev_err_probe(&pdev->dev, ret, @@ -541,14 +540,9 @@ static int rzg2l_adc_suspend(struct device *dev) }; int ret; - if (pm_runtime_suspended(dev)) { - adc->was_rpm_active = false; - } else { - ret = pm_runtime_force_suspend(dev); - if (ret) - return ret; - adc->was_rpm_active = true; - } + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; ret = reset_control_bulk_assert(ARRAY_SIZE(resets), resets); if (ret) @@ -557,9 +551,7 @@ static int rzg2l_adc_suspend(struct device *dev) return 0; rpm_restore: - if (adc->was_rpm_active) - pm_runtime_force_resume(dev); - + pm_runtime_force_resume(dev); return ret; } @@ -577,11 +569,9 @@ static int rzg2l_adc_resume(struct device *dev) if (ret) return ret; - if (adc->was_rpm_active) { - ret = pm_runtime_force_resume(dev); - if (ret) - goto resets_restore; - } + ret = pm_runtime_force_resume(dev); + if (ret) + goto resets_restore; ret = rzg2l_adc_hw_init(dev, adc); if (ret) @@ -590,10 +580,7 @@ static int rzg2l_adc_resume(struct device *dev) return 0; rpm_restore: - if (adc->was_rpm_active) { - pm_runtime_mark_last_busy(dev); - pm_runtime_put_autosuspend(dev); - } + pm_runtime_force_suspend(dev); resets_restore: reset_control_bulk_assert(ARRAY_SIZE(resets), resets); return ret; diff --git a/drivers/iio/adc/xilinx-ams.c b/drivers/iio/adc/xilinx-ams.c index 76dd0343f5f7..124470c92529 100644 --- a/drivers/iio/adc/xilinx-ams.c +++ b/drivers/iio/adc/xilinx-ams.c @@ -118,7 +118,7 @@ #define AMS_ALARM_THRESHOLD_OFF_10 0x10 #define AMS_ALARM_THRESHOLD_OFF_20 0x20 -#define AMS_ALARM_THR_DIRECT_MASK BIT(1) +#define AMS_ALARM_THR_DIRECT_MASK BIT(0) #define AMS_ALARM_THR_MIN 0x0000 #define AMS_ALARM_THR_MAX (BIT(16) - 1) @@ -389,6 +389,29 @@ static void ams_update_pl_alarm(struct ams *ams, unsigned long alarm_mask) ams_pl_update_reg(ams, AMS_REG_CONFIG3, AMS_REGCFG3_ALARM_MASK, cfg); } +static void ams_unmask(struct ams *ams) +{ + unsigned int status, unmask; + + status = readl(ams->base + AMS_ISR_0); + + /* Clear those bits which are not active anymore */ + unmask = (ams->current_masked_alarm ^ status) & ams->current_masked_alarm; + + /* Clear status of disabled alarm */ + unmask |= ams->intr_mask; + + ams->current_masked_alarm &= status; + + /* Also clear those which are masked out anyway */ + ams->current_masked_alarm &= ~ams->intr_mask; + + /* Clear the interrupts before we unmask them */ + writel(unmask, ams->base + AMS_ISR_0); + + ams_update_intrmask(ams, ~AMS_ALARM_MASK, ~AMS_ALARM_MASK); +} + static void ams_update_alarm(struct ams *ams, unsigned long alarm_mask) { unsigned long flags; @@ -401,6 +424,7 @@ static void ams_update_alarm(struct ams *ams, unsigned long alarm_mask) spin_lock_irqsave(&ams->intr_lock, flags); ams_update_intrmask(ams, AMS_ISR0_ALARM_MASK, ~alarm_mask); + ams_unmask(ams); spin_unlock_irqrestore(&ams->intr_lock, flags); } @@ -1035,28 +1059,9 @@ static void ams_handle_events(struct iio_dev *indio_dev, unsigned long events) static void ams_unmask_worker(struct work_struct *work) { struct ams *ams = container_of(work, struct ams, ams_unmask_work.work); - unsigned int status, unmask; spin_lock_irq(&ams->intr_lock); - - status = readl(ams->base + AMS_ISR_0); - - /* Clear those bits which are not active anymore */ - unmask = (ams->current_masked_alarm ^ status) & ams->current_masked_alarm; - - /* Clear status of disabled alarm */ - unmask |= ams->intr_mask; - - ams->current_masked_alarm &= status; - - /* Also clear those which are masked out anyway */ - ams->current_masked_alarm &= ~ams->intr_mask; - - /* Clear the interrupts before we unmask them */ - writel(unmask, ams->base + AMS_ISR_0); - - ams_update_intrmask(ams, ~AMS_ALARM_MASK, ~AMS_ALARM_MASK); - + ams_unmask(ams); spin_unlock_irq(&ams->intr_lock); /* If still pending some alarm re-trigger the timer */ diff --git a/drivers/iio/dac/ad5360.c b/drivers/iio/dac/ad5360.c index a57b0a093112..8271849b1c83 100644 --- a/drivers/iio/dac/ad5360.c +++ b/drivers/iio/dac/ad5360.c @@ -262,7 +262,7 @@ static int ad5360_update_ctrl(struct iio_dev *indio_dev, unsigned int set, unsigned int clr) { struct ad5360_state *st = iio_priv(indio_dev); - unsigned int ret; + int ret; mutex_lock(&st->lock); diff --git a/drivers/iio/dac/ad5421.c b/drivers/iio/dac/ad5421.c index 1462ee640b16..d9d7031c4432 100644 --- a/drivers/iio/dac/ad5421.c +++ b/drivers/iio/dac/ad5421.c @@ -186,7 +186,7 @@ static int ad5421_update_ctrl(struct iio_dev *indio_dev, unsigned int set, unsigned int clr) { struct ad5421_state *st = iio_priv(indio_dev); - unsigned int ret; + int ret; mutex_lock(&st->lock); diff --git a/drivers/iio/frequency/adf4350.c b/drivers/iio/frequency/adf4350.c index 47f1c7e9efa9..475a7a653bfb 100644 --- a/drivers/iio/frequency/adf4350.c +++ b/drivers/iio/frequency/adf4350.c @@ -149,6 +149,19 @@ static int adf4350_set_freq(struct adf4350_state *st, unsigned long long freq) if (freq > ADF4350_MAX_OUT_FREQ || freq < st->min_out_freq) return -EINVAL; + st->r4_rf_div_sel = 0; + + /* + * !\TODO: The below computation is making sure we get a power of 2 + * shift (st->r4_rf_div_sel) so that freq becomes higher or equal to + * ADF4350_MIN_VCO_FREQ. This might be simplified with fls()/fls_long() + * and friends. + */ + while (freq < ADF4350_MIN_VCO_FREQ) { + freq <<= 1; + st->r4_rf_div_sel++; + } + if (freq > ADF4350_MAX_FREQ_45_PRESC) { prescaler = ADF4350_REG1_PRESCALER; mdiv = 75; @@ -157,13 +170,6 @@ static int adf4350_set_freq(struct adf4350_state *st, unsigned long long freq) mdiv = 23; } - st->r4_rf_div_sel = 0; - - while (freq < ADF4350_MIN_VCO_FREQ) { - freq <<= 1; - st->r4_rf_div_sel++; - } - /* * Allow a predefined reference division factor * if not set, compute our own diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c index 8b15afca498c..271a4788604a 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c @@ -32,8 +32,12 @@ static int inv_icm42600_temp_read(struct inv_icm42600_state *st, s16 *temp) goto exit; *temp = (s16)be16_to_cpup(raw); + /* + * Temperature data is invalid if both accel and gyro are off. + * Return -EBUSY in this case. + */ if (*temp == INV_ICM42600_DATA_INVALID) - ret = -EINVAL; + ret = -EBUSY; exit: mutex_unlock(&st->lock); diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c index 68f60dc3c79d..32719f584c47 100644 --- a/drivers/iio/light/as73211.c +++ b/drivers/iio/light/as73211.c @@ -639,7 +639,7 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p) struct { __le16 chan[4]; aligned_s64 ts; - } scan; + } scan = { }; int data_result, ret; mutex_lock(&data->mutex); diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 74505c9ec1a0..6cdc8ed53520 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -3213,11 +3213,12 @@ int bmp280_common_probe(struct device *dev, /* Bring chip out of reset if there is an assigned GPIO line */ gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(gpiod)) + return dev_err_probe(dev, PTR_ERR(gpiod), "failed to get reset GPIO\n"); + /* Deassert the signal */ - if (gpiod) { - dev_info(dev, "release reset\n"); - gpiod_set_value(gpiod, 0); - } + dev_info(dev, "release reset\n"); + gpiod_set_value(gpiod, 0); data->regmap = regmap; diff --git a/drivers/iio/proximity/isl29501.c b/drivers/iio/proximity/isl29501.c index d1510fe24050..f69db6f2f380 100644 --- a/drivers/iio/proximity/isl29501.c +++ b/drivers/iio/proximity/isl29501.c @@ -938,12 +938,18 @@ static irqreturn_t isl29501_trigger_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct isl29501_private *isl29501 = iio_priv(indio_dev); const unsigned long *active_mask = indio_dev->active_scan_mask; - u32 buffer[4] __aligned(8) = {}; /* 1x16-bit + naturally aligned ts */ - - if (test_bit(ISL29501_DISTANCE_SCAN_INDEX, active_mask)) - isl29501_register_read(isl29501, REG_DISTANCE, buffer); + u32 value; + struct { + u16 data; + aligned_s64 ts; + } scan = { }; + + if (test_bit(ISL29501_DISTANCE_SCAN_INDEX, active_mask)) { + isl29501_register_read(isl29501, REG_DISTANCE, &value); + scan.data = value; + } - iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp); + iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp); iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index cae8e84821d7..205939680fd4 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/spi/spi.h> +#include <linux/types.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> #include <linux/iio/trigger.h> @@ -121,8 +122,15 @@ struct maxim_thermocouple_data { struct spi_device *spi; const struct maxim_thermocouple_chip *chip; char tc_type; - - u8 buffer[16] __aligned(IIO_DMA_MINALIGN); + /* Buffer for reading up to 2 hardware channels. */ + struct { + union { + __be16 raw16; + __be32 raw32; + __be16 raw[2]; + }; + aligned_s64 timestamp; + } buffer __aligned(IIO_DMA_MINALIGN); }; static int maxim_thermocouple_read(struct maxim_thermocouple_data *data, @@ -130,18 +138,16 @@ static int maxim_thermocouple_read(struct maxim_thermocouple_data *data, { unsigned int storage_bytes = data->chip->read_size; unsigned int shift = chan->scan_type.shift + (chan->address * 8); - __be16 buf16; - __be32 buf32; int ret; switch (storage_bytes) { case 2: - ret = spi_read(data->spi, (void *)&buf16, storage_bytes); - *val = be16_to_cpu(buf16); + ret = spi_read(data->spi, &data->buffer.raw16, storage_bytes); + *val = be16_to_cpu(data->buffer.raw16); break; case 4: - ret = spi_read(data->spi, (void *)&buf32, storage_bytes); - *val = be32_to_cpu(buf32); + ret = spi_read(data->spi, &data->buffer.raw32, storage_bytes); + *val = be32_to_cpu(data->buffer.raw32); break; default: ret = -EINVAL; @@ -166,9 +172,9 @@ static irqreturn_t maxim_thermocouple_trigger_handler(int irq, void *private) struct maxim_thermocouple_data *data = iio_priv(indio_dev); int ret; - ret = spi_read(data->spi, data->buffer, data->chip->read_size); + ret = spi_read(data->spi, data->buffer.raw, data->chip->read_size); if (!ret) { - iio_push_to_buffers_with_ts(indio_dev, data->buffer, + iio_push_to_buffers_with_ts(indio_dev, &data->buffer, sizeof(data->buffer), iio_get_time_ns(indio_dev)); } diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index b1c44ec1a3f3..572a91a62a7b 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -115,7 +115,7 @@ static int ib_init_umem_odp(struct ib_umem_odp *umem_odp, out_free_map: if (ib_uses_virt_dma(dev)) - kfree(map->pfn_list); + kvfree(map->pfn_list); else hmm_dma_map_free(dev->dma_device, map); return ret; @@ -287,7 +287,7 @@ static void ib_umem_odp_free(struct ib_umem_odp *umem_odp) mutex_unlock(&umem_odp->umem_mutex); mmu_interval_notifier_remove(&umem_odp->notifier); if (ib_uses_virt_dma(dev)) - kfree(umem_odp->map.pfn_list); + kvfree(umem_odp->map.pfn_list); else hmm_dma_map_free(dev->dma_device, &umem_odp->map); } diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 37c2bc3bdba5..260dc67b8b87 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -1921,7 +1921,6 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq, ib_srq); struct bnxt_re_dev *rdev = srq->rdev; - int rc; switch (srq_attr_mask) { case IB_SRQ_MAX_WR: @@ -1933,11 +1932,8 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, return -EINVAL; srq->qplib_srq.threshold = srq_attr->srq_limit; - rc = bnxt_qplib_modify_srq(&rdev->qplib_res, &srq->qplib_srq); - if (rc) { - ibdev_err(&rdev->ibdev, "Modify HW SRQ failed!"); - return rc; - } + bnxt_qplib_srq_arm_db(&srq->qplib_srq.dbinfo, srq->qplib_srq.threshold); + /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 293b0a96c8e3..df7cf8d68e27 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -2017,6 +2017,28 @@ static void bnxt_re_free_nqr_mem(struct bnxt_re_dev *rdev) rdev->nqr = NULL; } +/* When DEL_GID fails, driver is not freeing GID ctx memory. + * To avoid the memory leak, free the memory during unload + */ +static void bnxt_re_free_gid_ctx(struct bnxt_re_dev *rdev) +{ + struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl; + struct bnxt_re_gid_ctx *ctx, **ctx_tbl; + int i; + + if (!sgid_tbl->active) + return; + + ctx_tbl = sgid_tbl->ctx; + for (i = 0; i < sgid_tbl->max; i++) { + if (sgid_tbl->hw_id[i] == 0xFFFF) + continue; + + ctx = ctx_tbl[i]; + kfree(ctx); + } +} + static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type) { u8 type; @@ -2030,6 +2052,7 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type) if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags)) cancel_delayed_work_sync(&rdev->worker); + bnxt_re_free_gid_ctx(rdev); if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED, &rdev->flags)) bnxt_re_cleanup_res(rdev); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index dfe3177123e5..ee36b3d82cc0 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -705,9 +705,7 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, srq->dbinfo.db = srq->dpi->dbr; srq->dbinfo.max_slot = 1; srq->dbinfo.priv_db = res->dpi_tbl.priv_db; - if (srq->threshold) - bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA); - srq->arm_req = false; + bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA); return 0; fail: @@ -717,24 +715,6 @@ fail: return rc; } -int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res, - struct bnxt_qplib_srq *srq) -{ - struct bnxt_qplib_hwq *srq_hwq = &srq->hwq; - u32 count; - - count = __bnxt_qplib_get_avail(srq_hwq); - if (count > srq->threshold) { - srq->arm_req = false; - bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold); - } else { - /* Deferred arming */ - srq->arm_req = true; - } - - return 0; -} - int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_srq *srq) { @@ -776,7 +756,6 @@ int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq, struct bnxt_qplib_hwq *srq_hwq = &srq->hwq; struct rq_wqe *srqe; struct sq_sge *hw_sge; - u32 count = 0; int i, next; spin_lock(&srq_hwq->lock); @@ -808,15 +787,8 @@ int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq, bnxt_qplib_hwq_incr_prod(&srq->dbinfo, srq_hwq, srq->dbinfo.max_slot); - spin_lock(&srq_hwq->lock); - count = __bnxt_qplib_get_avail(srq_hwq); - spin_unlock(&srq_hwq->lock); /* Ring DB */ bnxt_qplib_ring_prod_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ); - if (srq->arm_req == true && count > srq->threshold) { - srq->arm_req = false; - bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold); - } return 0; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ab125f1d949e..4921a214c34c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -546,8 +546,6 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq, srqn_handler_t srq_handler); int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_srq *srq); -int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res, - struct bnxt_qplib_srq *srq); int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_srq *srq); void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 6cd05207ffed..cc5c82d96839 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -121,6 +121,7 @@ static int __alloc_pbl(struct bnxt_qplib_res *res, pbl->pg_arr = vmalloc_array(pages, sizeof(void *)); if (!pbl->pg_arr) return -ENOMEM; + memset(pbl->pg_arr, 0, pages * sizeof(void *)); pbl->pg_map_arr = vmalloc_array(pages, sizeof(dma_addr_t)); if (!pbl->pg_map_arr) { @@ -128,6 +129,7 @@ static int __alloc_pbl(struct bnxt_qplib_res *res, pbl->pg_arr = NULL; return -ENOMEM; } + memset(pbl->pg_map_arr, 0, pages * sizeof(dma_addr_t)); pbl->pg_count = 0; pbl->pg_size = sginfo->pgsize; diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c index 94c211df09d8..fdeec33c71da 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.c +++ b/drivers/infiniband/hw/erdma/erdma_verbs.c @@ -994,6 +994,8 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, old_entry = xa_store(&dev->qp_xa, 1, qp, GFP_KERNEL); if (xa_is_err(old_entry)) ret = xa_err(old_entry); + else + qp->ibqp.qp_num = 1; } else { ret = xa_alloc_cyclic(&dev->qp_xa, &qp->ibqp.qp_num, qp, XA_LIMIT(1, dev->attrs.max_qp - 1), @@ -1031,7 +1033,9 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (ret) goto err_out_cmd; } else { - init_kernel_qp(dev, qp, attrs); + ret = init_kernel_qp(dev, qp, attrs); + if (ret) + goto err_out_xa; } qp->attrs.max_send_sge = attrs->cap.max_send_sge; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 64bca08f3f1a..f82bdd46a917 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3043,7 +3043,7 @@ static void hns_roce_v2_exit(struct hns_roce_dev *hr_dev) if (!hr_dev->is_vf) hns_roce_free_link_table(hr_dev); - if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP09) + if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) free_dip_entry(hr_dev); } @@ -5476,7 +5476,7 @@ out: return ret; } -static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 qpn, +static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 sccn, void *buffer) { struct hns_roce_v2_scc_context *context; @@ -5488,7 +5488,7 @@ static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 qpn, return PTR_ERR(mailbox); ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma, HNS_ROCE_CMD_QUERY_SCCC, - qpn); + sccn); if (ret) goto out; diff --git a/drivers/infiniband/hw/hns/hns_roce_restrack.c b/drivers/infiniband/hw/hns/hns_roce_restrack.c index f637b73b946e..230187dda6a0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_restrack.c +++ b/drivers/infiniband/hw/hns/hns_roce_restrack.c @@ -100,6 +100,7 @@ int hns_roce_fill_res_qp_entry_raw(struct sk_buff *msg, struct ib_qp *ib_qp) struct hns_roce_v2_qp_context qpc; struct hns_roce_v2_scc_context sccc; } context = {}; + u32 sccn = hr_qp->qpn; int ret; if (!hr_dev->hw->query_qpc) @@ -116,7 +117,13 @@ int hns_roce_fill_res_qp_entry_raw(struct sk_buff *msg, struct ib_qp *ib_qp) !hr_dev->hw->query_sccc) goto out; - ret = hr_dev->hw->query_sccc(hr_dev, hr_qp->qpn, &context.sccc); + if (hr_qp->cong_type == CONG_TYPE_DIP) { + if (!hr_qp->dip) + goto out; + sccn = hr_qp->dip->dip_idx; + } + + ret = hr_dev->hw->query_sccc(hr_dev, sccn, &context.sccc); if (ret) ibdev_warn_ratelimited(&hr_dev->ib_dev, "failed to query SCCC, ret = %d.\n", diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 132a87e52d5c..ac0183a2ff7a 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -345,33 +345,15 @@ int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, static void rxe_skb_tx_dtor(struct sk_buff *skb) { - struct net_device *ndev = skb->dev; - struct rxe_dev *rxe; - unsigned int qp_index; - struct rxe_qp *qp; + struct rxe_qp *qp = skb->sk->sk_user_data; int skb_out; - rxe = rxe_get_dev_from_net(ndev); - if (!rxe && is_vlan_dev(ndev)) - rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); - if (WARN_ON(!rxe)) - return; - - qp_index = (int)(uintptr_t)skb->sk->sk_user_data; - if (!qp_index) - return; - - qp = rxe_pool_get_index(&rxe->qp_pool, qp_index); - if (!qp) - goto put_dev; - skb_out = atomic_dec_return(&qp->skb_out); - if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW) + if (unlikely(qp->need_req_skb && + skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) rxe_sched_task(&qp->send_task); rxe_put(qp); -put_dev: - ib_device_put(&rxe->ib_dev); sock_put(skb->sk); } @@ -383,6 +365,7 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; + rxe_get(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) @@ -405,6 +388,7 @@ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; + rxe_get(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) @@ -497,6 +481,9 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, goto out; } + /* Add time stamp to skb. */ + skb->tstamp = ktime_get(); + skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); /* FIXME: hold reference to this netdev until life of this skb. */ diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index f2af3e0aef35..95f1c1c2949d 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -244,7 +244,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk); if (err < 0) return err; - qp->sk->sk->sk_user_data = (void *)(uintptr_t)qp->elem.index; + qp->sk->sk->sk_user_data = qp; /* pick a source UDP port number for this QP based on * the source QPN. this spreads traffic for different QPs diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 7b5af6176de9..8de689b2c5ed 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3638,7 +3638,7 @@ static int __init parse_ivrs_acpihid(char *str) { u32 seg = 0, bus, dev, fn; char *hid, *uid, *p, *addr; - char acpiid[ACPIID_LEN] = {0}; + char acpiid[ACPIID_LEN + 1] = { }; /* size with NULL terminator */ int i; addr = strchr(str, '@'); @@ -3664,7 +3664,7 @@ static int __init parse_ivrs_acpihid(char *str) /* We have the '@', make it the terminator to get just the acpiid */ *addr++ = 0; - if (strlen(str) > ACPIID_LEN + 1) + if (strlen(str) > ACPIID_LEN) goto not_found; if (sscanf(str, "=%s", acpiid) != 1) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 5968043ac802..2a8b46b948f0 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2997,9 +2997,9 @@ void arm_smmu_attach_commit(struct arm_smmu_attach_state *state) /* ATS is being switched off, invalidate the entire ATC */ arm_smmu_atc_inv_master(master, IOMMU_NO_PASID); } - master->ats_enabled = state->ats_enabled; arm_smmu_remove_master_domain(master, state->old_domain, state->ssid); + master->ats_enabled = state->ats_enabled; } static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index be1aaaf8cd17..378104cd395e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -301,9 +301,11 @@ static void tegra241_vintf_user_handle_error(struct tegra241_vintf *vintf) struct iommu_vevent_tegra241_cmdqv vevent_data; int i; - for (i = 0; i < LVCMDQ_ERR_MAP_NUM_64; i++) - vevent_data.lvcmdq_err_map[i] = - readq_relaxed(REG_VINTF(vintf, LVCMDQ_ERR_MAP_64(i))); + for (i = 0; i < LVCMDQ_ERR_MAP_NUM_64; i++) { + u64 err = readq_relaxed(REG_VINTF(vintf, LVCMDQ_ERR_MAP_64(i))); + + vevent_data.lvcmdq_err_map[i] = cpu_to_le64(err); + } iommufd_viommu_report_event(viommu, IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV, &vevent_data, sizeof(vevent_data)); diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 2ca5809b238b..462b457ffd0c 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -339,7 +339,7 @@ iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd, } *base_pa = (page_to_pfn(pages[0]) << PAGE_SHIFT) + offset; - kfree(pages); + kvfree(pages); return access; out_unpin: @@ -349,7 +349,7 @@ out_detach: out_destroy: iommufd_access_destroy_internal(viommu->ictx, access); out_free: - kfree(pages); + kvfree(pages); return ERR_PTR(rc); } diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index 2d0d31ba2886..0eae2f4bdc5e 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -1283,7 +1283,7 @@ static phys_addr_t riscv_iommu_iova_to_phys(struct iommu_domain *iommu_domain, unsigned long *ptr; ptr = riscv_iommu_pte_fetch(domain, iova, &pte_size); - if (_io_pte_none(*ptr) || !_io_pte_present(*ptr)) + if (!ptr) return 0; return pfn_to_phys(__page_val_to_pfn(*ptr)) | (iova & (pte_size - 1)); diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 532db1de201b..b39d6f134ab2 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -998,8 +998,7 @@ static void viommu_get_resv_regions(struct device *dev, struct list_head *head) iommu_dma_get_resv_regions(dev, head); } -static const struct iommu_ops viommu_ops; -static struct virtio_driver virtio_iommu_drv; +static const struct bus_type *virtio_bus_type; static int viommu_match_node(struct device *dev, const void *data) { @@ -1008,8 +1007,9 @@ static int viommu_match_node(struct device *dev, const void *data) static struct viommu_dev *viommu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device(&virtio_iommu_drv.driver, NULL, - fwnode, viommu_match_node); + struct device *dev = bus_find_device(virtio_bus_type, NULL, fwnode, + viommu_match_node); + put_device(dev); return dev ? dev_to_virtio(dev)->priv : NULL; @@ -1160,6 +1160,9 @@ static int viommu_probe(struct virtio_device *vdev) if (!viommu) return -ENOMEM; + /* Borrow this for easy lookups later */ + virtio_bus_type = dev->bus; + spin_lock_init(&viommu->request_lock); ida_init(&viommu->domain_ids); viommu->dev = dev; @@ -1229,10 +1232,10 @@ static int viommu_probe(struct virtio_device *vdev) if (ret) goto err_free_vqs; - iommu_device_register(&viommu->iommu, &viommu_ops, parent_dev); - vdev->priv = viommu; + iommu_device_register(&viommu->iommu, &viommu_ops, parent_dev); + dev_info(dev, "input address: %u bits\n", order_base_2(viommu->geometry.aperture_end)); dev_info(dev, "page mask: %#llx\n", viommu->pgsize_bitmap); diff --git a/drivers/md/md.c b/drivers/md/md.c index ac85ec73a409..1baaf52c603c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -339,6 +339,7 @@ static int start_readonly; * so all the races disappear. */ static bool create_on_open = true; +static bool legacy_async_del_gendisk = true; /* * We have a system wide 'event count' that is incremented @@ -877,15 +878,18 @@ void mddev_unlock(struct mddev *mddev) export_rdev(rdev, mddev); } - /* Call del_gendisk after release reconfig_mutex to avoid - * deadlock (e.g. call del_gendisk under the lock and an - * access to sysfs files waits the lock) - * And MD_DELETED is only used for md raid which is set in - * do_md_stop. dm raid only uses md_stop to stop. So dm raid - * doesn't need to check MD_DELETED when getting reconfig lock - */ - if (test_bit(MD_DELETED, &mddev->flags)) - del_gendisk(mddev->gendisk); + if (!legacy_async_del_gendisk) { + /* + * Call del_gendisk after release reconfig_mutex to avoid + * deadlock (e.g. call del_gendisk under the lock and an + * access to sysfs files waits the lock) + * And MD_DELETED is only used for md raid which is set in + * do_md_stop. dm raid only uses md_stop to stop. So dm raid + * doesn't need to check MD_DELETED when getting reconfig lock + */ + if (test_bit(MD_DELETED, &mddev->flags)) + del_gendisk(mddev->gendisk); + } } EXPORT_SYMBOL_GPL(mddev_unlock); @@ -1419,7 +1423,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru else { if (sb->events_hi == sb->cp_events_hi && sb->events_lo == sb->cp_events_lo) { - mddev->resync_offset = sb->resync_offset; + mddev->resync_offset = sb->recovery_cp; } else mddev->resync_offset = 0; } @@ -1547,13 +1551,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev) mddev->minor_version = sb->minor_version; if (mddev->in_sync) { - sb->resync_offset = mddev->resync_offset; + sb->recovery_cp = mddev->resync_offset; sb->cp_events_hi = (mddev->events>>32); sb->cp_events_lo = (u32)mddev->events; if (mddev->resync_offset == MaxSector) sb->state = (1<< MD_SB_CLEAN); } else - sb->resync_offset = 0; + sb->recovery_cp = 0; sb->layout = mddev->layout; sb->chunk_size = mddev->chunk_sectors << 9; @@ -4835,9 +4839,42 @@ out_unlock: static struct md_sysfs_entry md_metadata = __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); +static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors) +{ + return rdev->raid_disk >= 0 && + !test_bit(Journal, &rdev->flags) && + !test_bit(Faulty, &rdev->flags) && + !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < sectors; +} + +static enum sync_action md_get_active_sync_action(struct mddev *mddev) +{ + struct md_rdev *rdev; + bool is_recover = false; + + if (mddev->resync_offset < MaxSector) + return ACTION_RESYNC; + + if (mddev->reshape_position != MaxSector) + return ACTION_RESHAPE; + + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) { + if (rdev_needs_recovery(rdev, MaxSector)) { + is_recover = true; + break; + } + } + rcu_read_unlock(); + + return is_recover ? ACTION_RECOVER : ACTION_IDLE; +} + enum sync_action md_sync_action(struct mddev *mddev) { unsigned long recovery = mddev->recovery; + enum sync_action active_action; /* * frozen has the highest priority, means running sync_thread will be @@ -4861,8 +4898,17 @@ enum sync_action md_sync_action(struct mddev *mddev) !test_bit(MD_RECOVERY_NEEDED, &recovery)) return ACTION_IDLE; - if (test_bit(MD_RECOVERY_RESHAPE, &recovery) || - mddev->reshape_position != MaxSector) + /* + * Check if any sync operation (resync/recover/reshape) is + * currently active. This ensures that only one sync operation + * can run at a time. Returns the type of active operation, or + * ACTION_IDLE if none are active. + */ + active_action = md_get_active_sync_action(mddev); + if (active_action != ACTION_IDLE) + return active_action; + + if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) return ACTION_RESHAPE; if (test_bit(MD_RECOVERY_RECOVER, &recovery)) @@ -5818,6 +5864,13 @@ static void md_kobj_release(struct kobject *ko) { struct mddev *mddev = container_of(ko, struct mddev, kobj); + if (legacy_async_del_gendisk) { + if (mddev->sysfs_state) + sysfs_put(mddev->sysfs_state); + if (mddev->sysfs_level) + sysfs_put(mddev->sysfs_level); + del_gendisk(mddev->gendisk); + } put_disk(mddev->gendisk); } @@ -6021,6 +6074,9 @@ static int md_alloc_and_put(dev_t dev, char *name) { struct mddev *mddev = md_alloc(dev, name); + if (legacy_async_del_gendisk) + pr_warn("md: async del_gendisk mode will be removed in future, please upgrade to mdadm-4.5+\n"); + if (IS_ERR(mddev)) return PTR_ERR(mddev); mddev_put(mddev); @@ -6431,10 +6487,22 @@ static void md_clean(struct mddev *mddev) mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; - /* if UNTIL_STOP is set, it's cleared here */ - mddev->hold_active = 0; - /* Don't clear MD_CLOSING, or mddev can be opened again. */ - mddev->flags &= BIT_ULL_MASK(MD_CLOSING); + + /* + * For legacy_async_del_gendisk mode, it can stop the array in the + * middle of assembling it, then it still can access the array. So + * it needs to clear MD_CLOSING. If not legacy_async_del_gendisk, + * it can't open the array again after stopping it. So it doesn't + * clear MD_CLOSING. + */ + if (legacy_async_del_gendisk && mddev->hold_active) { + clear_bit(MD_CLOSING, &mddev->flags); + } else { + /* if UNTIL_STOP is set, it's cleared here */ + mddev->hold_active = 0; + /* Don't clear MD_CLOSING, or mddev can be opened again. */ + mddev->flags &= BIT_ULL_MASK(MD_CLOSING); + } mddev->sb_flags = 0; mddev->ro = MD_RDWR; mddev->metadata_type[0] = 0; @@ -6658,7 +6726,8 @@ static int do_md_stop(struct mddev *mddev, int mode) export_array(mddev); md_clean(mddev); - set_bit(MD_DELETED, &mddev->flags); + if (!legacy_async_del_gendisk) + set_bit(MD_DELETED, &mddev->flags); } md_new_event(); sysfs_notify_dirent_safe(mddev->sysfs_state); @@ -8968,11 +9037,7 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) start = MaxSector; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) - if (rdev->raid_disk >= 0 && - !test_bit(Journal, &rdev->flags) && - !test_bit(Faulty, &rdev->flags) && - !test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < start) + if (rdev_needs_recovery(rdev, start)) start = rdev->recovery_offset; rcu_read_unlock(); @@ -9331,12 +9396,8 @@ void md_do_sync(struct md_thread *thread) test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) { rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) - if (rdev->raid_disk >= 0 && - mddev->delta_disks >= 0 && - !test_bit(Journal, &rdev->flags) && - !test_bit(Faulty, &rdev->flags) && - !test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < mddev->curr_resync) + if (mddev->delta_disks >= 0 && + rdev_needs_recovery(rdev, mddev->curr_resync)) rdev->recovery_offset = mddev->curr_resync; rcu_read_unlock(); } @@ -10392,6 +10453,7 @@ module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR); module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR); module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR); module_param(create_on_open, bool, S_IRUSR|S_IWUSR); +module_param(legacy_async_del_gendisk, bool, 0600); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD RAID framework"); diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 7f3f47db4c98..e4275f8ee5db 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -555,7 +555,6 @@ EXPORT_SYMBOL(memstick_add_host); */ void memstick_remove_host(struct memstick_host *host) { - host->removing = 1; flush_workqueue(workqueue); mutex_lock(&host->lock); if (host->card) diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c index 3878136227e4..5b5e9354fb2e 100644 --- a/drivers/memstick/host/rtsx_usb_ms.c +++ b/drivers/memstick/host/rtsx_usb_ms.c @@ -812,6 +812,7 @@ static void rtsx_usb_ms_drv_remove(struct platform_device *pdev) int err; host->eject = true; + msh->removing = true; cancel_work_sync(&host->handle_req); cancel_delayed_work_sync(&host->poll_card); diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index e2e66f5f4fb8..b32a2597d246 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o obj-$(CONFIG_SENSORS_APDS990X) += apds990x.o obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o obj-$(CONFIG_KGDB_TESTS) += kgdbts.o -obj-$(CONFIG_TEST_MISC_MINOR) += misc_minor_kunit.o obj-$(CONFIG_SGI_XP) += sgi-xp/ obj-$(CONFIG_SGI_GRU) += sgi-gru/ obj-$(CONFIG_SMPRO_ERRMON) += smpro-errmon.o diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c index 756ef6912b5a..04683b981e54 100644 --- a/drivers/misc/ad525x_dpot.c +++ b/drivers/misc/ad525x_dpot.c @@ -73,6 +73,7 @@ #include <linux/kernel.h> #include <linux/delay.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include "ad525x_dpot.h" @@ -418,10 +419,8 @@ static ssize_t sysfs_show_reg(struct device *dev, s32 value; if (reg & DPOT_ADDR_OTP_EN) - return sprintf(buf, "%s\n", - test_bit(DPOT_RDAC_MASK & reg, data->otp_en_mask) ? - "enabled" : "disabled"); - + return sprintf(buf, "%s\n", str_enabled_disabled( + test_bit(DPOT_RDAC_MASK & reg, data->otp_en_mask))); mutex_lock(&data->update_lock); value = dpot_read(data, reg); diff --git a/drivers/misc/amd-sbi/Kconfig b/drivers/misc/amd-sbi/Kconfig index 4840831c84ca..4aae0733d0fc 100644 --- a/drivers/misc/amd-sbi/Kconfig +++ b/drivers/misc/amd-sbi/Kconfig @@ -2,6 +2,7 @@ config AMD_SBRMI_I2C tristate "AMD side band RMI support" depends on I2C + select REGMAP_I2C help Side band RMI over I2C support for AMD out of band management. diff --git a/drivers/misc/apds990x.c b/drivers/misc/apds990x.c index e7d73c972f65..58946c4ff1a5 100644 --- a/drivers/misc/apds990x.c +++ b/drivers/misc/apds990x.c @@ -984,7 +984,6 @@ static ssize_t apds990x_power_state_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", !pm_runtime_suspended(dev)); - return 0; } static ssize_t apds990x_power_state_store(struct device *dev, diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index cd512284bfb3..46444bb47f65 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -79,6 +79,10 @@ static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg); if (rtsx_reg_check_reverse_socket(reg)) pcr->flags |= PCR_REVERSE_SOCKET; + if (rtsx_reg_check_cd_reverse(reg)) + pcr->option.sd_cd_reverse_en = 1; + if (rtsx_reg_check_wp_reverse(reg)) + pcr->option.sd_wp_reverse_en = 1; } static void rts5227_init_from_cfg(struct rtsx_pcr *pcr) @@ -127,8 +131,10 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) /* Configure force_clock_req */ if (pcr->flags & PCR_REVERSE_SOCKET) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x30, 0x30); - else - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x30, 0x00); + else { + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x20, option->sd_cd_reverse_en << 5); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x10, option->sd_wp_reverse_en << 4); + } if (CHK_PCI_PID(pcr, 0x522A)) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS522A_AUTOLOAD_CFG1, @@ -350,6 +356,8 @@ void rts5227_init_params(struct rtsx_pcr *pcr) pcr->ms_pull_ctl_disable_tbl = rts5227_ms_pull_ctl_disable_tbl; pcr->reg_pm_ctrl3 = PM_CTRL3; + pcr->option.sd_cd_reverse_en = 0; + pcr->option.sd_wp_reverse_en = 0; } static int rts522a_optimize_phy(struct rtsx_pcr *pcr) @@ -508,5 +516,4 @@ void rts522a_init_params(struct rtsx_pcr *pcr) pcr->hw_param.interrupt_en |= SD_OC_INT_EN; pcr->hw_param.ocp_glitch = SD_OCP_GLITCH_10M; pcr->option.sd_800mA_ocp_thd = RTS522A_OCP_THD_800; - } diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index 0c7f10bcf6f1..db7e735ac24f 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -84,6 +84,10 @@ static void rtsx5228_fetch_vendor_settings(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg); if (rtsx_reg_check_reverse_socket(reg)) pcr->flags |= PCR_REVERSE_SOCKET; + if (rtsx_reg_check_cd_reverse(reg)) + pcr->option.sd_cd_reverse_en = 1; + if (rtsx_reg_check_wp_reverse(reg)) + pcr->option.sd_wp_reverse_en = 1; } static int rts5228_optimize_phy(struct rtsx_pcr *pcr) @@ -432,8 +436,10 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) if (pcr->flags & PCR_REVERSE_SOCKET) rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30); - else - rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + else { + rtsx_pci_write_register(pcr, PETXCFG, 0x20, option->sd_cd_reverse_en << 5); + rtsx_pci_write_register(pcr, PETXCFG, 0x10, option->sd_wp_reverse_en << 4); + } /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced @@ -720,4 +726,6 @@ void rts5228_init_params(struct rtsx_pcr *pcr) hw_param->interrupt_en |= SD_OC_INT_EN; hw_param->ocp_glitch = SD_OCP_GLITCH_800U; option->sd_800mA_ocp_thd = RTS5228_LDO1_OCP_THD_930; + option->sd_cd_reverse_en = 0; + option->sd_wp_reverse_en = 0; } diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 6c81040e18be..38aefd8db452 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -60,6 +60,7 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr) pci_read_config_dword(pdev, PCR_SETTING_REG1, ®); pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg); + pci_write_config_dword(pdev, 0x718, 0x0007C000); if (!rtsx_vendor_setting_valid(reg)) { pcr_dbg(pcr, "skip fetch vendor setting\n"); @@ -82,6 +83,10 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr) pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg); if (rtsx_reg_check_reverse_socket(reg)) pcr->flags |= PCR_REVERSE_SOCKET; + if (rtsx_reg_check_cd_reverse(reg)) + pcr->option.sd_cd_reverse_en = 1; + if (rtsx_reg_check_wp_reverse(reg)) + pcr->option.sd_wp_reverse_en = 1; } static void rts5249_init_from_cfg(struct rtsx_pcr *pcr) @@ -254,9 +259,11 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) /* Configure driving */ rts5249_fill_driving(pcr, OUTPUT_3V3); if (pcr->flags & PCR_REVERSE_SOCKET) - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0xB0, 0xB0); - else - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0xB0, 0x80); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x30, 0x30); + else { + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x20, option->sd_cd_reverse_en << 5); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x10, option->sd_wp_reverse_en << 4); + } rtsx_pci_send_cmd(pcr, CMD_TIMEOUT_DEF); @@ -572,6 +579,9 @@ void rts5249_init_params(struct rtsx_pcr *pcr) option->ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5249_DEF; option->ltr_l1off_snooze_sspwrgate = LTR_L1OFF_SNOOZE_SSPWRGATE_5249_DEF; + + option->sd_cd_reverse_en = 0; + option->sd_wp_reverse_en = 0; } static int rts524a_write_phy(struct rtsx_pcr *pcr, u8 addr, u16 val) diff --git a/drivers/misc/cardreader/rts5264.c b/drivers/misc/cardreader/rts5264.c index d050c9fff7ac..99a2d5ea6421 100644 --- a/drivers/misc/cardreader/rts5264.c +++ b/drivers/misc/cardreader/rts5264.c @@ -527,8 +527,16 @@ static void rts5264_init_from_hw(struct rtsx_pcr *pcr) pcr->rtd3_en = rts5264_reg_to_rtd3(lval2); - if (rts5264_reg_check_reverse_socket(lval2)) - pcr->flags |= PCR_REVERSE_SOCKET; + if (rts5264_reg_check_reverse_socket(lval2)) { + if (is_version_higher_than(pcr, PID_5264, RTS5264_IC_VER_B)) + pcr->option.sd_cd_reverse_en = 1; + else + pcr->flags |= PCR_REVERSE_SOCKET; + } + + if (rts5264_reg_check_wp_reverse(lval2) && + is_version_higher_than(pcr, PID_5264, RTS5264_IC_VER_B)) + pcr->option.sd_wp_reverse_en = 1; pci_read_config_dword(pdev, setting_reg1, &lval1); pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg1, lval1); @@ -622,8 +630,10 @@ static int rts5264_extra_init_hw(struct rtsx_pcr *pcr) if (pcr->flags & PCR_REVERSE_SOCKET) rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30); - else - rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + else { + rtsx_pci_write_register(pcr, PETXCFG, 0x20, option->sd_cd_reverse_en << 5); + rtsx_pci_write_register(pcr, PETXCFG, 0x10, option->sd_wp_reverse_en << 4); + } /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced @@ -957,4 +967,6 @@ void rts5264_init_params(struct rtsx_pcr *pcr) hw_param->interrupt_en |= (SD_OC_INT_EN | SD_OVP_INT_EN); hw_param->ocp_glitch = SD_OCP_GLITCH_800U | SDVIO_OCP_GLITCH_800U; option->sd_800mA_ocp_thd = RTS5264_LDO1_OCP_THD_1150; + option->sd_cd_reverse_en = 0; + option->sd_wp_reverse_en = 0; } diff --git a/drivers/misc/cardreader/rts5264.h b/drivers/misc/cardreader/rts5264.h index f3e81daa708d..611ee253367c 100644 --- a/drivers/misc/cardreader/rts5264.h +++ b/drivers/misc/cardreader/rts5264.h @@ -14,6 +14,7 @@ #define rts5264_reg_to_aspm(reg) \ (((~(reg) >> 28) & 0x02) | (((reg) >> 28) & 0x01)) #define rts5264_reg_check_reverse_socket(reg) ((reg) & 0x04) +#define rts5264_reg_check_wp_reverse(reg) ((reg) & 0x8000) #define rts5264_reg_to_sd30_drive_sel_1v8(reg) (((reg) >> 22) & 0x03) #define rts5264_reg_to_sd30_drive_sel_3v3(reg) (((reg) >> 16) & 0x03) #define rts5264_reg_to_rtd3(reg) ((reg) & 0x08) diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h index 8e5951b61143..40562ff2be13 100644 --- a/drivers/misc/cardreader/rtsx_pcr.h +++ b/drivers/misc/cardreader/rtsx_pcr.h @@ -100,6 +100,8 @@ static inline u8 map_sd_drive(int idx) #define rtsx_reg_to_sd30_drive_sel_3v3(reg) (((reg) >> 5) & 0x03) #define rtsx_reg_to_card_drive_sel(reg) ((((reg) >> 25) & 0x01) << 6) #define rtsx_reg_check_reverse_socket(reg) ((reg) & 0x4000) +#define rtsx_reg_check_cd_reverse(reg) ((reg) & 0x800000) +#define rtsx_reg_check_wp_reverse(reg) ((reg) & 0x400000) #define rts5209_reg_to_aspm(reg) (((reg) >> 5) & 0x03) #define rts5209_reg_check_ms_pmos(reg) (!((reg) & 0x08)) #define rts5209_reg_to_sd30_drive_sel_1v8(reg) (((reg) >> 3) & 0x07) diff --git a/drivers/misc/dw-xdata-pcie.c b/drivers/misc/dw-xdata-pcie.c index efd0ca8cc925..a604c0e9c038 100644 --- a/drivers/misc/dw-xdata-pcie.c +++ b/drivers/misc/dw-xdata-pcie.c @@ -16,6 +16,7 @@ #include <linux/mutex.h> #include <linux/delay.h> #include <linux/pci.h> +#include <linux/string_choices.h> #define DW_XDATA_DRIVER_NAME "dw-xdata-pcie" @@ -132,7 +133,7 @@ static void dw_xdata_start(struct dw_xdata *dw, bool write) if (!(status & STATUS_DONE)) dev_dbg(dev, "xData: started %s direction\n", - write ? "write" : "read"); + str_write_read(write)); } static void dw_xdata_perf_meas(struct dw_xdata *dw, u64 *data, bool write) @@ -195,7 +196,7 @@ static void dw_xdata_perf(struct dw_xdata *dw, u64 *rate, bool write) mutex_unlock(&dw->mutex); dev_dbg(dev, "xData: time=%llu us, %s=%llu MB/s\n", - diff, write ? "write" : "read", *rate); + diff, str_write_read(write), *rate); } static struct dw_xdata *misc_dev_to_dw(struct miscdevice *misc_dev) diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index 0bef5b93bd6d..4d0ce47aa282 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -120,4 +120,22 @@ config EEPROM_EE1004 This driver can also be built as a module. If so, the module will be called ee1004. +config EEPROM_M24LR + tristate "STMicroelectronics M24LR RFID/NFC EEPROM support" + depends on I2C && SYSFS + select REGMAP_I2C + select NVMEM + select NVMEM_SYSFS + help + This enables support for STMicroelectronics M24LR RFID/NFC EEPROM + chips. These dual-interface devices expose two I2C addresses: + one for EEPROM memory access and another for control and system + configuration (e.g. UID, password handling). + + This driver provides a sysfs interface for control functions and + integrates with the nvmem subsystem for EEPROM access. + + To compile this driver as a module, choose M here: the + module will be called m24lr. + endmenu diff --git a/drivers/misc/eeprom/Makefile b/drivers/misc/eeprom/Makefile index 65794e526d5d..8f311fd6a4ce 100644 --- a/drivers/misc/eeprom/Makefile +++ b/drivers/misc/eeprom/Makefile @@ -7,3 +7,4 @@ obj-$(CONFIG_EEPROM_93XX46) += eeprom_93xx46.o obj-$(CONFIG_EEPROM_DIGSY_MTC_CFG) += digsy_mtc_eeprom.o obj-$(CONFIG_EEPROM_IDT_89HPESX) += idt_89hpesx.o obj-$(CONFIG_EEPROM_EE1004) += ee1004.o +obj-$(CONFIG_EEPROM_M24LR) += m24lr.o diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 2d0492867054..e2868f7bdb03 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -379,37 +379,49 @@ static int at25_fram_to_chip(struct device *dev, struct spi_eeprom *chip) struct at25_data *at25 = container_of(chip, struct at25_data, chip); u8 sernum[FM25_SN_LEN]; u8 id[FM25_ID_LEN]; + u32 val; int i; strscpy(chip->name, "fm25", sizeof(chip->name)); - /* Get ID of chip */ - fm25_aux_read(at25, id, FM25_RDID, FM25_ID_LEN); - /* There are inside-out FRAM variations, detect them and reverse the ID bytes */ - if (id[6] == 0x7f && id[2] == 0xc2) - for (i = 0; i < ARRAY_SIZE(id) / 2; i++) { - u8 tmp = id[i]; - int j = ARRAY_SIZE(id) - i - 1; + if (!device_property_read_u32(dev, "size", &val)) { + chip->byte_len = val; + } else { + /* Get ID of chip */ + fm25_aux_read(at25, id, FM25_RDID, FM25_ID_LEN); + /* There are inside-out FRAM variations, detect them and reverse the ID bytes */ + if (id[6] == 0x7f && id[2] == 0xc2) + for (i = 0; i < ARRAY_SIZE(id) / 2; i++) { + u8 tmp = id[i]; + int j = ARRAY_SIZE(id) - i - 1; + + id[i] = id[j]; + id[j] = tmp; + } + if (id[6] != 0xc2) { + dev_err(dev, "Error: no Cypress FRAM with device ID (manufacturer ID bank 7: %02x)\n", id[6]); + return -ENODEV; + } - id[i] = id[j]; - id[j] = tmp; + switch (id[7]) { + case 0x21 ... 0x26: + chip->byte_len = BIT(id[7] - 0x21 + 4) * 1024; + break; + case 0x2a ... 0x30: + /* CY15B116QN ... CY15B116QN */ + chip->byte_len = BIT(((id[7] >> 1) & 0xf) + 13); + break; + default: + dev_err(dev, "Error: unsupported size (id %02x)\n", id[7]); + return -ENODEV; } - if (id[6] != 0xc2) { - dev_err(dev, "Error: no Cypress FRAM (id %02x)\n", id[6]); - return -ENODEV; - } - switch (id[7]) { - case 0x21 ... 0x26: - chip->byte_len = BIT(id[7] - 0x21 + 4) * 1024; - break; - case 0x2a ... 0x30: - /* CY15B116QN ... CY15B116QN */ - chip->byte_len = BIT(((id[7] >> 1) & 0xf) + 13); - break; - default: - dev_err(dev, "Error: unsupported size (id %02x)\n", id[7]); - return -ENODEV; + if (id[8]) { + fm25_aux_read(at25, sernum, FM25_RDSN, FM25_SN_LEN); + /* Swap byte order */ + for (i = 0; i < FM25_SN_LEN; i++) + at25->sernum[i] = sernum[FM25_SN_LEN - 1 - i]; + } } if (chip->byte_len > 64 * 1024) @@ -417,13 +429,6 @@ static int at25_fram_to_chip(struct device *dev, struct spi_eeprom *chip) else chip->flags |= EE_ADDR2; - if (id[8]) { - fm25_aux_read(at25, sernum, FM25_RDSN, FM25_SN_LEN); - /* Swap byte order */ - for (i = 0; i < FM25_SN_LEN; i++) - at25->sernum[i] = sernum[FM25_SN_LEN - 1 - i]; - } - chip->page_size = PAGE_SIZE; return 0; } diff --git a/drivers/misc/eeprom/m24lr.c b/drivers/misc/eeprom/m24lr.c new file mode 100644 index 000000000000..7a9fd45a8e46 --- /dev/null +++ b/drivers/misc/eeprom/m24lr.c @@ -0,0 +1,606 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * m24lr.c - Sysfs control interface for ST M24LR series RFID/NFC chips + * + * Copyright (c) 2025 Abd-Alrhman Masalkhi <abd.masalkhi@gmail.com> + * + * This driver implements both the sysfs-based control interface and EEPROM + * access for STMicroelectronics M24LR series chips (e.g., M24LR04E-R). + * It provides access to control registers for features such as password + * authentication, memory protection, and device configuration. In addition, + * it manages read and write operations to the EEPROM region of the chip. + */ + +#include <linux/device.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/nvmem-provider.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/regmap.h> + +#define M24LR_WRITE_TIMEOUT 25u +#define M24LR_READ_TIMEOUT (M24LR_WRITE_TIMEOUT) + +/** + * struct m24lr_chip - describes chip-specific sysfs layout + * @sss_len: the length of the sss region + * @page_size: chip-specific limit on the maximum number of bytes allowed + * in a single write operation. + * @eeprom_size: size of the EEPROM in byte + * + * Supports multiple M24LR chip variants (e.g., M24LRxx) by allowing each + * to define its own set of sysfs attributes, depending on its available + * registers and features. + */ +struct m24lr_chip { + unsigned int sss_len; + unsigned int page_size; + unsigned int eeprom_size; +}; + +/** + * struct m24lr - core driver data for M24LR chip control + * @uid: 64 bits unique identifier stored in the device + * @sss_len: the length of the sss region + * @page_size: chip-specific limit on the maximum number of bytes allowed + * in a single write operation. + * @eeprom_size: size of the EEPROM in byte + * @ctl_regmap: regmap interface for accessing the system parameter sector + * @eeprom_regmap: regmap interface for accessing the EEPROM + * @lock: mutex to synchronize operations to the device + * + * Central data structure holding the state and resources used by the + * M24LR device driver. + */ +struct m24lr { + u64 uid; + unsigned int sss_len; + unsigned int page_size; + unsigned int eeprom_size; + struct regmap *ctl_regmap; + struct regmap *eeprom_regmap; + struct mutex lock; /* synchronize operations to the device */ +}; + +static const struct regmap_range m24lr_ctl_vo_ranges[] = { + regmap_reg_range(0, 63), +}; + +static const struct regmap_access_table m24lr_ctl_vo_table = { + .yes_ranges = m24lr_ctl_vo_ranges, + .n_yes_ranges = ARRAY_SIZE(m24lr_ctl_vo_ranges), +}; + +static const struct regmap_config m24lr_ctl_regmap_conf = { + .name = "m24lr_ctl", + .reg_stride = 1, + .reg_bits = 16, + .val_bits = 8, + .disable_locking = false, + .cache_type = REGCACHE_RBTREE,/* Flat can't be used, there's huge gap */ + .volatile_table = &m24lr_ctl_vo_table, +}; + +/* Chip descriptor for M24LR04E-R variant */ +static const struct m24lr_chip m24lr04e_r_chip = { + .page_size = 4, + .eeprom_size = 512, + .sss_len = 4, +}; + +/* Chip descriptor for M24LR16E-R variant */ +static const struct m24lr_chip m24lr16e_r_chip = { + .page_size = 4, + .eeprom_size = 2048, + .sss_len = 16, +}; + +/* Chip descriptor for M24LR64E-R variant */ +static const struct m24lr_chip m24lr64e_r_chip = { + .page_size = 4, + .eeprom_size = 8192, + .sss_len = 64, +}; + +static const struct i2c_device_id m24lr_ids[] = { + { "m24lr04e-r", (kernel_ulong_t)&m24lr04e_r_chip}, + { "m24lr16e-r", (kernel_ulong_t)&m24lr16e_r_chip}, + { "m24lr64e-r", (kernel_ulong_t)&m24lr64e_r_chip}, + { } +}; +MODULE_DEVICE_TABLE(i2c, m24lr_ids); + +static const struct of_device_id m24lr_of_match[] = { + { .compatible = "st,m24lr04e-r", .data = &m24lr04e_r_chip}, + { .compatible = "st,m24lr16e-r", .data = &m24lr16e_r_chip}, + { .compatible = "st,m24lr64e-r", .data = &m24lr64e_r_chip}, + { } +}; +MODULE_DEVICE_TABLE(of, m24lr_of_match); + +/** + * m24lr_regmap_read - read data using regmap with retry on failure + * @regmap: regmap instance for the device + * @buf: buffer to store the read data + * @size: number of bytes to read + * @offset: starting register address + * + * Attempts to read a block of data from the device with retries and timeout. + * Some M24LR chips may transiently NACK reads (e.g., during internal write + * cycles), so this function retries with a short sleep until the timeout + * expires. + * + * Returns: + * Number of bytes read on success, + * -ETIMEDOUT if the read fails within the timeout window. + */ +static ssize_t m24lr_regmap_read(struct regmap *regmap, u8 *buf, + size_t size, unsigned int offset) +{ + int err; + unsigned long timeout, read_time; + ssize_t ret = -ETIMEDOUT; + + timeout = jiffies + msecs_to_jiffies(M24LR_READ_TIMEOUT); + do { + read_time = jiffies; + + err = regmap_bulk_read(regmap, offset, buf, size); + if (!err) { + ret = size; + break; + } + + usleep_range(1000, 2000); + } while (time_before(read_time, timeout)); + + return ret; +} + +/** + * m24lr_regmap_write - write data using regmap with retry on failure + * @regmap: regmap instance for the device + * @buf: buffer containing the data to write + * @size: number of bytes to write + * @offset: starting register address + * + * Attempts to write a block of data to the device with retries and a timeout. + * Some M24LR devices may NACK I2C writes while an internal write operation + * is in progress. This function retries the write operation with a short delay + * until it succeeds or the timeout is reached. + * + * Returns: + * Number of bytes written on success, + * -ETIMEDOUT if the write fails within the timeout window. + */ +static ssize_t m24lr_regmap_write(struct regmap *regmap, const u8 *buf, + size_t size, unsigned int offset) +{ + int err; + unsigned long timeout, write_time; + ssize_t ret = -ETIMEDOUT; + + timeout = jiffies + msecs_to_jiffies(M24LR_WRITE_TIMEOUT); + + do { + write_time = jiffies; + + err = regmap_bulk_write(regmap, offset, buf, size); + if (!err) { + ret = size; + break; + } + + usleep_range(1000, 2000); + } while (time_before(write_time, timeout)); + + return ret; +} + +static ssize_t m24lr_read(struct m24lr *m24lr, u8 *buf, size_t size, + unsigned int offset, bool is_eeprom) +{ + struct regmap *regmap; + ssize_t ret; + + if (is_eeprom) + regmap = m24lr->eeprom_regmap; + else + regmap = m24lr->ctl_regmap; + + mutex_lock(&m24lr->lock); + ret = m24lr_regmap_read(regmap, buf, size, offset); + mutex_unlock(&m24lr->lock); + + return ret; +} + +/** + * m24lr_write - write buffer to M24LR device with page alignment handling + * @m24lr: pointer to driver context + * @buf: data buffer to write + * @size: number of bytes to write + * @offset: target register address in the device + * @is_eeprom: true if the write should target the EEPROM, + * false if it should target the system parameters sector. + * + * Writes data to the M24LR device using regmap, split into chunks no larger + * than page_size to respect device-specific write limitations (e.g., page + * size or I2C hold-time concerns). Each chunk is aligned to the page boundary + * defined by page_size. + * + * Returns: + * Total number of bytes written on success, + * A negative error code if any write fails. + */ +static ssize_t m24lr_write(struct m24lr *m24lr, const u8 *buf, size_t size, + unsigned int offset, bool is_eeprom) +{ + unsigned int n, next_sector; + struct regmap *regmap; + ssize_t ret = 0; + ssize_t err; + + if (is_eeprom) + regmap = m24lr->eeprom_regmap; + else + regmap = m24lr->ctl_regmap; + + n = min_t(unsigned int, size, m24lr->page_size); + next_sector = roundup(offset + 1, m24lr->page_size); + if (offset + n > next_sector) + n = next_sector - offset; + + mutex_lock(&m24lr->lock); + while (n) { + err = m24lr_regmap_write(regmap, buf + offset, n, offset); + if (IS_ERR_VALUE(err)) { + if (!ret) + ret = err; + + break; + } + + offset += n; + size -= n; + ret += n; + n = min_t(unsigned int, size, m24lr->page_size); + } + mutex_unlock(&m24lr->lock); + + return ret; +} + +/** + * m24lr_write_pass - Write password to M24LR043-R using secure format + * @m24lr: Pointer to device control structure + * @buf: Input buffer containing hex-encoded password + * @count: Number of bytes in @buf + * @code: Operation code to embed between password copies + * + * This function parses a 4-byte password, encodes it in big-endian format, + * and constructs a 9-byte sequence of the form: + * + * [BE(password), code, BE(password)] + * + * The result is written to register 0x0900 (2304), which is the password + * register in M24LR04E-R chip. + * + * Return: Number of bytes written on success, or negative error code on failure + */ +static ssize_t m24lr_write_pass(struct m24lr *m24lr, const char *buf, + size_t count, u8 code) +{ + __be32 be_pass; + u8 output[9]; + ssize_t ret; + u32 pass; + int err; + + if (!count) + return -EINVAL; + + if (count > 8) + return -EINVAL; + + err = kstrtou32(buf, 16, &pass); + if (err) + return err; + + be_pass = cpu_to_be32(pass); + + memcpy(output, &be_pass, sizeof(be_pass)); + output[4] = code; + memcpy(output + 5, &be_pass, sizeof(be_pass)); + + mutex_lock(&m24lr->lock); + ret = m24lr_regmap_write(m24lr->ctl_regmap, output, 9, 2304); + mutex_unlock(&m24lr->lock); + + return ret; +} + +static ssize_t m24lr_read_reg_le(struct m24lr *m24lr, u64 *val, + unsigned int reg_addr, + unsigned int reg_size) +{ + ssize_t ret; + __le64 input = 0; + + ret = m24lr_read(m24lr, (u8 *)&input, reg_size, reg_addr, false); + if (IS_ERR_VALUE(ret)) + return ret; + + if (ret != reg_size) + return -EINVAL; + + switch (reg_size) { + case 1: + *val = *(u8 *)&input; + break; + case 2: + *val = le16_to_cpu((__le16)input); + break; + case 4: + *val = le32_to_cpu((__le32)input); + break; + case 8: + *val = le64_to_cpu((__le64)input); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int m24lr_nvmem_read(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + ssize_t err; + struct m24lr *m24lr = priv; + + if (!bytes) + return bytes; + + if (offset + bytes > m24lr->eeprom_size) + return -EINVAL; + + err = m24lr_read(m24lr, val, bytes, offset, true); + if (IS_ERR_VALUE(err)) + return err; + + return 0; +} + +static int m24lr_nvmem_write(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + ssize_t err; + struct m24lr *m24lr = priv; + + if (!bytes) + return -EINVAL; + + if (offset + bytes > m24lr->eeprom_size) + return -EINVAL; + + err = m24lr_write(m24lr, val, bytes, offset, true); + if (IS_ERR_VALUE(err)) + return err; + + return 0; +} + +static ssize_t m24lr_ctl_sss_read(struct file *filep, struct kobject *kobj, + const struct bin_attribute *attr, char *buf, + loff_t offset, size_t count) +{ + struct m24lr *m24lr = attr->private; + + if (!count) + return count; + + if (size_add(offset, count) > m24lr->sss_len) + return -EINVAL; + + return m24lr_read(m24lr, buf, count, offset, false); +} + +static ssize_t m24lr_ctl_sss_write(struct file *filep, struct kobject *kobj, + const struct bin_attribute *attr, char *buf, + loff_t offset, size_t count) +{ + struct m24lr *m24lr = attr->private; + + if (!count) + return -EINVAL; + + if (size_add(offset, count) > m24lr->sss_len) + return -EINVAL; + + return m24lr_write(m24lr, buf, count, offset, false); +} +static BIN_ATTR(sss, 0600, m24lr_ctl_sss_read, m24lr_ctl_sss_write, 0); + +static ssize_t new_pass_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct m24lr *m24lr = i2c_get_clientdata(to_i2c_client(dev)); + + return m24lr_write_pass(m24lr, buf, count, 7); +} +static DEVICE_ATTR_WO(new_pass); + +static ssize_t unlock_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct m24lr *m24lr = i2c_get_clientdata(to_i2c_client(dev)); + + return m24lr_write_pass(m24lr, buf, count, 9); +} +static DEVICE_ATTR_WO(unlock); + +static ssize_t uid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct m24lr *m24lr = i2c_get_clientdata(to_i2c_client(dev)); + + return sysfs_emit(buf, "%llx\n", m24lr->uid); +} +static DEVICE_ATTR_RO(uid); + +static ssize_t total_sectors_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct m24lr *m24lr = i2c_get_clientdata(to_i2c_client(dev)); + + return sysfs_emit(buf, "%x\n", m24lr->sss_len); +} +static DEVICE_ATTR_RO(total_sectors); + +static struct attribute *m24lr_ctl_dev_attrs[] = { + &dev_attr_unlock.attr, + &dev_attr_new_pass.attr, + &dev_attr_uid.attr, + &dev_attr_total_sectors.attr, + NULL, +}; + +static const struct m24lr_chip *m24lr_get_chip(struct device *dev) +{ + const struct m24lr_chip *ret; + const struct i2c_device_id *id; + + id = i2c_match_id(m24lr_ids, to_i2c_client(dev)); + + if (dev->of_node && of_match_device(m24lr_of_match, dev)) + ret = of_device_get_match_data(dev); + else if (id) + ret = (void *)id->driver_data; + else + ret = acpi_device_get_match_data(dev); + + return ret; +} + +static int m24lr_probe(struct i2c_client *client) +{ + struct regmap_config eeprom_regmap_conf = {0}; + struct nvmem_config nvmem_conf = {0}; + struct device *dev = &client->dev; + struct i2c_client *eeprom_client; + const struct m24lr_chip *chip; + struct regmap *eeprom_regmap; + struct nvmem_device *nvmem; + struct regmap *ctl_regmap; + struct m24lr *m24lr; + u32 regs[2]; + long err; + + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) + return -EOPNOTSUPP; + + chip = m24lr_get_chip(dev); + if (!chip) + return -ENODEV; + + m24lr = devm_kzalloc(dev, sizeof(struct m24lr), GFP_KERNEL); + if (!m24lr) + return -ENOMEM; + + err = device_property_read_u32_array(dev, "reg", regs, ARRAY_SIZE(regs)); + if (err) + return dev_err_probe(dev, err, "Failed to read 'reg' property\n"); + + /* Create a second I2C client for the eeprom interface */ + eeprom_client = devm_i2c_new_dummy_device(dev, client->adapter, regs[1]); + if (IS_ERR(eeprom_client)) + return dev_err_probe(dev, PTR_ERR(eeprom_client), + "Failed to create dummy I2C client for the EEPROM\n"); + + ctl_regmap = devm_regmap_init_i2c(client, &m24lr_ctl_regmap_conf); + if (IS_ERR(ctl_regmap)) + return dev_err_probe(dev, PTR_ERR(ctl_regmap), + "Failed to init regmap\n"); + + eeprom_regmap_conf.name = "m24lr_eeprom"; + eeprom_regmap_conf.reg_bits = 16; + eeprom_regmap_conf.val_bits = 8; + eeprom_regmap_conf.disable_locking = true; + eeprom_regmap_conf.max_register = chip->eeprom_size - 1; + + eeprom_regmap = devm_regmap_init_i2c(eeprom_client, + &eeprom_regmap_conf); + if (IS_ERR(eeprom_regmap)) + return dev_err_probe(dev, PTR_ERR(eeprom_regmap), + "Failed to init regmap\n"); + + mutex_init(&m24lr->lock); + m24lr->sss_len = chip->sss_len; + m24lr->page_size = chip->page_size; + m24lr->eeprom_size = chip->eeprom_size; + m24lr->eeprom_regmap = eeprom_regmap; + m24lr->ctl_regmap = ctl_regmap; + + nvmem_conf.dev = &eeprom_client->dev; + nvmem_conf.owner = THIS_MODULE; + nvmem_conf.type = NVMEM_TYPE_EEPROM; + nvmem_conf.reg_read = m24lr_nvmem_read; + nvmem_conf.reg_write = m24lr_nvmem_write; + nvmem_conf.size = chip->eeprom_size; + nvmem_conf.word_size = 1; + nvmem_conf.stride = 1; + nvmem_conf.priv = m24lr; + + nvmem = devm_nvmem_register(dev, &nvmem_conf); + if (IS_ERR(nvmem)) + return dev_err_probe(dev, PTR_ERR(nvmem), + "Failed to register nvmem\n"); + + i2c_set_clientdata(client, m24lr); + i2c_set_clientdata(eeprom_client, m24lr); + + bin_attr_sss.size = chip->sss_len; + bin_attr_sss.private = m24lr; + err = sysfs_create_bin_file(&dev->kobj, &bin_attr_sss); + if (err) + return dev_err_probe(dev, err, + "Failed to create sss bin file\n"); + + /* test by reading the uid, if success store it */ + err = m24lr_read_reg_le(m24lr, &m24lr->uid, 2324, sizeof(m24lr->uid)); + if (IS_ERR_VALUE(err)) + goto remove_bin_file; + + return 0; + +remove_bin_file: + sysfs_remove_bin_file(&dev->kobj, &bin_attr_sss); + + return err; +} + +static void m24lr_remove(struct i2c_client *client) +{ + sysfs_remove_bin_file(&client->dev.kobj, &bin_attr_sss); +} + +ATTRIBUTE_GROUPS(m24lr_ctl_dev); + +static struct i2c_driver m24lr_driver = { + .driver = { + .name = "m24lr", + .of_match_table = m24lr_of_match, + .dev_groups = m24lr_ctl_dev_groups, + }, + .probe = m24lr_probe, + .remove = m24lr_remove, + .id_table = m24lr_ids, +}; +module_i2c_driver(m24lr_driver); + +MODULE_AUTHOR("Abd-Alrhman Masalkhi"); +MODULE_DESCRIPTION("st m24lr control driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 53e88a1bc430..8e1d97873423 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -27,8 +27,7 @@ #define MDSP_DOMAIN_ID (1) #define SDSP_DOMAIN_ID (2) #define CDSP_DOMAIN_ID (3) -#define CDSP1_DOMAIN_ID (4) -#define FASTRPC_DEV_MAX 5 /* adsp, mdsp, slpi, cdsp, cdsp1 */ +#define GDSP_DOMAIN_ID (4) #define FASTRPC_MAX_SESSIONS 14 #define FASTRPC_MAX_VMIDS 16 #define FASTRPC_ALIGN 128 @@ -106,8 +105,6 @@ #define miscdev_to_fdevice(d) container_of(d, struct fastrpc_device, miscdev) -static const char *domains[FASTRPC_DEV_MAX] = { "adsp", "mdsp", - "sdsp", "cdsp", "cdsp1" }; struct fastrpc_phy_page { u64 addr; /* physical address */ u64 size; /* size of contiguous region */ @@ -1723,7 +1720,6 @@ static int fastrpc_get_info_from_kernel(struct fastrpc_ioctl_capability *cap, uint32_t attribute_id = cap->attribute_id; uint32_t *dsp_attributes; unsigned long flags; - uint32_t domain = cap->domain; int err; spin_lock_irqsave(&cctx->lock, flags); @@ -1741,7 +1737,7 @@ static int fastrpc_get_info_from_kernel(struct fastrpc_ioctl_capability *cap, err = fastrpc_get_info_from_dsp(fl, dsp_attributes, FASTRPC_MAX_DSP_ATTRIBUTES); if (err == DSP_UNSUPPORTED_API) { dev_info(&cctx->rpdev->dev, - "Warning: DSP capabilities not supported on domain: %d\n", domain); + "Warning: DSP capabilities not supported\n"); kfree(dsp_attributes); return -EOPNOTSUPP; } else if (err) { @@ -1769,17 +1765,6 @@ static int fastrpc_get_dsp_info(struct fastrpc_user *fl, char __user *argp) return -EFAULT; cap.capability = 0; - if (cap.domain >= FASTRPC_DEV_MAX) { - dev_err(&fl->cctx->rpdev->dev, "Error: Invalid domain id:%d, err:%d\n", - cap.domain, err); - return -ECHRNG; - } - - /* Fastrpc Capablities does not support modem domain */ - if (cap.domain == MDSP_DOMAIN_ID) { - dev_err(&fl->cctx->rpdev->dev, "Error: modem not supported %d\n", err); - return -ECHRNG; - } if (cap.attribute_id >= FASTRPC_MAX_DSP_ATTRIBUTES) { dev_err(&fl->cctx->rpdev->dev, "Error: invalid attribute: %d, err: %d\n", @@ -2255,6 +2240,22 @@ static int fastrpc_device_register(struct device *dev, struct fastrpc_channel_ct return err; } +static int fastrpc_get_domain_id(const char *domain) +{ + if (!strncmp(domain, "adsp", 4)) + return ADSP_DOMAIN_ID; + else if (!strncmp(domain, "cdsp", 4)) + return CDSP_DOMAIN_ID; + else if (!strncmp(domain, "mdsp", 4)) + return MDSP_DOMAIN_ID; + else if (!strncmp(domain, "sdsp", 4)) + return SDSP_DOMAIN_ID; + else if (!strncmp(domain, "gdsp", 4)) + return GDSP_DOMAIN_ID; + + return -EINVAL; +} + static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) { struct device *rdev = &rpdev->dev; @@ -2270,15 +2271,10 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) return err; } - for (i = 0; i < FASTRPC_DEV_MAX; i++) { - if (!strcmp(domains[i], domain)) { - domain_id = i; - break; - } - } + domain_id = fastrpc_get_domain_id(domain); if (domain_id < 0) { - dev_info(rdev, "FastRPC Invalid Domain ID %d\n", domain_id); + dev_info(rdev, "FastRPC Domain %s not supported\n", domain); return -EINVAL; } @@ -2325,21 +2321,21 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) case ADSP_DOMAIN_ID: case MDSP_DOMAIN_ID: case SDSP_DOMAIN_ID: - /* Unsigned PD offloading is only supported on CDSP and CDSP1 */ + /* Unsigned PD offloading is only supported on CDSP and GDSP */ data->unsigned_support = false; - err = fastrpc_device_register(rdev, data, secure_dsp, domains[domain_id]); + err = fastrpc_device_register(rdev, data, secure_dsp, domain); if (err) goto err_free_data; break; case CDSP_DOMAIN_ID: - case CDSP1_DOMAIN_ID: + case GDSP_DOMAIN_ID: data->unsigned_support = true; /* Create both device nodes so that we can allow both Signed and Unsigned PD */ - err = fastrpc_device_register(rdev, data, true, domains[domain_id]); + err = fastrpc_device_register(rdev, data, true, domain); if (err) goto err_free_data; - err = fastrpc_device_register(rdev, data, false, domains[domain_id]); + err = fastrpc_device_register(rdev, data, false, domain); if (err) goto err_deregister_fdev; break; diff --git a/drivers/misc/genwqe/card_ddcb.c b/drivers/misc/genwqe/card_ddcb.c index 500b1feaf1f6..fd7d5cd50d39 100644 --- a/drivers/misc/genwqe/card_ddcb.c +++ b/drivers/misc/genwqe/card_ddcb.c @@ -923,7 +923,7 @@ int __genwqe_execute_raw_ddcb(struct genwqe_dev *cd, } if (cmd->asv_length > DDCB_ASV_LENGTH) { dev_err(&pci_dev->dev, "[%s] err: wrong asv_length of %d\n", - __func__, cmd->asiv_length); + __func__, cmd->asv_length); return -EINVAL; } rc = __genwqe_enqueue_ddcb(cd, req, f_flags); diff --git a/drivers/misc/hisi_hikey_usb.c b/drivers/misc/hisi_hikey_usb.c index ffe7b945a298..2c6e448a47f1 100644 --- a/drivers/misc/hisi_hikey_usb.c +++ b/drivers/misc/hisi_hikey_usb.c @@ -18,6 +18,7 @@ #include <linux/property.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/usb/role.h> #define DEVICE_DRIVER_NAME "hisi_hikey_usb" @@ -67,7 +68,7 @@ static void hub_power_ctrl(struct hisi_hikey_usb *hisi_hikey_usb, int value) if (ret) dev_err(hisi_hikey_usb->dev, "Can't switch regulator state to %s\n", - value ? "enabled" : "disabled"); + str_enabled_disabled(value)); } static void usb_switch_ctrl(struct hisi_hikey_usb *hisi_hikey_usb, diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index c44de892a61e..2d5c1df82732 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -525,15 +525,9 @@ static ssize_t remote_settings_file_write(struct file *file, const char __user * if (*offset != 0) return 0; - buff = kzalloc (count + 1, GFP_KERNEL); - if (!buff) - return -ENOMEM; - - - if (copy_from_user(buff, ubuff, count)) { - kfree(buff); - return -EFAULT; - } + buff = memdup_user_nul(ubuff, count); + if (IS_ERR(buff)) + return PTR_ERR(buff); value = simple_strtoul(buff, NULL, 10); writel(value, address); diff --git a/drivers/misc/lis3lv02d/Kconfig b/drivers/misc/lis3lv02d/Kconfig index 56005243a230..9d546a42a563 100644 --- a/drivers/misc/lis3lv02d/Kconfig +++ b/drivers/misc/lis3lv02d/Kconfig @@ -4,7 +4,7 @@ # config SENSORS_LIS3_SPI - tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer (SPI)" + tristate "STMicroelectronics LIS3LV02Dx three-axis digital accelerometer (SPI)" depends on !ACPI && SPI_MASTER && INPUT select SENSORS_LIS3LV02D help @@ -20,7 +20,7 @@ config SENSORS_LIS3_SPI is called lis3lv02d_spi. config SENSORS_LIS3_I2C - tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer (I2C)" + tristate "STMicroelectronics LIS3LV02Dx three-axis digital accelerometer (I2C)" depends on I2C && INPUT select SENSORS_LIS3LV02D help diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index 90dba20b2de7..e6a1d3534663 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -386,7 +386,7 @@ static int mei_nfc_if_version(struct mei_cl *cl, ret = __mei_cl_send(cl, (u8 *)&cmd, sizeof(cmd), 0, MEI_CL_IO_TX_BLOCKING); if (ret < 0) { - dev_err(bus->dev, "Could not send IF version cmd ret = %d\n", ret); + dev_err(&bus->dev, "Could not send IF version cmd ret = %d\n", ret); return ret; } @@ -401,14 +401,14 @@ static int mei_nfc_if_version(struct mei_cl *cl, bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length, &vtag, 0, 0); if (bytes_recv < 0 || (size_t)bytes_recv < if_version_length) { - dev_err(bus->dev, "Could not read IF version ret = %d\n", bytes_recv); + dev_err(&bus->dev, "Could not read IF version ret = %d\n", bytes_recv); ret = -EIO; goto err; } memcpy(ver, reply->data, sizeof(*ver)); - dev_info(bus->dev, "NFC MEI VERSION: IVN 0x%x Vendor ID 0x%x Type 0x%x\n", + dev_info(&bus->dev, "NFC MEI VERSION: IVN 0x%x Vendor ID 0x%x Type 0x%x\n", ver->fw_ivn, ver->vendor_id, ver->radio_type); err: diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 5cc3ad07d5be..38735a41f750 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -637,7 +637,7 @@ EXPORT_SYMBOL_GPL(mei_cldev_enabled); */ static bool mei_cl_bus_module_get(struct mei_cl_device *cldev) { - return try_module_get(cldev->bus->dev->driver->owner); + return try_module_get(cldev->bus->parent->driver->owner); } /** @@ -647,7 +647,7 @@ static bool mei_cl_bus_module_get(struct mei_cl_device *cldev) */ static void mei_cl_bus_module_put(struct mei_cl_device *cldev) { - module_put(cldev->bus->dev->driver->owner); + module_put(cldev->bus->parent->driver->owner); } /** @@ -814,7 +814,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev) ret = mei_cl_connect(cl, cldev->me_cl, NULL); if (ret < 0) { - dev_err(&cldev->dev, "cannot connect\n"); + dev_dbg(&cldev->dev, "cannot connect\n"); mei_cl_bus_vtag_free(cldev); } @@ -1285,16 +1285,20 @@ static const struct bus_type mei_cl_bus_type = { static struct mei_device *mei_dev_bus_get(struct mei_device *bus) { - if (bus) - get_device(bus->dev); + if (bus) { + get_device(&bus->dev); + get_device(bus->parent); + } return bus; } static void mei_dev_bus_put(struct mei_device *bus) { - if (bus) - put_device(bus->dev); + if (bus) { + put_device(bus->parent); + put_device(&bus->dev); + } } static void mei_cl_bus_dev_release(struct device *dev) @@ -1328,7 +1332,7 @@ static const struct device_type mei_cl_device_type = { static inline void mei_cl_bus_set_name(struct mei_cl_device *cldev) { dev_set_name(&cldev->dev, "%s-%pUl", - dev_name(cldev->bus->dev), + dev_name(cldev->bus->parent), mei_me_cl_uuid(cldev->me_cl)); } @@ -1357,7 +1361,7 @@ static struct mei_cl_device *mei_cl_bus_dev_alloc(struct mei_device *bus, } device_initialize(&cldev->dev); - cldev->dev.parent = bus->dev; + cldev->dev.parent = bus->parent; cldev->dev.bus = &mei_cl_bus_type; cldev->dev.type = &mei_cl_device_type; cldev->bus = mei_dev_bus_get(bus); @@ -1492,7 +1496,7 @@ static void mei_cl_bus_dev_init(struct mei_device *bus, WARN_ON(!mutex_is_locked(&bus->cl_bus_lock)); - dev_dbg(bus->dev, "initializing %pUl", mei_me_cl_uuid(me_cl)); + dev_dbg(&bus->dev, "initializing %pUl", mei_me_cl_uuid(me_cl)); if (me_cl->bus_added) return; @@ -1543,7 +1547,7 @@ static void mei_cl_bus_rescan(struct mei_device *bus) } mutex_unlock(&bus->cl_bus_lock); - dev_dbg(bus->dev, "rescan end"); + dev_dbg(&bus->dev, "rescan end"); } void mei_cl_bus_rescan_work(struct work_struct *work) diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 3db07d2a881f..159e8b841564 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -262,7 +262,7 @@ void mei_me_cl_rm_by_uuid(struct mei_device *dev, const uuid_le *uuid) { struct mei_me_client *me_cl; - dev_dbg(dev->dev, "remove %pUl\n", uuid); + dev_dbg(&dev->dev, "remove %pUl\n", uuid); down_write(&dev->me_clients_rwsem); me_cl = __mei_me_cl_by_uuid(dev, uuid); @@ -635,12 +635,12 @@ int mei_cl_link(struct mei_cl *cl) id = find_first_zero_bit(dev->host_clients_map, MEI_CLIENTS_MAX); if (id >= MEI_CLIENTS_MAX) { - dev_err(dev->dev, "id exceeded %d", MEI_CLIENTS_MAX); + dev_err(&dev->dev, "id exceeded %d", MEI_CLIENTS_MAX); return -EMFILE; } if (dev->open_handle_count >= MEI_MAX_OPEN_HANDLE_COUNT) { - dev_err(dev->dev, "open_handle_count exceeded %d", + dev_err(&dev->dev, "open_handle_count exceeded %d", MEI_MAX_OPEN_HANDLE_COUNT); return -EMFILE; } @@ -709,9 +709,9 @@ void mei_host_client_init(struct mei_device *dev) schedule_work(&dev->bus_rescan_work); - pm_runtime_mark_last_busy(dev->dev); - dev_dbg(dev->dev, "rpm: autosuspend\n"); - pm_request_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + dev_dbg(&dev->dev, "rpm: autosuspend\n"); + pm_request_autosuspend(dev->parent); } /** @@ -724,12 +724,12 @@ bool mei_hbuf_acquire(struct mei_device *dev) { if (mei_pg_state(dev) == MEI_PG_ON || mei_pg_in_transition(dev)) { - dev_dbg(dev->dev, "device is in pg\n"); + dev_dbg(&dev->dev, "device is in pg\n"); return false; } if (!dev->hbuf_is_ready) { - dev_dbg(dev->dev, "hbuf is not ready\n"); + dev_dbg(&dev->dev, "hbuf is not ready\n"); return false; } @@ -981,9 +981,9 @@ int mei_cl_disconnect(struct mei_cl *cl) return 0; } - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); return rets; } @@ -991,8 +991,8 @@ int mei_cl_disconnect(struct mei_cl *cl) rets = __mei_cl_disconnect(cl); cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); return rets; } @@ -1118,9 +1118,9 @@ int mei_cl_connect(struct mei_cl *cl, struct mei_me_client *me_cl, goto nortpm; } - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); goto nortpm; } @@ -1167,8 +1167,8 @@ int mei_cl_connect(struct mei_cl *cl, struct mei_me_client *me_cl, rets = cl->status; out: cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); mei_io_cb_free(cb); @@ -1517,9 +1517,9 @@ int mei_cl_notify_request(struct mei_cl *cl, if (!mei_cl_is_connected(cl)) return -ENODEV; - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); return rets; } @@ -1554,8 +1554,8 @@ int mei_cl_notify_request(struct mei_cl *cl, out: cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); mei_io_cb_free(cb); return rets; @@ -1683,9 +1683,9 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length, const struct file *fp) mei_cl_set_read_by_fp(cl, fp); - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); goto nortpm; } @@ -1702,8 +1702,8 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length, const struct file *fp) out: cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); nortpm: if (rets) mei_io_cb_free(cb); @@ -1972,9 +1972,9 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time blocking = cb->blocking; data = buf->data; - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %zd\n", rets); goto free; } @@ -2092,8 +2092,8 @@ out: rets = buf_len; err: cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); free: mei_io_cb_free(cb); @@ -2119,8 +2119,8 @@ void mei_cl_complete(struct mei_cl *cl, struct mei_cl_cb *cb) if (waitqueue_active(&cl->tx_wait)) { wake_up_interruptible(&cl->tx_wait); } else { - pm_runtime_mark_last_busy(dev->dev); - pm_request_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_request_autosuspend(dev->parent); } break; @@ -2251,7 +2251,7 @@ int mei_cl_irq_dma_unmap(struct mei_cl *cl, struct mei_cl_cb *cb, static int mei_cl_dma_alloc(struct mei_cl *cl, u8 buf_id, size_t size) { - cl->dma.vaddr = dmam_alloc_coherent(cl->dev->dev, size, + cl->dma.vaddr = dmam_alloc_coherent(&cl->dev->dev, size, &cl->dma.daddr, GFP_KERNEL); if (!cl->dma.vaddr) return -ENOMEM; @@ -2265,7 +2265,7 @@ static int mei_cl_dma_alloc(struct mei_cl *cl, u8 buf_id, size_t size) static void mei_cl_dma_free(struct mei_cl *cl) { cl->dma.buffer_id = 0; - dmam_free_coherent(cl->dev->dev, + dmam_free_coherent(&cl->dev->dev, cl->dma.size, cl->dma.vaddr, cl->dma.daddr); cl->dma.size = 0; cl->dma.vaddr = NULL; @@ -2321,16 +2321,16 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp, return -EPROTO; } - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); return rets; } rets = mei_cl_dma_alloc(cl, buffer_id, size); if (rets) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); return rets; } @@ -2366,8 +2366,8 @@ out: mei_cl_dma_free(cl); cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); mei_io_cb_free(cb); return rets; @@ -2406,9 +2406,9 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) if (!cl->dma_mapped) return -EPROTO; - rets = pm_runtime_get(dev->dev); + rets = pm_runtime_get(dev->parent); if (rets < 0 && rets != -EINPROGRESS) { - pm_runtime_put_noidle(dev->dev); + pm_runtime_put_noidle(dev->parent); cl_err(dev, cl, "rpm: get failed %d\n", rets); return rets; } @@ -2444,8 +2444,8 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) mei_cl_dma_free(cl); out: cl_dbg(dev, cl, "rpm: autosuspend\n"); - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_runtime_put_autosuspend(dev->parent); mei_io_cb_free(cb); return rets; diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 01ed26a148c4..031114478bcb 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -275,12 +275,12 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp); #define MEI_CL_PRM(cl) (cl)->host_client_id, mei_cl_me_id(cl) #define cl_dbg(dev, cl, format, arg...) \ - dev_dbg((dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) + dev_dbg(&(dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) #define cl_warn(dev, cl, format, arg...) \ - dev_warn((dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) + dev_warn(&(dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) #define cl_err(dev, cl, format, arg...) \ - dev_err((dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) + dev_err(&(dev)->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) #endif /* _MEI_CLIENT_H_ */ diff --git a/drivers/misc/mei/dma-ring.c b/drivers/misc/mei/dma-ring.c index 651e77ef82bd..6277c4a5b0fd 100644 --- a/drivers/misc/mei/dma-ring.c +++ b/drivers/misc/mei/dma-ring.c @@ -30,7 +30,7 @@ static int mei_dmam_dscr_alloc(struct mei_device *dev, if (dscr->vaddr) return 0; - dscr->vaddr = dmam_alloc_coherent(dev->dev, dscr->size, &dscr->daddr, + dscr->vaddr = dmam_alloc_coherent(dev->parent, dscr->size, &dscr->daddr, GFP_KERNEL); if (!dscr->vaddr) return -ENOMEM; @@ -50,7 +50,7 @@ static void mei_dmam_dscr_free(struct mei_device *dev, if (!dscr->vaddr) return; - dmam_free_coherent(dev->dev, dscr->size, dscr->vaddr, dscr->daddr); + dmam_free_coherent(dev->parent, dscr->size, dscr->vaddr, dscr->daddr); dscr->vaddr = NULL; } @@ -177,7 +177,7 @@ void mei_dma_ring_read(struct mei_device *dev, unsigned char *buf, u32 len) if (WARN_ON(!ctrl)) return; - dev_dbg(dev->dev, "reading from dma %u bytes\n", len); + dev_dbg(&dev->dev, "reading from dma %u bytes\n", len); if (!len) return; @@ -254,7 +254,7 @@ void mei_dma_ring_write(struct mei_device *dev, unsigned char *buf, u32 len) if (WARN_ON(!ctrl)) return; - dev_dbg(dev->dev, "writing to dma %u bytes\n", len); + dev_dbg(&dev->dev, "writing to dma %u bytes\n", len); hbuf_depth = mei_dma_ring_hbuf_depth(dev); wr_idx = READ_ONCE(ctrl->hbuf_wr_idx) & (hbuf_depth - 1); slots = mei_data2slots(len); diff --git a/drivers/misc/mei/gsc-me.c b/drivers/misc/mei/gsc-me.c index 5a8c26c3df13..93cba090ea08 100644 --- a/drivers/misc/mei/gsc-me.c +++ b/drivers/misc/mei/gsc-me.c @@ -106,11 +106,15 @@ static int mei_gsc_probe(struct auxiliary_device *aux_dev, } } + ret = mei_register(dev, device); + if (ret) + goto deinterrupt; + pm_runtime_get_noresume(device); pm_runtime_set_active(device); pm_runtime_enable(device); - /* Continue to char device setup in spite of firmware handshake failure. + /* Continue in spite of firmware handshake failure. * In order to provide access to the firmware status registers to the user * space via sysfs. */ @@ -120,18 +124,12 @@ static int mei_gsc_probe(struct auxiliary_device *aux_dev, pm_runtime_set_autosuspend_delay(device, MEI_GSC_RPM_TIMEOUT); pm_runtime_use_autosuspend(device); - ret = mei_register(dev, device); - if (ret) - goto register_err; - pm_runtime_put_noidle(device); return 0; -register_err: - mei_stop(dev); +deinterrupt: if (!mei_me_hw_use_polling(hw)) devm_free_irq(device, hw->irq, dev); - err: dev_err(device, "probe failed: %d\n", ret); dev_set_drvdata(device, NULL); @@ -152,13 +150,13 @@ static void mei_gsc_remove(struct auxiliary_device *aux_dev) if (mei_me_hw_use_polling(hw)) kthread_stop(hw->polling_thread); - mei_deregister(dev); - pm_runtime_disable(&aux_dev->dev); mei_disable_interrupts(dev); if (!mei_me_hw_use_polling(hw)) devm_free_irq(&aux_dev->dev, hw->irq, dev); + + mei_deregister(dev); } static int __maybe_unused mei_gsc_pm_suspend(struct device *device) @@ -252,7 +250,7 @@ static int __maybe_unused mei_gsc_pm_runtime_resume(struct device *device) irq_ret = mei_me_irq_thread_handler(1, dev); if (irq_ret != IRQ_HANDLED) - dev_err(dev->dev, "thread handler fail %d\n", irq_ret); + dev_err(&dev->dev, "thread handler fail %d\n", irq_ret); return 0; } diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 4fe9a2752d43..ccd9df5d1c7d 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -239,7 +239,7 @@ int mei_hbm_start_wait(struct mei_device *dev) if (ret == 0 && (dev->hbm_state <= MEI_HBM_STARTING)) { dev->hbm_state = MEI_HBM_IDLE; - dev_err(dev->dev, "waiting for mei start failed\n"); + dev_err(&dev->dev, "waiting for mei start failed\n"); return -ETIME; } return 0; @@ -271,8 +271,7 @@ int mei_hbm_start_req(struct mei_device *dev) dev->hbm_state = MEI_HBM_IDLE; ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) { - dev_err(dev->dev, "version message write failed: ret = %d\n", - ret); + dev_err(&dev->dev, "version message write failed: ret = %d\n", ret); return ret; } @@ -312,8 +311,7 @@ static int mei_hbm_dma_setup_req(struct mei_device *dev) ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) { - dev_err(dev->dev, "dma setup request write failed: ret = %d.\n", - ret); + dev_err(&dev->dev, "dma setup request write failed: ret = %d.\n", ret); return ret; } @@ -351,8 +349,7 @@ static int mei_hbm_capabilities_req(struct mei_device *dev) ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) { - dev_err(dev->dev, - "capabilities request write failed: ret = %d.\n", ret); + dev_err(&dev->dev, "capabilities request write failed: ret = %d.\n", ret); return ret; } @@ -386,8 +383,7 @@ static int mei_hbm_enum_clients_req(struct mei_device *dev) ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) { - dev_err(dev->dev, "enumeration request write failed: ret = %d.\n", - ret); + dev_err(&dev->dev, "enumeration request write failed: ret = %d.\n", ret); return ret; } dev->hbm_state = MEI_HBM_ENUM_CLIENTS; @@ -443,7 +439,7 @@ static int mei_hbm_add_cl_resp(struct mei_device *dev, u8 addr, u8 status) struct hbm_add_client_response resp; int ret; - dev_dbg(dev->dev, "adding client response\n"); + dev_dbg(&dev->dev, "adding client response\n"); mei_hbm_hdr(&mei_hdr, sizeof(resp)); @@ -454,8 +450,7 @@ static int mei_hbm_add_cl_resp(struct mei_device *dev, u8 addr, u8 status) ret = mei_hbm_write_message(dev, &mei_hdr, &resp); if (ret) - dev_err(dev->dev, "add client response write failed: ret = %d\n", - ret); + dev_err(&dev->dev, "add client response write failed: ret = %d\n", ret); return ret; } @@ -752,7 +747,7 @@ static int mei_hbm_prop_req(struct mei_device *dev, unsigned long start_idx) ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) { - dev_err(dev->dev, "properties request write failed: ret = %d\n", + dev_err(&dev->dev, "properties request write failed: ret = %d\n", ret); return ret; } @@ -788,7 +783,7 @@ int mei_hbm_pg(struct mei_device *dev, u8 pg_cmd) ret = mei_hbm_write_message(dev, &mei_hdr, &req); if (ret) - dev_err(dev->dev, "power gate command write failed.\n"); + dev_err(&dev->dev, "power gate command write failed.\n"); return ret; } EXPORT_SYMBOL_GPL(mei_hbm_pg); @@ -847,7 +842,7 @@ static int mei_hbm_add_single_tx_flow_ctrl_creds(struct mei_device *dev, me_cl = mei_me_cl_by_id(dev, fctrl->me_addr); if (!me_cl) { - dev_err(dev->dev, "no such me client %d\n", fctrl->me_addr); + dev_err(&dev->dev, "no such me client %d\n", fctrl->me_addr); return -ENOENT; } @@ -857,7 +852,7 @@ static int mei_hbm_add_single_tx_flow_ctrl_creds(struct mei_device *dev, } me_cl->tx_flow_ctrl_creds++; - dev_dbg(dev->dev, "recv flow ctrl msg ME %d (single) creds = %d.\n", + dev_dbg(&dev->dev, "recv flow ctrl msg ME %d (single) creds = %d.\n", fctrl->me_addr, me_cl->tx_flow_ctrl_creds); rets = 0; @@ -1085,7 +1080,7 @@ static int mei_hbm_pg_enter_res(struct mei_device *dev) { if (mei_pg_state(dev) != MEI_PG_OFF || dev->pg_event != MEI_PG_EVENT_WAIT) { - dev_err(dev->dev, "hbm: pg entry response: state mismatch [%s, %d]\n", + dev_err(&dev->dev, "hbm: pg entry response: state mismatch [%s, %d]\n", mei_pg_state_str(mei_pg_state(dev)), dev->pg_event); return -EPROTO; } @@ -1103,7 +1098,7 @@ static int mei_hbm_pg_enter_res(struct mei_device *dev) */ void mei_hbm_pg_resume(struct mei_device *dev) { - pm_request_resume(dev->dev); + pm_request_resume(dev->parent); } EXPORT_SYMBOL_GPL(mei_hbm_pg_resume); @@ -1119,7 +1114,7 @@ static int mei_hbm_pg_exit_res(struct mei_device *dev) if (mei_pg_state(dev) != MEI_PG_ON || (dev->pg_event != MEI_PG_EVENT_WAIT && dev->pg_event != MEI_PG_EVENT_IDLE)) { - dev_err(dev->dev, "hbm: pg exit response: state mismatch [%s, %d]\n", + dev_err(&dev->dev, "hbm: pg exit response: state mismatch [%s, %d]\n", mei_pg_state_str(mei_pg_state(dev)), dev->pg_event); return -EPROTO; } @@ -1276,19 +1271,19 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) * hbm is put to idle during system reset */ if (dev->hbm_state == MEI_HBM_IDLE) { - dev_dbg(dev->dev, "hbm: state is idle ignore spurious messages\n"); + dev_dbg(&dev->dev, "hbm: state is idle ignore spurious messages\n"); return 0; } switch (mei_msg->hbm_cmd) { case HOST_START_RES_CMD: - dev_dbg(dev->dev, "hbm: start: response message received.\n"); + dev_dbg(&dev->dev, "hbm: start: response message received.\n"); dev->init_clients_timer = 0; version_res = (struct hbm_host_version_response *)mei_msg; - dev_dbg(dev->dev, "HBM VERSION: DRIVER=%02d:%02d DEVICE=%02d:%02d\n", + dev_dbg(&dev->dev, "HBM VERSION: DRIVER=%02d:%02d DEVICE=%02d:%02d\n", HBM_MAJOR_VERSION, HBM_MINOR_VERSION, version_res->me_max_version.major_version, version_res->me_max_version.minor_version); @@ -1304,11 +1299,11 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) } if (!mei_hbm_version_is_supported(dev)) { - dev_warn(dev->dev, "hbm: start: version mismatch - stopping the driver.\n"); + dev_warn(&dev->dev, "hbm: start: version mismatch - stopping the driver.\n"); dev->hbm_state = MEI_HBM_STOPPED; if (mei_hbm_stop_req(dev)) { - dev_err(dev->dev, "hbm: start: failed to send stop request\n"); + dev_err(&dev->dev, "hbm: start: failed to send stop request\n"); return -EIO; } break; @@ -1320,10 +1315,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->hbm_state != MEI_HBM_STARTING) { if (dev->dev_state == MEI_DEV_POWER_DOWN || dev->dev_state == MEI_DEV_POWERING_DOWN) { - dev_dbg(dev->dev, "hbm: start: on shutdown, ignoring\n"); + dev_dbg(&dev->dev, "hbm: start: on shutdown, ignoring\n"); return 0; } - dev_err(dev->dev, "hbm: start: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: start: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } @@ -1337,7 +1332,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->hbm_f_dr_supported) { if (mei_dmam_ring_alloc(dev)) - dev_info(dev->dev, "running w/o dma ring\n"); + dev_info(&dev->dev, "running w/o dma ring\n"); if (mei_dma_ring_is_allocated(dev)) { if (mei_hbm_dma_setup_req(dev)) return -EIO; @@ -1357,7 +1352,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; case MEI_HBM_CAPABILITIES_RES_CMD: - dev_dbg(dev->dev, "hbm: capabilities response: message received.\n"); + dev_dbg(&dev->dev, "hbm: capabilities response: message received.\n"); dev->init_clients_timer = 0; @@ -1365,10 +1360,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->hbm_state != MEI_HBM_CAP_SETUP) { if (dev->dev_state == MEI_DEV_POWER_DOWN || dev->dev_state == MEI_DEV_POWERING_DOWN) { - dev_dbg(dev->dev, "hbm: capabilities response: on shutdown, ignoring\n"); + dev_dbg(&dev->dev, "hbm: capabilities response: on shutdown, ignoring\n"); return 0; } - dev_err(dev->dev, "hbm: capabilities response: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: capabilities response: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } @@ -1384,7 +1379,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->hbm_f_dr_supported) { if (mei_dmam_ring_alloc(dev)) - dev_info(dev->dev, "running w/o dma ring\n"); + dev_info(&dev->dev, "running w/o dma ring\n"); if (mei_dma_ring_is_allocated(dev)) { if (mei_hbm_dma_setup_req(dev)) return -EIO; @@ -1400,7 +1395,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; case MEI_HBM_DMA_SETUP_RES_CMD: - dev_dbg(dev->dev, "hbm: dma setup response: message received.\n"); + dev_dbg(&dev->dev, "hbm: dma setup response: message received.\n"); dev->init_clients_timer = 0; @@ -1408,10 +1403,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->hbm_state != MEI_HBM_DR_SETUP) { if (dev->dev_state == MEI_DEV_POWER_DOWN || dev->dev_state == MEI_DEV_POWERING_DOWN) { - dev_dbg(dev->dev, "hbm: dma setup response: on shutdown, ignoring\n"); + dev_dbg(&dev->dev, "hbm: dma setup response: on shutdown, ignoring\n"); return 0; } - dev_err(dev->dev, "hbm: dma setup response: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: dma setup response: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } @@ -1422,9 +1417,9 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) u8 status = dma_setup_res->status; if (status == MEI_HBMS_NOT_ALLOWED) { - dev_dbg(dev->dev, "hbm: dma setup not allowed\n"); + dev_dbg(&dev->dev, "hbm: dma setup not allowed\n"); } else { - dev_info(dev->dev, "hbm: dma setup response: failure = %d %s\n", + dev_info(&dev->dev, "hbm: dma setup response: failure = %d %s\n", status, mei_hbm_status_str(status)); } @@ -1437,38 +1432,38 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; case CLIENT_CONNECT_RES_CMD: - dev_dbg(dev->dev, "hbm: client connect response: message received.\n"); + dev_dbg(&dev->dev, "hbm: client connect response: message received.\n"); mei_hbm_cl_res(dev, cl_cmd, MEI_FOP_CONNECT); break; case CLIENT_DISCONNECT_RES_CMD: - dev_dbg(dev->dev, "hbm: client disconnect response: message received.\n"); + dev_dbg(&dev->dev, "hbm: client disconnect response: message received.\n"); mei_hbm_cl_res(dev, cl_cmd, MEI_FOP_DISCONNECT); break; case MEI_FLOW_CONTROL_CMD: - dev_dbg(dev->dev, "hbm: client flow control response: message received.\n"); + dev_dbg(&dev->dev, "hbm: client flow control response: message received.\n"); fctrl = (struct hbm_flow_control *)mei_msg; mei_hbm_cl_tx_flow_ctrl_creds_res(dev, fctrl); break; case MEI_PG_ISOLATION_ENTRY_RES_CMD: - dev_dbg(dev->dev, "hbm: power gate isolation entry response received\n"); + dev_dbg(&dev->dev, "hbm: power gate isolation entry response received\n"); ret = mei_hbm_pg_enter_res(dev); if (ret) return ret; break; case MEI_PG_ISOLATION_EXIT_REQ_CMD: - dev_dbg(dev->dev, "hbm: power gate isolation exit request received\n"); + dev_dbg(&dev->dev, "hbm: power gate isolation exit request received\n"); ret = mei_hbm_pg_exit_res(dev); if (ret) return ret; break; case HOST_CLIENT_PROPERTIES_RES_CMD: - dev_dbg(dev->dev, "hbm: properties response: message received.\n"); + dev_dbg(&dev->dev, "hbm: properties response: message received.\n"); dev->init_clients_timer = 0; @@ -1476,10 +1471,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->hbm_state != MEI_HBM_CLIENT_PROPERTIES) { if (dev->dev_state == MEI_DEV_POWER_DOWN || dev->dev_state == MEI_DEV_POWERING_DOWN) { - dev_dbg(dev->dev, "hbm: properties response: on shutdown, ignoring\n"); + dev_dbg(&dev->dev, "hbm: properties response: on shutdown, ignoring\n"); return 0; } - dev_err(dev->dev, "hbm: properties response: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: properties response: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } @@ -1487,10 +1482,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) props_res = (struct hbm_props_response *)mei_msg; if (props_res->status == MEI_HBMS_CLIENT_NOT_FOUND) { - dev_dbg(dev->dev, "hbm: properties response: %d CLIENT_NOT_FOUND\n", + dev_dbg(&dev->dev, "hbm: properties response: %d CLIENT_NOT_FOUND\n", props_res->me_addr); } else if (props_res->status) { - dev_err(dev->dev, "hbm: properties response: wrong status = %d %s\n", + dev_err(&dev->dev, "hbm: properties response: wrong status = %d %s\n", props_res->status, mei_hbm_status_str(props_res->status)); return -EPROTO; @@ -1505,7 +1500,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; case HOST_ENUM_RES_CMD: - dev_dbg(dev->dev, "hbm: enumeration response: message received\n"); + dev_dbg(&dev->dev, "hbm: enumeration response: message received\n"); dev->init_clients_timer = 0; @@ -1519,10 +1514,10 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->hbm_state != MEI_HBM_ENUM_CLIENTS) { if (dev->dev_state == MEI_DEV_POWER_DOWN || dev->dev_state == MEI_DEV_POWERING_DOWN) { - dev_dbg(dev->dev, "hbm: enumeration response: on shutdown, ignoring\n"); + dev_dbg(&dev->dev, "hbm: enumeration response: on shutdown, ignoring\n"); return 0; } - dev_err(dev->dev, "hbm: enumeration response: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: enumeration response: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } @@ -1536,77 +1531,77 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; case HOST_STOP_RES_CMD: - dev_dbg(dev->dev, "hbm: stop response: message received\n"); + dev_dbg(&dev->dev, "hbm: stop response: message received\n"); dev->init_clients_timer = 0; if (dev->hbm_state != MEI_HBM_STOPPED) { - dev_err(dev->dev, "hbm: stop response: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: stop response: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } mei_set_devstate(dev, MEI_DEV_POWER_DOWN); - dev_info(dev->dev, "hbm: stop response: resetting.\n"); + dev_info(&dev->dev, "hbm: stop response: resetting.\n"); /* force the reset */ return -EPROTO; case CLIENT_DISCONNECT_REQ_CMD: - dev_dbg(dev->dev, "hbm: disconnect request: message received\n"); + dev_dbg(&dev->dev, "hbm: disconnect request: message received\n"); disconnect_req = (struct hbm_client_connect_request *)mei_msg; mei_hbm_fw_disconnect_req(dev, disconnect_req); break; case ME_STOP_REQ_CMD: - dev_dbg(dev->dev, "hbm: stop request: message received\n"); + dev_dbg(&dev->dev, "hbm: stop request: message received\n"); dev->hbm_state = MEI_HBM_STOPPED; if (mei_hbm_stop_req(dev)) { - dev_err(dev->dev, "hbm: stop request: failed to send stop request\n"); + dev_err(&dev->dev, "hbm: stop request: failed to send stop request\n"); return -EIO; } break; case MEI_HBM_ADD_CLIENT_REQ_CMD: - dev_dbg(dev->dev, "hbm: add client request received\n"); + dev_dbg(&dev->dev, "hbm: add client request received\n"); /* * after the host receives the enum_resp * message clients may be added or removed */ if (dev->hbm_state <= MEI_HBM_ENUM_CLIENTS || dev->hbm_state >= MEI_HBM_STOPPED) { - dev_err(dev->dev, "hbm: add client: state mismatch, [%d, %d]\n", + dev_err(&dev->dev, "hbm: add client: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); return -EPROTO; } add_cl_req = (struct hbm_add_client_request *)mei_msg; ret = mei_hbm_fw_add_cl_req(dev, add_cl_req); if (ret) { - dev_err(dev->dev, "hbm: add client: failed to send response %d\n", + dev_err(&dev->dev, "hbm: add client: failed to send response %d\n", ret); return -EIO; } - dev_dbg(dev->dev, "hbm: add client request processed\n"); + dev_dbg(&dev->dev, "hbm: add client request processed\n"); break; case MEI_HBM_NOTIFY_RES_CMD: - dev_dbg(dev->dev, "hbm: notify response received\n"); + dev_dbg(&dev->dev, "hbm: notify response received\n"); mei_hbm_cl_res(dev, cl_cmd, notify_res_to_fop(cl_cmd)); break; case MEI_HBM_NOTIFICATION_CMD: - dev_dbg(dev->dev, "hbm: notification\n"); + dev_dbg(&dev->dev, "hbm: notification\n"); mei_hbm_cl_notify(dev, cl_cmd); break; case MEI_HBM_CLIENT_DMA_MAP_RES_CMD: - dev_dbg(dev->dev, "hbm: client dma map response: message received.\n"); + dev_dbg(&dev->dev, "hbm: client dma map response: message received.\n"); client_dma_res = (struct hbm_client_dma_response *)mei_msg; mei_hbm_cl_dma_map_res(dev, client_dma_res); break; case MEI_HBM_CLIENT_DMA_UNMAP_RES_CMD: - dev_dbg(dev->dev, "hbm: client dma unmap response: message received.\n"); + dev_dbg(&dev->dev, "hbm: client dma unmap response: message received.\n"); client_dma_res = (struct hbm_client_dma_response *)mei_msg; mei_hbm_cl_dma_unmap_res(dev, client_dma_res); break; diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index d11a0740b47c..d4612c659784 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -84,7 +84,7 @@ static inline u32 mei_me_mecsr_read(const struct mei_device *dev) u32 reg; reg = mei_me_reg_read(to_me_hw(dev), ME_CSR_HA); - trace_mei_reg_read(dev->dev, "ME_CSR_HA", ME_CSR_HA, reg); + trace_mei_reg_read(&dev->dev, "ME_CSR_HA", ME_CSR_HA, reg); return reg; } @@ -101,7 +101,7 @@ static inline u32 mei_hcsr_read(const struct mei_device *dev) u32 reg; reg = mei_me_reg_read(to_me_hw(dev), H_CSR); - trace_mei_reg_read(dev->dev, "H_CSR", H_CSR, reg); + trace_mei_reg_read(&dev->dev, "H_CSR", H_CSR, reg); return reg; } @@ -114,7 +114,7 @@ static inline u32 mei_hcsr_read(const struct mei_device *dev) */ static inline void mei_hcsr_write(struct mei_device *dev, u32 reg) { - trace_mei_reg_write(dev->dev, "H_CSR", H_CSR, reg); + trace_mei_reg_write(&dev->dev, "H_CSR", H_CSR, reg); mei_me_reg_write(to_me_hw(dev), H_CSR, reg); } @@ -156,7 +156,7 @@ static inline u32 mei_me_d0i3c_read(const struct mei_device *dev) u32 reg; reg = mei_me_reg_read(to_me_hw(dev), H_D0I3C); - trace_mei_reg_read(dev->dev, "H_D0I3C", H_D0I3C, reg); + trace_mei_reg_read(&dev->dev, "H_D0I3C", H_D0I3C, reg); return reg; } @@ -169,7 +169,7 @@ static inline u32 mei_me_d0i3c_read(const struct mei_device *dev) */ static inline void mei_me_d0i3c_write(struct mei_device *dev, u32 reg) { - trace_mei_reg_write(dev->dev, "H_D0I3C", H_D0I3C, reg); + trace_mei_reg_write(&dev->dev, "H_D0I3C", H_D0I3C, reg); mei_me_reg_write(to_me_hw(dev), H_D0I3C, reg); } @@ -189,7 +189,7 @@ static int mei_me_trc_status(struct mei_device *dev, u32 *trc) return -EOPNOTSUPP; *trc = mei_me_reg_read(hw, ME_TRC); - trace_mei_reg_read(dev->dev, "ME_TRC", ME_TRC, *trc); + trace_mei_reg_read(&dev->dev, "ME_TRC", ME_TRC, *trc); return 0; } @@ -217,7 +217,7 @@ static int mei_me_fw_status(struct mei_device *dev, for (i = 0; i < fw_src->count && i < MEI_FW_STATUS_MAX; i++) { ret = hw->read_fws(dev, fw_src->status[i], &fw_status->status[i]); - trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HFS_X", + trace_mei_pci_cfg_read(&dev->dev, "PCI_CFG_HFS_X", fw_src->status[i], fw_status->status[i]); if (ret) @@ -251,7 +251,7 @@ static int mei_me_hw_config(struct mei_device *dev) reg = 0; hw->read_fws(dev, PCI_CFG_HFS_1, ®); - trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HFS_1", PCI_CFG_HFS_1, reg); + trace_mei_pci_cfg_read(&dev->dev, "PCI_CFG_HFS_1", PCI_CFG_HFS_1, reg); hw->d0i3_supported = ((reg & PCI_CFG_HFS_1_D0I3_MSK) == PCI_CFG_HFS_1_D0I3_MSK); @@ -447,7 +447,7 @@ static void mei_gsc_pxp_check(struct mei_device *dev) return; hw->read_fws(dev, PCI_CFG_HFS_5, &fwsts5); - trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HFS_5", PCI_CFG_HFS_5, fwsts5); + trace_mei_pci_cfg_read(&dev->dev, "PCI_CFG_HFS_5", PCI_CFG_HFS_5, fwsts5); if ((fwsts5 & GSC_CFG_HFS_5_BOOT_TYPE_MSK) == GSC_CFG_HFS_5_BOOT_TYPE_PXP) { if (dev->gsc_reset_to_pxp == MEI_DEV_RESET_TO_PXP_DEFAULT) @@ -460,10 +460,10 @@ static void mei_gsc_pxp_check(struct mei_device *dev) return; if ((fwsts5 & GSC_CFG_HFS_5_BOOT_TYPE_MSK) == GSC_CFG_HFS_5_BOOT_TYPE_PXP) { - dev_dbg(dev->dev, "pxp mode is ready 0x%08x\n", fwsts5); + dev_dbg(&dev->dev, "pxp mode is ready 0x%08x\n", fwsts5); dev->pxp_mode = MEI_DEV_PXP_READY; } else { - dev_dbg(dev->dev, "pxp mode is not ready 0x%08x\n", fwsts5); + dev_dbg(&dev->dev, "pxp mode is not ready 0x%08x\n", fwsts5); } } @@ -482,7 +482,7 @@ static int mei_me_hw_ready_wait(struct mei_device *dev) dev->timeouts.hw_ready); mutex_lock(&dev->device_lock); if (!dev->recvd_hw_ready) { - dev_err(dev->dev, "wait hw ready failed\n"); + dev_err(&dev->dev, "wait hw ready failed\n"); return -ETIME; } @@ -494,43 +494,6 @@ static int mei_me_hw_ready_wait(struct mei_device *dev) } /** - * mei_me_check_fw_reset - check for the firmware reset error and exception conditions - * - * @dev: mei device - */ -static void mei_me_check_fw_reset(struct mei_device *dev) -{ - struct mei_fw_status fw_status; - char fw_sts_str[MEI_FW_STATUS_STR_SZ] = {0}; - int ret; - u32 fw_pm_event = 0; - - if (!dev->saved_fw_status_flag) - goto end; - - if (dev->gsc_reset_to_pxp == MEI_DEV_RESET_TO_PXP_PERFORMED) { - ret = mei_fw_status(dev, &fw_status); - if (!ret) { - fw_pm_event = fw_status.status[1] & PCI_CFG_HFS_2_PM_EVENT_MASK; - if (fw_pm_event != PCI_CFG_HFS_2_PM_CMOFF_TO_CMX_ERROR && - fw_pm_event != PCI_CFG_HFS_2_PM_CM_RESET_ERROR) - goto end; - } else { - dev_err(dev->dev, "failed to read firmware status: %d\n", ret); - } - } - - mei_fw_status2str(&dev->saved_fw_status, fw_sts_str, sizeof(fw_sts_str)); - dev_warn(dev->dev, "unexpected reset: fw_pm_event = 0x%x, dev_state = %u fw status = %s\n", - fw_pm_event, dev->saved_dev_state, fw_sts_str); - -end: - if (dev->gsc_reset_to_pxp == MEI_DEV_RESET_TO_PXP_PERFORMED) - dev->gsc_reset_to_pxp = MEI_DEV_RESET_TO_PXP_DONE; - dev->saved_fw_status_flag = false; -} - -/** * mei_me_hw_start - hw start routine * * @dev: mei device @@ -540,11 +503,12 @@ static int mei_me_hw_start(struct mei_device *dev) { int ret = mei_me_hw_ready_wait(dev); - if (kind_is_gsc(dev) || kind_is_gscfi(dev)) - mei_me_check_fw_reset(dev); + if ((kind_is_gsc(dev) || kind_is_gscfi(dev)) && + dev->gsc_reset_to_pxp == MEI_DEV_RESET_TO_PXP_PERFORMED) + dev->gsc_reset_to_pxp = MEI_DEV_RESET_TO_PXP_DONE; if (ret) return ret; - dev_dbg(dev->dev, "hw is ready\n"); + dev_dbg(&dev->dev, "hw is ready\n"); mei_me_host_set_ready(dev); return ret; @@ -644,14 +608,14 @@ static int mei_me_hbuf_write(struct mei_device *dev, return -EINVAL; if (!data && data_len) { - dev_err(dev->dev, "wrong parameters null data with data_len = %zu\n", data_len); + dev_err(&dev->dev, "wrong parameters null data with data_len = %zu\n", data_len); return -EINVAL; } - dev_dbg(dev->dev, MEI_HDR_FMT, MEI_HDR_PRM((struct mei_msg_hdr *)hdr)); + dev_dbg(&dev->dev, MEI_HDR_FMT, MEI_HDR_PRM((struct mei_msg_hdr *)hdr)); empty_slots = mei_hbuf_empty_slots(dev); - dev_dbg(dev->dev, "empty slots = %d.\n", empty_slots); + dev_dbg(&dev->dev, "empty slots = %d.\n", empty_slots); if (empty_slots < 0) return -EOVERFLOW; @@ -706,7 +670,7 @@ static int mei_me_count_full_read_slots(struct mei_device *dev) if (filled_slots > buffer_depth) return -EOVERFLOW; - dev_dbg(dev->dev, "filled_slots =%08x\n", filled_slots); + dev_dbg(&dev->dev, "filled_slots =%08x\n", filled_slots); return (int)filled_slots; } @@ -748,11 +712,11 @@ static void mei_me_pg_set(struct mei_device *dev) u32 reg; reg = mei_me_reg_read(hw, H_HPG_CSR); - trace_mei_reg_read(dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); + trace_mei_reg_read(&dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); reg |= H_HPG_CSR_PGI; - trace_mei_reg_write(dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); + trace_mei_reg_write(&dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); mei_me_reg_write(hw, H_HPG_CSR, reg); } @@ -767,13 +731,13 @@ static void mei_me_pg_unset(struct mei_device *dev) u32 reg; reg = mei_me_reg_read(hw, H_HPG_CSR); - trace_mei_reg_read(dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); + trace_mei_reg_read(&dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); WARN(!(reg & H_HPG_CSR_PGI), "PGI is not set\n"); reg |= H_HPG_CSR_PGIHEXR; - trace_mei_reg_write(dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); + trace_mei_reg_write(&dev->dev, "H_HPG_CSR", H_HPG_CSR, reg); mei_me_reg_write(hw, H_HPG_CSR, reg); } @@ -905,7 +869,7 @@ static bool mei_me_pg_is_enabled(struct mei_device *dev) return true; notsupported: - dev_dbg(dev->dev, "pg: not supported: d0i3 = %d HGP = %d hbm version %d.%d ?= %d.%d\n", + dev_dbg(&dev->dev, "pg: not supported: d0i3 = %d HGP = %d hbm version %d.%d ?= %d.%d\n", hw->d0i3_supported, !!(reg & ME_PGIC_HRA), dev->version.major_version, @@ -974,7 +938,7 @@ static int mei_me_d0i3_enter_sync(struct mei_device *dev) reg = mei_me_d0i3c_read(dev); if (reg & H_D0I3C_I3) { /* we are in d0i3, nothing to do */ - dev_dbg(dev->dev, "d0i3 set not needed\n"); + dev_dbg(&dev->dev, "d0i3 set not needed\n"); ret = 0; goto on; } @@ -1003,7 +967,7 @@ static int mei_me_d0i3_enter_sync(struct mei_device *dev) reg = mei_me_d0i3_set(dev, true); if (!(reg & H_D0I3C_CIP)) { - dev_dbg(dev->dev, "d0i3 enter wait not needed\n"); + dev_dbg(&dev->dev, "d0i3 enter wait not needed\n"); ret = 0; goto on; } @@ -1027,7 +991,7 @@ on: hw->pg_state = MEI_PG_ON; out: dev->pg_event = MEI_PG_EVENT_IDLE; - dev_dbg(dev->dev, "d0i3 enter ret = %d\n", ret); + dev_dbg(&dev->dev, "d0i3 enter ret = %d\n", ret); return ret; } @@ -1049,7 +1013,7 @@ static int mei_me_d0i3_enter(struct mei_device *dev) reg = mei_me_d0i3c_read(dev); if (reg & H_D0I3C_I3) { /* we are in d0i3, nothing to do */ - dev_dbg(dev->dev, "already d0i3 : set not needed\n"); + dev_dbg(&dev->dev, "already d0i3 : set not needed\n"); goto on; } @@ -1057,7 +1021,7 @@ static int mei_me_d0i3_enter(struct mei_device *dev) on: hw->pg_state = MEI_PG_ON; dev->pg_event = MEI_PG_EVENT_IDLE; - dev_dbg(dev->dev, "d0i3 enter\n"); + dev_dbg(&dev->dev, "d0i3 enter\n"); return 0; } @@ -1079,14 +1043,14 @@ static int mei_me_d0i3_exit_sync(struct mei_device *dev) reg = mei_me_d0i3c_read(dev); if (!(reg & H_D0I3C_I3)) { /* we are not in d0i3, nothing to do */ - dev_dbg(dev->dev, "d0i3 exit not needed\n"); + dev_dbg(&dev->dev, "d0i3 exit not needed\n"); ret = 0; goto off; } reg = mei_me_d0i3_unset(dev); if (!(reg & H_D0I3C_CIP)) { - dev_dbg(dev->dev, "d0i3 exit wait not needed\n"); + dev_dbg(&dev->dev, "d0i3 exit wait not needed\n"); ret = 0; goto off; } @@ -1111,7 +1075,7 @@ off: out: dev->pg_event = MEI_PG_EVENT_IDLE; - dev_dbg(dev->dev, "d0i3 exit ret = %d\n", ret); + dev_dbg(&dev->dev, "d0i3 exit ret = %d\n", ret); return ret; } @@ -1154,7 +1118,7 @@ static void mei_me_d0i3_intr(struct mei_device *dev, u32 intr_source) * force H_RDY because it could be * wiped off during PG */ - dev_dbg(dev->dev, "d0i3 set host ready\n"); + dev_dbg(&dev->dev, "d0i3 set host ready\n"); mei_me_host_set_ready(dev); } } else { @@ -1170,7 +1134,7 @@ static void mei_me_d0i3_intr(struct mei_device *dev, u32 intr_source) * we got here because of HW initiated exit from D0i3. * Start runtime pm resume sequence to exit low power state. */ - dev_dbg(dev->dev, "d0i3 want resume\n"); + dev_dbg(&dev->dev, "d0i3 want resume\n"); mei_hbm_pg_resume(dev); } } @@ -1250,7 +1214,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) } } - pm_runtime_set_active(dev->dev); + pm_runtime_set_active(dev->parent); hcsr = mei_hcsr_read(dev); /* H_RST may be found lit before reset is started, @@ -1259,7 +1223,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) * we need to clean H_RST bit to start a successful reset sequence. */ if ((hcsr & H_RST) == H_RST) { - dev_warn(dev->dev, "H_RST is set = 0x%08X", hcsr); + dev_warn(&dev->dev, "H_RST is set = 0x%08X", hcsr); hcsr &= ~H_RST; mei_hcsr_set(dev, hcsr); hcsr = mei_hcsr_read(dev); @@ -1280,10 +1244,10 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) hcsr = mei_hcsr_read(dev); if ((hcsr & H_RST) == 0) - dev_warn(dev->dev, "H_RST is not set = 0x%08X", hcsr); + dev_warn(&dev->dev, "H_RST is not set = 0x%08X", hcsr); if ((hcsr & H_RDY) == H_RDY) - dev_warn(dev->dev, "H_RDY is not cleared 0x%08X", hcsr); + dev_warn(&dev->dev, "H_RDY is not cleared 0x%08X", hcsr); if (!intr_enable) { mei_me_hw_reset_release(dev); @@ -1313,7 +1277,7 @@ irqreturn_t mei_me_irq_quick_handler(int irq, void *dev_id) if (!me_intr_src(hcsr)) return IRQ_NONE; - dev_dbg(dev->dev, "interrupt source 0x%08X\n", me_intr_src(hcsr)); + dev_dbg(&dev->dev, "interrupt source 0x%08X\n", me_intr_src(hcsr)); /* disable interrupts on device */ me_intr_disable(dev, hcsr); @@ -1339,7 +1303,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) u32 hcsr; int rets = 0; - dev_dbg(dev->dev, "function called after ISR to handle the interrupt processing.\n"); + dev_dbg(&dev->dev, "function called after ISR to handle the interrupt processing.\n"); /* initialize our complete list */ mutex_lock(&dev->device_lock); @@ -1351,10 +1315,10 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) /* check if ME wants a reset */ if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) { if (kind_is_gsc(dev) || kind_is_gscfi(dev)) { - dev_dbg(dev->dev, "FW not ready: resetting: dev_state = %d\n", + dev_dbg(&dev->dev, "FW not ready: resetting: dev_state = %d\n", dev->dev_state); } else { - dev_warn(dev->dev, "FW not ready: resetting: dev_state = %d\n", + dev_warn(&dev->dev, "FW not ready: resetting: dev_state = %d\n", dev->dev_state); } if (dev->dev_state == MEI_DEV_POWERING_DOWN || @@ -1373,18 +1337,29 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) /* check if we need to start the dev */ if (!mei_host_is_ready(dev)) { if (mei_hw_is_ready(dev)) { - dev_dbg(dev->dev, "we need to start the dev.\n"); - dev->recvd_hw_ready = true; - wake_up(&dev->wait_hw_ready); + /* synchronized by dev mutex */ + if (waitqueue_active(&dev->wait_hw_ready)) { + dev_dbg(&dev->dev, "we need to start the dev.\n"); + dev->recvd_hw_ready = true; + wake_up(&dev->wait_hw_ready); + } else if (dev->dev_state != MEI_DEV_UNINITIALIZED && + dev->dev_state != MEI_DEV_POWERING_DOWN && + dev->dev_state != MEI_DEV_POWER_DOWN) { + dev_dbg(&dev->dev, "Force link reset.\n"); + schedule_work(&dev->reset_work); + } else { + dev_dbg(&dev->dev, "Ignore this interrupt in state = %d\n", + dev->dev_state); + } } else { - dev_dbg(dev->dev, "Spurious Interrupt\n"); + dev_dbg(&dev->dev, "Spurious Interrupt\n"); } goto end; } /* check slots available for reading */ slots = mei_count_full_read_slots(dev); while (slots > 0) { - dev_dbg(dev->dev, "slots to read = %08x\n", slots); + dev_dbg(&dev->dev, "slots to read = %08x\n", slots); rets = mei_irq_read_handler(dev, &cmpl_list, &slots); /* There is a race between ME write and interrupt delivery: * Not all data is always available immediately after the @@ -1394,7 +1369,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) break; if (rets) { - dev_err(dev->dev, "mei_irq_read_handler ret = %d, state = %d.\n", + dev_err(&dev->dev, "mei_irq_read_handler ret = %d, state = %d.\n", rets, dev->dev_state); if (dev->dev_state != MEI_DEV_RESETTING && dev->dev_state != MEI_DEV_DISABLED && @@ -1421,7 +1396,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) mei_irq_compl_handler(dev, &cmpl_list); end: - dev_dbg(dev->dev, "interrupt thread end ret = %d\n", rets); + dev_dbg(&dev->dev, "interrupt thread end ret = %d\n", rets); mei_me_intr_enable(dev); mutex_unlock(&dev->device_lock); return IRQ_HANDLED; @@ -1453,7 +1428,7 @@ int mei_me_polling_thread(void *_dev) irqreturn_t irq_ret; long polling_timeout = MEI_POLLING_TIMEOUT_ACTIVE; - dev_dbg(dev->dev, "kernel thread is running\n"); + dev_dbg(&dev->dev, "kernel thread is running\n"); while (!kthread_should_stop()) { struct mei_me_hw *hw = to_me_hw(dev); u32 hcsr; @@ -1470,7 +1445,7 @@ int mei_me_polling_thread(void *_dev) polling_timeout = MEI_POLLING_TIMEOUT_ACTIVE; irq_ret = mei_me_irq_thread_handler(1, dev); if (irq_ret != IRQ_HANDLED) - dev_err(dev->dev, "irq_ret %d\n", irq_ret); + dev_err(&dev->dev, "irq_ret %d\n", irq_ret); } else { /* * Increase timeout by MEI_POLLING_TIMEOUT_ACTIVE @@ -1804,7 +1779,7 @@ struct mei_device *mei_me_dev_init(struct device *parent, struct mei_me_hw *hw; int i; - dev = devm_kzalloc(parent, sizeof(*dev) + sizeof(*hw), GFP_KERNEL); + dev = kzalloc(sizeof(*dev) + sizeof(*hw), GFP_KERNEL); if (!dev) return NULL; diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c index e9476f9ae25d..e4688c391027 100644 --- a/drivers/misc/mei/hw-txe.c +++ b/drivers/misc/mei/hw-txe.c @@ -160,7 +160,7 @@ static bool mei_txe_aliveness_set(struct mei_device *dev, u32 req) struct mei_txe_hw *hw = to_txe_hw(dev); bool do_req = hw->aliveness != req; - dev_dbg(dev->dev, "Aliveness current=%d request=%d\n", + dev_dbg(&dev->dev, "Aliveness current=%d request=%d\n", hw->aliveness, req); if (do_req) { dev->pg_event = MEI_PG_EVENT_WAIT; @@ -227,7 +227,7 @@ static int mei_txe_aliveness_poll(struct mei_device *dev, u32 expected) hw->aliveness = mei_txe_aliveness_get(dev); if (hw->aliveness == expected) { dev->pg_event = MEI_PG_EVENT_IDLE; - dev_dbg(dev->dev, "aliveness settled after %lld usecs\n", + dev_dbg(&dev->dev, "aliveness settled after %lld usecs\n", ktime_to_us(ktime_sub(ktime_get(), start))); return 0; } @@ -235,7 +235,7 @@ static int mei_txe_aliveness_poll(struct mei_device *dev, u32 expected) } while (ktime_before(ktime_get(), stop)); dev->pg_event = MEI_PG_EVENT_IDLE; - dev_err(dev->dev, "aliveness timed out\n"); + dev_err(&dev->dev, "aliveness timed out\n"); return -ETIME; } @@ -270,10 +270,10 @@ static int mei_txe_aliveness_wait(struct mei_device *dev, u32 expected) ret = hw->aliveness == expected ? 0 : -ETIME; if (ret) - dev_warn(dev->dev, "aliveness timed out = %ld aliveness = %d event = %d\n", + dev_warn(&dev->dev, "aliveness timed out = %ld aliveness = %d event = %d\n", err, hw->aliveness, dev->pg_event); else - dev_dbg(dev->dev, "aliveness settled after = %d msec aliveness = %d event = %d\n", + dev_dbg(&dev->dev, "aliveness settled after = %d msec aliveness = %d event = %d\n", jiffies_to_msecs(timeout - err), hw->aliveness, dev->pg_event); @@ -438,7 +438,7 @@ static void mei_txe_intr_enable(struct mei_device *dev) */ static void mei_txe_synchronize_irq(struct mei_device *dev) { - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev->parent); synchronize_irq(pdev->irq); } @@ -464,7 +464,7 @@ static bool mei_txe_pending_interrupts(struct mei_device *dev) TXE_INTR_OUT_DB)); if (ret) { - dev_dbg(dev->dev, + dev_dbg(&dev->dev, "Pending Interrupts InReady=%01d Readiness=%01d, Aliveness=%01d, OutDoor=%01d\n", !!(hw->intr_cause & TXE_INTR_IN_READY), !!(hw->intr_cause & TXE_INTR_READINESS), @@ -612,7 +612,7 @@ static int mei_txe_readiness_wait(struct mei_device *dev) msecs_to_jiffies(SEC_RESET_WAIT_TIMEOUT)); mutex_lock(&dev->device_lock); if (!dev->recvd_hw_ready) { - dev_err(dev->dev, "wait for readiness failed\n"); + dev_err(&dev->dev, "wait for readiness failed\n"); return -ETIME; } @@ -638,7 +638,7 @@ static int mei_txe_fw_status(struct mei_device *dev, struct mei_fw_status *fw_status) { const struct mei_fw_status *fw_src = &mei_txe_fw_sts; - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev->parent); int ret; int i; @@ -649,7 +649,7 @@ static int mei_txe_fw_status(struct mei_device *dev, for (i = 0; i < fw_src->count && i < MEI_FW_STATUS_MAX; i++) { ret = pci_read_config_dword(pdev, fw_src->status[i], &fw_status->status[i]); - trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HSF_X", + trace_mei_pci_cfg_read(&dev->dev, "PCI_CFG_HSF_X", fw_src->status[i], fw_status->status[i]); if (ret) @@ -677,7 +677,7 @@ static int mei_txe_hw_config(struct mei_device *dev) hw->aliveness = mei_txe_aliveness_get(dev); hw->readiness = mei_txe_readiness_get(dev); - dev_dbg(dev->dev, "aliveness_resp = 0x%08x, readiness = 0x%08x.\n", + dev_dbg(&dev->dev, "aliveness_resp = 0x%08x, readiness = 0x%08x.\n", hw->aliveness, hw->readiness); return 0; @@ -708,7 +708,7 @@ static int mei_txe_write(struct mei_device *dev, if (WARN_ON(!hdr || !data || hdr_len & 0x3)) return -EINVAL; - dev_dbg(dev->dev, MEI_HDR_FMT, MEI_HDR_PRM((struct mei_msg_hdr *)hdr)); + dev_dbg(&dev->dev, MEI_HDR_FMT, MEI_HDR_PRM((struct mei_msg_hdr *)hdr)); dw_cnt = mei_data2slots(hdr_len + data_len); if (dw_cnt > slots) @@ -724,7 +724,7 @@ static int mei_txe_write(struct mei_device *dev, char fw_sts_str[MEI_FW_STATUS_STR_SZ]; mei_fw_status_str(dev, fw_sts_str, MEI_FW_STATUS_STR_SZ); - dev_err(dev->dev, "Input is not ready %s\n", fw_sts_str); + dev_err(&dev->dev, "Input is not ready %s\n", fw_sts_str); return -EAGAIN; } @@ -828,13 +828,13 @@ static int mei_txe_read(struct mei_device *dev, reg_buf = (u32 *)buf; rem = len & 0x3; - dev_dbg(dev->dev, "buffer-length = %lu buf[0]0x%08X\n", + dev_dbg(&dev->dev, "buffer-length = %lu buf[0]0x%08X\n", len, mei_txe_out_data_read(dev, 0)); for (i = 0; i < len / MEI_SLOT_SIZE; i++) { /* skip header: index starts from 1 */ reg = mei_txe_out_data_read(dev, i + 1); - dev_dbg(dev->dev, "buf[%d] = 0x%08X\n", i, reg); + dev_dbg(&dev->dev, "buf[%d] = 0x%08X\n", i, reg); *reg_buf++ = reg; } @@ -879,7 +879,7 @@ static int mei_txe_hw_reset(struct mei_device *dev, bool intr_enable) */ if (aliveness_req != hw->aliveness) if (mei_txe_aliveness_poll(dev, aliveness_req) < 0) { - dev_err(dev->dev, "wait for aliveness settle failed ... bailing out\n"); + dev_err(&dev->dev, "wait for aliveness settle failed ... bailing out\n"); return -EIO; } @@ -889,7 +889,7 @@ static int mei_txe_hw_reset(struct mei_device *dev, bool intr_enable) if (aliveness_req) { mei_txe_aliveness_set(dev, 0); if (mei_txe_aliveness_poll(dev, 0) < 0) { - dev_err(dev->dev, "wait for aliveness failed ... bailing out\n"); + dev_err(&dev->dev, "wait for aliveness failed ... bailing out\n"); return -EIO; } } @@ -921,7 +921,7 @@ static int mei_txe_hw_start(struct mei_device *dev) ret = mei_txe_readiness_wait(dev); if (ret < 0) { - dev_err(dev->dev, "waiting for readiness failed\n"); + dev_err(&dev->dev, "waiting for readiness failed\n"); return ret; } @@ -937,11 +937,11 @@ static int mei_txe_hw_start(struct mei_device *dev) ret = mei_txe_aliveness_set_sync(dev, 1); if (ret < 0) { - dev_err(dev->dev, "wait for aliveness failed ... bailing out\n"); + dev_err(&dev->dev, "wait for aliveness failed ... bailing out\n"); return ret; } - pm_runtime_set_active(dev->dev); + pm_runtime_set_active(dev->parent); /* enable input ready interrupts: * SEC_IPC_HOST_INT_MASK.IPC_INPUT_READY_INT_MASK @@ -1049,7 +1049,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) s32 slots; int rets = 0; - dev_dbg(dev->dev, "irq thread: Interrupt Registers HHISR|HISR|SEC=%02X|%04X|%02X\n", + dev_dbg(&dev->dev, "irq thread: Interrupt Registers HHISR|HISR|SEC=%02X|%04X|%02X\n", mei_txe_br_reg_read(hw, HHISR_REG), mei_txe_br_reg_read(hw, HISR_REG), mei_txe_sec_reg_read_silent(hw, SEC_IPC_HOST_INT_STATUS_REG)); @@ -1059,7 +1059,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) mutex_lock(&dev->device_lock); INIT_LIST_HEAD(&cmpl_list); - if (pci_dev_msi_enabled(to_pci_dev(dev->dev))) + if (pci_dev_msi_enabled(to_pci_dev(dev->parent))) mei_txe_check_and_ack_intrs(dev, true); /* show irq events */ @@ -1073,17 +1073,17 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) * or TXE driver resetting the HECI interface. */ if (test_and_clear_bit(TXE_INTR_READINESS_BIT, &hw->intr_cause)) { - dev_dbg(dev->dev, "Readiness Interrupt was received...\n"); + dev_dbg(&dev->dev, "Readiness Interrupt was received...\n"); /* Check if SeC is going through reset */ if (mei_txe_readiness_is_sec_rdy(hw->readiness)) { - dev_dbg(dev->dev, "we need to start the dev.\n"); + dev_dbg(&dev->dev, "we need to start the dev.\n"); dev->recvd_hw_ready = true; } else { dev->recvd_hw_ready = false; if (dev->dev_state != MEI_DEV_RESETTING) { - dev_warn(dev->dev, "FW not ready: resetting.\n"); + dev_warn(&dev->dev, "FW not ready: resetting.\n"); schedule_work(&dev->reset_work); goto end; @@ -1100,7 +1100,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) if (test_and_clear_bit(TXE_INTR_ALIVENESS_BIT, &hw->intr_cause)) { /* Clear the interrupt cause */ - dev_dbg(dev->dev, + dev_dbg(&dev->dev, "Aliveness Interrupt: Status: %d\n", hw->aliveness); dev->pg_event = MEI_PG_EVENT_RECEIVED; if (waitqueue_active(&hw->wait_aliveness_resp)) @@ -1118,7 +1118,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) if (rets && (dev->dev_state != MEI_DEV_RESETTING && dev->dev_state != MEI_DEV_POWER_DOWN)) { - dev_err(dev->dev, + dev_err(&dev->dev, "mei_irq_read_handler ret = %d.\n", rets); schedule_work(&dev->reset_work); @@ -1136,7 +1136,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) dev->hbuf_is_ready = mei_hbuf_is_ready(dev); rets = mei_irq_write_handler(dev, &cmpl_list); if (rets && rets != -EMSGSIZE) - dev_err(dev->dev, "mei_irq_write_handler ret = %d.\n", + dev_err(&dev->dev, "mei_irq_write_handler ret = %d.\n", rets); dev->hbuf_is_ready = mei_hbuf_is_ready(dev); } @@ -1144,7 +1144,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id) mei_irq_compl_handler(dev, &cmpl_list); end: - dev_dbg(dev->dev, "interrupt thread end ret = %d\n", rets); + dev_dbg(&dev->dev, "interrupt thread end ret = %d\n", rets); mutex_unlock(&dev->device_lock); @@ -1197,7 +1197,7 @@ struct mei_device *mei_txe_dev_init(struct pci_dev *pdev) struct mei_device *dev; struct mei_txe_hw *hw; - dev = devm_kzalloc(&pdev->dev, sizeof(*dev) + sizeof(*hw), GFP_KERNEL); + dev = kzalloc(sizeof(*dev) + sizeof(*hw), GFP_KERNEL); if (!dev) return NULL; diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index 2e9cf6f4efb6..3771aa09c592 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -27,6 +27,8 @@ #define MKHI_RCV_TIMEOUT 500 /* receive timeout in msec */ #define MKHI_RCV_TIMEOUT_SLOW 10000 /* receive timeout in msec, slow FW */ +#define MEI_LINK_RESET_WAIT_TIMEOUT_MSEC 500 /* Max wait timeout for link reset, in msec */ + /* * FW page size for DMA allocations */ diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index 8ef2b1df8ac7..b789c4d9c709 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -89,22 +89,6 @@ void mei_cancel_work(struct mei_device *dev) } EXPORT_SYMBOL_GPL(mei_cancel_work); -static void mei_save_fw_status(struct mei_device *dev) -{ - struct mei_fw_status fw_status; - int ret; - - ret = mei_fw_status(dev, &fw_status); - if (ret) { - dev_err(dev->dev, "failed to read firmware status: %d\n", ret); - return; - } - - dev->saved_dev_state = dev->dev_state; - dev->saved_fw_status_flag = true; - memcpy(&dev->saved_fw_status, &fw_status, sizeof(fw_status)); -} - /** * mei_reset - resets host and fw. * @@ -126,11 +110,10 @@ int mei_reset(struct mei_device *dev) mei_fw_status_str(dev, fw_sts_str, MEI_FW_STATUS_STR_SZ); if (kind_is_gsc(dev) || kind_is_gscfi(dev)) { - dev_dbg(dev->dev, "unexpected reset: dev_state = %s fw status = %s\n", + dev_dbg(&dev->dev, "unexpected reset: dev_state = %s fw status = %s\n", mei_dev_state_str(state), fw_sts_str); - mei_save_fw_status(dev); } else { - dev_warn(dev->dev, "unexpected reset: dev_state = %s fw status = %s\n", + dev_warn(&dev->dev, "unexpected reset: dev_state = %s fw status = %s\n", mei_dev_state_str(state), fw_sts_str); } } @@ -150,7 +133,7 @@ int mei_reset(struct mei_device *dev) dev->reset_count++; if (dev->reset_count > MEI_MAX_CONSEC_RESET) { - dev_err(dev->dev, "reset: reached maximal consecutive resets: disabling the device\n"); + dev_err(&dev->dev, "reset: reached maximal consecutive resets: disabling the device\n"); mei_set_devstate(dev, MEI_DEV_DISABLED); return -ENODEV; } @@ -170,12 +153,12 @@ int mei_reset(struct mei_device *dev) memset(dev->rd_msg_hdr, 0, sizeof(dev->rd_msg_hdr)); if (ret) { - dev_err(dev->dev, "hw_reset failed ret = %d\n", ret); + dev_err(&dev->dev, "hw_reset failed ret = %d\n", ret); return ret; } if (state == MEI_DEV_POWER_DOWN) { - dev_dbg(dev->dev, "powering down: end of reset\n"); + dev_dbg(&dev->dev, "powering down: end of reset\n"); mei_set_devstate(dev, MEI_DEV_DISABLED); return 0; } @@ -185,21 +168,21 @@ int mei_reset(struct mei_device *dev) char fw_sts_str[MEI_FW_STATUS_STR_SZ]; mei_fw_status_str(dev, fw_sts_str, MEI_FW_STATUS_STR_SZ); - dev_err(dev->dev, "hw_start failed ret = %d fw status = %s\n", ret, fw_sts_str); + dev_err(&dev->dev, "hw_start failed ret = %d fw status = %s\n", ret, fw_sts_str); return ret; } if (dev->dev_state != MEI_DEV_RESETTING) { - dev_dbg(dev->dev, "wrong state = %d on link start\n", dev->dev_state); + dev_dbg(&dev->dev, "wrong state = %d on link start\n", dev->dev_state); return 0; } - dev_dbg(dev->dev, "link is established start sending messages.\n"); + dev_dbg(&dev->dev, "link is established start sending messages.\n"); mei_set_devstate(dev, MEI_DEV_INIT_CLIENTS); ret = mei_hbm_start_req(dev); if (ret) { - dev_err(dev->dev, "hbm_start failed ret = %d\n", ret); + dev_err(&dev->dev, "hbm_start failed ret = %d\n", ret); mei_set_devstate(dev, MEI_DEV_RESETTING); return ret; } @@ -228,7 +211,7 @@ int mei_start(struct mei_device *dev) if (ret) goto err; - dev_dbg(dev->dev, "reset in start the mei device.\n"); + dev_dbg(&dev->dev, "reset in start the mei device.\n"); dev->reset_count = 0; do { @@ -236,27 +219,27 @@ int mei_start(struct mei_device *dev) ret = mei_reset(dev); if (ret == -ENODEV || dev->dev_state == MEI_DEV_DISABLED) { - dev_err(dev->dev, "reset failed ret = %d", ret); + dev_err(&dev->dev, "reset failed ret = %d", ret); goto err; } } while (ret); if (mei_hbm_start_wait(dev)) { - dev_err(dev->dev, "HBM haven't started"); + dev_err(&dev->dev, "HBM haven't started"); goto err; } if (!mei_hbm_version_is_supported(dev)) { - dev_dbg(dev->dev, "MEI start failed.\n"); + dev_dbg(&dev->dev, "MEI start failed.\n"); goto err; } - dev_dbg(dev->dev, "link layer has been established.\n"); + dev_dbg(&dev->dev, "link layer has been established.\n"); mutex_unlock(&dev->device_lock); return 0; err: - dev_err(dev->dev, "link layer initialization failed.\n"); + dev_err(&dev->dev, "link layer initialization failed.\n"); mei_set_devstate(dev, MEI_DEV_DISABLED); mutex_unlock(&dev->device_lock); return -ENODEV; @@ -284,7 +267,7 @@ int mei_restart(struct mei_device *dev) mutex_unlock(&dev->device_lock); if (err == -ENODEV || dev->dev_state == MEI_DEV_DISABLED) { - dev_err(dev->dev, "device disabled = %d\n", err); + dev_err(&dev->dev, "device disabled = %d\n", err); return -ENODEV; } @@ -313,7 +296,7 @@ static void mei_reset_work(struct work_struct *work) mutex_unlock(&dev->device_lock); if (dev->dev_state == MEI_DEV_DISABLED) { - dev_err(dev->dev, "device disabled = %d\n", ret); + dev_err(&dev->dev, "device disabled = %d\n", ret); return; } @@ -324,7 +307,7 @@ static void mei_reset_work(struct work_struct *work) void mei_stop(struct mei_device *dev) { - dev_dbg(dev->dev, "stopping the device.\n"); + dev_dbg(&dev->dev, "stopping the device.\n"); mutex_lock(&dev->device_lock); mei_set_devstate(dev, MEI_DEV_POWERING_DOWN); @@ -365,7 +348,7 @@ bool mei_write_is_idle(struct mei_device *dev) list_empty(&dev->write_list) && list_empty(&dev->write_waiting_list)); - dev_dbg(dev->dev, "write pg: is idle[%d] state=%s ctrl=%01d write=%01d wwait=%01d\n", + dev_dbg(&dev->dev, "write pg: is idle[%d] state=%s ctrl=%01d write=%01d wwait=%01d\n", idle, mei_dev_state_str(dev->dev_state), list_empty(&dev->ctrl_wr_list), @@ -380,12 +363,12 @@ EXPORT_SYMBOL_GPL(mei_write_is_idle); * mei_device_init - initialize mei_device structure * * @dev: the mei device - * @device: the device structure + * @parent: the parent device * @slow_fw: configure longer timeouts as FW is slow * @hw_ops: hw operations */ void mei_device_init(struct mei_device *dev, - struct device *device, + struct device *parent, bool slow_fw, const struct mei_hw_ops *hw_ops) { @@ -399,7 +382,8 @@ void mei_device_init(struct mei_device *dev, init_waitqueue_head(&dev->wait_hw_ready); init_waitqueue_head(&dev->wait_pg); init_waitqueue_head(&dev->wait_hbm_start); - dev->dev_state = MEI_DEV_INITIALIZING; + dev->dev_state = MEI_DEV_UNINITIALIZED; + init_waitqueue_head(&dev->wait_dev_state); dev->reset_count = 0; INIT_LIST_HEAD(&dev->write_list); @@ -426,7 +410,7 @@ void mei_device_init(struct mei_device *dev, dev->pg_event = MEI_PG_EVENT_IDLE; dev->ops = hw_ops; - dev->dev = device; + dev->parent = parent; dev->timeouts.hw_ready = mei_secs_to_jiffies(MEI_HW_READY_TIMEOUT); dev->timeouts.connect = MEI_CONNECT_TIMEOUT; @@ -442,6 +426,6 @@ void mei_device_init(struct mei_device *dev, dev->timeouts.hbm = mei_secs_to_jiffies(MEI_HBM_TIMEOUT); dev->timeouts.mkhi_recv = msecs_to_jiffies(MKHI_RCV_TIMEOUT); } + dev->timeouts.link_reset_wait = msecs_to_jiffies(MEI_LINK_RESET_WAIT_TIMEOUT_MSEC); } EXPORT_SYMBOL_GPL(mei_device_init); - diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index d472f6bbe767..3aa66b6b0d36 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -76,7 +76,7 @@ static void mei_irq_discard_msg(struct mei_device *dev, struct mei_msg_hdr *hdr, * that length fits into rd_msg_buf */ mei_read_slots(dev, dev->rd_msg_buf, discard_len); - dev_dbg(dev->dev, "discarding message " MEI_HDR_FMT "\n", + dev_dbg(&dev->dev, "discarding message " MEI_HDR_FMT "\n", MEI_HDR_PRM(hdr)); } @@ -229,8 +229,8 @@ static int mei_cl_irq_read_msg(struct mei_cl *cl, cl_dbg(dev, cl, "completed read length = %zu\n", cb->buf_idx); list_move_tail(&cb->list, cmpl_list); } else { - pm_runtime_mark_last_busy(dev->dev); - pm_request_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_request_autosuspend(dev->parent); } return 0; @@ -310,8 +310,8 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb, return ret; } - pm_runtime_mark_last_busy(dev->dev); - pm_request_autosuspend(dev->dev); + pm_runtime_mark_last_busy(dev->parent); + pm_request_autosuspend(dev->parent); list_move_tail(&cb->list, &cl->rd_pending); @@ -373,21 +373,21 @@ int mei_irq_read_handler(struct mei_device *dev, dev->rd_msg_hdr[0] = mei_read_hdr(dev); dev->rd_msg_hdr_count = 1; (*slots)--; - dev_dbg(dev->dev, "slots =%08x.\n", *slots); + dev_dbg(&dev->dev, "slots =%08x.\n", *slots); ret = hdr_is_valid(dev->rd_msg_hdr[0]); if (ret) { - dev_err(dev->dev, "corrupted message header 0x%08X\n", + dev_err(&dev->dev, "corrupted message header 0x%08X\n", dev->rd_msg_hdr[0]); goto end; } } mei_hdr = (struct mei_msg_hdr *)dev->rd_msg_hdr; - dev_dbg(dev->dev, MEI_HDR_FMT, MEI_HDR_PRM(mei_hdr)); + dev_dbg(&dev->dev, MEI_HDR_FMT, MEI_HDR_PRM(mei_hdr)); if (mei_slots2data(*slots) < mei_hdr->length) { - dev_err(dev->dev, "less data available than length=%08x.\n", + dev_err(&dev->dev, "less data available than length=%08x.\n", *slots); /* we can't read the message */ ret = -ENODATA; @@ -402,18 +402,18 @@ int mei_irq_read_handler(struct mei_device *dev, dev->rd_msg_hdr[1] = mei_read_hdr(dev); dev->rd_msg_hdr_count++; (*slots)--; - dev_dbg(dev->dev, "extended header is %08x\n", dev->rd_msg_hdr[1]); + dev_dbg(&dev->dev, "extended header is %08x\n", dev->rd_msg_hdr[1]); } meta_hdr = ((struct mei_ext_meta_hdr *)&dev->rd_msg_hdr[1]); if (check_add_overflow((u32)sizeof(*meta_hdr), mei_slots2data(meta_hdr->size), &hdr_size_ext)) { - dev_err(dev->dev, "extended message size too big %d\n", + dev_err(&dev->dev, "extended message size too big %d\n", meta_hdr->size); return -EBADMSG; } if (hdr_size_left < hdr_size_ext) { - dev_err(dev->dev, "corrupted message header len %d\n", + dev_err(&dev->dev, "corrupted message header len %d\n", mei_hdr->length); return -EBADMSG; } @@ -422,7 +422,7 @@ int mei_irq_read_handler(struct mei_device *dev, ext_hdr_end = meta_hdr->size + 2; for (i = dev->rd_msg_hdr_count; i < ext_hdr_end; i++) { dev->rd_msg_hdr[i] = mei_read_hdr(dev); - dev_dbg(dev->dev, "extended header %d is %08x\n", i, + dev_dbg(&dev->dev, "extended header %d is %08x\n", i, dev->rd_msg_hdr[i]); dev->rd_msg_hdr_count++; (*slots)--; @@ -431,7 +431,7 @@ int mei_irq_read_handler(struct mei_device *dev, if (mei_hdr->dma_ring) { if (hdr_size_left != sizeof(dev->rd_msg_hdr[ext_hdr_end])) { - dev_err(dev->dev, "corrupted message header len %d\n", + dev_err(&dev->dev, "corrupted message header len %d\n", mei_hdr->length); return -EBADMSG; } @@ -446,8 +446,7 @@ int mei_irq_read_handler(struct mei_device *dev, if (hdr_is_hbm(mei_hdr)) { ret = mei_hbm_dispatch(dev, mei_hdr); if (ret) { - dev_dbg(dev->dev, "mei_hbm_dispatch failed ret = %d\n", - ret); + dev_dbg(&dev->dev, "mei_hbm_dispatch failed ret = %d\n", ret); goto end; } goto reset_slots; @@ -474,7 +473,7 @@ int mei_irq_read_handler(struct mei_device *dev, ret = 0; goto reset_slots; } - dev_err(dev->dev, "no destination client found 0x%08X\n", dev->rd_msg_hdr[0]); + dev_err(&dev->dev, "no destination client found 0x%08X\n", dev->rd_msg_hdr[0]); ret = -EBADMSG; goto end; @@ -485,7 +484,7 @@ reset_slots: *slots = mei_count_full_read_slots(dev); if (*slots == -EOVERFLOW) { /* overflow - reset */ - dev_err(dev->dev, "resetting due to slots overflow.\n"); + dev_err(&dev->dev, "resetting due to slots overflow.\n"); /* set the event since message has been read */ ret = -ERANGE; goto end; @@ -525,7 +524,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct list_head *cmpl_list) return -EMSGSIZE; /* complete all waiting for write CB */ - dev_dbg(dev->dev, "complete all waiting for write cb.\n"); + dev_dbg(&dev->dev, "complete all waiting for write cb.\n"); list_for_each_entry_safe(cb, next, &dev->write_waiting_list, list) { cl = cb->cl; @@ -537,7 +536,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct list_head *cmpl_list) } /* complete control write list CB */ - dev_dbg(dev->dev, "complete control write list cb.\n"); + dev_dbg(&dev->dev, "complete control write list cb.\n"); list_for_each_entry_safe(cb, next, &dev->ctrl_wr_list, list) { cl = cb->cl; switch (cb->fop_type) { @@ -591,7 +590,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct list_head *cmpl_list) } /* complete write list CB */ - dev_dbg(dev->dev, "complete write list cb.\n"); + dev_dbg(&dev->dev, "complete write list cb.\n"); list_for_each_entry_safe(cb, next, &dev->write_list, list) { cl = cb->cl; ret = mei_cl_irq_write(cl, cb, cmpl_list); @@ -656,7 +655,7 @@ void mei_timer(struct work_struct *work) if (dev->init_clients_timer) { if (--dev->init_clients_timer == 0) { - dev_err(dev->dev, "timer: init clients timeout hbm_state = %d.\n", + dev_err(&dev->dev, "timer: init clients timeout hbm_state = %d.\n", dev->hbm_state); mei_reset(dev); goto out; @@ -672,7 +671,7 @@ void mei_timer(struct work_struct *work) list_for_each_entry(cl, &dev->file_list, link) { if (cl->timer_count) { if (--cl->timer_count == 0) { - dev_err(dev->dev, "timer: connect/disconnect timeout.\n"); + dev_err(&dev->dev, "timer: connect/disconnect timeout.\n"); mei_connect_timeout(cl); goto out; } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 8a149a15b861..86a73684a373 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -51,12 +51,15 @@ static int mei_open(struct inode *inode, struct file *file) int err; - dev = container_of(inode->i_cdev, struct mei_device, cdev); + dev = idr_find(&mei_idr, iminor(inode)); + if (!dev) + return -ENODEV; + get_device(&dev->dev); mutex_lock(&dev->device_lock); if (dev->dev_state != MEI_DEV_ENABLED) { - dev_dbg(dev->dev, "dev_state != MEI_ENABLED dev_state = %s\n", + dev_dbg(&dev->dev, "dev_state != MEI_ENABLED dev_state = %s\n", mei_dev_state_str(dev->dev_state)); err = -ENODEV; goto err_unlock; @@ -77,6 +80,7 @@ static int mei_open(struct inode *inode, struct file *file) err_unlock: mutex_unlock(&dev->device_lock); + put_device(&dev->dev); return err; } @@ -152,6 +156,7 @@ out: file->private_data = NULL; mutex_unlock(&dev->device_lock); + put_device(&dev->dev); return rets; } @@ -418,6 +423,7 @@ static int mei_ioctl_connect_client(struct file *file, cl->state != MEI_FILE_DISCONNECTED) return -EBUSY; +retry: /* find ME client we're trying to connect to */ me_cl = mei_me_cl_by_uuid(dev, in_client_uuid); if (!me_cl) { @@ -449,6 +455,28 @@ static int mei_ioctl_connect_client(struct file *file, rets = mei_cl_connect(cl, me_cl, file); + if (rets && cl->status == -EFAULT && + (dev->dev_state == MEI_DEV_RESETTING || + dev->dev_state == MEI_DEV_INIT_CLIENTS)) { + /* in link reset, wait for it completion */ + mutex_unlock(&dev->device_lock); + rets = wait_event_interruptible_timeout(dev->wait_dev_state, + dev->dev_state == MEI_DEV_ENABLED, + dev->timeouts.link_reset_wait); + mutex_lock(&dev->device_lock); + if (rets < 0) { + if (signal_pending(current)) + rets = -EINTR; + goto end; + } + if (dev->dev_state != MEI_DEV_ENABLED) { + rets = -ETIME; + goto end; + } + mei_me_cl_put(me_cl); + goto retry; + } + end: mei_me_cl_put(me_cl); return rets; @@ -477,7 +505,7 @@ static int mei_vt_support_check(struct mei_device *dev, const uuid_le *uuid) me_cl = mei_me_cl_by_uuid(dev, uuid); if (!me_cl) { - dev_dbg(dev->dev, "Cannot connect to FW Client UUID = %pUl\n", + dev_dbg(&dev->dev, "Cannot connect to FW Client UUID = %pUl\n", uuid); return -ENOTTY; } @@ -641,7 +669,7 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data) struct mei_cl *cl = file->private_data; struct mei_connect_client_data conn; struct mei_connect_client_data_vtag conn_vtag; - const uuid_le *cl_uuid; + uuid_le cl_uuid; struct mei_client *props; u8 vtag; u32 notify_get, notify_req; @@ -669,18 +697,18 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data) rets = -EFAULT; goto out; } - cl_uuid = &conn.in_client_uuid; + cl_uuid = conn.in_client_uuid; props = &conn.out_client_properties; vtag = 0; - rets = mei_vt_support_check(dev, cl_uuid); + rets = mei_vt_support_check(dev, &cl_uuid); if (rets == -ENOTTY) goto out; if (!rets) - rets = mei_ioctl_connect_vtag(file, cl_uuid, props, + rets = mei_ioctl_connect_vtag(file, &cl_uuid, props, vtag); else - rets = mei_ioctl_connect_client(file, cl_uuid, props); + rets = mei_ioctl_connect_client(file, &cl_uuid, props); if (rets) goto out; @@ -702,14 +730,14 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data) goto out; } - cl_uuid = &conn_vtag.connect.in_client_uuid; + cl_uuid = conn_vtag.connect.in_client_uuid; props = &conn_vtag.out_client_properties; vtag = conn_vtag.connect.vtag; - rets = mei_vt_support_check(dev, cl_uuid); + rets = mei_vt_support_check(dev, &cl_uuid); if (rets == -EOPNOTSUPP) cl_dbg(dev, cl, "FW Client %pUl does not support vtags\n", - cl_uuid); + &cl_uuid); if (rets) goto out; @@ -719,7 +747,7 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data) goto out; } - rets = mei_ioctl_connect_vtag(file, cl_uuid, props, vtag); + rets = mei_ioctl_connect_vtag(file, &cl_uuid, props, vtag); if (rets) goto out; @@ -1115,7 +1143,12 @@ void mei_set_devstate(struct mei_device *dev, enum mei_dev_state state) dev->dev_state = state; - clsdev = class_find_device_by_devt(&mei_class, dev->cdev.dev); + wake_up_interruptible_all(&dev->wait_dev_state); + + if (!dev->cdev) + return; + + clsdev = class_find_device_by_devt(&mei_class, dev->cdev->dev); if (clsdev) { sysfs_notify(&clsdev->kobj, NULL, "dev_state"); put_device(clsdev); @@ -1191,7 +1224,7 @@ static int mei_minor_get(struct mei_device *dev) if (ret >= 0) dev->minor = ret; else if (ret == -ENOSPC) - dev_err(dev->dev, "too many mei devices\n"); + dev_err(&dev->dev, "too many mei devices\n"); mutex_unlock(&mei_minor_lock); return ret; @@ -1200,56 +1233,81 @@ static int mei_minor_get(struct mei_device *dev) /** * mei_minor_free - mark device minor number as free * - * @dev: device pointer + * @minor: minor number to free */ -static void mei_minor_free(struct mei_device *dev) +static void mei_minor_free(int minor) { mutex_lock(&mei_minor_lock); - idr_remove(&mei_idr, dev->minor); + idr_remove(&mei_idr, minor); mutex_unlock(&mei_minor_lock); } +static void mei_device_release(struct device *dev) +{ + kfree(dev_get_drvdata(dev)); +} + int mei_register(struct mei_device *dev, struct device *parent) { - struct device *clsdev; /* class device */ int ret, devno; + int minor; ret = mei_minor_get(dev); if (ret < 0) return ret; + minor = dev->minor; + /* Fill in the data structures */ devno = MKDEV(MAJOR(mei_devt), dev->minor); - cdev_init(&dev->cdev, &mei_fops); - dev->cdev.owner = parent->driver->owner; + + device_initialize(&dev->dev); + dev->dev.devt = devno; + dev->dev.class = &mei_class; + dev->dev.parent = parent; + dev->dev.groups = mei_groups; + dev->dev.release = mei_device_release; + dev_set_drvdata(&dev->dev, dev); + + dev->cdev = cdev_alloc(); + if (!dev->cdev) { + ret = -ENOMEM; + goto err; + } + dev->cdev->ops = &mei_fops; + dev->cdev->owner = parent->driver->owner; + cdev_set_parent(dev->cdev, &dev->dev.kobj); /* Add the device */ - ret = cdev_add(&dev->cdev, devno, 1); + ret = cdev_add(dev->cdev, devno, 1); if (ret) { - dev_err(parent, "unable to add device %d:%d\n", + dev_err(parent, "unable to add cdev for device %d:%d\n", MAJOR(mei_devt), dev->minor); - goto err_dev_add; + goto err_del_cdev; } - clsdev = device_create_with_groups(&mei_class, parent, devno, - dev, mei_groups, - "mei%d", dev->minor); + ret = dev_set_name(&dev->dev, "mei%d", dev->minor); + if (ret) { + dev_err(parent, "unable to set name to device %d:%d ret = %d\n", + MAJOR(mei_devt), dev->minor, ret); + goto err_del_cdev; + } - if (IS_ERR(clsdev)) { - dev_err(parent, "unable to create device %d:%d\n", - MAJOR(mei_devt), dev->minor); - ret = PTR_ERR(clsdev); - goto err_dev_create; + ret = device_add(&dev->dev); + if (ret) { + dev_err(parent, "unable to add device %d:%d ret = %d\n", + MAJOR(mei_devt), dev->minor, ret); + goto err_del_cdev; } - mei_dbgfs_register(dev, dev_name(clsdev)); + mei_dbgfs_register(dev, dev_name(&dev->dev)); return 0; -err_dev_create: - cdev_del(&dev->cdev); -err_dev_add: - mei_minor_free(dev); +err_del_cdev: + cdev_del(dev->cdev); +err: + mei_minor_free(minor); return ret; } EXPORT_SYMBOL_GPL(mei_register); @@ -1257,15 +1315,16 @@ EXPORT_SYMBOL_GPL(mei_register); void mei_deregister(struct mei_device *dev) { int devno; + int minor = dev->minor; - devno = dev->cdev.dev; - cdev_del(&dev->cdev); + devno = dev->cdev->dev; + cdev_del(dev->cdev); mei_dbgfs_deregister(dev); device_destroy(&mei_class, devno); - mei_minor_free(dev); + mei_minor_free(minor); } EXPORT_SYMBOL_GPL(mei_deregister); diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 37d7fb15cad7..0bf8d552c3ea 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -57,7 +57,8 @@ enum file_state { /* MEI device states */ enum mei_dev_state { - MEI_DEV_INITIALIZING = 0, + MEI_DEV_UNINITIALIZED = 0, + MEI_DEV_INITIALIZING, MEI_DEV_INIT_CLIENTS, MEI_DEV_ENABLED, MEI_DEV_RESETTING, @@ -465,13 +466,15 @@ struct mei_dev_timeouts { unsigned int d0i3; /* D0i3 set/unset max response time, in jiffies */ unsigned long hbm; /* HBM operation timeout, in jiffies */ unsigned long mkhi_recv; /* receive timeout, in jiffies */ + unsigned long link_reset_wait; /* link reset wait timeout, in jiffies */ }; /** * struct mei_device - MEI private device struct * - * @dev : device on a bus - * @cdev : character device + * @parent : device on a bus + * @dev : device object + * @cdev : character device pointer * @minor : minor number allocated for device * * @write_list : write pending list @@ -494,6 +497,7 @@ struct mei_dev_timeouts { * * @reset_count : number of consecutive resets * @dev_state : device state + * @wait_dev_state: wait queue for device state change * @hbm_state : state of host bus message protocol * @pxp_mode : PXP device mode * @init_clients_timer : HBM init handshake timeout @@ -547,17 +551,15 @@ struct mei_dev_timeouts { * * @dbgfs_dir : debugfs mei root directory * - * @saved_fw_status : saved firmware status - * @saved_dev_state : saved device state - * @saved_fw_status_flag : flag indicating that firmware status was saved * @gsc_reset_to_pxp : state of reset to the PXP mode * * @ops: : hw specific operations * @hw : hw specific data */ struct mei_device { - struct device *dev; - struct cdev cdev; + struct device *parent; + struct device dev; + struct cdev *cdev; int minor; struct list_head write_list; @@ -585,6 +587,7 @@ struct mei_device { */ unsigned long reset_count; enum mei_dev_state dev_state; + wait_queue_head_t wait_dev_state; enum mei_hbm_state hbm_state; enum mei_dev_pxp_mode pxp_mode; u16 init_clients_timer; @@ -648,9 +651,6 @@ struct mei_device { struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ - struct mei_fw_status saved_fw_status; - enum mei_dev_state saved_dev_state; - bool saved_fw_status_flag; enum mei_dev_reset_to_pxp gsc_reset_to_pxp; const struct mei_hw_ops *ops; @@ -703,7 +703,7 @@ static inline u32 mei_slots2data(int slots) * mei init function prototypes */ void mei_device_init(struct mei_device *dev, - struct device *device, + struct device *parent, bool slow_fw, const struct mei_hw_ops *hw_ops); int mei_reset(struct mei_device *dev); diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 3f9c60b579ae..b108a7c22388 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -143,7 +143,7 @@ static inline void mei_me_unset_pm_domain(struct mei_device *dev) {} static int mei_me_read_fws(const struct mei_device *dev, int where, u32 *val) { - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev->parent); return pci_read_config_dword(pdev, where, val); } @@ -238,19 +238,19 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto end; } + err = mei_register(dev, &pdev->dev); + if (err) + goto release_irq; + if (mei_start(dev)) { dev_err(&pdev->dev, "init hw failure.\n"); err = -ENODEV; - goto release_irq; + goto deregister; } pm_runtime_set_autosuspend_delay(&pdev->dev, MEI_ME_RPM_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); - err = mei_register(dev, &pdev->dev); - if (err) - goto stop; - pci_set_drvdata(pdev, dev); /* @@ -280,8 +280,8 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; -stop: - mei_stop(dev); +deregister: + mei_deregister(dev); release_irq: mei_cancel_work(dev); mei_disable_interrupts(dev); @@ -475,7 +475,7 @@ static int mei_me_pm_runtime_resume(struct device *device) */ static inline void mei_me_set_pm_domain(struct mei_device *dev) { - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev->parent); if (pdev->dev.bus && pdev->dev.bus->pm) { dev->pg_domain.ops = *pdev->dev.bus->pm; @@ -496,7 +496,7 @@ static inline void mei_me_set_pm_domain(struct mei_device *dev) static inline void mei_me_unset_pm_domain(struct mei_device *dev) { /* stop using pm callbacks if any */ - dev_pm_domain_set(dev->dev, NULL); + dev_pm_domain_set(dev->parent, NULL); } static const struct dev_pm_ops mei_me_pm_ops = { diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c index 2a584104ba38..c9eb5c5393e4 100644 --- a/drivers/misc/mei/pci-txe.c +++ b/drivers/misc/mei/pci-txe.c @@ -321,7 +321,7 @@ static int mei_txe_pm_runtime_resume(struct device *device) */ static inline void mei_txe_set_pm_domain(struct mei_device *dev) { - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev->parent); if (pdev->dev.bus && pdev->dev.bus->pm) { dev->pg_domain.ops = *pdev->dev.bus->pm; @@ -342,7 +342,7 @@ static inline void mei_txe_set_pm_domain(struct mei_device *dev) static inline void mei_txe_unset_pm_domain(struct mei_device *dev) { /* stop using pm callbacks if any */ - dev_pm_domain_set(dev->dev, NULL); + dev_pm_domain_set(dev->parent, NULL); } static const struct dev_pm_ops mei_txe_pm_ops = { diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index b2b5a20ae3fa..288e7b72e942 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -152,7 +152,7 @@ static int mei_vsc_hw_start(struct mei_device *mei_dev) MEI_VSC_POLL_TIMEOUT_US, true, hw, &buf, sizeof(buf)); if (ret) { - dev_err(mei_dev->dev, "wait fw ready failed: %d\n", ret); + dev_err(&mei_dev->dev, "wait fw ready failed: %d\n", ret); return ret; } @@ -259,7 +259,7 @@ static int mei_vsc_hw_reset(struct mei_device *mei_dev, bool intr_enable) if (!intr_enable) return 0; - return vsc_tp_init(hw->tp, mei_dev->dev); + return vsc_tp_init(hw->tp, mei_dev->parent); } static const struct mei_hw_ops mei_vsc_hw_ops = { @@ -325,7 +325,7 @@ static void mei_vsc_event_cb(void *context) mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev); ret = mei_irq_write_handler(mei_dev, &cmpl_list); if (ret) - dev_err(mei_dev->dev, "dispatch write request failed: %d\n", ret); + dev_err(&mei_dev->dev, "dispatch write request failed: %d\n", ret); mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev); mei_irq_compl_handler(mei_dev, &cmpl_list); @@ -343,12 +343,12 @@ static int mei_vsc_probe(struct platform_device *pdev) if (!tp) return dev_err_probe(dev, -ENODEV, "no platform data\n"); - mei_dev = devm_kzalloc(dev, size_add(sizeof(*mei_dev), sizeof(*hw)), - GFP_KERNEL); + mei_dev = kzalloc(size_add(sizeof(*mei_dev), sizeof(*hw)), GFP_KERNEL); if (!mei_dev) return -ENOMEM; mei_device_init(mei_dev, dev, false, &mei_vsc_hw_ops); + mei_dev->fw_f_fw_ver_supported = 0; mei_dev->kind = "ivsc"; @@ -360,22 +360,22 @@ static int mei_vsc_probe(struct platform_device *pdev) vsc_tp_register_event_cb(tp, mei_vsc_event_cb, mei_dev); + ret = mei_register(mei_dev, dev); + if (ret) + goto err_dereg; + ret = mei_start(mei_dev); if (ret) { dev_err_probe(dev, ret, "init hw failed\n"); goto err_cancel; } - ret = mei_register(mei_dev, dev); - if (ret) - goto err_stop; - - pm_runtime_enable(mei_dev->dev); + pm_runtime_enable(mei_dev->parent); return 0; -err_stop: - mei_stop(mei_dev); +err_dereg: + mei_deregister(mei_dev); err_cancel: mei_cancel_work(mei_dev); @@ -392,7 +392,7 @@ static void mei_vsc_remove(struct platform_device *pdev) struct mei_device *mei_dev = platform_get_drvdata(pdev); struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); - pm_runtime_disable(mei_dev->dev); + pm_runtime_disable(mei_dev->parent); mei_stop(mei_dev); diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 42878474e56e..60dbc815e501 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -99,6 +99,9 @@ #define HIWORD_UPDATE(val, mask, shift) \ ((val) << (shift) | (mask) << ((shift) + 16)) +#define CD_STABLE_TIMEOUT_US 1000000 +#define CD_STABLE_MAX_SLEEP_US 10 + /** * struct sdhci_arasan_soc_ctl_field - Field used in sdhci_arasan_soc_ctl_map * @@ -206,12 +209,15 @@ struct sdhci_arasan_data { * 19MHz instead */ #define SDHCI_ARASAN_QUIRK_CLOCK_25_BROKEN BIT(2) +/* Enable CD stable check before power-up */ +#define SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE BIT(3) }; struct sdhci_arasan_of_data { const struct sdhci_arasan_soc_ctl_map *soc_ctl_map; const struct sdhci_pltfm_data *pdata; const struct sdhci_arasan_clk_ops *clk_ops; + u32 quirks; }; static const struct sdhci_arasan_soc_ctl_map rk3399_soc_ctl_map = { @@ -514,6 +520,24 @@ static int sdhci_arasan_voltage_switch(struct mmc_host *mmc, return -EINVAL; } +static void sdhci_arasan_set_power_and_bus_voltage(struct sdhci_host *host, unsigned char mode, + unsigned short vdd) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host); + u32 reg; + + /* + * Ensure that the card detect logic has stabilized before powering up, this is + * necessary after a host controller reset. + */ + if (mode == MMC_POWER_UP && sdhci_arasan->quirks & SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE) + read_poll_timeout(sdhci_readl, reg, reg & SDHCI_CD_STABLE, CD_STABLE_MAX_SLEEP_US, + CD_STABLE_TIMEOUT_US, false, host, SDHCI_PRESENT_STATE); + + sdhci_set_power_and_bus_voltage(host, mode, vdd); +} + static const struct sdhci_ops sdhci_arasan_ops = { .set_clock = sdhci_arasan_set_clock, .get_max_clock = sdhci_pltfm_clk_get_max_clock, @@ -521,7 +545,7 @@ static const struct sdhci_ops sdhci_arasan_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_arasan_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, - .set_power = sdhci_set_power_and_bus_voltage, + .set_power = sdhci_arasan_set_power_and_bus_voltage, .hw_reset = sdhci_arasan_hw_reset, }; @@ -570,7 +594,7 @@ static const struct sdhci_ops sdhci_arasan_cqe_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_arasan_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, - .set_power = sdhci_set_power_and_bus_voltage, + .set_power = sdhci_arasan_set_power_and_bus_voltage, .irq = sdhci_arasan_cqhci_irq, }; @@ -1447,6 +1471,7 @@ static const struct sdhci_arasan_clk_ops zynqmp_clk_ops = { static struct sdhci_arasan_of_data sdhci_arasan_zynqmp_data = { .pdata = &sdhci_arasan_zynqmp_pdata, .clk_ops = &zynqmp_clk_ops, + .quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE, }; static const struct sdhci_arasan_clk_ops versal_clk_ops = { @@ -1457,6 +1482,7 @@ static const struct sdhci_arasan_clk_ops versal_clk_ops = { static struct sdhci_arasan_of_data sdhci_arasan_versal_data = { .pdata = &sdhci_arasan_zynqmp_pdata, .clk_ops = &versal_clk_ops, + .quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE, }; static const struct sdhci_arasan_clk_ops versal_net_clk_ops = { @@ -1467,6 +1493,7 @@ static const struct sdhci_arasan_clk_ops versal_net_clk_ops = { static struct sdhci_arasan_of_data sdhci_arasan_versal_net_data = { .pdata = &sdhci_arasan_versal_net_pdata, .clk_ops = &versal_net_clk_ops, + .quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE, }; static struct sdhci_arasan_of_data intel_keembay_emmc_data = { @@ -1937,6 +1964,8 @@ static int sdhci_arasan_probe(struct platform_device *pdev) if (of_device_is_compatible(np, "rockchip,rk3399-sdhci-5.1")) sdhci_arasan_update_clockmultiplier(host, 0x0); + sdhci_arasan->quirks |= data->quirks; + if (of_device_is_compatible(np, "intel,keembay-sdhci-5.1-emmc") || of_device_is_compatible(np, "intel,keembay-sdhci-5.1-sd") || of_device_is_compatible(np, "intel,keembay-sdhci-5.1-sdio")) { diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 4c2ae71770f7..3a1de477e9af 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -287,6 +287,20 @@ #define GLI_MAX_TUNING_LOOP 40 /* Genesys Logic chipset */ +static void sdhci_gli_mask_replay_timer_timeout(struct pci_dev *pdev) +{ + int aer; + u32 value; + + /* mask the replay timer timeout of AER */ + aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (aer) { + pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value); + value |= PCI_ERR_COR_REP_TIMER; + pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value); + } +} + static inline void gl9750_wt_on(struct sdhci_host *host) { u32 wt_value; @@ -607,7 +621,6 @@ static void gl9750_hw_setting(struct sdhci_host *host) { struct sdhci_pci_slot *slot = sdhci_priv(host); struct pci_dev *pdev; - int aer; u32 value; pdev = slot->chip->pdev; @@ -626,12 +639,7 @@ static void gl9750_hw_setting(struct sdhci_host *host) pci_set_power_state(pdev, PCI_D0); /* mask the replay timer timeout of AER */ - aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - if (aer) { - pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value); - value |= PCI_ERR_COR_REP_TIMER; - pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value); - } + sdhci_gli_mask_replay_timer_timeout(pdev); gl9750_wt_off(host); } @@ -806,7 +814,6 @@ static void sdhci_gl9755_set_clock(struct sdhci_host *host, unsigned int clock) static void gl9755_hw_setting(struct sdhci_pci_slot *slot) { struct pci_dev *pdev = slot->chip->pdev; - int aer; u32 value; gl9755_wt_on(pdev); @@ -841,12 +848,7 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot) pci_set_power_state(pdev, PCI_D0); /* mask the replay timer timeout of AER */ - aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - if (aer) { - pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value); - value |= PCI_ERR_COR_REP_TIMER; - pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value); - } + sdhci_gli_mask_replay_timer_timeout(pdev); gl9755_wt_off(pdev); } @@ -1751,7 +1753,7 @@ cleanup: return ret; } -static void gli_set_gl9763e(struct sdhci_pci_slot *slot) +static void gl9763e_hw_setting(struct sdhci_pci_slot *slot) { struct pci_dev *pdev = slot->chip->pdev; u32 value; @@ -1780,6 +1782,9 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot) value |= FIELD_PREP(GLI_9763E_HS400_RXDLY, GLI_9763E_HS400_RXDLY_5); pci_write_config_dword(pdev, PCIE_GLI_9763E_CLKRXDLY, value); + /* mask the replay timer timeout of AER */ + sdhci_gli_mask_replay_timer_timeout(pdev); + pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value); value &= ~GLI_9763E_VHS_REV; value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R); @@ -1923,7 +1928,7 @@ static int gli_probe_slot_gl9763e(struct sdhci_pci_slot *slot) gli_pcie_enable_msi(slot); host->mmc_host_ops.hs400_enhanced_strobe = gl9763e_hs400_enhanced_strobe; - gli_set_gl9763e(slot); + gl9763e_hw_setting(slot); sdhci_enable_v4_mode(host); return 0; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index e4fc345be7e5..17e62c61b6e6 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -156,6 +156,7 @@ struct sdhci_am654_data { #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) #define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1) +#define SDHCI_AM654_QUIRK_DISABLE_HS400 BIT(2) }; struct window { @@ -765,6 +766,7 @@ static int sdhci_am654_init(struct sdhci_host *host) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); + struct device *dev = mmc_dev(host->mmc); u32 ctl_cfg_2 = 0; u32 mask; u32 val; @@ -820,6 +822,12 @@ static int sdhci_am654_init(struct sdhci_host *host) if (ret) goto err_cleanup_host; + if (sdhci_am654->quirks & SDHCI_AM654_QUIRK_DISABLE_HS400 && + host->mmc->caps2 & (MMC_CAP2_HS400 | MMC_CAP2_HS400_ES)) { + dev_info(dev, "HS400 mode not supported on this silicon revision, disabling it\n"); + host->mmc->caps2 &= ~(MMC_CAP2_HS400 | MMC_CAP2_HS400_ES); + } + ret = __sdhci_add_host(host); if (ret) goto err_cleanup_host; @@ -883,6 +891,12 @@ static int sdhci_am654_get_of_property(struct platform_device *pdev, return 0; } +static const struct soc_device_attribute sdhci_am654_descope_hs400[] = { + { .family = "AM62PX", .revision = "SR1.0" }, + { .family = "AM62PX", .revision = "SR1.1" }, + { /* sentinel */ } +}; + static const struct of_device_id sdhci_am654_of_match[] = { { .compatible = "ti,am654-sdhci-5.1", @@ -970,6 +984,10 @@ static int sdhci_am654_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "parsing dt failed\n"); + soc = soc_device_match(sdhci_am654_descope_hs400); + if (soc) + sdhci_am654->quirks |= SDHCI_AM654_QUIRK_DISABLE_HS400; + host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch; host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; diff --git a/drivers/most/core.c b/drivers/most/core.c index a635d5082ebb..da319d108ea1 100644 --- a/drivers/most/core.c +++ b/drivers/most/core.c @@ -538,8 +538,8 @@ static struct most_channel *get_channel(char *mdev, char *mdev_ch) dev = bus_find_device_by_name(&mostbus, NULL, mdev); if (!dev) return NULL; - put_device(dev); iface = dev_get_drvdata(dev); + put_device(dev); list_for_each_entry_safe(c, tmp, &iface->p->channel_list, list) { if (!strcmp(dev_name(&c->dev), mdev_ch)) return c; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 2fca8e84ab10..4edc8e6b6b64 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -95,13 +95,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port, bool *update_slave_arr); static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); static void ad_tx_machine(struct port *port); -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params); +static void ad_periodic_machine(struct port *port); static void ad_port_selection_logic(struct port *port, bool *update_slave_arr); static void ad_agg_selection_logic(struct aggregator *aggregator, bool *update_slave_arr); static void ad_clear_agg(struct aggregator *aggregator); static void ad_initialize_agg(struct aggregator *aggregator); -static void ad_initialize_port(struct port *port, int lacp_fast); +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params); static void ad_enable_collecting(struct port *port); static void ad_disable_distributing(struct port *port, bool *update_slave_arr); @@ -1307,10 +1307,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) * case of EXPIRED even if LINK_DOWN didn't arrive for * the port. */ - port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->sm_vars &= ~AD_PORT_MATCHED; + /* Based on IEEE 8021AX-2014, Figure 6-18 - Receive + * machine state diagram, the statue should be + * Partner_Oper_Port_State.Synchronization = FALSE; + * Partner_Oper_Port_State.LACP_Timeout = Short Timeout; + * start current_while_timer(Short Timeout); + * Actor_Oper_Port_State.Expired = TRUE; + */ + port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT; - port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY; port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); port->actor_oper_port_state |= LACP_STATE_EXPIRED; port->sm_vars |= AD_PORT_CHURNED; @@ -1417,11 +1423,10 @@ static void ad_tx_machine(struct port *port) /** * ad_periodic_machine - handle a port's periodic state machine * @port: the port we're looking at - * @bond_params: bond parameters we will use * * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. */ -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params) +static void ad_periodic_machine(struct port *port) { periodic_states_t last_state; @@ -1430,8 +1435,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || - (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) || - !bond_params->lacp_active) { + (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) { port->sm_periodic_state = AD_NO_PERIODIC; } /* check if state machine should change state */ @@ -1955,16 +1959,16 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters * @port: the port we're looking at - * @lacp_fast: boolean. whether fast periodic should be used + * @bond_params: bond parameters we will use */ -static void ad_initialize_port(struct port *port, int lacp_fast) +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params) { static const struct port_params tmpl = { .system_priority = 0xffff, .key = 1, .port_number = 1, .port_priority = 0xff, - .port_state = 1, + .port_state = 0, }; static const struct lacpdu lacpdu = { .subtype = 0x01, @@ -1982,12 +1986,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->actor_port_priority = 0xff; port->actor_port_aggregator_identifier = 0; port->ntt = false; - port->actor_admin_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; - port->actor_oper_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; + port->actor_admin_port_state = LACP_STATE_AGGREGATION; + port->actor_oper_port_state = LACP_STATE_AGGREGATION; + if (bond_params->lacp_active) { + port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY; + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + } - if (lacp_fast) + if (bond_params->lacp_fast) port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT; memcpy(&port->partner_admin, &tmpl, sizeof(tmpl)); @@ -2201,7 +2207,7 @@ void bond_3ad_bind_slave(struct slave *slave) /* port initialization */ port = &(SLAVE_AD_INFO(slave)->port); - ad_initialize_port(port, bond->params.lacp_fast); + ad_initialize_port(port, &bond->params); port->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave)->id; @@ -2513,7 +2519,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } ad_rx_machine(NULL, port); - ad_periodic_machine(port, &bond->params); + ad_periodic_machine(port); ad_port_selection_logic(port, &update_slave_arr); ad_mux_machine(port, &update_slave_arr); ad_tx_machine(port); @@ -2883,6 +2889,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } +/** + * bond_3ad_update_lacp_active - change the lacp active + * @bond: bonding struct + * + * Update actor_oper_port_state when lacp_active is modified. + */ +void bond_3ad_update_lacp_active(struct bonding *bond) +{ + struct port *port = NULL; + struct list_head *iter; + struct slave *slave; + int lacp_active; + + lacp_active = bond->params.lacp_active; + spin_lock_bh(&bond->mode_lock); + bond_for_each_slave(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->port); + if (lacp_active) + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + else + port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY; + } + spin_unlock_bh(&bond->mode_lock); +} + size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1d639a3be6ba..3b6f815c55ff 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1660,6 +1660,7 @@ static int bond_option_lacp_active_set(struct bonding *bond, netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n", newval->string, newval->value); bond->params.lacp_active = newval->value; + bond_3ad_update_lacp_active(bond); return 0; } diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 9942fb6f7f4b..829b1f087e9e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2078,7 +2078,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, /* Start search operation */ reg = ARL_SRCH_STDN; - b53_write8(priv, offset, B53_ARL_SRCH_CTL, reg); + b53_write8(priv, B53_ARLIO_PAGE, offset, reg); do { ret = b53_arl_search_wait(priv); diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c index 76e490070e9c..c354abdafc1b 100644 --- a/drivers/net/dsa/microchip/ksz8.c +++ b/drivers/net/dsa/microchip/ksz8.c @@ -36,15 +36,14 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); + ksz_rmw8(dev, addr, bits, set ? bits : 0); } static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), - dev->dev_ops->get_port_addr(port, offset), - bits, set ? bits : 0); + ksz_rmw8(dev, dev->dev_ops->get_port_addr(port, offset), bits, + set ? bits : 0); } /** @@ -1955,16 +1954,19 @@ int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true); /* Enable aggressive back off algorithm in half duplex mode. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1, - SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + if (ret) + return ret; /* * Make sure unicast VLAN boundary is set as default and * enable no excessive collision drop. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + ret = ksz_rmw8(dev, REG_SW_CTRL_2, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + if (ret) + return ret; ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7292bfe2f7ca..9568cc391fe3 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1447,6 +1447,7 @@ static const struct regmap_range ksz8873_valid_regs[] = { regmap_reg_range(0x3f, 0x3f), /* advanced control registers */ + regmap_reg_range(0x43, 0x43), regmap_reg_range(0x60, 0x6f), regmap_reg_range(0x70, 0x75), regmap_reg_range(0x76, 0x78), @@ -2456,6 +2457,12 @@ static void ksz_update_port_member(struct ksz_device *dev, int port) dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } + /* HSR ports are setup once so need to use the assigned membership + * when the port is enabled. + */ + if (!port_member && p->stp_state == BR_STATE_FORWARDING && + (dev->hsr_ports & BIT(port))) + port_member = dev->hsr_ports; dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port); } diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 47411d2cbd28..88694b08afa1 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -736,10 +736,8 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, continue; } - if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) { - e->hash = 0xffff; + if (!airoha_ppe_foe_compare_entry(e, hwe)) continue; - } airoha_ppe_foe_commit_entry(ppe, &e->data, hash); commit_done = true; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5578ddcb465d..207a8bb36ae5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -926,15 +926,21 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { netmem_ref netmem; - netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp); + } else { + netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + *offset = 0; + } if (!netmem) return 0; - *mapping = page_pool_get_dma_addr_netmem(netmem); + *mapping = page_pool_get_dma_addr_netmem(netmem) + *offset; return netmem; } @@ -1029,7 +1035,7 @@ static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; netmem_ref netmem; - netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp); + netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp); if (!netmem) return -ENOMEM; @@ -3819,7 +3825,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, if (BNXT_RX_PAGE_MODE(bp)) pp.pool_size += bp->rx_ring_size / rx_size_fac; pp.nid = numa_node; - pp.napi = &rxr->bnapi->napi; pp.netdev = bp->dev; pp.dev = &bp->pdev->dev; pp.dma_dir = bp->rx_dir; @@ -3851,6 +3856,12 @@ err_destroy_pp: return PTR_ERR(pool); } +static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr) +{ + page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi); + page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi); +} + static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { u16 mem_size; @@ -3889,6 +3900,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node); if (rc) return rc; + bnxt_enable_rx_page_pool(rxr); rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0); if (rc < 0) @@ -5320,7 +5332,7 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all) { int i; - netdev_assert_locked(bp->dev); + netdev_assert_locked_or_invisible(bp->dev); /* Under netdev instance lock and all our NAPIs have been disabled. * It's safe to delete the hash table. @@ -16031,6 +16043,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) goto err_reset; } + bnxt_enable_rx_page_pool(rxr); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ce95fad8cedd..9693f0289435 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5113,7 +5113,8 @@ static const struct macb_config sama7g5_gem_config = { static const struct macb_config sama7g5_emac_config = { .caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | - MACB_CAPS_MIIONRGMII | MACB_CAPS_GEM_HAS_PTP, + MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_MIIONRGMII | + MACB_CAPS_GEM_HAS_PTP, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 1f411d7c4373..1be1b1ef31ee 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -2870,6 +2870,8 @@ static void gve_shutdown(struct pci_dev *pdev) struct gve_priv *priv = netdev_priv(netdev); bool was_up = netif_running(priv->dev); + netif_device_detach(netdev); + rtnl_lock(); netdev_lock(netdev); if (was_up && gve_close(priv->dev)) { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c index 503cfbfb4a8a..83cf75bf7a17 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) { int ret; - ASSERT_RTNL(); + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state)) + return -EBUSY; if (netif_running(priv->netdev)) { + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_warn(&priv->pdev->dev, "failed to reset because port is up\n"); return -EBUSY; @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) netif_device_detach(priv->netdev); priv->reset_type = type; - set_bit(HBG_NIC_STATE_RESETTING, &priv->state); clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET); if (ret) { @@ -84,29 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type) type != priv->reset_type) return 0; - ASSERT_RTNL(); - - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); ret = hbg_rebuild(priv); if (ret) { priv->stats.reset_fail_cnt++; set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_err(&priv->pdev->dev, "failed to rebuild after reset\n"); return ret; } netif_device_attach(priv->netdev); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_info(&priv->pdev->dev, "reset done\n"); return ret; } -/* must be protected by rtnl lock */ int hbg_reset(struct hbg_priv *priv) { int ret; - ASSERT_RTNL(); ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION); if (ret) return ret; @@ -171,7 +169,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct hbg_priv *priv = netdev_priv(netdev); - rtnl_lock(); hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR); } @@ -181,7 +178,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev) struct hbg_priv *priv = netdev_priv(netdev); hbg_reset_done(priv, HBG_RESET_TYPE_FLR); - rtnl_unlock(); } static const struct pci_error_handlers hbg_pci_err_handler = { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c index 8cca8316ba40..d0aa0661ecd4 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c @@ -12,6 +12,8 @@ #define HBG_HW_EVENT_WAIT_TIMEOUT_US (2 * 1000 * 1000) #define HBG_HW_EVENT_WAIT_INTERVAL_US (10 * 1000) +#define HBG_MAC_LINK_WAIT_TIMEOUT_US (500 * 1000) +#define HBG_MAC_LINK_WAIT_INTERVAL_US (5 * 1000) /* little endian or big endian. * ctrl means packet description, data means skb packet data */ @@ -228,6 +230,9 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr) void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) { + u32 link_status; + int ret; + hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE); hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR, @@ -239,8 +244,14 @@ void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE); - if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR, - HBG_REG_AN_NEG_STATE_NP_LINK_OK_B)) + /* wait MAC link up */ + ret = readl_poll_timeout(priv->io_base + HBG_REG_AN_NEG_STATE_ADDR, + link_status, + FIELD_GET(HBG_REG_AN_NEG_STATE_NP_LINK_OK_B, + link_status), + HBG_MAC_LINK_WAIT_INTERVAL_US, + HBG_MAC_LINK_WAIT_TIMEOUT_US); + if (ret) hbg_np_link_fail_task_schedule(priv); } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h index 2883a5899ae2..8b6110599e10 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h @@ -29,7 +29,12 @@ static inline bool hbg_fifo_is_full(struct hbg_priv *priv, enum hbg_dir dir) static inline u32 hbg_get_queue_used_num(struct hbg_ring *ring) { - return (ring->ntu + ring->len - ring->ntc) % ring->len; + u32 len = READ_ONCE(ring->len); + + if (!len) + return 0; + + return (READ_ONCE(ring->ntu) + len - READ_ONCE(ring->ntc)) % len; } netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 458e5eaa92e5..e79b14d50b24 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7149,6 +7149,13 @@ static int igc_probe(struct pci_dev *pdev, adapter->port_num = hw->bus.func; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + /* Disable ASPM L1.2 on I226 devices to avoid packet loss */ if (igc_is_device_id_i226(hw)) pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); @@ -7175,13 +7182,6 @@ static int igc_probe(struct pci_dev *pdev, netdev->mem_start = pci_resource_start(pdev, 0); netdev->mem_end = pci_resource_end(pdev, 0); - /* PCI config space info */ - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - hw->revision_id = pdev->revision; - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - /* Copy the default MAC and PHY function pointers */ memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c index 54f1b83dfe42..d227f4d2a2d1 100644 --- a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c @@ -543,6 +543,7 @@ int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter) attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = adapter->hw.bus.func; + attrs.no_phys_port_name = 1; ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id); devlink_port_attrs_set(devlink_port, &attrs); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6122a0abb41f..80e6a2ef1350 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -968,10 +968,6 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) clear_bit(__IXGBE_HANG_CHECK_ARMED, &adapter->tx_ring[i]->state); - - for (i = 0; i < adapter->num_xdp_queues; i++) - clear_bit(__IXGBE_HANG_CHECK_ARMED, - &adapter->xdp_ring[i]->state); } static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) @@ -1214,7 +1210,7 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring, struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); struct ixgbe_hw *hw = &adapter->hw; - e_err(drv, "Detected Tx Unit Hang%s\n" + e_err(drv, "Detected Tx Unit Hang\n" " Tx Queue <%d>\n" " TDH, TDT <%x>, <%x>\n" " next_to_use <%x>\n" @@ -1222,16 +1218,14 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring, "tx_buffer_info[next_to_clean]\n" " time_stamp <%lx>\n" " jiffies <%lx>\n", - ring_is_xdp(tx_ring) ? " (XDP)" : "", tx_ring->queue_index, IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), tx_ring->next_to_use, next, tx_ring->tx_buffer_info[next].time_stamp, jiffies); - if (!ring_is_xdp(tx_ring)) - netif_stop_subqueue(tx_ring->netdev, - tx_ring->queue_index); + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); } /** @@ -1451,6 +1445,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_bytes); adapter->tx_ipsec += total_ipsec; + if (ring_is_xdp(tx_ring)) + return !!budget; + if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { if (adapter->hw.mac.type == ixgbe_mac_e610) ixgbe_handle_mdd_event(adapter, tx_ring); @@ -1468,9 +1465,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } - if (ring_is_xdp(tx_ring)) - return !!budget; - #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); if (!__netif_txq_completed_wake(txq, total_packets, total_bytes, @@ -7974,12 +7968,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) return; /* Force detection of hung controller */ - if (netif_carrier_ok(adapter->netdev)) { + if (netif_carrier_ok(adapter->netdev)) for (i = 0; i < adapter->num_tx_queues; i++) set_check_for_tx_hang(adapter->tx_ring[i]); - for (i = 0; i < adapter->num_xdp_queues; i++) - set_check_for_tx_hang(adapter->xdp_ring[i]); - } if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { /* @@ -8199,13 +8190,6 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) return true; } - for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *ring = adapter->xdp_ring[i]; - - if (ring->next_to_use != ring->next_to_clean) - return true; - } - return false; } @@ -11005,6 +10989,10 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) return -ENETDOWN; + if (!netif_carrier_ok(adapter->netdev) || + !netif_running(adapter->netdev)) + return -ENETDOWN; + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index ac58964b2f08..7b941505a9d0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -398,7 +398,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) dma_addr_t dma; u32 cmd_type; - while (budget-- > 0) { + while (likely(budget)) { if (unlikely(!ixgbe_desc_unused(xdp_ring))) { work_done = false; break; @@ -433,6 +433,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) xdp_ring->next_to_use++; if (xdp_ring->next_to_use == xdp_ring->count) xdp_ring->next_to_use = 0; + + budget--; } if (tx_desc) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 1b765045aa63..b56395ac5a74 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -606,8 +606,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) if (!npc_check_field(rvu, blkaddr, NPC_LB, intf)) *features &= ~BIT_ULL(NPC_OUTER_VID); - /* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */ - if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) && + /* Allow extracting SPI field from AH and ESP headers at same offset */ + if (npc_is_field_present(rvu, NPC_IPSEC_SPI, intf) && (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH)))) *features |= BIT_ULL(NPC_IPSEC_SPI); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index c855fb799ce1..e9bd32741983 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -101,7 +101,9 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED)) return -1; + rcu_read_lock(); err = dev_fill_forward_path(dev, addr, &stack); + rcu_read_unlock(); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h index b59aee75de94..2c98a5299df3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h @@ -26,7 +26,6 @@ struct mlx5e_dcbx { u8 cap; /* Buffer configuration */ - bool manual_buffer; u32 cable_len; u32 xoff; u16 port_buff_cell_sz; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 5ae787656a7c..3efa8bf1d14e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev, /* Total shared buffer size is split in a ratio of 3:1 between * lossy and lossless pools respectively. */ - lossy_epool_size = (shared_buffer_size / 4) * 3; lossless_ipool_size = shared_buffer_size / 4; + lossy_epool_size = shared_buffer_size - lossless_ipool_size; mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0, lossy_epool_size); @@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv, u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5_core_dev *mdev = priv->mdev; int sz = MLX5_ST_SZ_BYTES(pbmc_reg); - u32 new_headroom_size = 0; - u32 current_headroom_size; + u32 current_headroom_cells = 0; + u32 new_headroom_cells = 0; void *in; int err; int i; - current_headroom_size = port_buffer->headroom_size; - in = kzalloc(sz, GFP_KERNEL); if (!in) return -ENOMEM; @@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv, for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); + current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size); + u64 size = port_buffer->buffer[i].size; u64 xoff = port_buffer->buffer[i].xoff; u64 xon = port_buffer->buffer[i].xon; - new_headroom_size += size; do_div(size, port_buff_cell_sz); + new_headroom_cells += size; do_div(xoff, port_buff_cell_sz); do_div(xon, port_buff_cell_sz); MLX5_SET(bufferx_reg, buffer, size, size); @@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv, MLX5_SET(bufferx_reg, buffer, xon_threshold, xon); } - new_headroom_size /= port_buff_cell_sz; - current_headroom_size /= port_buff_cell_sz; - err = port_update_shared_buffer(priv->mdev, current_headroom_size, - new_headroom_size); + err = port_update_shared_buffer(priv->mdev, current_headroom_cells, + new_headroom_cells); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c index a4263137fef5..01d522b02947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c @@ -173,6 +173,8 @@ static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs, memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions)); rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter); + rule_actions[0].counter.offset = + attr->counter->id - attr->counter->bulk->base_id; /* Modify header is special, it may require extra arguments outside the action itself. */ if (mh_action->mh_data) { rule_actions[1].modify_header.offset = mh_action->mh_data->offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 5fe016e477b3..d166c0d5189e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -362,6 +362,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev, static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { + u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN; struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; u32 old_cable_len = priv->dcbx.cable_len; @@ -389,7 +390,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, if (MLX5_BUFFER_SUPPORTED(mdev)) { pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en; - if (priv->dcbx.manual_buffer) + ret = mlx5_query_port_buffer_ownership(mdev, + &buffer_ownership); + if (ret) + netdev_err(dev, + "%s, Failed to get buffer ownership: %d\n", + __func__, ret); + + if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED) ret = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, &pfc_new, NULL, NULL); @@ -982,7 +990,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev, if (!changed) return 0; - priv->dcbx.manual_buffer = true; err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL, buffer_size, prio2buffer); return err; @@ -1252,7 +1259,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) priv->dcbx.cap |= DCB_CAP_DCBX_HOST; priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv); - priv->dcbx.manual_buffer = false; priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN; mlx5e_ets_init(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index b7102e14d23d..c33accadae0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -47,10 +47,12 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch * devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, vport_num - 1, external); } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { + u16 base_vport = mlx5_core_ec_vf_vport_base(dev); + memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, - vport_num - 1, false); + vport_num - base_vport, false); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 91d863c8c152..8b4977650183 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -102,6 +102,8 @@ struct mlx5_esw_sched_node { u8 level; /* Valid only when this node represents a traffic class. */ u8 tc; + /* Valid only for a TC arbiter node or vport TC arbiter. */ + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; }; static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) @@ -462,6 +464,7 @@ static int esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, struct netlink_ext_ack *extack) { + struct mlx5_esw_sched_node *parent = vport_node->parent; u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_core_dev *dev = vport_node->esw->dev; void *attr; @@ -477,7 +480,7 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport); MLX5_SET(scheduling_context, sched_ctx, parent_element_id, - vport_node->parent->ix); + parent ? parent->ix : vport_node->esw->qos.root_tsar_ix); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, vport_node->max_rate); @@ -608,10 +611,7 @@ static void esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, u32 *tc_bw) { - struct mlx5_esw_sched_node *vports_tc_node; - - list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) - tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share; + memcpy(tc_bw, tc_arbiter_node->tc_bw, sizeof(tc_arbiter_node->tc_bw)); } static void @@ -628,6 +628,7 @@ esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, u8 tc = vports_tc_node->tc; u32 bw_share; + tc_arbiter_node->tc_bw[tc] = tc_bw[tc]; bw_share = tc_bw[tc] * fw_max_bw_share; bw_share = esw_qos_calc_bw_share(bw_share, divider, fw_max_bw_share); @@ -786,48 +787,15 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta return err; } - if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) { - esw->qos.node0 = __esw_qos_create_vports_sched_node(esw, NULL, extack); - } else { - /* The eswitch doesn't support scheduling nodes. - * Create a software-only node0 using the root TSAR to attach vport QoS to. - */ - if (!__esw_qos_alloc_node(esw, - esw->qos.root_tsar_ix, - SCHED_NODE_TYPE_VPORTS_TSAR, - NULL)) - esw->qos.node0 = ERR_PTR(-ENOMEM); - else - list_add_tail(&esw->qos.node0->entry, - &esw->qos.domain->nodes); - } - if (IS_ERR(esw->qos.node0)) { - err = PTR_ERR(esw->qos.node0); - esw_warn(dev, "E-Switch create rate node 0 failed (%d)\n", err); - goto err_node0; - } refcount_set(&esw->qos.refcnt, 1); return 0; - -err_node0: - if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, - esw->qos.root_tsar_ix)) - esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n"); - - return err; } static void esw_qos_destroy(struct mlx5_eswitch *esw) { int err; - if (esw->qos.node0->ix != esw->qos.root_tsar_ix) - __esw_qos_destroy_node(esw->qos.node0, NULL); - else - __esw_qos_free_node(esw->qos.node0); - esw->qos.node0 = NULL; - err = mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, esw->qos.root_tsar_ix); @@ -990,13 +958,16 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - int err, new_level, max_level; + struct mlx5_esw_sched_node *parent = vport_node->parent; + int err; if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + int new_level, max_level; + /* Increase the parent's level by 2 to account for both the * TC arbiter and the vports TC scheduling element. */ - new_level = vport_node->parent->level + 2; + new_level = (parent ? parent->level : 2) + 2; max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev, log_esw_max_sched_depth); if (new_level > max_level) { @@ -1033,9 +1004,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, err_sched_nodes: if (type == SCHED_NODE_TYPE_RATE_LIMITER) { esw_qos_node_destroy_sched_element(vport_node, NULL); - list_add_tail(&vport_node->entry, - &vport_node->parent->children); - vport_node->level = vport_node->parent->level + 1; + esw_qos_node_attach_to_parent(vport_node); } else { esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL); } @@ -1083,7 +1052,6 @@ err_out: static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - struct mlx5_esw_sched_node *parent = vport_node->parent; enum sched_node_type curr_type = vport_node->type; if (curr_type == SCHED_NODE_TYPE_VPORT) @@ -1092,8 +1060,9 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a esw_qos_vport_tc_disable(vport, extack); vport_node->bw_share = 0; + memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw)); list_del_init(&vport_node->entry); - esw_qos_normalize_min_rate(parent->esw, parent, extack); + esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack); trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport); } @@ -1103,25 +1072,23 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; int err; esw_assert_qos_lock_held(vport->dev->priv.eswitch); - esw_qos_node_set_parent(vport->qos.sched_node, parent); - if (type == SCHED_NODE_TYPE_VPORT) { - err = esw_qos_vport_create_sched_element(vport->qos.sched_node, - extack); - } else { + esw_qos_node_set_parent(vport_node, parent); + if (type == SCHED_NODE_TYPE_VPORT) + err = esw_qos_vport_create_sched_element(vport_node, extack); + else err = esw_qos_vport_tc_enable(vport, type, extack); - } if (err) return err; - vport->qos.sched_node->type = type; - esw_qos_normalize_min_rate(parent->esw, parent, extack); - trace_mlx5_esw_vport_qos_create(vport->dev, vport, - vport->qos.sched_node->max_rate, - vport->qos.sched_node->bw_share); + vport_node->type = type; + esw_qos_normalize_min_rate(vport_node->esw, parent, extack); + trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate, + vport_node->bw_share); return 0; } @@ -1132,6 +1099,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; struct mlx5_esw_sched_node *sched_node; + struct mlx5_eswitch *parent_esw; int err; esw_assert_qos_lock_held(esw); @@ -1139,10 +1107,14 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t if (err) return err; - parent = parent ?: esw->qos.node0; - sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent); - if (!sched_node) + parent_esw = parent ? parent->esw : esw; + sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent); + if (!sched_node) { + esw_qos_put(esw); return -ENOMEM; + } + if (!parent) + list_add_tail(&sched_node->entry, &esw->qos.domain->nodes); sched_node->max_rate = max_rate; sched_node->min_rate = min_rate; @@ -1150,6 +1122,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t vport->qos.sched_node = sched_node; err = esw_qos_vport_enable(vport, type, parent, extack); if (err) { + __esw_qos_free_node(sched_node); esw_qos_put(esw); vport->qos.sched_node = NULL; } @@ -1157,6 +1130,19 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t return err; } +static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport) +{ + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw_assert_qos_lock_held(esw); + if (!vport->qos.sched_node) + return; + + esw_qos_vport_disable(vport, NULL); + mlx5_esw_qos_vport_qos_free(vport); + esw_qos_put(esw); +} + void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; @@ -1168,11 +1154,9 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport) goto unlock; parent = vport->qos.sched_node->parent; - WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node"); + WARN(parent, "Disabling QoS on port before detaching it from node"); - esw_qos_vport_disable(vport, NULL); - mlx5_esw_qos_vport_qos_free(vport); - esw_qos_put(esw); + mlx5_esw_qos_vport_disable_locked(vport); unlock: esw_qos_unlock(esw); } @@ -1262,13 +1246,13 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { - struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent; - enum sched_node_type curr_type = vport->qos.sched_node->type; + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *curr_parent = vport_node->parent; + enum sched_node_type curr_type = vport_node->type; u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; int err; esw_assert_qos_lock_held(vport->dev->priv.eswitch); - parent = parent ?: curr_parent; if (curr_type == type && curr_parent == parent) return 0; @@ -1276,10 +1260,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, if (err) return err; - if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { - esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node, - curr_tc_bw); - } + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) + esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw); esw_qos_vport_disable(vport, extack); @@ -1290,8 +1272,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, } if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { - esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node, - curr_tc_bw, extack); + esw_qos_set_tc_arbiter_bw_shares(vport_node, curr_tc_bw, + extack); } return err; @@ -1306,16 +1288,16 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw esw_assert_qos_lock_held(esw); curr_parent = vport->qos.sched_node->parent; - parent = parent ?: esw->qos.node0; if (curr_parent == parent) return 0; /* Set vport QoS type based on parent node type if different from * default QoS; otherwise, use the vport's current QoS type. */ - if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) type = SCHED_NODE_TYPE_RATE_LIMITER; - else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + else if (curr_parent && + curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) type = SCHED_NODE_TYPE_VPORT; else type = vport->qos.sched_node->type; @@ -1654,9 +1636,10 @@ static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw, static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport, u32 *tc_bw) { - struct mlx5_eswitch *esw = vport->qos.sched_node ? - vport->qos.sched_node->parent->esw : - vport->dev->priv.eswitch; + struct mlx5_esw_sched_node *node = vport->qos.sched_node; + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw = (node && node->parent) ? node->parent->esw : esw; return esw_qos_validate_unsupported_tc_bw(esw, tc_bw); } @@ -1673,6 +1656,21 @@ static bool esw_qos_tc_bw_disabled(u32 *tc_bw) return true; } +static void esw_vport_qos_prune_empty(struct mlx5_vport *vport) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + if (!vport_node) + return; + + if (vport_node->parent || vport_node->max_rate || + vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw)) + return; + + mlx5_esw_qos_vport_disable_locked(vport); +} + int mlx5_esw_qos_init(struct mlx5_eswitch *esw) { if (esw->qos.domain) @@ -1706,6 +1704,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void esw_qos_lock(esw); err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack); + if (err) + goto out; + esw_vport_qos_prune_empty(vport); +out: esw_qos_unlock(esw); return err; } @@ -1727,6 +1729,10 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * esw_qos_lock(esw); err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack); + if (err) + goto out; + esw_vport_qos_prune_empty(vport); +out: esw_qos_unlock(esw); return err; } @@ -1763,7 +1769,8 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, if (disable) { if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT, - NULL, extack); + vport_node->parent, extack); + esw_vport_qos_prune_empty(vport); goto unlock; } @@ -1775,7 +1782,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, } else { err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_TC_ARBITER_TSAR, - NULL, extack); + vport_node->parent, extack); } if (!err) esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack); @@ -1924,14 +1931,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate, void *priv, void *parent_priv, struct netlink_ext_ack *extack) { - struct mlx5_esw_sched_node *node; + struct mlx5_esw_sched_node *node = parent ? parent_priv : NULL; struct mlx5_vport *vport = priv; + int err; - if (!parent) - return mlx5_esw_qos_vport_update_parent(vport, NULL, extack); + err = mlx5_esw_qos_vport_update_parent(vport, node, extack); + if (!err) { + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw_qos_lock(esw); + esw_vport_qos_prune_empty(vport); + esw_qos_unlock(esw); + } - node = parent_priv; - return mlx5_esw_qos_vport_update_parent(vport, node, extack); + return err; } static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index b0b8ef3ec3c4..45506ad56847 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -373,11 +373,6 @@ struct mlx5_eswitch { refcount_t refcnt; u32 root_tsar_ix; struct mlx5_qos_domain *domain; - /* Contains all vports with QoS enabled but no explicit node. - * Cannot be NULL if QoS is enabled, but may be a fake node - * referencing the root TSAR if the esw doesn't support nodes. - */ - struct mlx5_esw_sched_node *node0; } qos; struct mlx5_esw_bridge_offloads *br_offloads; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b6d53db27cd5..9d3504f5abfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -367,6 +367,8 @@ int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); +int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev, + u8 *buffer_ownership); int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 549f1066d2a5..2d7adf7444ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -968,6 +968,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state) return err; } +int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev, + u8 *buffer_ownership) +{ + u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {}; + int err; + + if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) { + *buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN; + return 0; + } + + err = mlx5_query_pfcc_reg(mdev, out, sizeof(out)); + if (err) + return err; + + *buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership); + + return 0; +} + int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio) { int sz = MLX5_ST_SZ_BYTES(qpdpm_reg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c index 92de4b761a83..adeccc588e5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c @@ -74,9 +74,9 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher, static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) { - bool move_error = false, poll_error = false, drain_error = false; struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx; struct mlx5hws_matcher *matcher = bwc_matcher->matcher; + int drain_error = 0, move_error = 0, poll_error = 0; u16 bwc_queues = mlx5hws_bwc_queues(ctx); struct mlx5hws_rule_attr rule_attr; struct mlx5hws_bwc_rule *bwc_rule; @@ -84,6 +84,7 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) struct list_head *rules_list; u32 pending_rules; int i, ret = 0; + bool drain; mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr); @@ -99,23 +100,37 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) ret = mlx5hws_matcher_resize_rule_move(matcher, bwc_rule->rule, &rule_attr); - if (unlikely(ret && !move_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n", - ret); - move_error = true; + if (unlikely(ret)) { + if (!move_error) { + mlx5hws_err(ctx, + "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n", + ret); + move_error = ret; + } + /* Rule wasn't queued, no need to poll */ + continue; } pending_rules++; + drain = pending_rules >= + hws_bwc_get_burst_th(ctx, rule_attr.queue_id); ret = mlx5hws_bwc_queue_poll(ctx, rule_attr.queue_id, &pending_rules, - false); - if (unlikely(ret && !poll_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: poll failed (%d), attempting to move rest of the rules\n", - ret); - poll_error = true; + drain); + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving BWC rule: timeout polling for completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!poll_error) { + mlx5hws_err(ctx, + "Moving BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n", + ret); + poll_error = ret; + } } } @@ -126,17 +141,30 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) rule_attr.queue_id, &pending_rules, true); - if (unlikely(ret && !drain_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: drain failed (%d), attempting to move rest of the rules\n", - ret); - drain_error = true; + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving bwc rule: timeout draining completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!drain_error) { + mlx5hws_err(ctx, + "Moving bwc rule: drain failed (%d), attempting to move rest of the rules\n", + ret); + drain_error = ret; + } } } } - if (move_error || poll_error || drain_error) - ret = -EINVAL; + /* Return the first error that happened */ + if (unlikely(move_error)) + return move_error; + if (unlikely(poll_error)) + return poll_error; + if (unlikely(drain_error)) + return drain_error; return ret; } @@ -1035,6 +1063,21 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule, return 0; /* rule inserted successfully */ } + /* Rule insertion could fail due to queue being full, timeout, or + * matcher in resize. In such cases, no point in trying to rehash. + */ + if (ret == -EBUSY || ret == -ETIMEDOUT || ret == -EAGAIN) { + mutex_unlock(queue_lock); + mlx5hws_err(ctx, + "BWC rule insertion failed - %s (%d)\n", + ret == -EBUSY ? "queue is full" : + ret == -ETIMEDOUT ? "timeout" : + ret == -EAGAIN ? "matcher in resize" : "N/A", + ret); + hws_bwc_rule_cnt_dec(bwc_rule); + return ret; + } + /* At this point the rule wasn't added. * It could be because there was collision, or some other problem. * Try rehash by size and insert rule again - last chance. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c index ca7501c57468..14e79579c719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c @@ -1328,11 +1328,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) { struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx; struct mlx5hws_matcher *matcher = bwc_matcher->matcher; - bool move_error = false, poll_error = false; u16 bwc_queues = mlx5hws_bwc_queues(ctx); struct mlx5hws_bwc_rule *tmp_bwc_rule; struct mlx5hws_rule_attr rule_attr; struct mlx5hws_table *isolated_tbl; + int move_error = 0, poll_error = 0; struct mlx5hws_rule *tmp_rule; struct list_head *rules_list; u32 expected_completions = 1; @@ -1391,11 +1391,15 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) ret = mlx5hws_matcher_resize_rule_move(matcher, tmp_rule, &rule_attr); - if (unlikely(ret && !move_error)) { - mlx5hws_err(ctx, - "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n", - ret); - move_error = true; + if (unlikely(ret)) { + if (!move_error) { + mlx5hws_err(ctx, + "Moving complex BWC rule: move failed (%d), attempting to move rest of the rules\n", + ret); + move_error = ret; + } + /* Rule wasn't queued, no need to poll */ + continue; } expected_completions = 1; @@ -1403,11 +1407,19 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) rule_attr.queue_id, &expected_completions, true); - if (unlikely(ret && !poll_error)) { - mlx5hws_err(ctx, - "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n", - ret); - poll_error = true; + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving complex BWC rule: timeout polling for completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!poll_error) { + mlx5hws_err(ctx, + "Moving complex BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n", + ret); + poll_error = ret; + } } /* Done moving the rule to the new matcher, @@ -1422,8 +1434,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) } } - if (move_error || poll_error) - ret = -EINVAL; + /* Return the first error that happened */ + if (unlikely(move_error)) + return move_error; + if (unlikely(poll_error)) + return poll_error; return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c index 9c83753e4592..0bdcab2e5cf3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c @@ -55,6 +55,7 @@ int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev, MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type); + MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid); ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context); MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h index fa6bff210266..122ccc671628 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h @@ -36,6 +36,7 @@ struct mlx5hws_cmd_set_fte_attr { struct mlx5hws_cmd_ft_create_attr { u8 type; u8 level; + u16 uid; bool rtc_valid; bool decap_en; bool reformat_en; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c index 57592b92e24b..131e74b2b774 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c @@ -267,6 +267,7 @@ static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns, tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB; tbl_attr.level = ft_attr->level; + tbl_attr.uid = ft_attr->uid; tbl = mlx5hws_table_create(ctx, &tbl_attr); if (!tbl) { mlx5_core_err(ns->dev, "Failed creating hws flow_table\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c index f3ea09caba2b..32f87fdf3213 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c @@ -85,6 +85,7 @@ static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher) ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, + 0, &matcher->end_ft_id); if (ret) { mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n"); @@ -112,7 +113,9 @@ static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher) if (mlx5hws_matcher_is_isolated(matcher)) ret = hws_matcher_create_end_ft_isolated(matcher); else - ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, + ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, + tbl, + 0, &matcher->end_ft_id); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h index 59c14745ed0c..2498ceff2060 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h @@ -75,6 +75,7 @@ struct mlx5hws_context_attr { struct mlx5hws_table_attr { enum mlx5hws_table_type type; u32 level; + u16 uid; }; enum mlx5hws_matcher_flow_src { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index c4b22be19a9b..b0595c9b09e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -964,7 +964,6 @@ static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev, return -ENOMEM; MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index); - MLX5_SET(cqc, cqc_data, cqe_sz, queue->num_entries); MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries)); err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c index 568f691733f3..6113383ae47b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c @@ -9,6 +9,7 @@ u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl) } static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl, + u16 uid, struct mlx5hws_cmd_ft_create_attr *ft_attr) { ft_attr->type = tbl->fw_ft_type; @@ -16,7 +17,9 @@ static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl, ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1; else ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1; + ft_attr->rtc_valid = true; + ft_attr->uid = uid; } static void hws_table_set_cap_attr(struct mlx5hws_table *tbl, @@ -119,12 +122,12 @@ static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev, struct mlx5hws_table *tbl, - u32 *ft_id) + u16 uid, u32 *ft_id) { struct mlx5hws_cmd_ft_create_attr ft_attr = {0}; int ret; - hws_table_init_next_ft_attr(tbl, &ft_attr); + hws_table_init_next_ft_attr(tbl, uid, &ft_attr); hws_table_set_cap_attr(tbl, &ft_attr); ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id); @@ -189,7 +192,10 @@ static int hws_table_init(struct mlx5hws_table *tbl) } mutex_lock(&ctx->ctrl_lock); - ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id); + ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, + tbl, + tbl->uid, + &tbl->ft_id); if (ret) { mlx5hws_err(tbl->ctx, "Failed to create flow table object\n"); mutex_unlock(&ctx->ctrl_lock); @@ -239,6 +245,7 @@ struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx, tbl->ctx = ctx; tbl->type = attr->type; tbl->level = attr->level; + tbl->uid = attr->uid; ret = hws_table_init(tbl); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h index 0400cce0c317..1246f9bd8422 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h @@ -18,6 +18,7 @@ struct mlx5hws_table { enum mlx5hws_table_type type; u32 fw_ft_type; u32 level; + u16 uid; struct list_head matchers_list; struct list_head tbl_list_node; struct mlx5hws_default_miss default_miss; @@ -47,7 +48,7 @@ u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type, int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev, struct mlx5hws_table *tbl, - u32 *ft_id); + u16 uid, u32 *ft_id); void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl, u32 ft_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 618957d65663..9a2d64a0a858 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2375,6 +2375,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { ROUTER_EXP, false), MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD, ROUTER_EXP, false), + MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_LINK_LOCAL, FORWARD, + ROUTER_EXP, false), /* Multicast Router Traps */ MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false), MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 80ee5c4825dc..9962dc157901 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -94,6 +94,7 @@ enum { MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LINK_LOCAL = 0x16D, MLXSW_TRAP_ID_DISCARD_ROUTER_IRIF_EN = 0x178, MLXSW_TRAP_ID_DISCARD_ROUTER_ERIF_EN = 0x179, MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B, diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c index dd436bdff0f8..84c41f193561 100644 --- a/drivers/net/ethernet/microchip/lan865x/lan865x.c +++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c @@ -32,6 +32,10 @@ /* MAC Specific Addr 1 Top Reg */ #define LAN865X_REG_MAC_H_SADDR1 0x00010023 +/* MAC TSU Timer Increment Register */ +#define LAN865X_REG_MAC_TSU_TIMER_INCR 0x00010077 +#define MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS 0x0028 + struct lan865x_priv { struct work_struct multicast_work; struct net_device *netdev; @@ -311,6 +315,8 @@ static int lan865x_net_open(struct net_device *netdev) phy_start(netdev->phydev); + netif_start_queue(netdev); + return 0; } @@ -344,6 +350,21 @@ static int lan865x_probe(struct spi_device *spi) goto free_netdev; } + /* LAN865x Rev.B0/B1 configuration parameters from AN1760 + * As per the Configuration Application Note AN1760 published in the + * link, https://www.microchip.com/en-us/application-notes/an1760 + * Revision F (DS60001760G - June 2024), configure the MAC to set time + * stamping at the end of the Start of Frame Delimiter (SFD) and set the + * Timer Increment reg to 40 ns to be used as a 25 MHz internal clock. + */ + ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_TSU_TIMER_INCR, + MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS); + if (ret) { + dev_err(&spi->dev, "Failed to config TSU Timer Incr reg: %d\n", + ret); + goto oa_tc6_exit; + } + /* As per the point s3 in the below errata, SPI receive Ethernet frame * transfer may halt when starting the next frame in the same data block * (chunk) as the end of a previous frame. The RFA field should be diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h index 20decdeb9fdb..b9209eb6ea73 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase.h +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -241,7 +241,7 @@ union rtase_rx_desc { #define RTASE_RX_RES BIT(20) #define RTASE_RX_RUNT BIT(19) #define RTASE_RX_RWT BIT(18) -#define RTASE_RX_CRC BIT(16) +#define RTASE_RX_CRC BIT(17) #define RTASE_RX_V6F BIT(31) #define RTASE_RX_V4F BIT(30) #define RTASE_RX_UDPT BIT(29) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 09ae16e026eb..6c363f9b0ce2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -330,15 +330,11 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks); + ret = devm_clk_bulk_get_all_enabled(&pdev->dev, &plat_dat->clks); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n"); + return dev_err_probe(&pdev->dev, ret, "Failed to retrieve and enable all required clocks\n"); plat_dat->num_clks = ret; - ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks); - if (ret) - return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n"); - plat_dat->stmmac_clk = stmmac_pltfr_find_clk(plat_dat, data->stmmac_clk_name); @@ -346,7 +342,6 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) ret = data->probe(pdev, plat_dat, &stmmac_res); if (ret < 0) { dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n"); - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); return ret; } @@ -370,15 +365,11 @@ remove: static void dwc_eth_dwmac_remove(struct platform_device *pdev) { const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev); - struct plat_stmmacenet_data *plat_dat = dev_get_platdata(&pdev->dev); stmmac_dvr_remove(&pdev->dev); if (data->remove) data->remove(pdev); - - if (plat_dat) - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); } static const struct of_device_id dwc_eth_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 79b92130a03f..f6687c2f30f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1765,11 +1765,15 @@ err_gmac_powerdown: static void rk_gmac_remove(struct platform_device *pdev) { - struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(platform_get_drvdata(pdev)); + struct rk_priv_data *bsp_priv = priv->plat->bsp_priv; stmmac_dvr_remove(&pdev->dev); rk_gmac_powerdown(bsp_priv); + + if (priv->plat->phy_node && bsp_priv->integrated_phy) + clk_put(bsp_priv->clk_phy); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index c72ee759aae5..6c6c49e4b66f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -152,7 +152,7 @@ static int thead_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) { struct thead_dwmac *dwmac = plat->bsp_priv; - u32 reg; + u32 reg, div; switch (plat->mac_interface) { case PHY_INTERFACE_MODE_MII: @@ -164,6 +164,13 @@ static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: /* use pll */ + div = clk_get_rate(plat->stmmac_clk) / rgmii_clock(SPEED_1000); + reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) | + FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div); + + writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV); + writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV); + writel(GMAC_GTXCLK_SEL_PLL, dwmac->apb_base + GMAC_GTXCLK_SEL); reg = GMAC_TX_CLK_EN | GMAC_TX_CLK_N_EN | GMAC_TX_CLK_OUT_EN | GMAC_RX_CLK_EN | GMAC_RX_CLK_N_EN; @@ -211,6 +218,7 @@ static int thead_dwmac_probe(struct platform_device *pdev) struct stmmac_resources stmmac_res; struct plat_stmmacenet_data *plat; struct thead_dwmac *dwmac; + struct clk *apb_clk; void __iomem *apb; int ret; @@ -224,6 +232,19 @@ static int thead_dwmac_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, PTR_ERR(plat), "dt configuration failed\n"); + /* + * The APB clock is essential for accessing glue registers. However, + * old devicetrees don't describe it correctly. We continue to probe + * and emit a warning if it isn't present. + */ + apb_clk = devm_clk_get_enabled(&pdev->dev, "apb"); + if (PTR_ERR(apb_clk) == -ENOENT) + dev_warn(&pdev->dev, + "cannot get apb clock, link may break after speed changes\n"); + else if (IS_ERR(apb_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(apb_clk), + "failed to get apb clock\n"); + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); if (!dwmac) return -ENOMEM; diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 50bfbc2779e4..d8c9fe1d98c4 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -621,7 +621,8 @@ exit: static int icss_iep_extts_enable(struct icss_iep *iep, u32 index, int on) { - u32 val, cap, ret = 0; + u32 val, cap; + int ret = 0; mutex_lock(&iep->ptp_clk_mutex); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 2b973d6e2341..dadce6009791 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -50,6 +50,8 @@ /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) +static void emac_adjust_link(struct net_device *ndev); + static int emac_get_tx_ts(struct prueth_emac *emac, struct emac_tx_ts_response *rsp) { @@ -201,6 +203,44 @@ static void prueth_emac_stop(struct prueth *prueth) } } +static void icssg_enable_fw_offload(struct prueth *prueth) +{ + struct prueth_emac *emac; + int mac; + + for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { + emac = prueth->emac[mac]; + if (prueth->is_hsr_offload_mode) { + if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM) + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE); + else + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE); + } + + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) { + if (netif_running(emac->ndev)) { + icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, + ICSSG_FDB_ENTRY_P0_MEMBERSHIP | + ICSSG_FDB_ENTRY_P1_MEMBERSHIP | + ICSSG_FDB_ENTRY_P2_MEMBERSHIP | + ICSSG_FDB_ENTRY_BLOCK, + true); + icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID, + BIT(emac->port_id) | DEFAULT_PORT_MASK, + BIT(emac->port_id) | DEFAULT_UNTAG_MASK, + true); + if (prueth->is_hsr_offload_mode) + icssg_vtbl_modify(emac, DEFAULT_VID, + DEFAULT_PORT_MASK, + DEFAULT_UNTAG_MASK, true); + icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); + if (prueth->is_switch_mode) + icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); + } + } + } +} + static int prueth_emac_common_start(struct prueth *prueth) { struct prueth_emac *emac; @@ -229,6 +269,10 @@ static int prueth_emac_common_start(struct prueth *prueth) ret = icssg_config(prueth, emac, slice); if (ret) goto disable_class; + + mutex_lock(&emac->ndev->phydev->lock); + emac_adjust_link(emac->ndev); + mutex_unlock(&emac->ndev->phydev->lock); } ret = prueth_emac_start(prueth); @@ -747,6 +791,7 @@ static int emac_ndo_open(struct net_device *ndev) ret = prueth_emac_common_start(prueth); if (ret) goto free_rx_irq; + icssg_enable_fw_offload(prueth); } flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET; @@ -1354,8 +1399,7 @@ static int prueth_emac_restart(struct prueth *prueth) static void icssg_change_mode(struct prueth *prueth) { - struct prueth_emac *emac; - int mac, ret; + int ret; ret = prueth_emac_restart(prueth); if (ret) { @@ -1363,35 +1407,7 @@ static void icssg_change_mode(struct prueth *prueth) return; } - for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { - emac = prueth->emac[mac]; - if (prueth->is_hsr_offload_mode) { - if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM) - icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE); - else - icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE); - } - - if (netif_running(emac->ndev)) { - icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, - ICSSG_FDB_ENTRY_P0_MEMBERSHIP | - ICSSG_FDB_ENTRY_P1_MEMBERSHIP | - ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, - true); - icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID, - BIT(emac->port_id) | DEFAULT_PORT_MASK, - BIT(emac->port_id) | DEFAULT_UNTAG_MASK, - true); - if (prueth->is_hsr_offload_mode) - icssg_vtbl_modify(emac, DEFAULT_VID, - DEFAULT_PORT_MASK, - DEFAULT_UNTAG_MASK, true); - icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); - if (prueth->is_switch_mode) - icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); - } - } + icssg_enable_fw_offload(prueth); } static int prueth_netdevice_port_link(struct net_device *ndev, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c index 5d48df7a849f..3023ea2732ef 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c @@ -192,7 +192,7 @@ void wx_setup_vfmrqc_vf(struct wx *wx) u8 i, j; /* Fill out hash function seeds */ - netdev_rss_key_fill(wx->rss_key, sizeof(wx->rss_key)); + netdev_rss_key_fill(wx->rss_key, WX_RSS_KEY_SIZE); for (i = 0; i < WX_RSS_KEY_SIZE / 4; i++) wr32(wx, WX_VXRSSRK(i), wx->rss_key[i]); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 6011d7eae0c7..0d8a05fe541a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1160,6 +1160,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) struct axienet_local *lp = data; struct sk_buff *skb; u32 *app_metadata; + int i; skbuf_dma = axienet_get_rx_desc(lp, lp->rx_ring_tail++); skb = skbuf_dma->skb; @@ -1178,7 +1179,10 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) u64_stats_add(&lp->rx_packets, 1); u64_stats_add(&lp->rx_bytes, rx_len); u64_stats_update_end(&lp->rx_stat_sync); - axienet_rx_submit_desc(lp->ndev); + + for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail, + RX_BUF_NUM_DEFAULT); i++) + axienet_rx_submit_desc(lp->ndev); dma_async_issue_pending(lp->rx_chan); } @@ -1457,7 +1461,6 @@ static void axienet_rx_submit_desc(struct net_device *ndev) if (!skbuf_dma) return; - lp->rx_ring_head++; skb = netdev_alloc_skb(ndev, lp->max_frm_size); if (!skb) return; @@ -1482,6 +1485,7 @@ static void axienet_rx_submit_desc(struct net_device *ndev) skbuf_dma->desc = dma_rx_desc; dma_rx_desc->callback_param = lp; dma_rx_desc->callback_result = axienet_dma_rx_cb; + lp->rx_ring_head++; dmaengine_submit(dma_rx_desc); return; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 0e0fe32d2da4..045c5177262e 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -138,7 +138,7 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) static inline int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index cb6f5482d203..7397c693f984 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1061,6 +1061,7 @@ struct net_device_context { struct net_device __rcu *vf_netdev; struct netvsc_vf_pcpu_stats __percpu *vf_stats; struct delayed_work vf_takeover; + struct delayed_work vfns_work; /* 1: allocated, serial number is valid. 0: not allocated */ u32 vf_alloc; @@ -1075,6 +1076,8 @@ struct net_device_context { struct netvsc_device_info *saved_netvsc_dev_info; }; +void netvsc_vfns_work(struct work_struct *w); + /* Azure hosts don't support non-TCP port numbers in hashing for fragmented * packets. We can use ethtool to change UDP hash level when necessary. */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f44753756358..39c892e46cb0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2522,6 +2522,7 @@ static int netvsc_probe(struct hv_device *dev, spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); + INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work); net_device_ctx->vf_stats = netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats); @@ -2666,6 +2667,8 @@ static void netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); + nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev) { cancel_work_sync(&nvdev->subchan_work); @@ -2707,6 +2710,7 @@ static int netvsc_suspend(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev == NULL) { @@ -2800,6 +2804,27 @@ static void netvsc_event_set_vf_ns(struct net_device *ndev) } } +void netvsc_vfns_work(struct work_struct *w) +{ + struct net_device_context *ndev_ctx = + container_of(w, struct net_device_context, vfns_work.work); + struct net_device *ndev; + + if (!rtnl_trylock()) { + schedule_delayed_work(&ndev_ctx->vfns_work, 1); + return; + } + + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (!ndev) + goto out; + + netvsc_event_set_vf_ns(ndev); + +out: + rtnl_unlock(); +} + /* * On Hyper-V, every VF interface is matched with a corresponding * synthetic interface. The synthetic interface is presented first @@ -2810,10 +2835,12 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct net_device_context *ndev_ctx; int ret = 0; if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) { - netvsc_event_set_vf_ns(event_dev); + ndev_ctx = netdev_priv(event_dev); + schedule_delayed_work(&ndev_ctx->vfns_work, 0); return NOTIFY_DONE; } diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 39fe28af48b9..0178219f0db5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -710,9 +710,13 @@ static struct nsim_rq *nsim_queue_alloc(void) static void nsim_queue_free(struct net_device *dev, struct nsim_rq *rq) { hrtimer_cancel(&rq->napi_timer); - local_bh_disable(); - dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); - local_bh_enable(); + + if (rq->skb_queue.qlen) { + local_bh_disable(); + dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); + local_bh_enable(); + } + skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kfree(rq); } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index fda2e27c1810..cad6ed3aa10b 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -91,6 +91,7 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL; + gpiod_put(mdiodev->reset_gpio); reset_control_put(mdiodev->reset_ctrl); mdiodev->bus->mdio_map[mdiodev->addr] = NULL; diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c index 48dc4bf85125..f43973e73ea3 100644 --- a/drivers/net/phy/mdio_bus_provider.c +++ b/drivers/net/phy/mdio_bus_provider.c @@ -443,9 +443,6 @@ void mdiobus_unregister(struct mii_bus *bus) if (!mdiodev) continue; - if (mdiodev->reset_gpio) - gpiod_put(mdiodev->reset_gpio); - mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); } diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index 6a3d8a754eb8..58c6d47fbe04 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -362,6 +362,13 @@ struct vsc85xx_hw_stat { u16 mask; }; +struct vsc8531_skb_cb { + u32 ns; +}; + +#define VSC8531_SKB_CB(skb) \ + ((struct vsc8531_skb_cb *)((skb)->cb)) + struct vsc8531_private { int rate_magic; u16 supp_led_modes; @@ -410,6 +417,11 @@ struct vsc8531_private { */ struct mutex ts_lock; struct mutex phc_lock; + + /* list of skbs that were received and need timestamp information but it + * didn't received it yet + */ + struct sk_buff_head rx_skbs_list; }; /* Shared structure between the PHYs of the same package. diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 7ed6522fb0ef..f1c9ce351ab4 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2335,6 +2335,13 @@ static int vsc85xx_probe(struct phy_device *phydev) return vsc85xx_dt_led_modes_get(phydev, default_mode); } +static void vsc85xx_remove(struct phy_device *phydev) +{ + struct vsc8531_private *priv = phydev->priv; + + skb_queue_purge(&priv->rx_skbs_list); +} + /* Microsemi VSC85xx PHYs */ static struct phy_driver vsc85xx_driver[] = { { @@ -2589,6 +2596,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8574_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, @@ -2614,6 +2622,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8574_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, @@ -2639,6 +2648,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, @@ -2662,6 +2672,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, @@ -2685,6 +2696,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index 275706de5847..de6c7312e8f2 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1194,9 +1194,7 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts, { struct vsc8531_private *vsc8531 = container_of(mii_ts, struct vsc8531_private, mii_ts); - struct skb_shared_hwtstamps *shhwtstamps = NULL; struct vsc85xx_ptphdr *ptphdr; - struct timespec64 ts; unsigned long ns; if (!vsc8531->ptp->configured) @@ -1206,27 +1204,52 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts, type == PTP_CLASS_NONE) return false; - vsc85xx_gettime(&vsc8531->ptp->caps, &ts); - ptphdr = get_ptp_header_rx(skb, vsc8531->ptp->rx_filter); if (!ptphdr) return false; - shhwtstamps = skb_hwtstamps(skb); - memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); - ns = ntohl(ptphdr->rsrvd2); - /* nsec is in reserved field */ - if (ts.tv_nsec < ns) - ts.tv_sec--; + VSC8531_SKB_CB(skb)->ns = ns; + skb_queue_tail(&vsc8531->rx_skbs_list, skb); - shhwtstamps->hwtstamp = ktime_set(ts.tv_sec, ns); - netif_rx(skb); + ptp_schedule_worker(vsc8531->ptp->ptp_clock, 0); return true; } +static long vsc85xx_do_aux_work(struct ptp_clock_info *info) +{ + struct vsc85xx_ptp *ptp = container_of(info, struct vsc85xx_ptp, caps); + struct skb_shared_hwtstamps *shhwtstamps = NULL; + struct phy_device *phydev = ptp->phydev; + struct vsc8531_private *priv = phydev->priv; + struct sk_buff_head received; + struct sk_buff *rx_skb; + struct timespec64 ts; + unsigned long flags; + + __skb_queue_head_init(&received); + spin_lock_irqsave(&priv->rx_skbs_list.lock, flags); + skb_queue_splice_tail_init(&priv->rx_skbs_list, &received); + spin_unlock_irqrestore(&priv->rx_skbs_list.lock, flags); + + vsc85xx_gettime(info, &ts); + while ((rx_skb = __skb_dequeue(&received)) != NULL) { + shhwtstamps = skb_hwtstamps(rx_skb); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + + if (ts.tv_nsec < VSC8531_SKB_CB(rx_skb)->ns) + ts.tv_sec--; + + shhwtstamps->hwtstamp = ktime_set(ts.tv_sec, + VSC8531_SKB_CB(rx_skb)->ns); + netif_rx(rx_skb); + } + + return -1; +} + static const struct ptp_clock_info vsc85xx_clk_caps = { .owner = THIS_MODULE, .name = "VSC85xx timer", @@ -1240,6 +1263,7 @@ static const struct ptp_clock_info vsc85xx_clk_caps = { .adjfine = &vsc85xx_adjfine, .gettime64 = &vsc85xx_gettime, .settime64 = &vsc85xx_settime, + .do_aux_work = &vsc85xx_do_aux_work, }; static struct vsc8531_private *vsc8584_base_priv(struct phy_device *phydev) @@ -1567,6 +1591,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev) mutex_init(&vsc8531->phc_lock); mutex_init(&vsc8531->ts_lock); + skb_queue_head_init(&vsc8531->rx_skbs_list); /* Retrieve the shared load/save GPIO. Request it as non exclusive as * the same GPIO can be requested by all the PHYs of the same package. diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 4c6d905f0a9f..87adb6508017 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1965,24 +1965,27 @@ static int nxp_c45_macsec_ability(struct phy_device *phydev) return macsec_ability; } +static bool tja11xx_phy_id_compare(struct phy_device *phydev, + const struct phy_driver *phydrv) +{ + u32 id = phydev->is_c45 ? phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] : + phydev->phy_id; + + return phy_id_compare(id, phydrv->phy_id, phydrv->phy_id_mask); +} + static int tja11xx_no_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return !nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + !nxp_c45_macsec_ability(phydev); } static int tja11xx_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + nxp_c45_macsec_ability(phydev); } static const struct nxp_c45_regmap tja1120_regmap = { diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 8c98cbd4b06d..824c8dc4120b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -33,6 +33,7 @@ #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> +#include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> @@ -1598,11 +1599,14 @@ static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; - if (list_empty(&ppp->channels)) + pch = list_first_or_null_rcu(&ppp->channels, struct channel, clist); + if (!pch) + return -ENODEV; + + chan = READ_ONCE(pch->chan); + if (!chan) return -ENODEV; - pch = list_first_entry(&ppp->channels, struct channel, clist); - chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; @@ -2994,7 +2998,7 @@ ppp_unregister_channel(struct ppp_channel *chan) */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); - pch->chan = NULL; + WRITE_ONCE(pch->chan, NULL); spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); @@ -3515,7 +3519,7 @@ ppp_connect_channel(struct channel *pch, int unit) hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; - list_add_tail(&pch->clist, &ppp->channels); + list_add_tail_rcu(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); @@ -3545,10 +3549,11 @@ ppp_disconnect_channel(struct channel *pch) if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); - list_del(&pch->clist); + list_del_rcu(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); + synchronize_net(); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 399ce9febda4..f4e91ba64a66 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1041,6 +1041,10 @@ pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers) int pw_budget; pw_budget = regulator_get_unclaimed_power_budget(supply); + if (!pw_budget) + /* Do nothing if no power budget */ + continue; + /* Max power budget per manager */ if (pw_budget > 6000000) pw_budget = 6000000; @@ -1162,12 +1166,44 @@ pd692x0_write_ports_matrix(struct pd692x0_priv *priv, return 0; } +static void pd692x0_of_put_managers(struct pd692x0_priv *priv, + struct pd692x0_manager *manager, + int nmanagers) +{ + int i, j; + + for (i = 0; i < nmanagers; i++) { + for (j = 0; j < manager[i].nports; j++) + of_node_put(manager[i].port_node[j]); + of_node_put(manager[i].node); + } +} + +static void pd692x0_managers_free_pw_budget(struct pd692x0_priv *priv) +{ + int i; + + for (i = 0; i < PD692X0_MAX_MANAGERS; i++) { + struct regulator *supply; + + if (!priv->manager_reg[i] || !priv->manager_pw_budget[i]) + continue; + + supply = priv->manager_reg[i]->supply; + if (!supply) + continue; + + regulator_free_power_budget(supply, + priv->manager_pw_budget[i]); + } +} + static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) { struct pd692x0_manager *manager __free(kfree) = NULL; struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS]; - int ret, i, j, nmanagers; + int ret, nmanagers; /* Should we flash the port matrix */ if (priv->fw_state != PD692X0_FW_OK && @@ -1185,31 +1221,27 @@ static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) nmanagers = ret; ret = pd692x0_register_managers_regulator(priv, manager, nmanagers); if (ret) - goto out; + goto err_of_managers; ret = pd692x0_configure_managers(priv, nmanagers); if (ret) - goto out; + goto err_of_managers; ret = pd692x0_set_ports_matrix(priv, manager, nmanagers, port_matrix); if (ret) - goto out; + goto err_managers_req_pw; ret = pd692x0_write_ports_matrix(priv, port_matrix); if (ret) - goto out; - -out: - for (i = 0; i < nmanagers; i++) { - struct regulator *supply = priv->manager_reg[i]->supply; + goto err_managers_req_pw; - regulator_free_power_budget(supply, - priv->manager_pw_budget[i]); + pd692x0_of_put_managers(priv, manager, nmanagers); + return 0; - for (j = 0; j < manager[i].nports; j++) - of_node_put(manager[i].port_node[j]); - of_node_put(manager[i].node); - } +err_managers_req_pw: + pd692x0_managers_free_pw_budget(priv); +err_of_managers: + pd692x0_of_put_managers(priv, manager, nmanagers); return ret; } @@ -1748,6 +1780,7 @@ static void pd692x0_i2c_remove(struct i2c_client *client) { struct pd692x0_priv *priv = i2c_get_clientdata(client); + pd692x0_managers_free_pw_budget(priv); firmware_upload_unregister(priv->fwl); } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9b0318fb50b5..792ddda1ad49 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -676,6 +676,7 @@ static int ax88772_init_mdio(struct usbnet *dev) priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; + priv->mdio->phy_mask = ~(BIT(priv->phy_addr & 0x1f) | BIT(AX_EMBD_PHY_ADDR)); /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index ea0e5e276cd6..5d123df0a866 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -2087,6 +2087,13 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long)&wwan_info, }, + /* Intel modem (label from OEM reads Fibocom L850-GL) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x8087, 0x095a, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, + }, + /* DisplayLink docking stations */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index f5647ee0adde..e56901bb6ebc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1361,6 +1361,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1057, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990A */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1077, 2)}, /* Telit FN990A w/audio */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 995a7207bdf8..f357a7ac70ac 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -81,7 +81,7 @@ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) static __inline__ int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index edd811444ce5..e0d88d3199c1 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -28,6 +28,17 @@ source "drivers/nvmem/layouts/Kconfig" # Devices +config NVMEM_AN8855_EFUSE + tristate "Airoha AN8855 eFuse support" + depends on MFD_AIROHA_AN8855 || COMPILE_TEST + help + Say y here to enable support for reading eFuses on Airoha AN8855 + Switch. These are e.g. used to store factory programmed + calibration data required for the PHY. + + This driver can also be built as a module. If so, the module will + be called nvmem-an8855-efuse. + config NVMEM_APPLE_EFUSES tristate "Apple eFuse support" depends on ARCH_APPLE || COMPILE_TEST @@ -240,6 +251,16 @@ config NVMEM_NINTENDO_OTP This driver can also be built as a module. If so, the module will be called nvmem-nintendo-otp. +config NVMEM_S32G_OCOTP + tristate "S32G SoC OCOTP support" + depends on ARCH_S32 + help + This is a driver for the 'OCOTP' peripheral available on S32G + platforms. + + If you say Y here, you will get support for the One Time + Programmable memory pages. + config NVMEM_QCOM_QFPROM tristate "QCOM QFPROM Support" depends on ARCH_QCOM || COMPILE_TEST diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile index 2021d59688db..70a4464dcb1e 100644 --- a/drivers/nvmem/Makefile +++ b/drivers/nvmem/Makefile @@ -10,6 +10,8 @@ nvmem_layouts-y := layouts.o obj-y += layouts/ # Devices +obj-$(CONFIG_NVMEM_AN8855_EFUSE) += nvmem-an8855-efuse.o +nvmem-an8855-efuse-y := an8855-efuse.o obj-$(CONFIG_NVMEM_APPLE_EFUSES) += nvmem-apple-efuses.o nvmem-apple-efuses-y := apple-efuses.o obj-$(CONFIG_NVMEM_APPLE_SPMI) += apple_nvmem_spmi.o @@ -79,6 +81,8 @@ obj-$(CONFIG_NVMEM_SUNPLUS_OCOTP) += nvmem_sunplus_ocotp.o nvmem_sunplus_ocotp-y := sunplus-ocotp.o obj-$(CONFIG_NVMEM_SUNXI_SID) += nvmem_sunxi_sid.o nvmem_sunxi_sid-y := sunxi_sid.o +obj-$(CONFIG_NVMEM_S32G_OCOTP) += nvmem-s32g-ocotp-nvmem.o +nvmem-s32g-ocotp-nvmem-y := s32g-ocotp-nvmem.o obj-$(CONFIG_NVMEM_U_BOOT_ENV) += nvmem_u-boot-env.o nvmem_u-boot-env-y := u-boot-env.o obj-$(CONFIG_NVMEM_UNIPHIER_EFUSE) += nvmem-uniphier-efuse.o diff --git a/drivers/nvmem/an8855-efuse.c b/drivers/nvmem/an8855-efuse.c new file mode 100644 index 000000000000..d1afde6f623f --- /dev/null +++ b/drivers/nvmem/an8855-efuse.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Airoha AN8855 Switch EFUSE Driver + */ + +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/nvmem-provider.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> + +#define AN8855_EFUSE_CELL 50 + +#define AN8855_EFUSE_DATA0 0x1000a500 +#define AN8855_EFUSE_R50O GENMASK(30, 24) + +static int an8855_efuse_read(void *context, unsigned int offset, + void *val, size_t bytes) +{ + struct regmap *regmap = context; + + return regmap_bulk_read(regmap, AN8855_EFUSE_DATA0 + offset, + val, bytes / sizeof(u32)); +} + +static int an8855_efuse_probe(struct platform_device *pdev) +{ + struct nvmem_config an8855_nvmem_config = { + .name = "an8855-efuse", + .size = AN8855_EFUSE_CELL * sizeof(u32), + .stride = sizeof(u32), + .word_size = sizeof(u32), + .reg_read = an8855_efuse_read, + }; + struct device *dev = &pdev->dev; + struct nvmem_device *nvmem; + struct regmap *regmap; + + /* Assign NVMEM priv to MFD regmap */ + regmap = dev_get_regmap(dev->parent, NULL); + if (!regmap) + return -ENOENT; + + an8855_nvmem_config.priv = regmap; + an8855_nvmem_config.dev = dev; + nvmem = devm_nvmem_register(dev, &an8855_nvmem_config); + + return PTR_ERR_OR_ZERO(nvmem); +} + +static const struct of_device_id an8855_efuse_of_match[] = { + { .compatible = "airoha,an8855-efuse", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, an8855_efuse_of_match); + +static struct platform_driver an8855_efuse_driver = { + .probe = an8855_efuse_probe, + .driver = { + .name = "an8855-efuse", + .of_match_table = an8855_efuse_of_match, + }, +}; +module_platform_driver(an8855_efuse_driver); + +MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>"); +MODULE_DESCRIPTION("Driver for AN8855 Switch EFUSE"); +MODULE_LICENSE("GPL"); diff --git a/drivers/nvmem/s32g-ocotp-nvmem.c b/drivers/nvmem/s32g-ocotp-nvmem.c new file mode 100644 index 000000000000..119871ab3a94 --- /dev/null +++ b/drivers/nvmem/s32g-ocotp-nvmem.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2023-2025 NXP + */ + +#include <linux/device.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/nvmem-provider.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> + +struct s32g_ocotp_priv { + struct device *dev; + void __iomem *base; +}; + +static int s32g_ocotp_read(void *context, unsigned int offset, + void *val, size_t bytes) +{ + struct s32g_ocotp_priv *s32g_data = context; + u32 *dst = val; + + while (bytes >= sizeof(u32)) { + *dst++ = ioread32(s32g_data->base + offset); + + bytes -= sizeof(u32); + offset += sizeof(u32); + } + + return 0; +} + +static struct nvmem_keepout s32g_keepouts[] = { + { .start = 0, .end = 520 }, + { .start = 540, .end = 564 }, + { .start = 596, .end = 664 }, + { .start = 668, .end = 676 }, + { .start = 684, .end = 732 }, + { .start = 744, .end = 864 }, + { .start = 908, .end = 924 }, + { .start = 928, .end = 936 }, + { .start = 948, .end = 964 }, + { .start = 968, .end = 976 }, + { .start = 984, .end = 1012 }, +}; + +static struct nvmem_config s32g_ocotp_nvmem_config = { + .name = "s32g-ocotp", + .add_legacy_fixed_of_cells = true, + .read_only = true, + .word_size = 4, + .reg_read = s32g_ocotp_read, + .keepout = s32g_keepouts, + .nkeepout = ARRAY_SIZE(s32g_keepouts), +}; + +static const struct of_device_id ocotp_of_match[] = { + { .compatible = "nxp,s32g2-ocotp" }, + { /* sentinel */ } +}; + +static int s32g_ocotp_probe(struct platform_device *pdev) +{ + struct s32g_ocotp_priv *s32g_data; + struct device *dev = &pdev->dev; + struct nvmem_device *nvmem; + struct resource *res; + + s32g_data = devm_kzalloc(dev, sizeof(*s32g_data), GFP_KERNEL); + if (!s32g_data) + return -ENOMEM; + + s32g_data->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(s32g_data->base)) + return dev_err_probe(dev, PTR_ERR(s32g_data->base), + "Cannot map OCOTP device.\n"); + + s32g_data->dev = dev; + s32g_ocotp_nvmem_config.dev = dev; + s32g_ocotp_nvmem_config.priv = s32g_data; + s32g_ocotp_nvmem_config.size = resource_size(res); + + nvmem = devm_nvmem_register(dev, &s32g_ocotp_nvmem_config); + + return PTR_ERR_OR_ZERO(nvmem); +} + +static struct platform_driver s32g_ocotp_driver = { + .probe = s32g_ocotp_probe, + .driver = { + .name = "s32g-ocotp", + .of_match_table = ocotp_of_match, + }, +}; +module_platform_driver(s32g_ocotp_driver); +MODULE_AUTHOR("NXP"); +MODULE_DESCRIPTION("S32G OCOTP driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c index 443b15422fc1..601cbb22574f 100644 --- a/drivers/parisc/eisa_eeprom.c +++ b/drivers/parisc/eisa_eeprom.c @@ -15,8 +15,6 @@ #include <linux/uaccess.h> #include <asm/eisa_eeprom.h> -#define EISA_EEPROM_MINOR 241 - static loff_t eisa_eeprom_llseek(struct file *file, loff_t offset, int origin) { return fixed_size_llseek(file, offset, origin, HPEE_MAX_LENGTH); diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index f121836c3cf4..937ea6ae1ac4 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -400,7 +400,7 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) if (val & XILINX_PCIE_RPIFR1_MSI_INTR) { val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR2) & XILINX_PCIE_RPIFR2_MSG_DATA; - domain = pcie->msi_domain->parent; + domain = pcie->msi_domain; } else { val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >> XILINX_PCIE_RPIFR1_INTR_SHIFT; diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index b679c7f28f51..1bd5bf4a6097 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -306,9 +306,6 @@ static bool vmd_init_dev_msi_info(struct device *dev, struct irq_domain *domain, struct irq_domain *real_parent, struct msi_domain_info *info) { - if (WARN_ON_ONCE(info->bus_token != DOMAIN_BUS_PCI_DEVICE_MSIX)) - return false; - if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) return false; diff --git a/drivers/peci/controller/peci-npcm.c b/drivers/peci/controller/peci-npcm.c index c77591ca583d..931868991241 100644 --- a/drivers/peci/controller/peci-npcm.c +++ b/drivers/peci/controller/peci-npcm.c @@ -221,7 +221,6 @@ static const struct regmap_config npcm_peci_regmap_config = { .reg_bits = 8, .val_bits = 8, .max_register = NPCM_PECI_MAX_REG, - .fast_io = true, }; static const struct peci_controller_ops npcm_ops = { diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c index 54986a752f7d..a94009203e01 100644 --- a/drivers/platform/x86/amd/hsmp/acpi.c +++ b/drivers/platform/x86/amd/hsmp/acpi.c @@ -504,7 +504,7 @@ static int init_acpi(struct device *dev) dev_set_drvdata(dev, &hsmp_pdev->sock[sock_ind]); - return ret; + return 0; } static const struct bin_attribute hsmp_metric_tbl_attr = { diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c index 885e2f8136fd..19f82c1d3090 100644 --- a/drivers/platform/x86/amd/hsmp/hsmp.c +++ b/drivers/platform/x86/amd/hsmp/hsmp.c @@ -356,6 +356,11 @@ ssize_t hsmp_metric_tbl_read(struct hsmp_socket *sock, char *buf, size_t size) if (!sock || !buf) return -EINVAL; + if (!sock->metric_tbl_addr) { + dev_err(sock->dev, "Metrics table address not available\n"); + return -ENOMEM; + } + /* Do not support lseek(), also don't allow more than the size of metric table */ if (size != sizeof(struct hsmp_metric_table)) { dev_err(sock->dev, "Wrong buffer size\n"); diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index ded4c84f5ed1..7ffc659b2794 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -28,10 +28,15 @@ static struct quirk_entry quirk_spurious_8042 = { .spurious_8042 = true, }; +static struct quirk_entry quirk_s2idle_spurious_8042 = { + .s2idle_bug_mmio = FCH_PM_BASE + FCH_PM_SCRATCH, + .spurious_8042 = true, +}; + static const struct dmi_system_id fwbug_list[] = { { .ident = "L14 Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20X5"), @@ -39,7 +44,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14s Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20XF"), @@ -47,7 +52,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "X13 Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20XH"), @@ -55,7 +60,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14 Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20XK"), @@ -63,7 +68,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14 Gen1 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20UD"), @@ -71,7 +76,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14 Gen1 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20UE"), @@ -79,7 +84,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14s Gen1 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20UH"), @@ -87,7 +92,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "T14s Gen1 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20UJ"), @@ -95,7 +100,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "P14s Gen1 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "20Y1"), @@ -103,7 +108,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "P14s Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "21A0"), @@ -111,7 +116,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "P14s Gen2 AMD", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "21A1"), @@ -152,7 +157,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "IdeaPad 1 14AMN7", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82VF"), @@ -160,7 +165,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "IdeaPad 1 15AMN7", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82VG"), @@ -168,7 +173,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "IdeaPad 1 15AMN7", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82X5"), @@ -176,7 +181,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "IdeaPad Slim 3 14AMN8", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82XN"), @@ -184,7 +189,7 @@ static const struct dmi_system_id fwbug_list[] = { }, { .ident = "IdeaPad Slim 3 15AMN8", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82XQ"), @@ -193,7 +198,7 @@ static const struct dmi_system_id fwbug_list[] = { /* https://gitlab.freedesktop.org/drm/amd/-/issues/4434 */ { .ident = "Lenovo Yoga 6 13ALC6", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82ND"), @@ -202,7 +207,7 @@ static const struct dmi_system_id fwbug_list[] = { /* https://gitlab.freedesktop.org/drm/amd/-/issues/2684 */ { .ident = "HP Laptop 15s-eq2xxx", - .driver_data = &quirk_s2idle_bug, + .driver_data = &quirk_s2idle_spurious_8042, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15s-eq2xxx"), @@ -285,6 +290,16 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev) { const struct dmi_system_id *dmi_id; + /* + * IRQ1 may cause an interrupt during resume even without a keyboard + * press. + * + * Affects Renoir, Cezanne and Barcelo SoCs + * + * A solution is available in PMFW 64.66.0, but it must be activated by + * SBIOS. If SBIOS is known to have the fix a quirk can be added for + * a given system to avoid workaround. + */ if (dev->cpu_id == AMD_CPU_ID_CZN) dev->disable_8042_wakeup = true; @@ -295,6 +310,5 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev) if (dev->quirks->s2idle_bug_mmio) pr_info("Using s2idle quirk to avoid %s platform firmware bug\n", dmi_id->ident); - if (dev->quirks->spurious_8042) - dev->disable_8042_wakeup = true; + dev->disable_8042_wakeup = dev->quirks->spurious_8042; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index 0b9b23eb7c2c..bd318fd02ccf 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -530,19 +530,6 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) static int amd_pmc_wa_irq1(struct amd_pmc_dev *pdev) { struct device *d; - int rc; - - /* cezanne platform firmware has a fix in 64.66.0 */ - if (pdev->cpu_id == AMD_CPU_ID_CZN) { - if (!pdev->major) { - rc = amd_pmc_get_smu_version(pdev); - if (rc) - return rc; - } - - if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65)) - return 0; - } d = bus_find_device_by_name(&serio_bus, NULL, "serio0"); if (!d) diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c index 01c72b91a50d..444786102f02 100644 --- a/drivers/platform/x86/dell/dell-smbios-base.c +++ b/drivers/platform/x86/dell/dell-smbios-base.c @@ -39,6 +39,7 @@ struct token_sysfs_data { struct smbios_device { struct list_head list; struct device *device; + int priority; int (*call_fn)(struct calling_interface_buffer *arg); }; @@ -145,7 +146,7 @@ int dell_smbios_error(int value) } EXPORT_SYMBOL_GPL(dell_smbios_error); -int dell_smbios_register_device(struct device *d, void *call_fn) +int dell_smbios_register_device(struct device *d, int priority, void *call_fn) { struct smbios_device *priv; @@ -154,6 +155,7 @@ int dell_smbios_register_device(struct device *d, void *call_fn) return -ENOMEM; get_device(d); priv->device = d; + priv->priority = priority; priv->call_fn = call_fn; mutex_lock(&smbios_mutex); list_add_tail(&priv->list, &smbios_device_list); @@ -292,28 +294,25 @@ EXPORT_SYMBOL_GPL(dell_smbios_call_filter); int dell_smbios_call(struct calling_interface_buffer *buffer) { - int (*call_fn)(struct calling_interface_buffer *) = NULL; - struct device *selected_dev = NULL; + struct smbios_device *selected = NULL; struct smbios_device *priv; int ret; mutex_lock(&smbios_mutex); list_for_each_entry(priv, &smbios_device_list, list) { - if (!selected_dev || priv->device->id >= selected_dev->id) { - dev_dbg(priv->device, "Trying device ID: %d\n", - priv->device->id); - call_fn = priv->call_fn; - selected_dev = priv->device; + if (!selected || priv->priority >= selected->priority) { + dev_dbg(priv->device, "Trying device ID: %d\n", priv->priority); + selected = priv; } } - if (!selected_dev) { + if (!selected) { ret = -ENODEV; pr_err("No dell-smbios drivers are loaded\n"); goto out_smbios_call; } - ret = call_fn(buffer); + ret = selected->call_fn(buffer); out_smbios_call: mutex_unlock(&smbios_mutex); diff --git a/drivers/platform/x86/dell/dell-smbios-smm.c b/drivers/platform/x86/dell/dell-smbios-smm.c index 4d375985c85f..7055e2c40f34 100644 --- a/drivers/platform/x86/dell/dell-smbios-smm.c +++ b/drivers/platform/x86/dell/dell-smbios-smm.c @@ -125,8 +125,7 @@ int init_dell_smbios_smm(void) if (ret) goto fail_platform_device_add; - ret = dell_smbios_register_device(&platform_device->dev, - &dell_smbios_smm_call); + ret = dell_smbios_register_device(&platform_device->dev, 0, &dell_smbios_smm_call); if (ret) goto fail_register; diff --git a/drivers/platform/x86/dell/dell-smbios-wmi.c b/drivers/platform/x86/dell/dell-smbios-wmi.c index ae9012549560..a7dca8c59d60 100644 --- a/drivers/platform/x86/dell/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell/dell-smbios-wmi.c @@ -264,9 +264,7 @@ static int dell_smbios_wmi_probe(struct wmi_device *wdev, const void *context) if (ret) return ret; - /* ID is used by dell-smbios to set priority of drivers */ - wdev->dev.id = 1; - ret = dell_smbios_register_device(&wdev->dev, &dell_smbios_wmi_call); + ret = dell_smbios_register_device(&wdev->dev, 1, &dell_smbios_wmi_call); if (ret) return ret; diff --git a/drivers/platform/x86/dell/dell-smbios.h b/drivers/platform/x86/dell/dell-smbios.h index 77baa15eb523..f421b8533a9e 100644 --- a/drivers/platform/x86/dell/dell-smbios.h +++ b/drivers/platform/x86/dell/dell-smbios.h @@ -64,7 +64,7 @@ struct calling_interface_structure { struct calling_interface_token tokens[]; } __packed; -int dell_smbios_register_device(struct device *d, void *call_fn); +int dell_smbios_register_device(struct device *d, int priority, void *call_fn); void dell_smbios_unregister_device(struct device *d); int dell_smbios_error(int value); diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index db5fdee2109c..60c8ac8d902c 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -92,9 +92,9 @@ static const char * const victus_thermal_profile_boards[] = { "8A25" }; -/* DMI Board names of Victus 16-s1000 laptops */ +/* DMI Board names of Victus 16-r1000 and Victus 16-s1000 laptops */ static const char * const victus_s_thermal_profile_boards[] = { - "8C9C" + "8C99", "8C9C" }; enum hp_wmi_radio { diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c index 6df55c8e16b7..bfcf92aa4d69 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c @@ -192,9 +192,14 @@ static int uncore_read_control_freq(struct uncore_data *data, unsigned int *valu static int write_eff_lat_ctrl(struct uncore_data *data, unsigned int val, enum uncore_index index) { struct tpmi_uncore_cluster_info *cluster_info; + struct tpmi_uncore_struct *uncore_root; u64 control; cluster_info = container_of(data, struct tpmi_uncore_cluster_info, uncore_data); + uncore_root = cluster_info->uncore_root; + + if (uncore_root->write_blocked) + return -EPERM; if (cluster_info->root_domain) return -ENODATA; diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c index 92d1b62ea239..e9389876229e 100644 --- a/drivers/pps/kapi.c +++ b/drivers/pps/kapi.c @@ -109,16 +109,13 @@ struct pps_device *pps_register_source(struct pps_source_info *info, if (err < 0) { pr_err("%s: unable to create char device\n", info->name); - goto kfree_pps; + goto pps_register_source_exit; } dev_dbg(&pps->dev, "new PPS source %s\n", info->name); return pps; -kfree_pps: - kfree(pps); - pps_register_source_exit: pr_err("%s: unable to register source\n", info->name); diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 9463232af8d2..c6b8b6478276 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -374,6 +374,7 @@ int pps_register_cdev(struct pps_device *pps) pps->info.name); err = -EBUSY; } + kfree(pps); goto out_unlock; } pps->id = err; @@ -383,13 +384,11 @@ int pps_register_cdev(struct pps_device *pps) pps->dev.devt = MKDEV(pps_major, pps->id); dev_set_drvdata(&pps->dev, pps); dev_set_name(&pps->dev, "pps%d", pps->id); + pps->dev.release = pps_device_destruct; err = device_register(&pps->dev); if (err) goto free_idr; - /* Override the release function with our own */ - pps->dev.release = pps_device_destruct; - pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major, pps->id); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index a6aad743c282..b352df4cd3f9 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -24,6 +24,11 @@ #define PTP_DEFAULT_MAX_VCLOCKS 20 #define PTP_MAX_CHANNELS 2048 +enum { + PTP_LOCK_PHYSICAL = 0, + PTP_LOCK_VIRTUAL, +}; + struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; int head; diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index 2fdeedd60e21..64c950456517 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -154,6 +154,11 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp) return PTP_VCLOCK_REFRESH_INTERVAL; } +static void ptp_vclock_set_subclass(struct ptp_clock *ptp) +{ + lockdep_set_subclass(&ptp->clock.rwsem, PTP_LOCK_VIRTUAL); +} + static const struct ptp_clock_info ptp_vclock_info = { .owner = THIS_MODULE, .name = "ptp virtual clock", @@ -213,6 +218,8 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) return NULL; } + ptp_vclock_set_subclass(vclock->clock); + timecounter_init(&vclock->tc, &vclock->cc, 0); ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL); diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index feadb21a8f30..4be270f4d6c3 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -40,7 +40,6 @@ struct pca9450 { struct device *dev; struct regmap *regmap; struct gpio_desc *sd_vsel_gpio; - struct notifier_block restart_nb; enum pca9450_chip_type type; unsigned int rcnt; int irq; @@ -1100,10 +1099,9 @@ static irqreturn_t pca9450_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static int pca9450_i2c_restart_handler(struct notifier_block *nb, - unsigned long action, void *data) +static int pca9450_i2c_restart_handler(struct sys_off_data *data) { - struct pca9450 *pca9450 = container_of(nb, struct pca9450, restart_nb); + struct pca9450 *pca9450 = data->cb_data; struct i2c_client *i2c = container_of(pca9450->dev, struct i2c_client, dev); dev_dbg(&i2c->dev, "Restarting device..\n"); @@ -1261,10 +1259,9 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450->sd_vsel_fixed_low = of_property_read_bool(ldo5->dev.of_node, "nxp,sd-vsel-fixed-low"); - pca9450->restart_nb.notifier_call = pca9450_i2c_restart_handler; - pca9450->restart_nb.priority = PCA9450_RESTART_HANDLER_PRIORITY; - - if (register_restart_handler(&pca9450->restart_nb)) + if (devm_register_sys_off_handler(&i2c->dev, SYS_OFF_MODE_RESTART, + PCA9450_RESTART_HANDLER_PRIORITY, + pca9450_i2c_restart_handler, pca9450)) dev_warn(&i2c->dev, "Failed to register restart handler\n"); dev_info(&i2c->dev, "%s probed.\n", diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c index 5e67fdc88f49..d77ca486879f 100644 --- a/drivers/regulator/tps65219-regulator.c +++ b/drivers/regulator/tps65219-regulator.c @@ -454,9 +454,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev) irq_type->irq_name, irq_data); if (error) - return dev_err_probe(tps->dev, PTR_ERR(rdev), - "Failed to request %s IRQ %d: %d\n", - irq_type->irq_name, irq, error); + return dev_err_probe(tps->dev, error, + "Failed to request %s IRQ %d\n", + irq_type->irq_name, irq); } for (i = 0; i < pmic->dev_irq_size; ++i) { @@ -477,9 +477,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev) irq_type->irq_name, irq_data); if (error) - return dev_err_probe(tps->dev, PTR_ERR(rdev), - "Failed to request %s IRQ %d: %d\n", - irq_type->irq_name, irq, error); + return dev_err_probe(tps->dev, error, + "Failed to request %s IRQ %d\n", + irq_type->irq_name, irq); } return 0; diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index f2e42c1d51aa..98e334724a62 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -77,6 +77,13 @@ unsigned long sclp_console_full; /* The currently active SCLP command word. */ static sclp_cmdw_t active_cmd; +static inline struct sccb_header *sclpint_to_sccb(u32 sccb_int) +{ + if (sccb_int) + return __va(sccb_int); + return NULL; +} + static inline void sclp_trace(int prio, char *id, u32 a, u64 b, bool err) { struct sclp_trace_entry e; @@ -620,7 +627,7 @@ __sclp_find_req(u32 sccb) static bool ok_response(u32 sccb_int, sclp_cmdw_t cmd) { - struct sccb_header *sccb = (struct sccb_header *)__va(sccb_int); + struct sccb_header *sccb = sclpint_to_sccb(sccb_int); struct evbuf_header *evbuf; u16 response; @@ -659,7 +666,7 @@ static void sclp_interrupt_handler(struct ext_code ext_code, /* INT: Interrupt received (a=intparm, b=cmd) */ sclp_trace_sccb(0, "INT", param32, active_cmd, active_cmd, - (struct sccb_header *)__va(finished_sccb), + sclpint_to_sccb(finished_sccb), !ok_response(finished_sccb, active_cmd)); if (finished_sccb) { diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index c2fdc6553e62..1199d701c3f5 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -323,8 +323,6 @@ enum fnic_state { FNIC_IN_ETH_TRANS_FC_MODE, }; -struct mempool; - enum fnic_role_e { FNIC_ROLE_FCP_INITIATOR = 0, }; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 2db8d9529b8f..7c4d7bb3a56f 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -6280,7 +6280,6 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) } phba->nvmeio_trc_on = 1; phba->nvmeio_trc_output_idx = 0; - phba->nvmeio_trc = NULL; } else { nvmeio_off: phba->nvmeio_trc_size = 0; diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 2797aa75a689..aff6c9d5e7c2 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -666,7 +666,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport) * Take early refcount for outstanding I/O requests we schedule during * delete processing for unreg_vpi. Always keep this before * scsi_remove_host() as we can no longer obtain a reference through - * scsi_host_get() after scsi_host_remove as shost is set to SHOST_DEL. + * scsi_host_get() after scsi_remove_host as shost is set to SHOST_DEL. */ if (!scsi_host_get(shost)) return VPORT_INVAL; diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index a39f1da4ce47..a761c0aa5127 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -6606,6 +6606,8 @@ static struct iscsi_endpoint *qla4xxx_get_ep_fwdb(struct scsi_qla_host *ha, ep = qla4xxx_ep_connect(ha->host, (struct sockaddr *)dst_addr, 0); vfree(dst_addr); + if (IS_ERR(ep)) + return NULL; return ep; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 0847767d4d43..353cb60e1abe 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2674,8 +2674,10 @@ static int resp_rsup_tmfs(struct scsi_cmnd *scp, static int resp_err_recov_pg(unsigned char *p, int pcontrol, int target) { /* Read-Write Error Recovery page for mode_sense */ - unsigned char err_recov_pg[] = {0x1, 0xa, 0xc0, 11, 240, 0, 0, 0, - 5, 0, 0xff, 0xff}; + static const unsigned char err_recov_pg[] = { + 0x1, 0xa, 0xc0, 11, 240, 0, 0, 0, + 5, 0, 0xff, 0xff + }; memcpy(p, err_recov_pg, sizeof(err_recov_pg)); if (1 == pcontrol) @@ -2685,8 +2687,10 @@ static int resp_err_recov_pg(unsigned char *p, int pcontrol, int target) static int resp_disconnect_pg(unsigned char *p, int pcontrol, int target) { /* Disconnect-Reconnect page for mode_sense */ - unsigned char disconnect_pg[] = {0x2, 0xe, 128, 128, 0, 10, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0}; + static const unsigned char disconnect_pg[] = { + 0x2, 0xe, 128, 128, 0, 10, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0 + }; memcpy(p, disconnect_pg, sizeof(disconnect_pg)); if (1 == pcontrol) @@ -2696,9 +2700,11 @@ static int resp_disconnect_pg(unsigned char *p, int pcontrol, int target) static int resp_format_pg(unsigned char *p, int pcontrol, int target) { /* Format device page for mode_sense */ - unsigned char format_pg[] = {0x3, 0x16, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0x40, 0, 0, 0}; + static const unsigned char format_pg[] = { + 0x3, 0x16, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0x40, 0, 0, 0 + }; memcpy(p, format_pg, sizeof(format_pg)); put_unaligned_be16(sdebug_sectors_per, p + 10); @@ -2716,10 +2722,14 @@ static unsigned char caching_pg[] = {0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, static int resp_caching_pg(unsigned char *p, int pcontrol, int target) { /* Caching page for mode_sense */ - unsigned char ch_caching_pg[] = {/* 0x8, 18, */ 0x4, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; - unsigned char d_caching_pg[] = {0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, - 0xff, 0xff, 0xff, 0xff, 0x80, 0x14, 0, 0, 0, 0, 0, 0}; + static const unsigned char ch_caching_pg[] = { + /* 0x8, 18, */ 0x4, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 + }; + static const unsigned char d_caching_pg[] = { + 0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, + 0xff, 0xff, 0xff, 0xff, 0x80, 0x14, 0, 0, 0, 0, 0, 0 + }; if (SDEBUG_OPT_N_WCE & sdebug_opts) caching_pg[2] &= ~0x4; /* set WCE=0 (default WCE=1) */ @@ -2738,8 +2748,10 @@ static int resp_ctrl_m_pg(unsigned char *p, int pcontrol, int target) { /* Control mode page for mode_sense */ unsigned char ch_ctrl_m_pg[] = {/* 0xa, 10, */ 0x6, 0, 0, 0, 0, 0, 0, 0, 0, 0}; - unsigned char d_ctrl_m_pg[] = {0xa, 10, 2, 0, 0, 0, 0, 0, - 0, 0, 0x2, 0x4b}; + static const unsigned char d_ctrl_m_pg[] = { + 0xa, 10, 2, 0, 0, 0, 0, 0, + 0, 0, 0x2, 0x4b + }; if (sdebug_dsense) ctrl_m_pg[2] |= 0x4; @@ -2794,10 +2806,14 @@ static int resp_grouping_m_pg(unsigned char *p, int pcontrol, int target) static int resp_iec_m_pg(unsigned char *p, int pcontrol, int target) { /* Informational Exceptions control mode page for mode_sense */ - unsigned char ch_iec_m_pg[] = {/* 0x1c, 0xa, */ 0x4, 0xf, 0, 0, 0, 0, - 0, 0, 0x0, 0x0}; - unsigned char d_iec_m_pg[] = {0x1c, 0xa, 0x08, 0, 0, 0, 0, 0, - 0, 0, 0x0, 0x0}; + static const unsigned char ch_iec_m_pg[] = { + /* 0x1c, 0xa, */ 0x4, 0xf, 0, 0, 0, 0, + 0, 0, 0x0, 0x0 + }; + static const unsigned char d_iec_m_pg[] = { + 0x1c, 0xa, 0x08, 0, 0, 0, 0, 0, + 0, 0, 0x0, 0x0 + }; memcpy(p, iec_m_pg, sizeof(iec_m_pg)); if (1 == pcontrol) @@ -2809,8 +2825,9 @@ static int resp_iec_m_pg(unsigned char *p, int pcontrol, int target) static int resp_sas_sf_m_pg(unsigned char *p, int pcontrol, int target) { /* SAS SSP mode page - short format for mode_sense */ - unsigned char sas_sf_m_pg[] = {0x19, 0x6, - 0x6, 0x0, 0x7, 0xd0, 0x0, 0x0}; + static const unsigned char sas_sf_m_pg[] = { + 0x19, 0x6, 0x6, 0x0, 0x7, 0xd0, 0x0, 0x0 + }; memcpy(p, sas_sf_m_pg, sizeof(sas_sf_m_pg)); if (1 == pcontrol) @@ -2854,9 +2871,10 @@ static int resp_sas_pcd_m_spg(unsigned char *p, int pcontrol, int target, static int resp_sas_sha_m_spg(unsigned char *p, int pcontrol) { /* SAS SSP shared protocol specific port mode subpage */ - unsigned char sas_sha_m_pg[] = {0x59, 0x2, 0, 0xc, 0, 0x6, 0x10, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - }; + static const unsigned char sas_sha_m_pg[] = { + 0x59, 0x2, 0, 0xc, 0, 0x6, 0x10, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + }; memcpy(p, sas_sha_m_pg, sizeof(sas_sha_m_pg)); if (1 == pcontrol) @@ -2923,8 +2941,10 @@ static int process_medium_part_m_pg(struct sdebug_dev_info *devip, static int resp_compression_m_pg(unsigned char *p, int pcontrol, int target, unsigned char dce) { /* Compression page for mode_sense (tape) */ - unsigned char compression_pg[] = {0x0f, 14, 0x40, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 00, 00}; + static const unsigned char compression_pg[] = { + 0x0f, 14, 0x40, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0 + }; memcpy(p, compression_pg, sizeof(compression_pg)); if (dce) @@ -3282,9 +3302,10 @@ bad_pcode: static int resp_temp_l_pg(unsigned char *arr) { - unsigned char temp_l_pg[] = {0x0, 0x0, 0x3, 0x2, 0x0, 38, - 0x0, 0x1, 0x3, 0x2, 0x0, 65, - }; + static const unsigned char temp_l_pg[] = { + 0x0, 0x0, 0x3, 0x2, 0x0, 38, + 0x0, 0x1, 0x3, 0x2, 0x0, 65, + }; memcpy(arr, temp_l_pg, sizeof(temp_l_pg)); return sizeof(temp_l_pg); @@ -3292,8 +3313,9 @@ static int resp_temp_l_pg(unsigned char *arr) static int resp_ie_l_pg(unsigned char *arr) { - unsigned char ie_l_pg[] = {0x0, 0x0, 0x3, 0x3, 0x0, 0x0, 38, - }; + static const unsigned char ie_l_pg[] = { + 0x0, 0x0, 0x3, 0x3, 0x0, 0x0, 38, + }; memcpy(arr, ie_l_pg, sizeof(ie_l_pg)); if (iec_m_pg[2] & 0x4) { /* TEST bit set */ @@ -3305,11 +3327,12 @@ static int resp_ie_l_pg(unsigned char *arr) static int resp_env_rep_l_spg(unsigned char *arr) { - unsigned char env_rep_l_spg[] = {0x0, 0x0, 0x23, 0x8, - 0x0, 40, 72, 0xff, 45, 18, 0, 0, - 0x1, 0x0, 0x23, 0x8, - 0x0, 55, 72, 35, 55, 45, 0, 0, - }; + static const unsigned char env_rep_l_spg[] = { + 0x0, 0x0, 0x23, 0x8, + 0x0, 40, 72, 0xff, 45, 18, 0, 0, + 0x1, 0x0, 0x23, 0x8, + 0x0, 55, 72, 35, 55, 45, 0, 0, + }; memcpy(arr, env_rep_l_spg, sizeof(env_rep_l_spg)); return sizeof(env_rep_l_spg); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 169af7d47ce7..15ba493d2138 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -265,7 +265,7 @@ show_shost_supported_mode(struct device *dev, struct device_attribute *attr, return show_shost_mode(supported_mode, buf); } -static DEVICE_ATTR(supported_mode, S_IRUGO | S_IWUSR, show_shost_supported_mode, NULL); +static DEVICE_ATTR(supported_mode, S_IRUGO, show_shost_supported_mode, NULL); static ssize_t show_shost_active_mode(struct device *dev, @@ -279,7 +279,7 @@ show_shost_active_mode(struct device *dev, return show_shost_mode(shost->active_mode, buf); } -static DEVICE_ATTR(active_mode, S_IRUGO | S_IWUSR, show_shost_active_mode, NULL); +static DEVICE_ATTR(active_mode, S_IRUGO, show_shost_active_mode, NULL); static int check_reset_type(const char *str) { diff --git a/drivers/siox/siox-bus-gpio.c b/drivers/siox/siox-bus-gpio.c index d6f936464063..413d5f92311c 100644 --- a/drivers/siox/siox-bus-gpio.c +++ b/drivers/siox/siox-bus-gpio.c @@ -93,8 +93,7 @@ static int siox_gpio_probe(struct platform_device *pdev) smaster = devm_siox_master_alloc(dev, sizeof(*ddata)); if (!smaster) - return dev_err_probe(dev, -ENOMEM, - "failed to allocate siox master\n"); + return -ENOMEM; platform_set_drvdata(pdev, smaster); ddata = siox_master_get_devdata(smaster); diff --git a/drivers/slimbus/Kconfig b/drivers/slimbus/Kconfig index a0fdf9d792cb..60b0dcbc0ebb 100644 --- a/drivers/slimbus/Kconfig +++ b/drivers/slimbus/Kconfig @@ -13,13 +13,6 @@ menuconfig SLIMBUS if SLIMBUS # SLIMbus controllers -config SLIM_QCOM_CTRL - tristate "Qualcomm SLIMbus Manager Component" - depends on HAS_IOMEM - help - Select driver if Qualcomm's SLIMbus Manager Component is - programmed using Linux kernel. - config SLIM_QCOM_NGD_CTRL tristate "Qualcomm SLIMbus Satellite Non-Generic Device Component" depends on HAS_IOMEM && DMA_ENGINE && NET diff --git a/drivers/slimbus/Makefile b/drivers/slimbus/Makefile index d9aa011b6804..3cfb41c3b592 100644 --- a/drivers/slimbus/Makefile +++ b/drivers/slimbus/Makefile @@ -6,8 +6,5 @@ obj-$(CONFIG_SLIMBUS) += slimbus.o slimbus-y := core.o messaging.o sched.o stream.o #Controllers -obj-$(CONFIG_SLIM_QCOM_CTRL) += slim-qcom-ctrl.o -slim-qcom-ctrl-y := qcom-ctrl.o - obj-$(CONFIG_SLIM_QCOM_NGD_CTRL) += slim-qcom-ngd-ctrl.o slim-qcom-ngd-ctrl-y := qcom-ngd-ctrl.o diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c index 6f01d944f9c6..e2dbe4a66b70 100644 --- a/drivers/slimbus/messaging.c +++ b/drivers/slimbus/messaging.c @@ -143,8 +143,6 @@ int slim_do_transfer(struct slim_controller *ctrl, struct slim_msg_txn *txn) if (!txn->msg->comp) txn->comp = &done; - else - txn->comp = txn->comp; } ret = ctrl->xfer_msg(ctrl, txn); @@ -224,7 +222,7 @@ static u16 slim_slicesize(int code) /** * slim_xfer_msg() - Transfer a value info message on slim device * - * @sbdev: slim device to which this msg has to be transfered + * @sbdev: slim device to which this msg has to be transferred * @msg: value info message pointer * @mc: message code of the message * diff --git a/drivers/slimbus/qcom-ctrl.c b/drivers/slimbus/qcom-ctrl.c deleted file mode 100644 index ab344f7472f2..000000000000 --- a/drivers/slimbus/qcom-ctrl.c +++ /dev/null @@ -1,735 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2011-2017, The Linux Foundation - */ - -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/io.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> -#include <linux/delay.h> -#include <linux/clk.h> -#include <linux/of.h> -#include <linux/pm_runtime.h> -#include "slimbus.h" - -/* Manager registers */ -#define MGR_CFG 0x200 -#define MGR_STATUS 0x204 -#define MGR_INT_EN 0x210 -#define MGR_INT_STAT 0x214 -#define MGR_INT_CLR 0x218 -#define MGR_TX_MSG 0x230 -#define MGR_RX_MSG 0x270 -#define MGR_IE_STAT 0x2F0 -#define MGR_VE_STAT 0x300 -#define MGR_CFG_ENABLE 1 - -/* Framer registers */ -#define FRM_CFG 0x400 -#define FRM_STAT 0x404 -#define FRM_INT_EN 0x410 -#define FRM_INT_STAT 0x414 -#define FRM_INT_CLR 0x418 -#define FRM_WAKEUP 0x41C -#define FRM_CLKCTL_DONE 0x420 -#define FRM_IE_STAT 0x430 -#define FRM_VE_STAT 0x440 - -/* Interface registers */ -#define INTF_CFG 0x600 -#define INTF_STAT 0x604 -#define INTF_INT_EN 0x610 -#define INTF_INT_STAT 0x614 -#define INTF_INT_CLR 0x618 -#define INTF_IE_STAT 0x630 -#define INTF_VE_STAT 0x640 - -/* Interrupt status bits */ -#define MGR_INT_TX_NACKED_2 BIT(25) -#define MGR_INT_MSG_BUF_CONTE BIT(26) -#define MGR_INT_RX_MSG_RCVD BIT(30) -#define MGR_INT_TX_MSG_SENT BIT(31) - -/* Framer config register settings */ -#define FRM_ACTIVE 1 -#define CLK_GEAR 7 -#define ROOT_FREQ 11 -#define REF_CLK_GEAR 15 -#define INTR_WAKE 19 - -#define SLIM_MSG_ASM_FIRST_WORD(l, mt, mc, dt, ad) \ - ((l) | ((mt) << 5) | ((mc) << 8) | ((dt) << 15) | ((ad) << 16)) - -#define SLIM_ROOT_FREQ 24576000 -#define QCOM_SLIM_AUTOSUSPEND 1000 - -/* MAX message size over control channel */ -#define SLIM_MSGQ_BUF_LEN 40 -#define QCOM_TX_MSGS 2 -#define QCOM_RX_MSGS 8 -#define QCOM_BUF_ALLOC_RETRIES 10 - -#define CFG_PORT(r, v) ((v) ? CFG_PORT_V2(r) : CFG_PORT_V1(r)) - -/* V2 Component registers */ -#define CFG_PORT_V2(r) ((r ## _V2)) -#define COMP_CFG_V2 4 -#define COMP_TRUST_CFG_V2 0x3000 - -/* V1 Component registers */ -#define CFG_PORT_V1(r) ((r ## _V1)) -#define COMP_CFG_V1 0 -#define COMP_TRUST_CFG_V1 0x14 - -/* Resource group info for manager, and non-ported generic device-components */ -#define EE_MGR_RSC_GRP (1 << 10) -#define EE_NGD_2 (2 << 6) -#define EE_NGD_1 0 - -struct slim_ctrl_buf { - void *base; - spinlock_t lock; - int head; - int tail; - int sl_sz; - int n; -}; - -struct qcom_slim_ctrl { - struct slim_controller ctrl; - struct slim_framer framer; - struct device *dev; - void __iomem *base; - void __iomem *slew_reg; - - struct slim_ctrl_buf rx; - struct slim_ctrl_buf tx; - - struct completion **wr_comp; - int irq; - struct workqueue_struct *rxwq; - struct work_struct wd; - struct clk *rclk; - struct clk *hclk; -}; - -static void qcom_slim_queue_tx(struct qcom_slim_ctrl *ctrl, void *buf, - u8 len, u32 tx_reg) -{ - int count = (len + 3) >> 2; - - __iowrite32_copy(ctrl->base + tx_reg, buf, count); - - /* Ensure Oder of subsequent writes */ - mb(); -} - -static void *slim_alloc_rxbuf(struct qcom_slim_ctrl *ctrl) -{ - unsigned long flags; - int idx; - - spin_lock_irqsave(&ctrl->rx.lock, flags); - if ((ctrl->rx.tail + 1) % ctrl->rx.n == ctrl->rx.head) { - spin_unlock_irqrestore(&ctrl->rx.lock, flags); - dev_err(ctrl->dev, "RX QUEUE full!"); - return NULL; - } - idx = ctrl->rx.tail; - ctrl->rx.tail = (ctrl->rx.tail + 1) % ctrl->rx.n; - spin_unlock_irqrestore(&ctrl->rx.lock, flags); - - return ctrl->rx.base + (idx * ctrl->rx.sl_sz); -} - -static void slim_ack_txn(struct qcom_slim_ctrl *ctrl, int err) -{ - struct completion *comp; - unsigned long flags; - int idx; - - spin_lock_irqsave(&ctrl->tx.lock, flags); - idx = ctrl->tx.head; - ctrl->tx.head = (ctrl->tx.head + 1) % ctrl->tx.n; - spin_unlock_irqrestore(&ctrl->tx.lock, flags); - - comp = ctrl->wr_comp[idx]; - ctrl->wr_comp[idx] = NULL; - - complete(comp); -} - -static irqreturn_t qcom_slim_handle_tx_irq(struct qcom_slim_ctrl *ctrl, - u32 stat) -{ - int err = 0; - - if (stat & MGR_INT_TX_MSG_SENT) - writel_relaxed(MGR_INT_TX_MSG_SENT, - ctrl->base + MGR_INT_CLR); - - if (stat & MGR_INT_TX_NACKED_2) { - u32 mgr_stat = readl_relaxed(ctrl->base + MGR_STATUS); - u32 mgr_ie_stat = readl_relaxed(ctrl->base + MGR_IE_STAT); - u32 frm_stat = readl_relaxed(ctrl->base + FRM_STAT); - u32 frm_cfg = readl_relaxed(ctrl->base + FRM_CFG); - u32 frm_intr_stat = readl_relaxed(ctrl->base + FRM_INT_STAT); - u32 frm_ie_stat = readl_relaxed(ctrl->base + FRM_IE_STAT); - u32 intf_stat = readl_relaxed(ctrl->base + INTF_STAT); - u32 intf_intr_stat = readl_relaxed(ctrl->base + INTF_INT_STAT); - u32 intf_ie_stat = readl_relaxed(ctrl->base + INTF_IE_STAT); - - writel_relaxed(MGR_INT_TX_NACKED_2, ctrl->base + MGR_INT_CLR); - - dev_err(ctrl->dev, "TX Nack MGR:int:0x%x, stat:0x%x\n", - stat, mgr_stat); - dev_err(ctrl->dev, "TX Nack MGR:ie:0x%x\n", mgr_ie_stat); - dev_err(ctrl->dev, "TX Nack FRM:int:0x%x, stat:0x%x\n", - frm_intr_stat, frm_stat); - dev_err(ctrl->dev, "TX Nack FRM:cfg:0x%x, ie:0x%x\n", - frm_cfg, frm_ie_stat); - dev_err(ctrl->dev, "TX Nack INTF:intr:0x%x, stat:0x%x\n", - intf_intr_stat, intf_stat); - dev_err(ctrl->dev, "TX Nack INTF:ie:0x%x\n", - intf_ie_stat); - err = -ENOTCONN; - } - - slim_ack_txn(ctrl, err); - - return IRQ_HANDLED; -} - -static irqreturn_t qcom_slim_handle_rx_irq(struct qcom_slim_ctrl *ctrl, - u32 stat) -{ - u32 *rx_buf, pkt[10]; - bool q_rx = false; - u8 mc, mt, len; - - pkt[0] = readl_relaxed(ctrl->base + MGR_RX_MSG); - mt = SLIM_HEADER_GET_MT(pkt[0]); - len = SLIM_HEADER_GET_RL(pkt[0]); - mc = SLIM_HEADER_GET_MC(pkt[0]>>8); - - /* - * this message cannot be handled by ISR, so - * let work-queue handle it - */ - if (mt == SLIM_MSG_MT_CORE && mc == SLIM_MSG_MC_REPORT_PRESENT) { - rx_buf = (u32 *)slim_alloc_rxbuf(ctrl); - if (!rx_buf) { - dev_err(ctrl->dev, "dropping RX:0x%x due to RX full\n", - pkt[0]); - goto rx_ret_irq; - } - rx_buf[0] = pkt[0]; - - } else { - rx_buf = pkt; - } - - __ioread32_copy(rx_buf + 1, ctrl->base + MGR_RX_MSG + 4, - DIV_ROUND_UP(len, 4)); - - switch (mc) { - - case SLIM_MSG_MC_REPORT_PRESENT: - q_rx = true; - break; - case SLIM_MSG_MC_REPLY_INFORMATION: - case SLIM_MSG_MC_REPLY_VALUE: - slim_msg_response(&ctrl->ctrl, (u8 *)(rx_buf + 1), - (u8)(*rx_buf >> 24), (len - 4)); - break; - default: - dev_err(ctrl->dev, "unsupported MC,%x MT:%x\n", - mc, mt); - break; - } -rx_ret_irq: - writel(MGR_INT_RX_MSG_RCVD, ctrl->base + - MGR_INT_CLR); - if (q_rx) - queue_work(ctrl->rxwq, &ctrl->wd); - - return IRQ_HANDLED; -} - -static irqreturn_t qcom_slim_interrupt(int irq, void *d) -{ - struct qcom_slim_ctrl *ctrl = d; - u32 stat = readl_relaxed(ctrl->base + MGR_INT_STAT); - int ret = IRQ_NONE; - - if (stat & MGR_INT_TX_MSG_SENT || stat & MGR_INT_TX_NACKED_2) - ret = qcom_slim_handle_tx_irq(ctrl, stat); - - if (stat & MGR_INT_RX_MSG_RCVD) - ret = qcom_slim_handle_rx_irq(ctrl, stat); - - return ret; -} - -static int qcom_clk_pause_wakeup(struct slim_controller *sctrl) -{ - struct qcom_slim_ctrl *ctrl = dev_get_drvdata(sctrl->dev); - - clk_prepare_enable(ctrl->hclk); - clk_prepare_enable(ctrl->rclk); - enable_irq(ctrl->irq); - - writel_relaxed(1, ctrl->base + FRM_WAKEUP); - /* Make sure framer wakeup write goes through before ISR fires */ - mb(); - /* - * HW Workaround: Currently, slave is reporting lost-sync messages - * after SLIMbus comes out of clock pause. - * Transaction with slave fail before slave reports that message - * Give some time for that report to come - * SLIMbus wakes up in clock gear 10 at 24.576MHz. With each superframe - * being 250 usecs, we wait for 5-10 superframes here to ensure - * we get the message - */ - usleep_range(1250, 2500); - return 0; -} - -static void *slim_alloc_txbuf(struct qcom_slim_ctrl *ctrl, - struct slim_msg_txn *txn, - struct completion *done) -{ - unsigned long flags; - int idx; - - spin_lock_irqsave(&ctrl->tx.lock, flags); - if (((ctrl->tx.head + 1) % ctrl->tx.n) == ctrl->tx.tail) { - spin_unlock_irqrestore(&ctrl->tx.lock, flags); - dev_err(ctrl->dev, "controller TX buf unavailable"); - return NULL; - } - idx = ctrl->tx.tail; - ctrl->wr_comp[idx] = done; - ctrl->tx.tail = (ctrl->tx.tail + 1) % ctrl->tx.n; - - spin_unlock_irqrestore(&ctrl->tx.lock, flags); - - return ctrl->tx.base + (idx * ctrl->tx.sl_sz); -} - - -static int qcom_xfer_msg(struct slim_controller *sctrl, - struct slim_msg_txn *txn) -{ - struct qcom_slim_ctrl *ctrl = dev_get_drvdata(sctrl->dev); - DECLARE_COMPLETION_ONSTACK(done); - void *pbuf = slim_alloc_txbuf(ctrl, txn, &done); - unsigned long ms = txn->rl + HZ; - u8 *puc; - int ret = 0, retries = QCOM_BUF_ALLOC_RETRIES; - unsigned long time_left; - u8 la = txn->la; - u32 *head; - /* HW expects length field to be excluded */ - txn->rl--; - - /* spin till buffer is made available */ - if (!pbuf) { - while (retries--) { - usleep_range(10000, 15000); - pbuf = slim_alloc_txbuf(ctrl, txn, &done); - if (pbuf) - break; - } - } - - if (retries < 0 && !pbuf) - return -ENOMEM; - - puc = (u8 *)pbuf; - head = (u32 *)pbuf; - - if (txn->dt == SLIM_MSG_DEST_LOGICALADDR) { - *head = SLIM_MSG_ASM_FIRST_WORD(txn->rl, txn->mt, - txn->mc, 0, la); - puc += 3; - } else { - *head = SLIM_MSG_ASM_FIRST_WORD(txn->rl, txn->mt, - txn->mc, 1, la); - puc += 2; - } - - if (slim_tid_txn(txn->mt, txn->mc)) - *(puc++) = txn->tid; - - if (slim_ec_txn(txn->mt, txn->mc)) { - *(puc++) = (txn->ec & 0xFF); - *(puc++) = (txn->ec >> 8) & 0xFF; - } - - if (txn->msg && txn->msg->wbuf) - memcpy(puc, txn->msg->wbuf, txn->msg->num_bytes); - - qcom_slim_queue_tx(ctrl, head, txn->rl, MGR_TX_MSG); - time_left = wait_for_completion_timeout(&done, msecs_to_jiffies(ms)); - - if (!time_left) { - dev_err(ctrl->dev, "TX timed out:MC:0x%x,mt:0x%x", txn->mc, - txn->mt); - ret = -ETIMEDOUT; - } - - return ret; - -} - -static int qcom_set_laddr(struct slim_controller *sctrl, - struct slim_eaddr *ead, u8 laddr) -{ - struct qcom_slim_ctrl *ctrl = dev_get_drvdata(sctrl->dev); - struct { - __be16 manf_id; - __be16 prod_code; - u8 dev_index; - u8 instance; - u8 laddr; - } __packed p; - struct slim_val_inf msg = {0}; - DEFINE_SLIM_EDEST_TXN(txn, SLIM_MSG_MC_ASSIGN_LOGICAL_ADDRESS, - 10, laddr, &msg); - int ret; - - p.manf_id = cpu_to_be16(ead->manf_id); - p.prod_code = cpu_to_be16(ead->prod_code); - p.dev_index = ead->dev_index; - p.instance = ead->instance; - p.laddr = laddr; - - msg.wbuf = (void *)&p; - msg.num_bytes = 7; - ret = slim_do_transfer(&ctrl->ctrl, &txn); - - if (ret) - dev_err(ctrl->dev, "set LA:0x%x failed:ret:%d\n", - laddr, ret); - return ret; -} - -static int slim_get_current_rxbuf(struct qcom_slim_ctrl *ctrl, void *buf) -{ - unsigned long flags; - - spin_lock_irqsave(&ctrl->rx.lock, flags); - if (ctrl->rx.tail == ctrl->rx.head) { - spin_unlock_irqrestore(&ctrl->rx.lock, flags); - return -ENODATA; - } - memcpy(buf, ctrl->rx.base + (ctrl->rx.head * ctrl->rx.sl_sz), - ctrl->rx.sl_sz); - - ctrl->rx.head = (ctrl->rx.head + 1) % ctrl->rx.n; - spin_unlock_irqrestore(&ctrl->rx.lock, flags); - - return 0; -} - -static void qcom_slim_rxwq(struct work_struct *work) -{ - u8 buf[SLIM_MSGQ_BUF_LEN]; - u8 mc, mt; - int ret; - struct qcom_slim_ctrl *ctrl = container_of(work, struct qcom_slim_ctrl, - wd); - - while ((slim_get_current_rxbuf(ctrl, buf)) != -ENODATA) { - mt = SLIM_HEADER_GET_MT(buf[0]); - mc = SLIM_HEADER_GET_MC(buf[1]); - if (mt == SLIM_MSG_MT_CORE && - mc == SLIM_MSG_MC_REPORT_PRESENT) { - struct slim_eaddr ea; - u8 laddr; - - ea.manf_id = be16_to_cpup((__be16 *)&buf[2]); - ea.prod_code = be16_to_cpup((__be16 *)&buf[4]); - ea.dev_index = buf[6]; - ea.instance = buf[7]; - - ret = slim_device_report_present(&ctrl->ctrl, &ea, - &laddr); - if (ret < 0) - dev_err(ctrl->dev, "assign laddr failed:%d\n", - ret); - } else { - dev_err(ctrl->dev, "unexpected message:mc:%x, mt:%x\n", - mc, mt); - } - } -} - -static void qcom_slim_prg_slew(struct platform_device *pdev, - struct qcom_slim_ctrl *ctrl) -{ - if (!ctrl->slew_reg) { - /* SLEW RATE register for this SLIMbus */ - ctrl->slew_reg = devm_platform_ioremap_resource_byname(pdev, "slew"); - if (IS_ERR(ctrl->slew_reg)) - return; - } - - writel_relaxed(1, ctrl->slew_reg); - /* Make sure SLIMbus-slew rate enabling goes through */ - wmb(); -} - -static int qcom_slim_probe(struct platform_device *pdev) -{ - struct qcom_slim_ctrl *ctrl; - struct slim_controller *sctrl; - int ret, ver; - - ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL); - if (!ctrl) - return -ENOMEM; - - ctrl->hclk = devm_clk_get(&pdev->dev, "iface"); - if (IS_ERR(ctrl->hclk)) - return PTR_ERR(ctrl->hclk); - - ctrl->rclk = devm_clk_get(&pdev->dev, "core"); - if (IS_ERR(ctrl->rclk)) - return PTR_ERR(ctrl->rclk); - - ret = clk_set_rate(ctrl->rclk, SLIM_ROOT_FREQ); - if (ret) { - dev_err(&pdev->dev, "ref-clock set-rate failed:%d\n", ret); - return ret; - } - - ctrl->irq = platform_get_irq(pdev, 0); - if (ctrl->irq < 0) - return ctrl->irq; - - sctrl = &ctrl->ctrl; - sctrl->dev = &pdev->dev; - ctrl->dev = &pdev->dev; - platform_set_drvdata(pdev, ctrl); - dev_set_drvdata(ctrl->dev, ctrl); - - ctrl->base = devm_platform_ioremap_resource_byname(pdev, "ctrl"); - if (IS_ERR(ctrl->base)) - return PTR_ERR(ctrl->base); - - sctrl->set_laddr = qcom_set_laddr; - sctrl->xfer_msg = qcom_xfer_msg; - sctrl->wakeup = qcom_clk_pause_wakeup; - ctrl->tx.n = QCOM_TX_MSGS; - ctrl->tx.sl_sz = SLIM_MSGQ_BUF_LEN; - ctrl->rx.n = QCOM_RX_MSGS; - ctrl->rx.sl_sz = SLIM_MSGQ_BUF_LEN; - ctrl->wr_comp = kcalloc(QCOM_TX_MSGS, sizeof(struct completion *), - GFP_KERNEL); - if (!ctrl->wr_comp) - return -ENOMEM; - - spin_lock_init(&ctrl->rx.lock); - spin_lock_init(&ctrl->tx.lock); - INIT_WORK(&ctrl->wd, qcom_slim_rxwq); - ctrl->rxwq = create_singlethread_workqueue("qcom_slim_rx"); - if (!ctrl->rxwq) { - dev_err(ctrl->dev, "Failed to start Rx WQ\n"); - return -ENOMEM; - } - - ctrl->framer.rootfreq = SLIM_ROOT_FREQ / 8; - ctrl->framer.superfreq = - ctrl->framer.rootfreq / SLIM_CL_PER_SUPERFRAME_DIV8; - sctrl->a_framer = &ctrl->framer; - sctrl->clkgear = SLIM_MAX_CLK_GEAR; - - qcom_slim_prg_slew(pdev, ctrl); - - ret = devm_request_irq(&pdev->dev, ctrl->irq, qcom_slim_interrupt, - IRQF_TRIGGER_HIGH, "qcom_slim_irq", ctrl); - if (ret) { - dev_err(&pdev->dev, "request IRQ failed\n"); - goto err_request_irq_failed; - } - - ret = clk_prepare_enable(ctrl->hclk); - if (ret) - goto err_hclk_enable_failed; - - ret = clk_prepare_enable(ctrl->rclk); - if (ret) - goto err_rclk_enable_failed; - - ctrl->tx.base = devm_kcalloc(&pdev->dev, ctrl->tx.n, ctrl->tx.sl_sz, - GFP_KERNEL); - if (!ctrl->tx.base) { - ret = -ENOMEM; - goto err; - } - - ctrl->rx.base = devm_kcalloc(&pdev->dev,ctrl->rx.n, ctrl->rx.sl_sz, - GFP_KERNEL); - if (!ctrl->rx.base) { - ret = -ENOMEM; - goto err; - } - - /* Register with framework before enabling frame, clock */ - ret = slim_register_controller(&ctrl->ctrl); - if (ret) { - dev_err(ctrl->dev, "error adding controller\n"); - goto err; - } - - ver = readl_relaxed(ctrl->base); - /* Version info in 16 MSbits */ - ver >>= 16; - /* Component register initialization */ - writel(1, ctrl->base + CFG_PORT(COMP_CFG, ver)); - writel((EE_MGR_RSC_GRP | EE_NGD_2 | EE_NGD_1), - ctrl->base + CFG_PORT(COMP_TRUST_CFG, ver)); - - writel((MGR_INT_TX_NACKED_2 | - MGR_INT_MSG_BUF_CONTE | MGR_INT_RX_MSG_RCVD | - MGR_INT_TX_MSG_SENT), ctrl->base + MGR_INT_EN); - writel(1, ctrl->base + MGR_CFG); - /* Framer register initialization */ - writel((1 << INTR_WAKE) | (0xA << REF_CLK_GEAR) | - (0xA << CLK_GEAR) | (1 << ROOT_FREQ) | (1 << FRM_ACTIVE) | 1, - ctrl->base + FRM_CFG); - writel(MGR_CFG_ENABLE, ctrl->base + MGR_CFG); - writel(1, ctrl->base + INTF_CFG); - writel(1, ctrl->base + CFG_PORT(COMP_CFG, ver)); - - pm_runtime_use_autosuspend(&pdev->dev); - pm_runtime_set_autosuspend_delay(&pdev->dev, QCOM_SLIM_AUTOSUSPEND); - pm_runtime_set_active(&pdev->dev); - pm_runtime_mark_last_busy(&pdev->dev); - pm_runtime_enable(&pdev->dev); - - dev_dbg(ctrl->dev, "QCOM SB controller is up:ver:0x%x!\n", ver); - return 0; - -err: - clk_disable_unprepare(ctrl->rclk); -err_rclk_enable_failed: - clk_disable_unprepare(ctrl->hclk); -err_hclk_enable_failed: -err_request_irq_failed: - destroy_workqueue(ctrl->rxwq); - return ret; -} - -static void qcom_slim_remove(struct platform_device *pdev) -{ - struct qcom_slim_ctrl *ctrl = platform_get_drvdata(pdev); - - pm_runtime_disable(&pdev->dev); - slim_unregister_controller(&ctrl->ctrl); - clk_disable_unprepare(ctrl->rclk); - clk_disable_unprepare(ctrl->hclk); - destroy_workqueue(ctrl->rxwq); -} - -/* - * If PM_RUNTIME is not defined, these 2 functions become helper - * functions to be called from system suspend/resume. - */ -#ifdef CONFIG_PM -static int qcom_slim_runtime_suspend(struct device *device) -{ - struct qcom_slim_ctrl *ctrl = dev_get_drvdata(device); - int ret; - - dev_dbg(device, "pm_runtime: suspending...\n"); - ret = slim_ctrl_clk_pause(&ctrl->ctrl, false, SLIM_CLK_UNSPECIFIED); - if (ret) { - dev_err(device, "clk pause not entered:%d", ret); - } else { - disable_irq(ctrl->irq); - clk_disable_unprepare(ctrl->hclk); - clk_disable_unprepare(ctrl->rclk); - } - return ret; -} - -static int qcom_slim_runtime_resume(struct device *device) -{ - struct qcom_slim_ctrl *ctrl = dev_get_drvdata(device); - int ret = 0; - - dev_dbg(device, "pm_runtime: resuming...\n"); - ret = slim_ctrl_clk_pause(&ctrl->ctrl, true, 0); - if (ret) - dev_err(device, "clk pause not exited:%d", ret); - return ret; -} -#endif - -#ifdef CONFIG_PM_SLEEP -static int qcom_slim_suspend(struct device *dev) -{ - int ret = 0; - - if (!pm_runtime_enabled(dev) || - (!pm_runtime_suspended(dev))) { - dev_dbg(dev, "system suspend"); - ret = qcom_slim_runtime_suspend(dev); - } - - return ret; -} - -static int qcom_slim_resume(struct device *dev) -{ - if (!pm_runtime_enabled(dev) || !pm_runtime_suspended(dev)) { - int ret; - - dev_dbg(dev, "system resume"); - ret = qcom_slim_runtime_resume(dev); - if (!ret) { - pm_runtime_mark_last_busy(dev); - pm_request_autosuspend(dev); - } - return ret; - - } - return 0; -} -#endif /* CONFIG_PM_SLEEP */ - -static const struct dev_pm_ops qcom_slim_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(qcom_slim_suspend, qcom_slim_resume) - SET_RUNTIME_PM_OPS( - qcom_slim_runtime_suspend, - qcom_slim_runtime_resume, - NULL - ) -}; - -static const struct of_device_id qcom_slim_dt_match[] = { - { .compatible = "qcom,slim", }, - {} -}; -MODULE_DEVICE_TABLE(of, qcom_slim_dt_match); - -static struct platform_driver qcom_slim_driver = { - .probe = qcom_slim_probe, - .remove = qcom_slim_remove, - .driver = { - .name = "qcom_slim_ctrl", - .of_match_table = qcom_slim_dt_match, - .pm = &qcom_slim_dev_pm_ops, - }, -}; -module_platform_driver(qcom_slim_driver); - -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Qualcomm SLIMbus Controller"); diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 2a5f24ee858c..034a2a535a1e 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -1232,7 +1232,7 @@ err: } static int tegra_powergate_of_get_resets(struct tegra_powergate *pg, - struct device_node *np, bool off) + struct device_node *np) { struct device *dev = pg->pmc->dev; int err; @@ -1247,22 +1247,6 @@ static int tegra_powergate_of_get_resets(struct tegra_powergate *pg, err = reset_control_acquire(pg->reset); if (err < 0) { pr_err("failed to acquire resets: %d\n", err); - goto out; - } - - if (off) { - err = reset_control_assert(pg->reset); - } else { - err = reset_control_deassert(pg->reset); - if (err < 0) - goto out; - - reset_control_release(pg->reset); - } - -out: - if (err) { - reset_control_release(pg->reset); reset_control_put(pg->reset); } @@ -1308,20 +1292,43 @@ static int tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np) goto set_available; } - err = tegra_powergate_of_get_resets(pg, np, off); + err = tegra_powergate_of_get_resets(pg, np); if (err < 0) { dev_err(dev, "failed to get resets for %pOFn: %d\n", np, err); goto remove_clks; } - if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) { - if (off) - WARN_ON(tegra_powergate_power_up(pg, true)); + /* + * If the power-domain is off, then ensure the resets are asserted. + * If the power-domain is on, then power down to ensure that when is + * it turned on the power-domain, clocks and resets are all in the + * expected state. + */ + if (off) { + err = reset_control_assert(pg->reset); + if (err) { + pr_err("failed to assert resets: %d\n", err); + goto remove_resets; + } + } else { + err = tegra_powergate_power_down(pg); + if (err) { + dev_err(dev, "failed to turn off PM domain %s: %d\n", + pg->genpd.name, err); + goto remove_resets; + } + } + /* + * If PM_GENERIC_DOMAINS is not enabled, power-on + * the domain and skip the genpd registration. + */ + if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) { + WARN_ON(tegra_powergate_power_up(pg, true)); goto remove_resets; } - err = pm_genpd_init(&pg->genpd, NULL, off); + err = pm_genpd_init(&pg->genpd, NULL, true); if (err < 0) { dev_err(dev, "failed to initialise PM domain %pOFn: %d\n", np, err); diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 67d4000c3cef..313e444a34f3 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -330,13 +330,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) } if (config.speed_hz > perclk_rate / 2) { - dev_err(fsl_lpspi->dev, - "per-clk should be at least two times of transfer speed"); - return -EINVAL; + div = 2; + } else { + div = DIV_ROUND_UP(perclk_rate, config.speed_hz); } - div = DIV_ROUND_UP(perclk_rate, config.speed_hz); - for (prescale = 0; prescale <= prescale_max; prescale++) { scldiv = div / (1 << prescale) - 2; if (scldiv >= 0 && scldiv < 256) { diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index d3b7e857b377..064b99204d9a 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -265,6 +265,9 @@ static bool spi_mem_internal_supports_op(struct spi_mem *mem, */ bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + /* Make sure the operation frequency is correct before going futher */ + spi_mem_adjust_op_freq(mem, (struct spi_mem_op *)op); + if (spi_mem_check_op(op)) return false; @@ -577,6 +580,7 @@ EXPORT_SYMBOL_GPL(spi_mem_adjust_op_freq); * spi_mem_calc_op_duration() - Derives the theoretical length (in ns) of an * operation. This helps finding the best variant * among a list of possible choices. + * @mem: the SPI memory * @op: the operation to benchmark * * Some chips have per-op frequency limitations, PCBs usually have their own diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c index a8c4eb1cbde1..0ceaad7dba3c 100644 --- a/drivers/spi/spi-qpic-snand.c +++ b/drivers/spi/spi-qpic-snand.c @@ -210,13 +210,21 @@ static int qcom_spi_ooblayout_ecc(struct mtd_info *mtd, int section, struct qcom_nand_controller *snandc = nand_to_qcom_snand(nand); struct qpic_ecc *qecc = snandc->qspi->ecc; - if (section > 1) - return -ERANGE; - - oobregion->length = qecc->ecc_bytes_hw + qecc->spare_bytes; - oobregion->offset = mtd->oobsize - oobregion->length; + switch (section) { + case 0: + oobregion->offset = 0; + oobregion->length = qecc->bytes * (qecc->steps - 1) + + qecc->bbm_size; + return 0; + case 1: + oobregion->offset = qecc->bytes * (qecc->steps - 1) + + qecc->bbm_size + + qecc->steps * 4; + oobregion->length = mtd->oobsize - oobregion->offset; + return 0; + } - return 0; + return -ERANGE; } static int qcom_spi_ooblayout_free(struct mtd_info *mtd, int section, @@ -1196,7 +1204,7 @@ static int qcom_spi_program_oob(struct qcom_nand_controller *snandc, u32 cfg0, cfg1, ecc_bch_cfg, ecc_buf_cfg; cfg0 = (ecc_cfg->cfg0 & ~CW_PER_PAGE_MASK) | - FIELD_PREP(CW_PER_PAGE_MASK, num_cw - 1); + FIELD_PREP(CW_PER_PAGE_MASK, 0); cfg1 = ecc_cfg->cfg1; ecc_bch_cfg = ecc_cfg->ecc_bch_cfg; ecc_buf_cfg = ecc_cfg->ecc_buf_cfg; diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c index 49ab4c515156..c07c61dc4938 100644 --- a/drivers/spi/spi-st-ssc4.c +++ b/drivers/spi/spi-st-ssc4.c @@ -378,7 +378,7 @@ static void spi_st_remove(struct platform_device *pdev) pinctrl_pm_select_sleep_state(&pdev->dev); } -static int __maybe_unused spi_st_runtime_suspend(struct device *dev) +static int spi_st_runtime_suspend(struct device *dev) { struct spi_controller *host = dev_get_drvdata(dev); struct spi_st *spi_st = spi_controller_get_devdata(host); @@ -391,7 +391,7 @@ static int __maybe_unused spi_st_runtime_suspend(struct device *dev) return 0; } -static int __maybe_unused spi_st_runtime_resume(struct device *dev) +static int spi_st_runtime_resume(struct device *dev) { struct spi_controller *host = dev_get_drvdata(dev); struct spi_st *spi_st = spi_controller_get_devdata(host); @@ -428,8 +428,8 @@ static int __maybe_unused spi_st_resume(struct device *dev) } static const struct dev_pm_ops spi_st_pm = { - SET_SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume) - SET_RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume) + RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL) }; static const struct of_device_id stm_spi_match[] = { @@ -441,7 +441,7 @@ MODULE_DEVICE_TABLE(of, stm_spi_match); static struct platform_driver spi_st_driver = { .driver = { .name = "spi-st", - .pm = pm_sleep_ptr(&spi_st_pm), + .pm = pm_ptr(&spi_st_pm), .of_match_table = of_match_ptr(stm_spi_match), }, .probe = spi_st_probe, diff --git a/drivers/tty/serial/8250/8250_rsa.c b/drivers/tty/serial/8250/8250_rsa.c index d34093cc03ad..12a65b79583c 100644 --- a/drivers/tty/serial/8250/8250_rsa.c +++ b/drivers/tty/serial/8250/8250_rsa.c @@ -147,7 +147,7 @@ void rsa_enable(struct uart_8250_port *up) if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_enable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_enable, "8250_base"); /* * Attempts to turn off the RSA FIFO and resets the RSA board back to 115kbps compat mode. It is @@ -179,7 +179,7 @@ void rsa_disable(struct uart_8250_port *up) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; uart_port_unlock_irq(&up->port); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_disable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_disable, "8250_base"); void rsa_autoconfig(struct uart_8250_port *up) { @@ -192,7 +192,7 @@ void rsa_autoconfig(struct uart_8250_port *up) if (__rsa_enable(up)) up->port.type = PORT_RSA; } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_autoconfig, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_autoconfig, "8250_base"); void rsa_reset(struct uart_8250_port *up) { @@ -201,7 +201,7 @@ void rsa_reset(struct uart_8250_port *up) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_reset, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_reset, "8250_base"); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 96ad57c3144b..9a43102b2b21 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1303,7 +1303,7 @@ static u32 ufshcd_pending_cmds(struct ufs_hba *hba) * * Return: 0 upon success; -EBUSY upon timeout. */ -static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba, +static int ufshcd_wait_for_pending_cmds(struct ufs_hba *hba, u64 wait_timeout_us) { int ret = 0; @@ -1431,7 +1431,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) down_write(&hba->clk_scaling_lock); if (!hba->clk_scaling.is_allowed || - ufshcd_wait_for_doorbell_clr(hba, timeout_us)) { + ufshcd_wait_for_pending_cmds(hba, timeout_us)) { ret = -EBUSY; up_write(&hba->clk_scaling_lock); mutex_unlock(&hba->wb_mutex); @@ -3199,7 +3199,8 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) } /* - * Return: 0 upon success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, int max_timeout) @@ -3275,7 +3276,6 @@ retry: } } - WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err); return err; } @@ -3294,7 +3294,8 @@ static void ufshcd_dev_man_unlock(struct ufs_hba *hba) } /* - * Return: 0 upon success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, const u32 tag, int timeout) @@ -3317,7 +3318,8 @@ static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, * @cmd_type: specifies the type (NOP, Query...) * @timeout: timeout in milliseconds * - * Return: 0 upon success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. * * NOTE: Since there is only one available tag for device management commands, * it is expected you hold the hba->dev_cmd.lock mutex. @@ -3363,6 +3365,10 @@ static inline void ufshcd_init_query(struct ufs_hba *hba, (*request)->upiu_req.selector = selector; } +/* + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. + */ static int ufshcd_query_flag_retry(struct ufs_hba *hba, enum query_opcode opcode, enum flag_idn idn, u8 index, bool *flag_res) { @@ -3383,7 +3389,6 @@ static int ufshcd_query_flag_retry(struct ufs_hba *hba, dev_err(hba->dev, "%s: query flag, opcode %d, idn %d, failed with error %d after %d retries\n", __func__, opcode, idn, ret, retries); - WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret); return ret; } @@ -3395,7 +3400,8 @@ static int ufshcd_query_flag_retry(struct ufs_hba *hba, * @index: flag index to access * @flag_res: the flag value after the query request completes * - * Return: 0 for success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, enum flag_idn idn, u8 index, bool *flag_res) @@ -3451,7 +3457,6 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, out_unlock: ufshcd_dev_man_unlock(hba); - WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err); return err; } @@ -3464,8 +3469,9 @@ out_unlock: * @selector: selector field * @attr_val: the attribute value after the query request completes * - * Return: 0 upon success; < 0 upon failure. -*/ + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. + */ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, enum attr_idn idn, u8 index, u8 selector, u32 *attr_val) { @@ -3513,7 +3519,6 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, out_unlock: ufshcd_dev_man_unlock(hba); - WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err); return err; } @@ -3528,8 +3533,9 @@ out_unlock: * @attr_val: the attribute value after the query request * completes * - * Return: 0 for success; < 0 upon failure. -*/ + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. + */ int ufshcd_query_attr_retry(struct ufs_hba *hba, enum query_opcode opcode, enum attr_idn idn, u8 index, u8 selector, u32 *attr_val) @@ -3551,12 +3557,12 @@ int ufshcd_query_attr_retry(struct ufs_hba *hba, dev_err(hba->dev, "%s: query attribute, idn %d, failed with error %d after %d retries\n", __func__, idn, ret, QUERY_REQ_RETRIES); - WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret); return ret; } /* - * Return: 0 if successful; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int __ufshcd_query_descriptor(struct ufs_hba *hba, enum query_opcode opcode, enum desc_idn idn, u8 index, @@ -3615,7 +3621,6 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba, out_unlock: hba->dev_cmd.query.descriptor = NULL; ufshcd_dev_man_unlock(hba); - WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err); return err; } @@ -3632,7 +3637,8 @@ out_unlock: * The buf_len parameter will contain, on return, the length parameter * received on the response. * - * Return: 0 for success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ int ufshcd_query_descriptor_retry(struct ufs_hba *hba, enum query_opcode opcode, @@ -3650,7 +3656,6 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba, break; } - WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err); return err; } @@ -3663,7 +3668,8 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba, * @param_read_buf: pointer to buffer where parameter would be read * @param_size: sizeof(param_read_buf) * - * Return: 0 in case of success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ int ufshcd_read_desc_param(struct ufs_hba *hba, enum desc_idn desc_id, @@ -3730,7 +3736,6 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, out: if (is_kmalloc) kfree(desc_buf); - WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret); return ret; } @@ -4781,7 +4786,8 @@ EXPORT_SYMBOL_GPL(ufshcd_config_pwr_mode); * * Set fDeviceInit flag and poll until device toggles it. * - * Return: 0 upon success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_complete_dev_init(struct ufs_hba *hba) { @@ -5135,7 +5141,8 @@ out: * not respond with NOP IN UPIU within timeout of %NOP_OUT_TIMEOUT * and we retry sending NOP OUT for %NOP_OUT_RETRIES iterations. * - * Return: 0 upon success; < 0 upon failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_verify_dev_init(struct ufs_hba *hba) { @@ -5559,9 +5566,9 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) irqreturn_t retval = IRQ_NONE; struct uic_command *cmd; - spin_lock(hba->host->host_lock); + guard(spinlock_irqsave)(hba->host->host_lock); cmd = hba->active_uic_cmd; - if (WARN_ON_ONCE(!cmd)) + if (!cmd) goto unlock; if (ufshcd_is_auto_hibern8_error(hba, intr_status)) @@ -5586,8 +5593,6 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) ufshcd_add_uic_command_trace(hba, cmd, UFS_CMD_COMP); unlock: - spin_unlock(hba->host->host_lock); - return retval; } @@ -5869,7 +5874,8 @@ static inline int ufshcd_enable_ee(struct ufs_hba *hba, u16 mask) * as the device is allowed to manage its own way of handling background * operations. * - * Return: zero on success, non-zero on failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_enable_auto_bkops(struct ufs_hba *hba) { @@ -5908,7 +5914,8 @@ out: * host is idle so that BKOPS are managed effectively without any negative * impacts. * - * Return: zero on success, non-zero on failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba) { @@ -6058,6 +6065,10 @@ out: __func__, err); } +/* + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. + */ int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id) { struct utp_upiu_query_v4_0 *upiu_resp; @@ -6920,7 +6931,7 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status) bool queue_eh_work = false; irqreturn_t retval = IRQ_NONE; - spin_lock(hba->host->host_lock); + guard(spinlock_irqsave)(hba->host->host_lock); hba->errors |= UFSHCD_ERROR_MASK & intr_status; if (hba->errors & INT_FATAL_ERRORS) { @@ -6979,7 +6990,7 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status) */ hba->errors = 0; hba->uic_error = 0; - spin_unlock(hba->host->host_lock); + return retval; } @@ -7138,14 +7149,19 @@ static irqreturn_t ufshcd_threaded_intr(int irq, void *__hba) static irqreturn_t ufshcd_intr(int irq, void *__hba) { struct ufs_hba *hba = __hba; + u32 intr_status, enabled_intr_status; /* Move interrupt handling to thread when MCQ & ESI are not enabled */ if (!hba->mcq_enabled || !hba->mcq_esi_enabled) return IRQ_WAKE_THREAD; + intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); + enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); + + ufshcd_writel(hba, intr_status, REG_INTERRUPT_STATUS); + /* Directly handle interrupts since MCQ ESI handlers does the hard job */ - return ufshcd_sl_intr(hba, ufshcd_readl(hba, REG_INTERRUPT_STATUS) & - ufshcd_readl(hba, REG_INTERRUPT_ENABLE)); + return ufshcd_sl_intr(hba, enabled_intr_status); } static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag) @@ -7449,7 +7465,8 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, * @sg_list: Pointer to SG list when DATA IN/OUT UPIU is required in ARPMB operation * @dir: DMA direction * - * Return: zero on success, non-zero on failure. + * Return: 0 upon success; > 0 in case the UFS device reported an OCS error; + * < 0 if another error occurred. */ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *req_upiu, struct utp_upiu_req *rsp_upiu, struct ufs_ehs *req_ehs, @@ -10516,8 +10533,7 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = devm_add_action_or_reset(dev, ufshcd_devres_release, host); if (err) - return dev_err_probe(dev, err, - "failed to add ufshcd dealloc action\n"); + return err; host->nr_maps = HCTX_TYPE_POLL + 1; hba = shost_priv(host); diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index 86ae73b89d4d..f902ce08c95a 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -818,7 +818,7 @@ static u32 ufs_mtk_mcq_get_irq(struct ufs_hba *hba, unsigned int cpu) unsigned int q_index; q_index = map->mq_map[cpu]; - if (q_index > nr) { + if (q_index >= nr) { dev_err(hba->dev, "hwq index %d exceed %d\n", q_index, nr); return MTK_MCQ_INVALID_IRQ; diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 76fc70503a62..9574fdc2bb0f 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -2070,17 +2070,6 @@ static irqreturn_t ufs_qcom_mcq_esi_handler(int irq, void *data) return IRQ_HANDLED; } -static void ufs_qcom_irq_free(struct ufs_qcom_irq *uqi) -{ - for (struct ufs_qcom_irq *q = uqi; q->irq; q++) - devm_free_irq(q->hba->dev, q->irq, q->hba); - - platform_device_msi_free_irqs_all(uqi->hba->dev); - devm_kfree(uqi->hba->dev, uqi); -} - -DEFINE_FREE(ufs_qcom_irq, struct ufs_qcom_irq *, if (_T) ufs_qcom_irq_free(_T)) - static int ufs_qcom_config_esi(struct ufs_hba *hba) { struct ufs_qcom_host *host = ufshcd_get_variant(hba); @@ -2095,18 +2084,18 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba) */ nr_irqs = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL]; - struct ufs_qcom_irq *qi __free(ufs_qcom_irq) = - devm_kcalloc(hba->dev, nr_irqs, sizeof(*qi), GFP_KERNEL); - if (!qi) - return -ENOMEM; - /* Preset so __free() has a pointer to hba in all error paths */ - qi[0].hba = hba; - ret = platform_device_msi_init_and_alloc_irqs(hba->dev, nr_irqs, ufs_qcom_write_msi_msg); if (ret) { - dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret); - return ret; + dev_warn(hba->dev, "Platform MSI not supported or failed, continuing without ESI\n"); + return ret; /* Continue without ESI */ + } + + struct ufs_qcom_irq *qi = devm_kcalloc(hba->dev, nr_irqs, sizeof(*qi), GFP_KERNEL); + + if (!qi) { + platform_device_msi_free_irqs_all(hba->dev); + return -ENOMEM; } for (int idx = 0; idx < nr_irqs; idx++) { @@ -2117,15 +2106,17 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba) ret = devm_request_irq(hba->dev, qi[idx].irq, ufs_qcom_mcq_esi_handler, IRQF_SHARED, "qcom-mcq-esi", qi + idx); if (ret) { - dev_err(hba->dev, "%s: Fail to request IRQ for %d, err = %d\n", + dev_err(hba->dev, "%s: Failed to request IRQ for %d, err = %d\n", __func__, qi[idx].irq, ret); - qi[idx].irq = 0; + /* Free previously allocated IRQs */ + for (int j = 0; j < idx; j++) + devm_free_irq(hba->dev, qi[j].irq, qi + j); + platform_device_msi_free_irqs_all(hba->dev); + devm_kfree(hba->dev, qi); return ret; } } - retain_and_null_ptr(qi); - if (host->hw_ver.major >= 6) { ufshcd_rmwl(hba, ESI_VEC_MASK, FIELD_PREP(ESI_VEC_MASK, MAX_ESI_VEC - 1), REG_UFS_CFG3); diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index b39239f641f2..b87e03777395 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -630,6 +630,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xA847), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { PCI_VDEVICE(INTEL, 0x7747), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { PCI_VDEVICE(INTEL, 0xE447), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4D47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/uio/uio_aec.c b/drivers/uio/uio_aec.c index 8c164e51ff9e..dafcc5f44f24 100644 --- a/drivers/uio/uio_aec.c +++ b/drivers/uio/uio_aec.c @@ -33,7 +33,7 @@ #define MAILBOX 0x0F -static struct pci_device_id ids[] = { +static const struct pci_device_id ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AEC, PCI_DEVICE_ID_AEC_VITCLTC), }, { 0, } }; diff --git a/drivers/uio/uio_cif.c b/drivers/uio/uio_cif.c index 1cc3b8b5a345..4e4b589ddef1 100644 --- a/drivers/uio/uio_cif.c +++ b/drivers/uio/uio_cif.c @@ -105,7 +105,7 @@ static void hilscher_pci_remove(struct pci_dev *dev) iounmap(info->mem[0].internal_addr); } -static struct pci_device_id hilscher_pci_ids[] = { +static const struct pci_device_id hilscher_pci_ids[] = { { .vendor = PCI_VENDOR_ID_PLX, .device = PCI_DEVICE_ID_PLX_9030, diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index 31aa75110ba5..41c18ec62a45 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -297,28 +297,6 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev) return devm_uio_register_device(&pdev->dev, priv->uioinfo); } -static int uio_dmem_genirq_runtime_nop(struct device *dev) -{ - /* Runtime PM callback shared between ->runtime_suspend() - * and ->runtime_resume(). Simply returns success. - * - * In this driver pm_runtime_get_sync() and pm_runtime_put_sync() - * are used at open() and release() time. This allows the - * Runtime PM code to turn off power to the device while the - * device is unused, ie before open() and after release(). - * - * This Runtime PM callback does not need to save or restore - * any registers since user space is responsbile for hardware - * register reinitialization after open(). - */ - return 0; -} - -static const struct dev_pm_ops uio_dmem_genirq_dev_pm_ops = { - .runtime_suspend = uio_dmem_genirq_runtime_nop, - .runtime_resume = uio_dmem_genirq_runtime_nop, -}; - #ifdef CONFIG_OF static const struct of_device_id uio_of_genirq_match[] = { { /* empty for now */ }, @@ -330,7 +308,6 @@ static struct platform_driver uio_dmem_genirq = { .probe = uio_dmem_genirq_probe, .driver = { .name = DRIVER_NAME, - .pm = &uio_dmem_genirq_dev_pm_ops, .of_match_table = of_match_ptr(uio_of_genirq_match), }, }; diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index f19efad4d6f8..3f8e2e27697f 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -111,7 +111,6 @@ static void hv_uio_channel_cb(void *context) struct hv_device *hv_dev; struct hv_uio_private_data *pdata; - chan->inbound.ring_buffer->interrupt_mask = 1; virt_mb(); /* @@ -183,8 +182,6 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) return; } - /* Disable interrupts on sub channel */ - new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { @@ -227,9 +224,7 @@ hv_uio_open(struct uio_info *info, struct inode *inode) ret = vmbus_connect_ring(dev->channel, hv_uio_channel_cb, dev->channel); - if (ret == 0) - dev->channel->inbound.ring_buffer->interrupt_mask = 1; - else + if (ret) atomic_dec(&pdata->refcnt); return ret; diff --git a/drivers/uio/uio_netx.c b/drivers/uio/uio_netx.c index a1a58802c793..18917b2ac04c 100644 --- a/drivers/uio/uio_netx.c +++ b/drivers/uio/uio_netx.c @@ -127,7 +127,7 @@ static void netx_pci_remove(struct pci_dev *dev) iounmap(info->mem[0].internal_addr); } -static struct pci_device_id netx_pci_ids[] = { +static const struct pci_device_id netx_pci_ids[] = { { .vendor = PCI_VENDOR_ID_HILSCHER, .device = PCI_DEVICE_ID_HILSCHER_NETX, diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c index 2ec7d25e8264..0a1885d1b2e3 100644 --- a/drivers/uio/uio_pdrv_genirq.c +++ b/drivers/uio/uio_pdrv_genirq.c @@ -249,34 +249,11 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev) return ret; } -static int uio_pdrv_genirq_runtime_nop(struct device *dev) -{ - /* Runtime PM callback shared between ->runtime_suspend() - * and ->runtime_resume(). Simply returns success. - * - * In this driver pm_runtime_get_sync() and pm_runtime_put_sync() - * are used at open() and release() time. This allows the - * Runtime PM code to turn off power to the device while the - * device is unused, ie before open() and after release(). - * - * This Runtime PM callback does not need to save or restore - * any registers since user space is responsbile for hardware - * register reinitialization after open(). - */ - return 0; -} - -static const struct dev_pm_ops uio_pdrv_genirq_dev_pm_ops = { - .runtime_suspend = uio_pdrv_genirq_runtime_nop, - .runtime_resume = uio_pdrv_genirq_runtime_nop, -}; - #ifdef CONFIG_OF static struct of_device_id uio_of_genirq_match[] = { { /* This is filled with module_parm */ }, { /* Sentinel */ }, }; -MODULE_DEVICE_TABLE(of, uio_of_genirq_match); module_param_string(of_id, uio_of_genirq_match[0].compatible, 128, 0); MODULE_PARM_DESC(of_id, "Openfirmware id of the device to be handled by uio"); #endif @@ -285,7 +262,6 @@ static struct platform_driver uio_pdrv_genirq = { .probe = uio_pdrv_genirq_probe, .driver = { .name = DRIVER_NAME, - .pm = &uio_pdrv_genirq_dev_pm_ops, .of_match_table = of_match_ptr(uio_of_genirq_match), }, }; diff --git a/drivers/uio/uio_sercos3.c b/drivers/uio/uio_sercos3.c index b93a5f8f4cba..12afc2fa1a0b 100644 --- a/drivers/uio/uio_sercos3.c +++ b/drivers/uio/uio_sercos3.c @@ -191,7 +191,7 @@ static void sercos3_pci_remove(struct pci_dev *dev) } } -static struct pci_device_id sercos3_pci_ids[] = { +static const struct pci_device_id sercos3_pci_ids[] = { { .vendor = PCI_VENDOR_ID_PLX, .device = PCI_DEVICE_ID_PLX_9030, diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index e1ec9b38f5b9..d7c2a1a3c271 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -338,7 +338,8 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event) schedule_work(&ci->usb_phy->chg_work); break; case CI_HDRC_CONTROLLER_PULLUP_EVENT: - if (ci->role == CI_ROLE_GADGET) + if (ci->role == CI_ROLE_GADGET && + ci->gadget.speed == USB_SPEED_HIGH) imx_usbmisc_pullup(data->usbmisc_data, ci->gadget.connected); break; diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index 3d20c5e76c6a..b1418885707c 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -1068,15 +1068,24 @@ static void usbmisc_imx7d_pullup(struct imx_usbmisc_data *data, bool on) unsigned long flags; u32 val; + if (on) + return; + spin_lock_irqsave(&usbmisc->lock, flags); val = readl(usbmisc->base + MX7D_USBNC_USB_CTRL2); - if (!on) { - val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK; - val |= MX7D_USBNC_USB_CTRL2_OPMODE(1); - val |= MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN; - } else { - val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN; - } + val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK; + val |= MX7D_USBNC_USB_CTRL2_OPMODE(1); + val |= MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN; + writel(val, usbmisc->base + MX7D_USBNC_USB_CTRL2); + spin_unlock_irqrestore(&usbmisc->lock, flags); + + /* Last for at least 1 micro-frame to let host see disconnect signal */ + usleep_range(125, 150); + + spin_lock_irqsave(&usbmisc->lock, flags); + val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK; + val |= MX7D_USBNC_USB_CTRL2_OPMODE(0); + val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN; writel(val, usbmisc->base + MX7D_USBNC_USB_CTRL2); spin_unlock_irqrestore(&usbmisc->lock, flags); } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 03771bbc6c01..9dd79769cad1 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1636,7 +1636,6 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; - unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1654,14 +1653,13 @@ static void __usb_hcd_giveback_urb(struct urb *urb) /* pass ownership to the completion handler */ urb->status = status; /* - * Only collect coverage in the softirq context and disable interrupts - * to avoid scenarios with nested remote coverage collection sections - * that KCOV does not support. - * See the comment next to kcov_remote_start_usb_softirq() for details. + * This function can be called in task context inside another remote + * coverage collection section, but kcov doesn't support that kind of + * recursion yet. Only collect coverage in softirq context for now. */ - flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); + kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); urb->complete(urb); - kcov_remote_stop_softirq(flags); + kcov_remote_stop_softirq(); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); @@ -1719,10 +1717,10 @@ static void usb_giveback_urb_bh(struct work_struct *work) * @urb: urb being returned to the USB device driver. * @status: completion status code for the URB. * - * Context: atomic. The completion callback is invoked in caller's context. - * For HCDs with HCD_BH flag set, the completion callback is invoked in BH - * context (except for URBs submitted to the root hub which always complete in - * caller's context). + * Context: atomic. The completion callback is invoked either in a work queue + * (BH) context or in the caller's context, depending on whether the HCD_BH + * flag is set in the @hcd structure, except that URBs submitted to the + * root hub always complete in BH context. * * This hands the URB from HCD to its USB device driver, using its * completion function. The HCD has freed all per-urb resources @@ -2166,7 +2164,7 @@ static struct urb *request_single_step_set_feature_urb( urb->complete = usb_ehset_completion; urb->status = -EINPROGRESS; urb->actual_length = 0; - urb->transfer_flags = URB_DIR_IN; + urb->transfer_flags = URB_DIR_IN | URB_NO_TRANSFER_DMA_MAP; usb_get_urb(urb); atomic_inc(&urb->use_count); atomic_inc(&urb->dev->urbnum); @@ -2230,9 +2228,15 @@ int ehset_single_step_set_feature(struct usb_hcd *hcd, int port) /* Complete remaining DATA and STATUS stages using the same URB */ urb->status = -EINPROGRESS; + urb->transfer_flags &= ~URB_NO_TRANSFER_DMA_MAP; usb_get_urb(urb); atomic_inc(&urb->use_count); atomic_inc(&urb->dev->urbnum); + if (map_urb_for_dma(hcd, urb, GFP_KERNEL)) { + usb_put_urb(urb); + goto out1; + } + retval = hcd->driver->submit_single_step_set_feature(hcd, urb, 0); if (!retval && !wait_for_completion_timeout(&done, msecs_to_jiffies(2000))) { diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index ff0ff95d5cca..f5bc53875330 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -371,6 +371,7 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM }, /* SanDisk Corp. SanDisk 3.2Gen1 */ + { USB_DEVICE(0x0781, 0x5596), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT }, /* SanDisk Extreme 55AE */ diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 54a4ee2b90b7..39c72cb52ce7 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -41,6 +41,7 @@ #define PCI_DEVICE_ID_INTEL_TGPLP 0xa0ee #define PCI_DEVICE_ID_INTEL_TGPH 0x43ee #define PCI_DEVICE_ID_INTEL_JSP 0x4dee +#define PCI_DEVICE_ID_INTEL_WCL 0x4d7e #define PCI_DEVICE_ID_INTEL_ADL 0x460e #define PCI_DEVICE_ID_INTEL_ADL_PCH 0x51ee #define PCI_DEVICE_ID_INTEL_ADLN 0x465e @@ -431,6 +432,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, TGPLP, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, TGPH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, JSP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, WCL, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, ADL, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, ADL_PCH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, ADLN, &dwc3_pci_intel_swnode) }, diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 666ac432f52d..b4229aa13f37 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -288,7 +288,9 @@ void dwc3_ep0_out_start(struct dwc3 *dwc) dwc3_ep0_prepare_one_trb(dep, dwc->ep0_trb_addr, 8, DWC3_TRBCTL_CONTROL_SETUP, false); ret = dwc3_ep0_start_trans(dep); - WARN_ON(ret < 0); + if (ret < 0) + dev_err(dwc->dev, "ep0 out start transfer failed: %d\n", ret); + for (i = 2; i < DWC3_ENDPOINTS_NUM; i++) { struct dwc3_ep *dwc3_ep; @@ -1061,7 +1063,9 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, ret = dwc3_ep0_start_trans(dep); } - WARN_ON(ret < 0); + if (ret < 0) + dev_err(dwc->dev, + "ep0 data phase start transfer failed: %d\n", ret); } static int dwc3_ep0_start_control_status(struct dwc3_ep *dep) @@ -1078,7 +1082,12 @@ static int dwc3_ep0_start_control_status(struct dwc3_ep *dep) static void __dwc3_ep0_do_control_status(struct dwc3 *dwc, struct dwc3_ep *dep) { - WARN_ON(dwc3_ep0_start_control_status(dep)); + int ret; + + ret = dwc3_ep0_start_control_status(dep); + if (ret) + dev_err(dwc->dev, + "ep0 status phase start transfer failed: %d\n", ret); } static void dwc3_ep0_do_control_status(struct dwc3 *dwc, @@ -1121,7 +1130,10 @@ void dwc3_ep0_end_control_data(struct dwc3 *dwc, struct dwc3_ep *dep) cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); memset(¶ms, 0, sizeof(params)); ret = dwc3_send_gadget_ep_cmd(dep, cmd, ¶ms); - WARN_ON_ONCE(ret); + if (ret) + dev_err_ratelimited(dwc->dev, + "ep0 data phase end transfer failed: %d\n", ret); + dep->resource_index = 0; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 25db36c63951..554f997eb8c4 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1772,7 +1772,11 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int dep->flags |= DWC3_EP_DELAY_STOP; return 0; } - WARN_ON_ONCE(ret); + + if (ret) + dev_err_ratelimited(dep->dwc->dev, + "end transfer failed: %d\n", ret); + dep->resource_index = 0; if (!interrupt) @@ -3777,6 +3781,15 @@ static void dwc3_gadget_endpoint_transfer_complete(struct dwc3_ep *dep, static void dwc3_gadget_endpoint_transfer_not_ready(struct dwc3_ep *dep, const struct dwc3_event_depevt *event) { + /* + * During a device-initiated disconnect, a late xferNotReady event can + * be generated after the End Transfer command resets the event filter, + * but before the controller is halted. Ignore it to prevent a new + * transfer from starting. + */ + if (!dep->dwc->connected) + return; + dwc3_gadget_endpoint_frame_from_event(dep, event); /* @@ -4039,7 +4052,9 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc) dep->flags &= ~DWC3_EP_STALL; ret = dwc3_send_clear_stall_ep_cmd(dep); - WARN_ON_ONCE(ret); + if (ret) + dev_err_ratelimited(dwc->dev, + "failed to clear STALL on %s\n", dep->name); } } diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 2957316fd3d0..1d3085cc9d22 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -502,6 +502,7 @@ struct tegra_xudc { struct clk_bulk_data *clks; bool device_mode; + bool current_device_mode; struct work_struct usb_role_sw_work; struct phy **usb3_phy; @@ -715,6 +716,8 @@ static void tegra_xudc_device_mode_on(struct tegra_xudc *xudc) phy_set_mode_ext(xudc->curr_utmi_phy, PHY_MODE_USB_OTG, USB_ROLE_DEVICE); + + xudc->current_device_mode = true; } static void tegra_xudc_device_mode_off(struct tegra_xudc *xudc) @@ -725,6 +728,8 @@ static void tegra_xudc_device_mode_off(struct tegra_xudc *xudc) dev_dbg(xudc->dev, "device mode off\n"); + xudc->current_device_mode = false; + connected = !!(xudc_readl(xudc, PORTSC) & PORTSC_CCS); reinit_completion(&xudc->disconnect_complete); @@ -4044,10 +4049,10 @@ static int __maybe_unused tegra_xudc_resume(struct device *dev) spin_lock_irqsave(&xudc->lock, flags); xudc->suspended = false; + if (xudc->device_mode != xudc->current_device_mode) + schedule_work(&xudc->usb_role_sw_work); spin_unlock_irqrestore(&xudc->lock, flags); - schedule_work(&xudc->usb_role_sw_work); - pm_runtime_enable(dev); return 0; diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 92bb84f8132a..b3a59ce1b3f4 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -704,8 +704,7 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci, if (!xhci->devs[i]) continue; - retval = xhci_disable_slot(xhci, i); - xhci_free_virt_device(xhci, i); + retval = xhci_disable_and_free_slot(xhci, i); if (retval) xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n", i, retval); diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 07289333a1e8..81eaad87a3d9 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -865,21 +865,20 @@ free_tts: * will be manipulated by the configure endpoint, allocate device, or update * hub functions while this function is removing the TT entries from the list. */ -void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id) +void xhci_free_virt_device(struct xhci_hcd *xhci, struct xhci_virt_device *dev, + int slot_id) { - struct xhci_virt_device *dev; int i; int old_active_eps = 0; /* Slot ID 0 is reserved */ - if (slot_id == 0 || !xhci->devs[slot_id]) + if (slot_id == 0 || !dev) return; - dev = xhci->devs[slot_id]; - - xhci->dcbaa->dev_context_ptrs[slot_id] = 0; - if (!dev) - return; + /* If device ctx array still points to _this_ device, clear it */ + if (dev->out_ctx && + xhci->dcbaa->dev_context_ptrs[slot_id] == cpu_to_le64(dev->out_ctx->dma)) + xhci->dcbaa->dev_context_ptrs[slot_id] = 0; trace_xhci_free_virt_device(dev); @@ -920,8 +919,9 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id) dev->udev->slot_id = 0; if (dev->rhub_port && dev->rhub_port->slot_id == slot_id) dev->rhub_port->slot_id = 0; - kfree(xhci->devs[slot_id]); - xhci->devs[slot_id] = NULL; + if (xhci->devs[slot_id] == dev) + xhci->devs[slot_id] = NULL; + kfree(dev); } /* @@ -962,7 +962,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i out: /* we are now at a leaf device */ xhci_debugfs_remove_slot(xhci, slot_id); - xhci_free_virt_device(xhci, slot_id); + xhci_free_virt_device(xhci, vdev, slot_id); } int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c index 620f8f0febb8..86df80399c9f 100644 --- a/drivers/usb/host/xhci-pci-renesas.c +++ b/drivers/usb/host/xhci-pci-renesas.c @@ -47,8 +47,9 @@ #define RENESAS_ROM_ERASE_MAGIC 0x5A65726F #define RENESAS_ROM_WRITE_MAGIC 0x53524F4D -#define RENESAS_RETRY 10000 -#define RENESAS_DELAY 10 +#define RENESAS_RETRY 50000 /* 50000 * RENESAS_DELAY ~= 500ms */ +#define RENESAS_CHIP_ERASE_RETRY 500000 /* 500000 * RENESAS_DELAY ~= 5s */ +#define RENESAS_DELAY 10 #define RENESAS_FW_NAME "renesas_usb_fw.mem" @@ -407,7 +408,7 @@ static void renesas_rom_erase(struct pci_dev *pdev) /* sleep a bit while ROM is erased */ msleep(20); - for (i = 0; i < RENESAS_RETRY; i++) { + for (i = 0; i < RENESAS_CHIP_ERASE_RETRY; i++) { retval = pci_read_config_byte(pdev, RENESAS_ROM_STATUS, &status); status &= RENESAS_ROM_STATUS_ERASE; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index ecd757d482c5..4f8f5aab109d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1592,7 +1592,8 @@ static void xhci_handle_cmd_enable_slot(int slot_id, struct xhci_command *comman command->slot_id = 0; } -static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id) +static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id, + u32 cmd_comp_code) { struct xhci_virt_device *virt_dev; struct xhci_slot_ctx *slot_ctx; @@ -1607,6 +1608,10 @@ static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id) if (xhci->quirks & XHCI_EP_LIMIT_QUIRK) /* Delete default control endpoint resources */ xhci_free_device_endpoint_resources(xhci, virt_dev, true); + if (cmd_comp_code == COMP_SUCCESS) { + xhci->dcbaa->dev_context_ptrs[slot_id] = 0; + xhci->devs[slot_id] = NULL; + } } static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id) @@ -1856,7 +1861,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, xhci_handle_cmd_enable_slot(slot_id, cmd, cmd_comp_code); break; case TRB_DISABLE_SLOT: - xhci_handle_cmd_disable_slot(xhci, slot_id); + xhci_handle_cmd_disable_slot(xhci, slot_id, cmd_comp_code); break; case TRB_CONFIG_EP: if (!cmd->completion) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 47151ca527bf..742c23826e17 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -309,6 +309,7 @@ int xhci_enable_interrupter(struct xhci_interrupter *ir) return -EINVAL; iman = readl(&ir->ir_set->iman); + iman &= ~IMAN_IP; iman |= IMAN_IE; writel(iman, &ir->ir_set->iman); @@ -325,6 +326,7 @@ int xhci_disable_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir) return -EINVAL; iman = readl(&ir->ir_set->iman); + iman &= ~IMAN_IP; iman &= ~IMAN_IE; writel(iman, &ir->ir_set->iman); @@ -3932,8 +3934,7 @@ static int xhci_discover_or_reset_device(struct usb_hcd *hcd, * Obtaining a new device slot to inform the xHCI host that * the USB device has been reset. */ - ret = xhci_disable_slot(xhci, udev->slot_id); - xhci_free_virt_device(xhci, udev->slot_id); + ret = xhci_disable_and_free_slot(xhci, udev->slot_id); if (!ret) { ret = xhci_alloc_dev(hcd, udev); if (ret == 1) @@ -4090,7 +4091,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) xhci_disable_slot(xhci, udev->slot_id); spin_lock_irqsave(&xhci->lock, flags); - xhci_free_virt_device(xhci, udev->slot_id); + xhci_free_virt_device(xhci, virt_dev, udev->slot_id); spin_unlock_irqrestore(&xhci->lock, flags); } @@ -4139,6 +4140,16 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) return 0; } +int xhci_disable_and_free_slot(struct xhci_hcd *xhci, u32 slot_id) +{ + struct xhci_virt_device *vdev = xhci->devs[slot_id]; + int ret; + + ret = xhci_disable_slot(xhci, slot_id); + xhci_free_virt_device(xhci, vdev, slot_id); + return ret; +} + /* * Checks if we have enough host controller resources for the default control * endpoint. @@ -4245,8 +4256,7 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev) return 1; disable_slot: - xhci_disable_slot(xhci, udev->slot_id); - xhci_free_virt_device(xhci, udev->slot_id); + xhci_disable_and_free_slot(xhci, udev->slot_id); return 0; } @@ -4382,8 +4392,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, dev_warn(&udev->dev, "Device not responding to setup %s.\n", act); mutex_unlock(&xhci->mutex); - ret = xhci_disable_slot(xhci, udev->slot_id); - xhci_free_virt_device(xhci, udev->slot_id); + ret = xhci_disable_and_free_slot(xhci, udev->slot_id); if (!ret) { if (xhci_alloc_dev(hcd, udev) == 1) xhci_setup_addressable_virt_dev(xhci, udev); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index a20f4e7cd43a..85d5b964bf1e 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1791,7 +1791,7 @@ void xhci_dbg_trace(struct xhci_hcd *xhci, void (*trace)(struct va_format *), /* xHCI memory management */ void xhci_mem_cleanup(struct xhci_hcd *xhci); int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags); -void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id); +void xhci_free_virt_device(struct xhci_hcd *xhci, struct xhci_virt_device *dev, int slot_id); int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, struct usb_device *udev, gfp_t flags); int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *udev); void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci, @@ -1888,6 +1888,7 @@ void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags); int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); +int xhci_disable_and_free_slot(struct xhci_hcd *xhci, u32 slot_id); int xhci_ext_cap_init(struct xhci_hcd *xhci); int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup); diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c index 7dea28c2b8ee..cb5bbb19060e 100644 --- a/drivers/usb/storage/realtek_cr.c +++ b/drivers/usb/storage/realtek_cr.c @@ -252,7 +252,7 @@ static int rts51x_bulk_transport(struct us_data *us, u8 lun, return USB_STOR_TRANSPORT_ERROR; } - residue = bcs->Residue; + residue = le32_to_cpu(bcs->Residue); if (bcs->Tag != us->tag) return USB_STOR_TRANSPORT_ERROR; diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 54f0b1c83317..dfa5276a5a43 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -934,6 +934,13 @@ UNUSUAL_DEV( 0x05e3, 0x0723, 0x9451, 0x9451, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SANE_SENSE ), +/* Added by Maël GUERIN <mael.guerin@murena.io> */ +UNUSUAL_DEV( 0x0603, 0x8611, 0x0000, 0xffff, + "Novatek", + "NTK96550-based camera", + USB_SC_SCSI, USB_PR_BULK, NULL, + US_FL_BULK_IGNORE_TAG ), + /* * Reported by Hanno Boeck <hanno@gmx.de> * Taken from the Lycoris Kernel @@ -1494,6 +1501,28 @@ UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_WP_DETECT ), +/* + * Reported by Zenm Chen <zenmchen@gmail.com> + * Ignore driver CD mode, otherwise usb_modeswitch may fail to switch + * the device into Wi-Fi mode. + */ +UNUSUAL_DEV( 0x0bda, 0x1a2b, 0x0000, 0xffff, + "Realtek", + "DISK", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_DEVICE ), + +/* + * Reported by Zenm Chen <zenmchen@gmail.com> + * Ignore driver CD mode, otherwise usb_modeswitch may fail to switch + * the device into Wi-Fi mode. + */ +UNUSUAL_DEV( 0x0bda, 0xa192, 0x0000, 0xffff, + "Realtek", + "DISK", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_DEVICE ), + UNUSUAL_DEV( 0x0d49, 0x7310, 0x0000, 0x9999, "Maxtor", "USB to SATA", diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index a4ff2403ddd6..870a71f953f6 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -1485,6 +1485,9 @@ static irqreturn_t fusb302_irq_intn(int irq, void *dev_id) struct fusb302_chip *chip = dev_id; unsigned long flags; + /* Disable our level triggered IRQ until our irq_work has cleared it */ + disable_irq_nosync(chip->gpio_int_n_irq); + spin_lock_irqsave(&chip->irq_lock, flags); if (chip->irq_suspended) chip->irq_while_suspended = true; @@ -1627,6 +1630,7 @@ static void fusb302_irq_work(struct work_struct *work) } done: mutex_unlock(&chip->lock); + enable_irq(chip->gpio_int_n_irq); } static int init_gpio(struct fusb302_chip *chip) @@ -1751,10 +1755,9 @@ static int fusb302_probe(struct i2c_client *client) goto destroy_workqueue; } - ret = devm_request_threaded_irq(dev, chip->gpio_int_n_irq, - NULL, fusb302_irq_intn, - IRQF_ONESHOT | IRQF_TRIGGER_LOW, - "fsc_interrupt_int_n", chip); + ret = request_irq(chip->gpio_int_n_irq, fusb302_irq_intn, + IRQF_ONESHOT | IRQF_TRIGGER_LOW, + "fsc_interrupt_int_n", chip); if (ret < 0) { dev_err(dev, "cannot request IRQ for GPIO Int_N, ret=%d", ret); goto tcpm_unregister_port; @@ -1779,6 +1782,7 @@ static void fusb302_remove(struct i2c_client *client) struct fusb302_chip *chip = i2c_get_clientdata(client); disable_irq_wake(chip->gpio_int_n_irq); + free_irq(chip->gpio_int_n_irq, chip); cancel_work_sync(&chip->irq_work); cancel_delayed_work_sync(&chip->bc_lvl_handler); tcpm_unregister_port(chip->tcpm_port); diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c index 0cdda06592fd..af8da6dc60ae 100644 --- a/drivers/usb/typec/tcpm/maxim_contaminant.c +++ b/drivers/usb/typec/tcpm/maxim_contaminant.c @@ -188,6 +188,11 @@ static int max_contaminant_read_comparators(struct max_tcpci_chip *chip, u8 *ven if (ret < 0) return ret; + /* Disable low power mode */ + ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCLPMODESEL, + FIELD_PREP(CCLPMODESEL, + LOW_POWER_MODE_DISABLE)); + /* Sleep to allow comparators settle */ usleep_range(5000, 6000); ret = regmap_update_bits(regmap, TCPC_TCPC_CTRL, TCPC_TCPC_CTRL_ORIENTATION, PLUG_ORNT_CC1); @@ -324,6 +329,39 @@ static int max_contaminant_enable_dry_detection(struct max_tcpci_chip *chip) return 0; } +static int max_contaminant_enable_toggling(struct max_tcpci_chip *chip) +{ + struct regmap *regmap = chip->data.regmap; + int ret; + + /* Disable dry detection if enabled. */ + ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCLPMODESEL, + FIELD_PREP(CCLPMODESEL, + LOW_POWER_MODE_DISABLE)); + if (ret) + return ret; + + ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL1, CCCONNDRY, 0); + if (ret) + return ret; + + ret = max_tcpci_write8(chip, TCPC_ROLE_CTRL, TCPC_ROLE_CTRL_DRP | + FIELD_PREP(TCPC_ROLE_CTRL_CC1, + TCPC_ROLE_CTRL_CC_RD) | + FIELD_PREP(TCPC_ROLE_CTRL_CC2, + TCPC_ROLE_CTRL_CC_RD)); + if (ret) + return ret; + + ret = regmap_update_bits(regmap, TCPC_TCPC_CTRL, + TCPC_TCPC_CTRL_EN_LK4CONN_ALRT, + TCPC_TCPC_CTRL_EN_LK4CONN_ALRT); + if (ret) + return ret; + + return max_tcpci_write8(chip, TCPC_COMMAND, TCPC_CMD_LOOK4CONNECTION); +} + bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect_while_debounce, bool *cc_handled) { @@ -340,6 +378,12 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect if (ret < 0) return false; + if (cc_status & TCPC_CC_STATUS_TOGGLING) { + if (chip->contaminant_state == DETECTED) + return true; + return false; + } + if (chip->contaminant_state == NOT_DETECTED || chip->contaminant_state == SINK) { if (!disconnect_while_debounce) msleep(100); @@ -372,6 +416,12 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect max_contaminant_enable_dry_detection(chip); return true; } + + ret = max_contaminant_enable_toggling(chip); + if (ret) + dev_err(chip->dev, + "Failed to enable toggling, ret=%d", + ret); } } else if (chip->contaminant_state == DETECTED) { if (!(cc_status & TCPC_CC_STATUS_TOGGLING)) { @@ -379,6 +429,14 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect if (chip->contaminant_state == DETECTED) { max_contaminant_enable_dry_detection(chip); return true; + } else { + ret = max_contaminant_enable_toggling(chip); + if (ret) { + dev_err(chip->dev, + "Failed to enable toggling, ret=%d", + ret); + return true; + } } } } diff --git a/drivers/usb/typec/tcpm/tcpci_maxim.h b/drivers/usb/typec/tcpm/tcpci_maxim.h index 76270d5c2838..b33540a42a95 100644 --- a/drivers/usb/typec/tcpm/tcpci_maxim.h +++ b/drivers/usb/typec/tcpm/tcpci_maxim.h @@ -21,6 +21,7 @@ #define CCOVPDIS BIT(6) #define SBURPCTRL BIT(5) #define CCLPMODESEL GENMASK(4, 3) +#define LOW_POWER_MODE_DISABLE 0 #define ULTRA_LOW_POWER_MODE 1 #define CCRPCTRL GENMASK(2, 0) #define UA_1_SRC 1 diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index d2b3ae7113ab..b01ec99106cd 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -116,13 +116,11 @@ e_free: static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) { + struct snp_derived_key_resp *derived_key_resp __free(kfree) = NULL; struct snp_derived_key_req *derived_key_req __free(kfree) = NULL; - struct snp_derived_key_resp derived_key_resp = {0}; struct snp_msg_desc *mdesc = snp_dev->msg_desc; struct snp_guest_req req = {}; int rc, resp_len; - /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */ - u8 buf[64 + 16]; if (!arg->req_data || !arg->resp_data) return -EINVAL; @@ -132,8 +130,9 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque * response payload. Make sure that it has enough space to cover the * authtag. */ - resp_len = sizeof(derived_key_resp.data) + mdesc->ctx->authsize; - if (sizeof(buf) < resp_len) + resp_len = sizeof(derived_key_resp->data) + mdesc->ctx->authsize; + derived_key_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!derived_key_resp) return -ENOMEM; derived_key_req = kzalloc(sizeof(*derived_key_req), GFP_KERNEL_ACCOUNT); @@ -149,23 +148,21 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque req.vmpck_id = mdesc->vmpck_id; req.req_buf = derived_key_req; req.req_sz = sizeof(*derived_key_req); - req.resp_buf = buf; + req.resp_buf = derived_key_resp; req.resp_sz = resp_len; req.exit_code = SVM_VMGEXIT_GUEST_REQUEST; rc = snp_send_guest_request(mdesc, &req); arg->exitinfo2 = req.exitinfo2; - if (rc) - return rc; - - memcpy(derived_key_resp.data, buf, sizeof(derived_key_resp.data)); - if (copy_to_user((void __user *)arg->resp_data, &derived_key_resp, - sizeof(derived_key_resp))) - rc = -EFAULT; + if (!rc) { + if (copy_to_user((void __user *)arg->resp_data, derived_key_resp, + sizeof(derived_key_resp->data))) + rc = -EFAULT; + } /* The response buffer contains the sensitive data, explicitly clear it. */ - memzero_explicit(buf, sizeof(buf)); - memzero_explicit(&derived_key_resp, sizeof(derived_key_resp)); + memzero_explicit(derived_key_resp, sizeof(*derived_key_resp)); + return rc; } diff --git a/drivers/w1/masters/matrox_w1.c b/drivers/w1/masters/matrox_w1.c index 2852cd2dc67c..146fa7c6e74e 100644 --- a/drivers/w1/masters/matrox_w1.c +++ b/drivers/w1/masters/matrox_w1.c @@ -47,7 +47,6 @@ struct matrox_device { unsigned long phys_addr; void __iomem *virt_addr; - unsigned long found; struct w1_bus_master *bus_master; }; @@ -158,8 +157,6 @@ static int matrox_w1_probe(struct pci_dev *pdev, const struct pci_device_id *ent pci_set_drvdata(pdev, dev); - dev->found = 1; - dev_info(&pdev->dev, "Matrox G400 GPIO transport layer for 1-wire.\n"); return 0; @@ -176,10 +173,9 @@ static void matrox_w1_remove(struct pci_dev *pdev) { struct matrox_device *dev = pci_get_drvdata(pdev); - if (dev->found) { - w1_remove_master_device(dev->bus_master); - iounmap(dev->virt_addr); - } + w1_remove_master_device(dev->bus_master); + iounmap(dev->virt_addr); + kfree(dev); } diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 3c9da446b85d..528682bf0c7f 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -718,26 +718,6 @@ int xs_watch_msg(struct xs_watch_event *event) return 0; } -/* - * Certain older XenBus toolstack cannot handle reading values that are - * not populated. Some Xen 3.4 installation are incapable of doing this - * so if we are running on anything older than 4 do not attempt to read - * control/platform-feature-xs_reset_watches. - */ -static bool xen_strict_xenbus_quirk(void) -{ -#ifdef CONFIG_X86 - uint32_t eax, ebx, ecx, edx, base; - - base = xen_cpuid_base(); - cpuid(base + 1, &eax, &ebx, &ecx, &edx); - - if ((eax >> 16) < 4) - return true; -#endif - return false; - -} static void xs_reset_watches(void) { int err; @@ -745,9 +725,6 @@ static void xs_reset_watches(void) if (!xen_hvm_domain() || xen_initial_domain()) return; - if (xen_strict_xenbus_quirk()) - return; - if (!xenbus_read_unsigned("control", "platform-feature-xs_reset_watches", 0)) return; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 1d847a939f29..180a458fc4f7 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -129,7 +129,7 @@ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *n } return inode; } -EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); +EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 835b0deef9bb..c953297aa89a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1512,7 +1512,7 @@ out: /* * Return 0 if we have submitted or queued the sector for submission. - * Return <0 for critical errors. + * Return <0 for critical errors, and the sector will have its dirty flag cleared. * * Caller should make sure filepos < i_size and handle filepos >= i_size case. */ @@ -1535,8 +1535,17 @@ static int submit_one_sector(struct btrfs_inode *inode, ASSERT(filepos < i_size); em = btrfs_get_extent(inode, NULL, filepos, sectorsize); - if (IS_ERR(em)) + if (IS_ERR(em)) { + /* + * When submission failed, we should still clear the folio dirty. + * Or the folio will be written back again but without any + * ordered extent. + */ + btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize); + btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize); + btrfs_folio_clear_writeback(fs_info, folio, filepos, sectorsize); return PTR_ERR(em); + } extent_offset = filepos - em->start; em_end = btrfs_extent_map_end(em); @@ -1609,8 +1618,12 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, folio_unlock(folio); return 1; } - if (ret < 0) + if (ret < 0) { + btrfs_folio_clear_dirty(fs_info, folio, start, len); + btrfs_folio_set_writeback(fs_info, folio, start, len); + btrfs_folio_clear_writeback(fs_info, folio, start, len); return ret; + } for (cur = start; cur < start + len; cur += fs_info->sectorsize) set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap); @@ -1666,8 +1679,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, * Here we set writeback and clear for the range. If the full folio * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. * - * If we hit any error, the corresponding sector will still be dirty - * thus no need to clear PAGECACHE_TAG_DIRTY. + * If we hit any error, the corresponding sector will have its dirty + * flag cleared and writeback finished, thus no need to handle the error case. */ if (!submitted_io && !error) { btrfs_folio_set_writeback(fs_info, folio, start, len); @@ -1813,6 +1826,7 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *e xas_load(&xas); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); @@ -4331,15 +4345,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio) unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1; int ret; - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) { /* * The same as try_release_extent_buffer(), to ensure the eb * won't disappear out from under us. */ spin_lock(&eb->refs_lock); + rcu_read_unlock(); + if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); continue; } @@ -4358,11 +4375,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio) * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ - xa_unlock_irq(&fs_info->buffer_tree); release_extent_buffer(eb); - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); } - xa_unlock_irq(&fs_info->buffer_tree); + rcu_read_unlock(); /* * Finally to check if we have cleared folio private, as if we have @@ -4375,7 +4391,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio) ret = 0; spin_unlock(&folio->mapping->i_private_lock); return ret; - } int try_release_extent_buffer(struct folio *folio) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b77dd22b8cdb..9e4aec7330cb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, while (index <= end_index) { folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); - index++; - if (IS_ERR(folio)) + if (IS_ERR(folio)) { + index++; continue; + } + index = folio_end(folio) >> PAGE_SHIFT; /* * Here we just clear all Ordered bits for every page in the * range, then btrfs_mark_ordered_io_finished() will handle @@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio * cleaered by the caller. */ if (ret < 0) - btrfs_cleanup_ordered_extents(inode, file_pos, end); + btrfs_cleanup_ordered_extents(inode, file_pos, len); return ret; } @@ -4187,6 +4189,23 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, return ret; } +static void update_time_after_link_or_unlink(struct btrfs_inode *dir) +{ + struct timespec64 now; + + /* + * If we are replaying a log tree, we do not want to update the mtime + * and ctime of the parent directory with the current time, since the + * log replay procedure is responsible for setting them to their correct + * values (the ones it had when the fsync was done). + */ + if (test_bit(BTRFS_FS_LOG_RECOVERING, &dir->root->fs_info->flags)) + return; + + now = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, now); +} + /* * unlink helper that gets used here in inode.c and in the tree logging * recovery code. It remove a link in a directory with a given name, and @@ -4287,7 +4306,7 @@ skip_backref: inode_inc_iversion(&inode->vfs_inode); inode_set_ctime_current(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); - inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); + update_time_after_link_or_unlink(dir); return btrfs_update_inode(trans, dir); } @@ -6681,15 +6700,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + name->len * 2); inode_inc_iversion(&parent_inode->vfs_inode); - /* - * If we are replaying a log tree, we do not want to update the mtime - * and ctime of the parent directory with the current time, since the - * log replay procedure is responsible for setting them to their correct - * values (the ones it had when the fsync was done). - */ - if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) - inode_set_mtime_to_ts(&parent_inode->vfs_inode, - inode_set_ctime_current(&parent_inode->vfs_inode)); + update_time_after_link_or_unlink(parent_inode); ret = btrfs_update_inode(trans, parent_inode); if (ret) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1a5972178b3a..ccaa9a3cf1ce 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *src, int sign) { struct btrfs_qgroup *qgroup; - struct btrfs_qgroup *cur; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; int ret = 0; @@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, goto out; qgroup_iterator_add(&qgroup_list, qgroup); - list_for_each_entry(cur, &qgroup_list, iterator) { + list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e58151933844..7256f6748c8f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, if (btrfs_root_id(root) == objectid) { u64 commit_root_gen; + /* + * Relocation will wait for cleaner thread, and any half-dropped + * subvolume will be fully cleaned up at mount time. + * So here we shouldn't hit a subvolume with non-zero drop_progress. + * + * If this isn't the case, error out since it can make us attempt to + * drop references for extents that were already dropped before. + */ + if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) { + struct btrfs_key cpu_key; + + btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress); + btrfs_err(fs_info, + "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)", + objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset); + ret = -EUCLEAN; + goto fail; + } + /* called by btrfs_init_reloc_root */ ret = btrfs_copy_root(trans, root, root->commit_root, &eb, BTRFS_TREE_RELOC_OBJECTID); diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index c9b3821957f7..cb4f97833dc3 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -448,8 +448,25 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, spin_lock_irqsave(&bfs->lock, flags); bitmap_set(bfs->bitmaps, start_bit, len >> fs_info->sectorsize_bits); + + /* + * Don't clear the TOWRITE tag when starting writeback on a still-dirty + * folio. Doing so can cause WB_SYNC_ALL writepages() to overlook it, + * assume writeback is complete, and exit too early — violating sync + * ordering guarantees. + */ if (!folio_test_writeback(folio)) - folio_start_writeback(folio); + __folio_start_writeback(folio, true); + if (!folio_test_dirty(folio)) { + struct address_space *mapping = folio_mapping(folio); + XA_STATE(xas, &mapping->i_pages, folio->index); + unsigned long flags; + + xas_lock_irqsave(&xas, flags); + xas_load(&xas); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); + } spin_unlock_irqrestore(&bfs->lock, flags); } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 68e35a3700ff..a262b494a89f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -88,6 +88,9 @@ struct btrfs_fs_context { refcount_t refs; }; +static void btrfs_emit_options(struct btrfs_fs_info *info, + struct btrfs_fs_context *old); + enum { Opt_acl, Opt_clear_cache, @@ -698,12 +701,9 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) { if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) { - btrfs_info(info, "disk space caching is enabled"); btrfs_warn(info, "space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2"); } - if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE)) - btrfs_info(info, "using free-space-tree"); } return ret; @@ -980,6 +980,8 @@ static int btrfs_fill_super(struct super_block *sb, return ret; } + btrfs_emit_options(fs_info, NULL); + inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); @@ -1437,7 +1439,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info, { btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum"); btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts"); - btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum"); + btrfs_info_if_set(info, old, NODATACOW, "setting nodatacow"); btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations"); btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme"); btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers"); @@ -1459,10 +1461,11 @@ static void btrfs_emit_options(struct btrfs_fs_info *info, btrfs_info_if_set(info, old, IGNOREMETACSUMS, "ignoring meta csums"); btrfs_info_if_set(info, old, IGNORESUPERFLAGS, "ignoring unknown super block flags"); + btrfs_info_if_unset(info, old, NODATASUM, "setting datasum"); btrfs_info_if_unset(info, old, NODATACOW, "setting datacow"); btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations"); btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme"); - btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers"); + btrfs_info_if_unset(info, old, NOBARRIER, "turning on barriers"); btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log"); btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching"); btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree"); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2186e87fb61b..69e11557fd13 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ -static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) +static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); - return; + return -ENOENT; } spin_lock(&cache->space_info->lock); @@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); + + return 0; } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { - int ret; - btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); - if (trans) { - ret = btrfs_pin_reserved_extent(trans, eb); - if (ret) - return ret; - } else { - unaccount_log_buffer(eb->fs_info, eb->start); - } + if (trans) + return btrfs_pin_reserved_extent(trans, eb); - return 0; + return unaccount_log_buffer(eb->fs_info, eb->start); } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 245e813ecd78..ea662036f441 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -17,6 +17,7 @@ #include "accessors.h" #include "bio.h" #include "transaction.h" +#include "sysfs.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096 @@ -42,6 +43,9 @@ /* Number of superblock log zones */ #define BTRFS_NR_SB_LOG_ZONES 2 +/* Default number of max active zones when the device has no limits. */ +#define BTRFS_DEFAULT_MAX_ACTIVE_ZONES 128 + /* * Minimum of active zones we need: * @@ -416,7 +420,10 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; - max_active_zones = bdev_max_active_zones(bdev); + max_active_zones = min_not_zero(bdev_max_active_zones(bdev), + bdev_max_open_zones(bdev)); + if (!max_active_zones && zone_info->nr_zones > BTRFS_DEFAULT_MAX_ACTIVE_ZONES) + max_active_zones = BTRFS_DEFAULT_MAX_ACTIVE_ZONES; if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) { btrfs_err(fs_info, "zoned: %s: max active zones %u is too small, need at least %u active zones", @@ -2168,10 +2175,15 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } - /* No space left */ - if (btrfs_zoned_bg_is_full(block_group)) { - ret = false; - goto out_unlock; + if (block_group->flags & BTRFS_BLOCK_GROUP_DATA) { + /* The caller should check if the block group is full. */ + if (WARN_ON_ONCE(btrfs_zoned_bg_is_full(block_group))) { + ret = false; + goto out_unlock; + } + } else { + /* Since it is already written, it should have been active. */ + WARN_ON_ONCE(block_group->meta_write_pointer != block_group->start); } for (i = 0; i < map->num_stripes; i++) { @@ -2230,7 +2242,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group) struct btrfs_fs_info *fs_info = block_group->fs_info; const u64 end = block_group->start + block_group->length; struct extent_buffer *eb; - unsigned long index, start = (block_group->start >> fs_info->sectorsize_bits); + unsigned long index, start = (block_group->start >> fs_info->nodesize_bits); rcu_read_lock(); xa_for_each_start(&fs_info->buffer_tree, index, eb, start) { @@ -2245,6 +2257,40 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group) rcu_read_unlock(); } +static int call_zone_finish(struct btrfs_block_group *block_group, + struct btrfs_io_stripe *stripe) +{ + struct btrfs_device *device = stripe->dev; + const u64 physical = stripe->physical; + struct btrfs_zoned_device_info *zinfo = device->zone_info; + int ret; + + if (!device->bdev) + return 0; + + if (zinfo->max_active_zones == 0) + return 0; + + if (btrfs_dev_is_sequential(device, physical)) { + unsigned int nofs_flags; + + nofs_flags = memalloc_nofs_save(); + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + zinfo->zone_size >> SECTOR_SHIFT); + memalloc_nofs_restore(nofs_flags); + + if (ret) + return ret; + } + + if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA)) + zinfo->reserved_active_zones++; + btrfs_dev_clear_active_zone(device, physical); + + return 0; +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -2329,31 +2375,12 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - struct btrfs_device *device = map->stripes[i].dev; - const u64 physical = map->stripes[i].physical; - struct btrfs_zoned_device_info *zinfo = device->zone_info; - unsigned int nofs_flags; - - if (!device->bdev) - continue; - - if (zinfo->max_active_zones == 0) - continue; - - nofs_flags = memalloc_nofs_save(); - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - zinfo->zone_size >> SECTOR_SHIFT); - memalloc_nofs_restore(nofs_flags); + ret = call_zone_finish(block_group, &map->stripes[i]); if (ret) { up_read(&dev_replace->rwsem); return ret; } - - if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA)) - zinfo->reserved_active_zones++; - btrfs_dev_clear_active_zone(device, physical); } up_read(&dev_replace->rwsem); @@ -2504,12 +2531,12 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info) { struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; - struct btrfs_space_info *space_info = data_sinfo->sub_group[0]; + struct btrfs_space_info *space_info = data_sinfo; struct btrfs_trans_handle *trans; struct btrfs_block_group *bg; struct list_head *bg_list; u64 alloc_flags; - bool initial = false; + bool first = true; bool did_chunk_alloc = false; int index; int ret; @@ -2523,21 +2550,52 @@ void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info) if (sb_rdonly(fs_info->sb)) return; - ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); alloc_flags = btrfs_get_alloc_profile(fs_info, space_info->flags); index = btrfs_bg_flags_to_raid_index(alloc_flags); - bg_list = &data_sinfo->block_groups[index]; + /* Scan the data space_info to find empty block groups. Take the second one. */ again: + bg_list = &space_info->block_groups[index]; list_for_each_entry(bg, bg_list, list) { - if (bg->used > 0) + if (bg->alloc_offset != 0) continue; - if (!initial) { - initial = true; + if (first) { + first = false; continue; } + if (space_info == data_sinfo) { + /* Migrate the block group to the data relocation space_info. */ + struct btrfs_space_info *reloc_sinfo = data_sinfo->sub_group[0]; + int factor; + + ASSERT(reloc_sinfo->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); + factor = btrfs_bg_type_to_factor(bg->flags); + + down_write(&space_info->groups_sem); + list_del_init(&bg->list); + /* We can assume this as we choose the second empty one. */ + ASSERT(!list_empty(&space_info->block_groups[index])); + up_write(&space_info->groups_sem); + + spin_lock(&space_info->lock); + space_info->total_bytes -= bg->length; + space_info->disk_total -= bg->length * factor; + /* There is no allocation ever happened. */ + ASSERT(bg->used == 0); + ASSERT(bg->zone_unusable == 0); + /* No super block in a block group on the zoned setup. */ + ASSERT(bg->bytes_super == 0); + spin_unlock(&space_info->lock); + + bg->space_info = reloc_sinfo; + if (reloc_sinfo->block_group_kobjs[index] == NULL) + btrfs_sysfs_add_block_group_type(bg); + + btrfs_add_bg_to_space_info(fs_info, bg); + } + fs_info->data_reloc_bg = bg->start; set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &bg->runtime_flags); btrfs_zone_activate(bg); @@ -2552,11 +2610,18 @@ again: if (IS_ERR(trans)) return; + /* Allocate new BG in the data relocation space_info. */ + space_info = data_sinfo->sub_group[0]; + ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); ret = btrfs_chunk_alloc(trans, space_info, alloc_flags, CHUNK_ALLOC_FORCE); btrfs_end_transaction(trans); if (ret == 1) { + /* + * We allocated a new block group in the data relocation space_info. We + * can take that one. + */ + first = false; did_chunk_alloc = true; - bg_list = &space_info->block_groups[index]; goto again; } } @@ -2650,7 +2715,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) spin_lock(&block_group->lock); if (block_group->reserved || block_group->alloc_offset == 0 || - (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) || + !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) || test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); continue; diff --git a/fs/buffer.c b/fs/buffer.c index ead4dc85debd..6a8752f7bbed 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -157,8 +157,8 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { - __end_buffer_read_notouch(bh, uptodate); put_bh(bh); + __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); diff --git a/fs/coredump.c b/fs/coredump.c index fedbead956ed..5dce257c67fc 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -345,7 +345,7 @@ static bool coredump_parse(struct core_name *cn, struct coredump_params *cprm, was_space = false; err = cn_printf(cn, "%c", '\0'); if (err) - return err; + return false; (*argv)[(*argc)++] = cn->used; } } @@ -1743,6 +1743,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t done = 0; int ret; + if (WARN_ON_ONCE(iocb->ki_flags & IOCB_ATOMIC)) + return -EIO; + if (!iomi.len) return 0; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index a0357b0cf362..c12d649df6a5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -183,6 +183,9 @@ static int debugfs_reconfigure(struct fs_context *fc) struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; + if (!new_opts) + return 0; + sync_filesystem(sb); /* structure copy of new mount options to sb */ @@ -282,10 +285,16 @@ static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) static int debugfs_get_tree(struct fs_context *fc) { + int err; + if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return -EPERM; - return get_tree_single(fc, debugfs_fill_super); + err = get_tree_single(fc, debugfs_fill_super); + if (err) + return err; + + return debugfs_reconfigure(fc); } static void debugfs_free_fc(struct fs_context *fc) diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 7b26efc271ee..d81f3318417d 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -3,8 +3,18 @@ config EROFS_FS tristate "EROFS filesystem support" depends on BLOCK + select CACHEFILES if EROFS_FS_ONDEMAND select CRC32 + select CRYPTO if EROFS_FS_ZIP_ACCEL + select CRYPTO_DEFLATE if EROFS_FS_ZIP_ACCEL select FS_IOMAP + select LZ4_DECOMPRESS if EROFS_FS_ZIP + select NETFS_SUPPORT if EROFS_FS_ONDEMAND + select XXHASH if EROFS_FS_XATTR + select XZ_DEC if EROFS_FS_ZIP_LZMA + select XZ_DEC_MICROLZMA if EROFS_FS_ZIP_LZMA + select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE + select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD help EROFS (Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (e.g. no buffer heads, inline @@ -38,7 +48,6 @@ config EROFS_FS_DEBUG config EROFS_FS_XATTR bool "EROFS extended attributes" depends on EROFS_FS - select XXHASH default y help Extended attributes are name:value pairs associated with inodes by @@ -94,7 +103,6 @@ config EROFS_FS_BACKED_BY_FILE config EROFS_FS_ZIP bool "EROFS Data Compression Support" depends on EROFS_FS - select LZ4_DECOMPRESS default y help Enable transparent compression support for EROFS file systems. @@ -104,8 +112,6 @@ config EROFS_FS_ZIP config EROFS_FS_ZIP_LZMA bool "EROFS LZMA compressed data support" depends on EROFS_FS_ZIP - select XZ_DEC - select XZ_DEC_MICROLZMA help Saying Y here includes support for reading EROFS file systems containing LZMA compressed data, specifically called microLZMA. It @@ -117,7 +123,6 @@ config EROFS_FS_ZIP_LZMA config EROFS_FS_ZIP_DEFLATE bool "EROFS DEFLATE compressed data support" depends on EROFS_FS_ZIP - select ZLIB_INFLATE help Saying Y here includes support for reading EROFS file systems containing DEFLATE compressed data. It gives better compression @@ -132,7 +137,6 @@ config EROFS_FS_ZIP_DEFLATE config EROFS_FS_ZIP_ZSTD bool "EROFS Zstandard compressed data support" depends on EROFS_FS_ZIP - select ZSTD_DECOMPRESS help Saying Y here includes support for reading EROFS file systems containing Zstandard compressed data. It gives better compression @@ -147,8 +151,6 @@ config EROFS_FS_ZIP_ZSTD config EROFS_FS_ZIP_ACCEL bool "EROFS hardware decompression support" depends on EROFS_FS_ZIP - select CRYPTO - select CRYPTO_DEFLATE help Saying Y here includes hardware accelerator support for reading EROFS file systems containing compressed data. It gives better @@ -163,9 +165,7 @@ config EROFS_FS_ZIP_ACCEL config EROFS_FS_ONDEMAND bool "EROFS fscache-based on-demand read support (deprecated)" depends on EROFS_FS - select NETFS_SUPPORT select FSCACHE - select CACHEFILES select CACHEFILES_ONDEMAND help This permits EROFS to use fscache-backed data blobs with on-demand diff --git a/fs/erofs/super.c b/fs/erofs/super.c index e1020aa60771..1b529ace4db0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -174,6 +174,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); + if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { + erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", + dif->path); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; @@ -210,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb, ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } - if (!ondisk_extradevs) + if (!ondisk_extradevs) { + if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { + erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } return 0; + } if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; @@ -313,8 +323,8 @@ static int erofs_read_superblock(struct super_block *sb) sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) { sbi->root_nid = le64_to_cpu(dsb->rootnid_8b); - sbi->dif0.blocks = (sbi->dif0.blocks << 32) | - le16_to_cpu(dsb->rb.blocks_hi); + sbi->dif0.blocks = sbi->dif0.blocks | + ((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32); } else { sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b); } @@ -338,7 +348,6 @@ static int erofs_read_superblock(struct super_block *sb) if (ret < 0) goto out; - /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_48bit(sbi)) @@ -671,14 +680,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return invalfc(fc, "cannot use fsoffset in fscache mode"); } - if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dif0.dax_dev) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); - } else if (sbi->blkszbits != PAGE_SHIFT) { - errorfc(fc, "unsupported blocksize for DAX"); - clear_opt(&sbi->opt, DAX_ALWAYS); - } + if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) { + erofs_info(sb, "unsupported blocksize for DAX"); + clear_opt(&sbi->opt, DAX_ALWAYS); } sb->s_time_gran = 1; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 792f20888a8f..2d73297003d2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1432,6 +1432,16 @@ static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) } #endif +/* Use (kthread_)work in atomic contexts to minimize scheduling overhead */ +static inline bool z_erofs_in_atomic(void) +{ + if (IS_ENABLED(CONFIG_PREEMPTION) && rcu_preempt_depth()) + return true; + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return true; + return !preemptible(); +} + static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, int bios) { @@ -1446,8 +1456,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; - /* Use (kthread_)work and sync decompression for atomic contexts only */ - if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) { + if (z_erofs_in_atomic()) { #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD struct kthread_worker *worker; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 383c6edea6dd..91185c40f755 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -393,6 +393,14 @@ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb, /* Reserved GDT blocks */ if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) { len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); + + /* + * mkfs.ext4 can set s_reserved_gdt_blocks as 0 in some cases, + * check for that. + */ + if (!len) + return 0; + error = ext4_getfsmap_fill(meta_list, fsb, len, EXT4_FMR_OWN_RESV_GDT); if (error) @@ -526,6 +534,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb, ext4_group_t end_ag; ext4_grpblk_t first_cluster; ext4_grpblk_t last_cluster; + struct ext4_fsmap irec; int error = 0; bofs = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -609,10 +618,18 @@ static int ext4_getfsmap_datadev(struct super_block *sb, goto err; } - /* Report any gaps at the end of the bg */ + /* + * The dummy record below will cause ext4_getfsmap_helper() to report + * any allocated blocks at the end of the range. + */ + irec.fmr_device = 0; + irec.fmr_physical = end_fsb + 1; + irec.fmr_length = 0; + irec.fmr_owner = EXT4_FMR_OWN_FREE; + irec.fmr_flags = 0; + info->gfi_last = true; - error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1, - 0, info); + error = ext4_getfsmap_helper(sb, info, &irec); if (error) goto err; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 7de327fa7b1c..d45124318200 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -539,7 +539,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, int indirect_blks; int blocks_to_boundary = 0; int depth; - int count = 0; + u64 count = 0; ext4_fsblk_t first_block = 0; trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); @@ -588,7 +588,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, count++; /* Fill in size of a hole we found */ map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, count); + map->m_len = umin(map->m_len, count); goto cleanup; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ed54c4d0f2f9..5b7a15db4953 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -146,7 +146,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, */ int ext4_inode_is_fast_symlink(struct inode *inode) { - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + if (!ext4_has_feature_ea_inode(inode->i_sb)) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; @@ -3155,7 +3155,7 @@ retry: folio_unlock(folio); folio_put(folio); /* - * block_write_begin may have instantiated a few blocks + * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold inode lock. */ diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d83f91b62317..2cd36f59c9e3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2965,7 +2965,6 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir, struct inode *inode) { struct buffer_head *dir_block = NULL; - struct ext4_dir_entry_2 *de; ext4_lblk_t block = 0; int err; @@ -2982,10 +2981,7 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir, dir_block = ext4_append(handle, inode, &block); if (IS_ERR(dir_block)) return PTR_ERR(dir_block); - de = (struct ext4_dir_entry_2 *)dir_block->b_data; err = ext4_init_dirblock(handle, inode, dir_block, dir->i_ino, NULL, 0); - if (err) - goto out; out: brelse(dir_block); return err; diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 7c7f792ad6ab..524d4658fa40 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -589,8 +589,9 @@ int ext4_init_orphan_info(struct super_block *sb) } oi->of_blocks = inode->i_size >> sb->s_blocksize_bits; oi->of_csum_seed = EXT4_I(inode)->i_csum_seed; - oi->of_binfo = kmalloc(oi->of_blocks*sizeof(struct ext4_orphan_block), - GFP_KERNEL); + oi->of_binfo = kmalloc_array(oi->of_blocks, + sizeof(struct ext4_orphan_block), + GFP_KERNEL); if (!oi->of_binfo) { ret = -ENOMEM; goto out_put; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3d8b0f6d2dea..39abfeec5f36 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -547,7 +547,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio, * first page of the bio. Otherwise it can deadlock. */ if (io->io_bio) - gfp_flags = GFP_NOWAIT | __GFP_NOWARN; + gfp_flags = GFP_NOWAIT; retry_encrypt: bounce_page = fscrypt_encrypt_pagecache_blocks(folio, enc_bytes, 0, gfp_flags); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c7d39da7e733..699c15db28a8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -268,7 +268,7 @@ struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, - sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); + sb->s_blocksize, GFP_NOWAIT); if (likely(bh)) { if (trylock_buffer(bh)) @@ -1998,6 +1998,9 @@ int ext4_init_fs_context(struct fs_context *fc) fc->fs_private = ctx; fc->ops = &ext4_context_ops; + /* i_version is always enabled now */ + fc->sb_flags |= SB_I_VERSION; + return 0; } @@ -2975,6 +2978,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); + if (nodefs && sb->s_flags & SB_I_VERSION) + SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & @@ -5314,9 +5319,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); - /* i_version is always enabled now */ - sb->s_flags |= SB_I_VERSION; - /* HSM events are allowed by default. */ sb->s_iflags |= SB_I_ALLOW_HSM; @@ -5414,6 +5416,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; + if (bdev_read_only(sb->s_bdev)) + needs_recovery = 0; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " diff --git a/fs/fhandle.c b/fs/fhandle.c index 7c236f64cdea..68a7d2861c58 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -402,7 +402,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, if (retval) return retval; - CLASS(get_unused_fd, fd)(O_CLOEXEC); + CLASS(get_unused_fd, fd)(open_flag); if (fd < 0) return fd; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index cc57367fb641..a07b8cf73ae2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2608,10 +2608,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); - spin_unlock(&wb->list_lock); - spin_unlock(&inode->i_lock); - trace_writeback_dirty_inode_enqueue(inode); - /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread @@ -2621,6 +2617,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); + + spin_unlock(&wb->list_lock); + spin_unlock(&inode->i_lock); + trace_writeback_dirty_inode_enqueue(inode); + return; } } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ecb869e895ab..67c2318bfc42 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -289,11 +289,6 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, } } - if (attr->blksize != 0) - inode->i_blkbits = ilog2(attr->blksize); - else - inode->i_blkbits = inode->i_sb->s_blocksize_bits; - /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 6f25d4cfea9f..b84f6af2eb4c 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -363,14 +363,14 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) if (iomap->flags & IOMAP_F_SHARED) dio->flags |= IOMAP_DIO_COW; - if (iomap->flags & IOMAP_F_NEW) { + if (iomap->flags & IOMAP_F_NEW) need_zeroout = true; - } else if (iomap->type == IOMAP_MAPPED) { - if (iomap_dio_can_use_fua(iomap, dio)) - bio_opf |= REQ_FUA; - else - dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; - } + else if (iomap->type == IOMAP_MAPPED && + iomap_dio_can_use_fua(iomap, dio)) + bio_opf |= REQ_FUA; + + if (!(bio_opf & REQ_FUA)) + dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; /* * We can only do deferred completion for pure overwrites that diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index b3971e91e8eb..38861ca04899 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -285,6 +285,7 @@ restart: retry: if (batch_count) __flush_batch(journal, &batch_count); + cond_resched(); spin_lock(&journal->j_list_lock); goto restart; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 3c293a5a21b1..457f91c412d4 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -142,9 +142,9 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_iattrs *attrs; - attrs = kernfs_iattrs_noalloc(kn); + attrs = kernfs_iattrs(kn); if (!attrs) - return -ENODATA; + return -ENOMEM; return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); } diff --git a/fs/namespace.c b/fs/namespace.c index ddfd4457d338..ae6d1312b184 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1197,10 +1197,7 @@ static void commit_tree(struct mount *mnt) if (!mnt_ns_attached(mnt)) { for (struct mount *m = mnt; m; m = next_mnt(m, mnt)) - if (unlikely(mnt_ns_attached(m))) - m = skip_mnt_tree(m); - else - mnt_add_to_ns(n, m); + mnt_add_to_ns(n, m); n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; } @@ -2704,6 +2701,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, lock_mnt_tree(child); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); + commit_tree(child); if (q) { struct mountpoint *mp = root.mp; struct mount *r = child; @@ -2713,7 +2711,6 @@ static int attach_recursive_mnt(struct mount *source_mnt, mp = shorter; mnt_change_mountpoint(r, mp, q); } - commit_tree(child); } unpin_mountpoint(&root); unlock_mount_hash(); @@ -2862,6 +2859,19 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) return attach_recursive_mnt(mnt, p, mp); } +static int may_change_propagation(const struct mount *m) +{ + struct mnt_namespace *ns = m->mnt_ns; + + // it must be mounted in some namespace + if (IS_ERR_OR_NULL(ns)) // is_mounted() + return -EINVAL; + // and the caller must be admin in userns of that namespace + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + return 0; +} + /* * Sanity check the flags to change_mnt_propagation. */ @@ -2898,10 +2908,10 @@ static int do_change_type(struct path *path, int ms_flags) return -EINVAL; namespace_lock(); - if (!check_mnt(mnt)) { - err = -EINVAL; + err = may_change_propagation(mnt); + if (err) goto out_unlock; - } + if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) @@ -3347,18 +3357,11 @@ static int do_set_group(struct path *from_path, struct path *to_path) namespace_lock(); - err = -EINVAL; - /* To and From must be mounted */ - if (!is_mounted(&from->mnt)) - goto out; - if (!is_mounted(&to->mnt)) - goto out; - - err = -EPERM; - /* We should be allowed to modify mount namespaces of both mounts */ - if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) + err = may_change_propagation(from); + if (err) goto out; - if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) + err = may_change_propagation(to); + if (err) goto out; err = -EINVAL; @@ -4551,20 +4554,10 @@ SYSCALL_DEFINE5(move_mount, if (flags & MOVE_MOUNT_SET_GROUP) mflags |= MNT_TREE_PROPAGATION; if (flags & MOVE_MOUNT_BENEATH) mflags |= MNT_TREE_BENEATH; - lflags = 0; - if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; - if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; uflags = 0; - if (flags & MOVE_MOUNT_F_EMPTY_PATH) uflags = AT_EMPTY_PATH; - from_name = getname_maybe_null(from_pathname, uflags); - if (IS_ERR(from_name)) - return PTR_ERR(from_name); + if (flags & MOVE_MOUNT_T_EMPTY_PATH) + uflags = AT_EMPTY_PATH; - lflags = 0; - if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; - if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; - uflags = 0; - if (flags & MOVE_MOUNT_T_EMPTY_PATH) uflags = AT_EMPTY_PATH; to_name = getname_maybe_null(to_pathname, uflags); if (IS_ERR(to_name)) return PTR_ERR(to_name); @@ -4577,11 +4570,24 @@ SYSCALL_DEFINE5(move_mount, to_path = fd_file(f_to)->f_path; path_get(&to_path); } else { + lflags = 0; + if (flags & MOVE_MOUNT_T_SYMLINKS) + lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_T_AUTOMOUNTS) + lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL); if (ret) return ret; } + uflags = 0; + if (flags & MOVE_MOUNT_F_EMPTY_PATH) + uflags = AT_EMPTY_PATH; + + from_name = getname_maybe_null(from_pathname, uflags); + if (IS_ERR(from_name)) + return PTR_ERR(from_name); + if (!from_name && from_dfd >= 0) { CLASS(fd_raw, f_from)(from_dfd); if (fd_empty(f_from)) @@ -4590,6 +4596,11 @@ SYSCALL_DEFINE5(move_mount, return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags); } + lflags = 0; + if (flags & MOVE_MOUNT_F_SYMLINKS) + lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_F_AUTOMOUNTS) + lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL); if (ret) return ret; @@ -5176,7 +5187,8 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, int ret; struct mount_kattr kattr = {}; - kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; + if (flags & OPEN_TREE_CLONE) + kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3e804da1e1eb..a95e7aadafd0 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -281,8 +281,10 @@ reassess: } else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) { notes |= MADE_PROGRESS; } else { - if (!stream->failed) + if (!stream->failed) { stream->transferred += transferred; + stream->transferred_valid = true; + } if (front->transferred < front->len) set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags); notes |= MADE_PROGRESS; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 0f3a36852a4d..cbf3d9194c7b 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -254,6 +254,7 @@ reassess_streams: if (front->start + front->transferred > stream->collected_to) { stream->collected_to = front->start + front->transferred; stream->transferred = stream->collected_to - wreq->start; + stream->transferred_valid = true; notes |= MADE_PROGRESS; } if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { @@ -356,6 +357,7 @@ bool netfs_write_collection(struct netfs_io_request *wreq) { struct netfs_inode *ictx = netfs_inode(wreq->inode); size_t transferred; + bool transferred_valid = false; int s; _enter("R=%x", wreq->debug_id); @@ -376,12 +378,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq) continue; if (!list_empty(&stream->subrequests)) return false; - if (stream->transferred < transferred) + if (stream->transferred_valid && + stream->transferred < transferred) { transferred = stream->transferred; + transferred_valid = true; + } } /* Okay, declare that all I/O is complete. */ - wreq->transferred = transferred; + if (transferred_valid) + wreq->transferred = transferred; trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); if (wreq->io_streams[1].active && diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 50bee2c4130d..0584cba1a043 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -118,12 +118,12 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, wreq->io_streams[0].prepare_write = ictx->ops->prepare_write; wreq->io_streams[0].issue_write = ictx->ops->issue_write; wreq->io_streams[0].collected_to = start; - wreq->io_streams[0].transferred = LONG_MAX; + wreq->io_streams[0].transferred = 0; wreq->io_streams[1].stream_nr = 1; wreq->io_streams[1].source = NETFS_WRITE_TO_CACHE; wreq->io_streams[1].collected_to = start; - wreq->io_streams[1].transferred = LONG_MAX; + wreq->io_streams[1].transferred = 0; if (fscache_resources_valid(&wreq->cache_resources)) { wreq->io_streams[1].avail = true; wreq->io_streams[1].active = true; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 11968dcb7243..6e69ce43a13f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -253,13 +253,14 @@ nfs_page_group_unlock(struct nfs_page *req) nfs_page_clear_headlock(req); } -/* - * nfs_page_group_sync_on_bit_locked +/** + * nfs_page_group_sync_on_bit_locked - Test if all requests have @bit set + * @req: request in page group + * @bit: PG_* bit that is used to sync page group * * must be called with page group lock held */ -static bool -nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +bool nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) { struct nfs_page *head = req->wb_head; struct nfs_page *tmp; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index fa5c41d0989a..8b7c04737967 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -153,20 +153,10 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode) } } -static int -nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) +static void nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) { - int ret; - - if (!test_bit(PG_REMOVE, &req->wb_flags)) - return 0; - ret = nfs_page_group_lock(req); - if (ret) - return ret; if (test_and_clear_bit(PG_REMOVE, &req->wb_flags)) nfs_page_set_inode_ref(req, inode); - nfs_page_group_unlock(req); - return 0; } /** @@ -585,19 +575,18 @@ retry: } } + ret = nfs_page_group_lock(head); + if (ret < 0) + goto out_unlock; + /* Ensure that nobody removed the request before we locked it */ if (head != folio->private) { + nfs_page_group_unlock(head); nfs_unlock_and_release_request(head); goto retry; } - ret = nfs_cancel_remove_inode(head, inode); - if (ret < 0) - goto out_unlock; - - ret = nfs_page_group_lock(head); - if (ret < 0) - goto out_unlock; + nfs_cancel_remove_inode(head, inode); /* lock each request in the page group */ for (subreq = head->wb_this_page; @@ -786,7 +775,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) { struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); - if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + nfs_page_group_lock(req); + if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio->mapping; @@ -798,6 +788,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } spin_unlock(&mapping->i_private_lock); } + nfs_page_group_unlock(req); if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { atomic_long_dec(&nfsi->nrequests); diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 4f6468eb2adf..cb237f1b902a 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, if (nfsd_file_get(new) == NULL) goto again; /* - * Drop the ref we were going to install and the - * one we were going to return. + * Drop the ref we were going to install (both file and + * net) and the one we were going to return (only file). */ nfsd_file_put(localio); + nfsd_net_put(net); nfsd_file_put(localio); localio = new; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 98ab55ba3ced..edf050766e57 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -470,7 +470,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (!iap->ia_valid) return 0; - iap->ia_valid |= ATTR_CTIME; + /* + * If ATTR_DELEG is set, then this is an update from a client that + * holds a delegation. If this is an update for only the atime, the + * ctime should not be changed. If the update contains the mtime + * too, then ATTR_CTIME should already be set. + */ + if (!(iap->ia_valid & ATTR_DELEG)) + iap->ia_valid |= ATTR_CTIME; + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 70b8687dc45e..dbd63a74df4b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -225,7 +225,7 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr) { struct dentry *ret; - inode_lock(workdir->d_inode); + inode_lock_nested(workdir->d_inode, I_MUTEX_PARENT); ret = ovl_create_real(ofs, workdir, ovl_lookup_temp(ofs, workdir), attr); inode_unlock(workdir->d_inode); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index a33115e7384c..41033bac96cb 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -1552,7 +1552,8 @@ void ovl_copyattr(struct inode *inode) int ovl_parent_lock(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); - if (!child || child->d_parent == parent) + if (!child || + (!d_unhashed(child) && child->d_parent == parent)) return 0; inode_unlock(parent->d_inode); diff --git a/fs/pidfs.c b/fs/pidfs.c index edc35522d75c..108e7527f837 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -296,12 +296,12 @@ static __u32 pidfs_coredump_mask(unsigned long mm_flags) static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) { struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg; + struct task_struct *task __free(put_task) = NULL; struct pid *pid = pidfd_pid(file); size_t usize = _IOC_SIZE(cmd); struct pidfd_info kinfo = {}; struct pidfs_exit_info *exit_info; struct user_namespace *user_ns; - struct task_struct *task; struct pidfs_attr *attr; const struct cred *c; __u64 mask; diff --git a/fs/pnode.c b/fs/pnode.c index 81f7599bdac4..6f7d02f3fa98 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -111,7 +111,8 @@ void change_mnt_propagation(struct mount *mnt, int type) return; } if (IS_MNT_SHARED(mnt)) { - m = propagation_source(mnt); + if (type == MS_SLAVE || !hlist_empty(&mnt->mnt_slave_list)) + m = propagation_source(mnt); if (list_empty(&mnt->mnt_share)) { mnt_release_group_id(mnt); } else { @@ -637,10 +638,11 @@ void propagate_umount(struct list_head *set) } // now to_umount consists of all acceptable candidates - // deal with reparenting of remaining overmounts on those + // deal with reparenting of surviving overmounts on those list_for_each_entry(m, &to_umount, mnt_list) { - if (m->overmount) - reparent(m->overmount); + struct mount *over = m->overmount; + if (over && !will_be_unmounted(over)) + reparent(over); } // and fold them into the set diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3d6d8a9f13fc..29cca0e6d0ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -340,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file, priv->inode = inode; priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR_OR_NULL(priv->mm)) { - int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH; + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); seq_release_private(inode, file); return err; @@ -1148,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - pte_t ptent = huge_ptep_get(walk->mm, addr, pte); struct folio *folio = NULL; bool present = false; + spinlock_t *ptl; + pte_t ptent; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + ptent = huge_ptep_get(walk->mm, addr, pte); if (pte_present(ptent)) { folio = page_folio(pte_page(ptent)); present = true; @@ -1170,6 +1173,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); } + spin_unlock(ptl); return 0; } #else @@ -2017,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, struct pagemapread *pm = walk->private; struct vm_area_struct *vma = walk->vma; u64 flags = 0, frame = 0; + spinlock_t *ptl; int err = 0; pte_t pte; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep); pte = huge_ptep_get(walk->mm, addr, ptep); if (pte_present(pte)) { struct folio *folio = page_folio(pte_page(pte)); @@ -2050,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, err = add_to_pagemap(&pme, pm); if (err) - return err; + break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; } + spin_unlock(ptl); cond_resched(); return err; @@ -3128,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte); + pte_t huge_pte; struct numa_maps *md; struct page *page; + spinlock_t *ptl; + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + huge_pte = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(huge_pte)) - return 0; + goto out; page = pte_page(huge_pte); md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); +out: + spin_unlock(ptl); return 0; } diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index bc1c1e9b288a..43b86fa4d695 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -124,55 +124,44 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp = description; /* start with version and hostname portion of UNC string */ spnego_key = ERR_PTR(-EINVAL); - sprintf(dp, "ver=0x%x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, - hostname); - dp = description + strlen(description); + dp += sprintf(dp, "ver=0x%x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, + hostname); /* add the server address */ if (server->dstaddr.ss_family == AF_INET) - sprintf(dp, "ip4=%pI4", &sa->sin_addr); + dp += sprintf(dp, "ip4=%pI4", &sa->sin_addr); else if (server->dstaddr.ss_family == AF_INET6) - sprintf(dp, "ip6=%pI6", &sa6->sin6_addr); + dp += sprintf(dp, "ip6=%pI6", &sa6->sin6_addr); else goto out; - dp = description + strlen(description); - /* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */ if (server->sec_kerberos) - sprintf(dp, ";sec=krb5"); + dp += sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) - sprintf(dp, ";sec=mskrb5"); + dp += sprintf(dp, ";sec=mskrb5"); else if (server->sec_iakerb) - sprintf(dp, ";sec=iakerb"); + dp += sprintf(dp, ";sec=iakerb"); else { cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); - sprintf(dp, ";sec=krb5"); + dp += sprintf(dp, ";sec=krb5"); } - dp = description + strlen(description); - sprintf(dp, ";uid=0x%x", - from_kuid_munged(&init_user_ns, sesInfo->linux_uid)); + dp += sprintf(dp, ";uid=0x%x", + from_kuid_munged(&init_user_ns, sesInfo->linux_uid)); - dp = description + strlen(description); - sprintf(dp, ";creduid=0x%x", + dp += sprintf(dp, ";creduid=0x%x", from_kuid_munged(&init_user_ns, sesInfo->cred_uid)); - if (sesInfo->user_name) { - dp = description + strlen(description); - sprintf(dp, ";user=%s", sesInfo->user_name); - } + if (sesInfo->user_name) + dp += sprintf(dp, ";user=%s", sesInfo->user_name); - dp = description + strlen(description); - sprintf(dp, ";pid=0x%x", current->pid); + dp += sprintf(dp, ";pid=0x%x", current->pid); - if (sesInfo->upcall_target == UPTARGET_MOUNT) { - dp = description + strlen(description); - sprintf(dp, ";upcall_target=mount"); - } else { - dp = description + strlen(description); - sprintf(dp, ";upcall_target=app"); - } + if (sesInfo->upcall_target == UPTARGET_MOUNT) + dp += sprintf(dp, ";upcall_target=mount"); + else + dp += sprintf(dp, ";upcall_target=app"); cifs_dbg(FYI, "key description = %s\n", description); saved_cred = override_creds(spnego_cred); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 487f39cff77e..3ce7c614ccc0 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 55 -#define CIFS_VERSION "2.55" +#define SMB3_PRODUCT_BUILD 56 +#define CIFS_VERSION "2.56" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index e6830ab3a546..1e64a4fb6af0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1732,6 +1732,7 @@ struct mid_q_entry { int mid_rc; /* rc for MID_RC */ __le16 command; /* smb command code */ unsigned int optype; /* operation type */ + spinlock_t mid_lock; bool wait_cancelled:1; /* Cancelled while waiting for response */ bool deleted_from_q:1; /* Whether Mid has been dequeued frem pending_mid_q */ bool large_buf:1; /* if valid response, is pointer to large buf */ @@ -2036,6 +2037,9 @@ require use of the stronger protocol */ * cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo * ->invalidHandle initiate_cifs_search * ->oplock_break_cancelled + * mid_q_entry->mid_lock mid_q_entry->callback alloc_mid + * smb2_mid_entry_alloc + * (Any fields of mid_q_entry that will need protection) ****************************************************************************/ #ifdef DECLARE_GLOBALS_HERE @@ -2375,6 +2379,23 @@ static inline bool cifs_netbios_name(const char *name, size_t namelen) return ret; } +/* + * Execute mid callback atomically - ensures callback runs exactly once + * and prevents sleeping in atomic context. + */ +static inline void mid_execute_callback(struct mid_q_entry *mid) +{ + void (*callback)(struct mid_q_entry *mid); + + spin_lock(&mid->mid_lock); + callback = mid->callback; + mid->callback = NULL; /* Mark as executed, */ + spin_unlock(&mid->mid_lock); + + if (callback) + callback(mid); +} + #define CIFS_REPARSE_SUPPORT(tcon) \ ((tcon)->posix_extensions || \ (le32_to_cpu((tcon)->fsAttrInfo.Attributes) & \ diff --git a/fs/smb/client/cifstransport.c b/fs/smb/client/cifstransport.c index 352dafb888dd..e98b95eff8c9 100644 --- a/fs/smb/client/cifstransport.c +++ b/fs/smb/client/cifstransport.c @@ -46,6 +46,7 @@ alloc_mid(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); kref_init(&temp->refcount); + spin_lock_init(&temp->mid_lock); temp->mid = get_mid(smb_buffer); temp->pid = current->pid; temp->command = cpu_to_le16(smb_buffer->Command); @@ -345,16 +346,15 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(server, midQ); if (rc != 0) { send_cancel(server, &rqst, midQ); - spin_lock(&server->mid_queue_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED || - midQ->mid_state == MID_RESPONSE_RECEIVED) { + spin_lock(&midQ->mid_lock); + if (midQ->callback) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); add_credits(server, &credits, 0); return rc; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); } rc = cifs_sync_mid_result(midQ, server); @@ -527,15 +527,14 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, rc = wait_for_response(server, midQ); if (rc) { send_cancel(server, &rqst, midQ); - spin_lock(&server->mid_queue_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED || - midQ->mid_state == MID_RESPONSE_RECEIVED) { + spin_lock(&midQ->mid_lock); + if (midQ->callback) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); return rc; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); } /* We got the response - restart system call. */ diff --git a/fs/smb/client/compress.c b/fs/smb/client/compress.c index 766b4de13da7..db709f5cd2e1 100644 --- a/fs/smb/client/compress.c +++ b/fs/smb/client/compress.c @@ -155,58 +155,29 @@ static int cmp_bkt(const void *_a, const void *_b) } /* - * TODO: - * Support other iter types, if required. - * Only ITER_XARRAY is supported for now. + * Collect some 2K samples with 2K gaps between. */ -static int collect_sample(const struct iov_iter *iter, ssize_t max, u8 *sample) +static int collect_sample(const struct iov_iter *source, ssize_t max, u8 *sample) { - struct folio *folios[16], *folio; - unsigned int nr, i, j, npages; - loff_t start = iter->xarray_start + iter->iov_offset; - pgoff_t last, index = start / PAGE_SIZE; - size_t len, off, foff; - void *p; - int s = 0; - - last = (start + max - 1) / PAGE_SIZE; - do { - nr = xa_extract(iter->xarray, (void **)folios, index, last, ARRAY_SIZE(folios), - XA_PRESENT); - if (nr == 0) - return -EIO; - - for (i = 0; i < nr; i++) { - folio = folios[i]; - npages = folio_nr_pages(folio); - foff = start - folio_pos(folio); - off = foff % PAGE_SIZE; - - for (j = foff / PAGE_SIZE; j < npages; j++) { - size_t len2; - - len = min_t(size_t, max, PAGE_SIZE - off); - len2 = min_t(size_t, len, SZ_2K); - - p = kmap_local_page(folio_page(folio, j)); - memcpy(&sample[s], p, len2); - kunmap_local(p); - - s += len2; - - if (len2 < SZ_2K || s >= max - SZ_2K) - return s; - - max -= len; - if (max <= 0) - return s; - - start += len; - off = 0; - index++; - } - } - } while (nr == ARRAY_SIZE(folios)); + struct iov_iter iter = *source; + size_t s = 0; + + while (iov_iter_count(&iter) >= SZ_2K) { + size_t part = umin(umin(iov_iter_count(&iter), SZ_2K), max); + size_t n; + + n = copy_from_iter(sample + s, part, &iter); + if (n != part) + return -EFAULT; + + s += n; + max -= n; + + if (iov_iter_count(&iter) < PAGE_SIZE - SZ_2K) + break; + + iov_iter_advance(&iter, SZ_2K); + } return s; } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 587845a2452d..dd12f3eb61dc 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -335,7 +335,7 @@ cifs_abort_connection(struct TCP_Server_Info *server) cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_entry_safe(mid, nmid, &retry_list, qhead) { list_del_init(&mid->qhead); - mid->callback(mid); + mid_execute_callback(mid); release_mid(mid); } @@ -919,7 +919,7 @@ is_smb_response(struct TCP_Server_Info *server, unsigned char type) list_del_init(&mid->qhead); mid->mid_rc = mid_rc; mid->mid_state = MID_RC; - mid->callback(mid); + mid_execute_callback(mid); release_mid(mid); } @@ -1117,7 +1117,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) mid_entry = list_entry(tmp, struct mid_q_entry, qhead); cifs_dbg(FYI, "Callback mid %llu\n", mid_entry->mid); list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); + mid_execute_callback(mid_entry); release_mid(mid_entry); } /* 1/8th of sec is more than enough time for them to exit */ @@ -1394,7 +1394,7 @@ next_pdu: } if (!mids[i]->multiRsp || mids[i]->multiEnd) - mids[i]->callback(mids[i]); + mid_execute_callback(mids[i]); release_mid(mids[i]); } else if (server->ops->is_oplock_break && @@ -4205,7 +4205,6 @@ retry: return 0; } - server->lstrp = jiffies; server->tcpStatus = CifsInNegotiate; server->neg_start = jiffies; spin_unlock(&server->srv_lock); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 75be4b46bc6f..fe453a4b3dc8 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1943,15 +1943,24 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct tcon_link *tlink; struct cifs_tcon *tcon; + __u32 dosattr = 0, origattr = 0; struct TCP_Server_Info *server; struct iattr *attrs = NULL; - __u32 dosattr = 0, origattr = 0; + bool rehash = false; cifs_dbg(FYI, "cifs_unlink, dir=0x%p, dentry=0x%p\n", dir, dentry); if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* Unhash dentry in advance to prevent any concurrent opens */ + spin_lock(&dentry->d_lock); + if (!d_unhashed(dentry)) { + __d_drop(dentry); + rehash = true; + } + spin_unlock(&dentry->d_lock); + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -2003,7 +2012,8 @@ psx_del_no_retry: cifs_drop_nlink(inode); } } else if (rc == -ENOENT) { - d_drop(dentry); + if (simple_positive(dentry)) + d_delete(dentry); } else if (rc == -EBUSY) { if (server->ops->rename_pending_delete) { rc = server->ops->rename_pending_delete(full_path, @@ -2056,6 +2066,8 @@ unlink_out: kfree(attrs); free_xid(xid); cifs_put_tlink(tlink); + if (rehash) + d_rehash(dentry); return rc; } @@ -2462,6 +2474,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *tcon; + bool rehash = false; unsigned int xid; int rc, tmprc; int retry_count = 0; @@ -2477,6 +2490,17 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* + * Prevent any concurrent opens on the target by unhashing the dentry. + * VFS already unhashes the target when renaming directories. + */ + if (d_is_positive(target_dentry) && !d_is_dir(target_dentry)) { + if (!d_unhashed(target_dentry)) { + d_drop(target_dentry); + rehash = true; + } + } + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -2518,6 +2542,8 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } } + if (!rc) + rehash = false; /* * No-replace is the natural behavior for CIFS, so skip unlink hacks. */ @@ -2576,12 +2602,16 @@ unlink_target: goto cifs_rename_exit; rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); + if (!rc) + rehash = false; } /* force revalidate to go get info when needed */ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; cifs_rename_exit: + if (rehash) + d_rehash(target_dentry); kfree(info_buf_source); free_dentry_path(page2); free_dentry_path(page1); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ad8947434b71..94b1d7a395d5 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -772,6 +772,13 @@ next_iface: bytes_left -= sizeof(*p); break; } + /* Validate that Next doesn't point beyond the buffer */ + if (next > bytes_left) { + cifs_dbg(VFS, "%s: invalid Next pointer %zu > %zd\n", + __func__, next, bytes_left); + rc = -EINVAL; + goto out; + } p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next); bytes_left -= next; } @@ -783,7 +790,9 @@ next_iface: } /* Azure rounds the buffer size up 8, to a 16 byte boundary */ - if ((bytes_left > 8) || p->Next) + if ((bytes_left > 8) || + (bytes_left >= offsetof(struct network_interface_info_ioctl_rsp, Next) + + sizeof(p->Next) && p->Next)) cifs_dbg(VFS, "%s: incomplete interface info\n", __func__); ses->iface_last_update = jiffies; @@ -4487,7 +4496,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, for (int i = 1; i < num_rqst; i++) { struct smb_rqst *old = &old_rq[i - 1]; struct smb_rqst *new = &new_rq[i]; - struct folio_queue *buffer; + struct folio_queue *buffer = NULL; size_t size = iov_iter_count(&old->rq_iter); orig_len += smb_rqst_len(server, old); @@ -4805,7 +4814,7 @@ static void smb2_decrypt_offload(struct work_struct *work) dw->server->ops->is_network_name_deleted(dw->buf, dw->server); - mid->callback(mid); + mid_execute_callback(mid); } else { spin_lock(&dw->server->srv_lock); if (dw->server->tcpStatus == CifsNeedReconnect) { @@ -4813,7 +4822,7 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->mid_state = MID_RETRY_NEEDED; spin_unlock(&dw->server->mid_queue_lock); spin_unlock(&dw->server->srv_lock); - mid->callback(mid); + mid_execute_callback(mid); } else { spin_lock(&dw->server->mid_queue_lock); mid->mid_state = MID_REQUEST_SUBMITTED; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index ff9ef7fcd010..bc0e92eb2b64 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -771,6 +771,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *shdr, temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); kref_init(&temp->refcount); + spin_lock_init(&temp->mid_lock); temp->mid = le64_to_cpu(shdr->MessageId); temp->credits = credits > 0 ? credits : 1; temp->pid = current->pid; diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index c628e91c328b..02d6db431fd4 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1337,10 +1337,6 @@ void smbd_destroy(struct TCP_Server_Info *server) log_rdma_event(INFO, "cancelling idle timer\n"); cancel_delayed_work_sync(&info->idle_timer_work); - log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); - wait_event(info->wait_send_pending, - atomic_read(&info->send_pending) == 0); - /* It's not possible for upper layer to get to reassembly */ log_rdma_event(INFO, "drain the reassembly queue\n"); do { @@ -1986,7 +1982,11 @@ int smbd_send(struct TCP_Server_Info *server, */ wait_event(info->wait_send_pending, - atomic_read(&info->send_pending) == 0); + atomic_read(&info->send_pending) == 0 || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + + if (sc->status != SMBDIRECT_SOCKET_CONNECTED && rc == 0) + rc = -EAGAIN; return rc; } diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 32d528b4dd83..a61ba7f3fb86 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -1005,15 +1005,14 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, cifs_server_dbg(FYI, "Cancelling wait for mid %llu cmd: %d\n", midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(server, &rqst[i], midQ[i]); - spin_lock(&server->mid_queue_lock); + spin_lock(&midQ[i]->mid_lock); midQ[i]->wait_cancelled = true; - if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED || - midQ[i]->mid_state == MID_RESPONSE_RECEIVED) { + if (midQ[i]->callback) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ[i]->mid_lock); } } diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 3f04a2977ba8..67c4f73398df 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -504,7 +504,8 @@ void ksmbd_conn_transport_destroy(void) { mutex_lock(&init_lock); ksmbd_tcp_destroy(); - ksmbd_rdma_destroy(); + ksmbd_rdma_stop_listening(); stop_sessions(); + ksmbd_rdma_destroy(); mutex_unlock(&init_lock); } diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 31dd1caac1e8..2aa8084bb593 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -46,7 +46,12 @@ struct ksmbd_conn { struct mutex srv_mutex; int status; unsigned int cli_cap; - __be32 inet_addr; + union { + __be32 inet_addr; +#if IS_ENABLED(CONFIG_IPV6) + u8 inet6_addr[16]; +#endif + }; char *request_buf; struct ksmbd_transport *transport; struct nls_table *local_nls; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index d7a8a580d013..a04d5702820d 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1102,8 +1102,10 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, if (!atomic_inc_not_zero(&opinfo->refcount)) continue; - if (ksmbd_conn_releasing(opinfo->conn)) + if (ksmbd_conn_releasing(opinfo->conn)) { + opinfo_put(opinfo); continue; + } oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); @@ -1139,8 +1141,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) if (!atomic_inc_not_zero(&opinfo->refcount)) continue; - if (ksmbd_conn_releasing(opinfo->conn)) + if (ksmbd_conn_releasing(opinfo->conn)) { + opinfo_put(opinfo); continue; + } + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); } @@ -1343,8 +1348,10 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, if (!atomic_inc_not_zero(&brk_op->refcount)) continue; - if (ksmbd_conn_releasing(brk_op->conn)) + if (ksmbd_conn_releasing(brk_op->conn)) { + opinfo_put(brk_op); continue; + } if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 8d366db5f605..5466aa8c39b1 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2194,7 +2194,7 @@ int ksmbd_rdma_init(void) return 0; } -void ksmbd_rdma_destroy(void) +void ksmbd_rdma_stop_listening(void) { if (!smb_direct_listener.cm_id) return; @@ -2203,7 +2203,10 @@ void ksmbd_rdma_destroy(void) rdma_destroy_id(smb_direct_listener.cm_id); smb_direct_listener.cm_id = NULL; +} +void ksmbd_rdma_destroy(void) +{ if (smb_direct_wq) { destroy_workqueue(smb_direct_wq); smb_direct_wq = NULL; diff --git a/fs/smb/server/transport_rdma.h b/fs/smb/server/transport_rdma.h index 77aee4e5c9dc..a2291b77488a 100644 --- a/fs/smb/server/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h @@ -54,13 +54,15 @@ struct smb_direct_data_transfer { #ifdef CONFIG_SMB_SERVER_SMBDIRECT int ksmbd_rdma_init(void); +void ksmbd_rdma_stop_listening(void); void ksmbd_rdma_destroy(void); bool ksmbd_rdma_capable_netdev(struct net_device *netdev); void init_smbd_max_io_size(unsigned int sz); unsigned int get_smbd_max_read_write_size(void); #else static inline int ksmbd_rdma_init(void) { return 0; } -static inline int ksmbd_rdma_destroy(void) { return 0; } +static inline void ksmbd_rdma_stop_listening(void) { } +static inline void ksmbd_rdma_destroy(void) { } static inline bool ksmbd_rdma_capable_netdev(struct net_device *netdev) { return false; } static inline void init_smbd_max_io_size(unsigned int sz) { } static inline unsigned int get_smbd_max_read_write_size(void) { return 0; } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index b1df02e321b0..4337df97987d 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -85,7 +85,14 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk) return NULL; } +#if IS_ENABLED(CONFIG_IPV6) + if (client_sk->sk->sk_family == AF_INET6) + memcpy(&conn->inet6_addr, &client_sk->sk->sk_v6_daddr, 16); + else + conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr; +#else conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr; +#endif conn->transport = KSMBD_TRANS(t); KSMBD_TRANS(t)->conn = conn; KSMBD_TRANS(t)->ops = &ksmbd_tcp_transport_ops; @@ -229,7 +236,6 @@ static int ksmbd_kthread_fn(void *p) { struct socket *client_sk = NULL; struct interface *iface = (struct interface *)p; - struct inet_sock *csk_inet; struct ksmbd_conn *conn; int ret; @@ -252,13 +258,27 @@ static int ksmbd_kthread_fn(void *p) /* * Limits repeated connections from clients with the same IP. */ - csk_inet = inet_sk(client_sk->sk); down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) - if (csk_inet->inet_daddr == conn->inet_addr) { +#if IS_ENABLED(CONFIG_IPV6) + if (client_sk->sk->sk_family == AF_INET6) { + if (memcmp(&client_sk->sk->sk_v6_daddr, + &conn->inet6_addr, 16) == 0) { + ret = -EAGAIN; + break; + } + } else if (inet_sk(client_sk->sk)->inet_daddr == + conn->inet_addr) { + ret = -EAGAIN; + break; + } +#else + if (inet_sk(client_sk->sk)->inet_daddr == + conn->inet_addr) { ret = -EAGAIN; break; } +#endif up_read(&conn_list_lock); if (ret == -EAGAIN) continue; diff --git a/fs/splice.c b/fs/splice.c index 4d6df083e0c0..f5094b6d00a0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -739,6 +739,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, sd.pos = kiocb.ki_pos; if (ret <= 0) break; + WARN_ONCE(ret > sd.total_len - left, + "Splice Exceeded! ret=%zd tot=%zu left=%zu\n", + ret, sd.total_len, left); sd.num_spliced += ret; sd.total_len -= ret; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 992ea0e37257..4465cf05603a 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -187,10 +187,15 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) unsigned short flags; unsigned int fragments; u64 lookup_table_start, xattr_id_table_start, next_table; - int err; + int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); TRACE("Entered squashfs_fill_superblock\n"); + if (!devblksize) { + errorf(fc, "squashfs: unable to set blocksize\n"); + return -EINVAL; + } + sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL); if (sb->s_fs_info == NULL) { ERROR("Failed to allocate squashfs_sb_info\n"); @@ -201,12 +206,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) msblk->panic_on_errors = (opts->errors == Opt_errors_panic); - msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); - if (!msblk->devblksize) { - errorf(fc, "squashfs: unable to set blocksize\n"); - return -EINVAL; - } - + msblk->devblksize = devblksize; msblk->devblksize_log2 = ffz(~msblk->devblksize); mutex_init(&msblk->meta_index_mutex); diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 1e6e9c10cea2..a8187281eb96 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -479,7 +479,7 @@ DECLARE_EVENT_CLASS(xchk_dqiter_class, __field(xfs_exntst_t, state) ), TP_fast_assign( - __entry->dev = cursor->sc->ip->i_mount->m_super->s_dev; + __entry->dev = cursor->sc->mp->m_super->s_dev; __entry->dqtype = cursor->dqtype; __entry->ino = cursor->quota_ip->i_ino; __entry->cur_id = cursor->id; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 55a304cb3aef..f96fbf5c54c9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1101,9 +1101,6 @@ xfs_file_write_iter( if (xfs_is_shutdown(ip->i_mount)) return -EIO; - if (IS_DAX(inode)) - return xfs_file_dax_write(iocb, from); - if (iocb->ki_flags & IOCB_ATOMIC) { if (ocount < xfs_get_atomic_write_min(ip)) return -EINVAL; @@ -1116,6 +1113,9 @@ xfs_file_write_iter( return ret; } + if (IS_DAX(inode)) + return xfs_file_dax_write(iocb, from); + if (iocb->ki_flags & IOCB_DIRECT) { /* * Allow a directio write to fall back to a buffered diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 07fbdcc4cbf5..bd6d33557194 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -358,9 +358,20 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip) static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip) { + if (IS_DAX(VFS_IC(ip))) + return false; + return xfs_inode_buftarg(ip)->bt_awu_max > 0; } +static inline bool xfs_inode_can_sw_atomic_write(const struct xfs_inode *ip) +{ + if (IS_DAX(VFS_IC(ip))) + return false; + + return xfs_can_sw_atomic_write(ip->i_mount); +} + /* * In-core inode flags. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index fe1f74a3b6a3..e1051a530a50 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -219,7 +219,7 @@ xfs_bulk_ireq_setup( else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno) return -EINVAL; - breq->flags |= XFS_IBULK_SAME_AG; + breq->iwalk_flags |= XFS_IWALK_SAME_AG; /* Asking for an inode past the end of the AG? We're done! */ if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 149b5460fbfd..603effabe1ee 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -616,7 +616,8 @@ xfs_get_atomic_write_min( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (xfs_inode_can_hw_atomic_write(ip) || xfs_can_sw_atomic_write(mp)) + if (xfs_inode_can_hw_atomic_write(ip) || + xfs_inode_can_sw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; @@ -633,7 +634,7 @@ xfs_get_atomic_write_max( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (!xfs_can_sw_atomic_write(mp)) { + if (!xfs_inode_can_sw_atomic_write(ip)) { if (xfs_inode_can_hw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index c8c9b8d8309f..2aa37a4d2706 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -307,7 +307,6 @@ xfs_bulkstat( .breq = breq, }; struct xfs_trans *tp; - unsigned int iwalk_flags = 0; int error; if (breq->idmap != &nop_mnt_idmap) { @@ -328,10 +327,7 @@ xfs_bulkstat( * locking abilities to detect cycles in the inobt without deadlocking. */ tp = xfs_trans_alloc_empty(breq->mp); - if (breq->flags & XFS_IBULK_SAME_AG) - iwalk_flags |= XFS_IWALK_SAME_AG; - - error = xfs_iwalk(breq->mp, tp, breq->startino, iwalk_flags, + error = xfs_iwalk(breq->mp, tp, breq->startino, breq->iwalk_flags, xfs_bulkstat_iwalk, breq->icount, &bc); xfs_trans_cancel(tp); kfree(bc.buf); @@ -457,7 +453,7 @@ xfs_inumbers( * locking abilities to detect cycles in the inobt without deadlocking. */ tp = xfs_trans_alloc_empty(breq->mp); - error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->flags, + error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->iwalk_flags, xfs_inumbers_walk, breq->icount, &ic); xfs_trans_cancel(tp); diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index f10e8f8f2335..2d0612f14d6e 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -13,17 +13,15 @@ struct xfs_ibulk { xfs_ino_t startino; /* start with this inode */ unsigned int icount; /* number of elements in ubuffer */ unsigned int ocount; /* number of records returned */ - unsigned int flags; /* see XFS_IBULK_FLAG_* */ + unsigned int flags; /* XFS_IBULK_FLAG_* */ + unsigned int iwalk_flags; /* XFS_IWALK_FLAG_* */ }; -/* Only iterate within the same AG as startino */ -#define XFS_IBULK_SAME_AG (1U << 0) - /* Fill out the bs_extents64 field if set. */ -#define XFS_IBULK_NREXT64 (1U << 1) +#define XFS_IBULK_NREXT64 (1U << 0) /* Signal that we can return metadata directories. */ -#define XFS_IBULK_METADIR (1U << 2) +#define XFS_IBULK_METADIR (1U << 1) /* * Advance the user buffer pointer by one record of the given size. If the diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2133fbaf1766..dc32c5e34d81 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -779,6 +779,25 @@ xfs_set_max_atomic_write_opt( return -EINVAL; } + if (xfs_has_reflink(mp)) + goto set_limit; + + if (new_max_fsbs == 1) { + if (mp->m_ddev_targp->bt_awu_max || + (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_awu_max)) { + } else { + xfs_warn(mp, + "cannot support atomic writes of size %lluk with no reflink or HW support", + new_max_bytes >> 10); + return -EINVAL; + } + } else { + xfs_warn(mp, + "cannot support atomic writes of size %lluk with no reflink support", + new_max_bytes >> 10); + return -EINVAL; + } + set_limit: error = xfs_calc_atomic_write_reservation(mp, new_max_fsbs); if (error) { diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index e1794e3e3156..ac344e42846c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -455,6 +455,7 @@ DEFINE_EVENT(xfs_zone_alloc_class, name, \ xfs_extlen_t len), \ TP_ARGS(oz, rgbno, len)) DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks); +DEFINE_ZONE_ALLOC_EVENT(xfs_zone_skip_blocks); DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks); TRACE_EVENT(xfs_zone_gc_select_victim, diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index ece374d622b3..575e7028f423 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -253,8 +253,8 @@ xfs_trans_alloc( * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ retry: - WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); tp = __xfs_trans_alloc(mp, flags); + WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); error = xfs_trans_reserve(tp, resp, blocks, rtextents); if (error == -ENOSPC && want_retry) { xfs_trans_cancel(tp); diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 33f7eee521a8..f8bd6d741755 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -166,10 +166,9 @@ xfs_open_zone_mark_full( static void xfs_zone_record_blocks( struct xfs_trans *tp, - xfs_fsblock_t fsbno, - xfs_filblks_t len, struct xfs_open_zone *oz, - bool used) + xfs_fsblock_t fsbno, + xfs_filblks_t len) { struct xfs_mount *mp = tp->t_mountp; struct xfs_rtgroup *rtg = oz->oz_rtg; @@ -179,18 +178,37 @@ xfs_zone_record_blocks( xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); - if (used) { - rmapip->i_used_blocks += len; - ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); - } else { - xfs_add_frextents(mp, len); - } + rmapip->i_used_blocks += len; + ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); oz->oz_written += len; if (oz->oz_written == rtg_blocks(rtg)) xfs_open_zone_mark_full(oz); xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE); } +/* + * Called for blocks that have been written to disk, but not actually linked to + * an inode, which can happen when garbage collection races with user data + * writes to a file. + */ +static void +xfs_zone_skip_blocks( + struct xfs_open_zone *oz, + xfs_filblks_t len) +{ + struct xfs_rtgroup *rtg = oz->oz_rtg; + + trace_xfs_zone_skip_blocks(oz, 0, len); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + oz->oz_written += len; + if (oz->oz_written == rtg_blocks(rtg)) + xfs_open_zone_mark_full(oz); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + + xfs_add_frextents(rtg_mount(rtg), len); +} + static int xfs_zoned_map_extent( struct xfs_trans *tp, @@ -250,8 +268,7 @@ xfs_zoned_map_extent( } } - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - true); + xfs_zone_record_blocks(tp, oz, new->br_startblock, new->br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new); @@ -259,8 +276,7 @@ xfs_zoned_map_extent( skip: trace_xfs_reflink_cow_remap_skip(ip, new); - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - false); + xfs_zone_skip_blocks(oz, new->br_blockcount); return 0; } diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 8ed80cad77ec..b0e6653ee42e 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -866,13 +866,61 @@ struct drm_bridge_funcs { struct drm_connector *connector, bool enable, int direction); + /** + * @hdmi_cec_init: + * + * Initialize CEC part of the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_init)(struct drm_bridge *bridge, struct drm_connector *connector); + /** + * @hdmi_cec_enable: + * + * Enable or disable the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_enable)(struct drm_bridge *bridge, bool enable); + /** + * @hdmi_cec_log_addr: + * + * Set the logical address of the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_log_addr)(struct drm_bridge *bridge, u8 logical_addr); + /** + * @hdmi_cec_transmit: + * + * Transmit the message using the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_transmit)(struct drm_bridge *bridge, u8 attempts, u32 signal_free_time, struct cec_msg *msg); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95886b404b16..fe1797bbec42 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -656,6 +656,7 @@ enum { QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ + QUEUE_FLAG_QOS_ENABLED, /* qos is enabled */ QUEUE_FLAG_MAX }; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6f04a1d8c720..64ff73c533e5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -288,14 +288,6 @@ static inline void *offset_to_ptr(const int *off) #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -#define __ADDRESSABLE_ASM(sym) \ - .pushsection .discard.addressable,"aw"; \ - .align ARCH_SEL(8,4); \ - ARCH_SEL(.quad, .long) __stringify(sym); \ - .popsection; - -#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) - /* * This returns a constant expression while determining if an argument is * a constant expression, most importantly without evaluating the argument. diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index edfa61d80702..62cd7b35a29c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -168,6 +168,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_TEGRA_TIMER_STARTING, CPUHP_AP_ARMADA_TIMER_STARTING, + CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_REALTEK_TIMER_STARTING, diff --git a/include/linux/export.h b/include/linux/export.h index f35d03b4113b..a686fd0ba406 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -91,6 +91,6 @@ #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "GPL", ns) -#define EXPORT_SYMBOL_GPL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) +#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index cceb70415ed2..d38c6e538e5c 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -341,7 +341,11 @@ struct fw_address_handler { u64 length; fw_address_callback_t address_callback; void *callback_data; + + // Only for core functions. struct list_head link; + struct kref kref; + struct completion done; }; struct fw_address_region { diff --git a/include/linux/iio/frequency/adf4350.h b/include/linux/iio/frequency/adf4350.h index de45cf2ee1e4..ce2086f97e3f 100644 --- a/include/linux/iio/frequency/adf4350.h +++ b/include/linux/iio/frequency/adf4350.h @@ -51,7 +51,7 @@ /* REG3 Bit Definitions */ #define ADF4350_REG3_12BIT_CLKDIV(x) ((x) << 3) -#define ADF4350_REG3_12BIT_CLKDIV_MODE(x) ((x) << 16) +#define ADF4350_REG3_12BIT_CLKDIV_MODE(x) ((x) << 15) #define ADF4350_REG3_12BIT_CSR_EN (1 << 18) #define ADF4351_REG3_CHARGE_CANCELLATION_EN (1 << 21) #define ADF4351_REG3_ANTI_BACKLASH_3ns_EN (1 << 22) diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index 4696abfd311c..3e85afe794c0 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -264,12 +264,7 @@ static inline bool iosys_map_is_set(const struct iosys_map *map) */ static inline void iosys_map_clear(struct iosys_map *map) { - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } + memset(map, 0, sizeof(*map)); } /** diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index c4aa58032faf..f9a17fbbd398 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -160,7 +160,7 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2 do { struct folio *folio = folioq_folio(folioq, slot); - size_t part, remain, consumed; + size_t part, remain = 0, consumed; size_t fsize; void *base; @@ -168,14 +168,16 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2 break; fsize = folioq_folio_size(folioq, slot); - base = kmap_local_folio(folio, skip); - part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); - remain = step(base, progress, part, priv, priv2); - kunmap_local(base); - consumed = part - remain; - len -= consumed; - progress += consumed; - skip += consumed; + if (skip < fsize) { + base = kmap_local_folio(folio, skip); + part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); + remain = step(base, progress, part, priv, priv2); + kunmap_local(base); + consumed = part - remain; + len -= consumed; + progress += consumed; + skip += consumed; + } if (skip >= fsize) { skip = 0; slot++; diff --git a/include/linux/kcov.h b/include/linux/kcov.h index 75a2fb8b16c3..0143358874b0 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -57,47 +57,21 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * workaround for KCOV's lack of nested remote coverage sections support. - * - * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. - * - * kcov_remote_start_usb_softirq(): - * - * 1. Only collects coverage when called in the softirq context. This allows - * avoiding nested remote coverage collection sections in the task context. - * For example, USB/IP calls usb_hcd_giveback_urb() in the task context - * within an existing remote coverage collection section. Thus, KCOV should - * not attempt to start collecting coverage within the coverage collection - * section in __usb_hcd_giveback_urb() in this case. - * - * 2. Disables interrupts for the duration of the coverage collection section. - * This allows avoiding nested remote coverage collection sections in the - * softirq context (a softirq might occur during the execution of a work in - * the BH workqueue, which runs with in_serving_softirq() > 0). - * For example, usb_giveback_urb_bh() runs in the BH workqueue with - * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in - * the middle of its remote coverage collection section, and the interrupt - * handler might invoke __usb_hcd_giveback_urb() again. + * work around for kcov's lack of nested remote coverage sections support in + * task context. Adding support for nested sections is tracked in: + * https://bugzilla.kernel.org/show_bug.cgi?id=210337 */ -static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +static inline void kcov_remote_start_usb_softirq(u64 id) { - unsigned long flags = 0; - - if (in_serving_softirq()) { - local_irq_save(flags); + if (in_serving_softirq() && !in_hardirq()) kcov_remote_start_usb(id); - } - - return flags; } -static inline void kcov_remote_stop_softirq(unsigned long flags) +static inline void kcov_remote_stop_softirq(void) { - if (in_serving_softirq()) { + if (in_serving_softirq() && !in_hardirq()) kcov_remote_stop(); - local_irq_restore(flags); - } } #ifdef CONFIG_64BIT @@ -131,11 +105,8 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline unsigned long kcov_remote_start_usb_softirq(u64 id) -{ - return 0; -} -static inline void kcov_remote_stop_softirq(unsigned long flags) {} +static inline void kcov_remote_start_usb_softirq(u64 id) {} +static inline void kcov_remote_stop_softirq(void) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index acadd41e0b5c..9009e27b5f44 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -79,6 +79,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); +int set_movable_ops(const struct movable_operations *ops, enum pagetype type); #else @@ -100,6 +101,10 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } +static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type) +{ + return -ENOSYS; +} #endif /* CONFIG_MIGRATION */ diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3e6deb00fc85..7d0aa718499c 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -70,7 +70,16 @@ #define UHID_MINOR 239 #define USERIO_MINOR 240 #define VHOST_VSOCK_MINOR 241 +#define EISA_EEPROM_MINOR 241 #define RFKILL_MINOR 242 + +/* + * Misc char device minor code space division related to below macro: + * + * < 255 : Fixed minor code + * == 255 : Indicator to request dynamic minor code + * > 255 : Dynamic minor code requested, 1048320 minor codes totally. + */ #define MISC_DYNAMIC_MINOR 255 struct miscdevice { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f3a3b761abfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2071,6 +2071,8 @@ enum netdev_reg_state { * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. @@ -2482,8 +2484,9 @@ struct net_device { u64 max_pacing_offload_horizon; struct napi_config *napi_config; - unsigned long gro_flush_timeout; + u32 num_napi_configs; u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 185bd8196503..98c96d649bf9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,7 @@ struct netfs_io_stream { bool active; /* T if stream is active */ bool need_retry; /* T if this stream needs retrying */ bool failed; /* T if this stream failed */ + bool transferred_valid; /* T is ->transferred is valid */ }; /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 169b4ae30ff4..9aed39abc94b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head, extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int); extern int nfs_page_set_headlock(struct nfs_page *req); extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 3b4c36705a9b..3c5689356004 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1160,6 +1160,8 @@ struct rtsx_cr_option { bool ocp_en; u8 sd_400mA_ocp_thd; u8 sd_800mA_ocp_thd; + u8 sd_cd_reverse_en; + u8 sd_wp_reverse_en; }; /* diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b272382673d..f8188b833350 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2152,6 +2152,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p) static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + WARN_ON_ONCE(!m); /* The task should only be setting itself as blocked */ WARN_ON_ONCE(p != current); @@ -2162,8 +2164,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) * with a different mutex. Note, setting it to the same * lock repeatedly is ok. */ - WARN_ON_ONCE(p->blocked_on && p->blocked_on != m); - p->blocked_on = m; + WARN_ON_ONCE(blocked_on && blocked_on != m); + WRITE_ONCE(p->blocked_on, m); } static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) @@ -2174,16 +2176,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { - WARN_ON_ONCE(!m); - /* Currently we serialize blocked_on under the mutex::wait_lock */ - lockdep_assert_held_once(&m->wait_lock); - /* - * There may be cases where we re-clear already cleared - * blocked_on relationships, but make sure we are not - * clearing the relationship with a different lock. - */ - WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m); - p->blocked_on = NULL; + if (m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + /* Currently we serialize blocked_on under the mutex::wait_lock */ + lockdep_assert_held_once(&m->wait_lock); + /* + * There may be cases where we re-clear already cleared + * blocked_on relationships, but make sure we are not + * clearing the relationship with a different lock. + */ + WARN_ON_ONCE(blocked_on && blocked_on != m); + } + WRITE_ONCE(p->blocked_on, NULL); } static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ada5b56a4413..e5751f3070b8 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -647,7 +647,7 @@ static inline void sco_exit(void) #if IS_ENABLED(CONFIG_BT_LE) int iso_init(void); int iso_exit(void); -bool iso_enabled(void); +bool iso_inited(void); #else static inline int iso_init(void) { @@ -659,7 +659,7 @@ static inline int iso_exit(void) return 0; } -static inline bool iso_enabled(void) +static inline bool iso_inited(void) { return false; } diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4dc11c66f7b8..6906af7a8f24 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -129,7 +129,9 @@ struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; - unsigned int iso_num; + unsigned int cis_num; + unsigned int bis_num; + unsigned int pa_num; unsigned int le_num; unsigned int le_num_peripheral; }; @@ -1014,9 +1016,13 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) h->sco_num++; break; case CIS_LINK: + h->cis_num++; + break; case BIS_LINK: + h->bis_num++; + break; case PA_LINK: - h->iso_num++; + h->pa_num++; break; } } @@ -1042,9 +1048,13 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) h->sco_num--; break; case CIS_LINK: + h->cis_num--; + break; case BIS_LINK: + h->bis_num--; + break; case PA_LINK: - h->iso_num--; + h->pa_num--; break; } } @@ -1061,9 +1071,11 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) case ESCO_LINK: return h->sco_num; case CIS_LINK: + return h->cis_num; case BIS_LINK: + return h->bis_num; case PA_LINK: - return h->iso_num; + return h->pa_num; default: return 0; } @@ -1073,7 +1085,15 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num + + c->pa_num; +} + +static inline unsigned int hci_iso_count(struct hci_dev *hdev) +{ + struct hci_conn_hash *c = &hdev->conn_hash; + + return c->cis_num + c->bis_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) @@ -1915,6 +1935,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) +#define le_enabled(dev) (lmp_le_capable(dev) && \ + hci_dev_test_flag(dev, HCI_LE_ENABLED)) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) @@ -1932,6 +1954,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) +#define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev)) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ ((dev)->commands[39] & 0x04)) @@ -1981,14 +2004,23 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) +#define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) +#define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) +#define cis_central_enabled(dev) \ + (le_enabled(dev) && cis_central_capable(dev)) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) +#define cis_peripheral_enabled(dev) \ + (le_enabled(dev) && cis_peripheral_capable(dev)) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) -#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev)) +#define sync_recv_capable(dev) \ + ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 2053cd8e788a..dba369a2cf27 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); +void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); size_t bond_3ad_stats_size(void); diff --git a/include/net/devlink.h b/include/net/devlink.h index 93640a29427c..b32c9ceeb81d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -78,6 +78,9 @@ struct devlink_port_pci_sf_attrs { * @flavour: flavour of the port * @split: indicates if this is split port * @splittable: indicates if the port can be split. + * @no_phys_port_name: skip automatic phys_port_name generation; for + * compatibility only, newly added driver/port instance + * should never set this. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL * @phys: physical port attributes @@ -87,7 +90,8 @@ struct devlink_port_pci_sf_attrs { */ struct devlink_port_attrs { u8 split:1, - splittable:1; + splittable:1, + no_phys_port_name:1; u32 lanes; enum devlink_port_flavour flavour; struct netdev_phys_item_id switch_id; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff406ef4fd4a..29a36709e7f3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1163,6 +1163,14 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + if (ipvs->est_cpulist_valid) + return ipvs->sysctl_est_cpulist; + else + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return ipvs->sysctl_est_nice; @@ -1270,6 +1278,11 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return IPVS_EST_NICE; diff --git a/include/net/kcm.h b/include/net/kcm.h index 441e993be634..d9c35e71ecea 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -71,7 +71,6 @@ struct kcm_sock { struct list_head wait_psock_list; struct sk_buff *seq_skb; struct mutex tx_mutex; - u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ bool tx_wait; diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 431b593de709..1509a536cb85 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -265,6 +265,8 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi); void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 638948be4c50..738cd5b13c62 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1038,12 +1038,17 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir skb = __skb_dequeue(&sch->gso_skb); if (skb) { sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); return skb; } - if (direct) - return __qdisc_dequeue_head(&sch->q); - else + if (direct) { + skb = __qdisc_dequeue_head(&sch->q); + if (skb) + qdisc_qstats_backlog_dec(sch, skb); + return skb; + } else { return sch->dequeue(sch); + } } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index e17c4cadd04d..7c8bbe8ad1e2 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -107,8 +107,8 @@ #define CS35L56_DSP1_PMEM_5114 0x3804FE8 #define CS35L63_DSP1_FW_VER CS35L56_DSP1_FW_VER -#define CS35L63_DSP1_HALO_STATE 0x280396C -#define CS35L63_DSP1_PM_CUR_STATE 0x28042C8 +#define CS35L63_DSP1_HALO_STATE 0x2803C04 +#define CS35L63_DSP1_PM_CUR_STATE 0x2804518 #define CS35L63_PROTECTION_STATUS 0x340009C #define CS35L63_TRANSDUCER_ACTUAL_PS 0x34000F4 #define CS35L63_MAIN_RENDER_USER_MUTE 0x3400020 @@ -306,6 +306,7 @@ struct cs35l56_base { struct gpio_desc *reset_gpio; struct cs35l56_spi_payload *spi_payload_buf; const struct cs35l56_fw_reg *fw_reg; + const struct cirrus_amp_cal_controls *calibration_controls; }; static inline bool cs35l56_is_otp_register(unsigned int reg) diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h index ef9b9f19d212..273224df9282 100644 --- a/include/sound/tas2781-tlv.h +++ b/include/sound/tas2781-tlv.h @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2024 Texas Instruments Incorporated +// Copyright (C) 2022 - 2025 Texas Instruments Incorporated // https://www.ti.com // // The TAS2781 driver implements a flexible and configurable @@ -15,7 +15,7 @@ #ifndef __TAS2781_TLV_H__ #define __TAS2781_TLV_H__ -static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 50, 0); -static const __maybe_unused DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0); +static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2781_dvc_tlv, -10000, 50, 0); +static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2781_amp_tlv, 1100, 50, 0); #endif diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 1fd92021a573..03ee4c7010d7 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -38,7 +38,7 @@ enum { BINDER_TYPE_PTR = B_PACK_CHARS('p', 't', '*', B_TYPE_LARGE), }; -enum { +enum flat_binder_object_flags { FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff, FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100, diff --git a/include/uapi/linux/android/binder_netlink.h b/include/uapi/linux/android/binder_netlink.h new file mode 100644 index 000000000000..b218f96d6668 --- /dev/null +++ b/include/uapi/linux/android/binder_netlink.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/binder.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_ANDROID_BINDER_NETLINK_H +#define _UAPI_LINUX_ANDROID_BINDER_NETLINK_H + +#define BINDER_FAMILY_NAME "binder" +#define BINDER_FAMILY_VERSION 1 + +enum { + BINDER_A_REPORT_ERROR = 1, + BINDER_A_REPORT_CONTEXT, + BINDER_A_REPORT_FROM_PID, + BINDER_A_REPORT_FROM_TID, + BINDER_A_REPORT_TO_PID, + BINDER_A_REPORT_TO_TID, + BINDER_A_REPORT_IS_REPLY, + BINDER_A_REPORT_FLAGS, + BINDER_A_REPORT_CODE, + BINDER_A_REPORT_DATA_SIZE, + + __BINDER_A_REPORT_MAX, + BINDER_A_REPORT_MAX = (__BINDER_A_REPORT_MAX - 1) +}; + +enum { + BINDER_CMD_REPORT = 1, + + __BINDER_CMD_MAX, + BINDER_CMD_MAX = (__BINDER_CMD_MAX - 1) +}; + +#define BINDER_MCGRP_REPORT "report" + +#endif /* _UAPI_LINUX_ANDROID_BINDER_NETLINK_H */ diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h index 42fa15f8310d..b77d5c210c26 100644 --- a/include/uapi/linux/pfrut.h +++ b/include/uapi/linux/pfrut.h @@ -89,6 +89,7 @@ struct pfru_payload_hdr { __u32 hw_ver; __u32 rt_ver; __u8 platform_id[16]; + __u32 svn_ver; }; enum pfru_dsm_status { diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index b13946287277..ac74133a4768 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -173,7 +173,7 @@ typedef struct mdp_superblock_s { #else #error unspecified endianness #endif - __u32 resync_offset; /* 11 resync checkpoint sector count */ + __u32 recovery_cp; /* 11 resync checkpoint sector count */ /* There are only valid for minor_version > 90 */ __u64 reshape_position; /* 12,13 next address in array-space for reshape */ __u32 new_level; /* 14 new level we are reshaping to */ diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index f33d914d8f46..c6e2925f47e6 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -134,7 +134,7 @@ struct fastrpc_mem_unmap { }; struct fastrpc_ioctl_capability { - __u32 domain; + __u32 unused; /* deprecated, ignored by the kernel */ __u32 attribute_id; __u32 capability; /* dsp capability */ __u32 reserved[4]; diff --git a/io_uring/futex.c b/io_uring/futex.c index 692462d50c8c..9113a44984f3 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -288,6 +288,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) goto done_unlock; } + req->flags |= REQ_F_ASYNC_DATA; req->async_data = ifd; ifd->q = futex_q_init; ifd->q.bitset = iof->futex_mask; @@ -309,6 +310,8 @@ done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; kfree(ifd); return IOU_COMPLETE; } diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index be91edf34f01..17dfaa0395c4 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -357,6 +357,13 @@ static void create_worker_cb(struct callback_head *cb) worker = container_of(cb, struct io_worker, create_work); wq = worker->wq; acct = worker->acct; + + rcu_read_lock(); + do_create = !io_acct_activate_free_worker(acct); + rcu_read_unlock(); + if (!do_create) + goto no_need_create; + raw_spin_lock(&acct->workers_lock); if (acct->nr_workers < acct->max_workers) { @@ -367,6 +374,7 @@ static void create_worker_cb(struct callback_head *cb) if (do_create) { create_io_worker(wq, acct); } else { +no_need_create: atomic_dec(&acct->nr_running); io_worker_ref_put(wq); } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4ef69dd58734..93633613a165 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2119,6 +2119,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->file = NULL; req->tctx = current->io_uring; req->cancel_seq_set = false; + req->async_data = NULL; if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; diff --git a/io_uring/net.c b/io_uring/net.c index dd96e355982f..d69f2afa4f7a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -494,6 +494,15 @@ static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret) return nbufs; } +static int io_net_kbuf_recyle(struct io_kiocb *req, + struct io_async_msghdr *kmsg, int len) +{ + req->flags |= REQ_F_BL_NO_RECYCLE; + if (req->flags & REQ_F_BUFFERS_COMMIT) + io_kbuf_commit(req, req->buf_list, len, io_bundle_nbufs(kmsg, len)); + return IOU_RETRY; +} + static inline bool io_send_finish(struct io_kiocb *req, int *ret, struct io_async_msghdr *kmsg, unsigned issue_flags) @@ -562,8 +571,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg->msg.msg_controllen = 0; kmsg->msg.msg_control = NULL; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -674,8 +682,7 @@ retry_bundle: sr->len -= ret; sr->buf += ret; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1071,8 +1078,7 @@ retry_multishot: } if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return IOU_RETRY; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1218,8 +1224,7 @@ retry_multishot: sr->len -= ret; sr->buf += ret; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1500,8 +1505,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) zc->len -= ret; zc->buf += ret; zc->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1571,8 +1575,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags) if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 2ee603a98813..1224dd937df0 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -97,6 +97,7 @@ config KEXEC_JUMP config KEXEC_HANDOVER bool "kexec handover" depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE + depends on !DEFERRED_STRUCT_PAGE_INIT select MEMBLOCK_KHO_SCRATCH select KEXEC_FILE select DEBUG_FS diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f74d04429a29..27adb04df675 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -280,7 +280,7 @@ static inline void check_insane_mems_config(nodemask_t *nodes) { if (!cpusets_insane_config() && movable_only_nodes(nodes)) { - static_branch_enable(&cpusets_insane_config_key); + static_branch_enable_cpuslocked(&cpusets_insane_config_key); pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" "Cpuset allocations might fail even with a lot of memory available.\n", nodemask_pr_args(nodes)); @@ -1843,7 +1843,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, if (is_partition_valid(cs)) adding = cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); - } else if (is_partition_invalid(cs) && + } else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) && cpumask_subset(xcpus, parent->effective_xcpus)) { struct cgroup_subsys_state *css; struct cpuset *child; @@ -3358,14 +3358,12 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, else return -EINVAL; - css_get(&cs->css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); - css_put(&cs->css); return retval ?: nbytes; } @@ -3870,9 +3868,10 @@ retry: partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned - * back to a regular one. + * back to a regular one with a non-empty effective xcpus. */ - else if (is_partition_valid(parent) && is_partition_invalid(cs)) + else if (is_partition_valid(parent) && is_partition_invalid(cs) && + !cpumask_empty(cs->effective_xcpus)) partcmd = partcmd_update; if (partcmd >= 0) { diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 981e2f77ad4e..a198e40c799b 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -479,6 +479,9 @@ void css_rstat_exit(struct cgroup_subsys_state *css) if (!css_uses_rstat(css)) return; + if (!css->rstat_cpu) + return; + css_rstat_flush(css); /* sanity check */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 8060c2857bb2..872122e074e5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event); static void perf_event_unthrottle(struct perf_event *event, bool start) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return; + event->hw.interrupts = 0; if (start) event->pmu->start(event, 0); @@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start) static void perf_event_throttle(struct perf_event *event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return; + event->hw.interrupts = MAX_INTERRUPTS; event->pmu->stop(event, 0); if (event == event->group_leader) diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index c74eac572acd..2cd57096c38e 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -319,13 +319,13 @@ static __always_inline int futex_put_value(u32 val, u32 __user *to) { if (can_do_masked_user_access()) to = masked_user_access_begin(to); - else if (!user_read_access_begin(to, sizeof(*to))) + else if (!user_write_access_begin(to, sizeof(*to))) return -EFAULT; unsafe_put_user(val, to, Efault); - user_read_access_end(); + user_write_access_end(); return 0; Efault: - user_read_access_end(); + user_write_access_end(); return -EFAULT; } diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index e49743ae52c5..ecd1ac210dbd 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -144,14 +144,34 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, unsigned int order) { struct kho_mem_phys_bits *bits; - struct kho_mem_phys *physxa; + struct kho_mem_phys *physxa, *new_physxa; const unsigned long pfn_high = pfn >> order; might_sleep(); - physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa)); - if (IS_ERR(physxa)) - return PTR_ERR(physxa); + physxa = xa_load(&track->orders, order); + if (!physxa) { + int err; + + new_physxa = kzalloc(sizeof(*physxa), GFP_KERNEL); + if (!new_physxa) + return -ENOMEM; + + xa_init(&new_physxa->phys_bits); + physxa = xa_cmpxchg(&track->orders, order, NULL, new_physxa, + GFP_KERNEL); + + err = xa_err(physxa); + if (err || physxa) { + xa_destroy(&new_physxa->phys_bits); + kfree(new_physxa); + + if (err) + return err; + } else { + physxa = new_physxa; + } + } bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS, sizeof(*bits)); @@ -544,6 +564,7 @@ err_free_scratch_areas: err_free_scratch_desc: memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch)); err_disable_kho: + pr_warn("Failed to reserve scratch area, disabling kexec handover\n"); kho_enable = false; } diff --git a/kernel/kthread.c b/kernel/kthread.c index 0e98b228a8ef..31b072e8d427 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -893,6 +893,7 @@ out: return ret; } +EXPORT_SYMBOL_GPL(kthread_affine_preferred); /* * Re-affine kthreads according to their preferences diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 086fd5487ca7..31a785afee6c 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -342,8 +342,12 @@ static bool __ww_mutex_wound(struct MUTEX *lock, * When waking up the task to wound, be sure to clear the * blocked_on pointer. Otherwise we can see circular * blocked_on relationships that can't resolve. + * + * NOTE: We pass NULL here instead of lock, because we + * are waking the mutex owner, who may be currently + * blocked on a different mutex. */ - __clear_task_blocked_on(owner, lock); + __clear_task_blocked_on(owner, NULL); wake_q_add(wake_q, owner); } return true; diff --git a/kernel/params.c b/kernel/params.c index b92d64161b75..b96cfd693c99 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -513,13 +513,14 @@ EXPORT_SYMBOL(param_array_ops); int param_set_copystring(const char *val, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; + const size_t len = strnlen(val, kps->maxlen); - if (strnlen(val, kps->maxlen) == kps->maxlen) { + if (len == kps->maxlen) { pr_err("%s: string doesn't fit in %u chars.\n", kp->name, kps->maxlen-1); return -ENOSPC; } - strcpy(kps->string, val); + memcpy(kps->string, val, len + 1); return 0; } EXPORT_SYMBOL(param_set_copystring); @@ -841,7 +842,7 @@ static void __init param_sysfs_builtin(void) dot = strchr(kp->name, '.'); if (!dot) { /* This happens for core_param() */ - strcpy(modname, "kernel"); + strscpy(modname, "kernel"); name_len = 0; } else { name_len = dot - kp->name + 1; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 174ee243b349..8eff357b0436 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4262,6 +4262,8 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + rcu_preempt_deferred_qs_init(rdp); rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index de6ca13a7b5f..b8bbe7960cda 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -488,6 +488,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fc14adf15cbb..4cd170b2d655 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -763,8 +763,6 @@ static void rcu_read_unlock_special(struct task_struct *t) cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw = - IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -904,6 +902,10 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) } } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) +{ + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); +} #else /* #ifdef CONFIG_PREEMPT_RCU */ /* @@ -1103,6 +1105,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) { } + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7dedc9a16281..4ae32ef179dd 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5749,6 +5749,9 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) __setscheduler_class(p->policy, p->prio); struct sched_enq_and_set_ctx ctx; + if (!tryget_task_struct(p)) + continue; + if (old_class != new_class && p->se.sched_delayed) dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); @@ -5761,6 +5764,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) sched_enq_and_set_task(&ctx); check_class_changed(task_rq(p), p, old_class, p->prio); + put_task_struct(p); } scx_task_iter_stop(&sti); percpu_up_write(&scx_fork_rwsem); diff --git a/kernel/signal.c b/kernel/signal.c index e2c928de7d2c..fe9190d84f28 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4067,6 +4067,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, { struct pid *pid; enum pid_type type; + int ret; /* Enforce flags be set to 0 until we add an extension. */ if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) @@ -4108,7 +4109,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, } } - return do_pidfd_send_signal(pid, sig, type, info, flags); + ret = do_pidfd_send_signal(pid, sig, type, info, flags); + put_pid(pid); + + return ret; } static int diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index f4d200f0c610..2a42c1036ea8 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1397,6 +1397,7 @@ error: ftrace_graph_active--; gops->saved_func = NULL; fgraph_lru_release_index(i); + unregister_pm_notifier(&ftrace_suspend_notifier); } return ret; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 00b76d450a89..a69067367c29 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4661,13 +4661,17 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, } else { iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash); } + } else { + if (hash) + iter->hash = alloc_and_copy_ftrace_hash(hash->size_bits, hash); + else + iter->hash = EMPTY_HASH; + } - if (!iter->hash) { - trace_parser_put(&iter->parser); - goto out_unlock; - } - } else - iter->hash = hash; + if (!iter->hash) { + trace_parser_put(&iter->parser); + goto out_unlock; + } ret = 0; @@ -6543,9 +6547,6 @@ int ftrace_regex_release(struct inode *inode, struct file *file) ftrace_hash_move_and_update_ops(iter->ops, orig_hash, iter->hash, filter_hash); mutex_unlock(&ftrace_lock); - } else { - /* For read only, the hash is the ops hash */ - iter->hash = NULL; } mutex_unlock(&iter->ops->func_hash->regex_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bb71a0dc9d69..43460949ad3f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7666,7 +7666,7 @@ static __init int test_ringbuffer(void) rb_test_started = true; set_current_state(TASK_INTERRUPTIBLE); - /* Just run for 10 seconds */; + /* Just run for 10 seconds */ schedule_timeout(10 * HZ); kthread_stop(rb_hammer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4283ed4e8f59..1b7db732c0b1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1816,7 +1816,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; @@ -1830,7 +1830,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; } @@ -1848,12 +1848,14 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, while (cnt && !isspace(ch) && ch) { if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; - else - return -EINVAL; + else { + ret = -EINVAL; + goto fail; + } ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; } @@ -1868,11 +1870,15 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, /* Make sure the parsed string always terminates with '\0'. */ parser->buffer[parser->idx] = 0; } else { - return -EINVAL; + ret = -EINVAL; + goto fail; } *ppos += read; return read; +fail: + trace_parser_fail(parser); + return ret; } /* TODO add a seq_buf_to_buffer() */ @@ -10632,10 +10638,10 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m ret = print_trace_line(&iter); if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); + + trace_printk_seq(&iter.seq); } touch_nmi_watchdog(); - - trace_printk_seq(&iter.seq); } if (!cnt) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 1dbf1d3cf2f1..5f4bed5842f9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1292,6 +1292,7 @@ bool ftrace_event_is_function(struct trace_event_call *call); */ struct trace_parser { bool cont; + bool fail; char *buffer; unsigned idx; unsigned size; @@ -1299,7 +1300,7 @@ struct trace_parser { static inline bool trace_parser_loaded(struct trace_parser *parser) { - return (parser->idx != 0); + return !parser->fail && parser->idx != 0; } static inline bool trace_parser_cont(struct trace_parser *parser) @@ -1313,6 +1314,11 @@ static inline void trace_parser_clear(struct trace_parser *parser) parser->idx = 0; } +static inline void trace_parser_fail(struct trace_parser *parser) +{ + parser->fail = true; +} + extern int trace_parser_get_init(struct trace_parser *parser, int size); extern void trace_parser_put(struct trace_parser *parser); extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, @@ -2204,7 +2210,7 @@ static inline bool is_good_system_name(const char *name) static inline void sanitize_event_name(char *name) { while (*name++ != '\0') - if (*name == ':' || *name == '.') + if (*name == ':' || *name == '.' || *name == '*') *name = '_'; } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 66e1a527cf1a..a7f4b9a47a71 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -27,14 +27,21 @@ struct fgraph_cpu_data { unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH]; }; +struct fgraph_ent_args { + struct ftrace_graph_ent_entry ent; + /* Force the sizeof of args[] to have FTRACE_REGS_MAX_ARGS entries */ + unsigned long args[FTRACE_REGS_MAX_ARGS]; +}; + struct fgraph_data { struct fgraph_cpu_data __percpu *cpu_data; /* Place to preserve last processed entry. */ union { - struct ftrace_graph_ent_entry ent; + struct fgraph_ent_args ent; + /* TODO allow retaddr to have args */ struct fgraph_retaddr_ent_entry rent; - } ent; + }; struct ftrace_graph_ret_entry ret; int failed; int cpu; @@ -627,10 +634,13 @@ get_return_for_leaf(struct trace_iterator *iter, * Save current and next entries for later reference * if the output fails. */ - if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) - data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr; - else - data->ent.ent = *curr; + if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) { + data->rent = *(struct fgraph_retaddr_ent_entry *)curr; + } else { + int size = min((int)sizeof(data->ent), (int)iter->ent_size); + + memcpy(&data->ent, curr, size); + } /* * If the next event is not a return type, then * we only care about what type it is. Otherwise we can diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index c2b65b6a9bb6..1e6b008f8fca 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -140,8 +140,8 @@ config CRYPTO_LIB_CHACHA20POLY1305 config CRYPTO_LIB_SHA1 tristate help - The SHA-1 library functions. Select this if your module uses any of - the functions from <crypto/sha1.h>. + The SHA-1 and HMAC-SHA1 library functions. Select this if your module + uses any of the functions from <crypto/sha1.h>. config CRYPTO_LIB_SHA1_ARCH bool @@ -157,9 +157,9 @@ config CRYPTO_LIB_SHA1_ARCH config CRYPTO_LIB_SHA256 tristate help - Enable the SHA-256 library interface. This interface may be fulfilled - by either the generic implementation or an arch-specific one, if one - is available and enabled. + The SHA-224, SHA-256, HMAC-SHA224, and HMAC-SHA256 library functions. + Select this if your module uses any of these functions from + <crypto/sha2.h>. config CRYPTO_LIB_SHA256_ARCH bool diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index e4151be2ebd4..539d5d59a50e 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -100,7 +100,6 @@ ifeq ($(CONFIG_ARM),y) libsha256-y += arm/sha256-ce.o arm/sha256-core.o $(obj)/arm/sha256-core.S: $(src)/arm/sha256-armv4.pl $(call cmd,perlasm) -clean-files += arm/sha256-core.S AFLAGS_arm/sha256-core.o += $(aflags-thumb2-y) endif @@ -108,7 +107,6 @@ ifeq ($(CONFIG_ARM64),y) libsha256-y += arm64/sha256-core.o $(obj)/arm64/sha256-core.S: $(src)/arm64/sha2-armv8.pl $(call cmd,perlasm_with_args) -clean-files += arm64/sha256-core.S libsha256-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha256-ce.o endif @@ -132,7 +130,6 @@ ifeq ($(CONFIG_ARM),y) libsha512-y += arm/sha512-core.o $(obj)/arm/sha512-core.S: $(src)/arm/sha512-armv4.pl $(call cmd,perlasm) -clean-files += arm/sha512-core.S AFLAGS_arm/sha512-core.o += $(aflags-thumb2-y) endif @@ -140,7 +137,6 @@ ifeq ($(CONFIG_ARM64),y) libsha512-y += arm64/sha512-core.o $(obj)/arm64/sha512-core.S: $(src)/arm64/sha2-armv8.pl $(call cmd,perlasm_with_args) -clean-files += arm64/sha512-core.S libsha512-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha512-ce-core.o endif @@ -167,3 +163,7 @@ obj-$(CONFIG_PPC) += powerpc/ obj-$(CONFIG_RISCV) += riscv/ obj-$(CONFIG_S390) += s390/ obj-$(CONFIG_X86) += x86/ + +# clean-files must be defined unconditionally +clean-files += arm/sha256-core.S arm/sha512-core.S +clean-files += arm64/sha256-core.S arm64/sha512-core.S diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index a9e6ffcff04b..cce12287708e 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -434,7 +434,7 @@ void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir) if (dentry && !xa_is_err(dentry)) return; - ret = snprintf(name, sizeof(name), "%s@%px", dir->class, dir); + ret = snprintf(name, sizeof(name), "%s@%p", dir->class, dir); name[sizeof(name) - 1] = '\0'; if (ret < sizeof(name)) { diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 2a4a649805c1..03c5dbabb156 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -254,4 +254,10 @@ const struct movable_operations balloon_mops = { .putback_page = balloon_page_putback, }; +static int __init balloon_init(void) +{ + return set_movable_ops(&balloon_mops, PGTY_offline); +} +core_initcall(balloon_init); + #endif /* CONFIG_BALLOON_COMPACTION */ diff --git a/mm/damon/core.c b/mm/damon/core.c index 52a48c9316bc..70eff5cbe6ee 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -845,6 +845,18 @@ static struct damos_filter *damos_nth_filter(int n, struct damos *s) return NULL; } +static struct damos_filter *damos_nth_ops_filter(int n, struct damos *s) +{ + struct damos_filter *filter; + int i = 0; + + damos_for_each_ops_filter(filter, s) { + if (i++ == n) + return filter; + } + return NULL; +} + static void damos_commit_filter_arg( struct damos_filter *dst, struct damos_filter *src) { @@ -871,6 +883,7 @@ static void damos_commit_filter( { dst->type = src->type; dst->matching = src->matching; + dst->allow = src->allow; damos_commit_filter_arg(dst, src); } @@ -908,7 +921,7 @@ static int damos_commit_ops_filters(struct damos *dst, struct damos *src) int i = 0, j = 0; damos_for_each_ops_filter_safe(dst_filter, next, dst) { - src_filter = damos_nth_filter(i++, src); + src_filter = damos_nth_ops_filter(i++, src); if (src_filter) damos_commit_filter(dst_filter, src_filter); else diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 74056bcd6a2c..6536f16006c9 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2158,8 +2158,8 @@ static void damon_sysfs_scheme_rm_dirs(struct damon_sysfs_scheme *scheme) { damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); kobject_put(&scheme->access_pattern->kobj); - kobject_put(&scheme->dests->kobj); damos_sysfs_dests_rm_dirs(scheme->dests); + kobject_put(&scheme->dests->kobj); damon_sysfs_quotas_rm_dirs(scheme->quotas); kobject_put(&scheme->quotas->kobj); kobject_put(&scheme->watermarks->kobj); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index d19031f275a3..830107b6dd08 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -990,29 +990,34 @@ static void __init destroy_args(struct pgtable_debug_args *args) /* Free page table entries */ if (args->start_ptep) { + pmd_clear(args->pmdp); pte_free(args->mm, args->start_ptep); mm_dec_nr_ptes(args->mm); } if (args->start_pmdp) { + pud_clear(args->pudp); pmd_free(args->mm, args->start_pmdp); mm_dec_nr_pmds(args->mm); } if (args->start_pudp) { + p4d_clear(args->p4dp); pud_free(args->mm, args->start_pudp); mm_dec_nr_puds(args->mm); } - if (args->start_p4dp) + if (args->start_p4dp) { + pgd_clear(args->pgdp); p4d_free(args->mm, args->start_p4dp); + } /* Free vma and mm struct */ if (args->vma) vm_area_free(args->vma); if (args->mm) - mmdrop(args->mm); + mmput(args->mm); } static struct page * __init diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 2aa12dfa427a..e0968acc03aa 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 374a6a5193a7..6b40bdfd224c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ + vma_start_write(vma); result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; - vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 8d588e685311..84265983f239 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } @@ -2181,6 +2184,7 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2189,6 +2193,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e2e685b971bb..fc30ca4804bf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -853,9 +853,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, #define hwpoison_hugetlb_range NULL #endif +static int hwpoison_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + /* We also want to consider pages mapped into VM_PFNMAP. */ + return 0; +} + static const struct mm_walk_ops hwpoison_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, + .test_walk = hwpoison_test_walk, .walk_lock = PGWALK_RDLOCK, }; diff --git a/mm/migrate.c b/mm/migrate.c index 425401b2d4e1..9e5ef39ce73a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -43,8 +43,6 @@ #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/pagewalk.h> -#include <linux/balloon_compaction.h> -#include <linux/zsmalloc.h> #include <asm/tlbflush.h> @@ -53,6 +51,33 @@ #include "internal.h" #include "swap.h" +static const struct movable_operations *offline_movable_ops; +static const struct movable_operations *zsmalloc_movable_ops; + +int set_movable_ops(const struct movable_operations *ops, enum pagetype type) +{ + /* + * We only allow for selected types and don't handle concurrent + * registration attempts yet. + */ + switch (type) { + case PGTY_offline: + if (offline_movable_ops && ops) + return -EBUSY; + offline_movable_ops = ops; + break; + case PGTY_zsmalloc: + if (zsmalloc_movable_ops && ops) + return -EBUSY; + zsmalloc_movable_ops = ops; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(set_movable_ops); + static const struct movable_operations *page_movable_ops(struct page *page) { VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); @@ -62,15 +87,12 @@ static const struct movable_operations *page_movable_ops(struct page *page) * it as movable, the page type must be sticky until the page gets freed * back to the buddy. */ -#ifdef CONFIG_BALLOON_COMPACTION if (PageOffline(page)) /* Only balloon compaction sets PageOffline pages movable. */ - return &balloon_mops; -#endif /* CONFIG_BALLOON_COMPACTION */ -#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) + return offline_movable_ops; if (PageZsmalloc(page)) - return &zsmalloc_mops; -#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */ + return zsmalloc_movable_ops; + return NULL; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 78bded7acf79..113b48985834 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep, static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, pte_t oldpte, pte_t *pte, int target_node, - struct folio **foliop) + struct folio *folio) { - struct folio *folio = NULL; bool ret = true; bool toptier; int nid; @@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, if (pte_protnone(oldpte)) goto skip; - folio = vm_normal_folio(vma, addr, oldpte); if (!folio) goto skip; @@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); skip: - *foliop = folio; return ret; } @@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len, * retrieve sub-batches. */ static void commit_anon_folio_batch(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { - struct page *first_page = folio_page(folio, 0); bool expected_anon_exclusive; int sub_batch_idx = 0; int len; @@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma, } static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { bool set_write; @@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, /* idx = */ 0, set_write, tlb); return; } - commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb); + commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb); } static long change_pte_range(struct mmu_gather *tlb, @@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb, const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE; int max_nr_ptes = (end - addr) >> PAGE_SHIFT; struct folio *folio = NULL; + struct page *page; pte_t ptent; + page = vm_normal_page(vma, addr, oldpte); + if (page) + folio = page_folio(page); /* * Avoid trapping faults against the zero or KSM * pages. See similar comment in change_huge_pmd. */ if (prot_numa) { int ret = prot_numa_skip(vma, addr, oldpte, pte, - target_node, &folio); + target_node, folio); if (ret) { /* determine batch to skip */ @@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb, } } - if (!folio) - folio = vm_normal_folio(vma, addr, oldpte); - nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags); oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes); @@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb, */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pte_write(ptent)) - set_write_prot_commit_flush_ptes(vma, folio, + set_write_prot_commit_flush_ptes(vma, folio, page, addr, pte, oldpte, ptent, nr_ptes, tlb); else prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent, diff --git a/mm/mremap.c b/mm/mremap.c index 677a4d744df9..e618a706aff5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr if (max_nr == 1) return 1; + /* Avoid expensive folio lookup if we stand no chance of benefit. */ + if (pte_batch_hint(ptep, pte) == 1) + return 1; + folio = vm_normal_folio(vma, addr, pte); if (!folio || !folio_test_large(folio)) return 1; @@ -319,6 +323,25 @@ static inline bool arch_supports_page_table_move(void) } #endif +static inline bool uffd_supports_page_table_move(struct pagetable_move_control *pmc) +{ + /* + * If we are moving a VMA that has uffd-wp registered but with + * remap events disabled (new VMA will not be registered with uffd), we + * need to ensure that the uffd-wp state is cleared from all pgtables. + * This means recursing into lower page tables in move_page_tables(). + * + * We might get called with VMAs reversed when recovering from a + * failed page table move. In that case, the + * "old"-but-actually-"originally new" VMA during recovery will not have + * a uffd context. Recursing into lower page tables during the original + * move but not during the recovery move will cause trouble, because we + * run into already-existing page tables. So check both VMAs. + */ + return !vma_has_uffd_without_event_remap(pmc->old) && + !vma_has_uffd_without_event_remap(pmc->new); +} + #ifdef CONFIG_HAVE_MOVE_PMD static bool move_normal_pmd(struct pagetable_move_control *pmc, pmd_t *old_pmd, pmd_t *new_pmd) @@ -331,6 +354,8 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc, if (!arch_supports_page_table_move()) return false; + if (!uffd_supports_page_table_move(pmc)) + return false; /* * The destination pmd shouldn't be established, free_pgtables() * should have released it. @@ -357,15 +382,6 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc, if (WARN_ON_ONCE(!pmd_none(*new_pmd))) return false; - /* If this pmd belongs to a uffd vma with remap events disabled, we need - * to ensure that the uffd-wp state is cleared from all pgtables. This - * means recursing into lower page tables in move_page_tables(), and we - * can reuse the existing code if we simply treat the entry as "not - * moved". - */ - if (vma_has_uffd_without_event_remap(vma)) - return false; - /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -414,6 +430,8 @@ static bool move_normal_pud(struct pagetable_move_control *pmc, if (!arch_supports_page_table_move()) return false; + if (!uffd_supports_page_table_move(pmc)) + return false; /* * The destination pud shouldn't be established, free_pgtables() * should have released it. @@ -421,15 +439,6 @@ static bool move_normal_pud(struct pagetable_move_control *pmc, if (WARN_ON_ONCE(!pud_none(*new_pud))) return false; - /* If this pud belongs to a uffd vma with remap events disabled, we need - * to ensure that the uffd-wp state is cleared from all pgtables. This - * means recursing into lower page tables in move_page_tables(), and we - * can reuse the existing code if we simply treat the entry as "not - * moved". - */ - if (vma_has_uffd_without_event_remap(vma)) - return false; - /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -1616,7 +1625,7 @@ static void notify_uffd(struct vma_remap_struct *vrm, bool failed) static bool vma_multi_allowed(struct vm_area_struct *vma) { - struct file *file; + struct file *file = vma->vm_file; /* * We can't support moving multiple uffd VMAs as notify requires @@ -1629,15 +1638,17 @@ static bool vma_multi_allowed(struct vm_area_struct *vma) * Custom get unmapped area might result in MREMAP_FIXED not * being obeyed. */ - file = vma->vm_file; - if (file && !vma_is_shmem(vma) && !is_vm_hugetlb_page(vma)) { - const struct file_operations *fop = file->f_op; - - if (fop->get_unmapped_area) - return false; - } + if (!file || !file->f_op->get_unmapped_area) + return true; + /* Known good. */ + if (vma_is_shmem(vma)) + return true; + if (is_vm_hugetlb_page(vma)) + return true; + if (file->f_op->get_unmapped_area == thp_get_unmapped_area) + return true; - return true; + return false; } static int check_prep_vma(struct vma_remap_struct *vrm) @@ -1814,10 +1825,11 @@ static unsigned long remap_move(struct vma_remap_struct *vrm) unsigned long start = vrm->addr; unsigned long end = vrm->addr + vrm->old_len; unsigned long new_addr = vrm->new_addr; - bool allowed = true, seen_vma = false; unsigned long target_addr = new_addr; unsigned long res = -EFAULT; unsigned long last_end; + bool seen_vma = false; + VMA_ITERATOR(vmi, current->mm, start); /* @@ -1830,9 +1842,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm) unsigned long addr = max(vma->vm_start, start); unsigned long len = min(end, vma->vm_end) - addr; unsigned long offset, res_vma; - - if (!allowed) - return -EFAULT; + bool multi_allowed; /* No gap permitted at the start of the range. */ if (!seen_vma && start < vma->vm_start) @@ -1861,9 +1871,15 @@ static unsigned long remap_move(struct vma_remap_struct *vrm) vrm->new_addr = target_addr + offset; vrm->old_len = vrm->new_len = len; - allowed = vma_multi_allowed(vma); - if (seen_vma && !allowed) - return -EFAULT; + multi_allowed = vma_multi_allowed(vma); + if (!multi_allowed) { + /* This is not the first VMA, abort immediately. */ + if (seen_vma) + return -EFAULT; + /* This is the first, but there are more, abort. */ + if (vma->vm_end < end) + return -EFAULT; + } res_vma = check_prep_vma(vrm); if (!res_vma) @@ -1872,7 +1888,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm) return res_vma; if (!seen_vma) { - VM_WARN_ON_ONCE(allowed && res_vma != new_addr); + VM_WARN_ON_ONCE(multi_allowed && res_vma != new_addr); res = res_vma; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index cbed91b09640..45e6290e2e8b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1821,13 +1821,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pmd_folio(*src_pmd); - - if (!folio || (!is_huge_zero_folio(folio) && - !PageAnonExclusive(&folio->page))) { - spin_unlock(ptl); - err = -EBUSY; - break; + /* Can be a migration entry */ + if (pmd_present(*src_pmd)) { + struct folio *folio = pmd_folio(*src_pmd); + + if (!is_huge_zero_folio(folio) && + !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } } spin_unlock(ptl); diff --git a/mm/vmscan.c b/mm/vmscan.c index 7de11524a936..a48aec8bfd92 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -5772,9 +5772,9 @@ static int __init init_lru_gen(void) if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); - debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, 1, + debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false, &lru_gen_rw_fops); - debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, 0, + debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true, &lru_gen_ro_fops); return 0; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 2c5e56a65354..805a10b41266 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2246,9 +2246,16 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool); static int __init zs_init(void) { + int rc __maybe_unused; + #ifdef CONFIG_ZPOOL zpool_register_driver(&zs_zpool_driver); #endif +#ifdef CONFIG_COMPACTION + rc = set_movable_ops(&zsmalloc_mops, PGTY_zsmalloc); + if (rc) + return rc; +#endif zs_stat_init(); return 0; } @@ -2258,6 +2265,9 @@ static void __exit zs_exit(void) #ifdef CONFIG_ZPOOL zpool_unregister_driver(&zs_zpool_driver); #endif +#ifdef CONFIG_COMPACTION + set_movable_ops(NULL, PGTY_zsmalloc); +#endif zs_stat_exit(); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7d1e79f69cd1..7a879290dd28 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -339,7 +339,8 @@ static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data) case BT_CODEC_TRANSPARENT: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) - return false; + return -EINVAL; + param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x03; cp.rx_coding_format.id = 0x03; @@ -830,7 +831,17 @@ static void bis_cleanup(struct hci_conn *conn) /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ - bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECTED, + HCI_ROLE_MASTER); + if (bis) + return; + + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECT, + HCI_ROLE_MASTER); if (bis) return; @@ -2249,7 +2260,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, * the start periodic advertising and create BIG commands have * been queued */ - hci_conn_hash_list_state(hdev, bis_mark_per_adv, PA_LINK, + hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8aa5039b975a..fe7cdd67ad2a 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6745,8 +6745,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.in.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.out.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.in.phy = ev->c_phy; qos->ucast.out.phy = ev->p_phy; break; @@ -6760,8 +6760,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.out.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.in.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.out.phy = ev->c_phy; qos->ucast.in.phy = ev->p_phy; break; @@ -6957,9 +6957,14 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; } - if (ev->status != 0x42) + if (ev->status != 0x42) { /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); + /* Reset cleanup callback of PA Sync so it doesn't + * terminate the sync when deleting the connection. + */ + conn->cleanup = NULL; + } bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 2b4f21fbf9c1..31d72b9683ef 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3344,7 +3344,7 @@ static int hci_powered_update_adv_sync(struct hci_dev *hdev) * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) && list_empty(&hdev->adv_instances)) { if (ext_adv_capable(hdev)) { err = hci_setup_ext_adv_instance_sync(hdev, 0x00); @@ -4531,14 +4531,14 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!cis_capable(hdev)) + if (!iso_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; - cp.bit_value = 1; + cp.bit_value = iso_enabled(hdev) ? 0x01 : 0x00; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_HOST_FEATURE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); @@ -6985,8 +6985,6 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err) hci_dev_lock(hdev); - hci_dev_clear_flag(hdev, HCI_PA_SYNC); - if (!hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); @@ -7047,10 +7045,13 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) /* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update * it. */ - if (conn->sid == HCI_SID_INVALID) - __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, - HCI_EV_LE_EXT_ADV_REPORT, - conn->conn_timeout, NULL); + if (conn->sid == HCI_SID_INVALID) { + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, + HCI_EV_LE_EXT_ADV_REPORT, + conn->conn_timeout, NULL); + if (err == -ETIMEDOUT) + goto done; + } memset(&cp, 0, sizeof(cp)); cp.options = qos->bcast.options; @@ -7080,6 +7081,12 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); +done: + hci_dev_clear_flag(hdev, HCI_PA_SYNC); + + /* Update passive scan since HCI_PA_SYNC flag has been cleared */ + hci_update_passive_scan_sync(hdev); + return err; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 7bd3aa0a6db9..5ce823ca3aaf 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1347,7 +1347,7 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst); sa->iso_bdaddr_type = iso_pi(sk)->dst_type; - if (hcon && hcon->type == BIS_LINK) { + if (hcon && (hcon->type == BIS_LINK || hcon->type == PA_LINK)) { sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid; sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis; memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis, @@ -2483,11 +2483,11 @@ static const struct net_proto_family iso_sock_family_ops = { .create = iso_sock_create, }; -static bool iso_inited; +static bool inited; -bool iso_enabled(void) +bool iso_inited(void) { - return iso_inited; + return inited; } int iso_init(void) @@ -2496,7 +2496,7 @@ int iso_init(void) BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); - if (iso_inited) + if (inited) return -EALREADY; err = proto_register(&iso_proto, 0); @@ -2524,7 +2524,7 @@ int iso_init(void) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); - iso_inited = true; + inited = true; return 0; @@ -2535,7 +2535,7 @@ error: int iso_exit(void) { - if (!iso_inited) + if (!inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); @@ -2549,7 +2549,7 @@ int iso_exit(void) proto_unregister(&iso_proto); - iso_inited = false; + inited = false; return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1ce682038b51..3166f5fb876b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -922,19 +922,19 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; - if (cis_central_capable(hdev)) + if (cis_central_enabled(hdev)) settings |= MGMT_SETTING_CIS_CENTRAL; - if (cis_peripheral_capable(hdev)) + if (cis_peripheral_enabled(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; - if (bis_capable(hdev)) + if (bis_enabled(hdev)) settings |= MGMT_SETTING_ISO_BROADCASTER; - if (sync_recv_capable(hdev)) + if (sync_recv_enabled(hdev)) settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; - if (ll_privacy_capable(hdev)) + if (ll_privacy_enabled(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; return settings; @@ -4513,7 +4513,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, } if (IS_ENABLED(CONFIG_BT_LE)) { - flags = iso_enabled() ? BIT(0) : 0; + flags = iso_inited() ? BIT(0) : 0; memcpy(rp->features[idx].uuid, iso_socket_uuid, 16); rp->features[idx].flags = cpu_to_le32(flags); idx++; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 1377f31b719c..8ce145938b02 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4818,6 +4818,14 @@ void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MAX; + } + brmctx->multicast_query_interval = intvl_jiffies; } @@ -4834,6 +4842,14 @@ void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_STARTUP_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast startup query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MAX; + } + brmctx->multicast_startup_query_interval = intvl_jiffies; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b159aae594c0..8de0904b9627 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -31,6 +31,8 @@ #define BR_MULTICAST_DEFAULT_HASH_MAX 4096 #define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000) #define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN +#define BR_MULTICAST_QUERY_INTVL_MAX msecs_to_jiffies(86400000) /* 24 hours */ +#define BR_MULTICAST_STARTUP_QUERY_INTVL_MAX BR_MULTICAST_QUERY_INTVL_MAX #define BR_HWDOM_MAX BITS_PER_LONG diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 60f28e4fb5c0..4fd5a6ea26b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -43,6 +43,7 @@ config NF_CONNTRACK_BRIDGE config BRIDGE_NF_EBTABLES_LEGACY tristate "Legacy EBTABLES support" depends on BRIDGE && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help Legacy ebtables packet/frame classifier. diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..93a25d87b86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3779,6 +3779,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, features &= ~NETIF_F_TSO_MANGLEID; } + /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, + * so neither does TSO that depends on it. + */ + if (features & NETIF_F_IPV6_CSUM && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) + features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); + return features; } @@ -6999,7 +7011,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7033,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -7353,8 +7369,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ - if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = NETDEV_NAPI_THREADED_DISABLED; + if (napi_get_threaded_config(dev, napi)) + if (napi_kthread_create(napi)) + dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); @@ -11873,6 +11890,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) diff --git a/net/core/dev.h b/net/core/dev.h index ab69edc0c3e3..d6b08d435479 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -323,6 +323,14 @@ static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n) return NETDEV_NAPI_THREADED_DISABLED; } +static inline enum netdev_napi_threaded +napi_get_threaded_config(struct net_device *dev, struct napi_struct *n) +{ + if (n->config) + return n->config->threaded; + return dev->threaded; +} + int napi_set_threaded(struct napi_struct *n, enum netdev_napi_threaded threaded); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 05e2e22a8f7c..343a6cac21e3 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1201,6 +1201,35 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } +/** + * page_pool_enable_direct_recycling() - mark page pool as owned by NAPI + * @pool: page pool to modify + * @napi: NAPI instance to associate the page pool with + * + * Associate a page pool with a NAPI instance for lockless page recycling. + * This is useful when a new page pool has to be added to a NAPI instance + * without disabling that NAPI instance, to mark the point at which control + * path "hands over" the page pool to the NAPI instance. In most cases driver + * can simply set the @napi field in struct page_pool_params, and does not + * have to call this helper. + * + * The function is idempotent, but does not implement any refcounting. + * Single page_pool_disable_direct_recycling() will disable recycling, + * no matter how many times enable was called. + */ +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi) +{ + if (READ_ONCE(pool->p.napi) == napi) + return; + WARN_ON(!napi || pool->p.napi); + + mutex_lock(&page_pools_lock); + WRITE_ONCE(pool->p.napi, napi); + mutex_unlock(&page_pools_lock); +} +EXPORT_SYMBOL(page_pool_enable_direct_recycling); + void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. diff --git a/net/devlink/port.c b/net/devlink/port.c index 939081a0e615..cb8d4df61619 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1519,7 +1519,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!devlink_port->attrs_set) + if (!devlink_port->attrs_set || devlink_port->attrs.no_phys_port_name) return -EOPNOTSUPP; switch (attrs->flavour) { diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index b87b6a6fe070..102eccf5ead7 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -63,8 +63,14 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || - protocol == htons(ETH_P_HSR)) + protocol == htons(ETH_P_HSR)) { + if (!pskb_may_pull(skb, ETH_HLEN + HSR_HLEN)) { + kfree_skb(skb); + goto finish_consume; + } + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + } skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2c438b140e88..7dc9772fe2d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -14,6 +14,7 @@ config NF_DEFRAG_IPV4 config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. @@ -326,6 +327,7 @@ endif # IP_NF_IPTABLES config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help arptables is a legacy packet classifier. @@ -343,6 +345,7 @@ config IP_NF_ARPFILTER select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 87fd945a0d27..0d3cb2ba6fc8 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -247,8 +247,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (!oth) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(oldskb) < 0) + if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -321,8 +320,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 5128e2a5b00a..b1f3fd302e9d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -217,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 276860f65baa..81daf82ddc2d 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -10,6 +10,7 @@ menu "IPv6: Netfilter Configuration" config IP6_NF_IPTABLES_LEGACY tristate "Legacy IP6 tables support" depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help ip6tables is a legacy packet classifier. diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 838295fa32e3..cb2d38e80de9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; - if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) { + if (!skb_dst(oldskb)) { nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); if (!dst) return; @@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; - if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) && - nf_reject6_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0) return; icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index f78ecb6ad838..fd58426f222b 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -35,6 +35,7 @@ #include <net/xfrm.h> #include <crypto/hash.h> +#include <crypto/utils.h> #include <net/seg6.h> #include <net/genetlink.h> #include <net/seg6_hmac.h> @@ -280,7 +281,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output)) return false; - if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0) + if (crypto_memneq(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN)) return false; return true; @@ -304,6 +305,9 @@ int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo) struct seg6_pernet_data *sdata = seg6_pernet(net); int err; + if (!__hmac_get_algo(hinfo->alg_id)) + return -EINVAL; + err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node, rht_params); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 5120a763da0d..0a0eeaed0591 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a4971e6fa943..b4f01cb07561 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -430,7 +430,7 @@ static void psock_write_space(struct sock *sk) /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm && !unlikely(kcm->tx_stopped)) + if (kcm) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1693,12 +1693,6 @@ static int kcm_release(struct socket *sock) */ __skb_queue_purge(&sk->sk_write_queue); - /* Set tx_stopped. This is checked when psock is bound to a kcm and we - * get a writespace callback. This prevents further work being queued - * from the callback (unbinding the psock occurs after canceling work. - */ - kcm->tx_stopped = 1; - release_sock(sk); spin_lock_bh(&mux->lock); @@ -1714,7 +1708,7 @@ static int kcm_release(struct socket *sock) /* Cancel work. After this point there should be no outside references * to the kcm socket. */ - cancel_work_sync(&kcm->tx_work); + disable_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index fb6b46a952cb..69a3ccfc6310 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -1586,7 +1586,6 @@ static void mctp_test_bind_lookup(struct kunit *test) cleanup: kfree_skb(skb_sock); - kfree_skb(skb_pkt); /* Drop all binds */ for (size_t i = 0; i < ARRAY_SIZE(lookup_binds); i++) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 70c0ab0ecf90..2a8ea28442b2 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1118,7 +1118,9 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -/* Return false if a subflow has been reset, else return true */ +/* Return false in case of error (or subflow has been reset), + * else return true. + */ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -1222,7 +1224,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return true; + return false; memset(mpext, 0, sizeof(*mpext)); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 420d416e2603..136a380602ca 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -274,6 +274,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; + unsigned int timeout; pr_debug("msk=%p\n", msk); @@ -291,6 +292,10 @@ static void mptcp_pm_add_timer(struct timer_list *timer) goto out; } + timeout = mptcp_get_add_addr_timeout(sock_net(sk)); + if (!timeout) + goto out; + spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { @@ -302,7 +307,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) sk_reset_timer(sk, timer, - jiffies + mptcp_get_add_addr_timeout(sock_net(sk))); + jiffies + timeout); spin_unlock_bh(&msk->pm.lock); @@ -344,6 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + unsigned int timeout; lockdep_assert_held(&msk->pm.lock); @@ -353,9 +359,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); - return true; + goto reset_timer; } add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); @@ -369,8 +373,10 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry->retrans_times = 0; timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); +reset_timer: + timeout = mptcp_get_add_addr_timeout(net); + if (timeout) + sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout); return true; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index d39e7c178460..667803d72b64 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1085,7 +1085,6 @@ static void __flush_addrs(struct list_head *list) static void __reset_counters(struct pm_nl_pernet *pernet) { WRITE_ONCE(pernet->add_addr_signal_max, 0); - WRITE_ONCE(pernet->add_addr_accept_max, 0); WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f821ad2e19b3..15049b826732 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -265,7 +265,8 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, } set_user_nice(kd->task, sysctl_est_nice(ipvs)); - set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + if (sysctl_est_preferred_cpulist(ipvs)) + kthread_affine_preferred(kd->task, sysctl_est_preferred_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 486d52b45fe5..50fd6809380f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -884,8 +884,6 @@ errout: static int ctnetlink_done(struct netlink_callback *cb) { - if (cb->args[1]) - nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } @@ -1208,19 +1206,26 @@ ignore_entry: return 0; } +static unsigned long ctnetlink_get_id(const struct nf_conn *ct) +{ + unsigned long id = nf_ct_get_id(ct); + + return id ? id : 1; +} + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); - struct nf_conn *ct, *last; + unsigned long last_id = cb->args[1]; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; + struct nf_conn *ct; int res, i; spinlock_t *lockp; - last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); @@ -1257,7 +1262,7 @@ restart: continue; if (cb->args[1]) { - if (ct != last) + if (ctnetlink_get_id(ct) != last_id) continue; cb->args[1] = 0; } @@ -1270,8 +1275,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; + cb->args[1] = ctnetlink_get_id(ct); spin_unlock(lockp); goto out; } @@ -1284,12 +1288,10 @@ restart: } out: local_bh_enable(); - if (last) { + if (last_id) { /* nf ct hash resize happened, now clear the leftover. */ - if ((struct nf_conn *)cb->args[1] == last) + if (cb->args[1] == last_id) cb->args[1] = 0; - - nf_ct_put(last); } while (i) { @@ -3168,23 +3170,27 @@ errout: return 0; } #endif -static int ctnetlink_exp_done(struct netlink_callback *cb) + +static unsigned long ctnetlink_exp_id(const struct nf_conntrack_expect *exp) { - if (cb->args[1]) - nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); - return 0; + unsigned long id = (unsigned long)exp; + + id += nf_ct_get_id(exp->master); + id += exp->class; + + return id ? id : 1; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], @@ -3196,7 +3202,7 @@ restart: continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3205,9 +3211,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3218,32 +3222,30 @@ restart: } out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; if (cb->args[0]) return 0; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; + restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3251,9 +3253,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3264,9 +3264,6 @@ restart: cb->args[0] = 1; out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } @@ -3285,7 +3282,6 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, - .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, @@ -3335,7 +3331,6 @@ static int ctnetlink_get_expect(struct sk_buff *skb, else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, - .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b8b10a85233..1f14ef0436c6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -567,16 +567,16 @@ nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, return ret; if (*(u8 *)table->data == 0) - return ret; + return 0; /* Load nf_log_syslog only if no logger is currently registered */ for (i = 0; i < NFPROTO_NUMPROTO; i++) { if (nf_log_is_registered(i)) - return ret; + return 0; } request_module("%s", "nf_log_syslog"); - return ret; + return 0; } static struct ctl_table_header *nf_ct_netfilter_header; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 13d0ed9d1895..58c5425d61c2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2803,6 +2803,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats __percpu *stats = NULL; + struct nftables_pernet *nft_net; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -2845,6 +2846,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); nft_netdev_hook_free(h); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWCHAIN || + trans->table != ctx->table || + !nft_trans_chain_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_chain_hooks(trans), h)) { + nft_chain_release_hook(&hook); + return -EEXIST; + } } } } else { @@ -9060,6 +9075,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + struct nftables_pernet *nft_net; struct nft_hook *hook, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -9076,6 +9092,20 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); nft_netdev_hook_free(hook); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWFLOWTABLE || + trans->table != ctx->table || + !nft_trans_flowtable_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_flowtable_hooks(trans), hook)) { + err = -EEXIST; + goto err_flowtable_update_hook; + } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 1a19649c2851..9a10251228fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -426,10 +426,9 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m, local_bh_disable(); - if (unlikely(!raw_cpu_ptr(m->scratch))) - goto out; - scratch = *raw_cpu_ptr(m->scratch); + if (unlikely(!scratch)) + goto out; map_index = scratch->map_index; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index db5d367e43c4..2f090e253caf 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1150,12 +1150,12 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); + const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - const struct nft_set_ext *ext; unsigned long *res, *fill; bool map_index; int i; @@ -1246,13 +1246,13 @@ next_match: goto out; if (last) { - ext = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(ext) || - !nft_set_elem_active(ext, genmask))) { - ext = NULL; + const struct nft_set_ext *e = &f->mt[ret].e->ext; + + if (unlikely(nft_set_elem_expired(e) || + !nft_set_elem_active(e, genmask))) goto next_match; - } + ext = e; goto out; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 35d0409b0095..36affbb697c2 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -217,7 +217,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, level += err; /* Implies a giant cgroup tree */ - if (WARN_ON_ONCE(level > 255)) + if (level > 255) return -EOPNOTSUPP; priv->level = level; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index dbcfb948c867..32bacfc314c2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1750,7 +1750,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; - u32 idx; + u32 idx, tin; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); @@ -1760,6 +1760,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; } + tin = (u32)(b - q->tins); idx--; flow = &b->flows[idx]; @@ -1927,13 +1928,22 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { + bool same_flow = false; u32 dropped = 0; + u32 drop_id; while (q->buffer_used > q->buffer_limit) { dropped++; - cake_drop(sch, to_free); + drop_id = cake_drop(sch, to_free); + + if ((drop_id >> 16) == tin && + (drop_id & 0xFFFF) == idx) + same_flow = true; } b->drop_overlimit += dropped; + + if (same_flow) + return NET_XMIT_CN; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c93761040c6e..fa0314679e43 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -101,9 +101,9 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, @@ -142,15 +142,17 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 845375ebd4ea..4b975feb52b1 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -927,7 +927,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, q->sch = sch; dualpi2_reset_default(sch); - hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); if (opt && nla_len(opt)) { err = dualpi2_change(sch, opt, extack); @@ -937,7 +938,7 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, } hrtimer_start(&q->pi2_timer, next_pi2_timeout(q), - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); return 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 037f764822b9..82635dd2cfa5 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -651,6 +651,12 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { @@ -658,11 +664,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } - for (i = q->nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del_init(&q->classes[i].alist); - qdisc_purge_queue(q->classes[i].qdisc); - } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 902ff5470607..fee922da2f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1013,11 +1013,11 @@ static int fq_load_priomap(struct fq_sched_data *q, static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; - int err, drop_count = 0; - unsigned drop_len = 0; u32 fq_log; + int err; err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, NULL); @@ -1135,16 +1135,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = fq_resize(sch, fq_log); sch_tree_lock(sch); } + while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; - drop_len += qdisc_pkt_len(skb); + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - drop_count++; } - qdisc_tree_reduce_backlog(sch, drop_count, drop_len); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 2a0f3a513bfa..a14142392939 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -366,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; u32 quantum = 0; @@ -443,13 +444,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->memory_usage > q->memory_limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - q->cstats.drop_len += qdisc_pkt_len(skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - q->cstats.drop_count++; } - qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); - q->cstats.drop_count = 0; - q->cstats.drop_len = 0; + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b0e34daf1f75..7b96bc3ff891 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -287,10 +287,9 @@ begin: static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; - unsigned int len_dropped = 0; - unsigned int num_dropped = 0; int err; err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); @@ -368,11 +367,14 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - len_dropped += qdisc_pkt_len(skb); - num_dropped += 1; + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 5aa434b46707..2d4855e28a28 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -508,9 +508,9 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { static int hhf_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -561,15 +561,17 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, usecs_to_jiffies(us)); } - qlen = sch->q.qlen; - prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, - prev_backlog - sch->qstats.backlog); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c968ea763774..b5e40c51655a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -592,7 +592,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index ad46ee3ed5a9..0a377313b6a9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -141,9 +141,9 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { static int pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, @@ -193,15 +193,17 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2dc2666988fb..7e99894778d4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -117,7 +117,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!is_gso && skb_linearize(skb)) || + if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9311c38f7abe..e0e48f24cd61 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2568,8 +2568,9 @@ static void smc_listen_work(struct work_struct *work) goto out_decl; } - smc_listen_out_connected(new_smc); SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); + /* smc_listen_out() will release smcsk */ + smc_listen_out_connected(new_smc); goto out_free; out_unlock: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 46c156b121db..e2c5e0e626f9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg, } static int -svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags) { union { struct cmsghdr cmsg; u8 buf[CMSG_SPACE(sizeof(u8))]; } u; - struct socket *sock = svsk->sk_sock; + u8 alert[2]; + struct kvec alert_kvec = { + .iov_base = alert, + .iov_len = sizeof(alert), + }; + struct msghdr msg = { + .msg_flags = *msg_flags, + .msg_control = &u, + .msg_controllen = sizeof(u), + }; + int ret; + + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, + alert_kvec.iov_len); + ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT); + if (ret > 0 && + tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { + iov_iter_revert(&msg.msg_iter, ret); + ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN); + } + return ret; +} + +static int +svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg) +{ int ret; + struct socket *sock = svsk->sk_sock; - msg->msg_control = &u; - msg->msg_controllen = sizeof(u); ret = sock_recvmsg(sock, msg, MSG_DONTWAIT); - if (unlikely(msg->msg_controllen != sizeof(u))) - ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret); + if (msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR); + if (ret == 0 || ret == -EIO) + ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags); + } return ret; } @@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; diff --git a/net/tls/tls.h b/net/tls/tls.h index 774859b63f0d..4e077068e6d9 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -196,7 +196,7 @@ void tls_strp_msg_done(struct tls_strparser *strp); int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb); void tls_rx_msg_ready(struct tls_strparser *strp); -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); int tls_strp_msg_cow(struct tls_sw_context_rx *ctx); struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx); int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 095cf31bae0b..d71643b494a1 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -475,7 +475,7 @@ static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) strp->stm.offset = offset; } -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) { struct strp_msg *rxm; struct tls_msg *tlm; @@ -484,8 +484,11 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) DEBUG_NET_WARN_ON_ONCE(!strp->stm.full_len); if (!strp->copy_mode && force_refresh) { - if (WARN_ON(tcp_inq(strp->sk) < strp->stm.full_len)) - return; + if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) { + WRITE_ONCE(strp->msg_ready, 0); + memset(&strp->stm, 0, sizeof(strp->stm)); + return false; + } tls_strp_load_anchor_with_queue(strp, strp->stm.full_len); } @@ -495,6 +498,8 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) rxm->offset = strp->stm.offset; tlm = tls_msg(strp->anchor); tlm->control = strp->mark; + + return true; } /* Called with lock held on lower socket */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 549d1ea01a72..bac65d0d4e3e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1384,7 +1384,8 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, return sock_intr_errno(timeo); } - tls_strp_msg_load(&ctx->strp, released); + if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) + return tls_rx_rec_wait(sk, psock, nonblock, false); return 1; } @@ -1807,6 +1808,9 @@ int decrypt_skb(struct sock *sk, struct scatterlist *sgout) return tls_decrypt_sg(sk, NULL, sgout, &darg); } +/* All records returned from a recvmsg() call must have the same type. + * 0 is not a valid content type. Use it as "no type reported, yet". + */ static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm, u8 *control) { @@ -2050,8 +2054,10 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto end; + /* process_rx_list() will set @control if it processed any records */ copied = err; - if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) + if (len <= copied || rx_more || + (control && control != TLS_RECORD_TYPE_DATA)) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ead6a3c14b87..bebb355f3ffe 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -689,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port <= LAST_RESERVED_PORT) + if (port == VMADDR_PORT_ANY || + port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index d2819baea414..c7a1f080d2de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -155,7 +155,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(xmit_xfrm_check_overflow(skb))) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ @@ -415,10 +416,12 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct net_device *dev = x->xso.dev; bool check_tunnel_size; - if (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; - if ((dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { + if ((!dev || dev == xfrm_dst_path(dst)->dev) && + !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; @@ -430,6 +433,9 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) return false; ok: + if (!dev) + return true; + check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (x->props.family) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77db3b5fe4ac..78fcbb89cf32 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3297,7 +3297,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/rust/Makefile b/rust/Makefile index 4263462b8470..bfa915b0e588 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -65,6 +65,10 @@ core-cfgs = \ core-edition := $(if $(call rustc-min-version,108700),2024,2021) +# `rustdoc` did not save the target modifiers, thus workaround for +# the time being (https://github.com/rust-lang/rust/issues/144521). +rustdoc_modifiers_workaround := $(if $(call rustc-min-version,108800),-Cunsafe-allow-abi-mismatch=fixed-x18) + # `rustc` recognizes `--remap-path-prefix` since 1.26.0, but `rustdoc` only # since Rust 1.81.0. Moreover, `rustdoc` ICEs on out-of-tree builds since Rust # 1.82.0 (https://github.com/rust-lang/rust/issues/138520). Thus workaround both @@ -77,6 +81,7 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< -Zunstable-options --generate-link-to-definition \ --output $(rustdoc_output) \ --crate-name $(subst rustdoc-,,$@) \ + $(rustdoc_modifiers_workaround) \ $(if $(rustdoc_host),,--sysroot=/dev/null) \ @$(objtree)/include/generated/rustc_cfg $< @@ -106,14 +111,14 @@ rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \ rustdoc-macros: private rustdoc_host = yes rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \ --extern proc_macro -rustdoc-macros: $(src)/macros/lib.rs FORCE +rustdoc-macros: $(src)/macros/lib.rs rustdoc-clean FORCE +$(call if_changed,rustdoc) # Starting with Rust 1.82.0, skipping `-Wrustdoc::unescaped_backticks` should # not be needed -- see https://github.com/rust-lang/rust/pull/128307. rustdoc-core: private skip_flags = --edition=2021 -Wrustdoc::unescaped_backticks rustdoc-core: private rustc_target_flags = --edition=$(core-edition) $(core-cfgs) -rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE +rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs rustdoc-clean FORCE +$(call if_changed,rustdoc) rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE @@ -125,7 +130,8 @@ rustdoc-ffi: $(src)/ffi.rs rustdoc-core FORCE rustdoc-pin_init_internal: private rustdoc_host = yes rustdoc-pin_init_internal: private rustc_target_flags = --cfg kernel \ --extern proc_macro --crate-type proc-macro -rustdoc-pin_init_internal: $(src)/pin-init/internal/src/lib.rs FORCE +rustdoc-pin_init_internal: $(src)/pin-init/internal/src/lib.rs \ + rustdoc-clean FORCE +$(call if_changed,rustdoc) rustdoc-pin_init: private rustdoc_host = yes @@ -143,6 +149,9 @@ rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-ffi rustdoc-macros \ $(obj)/bindings.o FORCE +$(call if_changed,rustdoc) +rustdoc-clean: FORCE + $(Q)rm -rf $(rustdoc_output) + quiet_cmd_rustc_test_library = $(RUSTC_OR_CLIPPY_QUIET) TL $< cmd_rustc_test_library = \ OBJTREE=$(abspath $(objtree)) \ @@ -215,6 +224,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< --extern bindings --extern uapi \ --no-run --crate-name kernel -Zunstable-options \ --sysroot=/dev/null \ + $(rustdoc_modifiers_workaround) \ --test-builder $(objtree)/scripts/rustdoc_test_builder \ $< $(rustdoc_test_kernel_quiet); \ $(objtree)/scripts/rustdoc_test_gen diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 84d60635e8a9..9b3a4ab95818 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -50,6 +50,7 @@ #include <linux/dma-mapping.h> #include <linux/errname.h> #include <linux/ethtool.h> +#include <linux/fdtable.h> #include <linux/file.h> #include <linux/firmware.h> #include <linux/fs.h> @@ -71,6 +72,7 @@ #include <linux/sched.h> #include <linux/security.h> #include <linux/slab.h> +#include <linux/task_work.h> #include <linux/tracepoint.h> #include <linux/wait.h> #include <linux/workqueue.h> @@ -99,3 +101,9 @@ const xa_mark_t RUST_CONST_HELPER_XA_PRESENT = XA_PRESENT; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC1 = XA_FLAGS_ALLOC1; + +#if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_RUST) +#include "../../drivers/android/binder/rust_binder.h" +#include "../../drivers/android/binder/rust_binder_events.h" +#include "../../drivers/android/binder/page_range_helper.h" +#endif diff --git a/rust/helpers/binder.c b/rust/helpers/binder.c new file mode 100644 index 000000000000..224d38a92f1d --- /dev/null +++ b/rust/helpers/binder.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2025 Google LLC. + */ + +#include <linux/list_lru.h> +#include <linux/task_work.h> + +unsigned long rust_helper_list_lru_count(struct list_lru *lru) +{ + return list_lru_count(lru); +} + +unsigned long rust_helper_list_lru_walk(struct list_lru *lru, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long nr_to_walk) +{ + return list_lru_walk(lru, isolate, cb_arg, nr_to_walk); +} + +void rust_helper_init_task_work(struct callback_head *twork, + task_work_func_t func) +{ + init_task_work(twork, func); +} diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index 7cf7fe95e41d..8e8277bdddca 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -8,6 +8,7 @@ */ #include "auxiliary.c" +#include "binder.c" #include "blk.c" #include "bug.c" #include "build_assert.c" diff --git a/rust/helpers/page.c b/rust/helpers/page.c index b3f2b8fbf87f..7144de5a61db 100644 --- a/rust/helpers/page.c +++ b/rust/helpers/page.c @@ -2,6 +2,7 @@ #include <linux/gfp.h> #include <linux/highmem.h> +#include <linux/mm.h> struct page *rust_helper_alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -17,3 +18,10 @@ void rust_helper_kunmap_local(const void *addr) { kunmap_local(addr); } + +#ifndef NODE_NOT_IN_PAGE_FLAGS +int rust_helper_page_to_nid(const struct page *page) +{ + return page_to_nid(page); +} +#endif diff --git a/rust/helpers/security.c b/rust/helpers/security.c index 0c4c2065df28..ca22da09548d 100644 --- a/rust/helpers/security.c +++ b/rust/helpers/security.c @@ -17,4 +17,28 @@ void rust_helper_security_release_secctx(struct lsm_context *cp) { security_release_secctx(cp); } + +int rust_helper_security_binder_set_context_mgr(const struct cred *mgr) +{ + return security_binder_set_context_mgr(mgr); +} + +int rust_helper_security_binder_transaction(const struct cred *from, + const struct cred *to) +{ + return security_binder_transaction(from, to); +} + +int rust_helper_security_binder_transfer_binder(const struct cred *from, + const struct cred *to) +{ + return security_binder_transfer_binder(from, to); +} + +int rust_helper_security_binder_transfer_file(const struct cred *from, + const struct cred *to, + const struct file *file) +{ + return security_binder_transfer_file(from, to, file); +} #endif diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs index aa2dfa9dca4c..2692cf90c948 100644 --- a/rust/kernel/alloc/allocator.rs +++ b/rust/kernel/alloc/allocator.rs @@ -43,17 +43,6 @@ pub struct Vmalloc; /// For more details see [self]. pub struct KVmalloc; -/// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment. -fn aligned_size(new_layout: Layout) -> usize { - // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first. - let layout = new_layout.pad_to_align(); - - // Note that `layout.size()` (after padding) is guaranteed to be a multiple of `layout.align()` - // which together with the slab guarantees means the `krealloc` will return a properly aligned - // object (see comments in `kmalloc()` for more information). - layout.size() -} - /// # Invariants /// /// One of the following: `krealloc`, `vrealloc`, `kvrealloc`. @@ -88,7 +77,7 @@ impl ReallocFunc { old_layout: Layout, flags: Flags, ) -> Result<NonNull<[u8]>, AllocError> { - let size = aligned_size(layout); + let size = layout.size(); let ptr = match ptr { Some(ptr) => { if old_layout.size() == 0 { @@ -123,6 +112,17 @@ impl ReallocFunc { } } +impl Kmalloc { + /// Returns a [`Layout`] that makes [`Kmalloc`] fulfill the requested size and alignment of + /// `layout`. + pub fn aligned_layout(layout: Layout) -> Layout { + // Note that `layout.size()` (after padding) is guaranteed to be a multiple of + // `layout.align()` which together with the slab guarantees means that `Kmalloc` will return + // a properly aligned object (see comments in `kmalloc()` for more information). + layout.pad_to_align() + } +} + // SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that // - memory remains valid until it is explicitly freed, // - passing a pointer to a valid memory allocation is OK, @@ -135,6 +135,8 @@ unsafe impl Allocator for Kmalloc { old_layout: Layout, flags: Flags, ) -> Result<NonNull<[u8]>, AllocError> { + let layout = Kmalloc::aligned_layout(layout); + // SAFETY: `ReallocFunc::call` has the same safety requirements as `Allocator::realloc`. unsafe { ReallocFunc::KREALLOC.call(ptr, layout, old_layout, flags) } } @@ -176,6 +178,10 @@ unsafe impl Allocator for KVmalloc { old_layout: Layout, flags: Flags, ) -> Result<NonNull<[u8]>, AllocError> { + // `KVmalloc` may use the `Kmalloc` backend, hence we have to enforce a `Kmalloc` + // compatible layout. + let layout = Kmalloc::aligned_layout(layout); + // TODO: Support alignments larger than PAGE_SIZE. if layout.align() > bindings::PAGE_SIZE { pr_warn!("KVmalloc does not support alignments larger than PAGE_SIZE yet.\n"); diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs index a3074480bd8d..90dd987d40e4 100644 --- a/rust/kernel/alloc/allocator_test.rs +++ b/rust/kernel/alloc/allocator_test.rs @@ -22,6 +22,17 @@ pub type Kmalloc = Cmalloc; pub type Vmalloc = Kmalloc; pub type KVmalloc = Kmalloc; +impl Cmalloc { + /// Returns a [`Layout`] that makes [`Kmalloc`] fulfill the requested size and alignment of + /// `layout`. + pub fn aligned_layout(layout: Layout) -> Layout { + // Note that `layout.size()` (after padding) is guaranteed to be a multiple of + // `layout.align()` which together with the slab guarantees means that `Kmalloc` will return + // a properly aligned object (see comments in `kmalloc()` for more information). + layout.pad_to_align() + } +} + extern "C" { #[link_name = "aligned_alloc"] fn libc_aligned_alloc(align: usize, size: usize) -> *mut crate::ffi::c_void; diff --git a/rust/kernel/cred.rs b/rust/kernel/cred.rs index 2599f01e8b28..3aa2e4c4a50c 100644 --- a/rust/kernel/cred.rs +++ b/rust/kernel/cred.rs @@ -54,6 +54,12 @@ impl Credential { unsafe { &*ptr.cast() } } + /// Returns a raw pointer to the inner credential. + #[inline] + pub fn as_ptr(&self) -> *const bindings::cred { + self.0.get() + } + /// Get the id for this security context. #[inline] pub fn get_secid(&self) -> u32 { diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index b8613289de8e..5902b3714a16 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -15,23 +15,130 @@ use crate::c_str; pub mod property; -/// A reference-counted device. +/// The core representation of a device in the kernel's driver model. /// -/// This structure represents the Rust abstraction for a C `struct device`. This implementation -/// abstracts the usage of an already existing C `struct device` within Rust code that we get -/// passed from the C side. +/// This structure represents the Rust abstraction for a C `struct device`. A [`Device`] can either +/// exist as temporary reference (see also [`Device::from_raw`]), which is only valid within a +/// certain scope or as [`ARef<Device>`], owning a dedicated reference count. /// -/// An instance of this abstraction can be obtained temporarily or permanent. +/// # Device Types /// -/// A temporary one is bound to the lifetime of the C `struct device` pointer used for creation. -/// A permanent instance is always reference-counted and hence not restricted by any lifetime -/// boundaries. +/// A [`Device`] can represent either a bus device or a class device. /// -/// For subsystems it is recommended to create a permanent instance to wrap into a subsystem -/// specific device structure (e.g. `pci::Device`). This is useful for passing it to drivers in -/// `T::probe()`, such that a driver can store the `ARef<Device>` (equivalent to storing a -/// `struct device` pointer in a C driver) for arbitrary purposes, e.g. allocating DMA coherent -/// memory. +/// ## Bus Devices +/// +/// A bus device is a [`Device`] that is associated with a physical or virtual bus. Examples of +/// buses include PCI, USB, I2C, and SPI. Devices attached to a bus are registered with a specific +/// bus type, which facilitates matching devices with appropriate drivers based on IDs or other +/// identifying information. Bus devices are visible in sysfs under `/sys/bus/<bus-name>/devices/`. +/// +/// ## Class Devices +/// +/// A class device is a [`Device`] that is associated with a logical category of functionality +/// rather than a physical bus. Examples of classes include block devices, network interfaces, sound +/// cards, and input devices. Class devices are grouped under a common class and exposed to +/// userspace via entries in `/sys/class/<class-name>/`. +/// +/// # Device Context +/// +/// [`Device`] references are generic over a [`DeviceContext`], which represents the type state of +/// a [`Device`]. +/// +/// As the name indicates, this type state represents the context of the scope the [`Device`] +/// reference is valid in. For instance, the [`Bound`] context guarantees that the [`Device`] is +/// bound to a driver for the entire duration of the existence of a [`Device<Bound>`] reference. +/// +/// Other [`DeviceContext`] types besides [`Bound`] are [`Normal`], [`Core`] and [`CoreInternal`]. +/// +/// Unless selected otherwise [`Device`] defaults to the [`Normal`] [`DeviceContext`], which by +/// itself has no additional requirements. +/// +/// It is always up to the caller of [`Device::from_raw`] to select the correct [`DeviceContext`] +/// type for the corresponding scope the [`Device`] reference is created in. +/// +/// All [`DeviceContext`] types other than [`Normal`] are intended to be used with +/// [bus devices](#bus-devices) only. +/// +/// # Implementing Bus Devices +/// +/// This section provides a guideline to implement bus specific devices, such as [`pci::Device`] or +/// [`platform::Device`]. +/// +/// A bus specific device should be defined as follows. +/// +/// ```ignore +/// #[repr(transparent)] +/// pub struct Device<Ctx: device::DeviceContext = device::Normal>( +/// Opaque<bindings::bus_device_type>, +/// PhantomData<Ctx>, +/// ); +/// ``` +/// +/// Since devices are reference counted, [`AlwaysRefCounted`] should be implemented for `Device` +/// (i.e. `Device<Normal>`). Note that [`AlwaysRefCounted`] must not be implemented for any other +/// [`DeviceContext`], since all other device context types are only valid within a certain scope. +/// +/// In order to be able to implement the [`DeviceContext`] dereference hierarchy, bus device +/// implementations should call the [`impl_device_context_deref`] macro as shown below. +/// +/// ```ignore +/// // SAFETY: `Device` is a transparent wrapper of a type that doesn't depend on `Device`'s +/// // generic argument. +/// kernel::impl_device_context_deref!(unsafe { Device }); +/// ``` +/// +/// In order to convert from a any [`Device<Ctx>`] to [`ARef<Device>`], bus devices can implement +/// the following macro call. +/// +/// ```ignore +/// kernel::impl_device_context_into_aref!(Device); +/// ``` +/// +/// Bus devices should also implement the following [`AsRef`] implementation, such that users can +/// easily derive a generic [`Device`] reference. +/// +/// ```ignore +/// impl<Ctx: device::DeviceContext> AsRef<device::Device<Ctx>> for Device<Ctx> { +/// fn as_ref(&self) -> &device::Device<Ctx> { +/// ... +/// } +/// } +/// ``` +/// +/// # Implementing Class Devices +/// +/// Class device implementations require less infrastructure and depend slightly more on the +/// specific subsystem. +/// +/// An example implementation for a class device could look like this. +/// +/// ```ignore +/// #[repr(C)] +/// pub struct Device<T: class::Driver> { +/// dev: Opaque<bindings::class_device_type>, +/// data: T::Data, +/// } +/// ``` +/// +/// This class device uses the sub-classing pattern to embed the driver's private data within the +/// allocation of the class device. For this to be possible the class device is generic over the +/// class specific `Driver` trait implementation. +/// +/// Just like any device, class devices are reference counted and should hence implement +/// [`AlwaysRefCounted`] for `Device`. +/// +/// Class devices should also implement the following [`AsRef`] implementation, such that users can +/// easily derive a generic [`Device`] reference. +/// +/// ```ignore +/// impl<T: class::Driver> AsRef<device::Device> for Device<T> { +/// fn as_ref(&self) -> &device::Device { +/// ... +/// } +/// } +/// ``` +/// +/// An example for a class device implementation is [`drm::Device`]. /// /// # Invariants /// @@ -42,6 +149,12 @@ pub mod property; /// /// `bindings::device::release` is valid to be called from any thread, hence `ARef<Device>` can be /// dropped from any thread. +/// +/// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted +/// [`drm::Device`]: kernel::drm::Device +/// [`impl_device_context_deref`]: kernel::impl_device_context_deref +/// [`pci::Device`]: kernel::pci::Device +/// [`platform::Device`]: kernel::platform::Device #[repr(transparent)] pub struct Device<Ctx: DeviceContext = Normal>(Opaque<bindings::device>, PhantomData<Ctx>); @@ -311,28 +424,75 @@ unsafe impl Send for Device {} // synchronization in `struct device`. unsafe impl Sync for Device {} -/// Marker trait for the context of a bus specific device. +/// Marker trait for the context or scope of a bus specific device. +/// +/// [`DeviceContext`] is a marker trait for types representing the context of a bus specific +/// [`Device`]. +/// +/// The specific device context types are: [`CoreInternal`], [`Core`], [`Bound`] and [`Normal`]. /// -/// Some functions of a bus specific device should only be called from a certain context, i.e. bus -/// callbacks, such as `probe()`. +/// [`DeviceContext`] types are hierarchical, which means that there is a strict hierarchy that +/// defines which [`DeviceContext`] type can be derived from another. For instance, any +/// [`Device<Core>`] can dereference to a [`Device<Bound>`]. /// -/// This is the marker trait for structures representing the context of a bus specific device. +/// The following enumeration illustrates the dereference hierarchy of [`DeviceContext`] types. +/// +/// - [`CoreInternal`] => [`Core`] => [`Bound`] => [`Normal`] +/// +/// Bus devices can automatically implement the dereference hierarchy by using +/// [`impl_device_context_deref`]. +/// +/// Note that the guarantee for a [`Device`] reference to have a certain [`DeviceContext`] comes +/// from the specific scope the [`Device`] reference is valid in. +/// +/// [`impl_device_context_deref`]: kernel::impl_device_context_deref pub trait DeviceContext: private::Sealed {} -/// The [`Normal`] context is the context of a bus specific device when it is not an argument of -/// any bus callback. +/// The [`Normal`] context is the default [`DeviceContext`] of any [`Device`]. +/// +/// The normal context does not indicate any specific context. Any `Device<Ctx>` is also a valid +/// [`Device<Normal>`]. It is the only [`DeviceContext`] for which it is valid to implement +/// [`AlwaysRefCounted`] for. +/// +/// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted pub struct Normal; -/// The [`Core`] context is the context of a bus specific device when it is supplied as argument of -/// any of the bus callbacks, such as `probe()`. +/// The [`Core`] context is the context of a bus specific device when it appears as argument of +/// any bus specific callback, such as `probe()`. +/// +/// The core context indicates that the [`Device<Core>`] reference's scope is limited to the bus +/// callback it appears in. It is intended to be used for synchronization purposes. Bus device +/// implementations can implement methods for [`Device<Core>`], such that they can only be called +/// from bus callbacks. pub struct Core; -/// Semantically the same as [`Core`] but reserved for internal usage of the corresponding bus +/// Semantically the same as [`Core`], but reserved for internal usage of the corresponding bus /// abstraction. +/// +/// The internal core context is intended to be used in exactly the same way as the [`Core`] +/// context, with the difference that this [`DeviceContext`] is internal to the corresponding bus +/// abstraction. +/// +/// This context mainly exists to share generic [`Device`] infrastructure that should only be called +/// from bus callbacks with bus abstractions, but without making them accessible for drivers. pub struct CoreInternal; -/// The [`Bound`] context is the context of a bus specific device reference when it is guaranteed to -/// be bound for the duration of its lifetime. +/// The [`Bound`] context is the [`DeviceContext`] of a bus specific device when it is guaranteed to +/// be bound to a driver. +/// +/// The bound context indicates that for the entire duration of the lifetime of a [`Device<Bound>`] +/// reference, the [`Device`] is guaranteed to be bound to a driver. +/// +/// Some APIs, such as [`dma::CoherentAllocation`] or [`Devres`] rely on the [`Device`] to be bound, +/// which can be proven with the [`Bound`] device context. +/// +/// Any abstraction that can guarantee a scope where the corresponding bus device is bound, should +/// provide a [`Device<Bound>`] reference to its users for this scope. This allows users to benefit +/// from optimizations for accessing device resources, see also [`Devres::access`]. +/// +/// [`Devres`]: kernel::devres::Devres +/// [`Devres::access`]: kernel::devres::Devres::access +/// [`dma::CoherentAllocation`]: kernel::dma::CoherentAllocation pub struct Bound; mod private { diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs index da18091143a6..d04e3fcebafb 100644 --- a/rust/kernel/devres.rs +++ b/rust/kernel/devres.rs @@ -115,10 +115,11 @@ pub struct Devres<T: Send> { /// Contains all the fields shared with [`Self::callback`]. // TODO: Replace with `UnsafePinned`, once available. // - // Subsequently, the `drop_in_place()` in `Devres::drop` and the explicit `Send` and `Sync' - // impls can be removed. + // Subsequently, the `drop_in_place()` in `Devres::drop` and `Devres::new` as well as the + // explicit `Send` and `Sync' impls can be removed. #[pin] inner: Opaque<Inner<T>>, + _add_action: (), } impl<T: Send> Devres<T> { @@ -140,7 +141,15 @@ impl<T: Send> Devres<T> { dev: dev.into(), callback, // INVARIANT: `inner` is properly initialized. - inner <- { + inner <- Opaque::pin_init(try_pin_init!(Inner { + devm <- Completion::new(), + revoke <- Completion::new(), + data <- Revocable::new(data), + })), + // TODO: Replace with "initializer code blocks" [1] once available. + // + // [1] https://github.com/Rust-for-Linux/pin-init/pull/69 + _add_action: { // SAFETY: `this` is a valid pointer to uninitialized memory. let inner = unsafe { &raw mut (*this.as_ptr()).inner }; @@ -152,13 +161,13 @@ impl<T: Send> Devres<T> { // live at least as long as the returned `impl PinInit<Self, Error>`. to_result(unsafe { bindings::devm_add_action(dev.as_raw(), Some(callback), inner.cast()) - })?; + }).inspect_err(|_| { + let inner = Opaque::cast_into(inner); - Opaque::pin_init(try_pin_init!(Inner { - devm <- Completion::new(), - revoke <- Completion::new(), - data <- Revocable::new(data), - })) + // SAFETY: `inner` is a valid pointer to an `Inner<T>` and valid for both reads + // and writes. + unsafe { core::ptr::drop_in_place(inner) }; + })?; }, }) } diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs index a8f2675ba7a7..279e3af20682 100644 --- a/rust/kernel/driver.rs +++ b/rust/kernel/driver.rs @@ -2,8 +2,93 @@ //! Generic support for drivers of different buses (e.g., PCI, Platform, Amba, etc.). //! -//! Each bus / subsystem is expected to implement [`RegistrationOps`], which allows drivers to -//! register using the [`Registration`] class. +//! This documentation describes how to implement a bus specific driver API and how to align it with +//! the design of (bus specific) devices. +//! +//! Note: Readers are expected to know the content of the documentation of [`Device`] and +//! [`DeviceContext`]. +//! +//! # Driver Trait +//! +//! The main driver interface is defined by a bus specific driver trait. For instance: +//! +//! ```ignore +//! pub trait Driver: Send { +//! /// The type holding information about each device ID supported by the driver. +//! type IdInfo: 'static; +//! +//! /// The table of OF device ids supported by the driver. +//! const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = None; +//! +//! /// The table of ACPI device ids supported by the driver. +//! const ACPI_ID_TABLE: Option<acpi::IdTable<Self::IdInfo>> = None; +//! +//! /// Driver probe. +//! fn probe(dev: &Device<device::Core>, id_info: &Self::IdInfo) -> Result<Pin<KBox<Self>>>; +//! +//! /// Driver unbind (optional). +//! fn unbind(dev: &Device<device::Core>, this: Pin<&Self>) { +//! let _ = (dev, this); +//! } +//! } +//! ``` +//! +//! For specific examples see [`auxiliary::Driver`], [`pci::Driver`] and [`platform::Driver`]. +//! +//! The `probe()` callback should return a `Result<Pin<KBox<Self>>>`, i.e. the driver's private +//! data. The bus abstraction should store the pointer in the corresponding bus device. The generic +//! [`Device`] infrastructure provides common helpers for this purpose on its +//! [`Device<CoreInternal>`] implementation. +//! +//! All driver callbacks should provide a reference to the driver's private data. Once the driver +//! is unbound from the device, the bus abstraction should take back the ownership of the driver's +//! private data from the corresponding [`Device`] and [`drop`] it. +//! +//! All driver callbacks should provide a [`Device<Core>`] reference (see also [`device::Core`]). +//! +//! # Adapter +//! +//! The adapter implementation of a bus represents the abstraction layer between the C bus +//! callbacks and the Rust bus callbacks. It therefore has to be generic over an implementation of +//! the [driver trait](#driver-trait). +//! +//! ```ignore +//! pub struct Adapter<T: Driver>; +//! ``` +//! +//! There's a common [`Adapter`] trait that can be implemented to inherit common driver +//! infrastructure, such as finding the ID info from an [`of::IdTable`] or [`acpi::IdTable`]. +//! +//! # Driver Registration +//! +//! In order to register C driver types (such as `struct platform_driver`) the [adapter](#adapter) +//! should implement the [`RegistrationOps`] trait. +//! +//! This trait implementation can be used to create the actual registration with the common +//! [`Registration`] type. +//! +//! Typically, bus abstractions want to provide a bus specific `module_bus_driver!` macro, which +//! creates a kernel module with exactly one [`Registration`] for the bus specific adapter. +//! +//! The generic driver infrastructure provides a helper for this with the [`module_driver`] macro. +//! +//! # Device IDs +//! +//! Besides the common device ID types, such as [`of::DeviceId`] and [`acpi::DeviceId`], most buses +//! may need to implement their own device ID types. +//! +//! For this purpose the generic infrastructure in [`device_id`] should be used. +//! +//! [`auxiliary::Driver`]: kernel::auxiliary::Driver +//! [`Core`]: device::Core +//! [`Device`]: device::Device +//! [`Device<Core>`]: device::Device<device::Core> +//! [`Device<CoreInternal>`]: device::Device<device::CoreInternal> +//! [`DeviceContext`]: device::DeviceContext +//! [`device_id`]: kernel::device_id +//! [`module_driver`]: kernel::module_driver +//! [`pci::Driver`]: kernel::pci::Driver +//! [`platform::Driver`]: kernel::platform::Driver use crate::error::{Error, Result}; use crate::{acpi, device, of, str::CStr, try_pin_init, types::Opaque, ThisModule}; diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index 3bb7c83966cf..d29c477e89a8 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -5,6 +5,7 @@ //! C header: [`include/linux/drm/drm_device.h`](srctree/include/linux/drm/drm_device.h) use crate::{ + alloc::allocator::Kmalloc, bindings, device, drm, drm::driver::AllocImpl, error::from_err_ptr, @@ -12,7 +13,7 @@ use crate::{ prelude::*, types::{ARef, AlwaysRefCounted, Opaque}, }; -use core::{mem, ops::Deref, ptr, ptr::NonNull}; +use core::{alloc::Layout, mem, ops::Deref, ptr, ptr::NonNull}; #[cfg(CONFIG_DRM_LEGACY)] macro_rules! drm_legacy_fields { @@ -53,10 +54,8 @@ macro_rules! drm_legacy_fields { /// /// `self.dev` is a valid instance of a `struct device`. #[repr(C)] -#[pin_data] pub struct Device<T: drm::Driver> { dev: Opaque<bindings::drm_device>, - #[pin] data: T::Data, } @@ -96,6 +95,10 @@ impl<T: drm::Driver> Device<T> { /// Create a new `drm::Device` for a `drm::Driver`. pub fn new(dev: &device::Device, data: impl PinInit<T::Data, Error>) -> Result<ARef<Self>> { + // `__drm_dev_alloc` uses `kmalloc()` to allocate memory, hence ensure a `kmalloc()` + // compatible `Layout`. + let layout = Kmalloc::aligned_layout(Layout::new::<Self>()); + // SAFETY: // - `VTABLE`, as a `const` is pinned to the read-only section of the compilation, // - `dev` is valid by its type invarants, @@ -103,7 +106,7 @@ impl<T: drm::Driver> Device<T> { bindings::__drm_dev_alloc( dev.as_raw(), &Self::VTABLE, - mem::size_of::<Self>(), + layout.size(), mem::offset_of!(Self, dev), ) } @@ -117,9 +120,13 @@ impl<T: drm::Driver> Device<T> { // - `raw_data` is a valid pointer to uninitialized memory. // - `raw_data` will not move until it is dropped. unsafe { data.__pinned_init(raw_data) }.inspect_err(|_| { - // SAFETY: `__drm_dev_alloc()` was successful, hence `raw_drm` must be valid and the + // SAFETY: `raw_drm` is a valid pointer to `Self`, given that `__drm_dev_alloc` was + // successful. + let drm_dev = unsafe { Self::into_drm_device(raw_drm) }; + + // SAFETY: `__drm_dev_alloc()` was successful, hence `drm_dev` must be valid and the // refcount must be non-zero. - unsafe { bindings::drm_dev_put(ptr::addr_of_mut!((*raw_drm.as_ptr()).dev).cast()) }; + unsafe { bindings::drm_dev_put(drm_dev) }; })?; // SAFETY: The reference count is one, and now we take ownership of that reference as a @@ -140,6 +147,14 @@ impl<T: drm::Driver> Device<T> { unsafe { crate::container_of!(Opaque::cast_from(ptr), Self, dev) }.cast_mut() } + /// # Safety + /// + /// `ptr` must be a valid pointer to `Self`. + unsafe fn into_drm_device(ptr: NonNull<Self>) -> *mut bindings::drm_device { + // SAFETY: By the safety requirements of this function, `ptr` is a valid pointer to `Self`. + unsafe { &raw mut (*ptr.as_ptr()).dev }.cast() + } + /// Not intended to be called externally, except via declare_drm_ioctls!() /// /// # Safety @@ -189,8 +204,11 @@ unsafe impl<T: drm::Driver> AlwaysRefCounted for Device<T> { } unsafe fn dec_ref(obj: NonNull<Self>) { + // SAFETY: `obj` is a valid pointer to `Self`. + let drm_dev = unsafe { Self::into_drm_device(obj) }; + // SAFETY: The safety requirements guarantee that the refcount is non-zero. - unsafe { bindings::drm_dev_put(obj.cast().as_ptr()) }; + unsafe { bindings::drm_dev_put(drm_dev) }; } } diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs index 7a906099993f..7fe2dd197e37 100644 --- a/rust/kernel/faux.rs +++ b/rust/kernel/faux.rs @@ -4,7 +4,7 @@ //! //! This module provides bindings for working with faux devices in kernel modules. //! -//! C header: [`include/linux/device/faux.h`] +//! C header: [`include/linux/device/faux.h`](srctree/include/linux/device/faux.h) use crate::{bindings, device, error::code::*, prelude::*}; use core::ptr::{addr_of_mut, null, null_mut, NonNull}; diff --git a/rust/kernel/fs.rs b/rust/kernel/fs.rs index 0121b38c59e6..6ba6bdf143cb 100644 --- a/rust/kernel/fs.rs +++ b/rust/kernel/fs.rs @@ -6,3 +6,6 @@ pub mod file; pub use self::file::{File, LocalFile}; + +mod kiocb; +pub use self::kiocb::Kiocb; diff --git a/rust/kernel/fs/kiocb.rs b/rust/kernel/fs/kiocb.rs new file mode 100644 index 000000000000..84c936cd69b0 --- /dev/null +++ b/rust/kernel/fs/kiocb.rs @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! Kernel IO callbacks. +//! +//! C headers: [`include/linux/fs.h`](srctree/include/linux/fs.h) + +use core::marker::PhantomData; +use core::ptr::NonNull; +use kernel::types::ForeignOwnable; + +/// Wrapper for the kernel's `struct kiocb`. +/// +/// Currently this abstractions is incomplete and is essentially just a tuple containing a +/// reference to a file and a file position. +/// +/// The type `T` represents the filesystem or driver specific data associated with the file. +/// +/// # Invariants +/// +/// `inner` points at a valid `struct kiocb` whose file has the type `T` as its private data. +pub struct Kiocb<'a, T> { + inner: NonNull<bindings::kiocb>, + _phantom: PhantomData<&'a T>, +} + +impl<'a, T: ForeignOwnable> Kiocb<'a, T> { + /// Create a `Kiocb` from a raw pointer. + /// + /// # Safety + /// + /// The pointer must reference a valid `struct kiocb` for the duration of `'a`. The private + /// data of the file must be `T`. + pub unsafe fn from_raw(kiocb: *mut bindings::kiocb) -> Self { + Self { + // SAFETY: If a pointer is valid it is not null. + inner: unsafe { NonNull::new_unchecked(kiocb) }, + _phantom: PhantomData, + } + } + + /// Access the underlying `struct kiocb` directly. + pub fn as_raw(&self) -> *mut bindings::kiocb { + self.inner.as_ptr() + } + + /// Get the filesystem or driver specific data associated with the file. + pub fn file(&self) -> <T as ForeignOwnable>::Borrowed<'a> { + // SAFETY: We have shared access to this kiocb and hence the underlying file, so we can + // read the file's private data. + let private = unsafe { (*(*self.as_raw()).ki_filp).private_data }; + // SAFETY: The kiocb has shared access to the private data. + unsafe { <T as ForeignOwnable>::borrow(private) } + } + + /// Gets the current value of `ki_pos`. + pub fn ki_pos(&self) -> i64 { + // SAFETY: We have shared access to the kiocb, so we can read its `ki_pos` field. + unsafe { (*self.as_raw()).ki_pos } + } + + /// Gets a mutable reference to the `ki_pos` field. + pub fn ki_pos_mut(&mut self) -> &mut i64 { + // SAFETY: We have exclusive access to the kiocb, so we can write to `ki_pos`. + unsafe { &mut (*self.as_raw()).ki_pos } + } +} diff --git a/rust/kernel/iov.rs b/rust/kernel/iov.rs new file mode 100644 index 000000000000..43bae8923c46 --- /dev/null +++ b/rust/kernel/iov.rs @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2025 Google LLC. + +//! IO vectors. +//! +//! C headers: [`include/linux/iov_iter.h`](srctree/include/linux/iov_iter.h), +//! [`include/linux/uio.h`](srctree/include/linux/uio.h) + +use crate::{ + alloc::{Allocator, Flags}, + bindings, + prelude::*, + types::Opaque, +}; +use core::{marker::PhantomData, mem::MaybeUninit, ptr, slice}; + +const ITER_SOURCE: bool = bindings::ITER_SOURCE != 0; +const ITER_DEST: bool = bindings::ITER_DEST != 0; + +// Compile-time assertion for the above constants. +const _: () = { + build_assert!( + ITER_SOURCE != ITER_DEST, + "ITER_DEST and ITER_SOURCE should be different." + ); +}; + +/// An IO vector that acts as a source of data. +/// +/// The data may come from many different sources. This includes both things in kernel-space and +/// reading from userspace. It's not necessarily the case that the data source is immutable, so +/// rewinding the IO vector to read the same data twice is not guaranteed to result in the same +/// bytes. It's also possible that the data source is mapped in a thread-local manner using e.g. +/// `kmap_local_page()`, so this type is not `Send` to ensure that the mapping is read from the +/// right context in that scenario. +/// +/// # Invariants +/// +/// Must hold a valid `struct iov_iter` with `data_source` set to `ITER_SOURCE`. For the duration +/// of `'data`, it must be safe to read from this IO vector using the standard C methods for this +/// purpose. +#[repr(transparent)] +pub struct IovIterSource<'data> { + iov: Opaque<bindings::iov_iter>, + /// Represent to the type system that this value contains a pointer to readable data it does + /// not own. + _source: PhantomData<&'data [u8]>, +} + +impl<'data> IovIterSource<'data> { + /// Obtain an `IovIterSource` from a raw pointer. + /// + /// # Safety + /// + /// * The referenced `struct iov_iter` must be valid and must only be accessed through the + /// returned reference for the duration of `'iov`. + /// * The referenced `struct iov_iter` must have `data_source` set to `ITER_SOURCE`. + /// * For the duration of `'data`, it must be safe to read from this IO vector using the + /// standard C methods for this purpose. + #[track_caller] + #[inline] + pub unsafe fn from_raw<'iov>(ptr: *mut bindings::iov_iter) -> &'iov mut IovIterSource<'data> { + // SAFETY: The caller ensures that `ptr` is valid. + let data_source = unsafe { (*ptr).data_source }; + assert_eq!(data_source, ITER_SOURCE); + + // SAFETY: The caller ensures the type invariants for the right durations, and + // `IovIterSource` is layout compatible with `struct iov_iter`. + unsafe { &mut *ptr.cast::<IovIterSource<'data>>() } + } + + /// Access this as a raw `struct iov_iter`. + #[inline] + pub fn as_raw(&mut self) -> *mut bindings::iov_iter { + self.iov.get() + } + + /// Returns the number of bytes available in this IO vector. + /// + /// Note that this may overestimate the number of bytes. For example, reading from userspace + /// memory could fail with `EFAULT`, which will be treated as the end of the IO vector. + #[inline] + pub fn len(&self) -> usize { + // SAFETY: We have shared access to this IO vector, so we can read its `count` field. + unsafe { + (*self.iov.get()) + .__bindgen_anon_1 + .__bindgen_anon_1 + .as_ref() + .count + } + } + + /// Returns whether there are any bytes left in this IO vector. + /// + /// This may return `true` even if there are no more bytes available. For example, reading from + /// userspace memory could fail with `EFAULT`, which will be treated as the end of the IO vector. + #[inline] + pub fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Advance this IO vector by `bytes` bytes. + /// + /// If `bytes` is larger than the size of this IO vector, it is advanced to the end. + #[inline] + pub fn advance(&mut self, bytes: usize) { + // SAFETY: By the type invariants, `self.iov` is a valid IO vector. + unsafe { bindings::iov_iter_advance(self.as_raw(), bytes) }; + } + + /// Advance this IO vector backwards by `bytes` bytes. + /// + /// # Safety + /// + /// The IO vector must not be reverted to before its beginning. + #[inline] + pub unsafe fn revert(&mut self, bytes: usize) { + // SAFETY: By the type invariants, `self.iov` is a valid IO vector, and the caller + // ensures that `bytes` is in bounds. + unsafe { bindings::iov_iter_revert(self.as_raw(), bytes) }; + } + + /// Read data from this IO vector. + /// + /// Returns the number of bytes that have been copied. + #[inline] + pub fn copy_from_iter(&mut self, out: &mut [u8]) -> usize { + // SAFETY: `Self::copy_from_iter_raw` guarantees that it will not write any uninitialized + // bytes in the provided buffer, so `out` is still a valid `u8` slice after this call. + let out = unsafe { &mut *(ptr::from_mut(out) as *mut [MaybeUninit<u8>]) }; + + self.copy_from_iter_raw(out).len() + } + + /// Read data from this IO vector and append it to a vector. + /// + /// Returns the number of bytes that have been copied. + #[inline] + pub fn copy_from_iter_vec<A: Allocator>( + &mut self, + out: &mut Vec<u8, A>, + flags: Flags, + ) -> Result<usize> { + out.reserve(self.len(), flags)?; + let len = self.copy_from_iter_raw(out.spare_capacity_mut()).len(); + // SAFETY: + // - `len` is the length of a subslice of the spare capacity, so `len` is at most the + // length of the spare capacity. + // - `Self::copy_from_iter_raw` guarantees that the first `len` bytes of the spare capacity + // have been initialized. + unsafe { out.inc_len(len) }; + Ok(len) + } + + /// Read data from this IO vector into potentially uninitialized memory. + /// + /// Returns the sub-slice of the output that has been initialized. If the returned slice is + /// shorter than the input buffer, then the entire IO vector has been read. + /// + /// This will never write uninitialized bytes to the provided buffer. + #[inline] + pub fn copy_from_iter_raw(&mut self, out: &mut [MaybeUninit<u8>]) -> &mut [u8] { + let capacity = out.len(); + let out = out.as_mut_ptr().cast::<u8>(); + + // GUARANTEES: The C API guarantees that it does not write uninitialized bytes to the + // provided buffer. + // SAFETY: + // * By the type invariants, it is still valid to read from this IO vector. + // * `out` is valid for writing for `capacity` bytes because it comes from a slice of + // that length. + let len = unsafe { bindings::_copy_from_iter(out.cast(), capacity, self.as_raw()) }; + + // SAFETY: The underlying C api guarantees that initialized bytes have been written to the + // first `len` bytes of the spare capacity. + unsafe { slice::from_raw_parts_mut(out, len) } + } +} + +/// An IO vector that acts as a destination for data. +/// +/// IO vectors support many different types of destinations. This includes both buffers in +/// kernel-space and writing to userspace. It's possible that the destination buffer is mapped in a +/// thread-local manner using e.g. `kmap_local_page()`, so this type is not `Send` to ensure that +/// the mapping is written to the right context in that scenario. +/// +/// # Invariants +/// +/// Must hold a valid `struct iov_iter` with `data_source` set to `ITER_DEST`. For the duration of +/// `'data`, it must be safe to write to this IO vector using the standard C methods for this +/// purpose. +#[repr(transparent)] +pub struct IovIterDest<'data> { + iov: Opaque<bindings::iov_iter>, + /// Represent to the type system that this value contains a pointer to writable data it does + /// not own. + _source: PhantomData<&'data mut [u8]>, +} + +impl<'data> IovIterDest<'data> { + /// Obtain an `IovIterDest` from a raw pointer. + /// + /// # Safety + /// + /// * The referenced `struct iov_iter` must be valid and must only be accessed through the + /// returned reference for the duration of `'iov`. + /// * The referenced `struct iov_iter` must have `data_source` set to `ITER_DEST`. + /// * For the duration of `'data`, it must be safe to write to this IO vector using the + /// standard C methods for this purpose. + #[track_caller] + #[inline] + pub unsafe fn from_raw<'iov>(ptr: *mut bindings::iov_iter) -> &'iov mut IovIterDest<'data> { + // SAFETY: The caller ensures that `ptr` is valid. + let data_source = unsafe { (*ptr).data_source }; + assert_eq!(data_source, ITER_DEST); + + // SAFETY: The caller ensures the type invariants for the right durations, and + // `IovIterSource` is layout compatible with `struct iov_iter`. + unsafe { &mut *ptr.cast::<IovIterDest<'data>>() } + } + + /// Access this as a raw `struct iov_iter`. + #[inline] + pub fn as_raw(&mut self) -> *mut bindings::iov_iter { + self.iov.get() + } + + /// Returns the number of bytes available in this IO vector. + /// + /// Note that this may overestimate the number of bytes. For example, reading from userspace + /// memory could fail with EFAULT, which will be treated as the end of the IO vector. + #[inline] + pub fn len(&self) -> usize { + // SAFETY: We have shared access to this IO vector, so we can read its `count` field. + unsafe { + (*self.iov.get()) + .__bindgen_anon_1 + .__bindgen_anon_1 + .as_ref() + .count + } + } + + /// Returns whether there are any bytes left in this IO vector. + /// + /// This may return `true` even if there are no more bytes available. For example, reading from + /// userspace memory could fail with EFAULT, which will be treated as the end of the IO vector. + #[inline] + pub fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Advance this IO vector by `bytes` bytes. + /// + /// If `bytes` is larger than the size of this IO vector, it is advanced to the end. + #[inline] + pub fn advance(&mut self, bytes: usize) { + // SAFETY: By the type invariants, `self.iov` is a valid IO vector. + unsafe { bindings::iov_iter_advance(self.as_raw(), bytes) }; + } + + /// Advance this IO vector backwards by `bytes` bytes. + /// + /// # Safety + /// + /// The IO vector must not be reverted to before its beginning. + #[inline] + pub unsafe fn revert(&mut self, bytes: usize) { + // SAFETY: By the type invariants, `self.iov` is a valid IO vector, and the caller + // ensures that `bytes` is in bounds. + unsafe { bindings::iov_iter_revert(self.as_raw(), bytes) }; + } + + /// Write data to this IO vector. + /// + /// Returns the number of bytes that were written. If this is shorter than the provided slice, + /// then no more bytes can be written. + #[inline] + pub fn copy_to_iter(&mut self, input: &[u8]) -> usize { + // SAFETY: + // * By the type invariants, it is still valid to write to this IO vector. + // * `input` is valid for `input.len()` bytes. + unsafe { bindings::_copy_to_iter(input.as_ptr().cast(), input.len(), self.as_raw()) } + } + + /// Utility for implementing `read_iter` given the full contents of the file. + /// + /// The full contents of the file being read from is represented by `contents`. This call will + /// write the appropriate sub-slice of `contents` and update the file position in `ppos` so + /// that the file will appear to contain `contents` even if takes multiple reads to read the + /// entire file. + #[inline] + pub fn simple_read_from_buffer(&mut self, ppos: &mut i64, contents: &[u8]) -> Result<usize> { + if *ppos < 0 { + return Err(EINVAL); + } + let Ok(pos) = usize::try_from(*ppos) else { + return Ok(0); + }; + if pos >= contents.len() { + return Ok(0); + } + + // BOUNDS: We just checked that `pos < contents.len()` above. + let num_written = self.copy_to_iter(&contents[pos..]); + + // OVERFLOW: `pos+num_written <= contents.len() <= isize::MAX <= i64::MAX`. + *ppos = (pos + num_written) as i64; + + Ok(num_written) + } +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index ed53169e795c..99dbb7b2812e 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -92,6 +92,7 @@ pub mod fs; pub mod init; pub mod io; pub mod ioctl; +pub mod iov; pub mod jump_label; #[cfg(CONFIG_KUNIT)] pub mod kunit; diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs index 6373fe183b27..35630fc63875 100644 --- a/rust/kernel/miscdevice.rs +++ b/rust/kernel/miscdevice.rs @@ -13,7 +13,8 @@ use crate::{ device::Device, error::{to_result, Error, Result, VTABLE_DEFAULT_ERROR}, ffi::{c_int, c_long, c_uint, c_ulong}, - fs::File, + fs::{File, Kiocb}, + iov::{IovIterDest, IovIterSource}, mm::virt::VmaNew, prelude::*, seq_file::SeqFile, @@ -141,6 +142,16 @@ pub trait MiscDevice: Sized { build_error!(VTABLE_DEFAULT_ERROR) } + /// Read from this miscdevice. + fn read_iter(_kiocb: Kiocb<'_, Self::Ptr>, _iov: &mut IovIterDest<'_>) -> Result<usize> { + build_error!(VTABLE_DEFAULT_ERROR) + } + + /// Write to this miscdevice. + fn write_iter(_kiocb: Kiocb<'_, Self::Ptr>, _iov: &mut IovIterSource<'_>) -> Result<usize> { + build_error!(VTABLE_DEFAULT_ERROR) + } + /// Handler for ioctls. /// /// The `cmd` argument is usually manipulated using the utilities in [`kernel::ioctl`]. @@ -247,6 +258,46 @@ impl<T: MiscDevice> MiscdeviceVTable<T> { /// # Safety /// + /// `kiocb` must be correspond to a valid file that is associated with a + /// `MiscDeviceRegistration<T>`. `iter` must be a valid `struct iov_iter` for writing. + unsafe extern "C" fn read_iter( + kiocb: *mut bindings::kiocb, + iter: *mut bindings::iov_iter, + ) -> isize { + // SAFETY: The caller provides a valid `struct kiocb` associated with a + // `MiscDeviceRegistration<T>` file. + let kiocb = unsafe { Kiocb::from_raw(kiocb) }; + // SAFETY: This is a valid `struct iov_iter` for writing. + let iov = unsafe { IovIterDest::from_raw(iter) }; + + match T::read_iter(kiocb, iov) { + Ok(res) => res as isize, + Err(err) => err.to_errno() as isize, + } + } + + /// # Safety + /// + /// `kiocb` must be correspond to a valid file that is associated with a + /// `MiscDeviceRegistration<T>`. `iter` must be a valid `struct iov_iter` for writing. + unsafe extern "C" fn write_iter( + kiocb: *mut bindings::kiocb, + iter: *mut bindings::iov_iter, + ) -> isize { + // SAFETY: The caller provides a valid `struct kiocb` associated with a + // `MiscDeviceRegistration<T>` file. + let kiocb = unsafe { Kiocb::from_raw(kiocb) }; + // SAFETY: This is a valid `struct iov_iter` for reading. + let iov = unsafe { IovIterSource::from_raw(iter) }; + + match T::write_iter(kiocb, iov) { + Ok(res) => res as isize, + Err(err) => err.to_errno() as isize, + } + } + + /// # Safety + /// /// `file` must be a valid file that is associated with a `MiscDeviceRegistration<T>`. /// `vma` must be a vma that is currently being mmap'ed with this file. unsafe extern "C" fn mmap( @@ -341,6 +392,16 @@ impl<T: MiscDevice> MiscdeviceVTable<T> { open: Some(Self::open), release: Some(Self::release), mmap: if T::HAS_MMAP { Some(Self::mmap) } else { None }, + read_iter: if T::HAS_READ_ITER { + Some(Self::read_iter) + } else { + None + }, + write_iter: if T::HAS_WRITE_ITER { + Some(Self::write_iter) + } else { + None + }, unlocked_ioctl: if T::HAS_IOCTL { Some(Self::ioctl) } else { diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs index 7c1b17246ed5..811fe30e8e6f 100644 --- a/rust/kernel/page.rs +++ b/rust/kernel/page.rs @@ -85,6 +85,12 @@ impl Page { self.page.as_ptr() } + /// Get the node id containing this page. + pub fn nid(&self) -> i32 { + // SAFETY: Always safe to call with a valid page. + unsafe { bindings::page_to_nid(self.as_ptr()) } + } + /// Runs a piece of code with this page mapped to an address. /// /// The page is unmapped when this call returns. diff --git a/rust/kernel/security.rs b/rust/kernel/security.rs index 0c63e9e7e564..9d271695265f 100644 --- a/rust/kernel/security.rs +++ b/rust/kernel/security.rs @@ -8,9 +8,46 @@ use crate::{ bindings, + cred::Credential, error::{to_result, Result}, + fs::File, }; +/// Calls the security modules to determine if the given task can become the manager of a binder +/// context. +#[inline] +pub fn binder_set_context_mgr(mgr: &Credential) -> Result { + // SAFETY: `mrg.0` is valid because the shared reference guarantees a nonzero refcount. + to_result(unsafe { bindings::security_binder_set_context_mgr(mgr.as_ptr()) }) +} + +/// Calls the security modules to determine if binder transactions are allowed from task `from` to +/// task `to`. +#[inline] +pub fn binder_transaction(from: &Credential, to: &Credential) -> Result { + // SAFETY: `from` and `to` are valid because the shared references guarantee nonzero refcounts. + to_result(unsafe { bindings::security_binder_transaction(from.as_ptr(), to.as_ptr()) }) +} + +/// Calls the security modules to determine if task `from` is allowed to send binder objects +/// (owned by itself or other processes) to task `to` through a binder transaction. +#[inline] +pub fn binder_transfer_binder(from: &Credential, to: &Credential) -> Result { + // SAFETY: `from` and `to` are valid because the shared references guarantee nonzero refcounts. + to_result(unsafe { bindings::security_binder_transfer_binder(from.as_ptr(), to.as_ptr()) }) +} + +/// Calls the security modules to determine if task `from` is allowed to send the given file to +/// task `to` (which would get its own file descriptor) through a binder transaction. +#[inline] +pub fn binder_transfer_file(from: &Credential, to: &Credential, file: &File) -> Result { + // SAFETY: `from`, `to` and `file` are valid because the shared references guarantee nonzero + // refcounts. + to_result(unsafe { + bindings::security_binder_transfer_file(from.as_ptr(), to.as_ptr(), file.as_ptr()) + }) +} + /// A security context string. /// /// # Invariants diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h index 1409441359f5..de3562b08d0c 100644 --- a/rust/uapi/uapi_helper.h +++ b/rust/uapi/uapi_helper.h @@ -9,6 +9,7 @@ #include <uapi/asm-generic/ioctl.h> #include <uapi/drm/drm.h> #include <uapi/drm/nova_drm.h> +#include <uapi/linux/android/binder.h> #include <uapi/linux/mdio.h> #include <uapi/linux/mii.h> #include <uapi/linux/ethtool.h> diff --git a/samples/rust/rust_misc_device.rs b/samples/rust/rust_misc_device.rs index e7ab77448f75..d69bc33dbd99 100644 --- a/samples/rust/rust_misc_device.rs +++ b/samples/rust/rust_misc_device.rs @@ -100,13 +100,13 @@ use core::pin::Pin; use kernel::{ c_str, device::Device, - fs::File, + fs::{File, Kiocb}, ioctl::{_IO, _IOC_SIZE, _IOR, _IOW}, + iov::{IovIterDest, IovIterSource}, miscdevice::{MiscDevice, MiscDeviceOptions, MiscDeviceRegistration}, new_mutex, prelude::*, - sync::Mutex, - types::ARef, + sync::{aref::ARef, Mutex}, uaccess::{UserSlice, UserSliceReader, UserSliceWriter}, }; @@ -144,6 +144,7 @@ impl kernel::InPlaceModule for RustMiscDeviceModule { struct Inner { value: i32, + buffer: KVVec<u8>, } #[pin_data(PinnedDrop)] @@ -165,7 +166,10 @@ impl MiscDevice for RustMiscDevice { KBox::try_pin_init( try_pin_init! { RustMiscDevice { - inner <- new_mutex!( Inner{ value: 0_i32 } ), + inner <- new_mutex!(Inner { + value: 0_i32, + buffer: KVVec::new(), + }), dev: dev, } }, @@ -173,6 +177,33 @@ impl MiscDevice for RustMiscDevice { ) } + fn read_iter(mut kiocb: Kiocb<'_, Self::Ptr>, iov: &mut IovIterDest<'_>) -> Result<usize> { + let me = kiocb.file(); + dev_info!(me.dev, "Reading from Rust Misc Device Sample\n"); + + let inner = me.inner.lock(); + // Read the buffer contents, taking the file position into account. + let read = iov.simple_read_from_buffer(kiocb.ki_pos_mut(), &inner.buffer)?; + + Ok(read) + } + + fn write_iter(mut kiocb: Kiocb<'_, Self::Ptr>, iov: &mut IovIterSource<'_>) -> Result<usize> { + let me = kiocb.file(); + dev_info!(me.dev, "Writing to Rust Misc Device Sample\n"); + + let mut inner = me.inner.lock(); + + // Replace buffer contents. + inner.buffer.clear(); + let len = iov.copy_from_iter_vec(&mut inner.buffer, GFP_KERNEL)?; + + // Set position to zero so that future `read` calls will see the new contents. + *kiocb.ki_pos_mut() = 0; + + Ok(len) + } + fn ioctl(me: Pin<&RustMiscDevice>, _file: &File, cmd: u32, arg: usize) -> Result<isize> { dev_info!(me.dev, "IOCTLing Rust Misc Device Sample\n"); diff --git a/sound/core/timer.c b/sound/core/timer.c index 3ce12264eed8..d9fff5c87613 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -2139,14 +2139,14 @@ static int snd_utimer_create(struct snd_timer_uinfo *utimer_info, goto err_take_id; } + utimer->id = utimer_id; + utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id); if (!utimer->name) { err = -ENOMEM; goto err_get_name; } - utimer->id = utimer_id; - tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.card = -1; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e27a36e4e92a..0323606b3d6d 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -510,6 +510,15 @@ static void alc256_shutup(struct hda_codec *codec) hp_pin = 0x21; alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ + + /* 3k pull low control for Headset jack. */ + /* NOTE: call this before clearing the pin, otherwise codec stalls */ + /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly + * when booting with headset plugged. So skip setting it for the codec alc257 + */ + if (spec->en_3kpull_low) + alc_update_coef_idx(codec, 0x46, 0, 3 << 12); + hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); if (hp_pin_sense) { @@ -520,14 +529,6 @@ static void alc256_shutup(struct hda_codec *codec) msleep(75); - /* 3k pull low control for Headset jack. */ - /* NOTE: call this before clearing the pin, otherwise codec stalls */ - /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly - * when booting with headset plugged. So skip setting it for the codec alc257 - */ - if (spec->en_3kpull_low) - alc_update_coef_idx(codec, 0x46, 0, 3 << 12); - if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); @@ -3579,6 +3580,7 @@ enum { ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE, ALC294_FIXUP_ASUS_MIC, ALC294_FIXUP_ASUS_HEADSET_MIC, + ALC294_FIXUP_ASUS_I2C_HEADSET_MIC, ALC294_FIXUP_ASUS_SPK, ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, @@ -4889,6 +4891,15 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_I2C_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a19020 }, /* use as headset mic */ + { } + }, + .chained = true, + .chain_id = ALC287_FIXUP_CS35L41_I2C_2 + }, [ALC294_FIXUP_ASUS_SPK] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -6368,6 +6379,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8548, "HP EliteBook x360 830 G6", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x854a, "HP EliteBook 830 G6", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11), SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), @@ -6728,7 +6741,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC294_FIXUP_ASUS_I2C_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), @@ -7140,6 +7153,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x1ee7, 0x2078, "HONOR BRB-X M1010", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7158,6 +7172,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 45ac5e41bd4f..e34b17f0c9b9 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -265,9 +265,9 @@ static const struct snd_kcontrol_new tas2770_snd_controls[] = { }; static const struct snd_kcontrol_new tas2781_snd_controls[] = { - ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain", TAS2781_AMP_LEVEL, + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL, 1, 0, 20, 0, tas2781_amp_getvol, - tas2781_amp_putvol, amp_vol_tlv), + tas2781_amp_putvol, tas2781_amp_tlv), ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load", 0, tas2781_force_fwload_get, tas2781_force_fwload_put), }; @@ -305,7 +305,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h) efi_char16_t efi_name[TAS2563_CAL_VAR_NAME_MAX]; unsigned long max_size = TAS2563_CAL_DATA_SIZE; unsigned char var8[TAS2563_CAL_VAR_NAME_MAX]; - struct tasdevice_priv *p = h->hda_priv; + struct tasdevice_priv *p = h->priv; struct calidata *cd = &p->cali_data; struct cali_reg *r = &cd->cali_reg_array; unsigned int offset = 0; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c index 09a5d0f131b2..b9a55672bf15 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c @@ -494,9 +494,11 @@ static int tas2781_force_fwload_put(struct snd_kcontrol *kcontrol, static struct snd_kcontrol_new tas2781_snd_ctls[] = { ACARD_SINGLE_RANGE_EXT_TLV(NULL, TAS2781_AMP_LEVEL, 1, 0, 20, 0, - tas2781_amp_getvol, tas2781_amp_putvol, amp_vol_tlv), + tas2781_amp_getvol, tas2781_amp_putvol, + tas2781_amp_tlv), ACARD_SINGLE_RANGE_EXT_TLV(NULL, TAS2781_DVC_LVL, 0, 0, 200, 1, - tas2781_digital_getvol, tas2781_digital_putvol, dvc_tlv), + tas2781_digital_getvol, tas2781_digital_putvol, + tas2781_dvc_tlv), ACARD_SINGLE_BOOL_EXT(NULL, 0, tas2781_force_fwload_get, tas2781_force_fwload_put), }; diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c index fcf67e97a546..1bb3ff55b115 100644 --- a/sound/hda/controllers/intel.c +++ b/sound/hda/controllers/intel.c @@ -2077,7 +2077,6 @@ static const struct pci_device_id driver_denylist[] = { { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */ - { PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1022, 0xd601) }, /* ASRock X670E Taichi */ {} }; diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c index 4418b9ae33e6..b33344f65b8c 100644 --- a/sound/pci/azt3328.c +++ b/sound/pci/azt3328.c @@ -412,25 +412,25 @@ snd_azf3328_ctrl_outl(const struct snd_azf3328 *chip, unsigned reg, u32 value) outl(value, chip->ctrl_io + reg); } -static inline void +static inline void __maybe_unused snd_azf3328_game_outb(const struct snd_azf3328 *chip, unsigned reg, u8 value) { outb(value, chip->game_io + reg); } -static inline void +static inline void __maybe_unused snd_azf3328_game_outw(const struct snd_azf3328 *chip, unsigned reg, u16 value) { outw(value, chip->game_io + reg); } -static inline u8 +static inline u8 __maybe_unused snd_azf3328_game_inb(const struct snd_azf3328 *chip, unsigned reg) { return inb(chip->game_io + reg); } -static inline u16 +static inline u16 __maybe_unused snd_azf3328_game_inw(const struct snd_azf3328 *chip, unsigned reg) { return inw(chip->game_io + reg); diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig index bf362bfca456..ce74818bd715 100644 --- a/sound/soc/Kconfig +++ b/sound/soc/Kconfig @@ -111,7 +111,6 @@ source "sound/soc/bcm/Kconfig" source "sound/soc/cirrus/Kconfig" source "sound/soc/dwc/Kconfig" source "sound/soc/fsl/Kconfig" -source "sound/soc/generic/Kconfig" source "sound/soc/google/Kconfig" source "sound/soc/hisilicon/Kconfig" source "sound/soc/jz4740/Kconfig" @@ -149,5 +148,8 @@ source "sound/soc/codecs/Kconfig" source "sound/soc/sdw_utils/Kconfig" +# generic frame-work +source "sound/soc/generic/Kconfig" + endif # SND_SOC diff --git a/sound/soc/codecs/aw87390.c b/sound/soc/codecs/aw87390.c index 110009616966..ef6f64856988 100644 --- a/sound/soc/codecs/aw87390.c +++ b/sound/soc/codecs/aw87390.c @@ -177,7 +177,7 @@ static int aw87390_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw87390 *aw87390 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -194,17 +194,15 @@ static int aw87390_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw87390_dev_get_prof_name(aw87390->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88081.c b/sound/soc/codecs/aw88081.c index 3dd8428f08cc..d61a7b8c5470 100644 --- a/sound/soc/codecs/aw88081.c +++ b/sound/soc/codecs/aw88081.c @@ -914,12 +914,11 @@ static int aw88081_profile_info(struct snd_kcontrol *kcontrol, ret = aw88081_dev_get_prof_name(aw88081->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(uinfo->value.enumerated.name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88166.c b/sound/soc/codecs/aw88166.c index 4f76ebe11cc7..28f62b991ef2 100644 --- a/sound/soc/codecs/aw88166.c +++ b/sound/soc/codecs/aw88166.c @@ -1478,7 +1478,7 @@ static int aw88166_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88166 *aw88166 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -1495,17 +1495,15 @@ static int aw88166_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88166_dev_get_prof_name(aw88166->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88261.c b/sound/soc/codecs/aw88261.c index fb99871578c5..de11ae8dd9d9 100644 --- a/sound/soc/codecs/aw88261.c +++ b/sound/soc/codecs/aw88261.c @@ -819,7 +819,7 @@ static int aw88261_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88261 *aw88261 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -836,17 +836,15 @@ static int aw88261_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88261_dev_get_prof_name(aw88261->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88395/aw88395.c b/sound/soc/codecs/aw88395/aw88395.c index aea44a199b98..fb563b4c6971 100644 --- a/sound/soc/codecs/aw88395/aw88395.c +++ b/sound/soc/codecs/aw88395/aw88395.c @@ -175,7 +175,7 @@ static int aw88395_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88395 *aw88395 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -192,17 +192,15 @@ static int aw88395_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88395_dev_get_prof_name(aw88395->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88399.c b/sound/soc/codecs/aw88399.c index c23e70d64d0c..58846feb013d 100644 --- a/sound/soc/codecs/aw88399.c +++ b/sound/soc/codecs/aw88399.c @@ -1831,7 +1831,7 @@ static int aw88399_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88399 *aw88399 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -1848,17 +1848,15 @@ static int aw88399_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88399_dev_get_prof_name(aw88399->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index ee14031695a1..3905c9cb188a 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -393,74 +393,6 @@ static int cs35l56_sdw_update_status(struct sdw_slave *peripheral, return 0; } -static int cs35l63_sdw_kick_divider(struct cs35l56_private *cs35l56, - struct sdw_slave *peripheral) -{ - unsigned int curr_scale_reg, next_scale_reg; - int curr_scale, next_scale, ret; - - if (!cs35l56->base.init_done) - return 0; - - if (peripheral->bus->params.curr_bank) { - curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1; - next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0; - } else { - curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0; - next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1; - } - - /* - * Current clock scale value must be different to new value. - * Modify current to guarantee this. If next still has the dummy - * value we wrote when it was current, the core code has not set - * a new scale so restore its original good value - */ - curr_scale = sdw_read_no_pm(peripheral, curr_scale_reg); - if (curr_scale < 0) { - dev_err(cs35l56->base.dev, "Failed to read current clock scale: %d\n", curr_scale); - return curr_scale; - } - - next_scale = sdw_read_no_pm(peripheral, next_scale_reg); - if (next_scale < 0) { - dev_err(cs35l56->base.dev, "Failed to read next clock scale: %d\n", next_scale); - return next_scale; - } - - if (next_scale == CS35L56_SDW_INVALID_BUS_SCALE) { - next_scale = cs35l56->old_sdw_clock_scale; - ret = sdw_write_no_pm(peripheral, next_scale_reg, next_scale); - if (ret < 0) { - dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n", - ret); - return ret; - } - } - - cs35l56->old_sdw_clock_scale = curr_scale; - ret = sdw_write_no_pm(peripheral, curr_scale_reg, CS35L56_SDW_INVALID_BUS_SCALE); - if (ret < 0) { - dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n", ret); - return ret; - } - - dev_dbg(cs35l56->base.dev, "Next bus scale: %#x\n", next_scale); - - return 0; -} - -static int cs35l56_sdw_bus_config(struct sdw_slave *peripheral, - struct sdw_bus_params *params) -{ - struct cs35l56_private *cs35l56 = dev_get_drvdata(&peripheral->dev); - - if ((cs35l56->base.type == 0x63) && (cs35l56->base.rev < 0xa1)) - return cs35l63_sdw_kick_divider(cs35l56, peripheral); - - return 0; -} - static int __maybe_unused cs35l56_sdw_clk_stop(struct sdw_slave *peripheral, enum sdw_clk_stop_mode mode, enum sdw_clk_stop_type type) @@ -476,7 +408,6 @@ static const struct sdw_slave_ops cs35l56_sdw_ops = { .read_prop = cs35l56_sdw_read_prop, .interrupt_callback = cs35l56_sdw_interrupt, .update_status = cs35l56_sdw_update_status, - .bus_config = cs35l56_sdw_bus_config, #ifdef DEBUG .clk_stop = cs35l56_sdw_clk_stop, #endif diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index ba653f6ccfae..850fcf385996 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -838,6 +838,15 @@ const struct cirrus_amp_cal_controls cs35l56_calibration_controls = { }; EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, "SND_SOC_CS35L56_SHARED"); +static const struct cirrus_amp_cal_controls cs35l63_calibration_controls = { + .alg_id = 0xbf210, + .mem_region = WMFW_ADSP2_YM, + .ambient = "CAL_AMBIENT", + .calr = "CAL_R", + .status = "CAL_STATUS", + .checksum = "CAL_CHECKSUM", +}; + int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base) { u64 silicon_uid = 0; @@ -912,19 +921,31 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, "SND_SOC_CS35L56_SHARED"); void cs35l56_log_tuning(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp) { __be32 pid, sid, tid; + unsigned int alg_id; int ret; + switch (cs35l56_base->type) { + case 0x54: + case 0x56: + case 0x57: + alg_id = 0x9f212; + break; + default: + alg_id = 0xbf212; + break; + } + scoped_guard(mutex, &cs_dsp->pwr_lock) { ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_PRJCT_ID", - WMFW_ADSP2_XM, 0x9f212), + WMFW_ADSP2_XM, alg_id), 0, &pid, sizeof(pid)); if (!ret) ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_CHNNL_ID", - WMFW_ADSP2_XM, 0x9f212), + WMFW_ADSP2_XM, alg_id), 0, &sid, sizeof(sid)); if (!ret) ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_SNPSHT_ID", - WMFW_ADSP2_XM, 0x9f212), + WMFW_ADSP2_XM, alg_id), 0, &tid, sizeof(tid)); } @@ -974,8 +995,10 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) case 0x35A54: case 0x35A56: case 0x35A57: + cs35l56_base->calibration_controls = &cs35l56_calibration_controls; break; case 0x35A630: + cs35l56_base->calibration_controls = &cs35l63_calibration_controls; devid = devid >> 4; break; default: diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index b1c65d8331e7..2c1edbd636ef 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -695,7 +695,7 @@ static int cs35l56_write_cal(struct cs35l56_private *cs35l56) return ret; ret = cs_amp_write_cal_coeffs(&cs35l56->dsp.cs_dsp, - &cs35l56_calibration_controls, + cs35l56->base.calibration_controls, &cs35l56->base.cal_data); wm_adsp_stop(&cs35l56->dsp); diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h index bd77a57249d7..40a1800a4585 100644 --- a/sound/soc/codecs/cs35l56.h +++ b/sound/soc/codecs/cs35l56.h @@ -20,8 +20,6 @@ #define CS35L56_SDW_GEN_INT_MASK_1 0xc1 #define CS35L56_SDW_INT_MASK_CODEC_IRQ BIT(0) -#define CS35L56_SDW_INVALID_BUS_SCALE 0xf - #define CS35L56_RX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE) #define CS35L56_TX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE \ | SNDRV_PCM_FMTBIT_S32_LE) @@ -52,7 +50,6 @@ struct cs35l56_private { u8 asp_slot_count; bool tdm_mode; bool sysclk_set; - u8 old_sdw_clock_scale; u8 sdw_link_num; u8 sdw_unique_id; }; diff --git a/sound/soc/codecs/es8389.c b/sound/soc/codecs/es8389.c index ba1763f36f17..6e4c75d288ef 100644 --- a/sound/soc/codecs/es8389.c +++ b/sound/soc/codecs/es8389.c @@ -636,7 +636,7 @@ static int es8389_set_bias_level(struct snd_soc_component *component, regmap_write(es8389->regmap, ES8389_ANA_CTL1, 0x59); regmap_write(es8389->regmap, ES8389_ADC_EN, 0x00); regmap_write(es8389->regmap, ES8389_CLK_OFF1, 0x00); - regmap_write(es8389->regmap, ES8389_RESET, 0x7E); + regmap_write(es8389->regmap, ES8389_RESET, 0x3E); regmap_update_bits(es8389->regmap, ES8389_DAC_INV, 0x80, 0x80); usleep_range(8000, 8500); regmap_update_bits(es8389->regmap, ES8389_DAC_INV, 0x80, 0x00); diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 40d79bee4584..1da34cb3505f 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -2229,7 +2229,7 @@ static int tx_macro_register_mclk_output(struct tx_macro *tx) } static const struct snd_soc_component_driver tx_macro_component_drv = { - .name = "RX-MACRO", + .name = "TX-MACRO", .probe = tx_macro_component_probe, .controls = tx_macro_snd_controls, .num_controls = ARRAY_SIZE(tx_macro_snd_controls), diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c index b13d7a99bf63..dcddc28e8856 100644 --- a/sound/soc/codecs/rt1320-sdw.c +++ b/sound/soc/codecs/rt1320-sdw.c @@ -109,6 +109,7 @@ static const struct reg_sequence rt1320_blind_write[] = { { 0x0000d540, 0x01 }, { 0xd172, 0x2a }, { 0xc5d6, 0x01 }, + { 0xd478, 0xff }, }; static const struct reg_sequence rt1320_vc_blind_write[] = { @@ -159,7 +160,7 @@ static const struct reg_sequence rt1320_vc_blind_write[] = { { 0xd471, 0x3a }, { 0xd474, 0x11 }, { 0xd475, 0x32 }, - { 0xd478, 0x64 }, + { 0xd478, 0xff }, { 0xd479, 0x20 }, { 0xd47a, 0x10 }, { 0xd47c, 0xff }, diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c index f6f7c2ffde1c..a4bd29d7220b 100644 --- a/sound/soc/codecs/rt721-sdca.c +++ b/sound/soc/codecs/rt721-sdca.c @@ -278,6 +278,8 @@ static void rt721_sdca_jack_preset(struct rt721_sdca_priv *rt721) RT721_ENT_FLOAT_CTL1, 0x4040); rt_sdca_index_write(rt721->mbq_regmap, RT721_HDA_SDCA_FLOAT, RT721_ENT_FLOAT_CTL4, 0x1201); + rt_sdca_index_write(rt721->mbq_regmap, RT721_BOOST_CTRL, + RT721_BST_4CH_TOP_GATING_CTRL1, 0x002a); regmap_write(rt721->regmap, 0x2f58, 0x07); } diff --git a/sound/soc/codecs/rt721-sdca.h b/sound/soc/codecs/rt721-sdca.h index 0a82c107b19a..71fac9cd8739 100644 --- a/sound/soc/codecs/rt721-sdca.h +++ b/sound/soc/codecs/rt721-sdca.h @@ -56,6 +56,7 @@ struct rt721_sdca_dmic_kctrl_priv { #define RT721_CBJ_CTRL 0x0a #define RT721_CAP_PORT_CTRL 0x0c #define RT721_CLASD_AMP_CTRL 0x0d +#define RT721_BOOST_CTRL 0x0f #define RT721_VENDOR_REG 0x20 #define RT721_RC_CALIB_CTRL 0x40 #define RT721_VENDOR_EQ_L 0x53 @@ -93,6 +94,9 @@ struct rt721_sdca_dmic_kctrl_priv { /* Index (NID:0dh) */ #define RT721_CLASD_AMP_2CH_CAL 0x14 +/* Index (NID:0fh) */ +#define RT721_BST_4CH_TOP_GATING_CTRL1 0x05 + /* Index (NID:20h) */ #define RT721_JD_PRODUCT_NUM 0x00 #define RT721_ANALOG_BIAS_CTL3 0x04 diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c index b3d401ada176..6a601e7134ea 100644 --- a/sound/soc/codecs/sma1307.c +++ b/sound/soc/codecs/sma1307.c @@ -1749,7 +1749,7 @@ static void sma1307_setting_loaded(struct sma1307_priv *sma1307, const char *fil sma1307->set.header_size * sizeof(int)); if ((sma1307->set.checksum >> 8) != SMA1307_SETTING_CHECKSUM) { - dev_err(sma1307->dev, "%s: failed by dismatch \"%s\"\n", + dev_err(sma1307->dev, "%s: checksum failed \"%s\"\n", __func__, setting_file); sma1307->set.status = false; return; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 9f4d965a1335..0e09d794516f 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -908,12 +908,12 @@ static const struct snd_kcontrol_new tasdevice_cali_controls[] = { }; static const struct snd_kcontrol_new tas2781_snd_controls[] = { - SOC_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain", TAS2781_AMP_LEVEL, + SOC_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL, 1, 0, 20, 0, tas2781_amp_getvol, - tas2781_amp_putvol, amp_vol_tlv), - SOC_SINGLE_RANGE_EXT_TLV("Speaker Digital Gain", TAS2781_DVC_LVL, + tas2781_amp_putvol, tas2781_amp_tlv), + SOC_SINGLE_RANGE_EXT_TLV("Speaker Digital Volume", TAS2781_DVC_LVL, 0, 0, 200, 1, tas2781_digital_getvol, - tas2781_digital_putvol, dvc_tlv), + tas2781_digital_putvol, tas2781_dvc_tlv), }; static const struct snd_kcontrol_new tas2781_cali_controls[] = { @@ -1480,7 +1480,7 @@ static ssize_t acoustic_ctl_write(struct file *file, return PTR_ERR(src); if (src[0] > max_pkg_len && src[0] != count) { - dev_err(priv->dev, "pkg(%u), max(%u), count(%u) dismatch.\n", + dev_err(priv->dev, "pkg(%u), max(%u), count(%u) mismatch.\n", src[0], max_pkg_len, (unsigned int)count); ret = 0; goto exit; diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index c313b654236c..d0367b21f775 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -809,9 +809,9 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir) * are running concurrently. */ /* Software Reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); /* Clear SR bit to finish the reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR, 0); } static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, @@ -930,11 +930,11 @@ static int fsl_sai_dai_probe(struct snd_soc_dai *cpu_dai) unsigned int ofs = sai->soc_data->reg_offset; /* Software Reset for both Tx and Rx */ - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); /* Clear SR bit to finish the reset */ - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), 0); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, 0); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, 0); regmap_update_bits(sai->regmap, FSL_SAI_TCR1(ofs), FSL_SAI_CR1_RFW_MASK(sai->soc_data->fifo_depth), @@ -1824,11 +1824,11 @@ static int fsl_sai_runtime_resume(struct device *dev) regcache_cache_only(sai->regmap, false); regcache_mark_dirty(sai->regmap); - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); usleep_range(1000, 2000); - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), 0); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, 0); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, 0); ret = regcache_sync(sai->regmap); if (ret) diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index 0e489097d9c1..6ca21780f21d 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -469,11 +469,8 @@ static int stm32_i2smclk_determine_rate(struct clk_hw *hw, int ret; ret = stm32_i2s_calc_clk_div(i2s, req->best_parent_rate, req->rate); - if (ret) { - req->rate = ret; - - return 0; - } + if (ret) + return ret; mclk->freq = req->best_parent_rate / i2s->divider; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index ad6ced780634..5c235a5ba7e1 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -341,20 +341,28 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor len = le16_to_cpu(cluster->wLength); c = 0; - p += sizeof(struct uac3_cluster_header_descriptor); + p += sizeof(*cluster); + len -= sizeof(*cluster); - while (((p - (void *)cluster) < len) && (c < channels)) { + while (len > 0 && (c < channels)) { struct uac3_cluster_segment_descriptor *cs_desc = p; u16 cs_len; u8 cs_type; + if (len < sizeof(*cs_desc)) + break; cs_len = le16_to_cpu(cs_desc->wLength); + if (len < cs_len) + break; cs_type = cs_desc->bSegmentType; if (cs_type == UAC3_CHANNEL_INFORMATION) { struct uac3_cluster_information_segment_descriptor *is = p; unsigned char map; + if (cs_len < sizeof(*is)) + break; + /* * TODO: this conversion is not complete, update it * after adding UAC3 values to asound.h @@ -456,6 +464,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor chmap->map[c++] = map; } p += cs_len; + len -= cs_len; } if (channels < c) @@ -881,7 +890,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, u64 badd_formats = 0; unsigned int num_channels; struct audioformat *fp; - u16 cluster_id, wLength; + u16 cluster_id, wLength, cluster_wLength; int clock = 0; int err; @@ -1011,6 +1020,16 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, return ERR_PTR(-EIO); } + cluster_wLength = le16_to_cpu(cluster->wLength); + if (cluster_wLength < sizeof(*cluster) || + cluster_wLength > wLength) { + dev_err(&dev->dev, + "%u:%d : invalid Cluster Descriptor size\n", + iface_no, altno); + kfree(cluster); + return ERR_PTR(-EIO); + } + num_channels = cluster->bNrChannels; chmap = convert_chmap_v3(cluster); kfree(cluster); diff --git a/sound/usb/validate.c b/sound/usb/validate.c index 6fe206f6e911..a0d55b77c994 100644 --- a/sound/usb/validate.c +++ b/sound/usb/validate.c @@ -221,6 +221,17 @@ static bool validate_uac3_feature_unit(const void *p, return d->bLength >= sizeof(*d) + 4 + 2; } +static bool validate_uac3_power_domain_unit(const void *p, + const struct usb_desc_validator *v) +{ + const struct uac3_power_domain_descriptor *d = p; + + if (d->bLength < sizeof(*d)) + return false; + /* baEntities[] + wPDomainDescrStr */ + return d->bLength >= sizeof(*d) + d->bNrEntities + 2; +} + static bool validate_midi_out_jack(const void *p, const struct usb_desc_validator *v) { @@ -274,7 +285,7 @@ static const struct usb_desc_validator audio_validators[] = { /* UAC_VERSION_3, UAC3_EXTENDED_TERMINAL: not implemented yet */ FUNC(UAC_VERSION_3, UAC3_MIXER_UNIT, validate_mixer_unit), FUNC(UAC_VERSION_3, UAC3_SELECTOR_UNIT, validate_selector_unit), - FUNC(UAC_VERSION_3, UAC_FEATURE_UNIT, validate_uac3_feature_unit), + FUNC(UAC_VERSION_3, UAC3_FEATURE_UNIT, validate_uac3_feature_unit), /* UAC_VERSION_3, UAC3_EFFECT_UNIT: not implemented yet */ FUNC(UAC_VERSION_3, UAC3_PROCESSING_UNIT, validate_processing_unit), FUNC(UAC_VERSION_3, UAC3_EXTENSION_UNIT, validate_processing_unit), @@ -285,6 +296,7 @@ static const struct usb_desc_validator audio_validators[] = { struct uac3_clock_multiplier_descriptor), /* UAC_VERSION_3, UAC3_SAMPLE_RATE_CONVERTER: not implemented yet */ /* UAC_VERSION_3, UAC3_CONNECTORS: not implemented yet */ + FUNC(UAC_VERSION_3, UAC3_POWER_DOMAIN, validate_uac3_power_domain_unit), { } /* terminator */ }; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 57c669d2aa90..55d59ed507d5 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -193,7 +193,7 @@ static int load_xbc_from_initrd(int fd, char **buf) if (stat.st_size < BOOTCONFIG_FOOTER_SIZE) return 0; - if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) + if (lseek(fd, -(off_t)BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) return pr_errno("Failed to lseek for magic", -errno); if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) @@ -203,7 +203,7 @@ static int load_xbc_from_initrd(int fd, char **buf) if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0) + if (lseek(fd, -(off_t)BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0) return pr_errno("Failed to lseek for size", -errno); if (read(fd, &size, sizeof(uint32_t)) < 0) diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h new file mode 100644 index 000000000000..2e8e65d975c7 --- /dev/null +++ b/tools/include/linux/args.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_ARGS_H +#define _LINUX_ARGS_H + +/* + * How do these macros work? + * + * In __COUNT_ARGS() _0 to _12 are just placeholders from the start + * in order to make sure _n is positioned over the correct number + * from 12 to 0 (depending on X, which is a variadic argument list). + * They serve no purpose other than occupying a position. Since each + * macro parameter must have a distinct identifier, those identifiers + * are as good as any. + * + * In COUNT_ARGS() we use actual integers, so __COUNT_ARGS() returns + * that as _n. + */ + +/* This counts to 15. Any more, it will return 16th argument. */ +#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n +#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) + +/* Concatenate two parameters, but allow them to be expanded beforehand. */ +#define __CONCAT(a, b) a ## b +#define CONCATENATE(a, b) __CONCAT(a, b) + +#endif /* _LINUX_ARGS_H */ diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c index e39f86d97002..a80b75f7b061 100644 --- a/tools/objtool/arch/loongarch/special.c +++ b/tools/objtool/arch/loongarch/special.c @@ -27,6 +27,7 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, struct table_info *next_table; unsigned long tmp_insn_offset; unsigned long tmp_rodata_offset; + bool is_valid_list = false; rsec = find_section_by_name(file->elf, ".rela.discard.tablejump_annotate"); if (!rsec) @@ -35,6 +36,12 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, INIT_LIST_HEAD(&table_list); for_each_reloc(rsec, reloc) { + if (reloc->sym->sec->rodata) + continue; + + if (strcmp(insn->sec->name, reloc->sym->sec->name)) + continue; + orig_table = malloc(sizeof(struct table_info)); if (!orig_table) { WARN("malloc failed"); @@ -49,6 +56,22 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, if (reloc_idx(reloc) + 1 == sec_num_entries(rsec)) break; + + if (strcmp(insn->sec->name, (reloc + 1)->sym->sec->name)) { + list_for_each_entry(orig_table, &table_list, jump_info) { + if (orig_table->insn_offset == insn->offset) { + is_valid_list = true; + break; + } + } + + if (!is_valid_list) { + list_del_init(&table_list); + continue; + } + + break; + } } list_for_each_entry(orig_table, &table_list, jump_info) { diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1 index 500653ef98c7..8ac82b6f9189 100644 --- a/tools/power/cpupower/man/cpupower-set.1 +++ b/tools/power/cpupower/man/cpupower-set.1 @@ -81,10 +81,11 @@ Refer to the AMD P-State kernel documentation for further information. .RE .PP -\-\-turbo\-boost, \-t +\-\-turbo\-boost, \-\-boost, \-t .RS 4 -This option is used to enable or disable the turbo boost feature on -supported Intel and AMD processors. +This option is used to enable or disable the boost feature on +supported Intel and AMD processors, and other boost supported systems. +(The --boost option is an alias for the --turbo-boost option) This option takes as parameter either \fB1\fP to enable, or \fB0\fP to disable the feature. diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index fc750e127404..7d3732f5f2f6 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -128,7 +128,7 @@ static int get_boost_mode_x86(unsigned int cpu) /* ToDo: Make this more global */ unsigned long pstates[MAX_HW_PSTATES] = {0,}; - ret = cpufreq_has_boost_support(cpu, &support, &active, &b_states); + ret = cpufreq_has_x86_boost_support(cpu, &support, &active, &b_states); if (ret) { printf(_("Error while evaluating Boost Capabilities" " on CPU %d -- are you root?\n"), cpu); @@ -204,6 +204,18 @@ static int get_boost_mode_x86(unsigned int cpu) return 0; } +static int get_boost_mode_generic(unsigned int cpu) +{ + bool active; + + if (!cpufreq_has_generic_boost_support(&active)) { + printf(_(" boost state support:\n")); + printf(_(" Active: %s\n"), active ? _("yes") : _("no")); + } + + return 0; +} + /* --boost / -b */ static int get_boost_mode(unsigned int cpu) @@ -214,6 +226,8 @@ static int get_boost_mode(unsigned int cpu) cpupower_cpu_info.vendor == X86_VENDOR_HYGON || cpupower_cpu_info.vendor == X86_VENDOR_INTEL) return get_boost_mode_x86(cpu); + else + get_boost_mode_generic(cpu); freqs = cpufreq_get_boost_frequencies(cpu); if (freqs) { diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index 0677b58374ab..c2117e5650dd 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -21,6 +21,7 @@ static struct option set_opts[] = { {"epp", required_argument, NULL, 'e'}, {"amd-pstate-mode", required_argument, NULL, 'm'}, {"turbo-boost", required_argument, NULL, 't'}, + {"boost", required_argument, NULL, 't'}, { }, }; @@ -62,8 +63,8 @@ int cmd_set(int argc, char **argv) params.params = 0; /* parameter parsing */ - while ((ret = getopt_long(argc, argv, "b:e:m:", - set_opts, NULL)) != -1) { + while ((ret = getopt_long(argc, argv, "b:e:m:t:", + set_opts, NULL)) != -1) { switch (ret) { case 'b': if (params.perf_bias) diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 95749b8ee475..82ea62bdf5a2 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -103,6 +103,9 @@ extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ +int cpufreq_has_generic_boost_support(bool *active); +int cpupower_set_turbo_boost(int turbo_boost); + /* X86 ONLY ****************************************/ #if defined(__i386__) || defined(__x86_64__) @@ -118,7 +121,6 @@ extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu); extern int cpupower_set_epp(unsigned int cpu, char *epp); extern int cpupower_set_amd_pstate_mode(char *mode); -extern int cpupower_set_turbo_boost(int turbo_boost); /* Read/Write msr ****************************/ @@ -139,8 +141,8 @@ extern int decode_pstates(unsigned int cpu, int boost_states, /* AMD HW pstate decoding **************************/ -extern int cpufreq_has_boost_support(unsigned int cpu, int *support, - int *active, int * states); +int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, + int *active, int *states); /* AMD P-State stuff **************************/ bool cpupower_amd_pstate_enabled(void); @@ -181,13 +183,11 @@ static inline int cpupower_set_epp(unsigned int cpu, char *epp) { return -1; }; static inline int cpupower_set_amd_pstate_mode(char *mode) { return -1; }; -static inline int cpupower_set_turbo_boost(int turbo_boost) -{ return -1; }; /* Read/Write msr ****************************/ -static inline int cpufreq_has_boost_support(unsigned int cpu, int *support, - int *active, int * states) +static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, + int *active, int *states) { return -1; } static inline bool cpupower_amd_pstate_enabled(void) diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 76e461ff4f74..166dc1e470ea 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -8,15 +8,14 @@ #include "helpers/helpers.h" #include "helpers/sysfs.h" #include "cpufreq.h" +#include "cpupower_intern.h" #if defined(__i386__) || defined(__x86_64__) -#include "cpupower_intern.h" - #define MSR_AMD_HWCR 0xc0010015 -int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, - int *states) +int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, + int *states) { int ret; unsigned long long val; @@ -124,24 +123,6 @@ int cpupower_set_amd_pstate_mode(char *mode) return 0; } -int cpupower_set_turbo_boost(int turbo_boost) -{ - char path[SYSFS_PATH_MAX]; - char linebuf[2] = {}; - - snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); - - if (!is_valid_path(path)) - return -1; - - snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost); - - if (cpupower_write_sysfs(path, linebuf, 2) <= 0) - return -1; - - return 0; -} - bool cpupower_amd_pstate_enabled(void) { char *driver = cpufreq_get_driver(0); @@ -160,6 +141,39 @@ bool cpupower_amd_pstate_enabled(void) #endif /* #if defined(__i386__) || defined(__x86_64__) */ +int cpufreq_has_generic_boost_support(bool *active) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + unsigned long val; + char *endp; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); + + if (!is_valid_path(path)) + return -EACCES; + + if (cpupower_read_sysfs(path, linebuf, 2) <= 0) + return -EINVAL; + + val = strtoul(linebuf, &endp, 0); + if (endp == linebuf || errno == ERANGE) + return -EINVAL; + + switch (val) { + case 0: + *active = false; + break; + case 1: + *active = true; + break; + default: + return -EINVAL; + } + + return 0; +} + /* get_cpustate * * Gather the information of all online CPUs into bitmask struct @@ -259,3 +273,21 @@ void print_speed(unsigned long speed, int no_rounding) } } } + +int cpupower_set_turbo_boost(int turbo_boost) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); + + if (!is_valid_path(path)) + return -1; + + snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost); + + if (cpupower_write_sysfs(path, linebuf, 2) <= 0) + return -1; + + return 0; +} diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 5a5a7a5f7e1d..a4ac80bb1003 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -446,9 +446,6 @@ TEST_F(coredump, socket_detect_userspace_client) if (info.coredump_mask & PIDFD_COREDUMPED) goto out; - if (read(fd_coredump, &c, 1) < 1) - goto out; - exit_code = EXIT_SUCCESS; out: if (fd_peer_pidfd >= 0) diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 5b230deb19e8..9a3499827d4b 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -4,6 +4,7 @@ TEST_GEN_FILES += access_memory access_memory_even TEST_FILES = _damon_sysfs.py +TEST_FILES += drgn_dump_damon_status.py # functionality tests TEST_PROGS += sysfs.sh diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 2b10854e4b1e..44b98f17f8ff 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,8 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan_ipvlan.sh + bond_macvlan_ipvlan.sh \ + bond_passive_lacp.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh new file mode 100755 index 000000000000..9c3b089813df --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test if a bond interface works with lacp_active=off. + +# shellcheck disable=SC2034 +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +# shellcheck disable=SC1091 +source "$lib_dir"/../../../net/forwarding/lib.sh + +# shellcheck disable=SC2317 +check_port_state() +{ + local netns=$1 + local port=$2 + local state=$3 + + ip -n "${netns}" -d -j link show "$port" | \ + jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null +} + +check_pkt_count() +{ + RET=0 + local ns="$1" + local iface="$2" + + # wait 65s, one per 30s + slowwait_for_counter 65 2 tc_rule_handle_stats_get \ + "dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null +} + +setup() { + setup_ns c_ns s_ns + + # shellcheck disable=SC2154 + ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}" + ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}" + + # Add tc filter to count the pkts + tc -n "${c_ns}" qdisc add dev eth0 clsact + tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass + tc -n "${s_ns}" qdisc add dev eth1 clsact + tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass + + ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast + ip -n "${s_ns}" link set eth0 master bond0 + ip -n "${s_ns}" link set eth1 master bond0 + + ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast + ip -n "${c_ns}" link set eth0 master bond0 + ip -n "${c_ns}" link set eth1 master bond0 + +} + +trap cleanup_all_ns EXIT +setup + +# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s +# after interface up +ip -n "${c_ns}" link set bond0 up +sleep 2 + +# 1. The passive side shouldn't send LACPDU. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "802.3ad lacp_active off" "init port" + +ip -n "${s_ns}" link set bond0 up +# 2. The passive side should not have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1 +log_test "802.3ad lacp_active off" "port state active" + +# 3. The active side should have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1 +log_test "802.3ad lacp_active on" "port state active" + +# 4. Make sure the connection is not expired. +RET=0 +slowwait 5 check_port_state "${s_ns}" "eth0" "distributing" +slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1 +log_test "bond 802.3ad lacp_active off" "port connection" + +# After testing, disconnect one port on each side to check the state. +ip -n "${s_ns}" link set eth0 nomaster +ip -n "${s_ns}" link set eth0 up +ip -n "${c_ns}" link set eth1 nomaster +ip -n "${c_ns}" link set eth1 up +# Due to Periodic Machine and Rx Machine state change, the bond will still +# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure +# negotiation finished +sleep 5 + +# 5. The active side should keep sending LACPDU. +check_pkt_count "${s_ns}" "eth1" || RET=1 +log_test "bond 802.3ad lacp_active on" "port pkt after disconnect" + +# 6. The passive side shouldn't send LACPDU anymore. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "bond 802.3ad lacp_active off" "port pkt after disconnect" + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index dad4e5fda4db..4d16a69ffc65 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -6,6 +6,7 @@ CONFIG_MACVLAN=y CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py index b2698db39817..9699a100a87d 100755 --- a/tools/testing/selftests/drivers/net/napi_threaded.py +++ b/tools/testing/selftests/drivers/net/napi_threaded.py @@ -35,6 +35,8 @@ def _setup_deferred_cleanup(cfg) -> None: threaded = cmd(f"cat /sys/class/net/{cfg.ifname}/threaded").stdout defer(_set_threaded_state, cfg, threaded) + return combined + def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: """ @@ -49,7 +51,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -62,7 +64,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: nl.napi_set({'id': napi1_id, 'threaded': 'disabled'}) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") _assert_napi_threaded_enabled(nl, napi0_id) _assert_napi_threaded_disabled(nl, napi1_id) @@ -80,7 +82,7 @@ def change_num_queues(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -90,7 +92,7 @@ def change_num_queues(cfg, nl) -> None: _assert_napi_threaded_enabled(nl, napi1_id) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") # check napi threaded is set for both napis _assert_napi_threaded_enabled(nl, napi0_id) diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 81db85a5cc16..39a68078a79b 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -65,6 +65,7 @@ static int __do_binderfs_test(struct __test_metadata *_metadata) "oneway_spam_detection", "extended_error", "freeze_notification", + "transaction_report", }; change_mountns(_metadata); diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index fccf9e797a0c..5bd52a951cbd 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -5,10 +5,14 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> +#include <linux/userfaultfd.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> +#include <syscall.h> #include <time.h> #include <stdbool.h> @@ -168,6 +172,7 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start, if (first_val <= start && second_val >= end) { success = true; + fflush(maps_fp); break; } } @@ -175,6 +180,15 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start, return success; } +/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */ +static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size) +{ + unsigned long start = (unsigned long)ptr; + unsigned long end = start + size; + + return is_range_mapped(maps_fp, start, end); +} + /* * Returns the start address of the mapping on success, else returns * NULL on failure. @@ -733,6 +747,249 @@ out: dont_unmap ? " [dontunnmap]" : ""); } +#ifdef __NR_userfaultfd +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, + unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + const size_t size = 10 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + int uffd, err, i; + void *res; + struct uffdio_api api = { + .api = UFFD_API, + .features = UFFD_EVENT_PAGEFAULT, + }; + + uffd = syscall(__NR_userfaultfd, O_NONBLOCK); + if (uffd == -1) { + err = errno; + perror("userfaultfd"); + if (err == EPERM) { + ksft_test_result_skip("%s - missing uffd", test_name); + return; + } + success = false; + goto out; + } + if (ioctl(uffd, UFFDIO_API, &api)) { + perror("ioctl UFFDIO_API"); + success = false; + goto out_close_uffd; + } + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + + tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + if (munmap(tgt_ptr, size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* + * Unmap so we end up with: + * + * 0 2 4 6 8 10 offset in buffer + * |*| |*| |*| |*| |*| + * |*| |*| |*| |*| |*| + * + * Additionally, register each with UFFD. + */ + for (i = 0; i < 10; i += 2) { + void *unmap_ptr = &ptr[(i + 1) * page_size]; + unsigned long start = (unsigned long)&ptr[i * page_size]; + struct uffdio_register reg = { + .range = { + .start = start, + .len = page_size, + }, + .mode = UFFDIO_REGISTER_MODE_MISSING, + }; + + if (ioctl(uffd, UFFDIO_REGISTER, ®) == -1) { + perror("ioctl UFFDIO_REGISTER"); + success = false; + goto out_unmap; + } + if (munmap(unmap_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range which is invalid for multi VMA move. + * + * This will fail, and no VMA should be moved, as we check this ahead of + * time. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, + "Invalid uffd-armed VMA at start of multi range moved\n"); + success = false; + goto out_unmap; + } + + /* + * Now try to move a single VMA, this should succeed as not multi VMA + * move. + */ + res = mremap(ptr, page_size, page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + if (res == MAP_FAILED) { + perror("mremap single invalid-multi VMA"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA + * move valid) VMA at the start of ptr range. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + res = mmap(ptr, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + + /* + * Now try to move the entire range, we should succeed in moving the + * first VMA, but no others, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, "Valid VMA not moved\n"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and map valid VMA at start of ptr range, and replace + * all existing multi-move invalid VMAs, except the last, with valid + * multi-move VMAs. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + if (munmap(ptr, size - 2 * page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + for (i = 0; i < 8; i += 2) { + res = mmap(&ptr[i * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range, we should succeed in moving all but + * the last VMA, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + + for (i = 0; i < 10; i += 2) { + bool is_mapped = is_ptr_mapped(maps_fp, + &tgt_ptr[i * page_size], page_size); + + if (i < 8 && !is_mapped) { + fprintf(stderr, "Valid VMA not moved at %d\n", i); + success = false; + goto out_unmap; + } else if (i == 8 && is_mapped) { + fprintf(stderr, "Invalid VMA moved at %d\n", i); + success = false; + goto out_unmap; + } + } + +out_unmap: + if (munmap(tgt_ptr, size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); +out_close_uffd: + close(uffd); +out: + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} +#else +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + + ksft_test_result_skip("%s - missing uffd", test_name); +} +#endif /* __NR_userfaultfd */ + /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, char *rand_addr) @@ -1074,7 +1331,7 @@ int main(int argc, char **argv) char *rand_addr; size_t rand_size; int num_expand_tests = 2; - int num_misc_tests = 8; + int num_misc_tests = 9; struct test test_cases[MAX_TEST] = {}; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; @@ -1197,8 +1454,6 @@ int main(int argc, char **argv) mremap_expand_merge(maps_fp, page_size); mremap_expand_merge_offset(maps_fp, page_size); - fclose(maps_fp); - mremap_move_within_range(pattern_seed, rand_addr); mremap_move_1mb_from_start(pattern_seed, rand_addr); mremap_shrink_multiple_vmas(page_size, /* inplace= */true); @@ -1207,6 +1462,9 @@ int main(int argc, char **argv) mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true); mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false); mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true); + mremap_move_multi_invalid_vmas(maps_fp, page_size); + + fclose(maps_fp); if (run_perf_tests) { ksft_print_msg("\n%s\n", diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index b1e4618399be..a688871a98eb 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -107,6 +107,26 @@ #endif #endif +#ifndef __NR_open_tree_attr + #if defined __alpha__ + #define __NR_open_tree_attr 577 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_open_tree_attr (467 + 4000) + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_open_tree_attr (467 + 6000) + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_open_tree_attr (467 + 5000) + #endif + #elif defined __ia64__ + #define __NR_open_tree_attr (467 + 1024) + #else + #define __NR_open_tree_attr 467 + #endif +#endif + #ifndef MOUNT_ATTR_IDMAP #define MOUNT_ATTR_IDMAP 0x00100000 #endif @@ -121,6 +141,12 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag return syscall(__NR_mount_setattr, dfd, path, flags, attr, size); } +static inline int sys_open_tree_attr(int dfd, const char *path, unsigned int flags, + struct mount_attr *attr, size_t size) +{ + return syscall(__NR_open_tree_attr, dfd, path, flags, attr, size); +} + static ssize_t write_nointr(int fd, const void *buf, size_t count) { ssize_t ret; @@ -1222,6 +1248,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace) attr.userns_fd = get_userns_fd(0, 10000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1255,6 +1287,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace) ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1321,6 +1359,19 @@ TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace) ASSERT_EQ(close(open_tree_fd), 0); } +static bool expected_uid_gid(int dfd, const char *path, int flags, + uid_t expected_uid, gid_t expected_gid) +{ + int ret; + struct stat st; + + ret = fstatat(dfd, path, &st, flags); + if (ret < 0) + return false; + + return st.st_uid == expected_uid && st.st_gid == expected_gid; +} + /** * Validate that currently changing the idmapping of an idmapped mount fails. */ @@ -1331,6 +1382,8 @@ TEST_F(mount_setattr_idmapped, change_idmapping) .attr_set = MOUNT_ATTR_IDMAP, }; + ASSERT_TRUE(expected_uid_gid(-EBADF, "/mnt/D", 0, 0, 0)); + if (!mount_setattr_supported()) SKIP(return, "mount_setattr syscall not supported"); @@ -1348,27 +1401,25 @@ TEST_F(mount_setattr_idmapped, change_idmapping) AT_EMPTY_PATH, &attr, sizeof(attr)), 0); ASSERT_EQ(close(attr.userns_fd), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 0, 0)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + /* Change idmapping on a detached mount that is already idmapped. */ attr.userns_fd = get_userns_fd(0, 20000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + EXPECT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 20000, 20000)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } -static bool expected_uid_gid(int dfd, const char *path, int flags, - uid_t expected_uid, gid_t expected_gid) -{ - int ret; - struct stat st; - - ret = fstatat(dfd, path, &st, flags); - if (ret < 0) - return false; - - return st.st_uid == expected_uid && st.st_gid == expected_gid; -} - TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) { int open_tree_fd = -EBADF; diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index b98ea9449b8b..dfb6646cb97b 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -18,6 +18,8 @@ # | 2001:db8:1::1/64 2001:db8:2::1/64 | # | | # +-----------------------------------------------------------------+ +# +#shellcheck disable=SC2034 # SC doesn't see our uses of global variables ALL_TESTS=" ping_ipv4 @@ -27,6 +29,7 @@ ALL_TESTS=" ipv4_sip_equal_dip ipv6_sip_equal_dip ipv4_dip_link_local + ipv4_sip_link_local " NUM_NETIFS=4 @@ -330,6 +333,32 @@ ipv4_dip_link_local() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +ipv4_sip_link_local() +{ + local sip=169.254.1.1 + + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf."$rp1".rp_filter 0 + + tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \ + flower src_ip "$sip" action pass + + $MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \ + -A "$sip" -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 source IP is link-local" + + tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf."$rp1".rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh index 1f6f53e284b5..6269d5e23487 100755 --- a/tools/testing/selftests/net/forwarding/sch_ets.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -11,6 +11,7 @@ ALL_TESTS=" ets_test_strict ets_test_mixed ets_test_dwrr + ets_test_plug classifier_mode ets_test_strict ets_test_mixed diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh index 08240d3e3c87..79d837a2868a 100644 --- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -224,3 +224,11 @@ ets_test_dwrr() ets_set_dwrr_two_bands xfail_on_slow ets_dwrr_test_01 } + +ets_test_plug() +{ + ets_change_qdisc $put 2 "3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3" "1514 1514" + tc qdisc add dev $put handle 20: parent 10:4 plug + start_traffic_pktsize 100 $h1.10 192.0.2.1 192.0.2.2 00:c1:a0:c1:a0:00 "-c 1" + ets_qdisc_setup $put 2 +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index ac1349c4b9e5..4f07ac9fa207 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 3cf1e2a612ce..f3bcaa48df8f 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b8af65373b3a..82cae37d9c20 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3842,6 +3842,7 @@ endpoint_tests() # remove and re-add if reset_with_events "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0 pm_nl_set_limits $ns1 0 3 pm_nl_set_limits $ns2 3 3 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 9934a68df237..e934dd26a59d 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 2e6648a2b2c0..ac7ec6f94023 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -198,6 +198,7 @@ set_limits 1 9 2>/dev/null check "get_limits" "${default_limits}" "subflows above hard limit" set_limits 8 8 +flush_endpoint ## to make sure it doesn't affect the limits check "get_limits" "$(format_limits 8 8)" "set limits" flush_endpoint diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5ded3b3a7538..0f5640d8dc7f 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type, return sendmsg(fd, &msg, flags); } -static int tls_recv_cmsg(struct __test_metadata *_metadata, - int fd, unsigned char record_type, - void *data, size_t len, int flags) +static int __tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char *ctype, + void *data, size_t len, int flags) { char cbuf[CMSG_SPACE(sizeof(char))]; struct cmsghdr *cmsg; - unsigned char ctype; struct msghdr msg; struct iovec vec; int n; @@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata, EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - ctype = *((unsigned char *)CMSG_DATA(cmsg)); + if (ctype) + *ctype = *((unsigned char *)CMSG_DATA(cmsg)); + + return n; +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + unsigned char ctype; + int n; + + n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags); EXPECT_EQ(ctype, record_type); return n; @@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay) } } +struct raw_rec { + unsigned int plain_len; + unsigned char plain_data[100]; + unsigned int cipher_len; + unsigned char cipher_data[128]; +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */ +static const struct raw_rec id0_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33, + 0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf, + 0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd, + 0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */ +static const struct raw_rec id0_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b, + 0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae, + 0x88, 0xe1, 0xd2, 0x08, 0x4f, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */ +static const struct raw_rec id0_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90, + 0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03, + 0x68, 0x80, 0xd3, 0xd8, 0xcc, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */ +static const struct raw_rec id1_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c, + 0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3, + 0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff, + 0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */ +static const struct raw_rec id1_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe, + 0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6, + 0xb4, 0x7e, 0xef, 0x40, 0x2b, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */ +static const struct raw_rec id1_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86, + 0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc, + 0xc9, 0xbf, 0xfe, 0x5b, 0xb1, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_ctrl_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36, + 0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b, + 0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */ +static const struct raw_rec id2_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e, + 0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9, + 0x06, 0xdb, 0x79, 0xe5, 0x5d, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */ +static const struct raw_rec id2_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26, + 0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83, + 0x30, 0x48, 0x69, 0x1a, 0x47, + }, +}; + +FIXTURE(zero_len) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_VARIANT(zero_len) +{ + const struct raw_rec *recs[4]; + ssize_t recv_ret[4]; +}; + +FIXTURE_VARIANT_ADD(zero_len, data_data_data) +{ + .recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, }, + .recv_ret = { 33, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data) +{ + .recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, }, + .recv_ret = { 11, 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, }, + .recv_ret = { 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl) +{ + .recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0data_0data) +{ + .recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_SETUP(zero_len) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + if (self->notls) + return; + + /* Don't install keys on fd, we'll send raw records */ + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(zero_len) +{ + close(self->fd); + close(self->cfd); +} + +TEST_F(zero_len, test) +{ + const struct raw_rec *const *rec; + unsigned char buf[128]; + int rec_off; + int i; + + for (i = 0; i < 4 && variant->recs[i]; i++) + EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data, + variant->recs[i]->cipher_len, 0), + variant->recs[i]->cipher_len); + + rec = &variant->recs[0]; + rec_off = 0; + for (i = 0; i < 4; i++) { + int j, ret; + + ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1; + EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL, + buf, sizeof(buf), MSG_DONTWAIT), ret); + if (ret == -1) + EXPECT_EQ(errno, -variant->recv_ret[i]); + if (variant->recv_ret[i] == -EAGAIN) + break; + + for (j = 0; j < ret; j++) { + while (rec_off == (*rec)->plain_len) { + rec++; + rec_off = 0; + } + EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]); + rec_off++; + } + } +}; + FIXTURE(tls_err) { int fd, cfd; @@ -2708,6 +2998,67 @@ TEST(prequeue) { close(cfd); } +TEST(data_steal) { + struct tls_crypto_info_keys tls; + char buf[20000], buf2[20000]; + struct sockaddr_in addr; + int sfd, cfd, ret, fd; + int pid, status; + socklen_t len; + + len = sizeof(addr); + memrnd(buf, sizeof(buf)); + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls, 0); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0); + ASSERT_EQ(listen(sfd, 10), 0); + ASSERT_EQ(getsockname(sfd, &addr, &len), 0); + ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0); + ASSERT_GE(cfd = accept(sfd, &addr, &len), 0); + close(sfd); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0); + + /* Spawn a child and get it into the read wait path of the underlying + * TCP socket. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (!pid) { + EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL), + sizeof(buf) / 2); + exit(!__test_passed(_metadata)); + } + + usleep(10000); + ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0); + ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0); + + EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(wait(&status), pid); + EXPECT_EQ(status, 0); + EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1); + /* Don't check errno, the error will be different depending + * on what random bytes TLS interpreted as the record length. + */ + + close(fd); + close(cfd); +} + static void __attribute__((constructor)) fips_check(void) { int res; FILE *f; diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index 66773685a047..94bba4553130 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -202,11 +202,11 @@ static void print_first_lines(char *text, int nr) int offs = end - text; text[offs] = '\0'; - printf(text); + printf("%s", text); text[offs] = '\n'; printf("\n"); } else { - printf(text); + printf("%s", text); } } @@ -221,7 +221,7 @@ static void print_last_lines(char *text, int nr) nr--; start--; } - printf(start); + printf("%s", start); } static void print_boundaries(const char *title, FIXTURE_DATA(proc_maps_race) *self) diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 1c9ceb661c43..0cfbb111a2d0 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -6,7 +6,6 @@ #include <bpf/bpf.h> #include <sched.h> #include <scx/common.h> -#include <sched.h> #include <sys/wait.h> #include <unistd.h> diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 23a61e5b99d0..998e5a2f4579 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -186,6 +186,204 @@ ] }, { + "id": "34c0", + "name": "Test TBF with HHF Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "hhf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 hhf limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 hhf limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "fd68", + "name": "Test TBF with CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "514e", + "name": "Test TBF with PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "6c97", + "name": "Test TBF with FQ Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "5d0b", + "name": "Test TBF with FQ_CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "21c3", + "name": "Test TBF with FQ_PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { "id": "a4bb", "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue", "category": [ diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 95188065b2e9..6512dfbdbce3 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1400,7 +1400,7 @@ static int cmd_dev_get_features(void) if (!((1ULL << i) & features)) continue; - if (i < sizeof(feat_map) / sizeof(feat_map[0])) + if (i < ARRAY_SIZE(feat_map)) feat = feat_map[i]; else feat = "unknown"; @@ -1477,7 +1477,7 @@ static void __cmd_create_help(char *exe, bool recovery) printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n"); printf("\tdefault: nthreads=nr_queues"); - for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) { const struct ublk_tgt_ops *ops = tgt_ops_list[i]; if (ops->usage) diff --git a/tools/testing/shared/linux/idr.h b/tools/testing/shared/linux/idr.h index 4e342f2e37cf..676c5564e33f 100644 --- a/tools/testing/shared/linux/idr.h +++ b/tools/testing/shared/linux/idr.h @@ -1 +1,5 @@ +/* Avoid duplicate definitions due to system headers. */ +#ifdef __CONCAT +#undef __CONCAT +#endif #include "../../../../include/linux/idr.h" diff --git a/tools/tracing/latency/Makefile.config b/tools/tracing/latency/Makefile.config index 0fe6b50f029b..6efa13e3ca93 100644 --- a/tools/tracing/latency/Makefile.config +++ b/tools/tracing/latency/Makefile.config @@ -1,7 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-only +include $(srctree)/tools/scripts/utilities.mak + STOP_ERROR := +ifndef ($(NO_LIBTRACEEVENT),1) + ifeq ($(call get-executable,$(PKG_CONFIG)),) + $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it) + endif +endif + define lib_setup $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)")) $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)")) diff --git a/tools/tracing/rtla/Makefile.config b/tools/tracing/rtla/Makefile.config index 5f2231d8d626..07ff5e8f3006 100644 --- a/tools/tracing/rtla/Makefile.config +++ b/tools/tracing/rtla/Makefile.config @@ -1,10 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-only +include $(srctree)/tools/scripts/utilities.mak + STOP_ERROR := LIBTRACEEVENT_MIN_VERSION = 1.5 LIBTRACEFS_MIN_VERSION = 1.6 +ifndef ($(NO_LIBTRACEEVENT),1) + ifeq ($(call get-executable,$(PKG_CONFIG)),) + $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it) + endif +endif + define lib_setup $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)")) $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)")) |